bot: update RSS feed
This commit is contained in:
github-actions[bot]
260
feed.xml
260
feed.xml
@@ -7,243 +7,103 @@
|
|||||||
<docs>http://www.rssboard.org/rss-specification</docs>
|
<docs>http://www.rssboard.org/rss-specification</docs>
|
||||||
<generator>python-feedgen</generator>
|
<generator>python-feedgen</generator>
|
||||||
<language>en</language>
|
<language>en</language>
|
||||||
<lastBuildDate>Mon, 22 Jun 2026 00:24:34 +0000</lastBuildDate>
|
<lastBuildDate>Tue, 23 Jun 2026 00:23:46 +0000</lastBuildDate>
|
||||||
<item>
|
<item>
|
||||||
<title>Duration Aware Scheduling for ASR Serving Under Workload Drift</title>
|
<title>Distilling Examples into Task Instructions: Enhanced In-Context Learning for Real-World B2B Conversations</title>
|
||||||
<link>https://arxiv.org/abs/2603.11273</link>
|
<link>https://arxiv.org/abs/2606.15641</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.11273.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Darshan Makwana, Yash Jogi, Harsh Kotta, Aayush Kubba</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Scheduling policies in large-scale Automatic Speech Recognition (ASR) serving pipelines play a key role in determining end-to-end (E2E) latency. Yet, widely used serving engines rely on first-come-first-served (FCFS) scheduling, which ignores variability in request duration and leads to head-of-line blocking under workload drift. We show that audio duration is an accurate proxy for job processing time in ASR models such as Whisper, and use this insight to enable duration-aware scheduling. We integrate two classical algorithms, Shortest Job First (SJF) and Highest Response Ratio Next (HRRN), into vLLM and evaluate them under realistic and drifted workloads. On LibriSpeech test-clean, compared to baseline, SJF reduces median E2E latency by up to 73% at high load, but increases 90th-percentile tail latency by up to 97% due to starvation of long requests. HRRN addresses this trade-off: it reduces median E2E latency by up to 28% while bounding tail-latency degradation to at most 24%. These gains persist under workload drift, with no throughput penalty and <0.1\,ms scheduling overhead per request.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2606.15641.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Guy Rotman, Adi Kopilov, Danit Berger Zalmanson, Omri Allouche</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> In-context learning (ICL) is the standard method for low-resource classification, yet its efficacy in specialized domains remains largely unexplored. We address the challenge of classifying semantically complex, multi-party B2B conversations, where traditional ICL encounters significant limitations, especially as context length increases due to the concatenation of multiple few-shot examples. We introduce the Call Playbook dataset, featuring five classification tasks derived from real-world B2B conversations targeting core sales concepts. To bridge the gap between performance and practical utility, we propose novel knowledge extraction methods that distill verbose examples into compact, interpretable representations of structured classification criteria and precise task descriptions. Our approach achieves a 99\% reduction in token usage and improves macro-averaged AUC by up to 7\% over traditional ICL. Notably, it remains robust as context grows, unlike advanced token compression baselines which degrade by over 9 F1 points. Importantly, our framework enables direct refinement of classification logic, addressing critical needs for transparency, efficiency, and user interaction in real-world NLP applications.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.11273</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2606.15641</guid>
|
||||||
<pubDate>Wed, 11 Mar 2026 00:00:00 +0000</pubDate>
|
|
||||||
</item>
|
|
||||||
<item>
|
|
||||||
<title>ReSyn: A Generalized Recursive Regular Expression Synthesis Framework</title>
|
|
||||||
<link>https://arxiv.org/abs/2603.24624</link>
|
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.24624.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Seongmin Kim, Hyunjoon Cheon, Su-Hyeon Kim, Yo-Sub Han, Sang-Ki Ko</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Existing Programming-By-Example (PBE) systems often rely on simplified benchmarks that fail to capture the high structural complexity of real-world regexes, such as deeper nesting and frequent use of union operations. To overcome the resulting performance drop, we propose ReSyn, a synthesizer-agnostic divide-and-conquer framework that decomposes complex synthesis problem into manageable sub-problems. We also introduce Set2Regex, a parameter-efficient synthesizer capturing the permutation invariance of examples. Experimental results demonstrate that ReSyn significantly boosts accuracy across various synthesizers, and its combination with Set2Regex establishes a new state-of-the-art on challenging real-world benchmark. The complete source code, datasets, and pre-trained model checkpoints are publicly available at https://github.com/mrseongminkim/ReSyn.</p></description>
|
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.24624</guid>
|
|
||||||
<pubDate>Sat, 13 Jun 2026 00:00:00 +0000</pubDate>
|
|
||||||
</item>
|
|
||||||
<item>
|
|
||||||
<title>DragMesh-2: Physically Plausible Dexterous Hand-Object Interaction with Articulated Objects</title>
|
|
||||||
<link>https://arxiv.org/abs/2606.15133</link>
|
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2606.15133.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Tianshan Zhang, Yijia Duan, Yanjun Li, Zeyu Zhang, Hao Tang</p><p><b>Upvotes:</b> 69</p><p><b>Summary:</b> Dexterous interaction with articulated objects is important for household, assistive, and humanoid manipulation, where multi-finger hands can provide compliant contact patterns beyond parallel-jaw grasping. However, articulated-object manipulation differs from static-object manipulation: the target part cannot be directly actuated, and its motion must emerge through sustained physical hand--handle contact. This makes the transition from object-centric articulated generation to hand-driven dexterous hand--object interaction non-trivial, since geometric trajectory replay or open-loop execution does not model the contact dynamics required to move the articulated part. Moreover, policies trained only for task completion under fixed dynamics can overfit nominal contact loads, especially without tactile or force feedback, and may degrade when the contact load changes. To address these challenges, we present DragMesh-2, a contact-driven framework for dexterous interaction with articulated objects that extends articulated interaction from object-centric generation to hand-driven dexterous hand--object interaction, where articulated motion must arise through physical contact. We further propose PICA, a physically informed contact-aware training mechanism that injects physical signals into policy learning without tactile or force feedback, improving robustness and task success under changing contact loads. Finally, we conduct systematic evaluation across multiple damping conditions and articulated-object categories to study robustness under contact-load variation, and provide a pure-geometry dexterous interaction resource to support future loco-manipulation and humanoid hand--object interaction research. Across seven GAPartNet objects, DragMesh-2 achieves stronger robustness under contact-load variation than the compared methods while maintaining high task success across damping conditions.</p></description>
|
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2606.15133</guid>
|
|
||||||
<pubDate>Sat, 13 Jun 2026 00:00:00 +0000</pubDate>
|
|
||||||
</item>
|
|
||||||
<item>
|
|
||||||
<title>Selective Synergistic Learning for Video Object-Centric Learning</title>
|
|
||||||
<link>https://arxiv.org/abs/2606.15527</link>
|
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2606.15527.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> WonJun Moon, Jae-Pil Heo</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Typical video object-centric learning (VOCL) approaches employ slot-based frameworks that rely on reconstruction-driven encoder-decoder architectures, where learning is mediated by two spatial maps: attention maps from the encoder and object maps from the decoder. As these two distinct maps exhibit different properties, a recent dense alignment strategy attempted to reconcile this discrepancy by enforcing agreement across all spatio-temporal patches via contrastive learning. However, this indiscriminate alignment inadvertently propagates the inherent weaknesses of each module, such as noisy encoder predictions and blurred decoder boundaries. Moreover, computing dense similarities across all pairs incurs a computational cost quadratic in the total number of spatio-temporal patches, severely limiting scalability. Motivated by this, we propose Selective Synergistic Learning (SSync). Instead of exhaustive patch-to-patch alignment, SSync prevents error propagation by selectively distilling only the most reliable cues: leveraging the encoder strictly for boundary refinement and the decoder for interior denoising. This is realized via a pseudo-labeling with linear complexity, eliminating the need for quadratic spatial comparisons. Also, to prevent the reinforcement of architectural biases like slot redundancy, we introduce a transitive pseudo-label merging that consolidates overlapping slots based on spatio-temporal activation consistency. Extensive studies demonstrate that SSync improves decomposition quality and serves as a versatile, plug-and-play module while also exhibiting exceptional robustness to slot configurations. Code is available at github.com/wjun0830/SSync.</p></description>
|
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2606.15527</guid>
|
|
||||||
<pubDate>Sun, 14 Jun 2026 00:00:00 +0000</pubDate>
|
<pubDate>Sun, 14 Jun 2026 00:00:00 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>The Data Manifold under the Microscope</title>
|
<title>SpatialAvatar-0: High-Quality 4D Head Avatar with Multi-Stage Reconstruction</title>
|
||||||
<link>https://arxiv.org/abs/2606.15760</link>
|
<link>https://arxiv.org/abs/2606.15659</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2606.15760.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Marios Koulakis, Constantin Seibold</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> A significant gap exists between theory and practice in deep learning. Generalization and approximation error bounds are often derived for simplified models or are too loose to be informative. Many rely on the manifold hypothesis and on geometric regularity such as intrinsic dimension, curvature, and reach. Progress requires insight into data-manifold geometry and suitable benchmarks, yet existing options are polarized: analytic manifolds with known geometry but limited applicability, or real-world datasets where geometry is only coarsely estimable. We introduce a benchmarking framework for studying data geometry. We repurpose and extend dSprites and COIL-20 with additional transformation dimensions and dense, axis-aligned sampling, and pair them with finite-difference estimators that recover curvature, reach, and volume at near-ground-truth accuracy in a regime where general-purpose estimators are unreliable or difficult to deploy. The framework is intended as a controlled testbed, useful as a calibration environment for geometric estimators and a sandbox for probing theoretical assumptions. To illustrate its use, we present two application studies, namely assessing the scaling behavior of the bounds of Genovese et al. and Fefferman et al., and tracking the layer-wise geometry of a β-VAE, highlighting the behavior of current bounds and the value of controlled benchmarks for guiding and validating future theory. A reference implementation is available at https://github.com/koulakis/manifold-microscope.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2606.15659.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yiran Wang, Zeyu Zhang, Yuanming Li, Ziming Wang, Yang Zhao</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> High-quality 4D head avatars from one or a few source portraits are central to telepresence, AR/VR, and digital-human interaction. 3D Gaussian Splatting (3DGS) has emerged as the dominant representation, with two complementary regimes (generalizable feed-forward predictors and per-subject refiners) maturing in parallel. However, existing feed-forward predictors are trained on a single dataset family with a hard-coded source count, inheriting the corresponding domain bias. Per-subject refiners require 300K--600K iterations and rely on adaptive densification that destroys upstream Gaussian layouts, preventing the two regimes from sharing a representation end-to-end. To bridge both regimes we propose SpatialAvatar-0 on a shared FLAME-mesh-bound Gaussian representation: a feed-forward generator with a parameter-free K-source mean-pool and a monocular-temporal to multi-view-spatial two-phase schedule that anchors against identity-prior collapse onto the smaller multi-view set. We further introduce a 10K-iter layout-preserving per-subject refinement loop that freezes the FLAME-binding and Gaussian count and replaces densification with a three-component anti-spike regularization. On VFHQ/HDTF cross-domain zero-shot we surpass the in-domain leader GAGAvatar by +1.5 dB PSNR despite never training on either test domain, and on the SplattingAvatar monocular benchmark we lead every reported metric, surpassing the 300K-iter GeoAvatar by +1.3 dB PSNR at up to 60x shorter per-subject schedule than common SOTA baselines. Website: https://spatialwalk.github.io/SpatialAvatar-0.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2606.15760</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2606.15659</guid>
|
||||||
<pubDate>Sun, 14 Jun 2026 00:00:00 +0000</pubDate>
|
<pubDate>Sun, 14 Jun 2026 00:00:00 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>No Resource, No Benchmarks, No Problem? Evaluating and Improving LLMs for Code Generation in No-Resource Languages</title>
|
<title>Multi-Turn Reflective Masking Elicits Reasoning in Mask Diffusion Models</title>
|
||||||
<link>https://arxiv.org/abs/2606.16827</link>
|
<link>https://arxiv.org/abs/2606.16700</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2606.16827.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Alessandro Giagnorio, Alberto Martin-Lopez, Gabriele Bavota</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Large Language Models (LLMs) have significantly advanced the automation of software engineering tasks. One prominent example is code generation, where an LLM produces code in a specified programming language based on a natural language description. Most research in this area has focused on high-resource languages, such as Python or Java, which benefit from abundant training data. A smaller body of work has explored low-resource languages, which are underrepresented in training corpora. In contrast, no-resource languages for which LLMs have seen virtually no training data remain largely unstudied. These languages often emerge in industry, where organizations develop proprietary or domain-specific languages unsupported by commercial tools like GitHub Copilot. This results in the need for companies to deploy their own in-house code recommenders. To investigate possible solutions in this context, we build and release three code generation benchmarks for no-resource languages, based on two recently proposed programming languages for which very little training data is available. Using these benchmarks, we experiment several solutions to teach LLMs about no-resource languages, including prompt-based techniques as well as pre-training and fine-tuning exploiting the little data available. While further pre-training gives the largest performance gains for no-resource languages, applying it directly to instruction-tuned models harms their ability to follow instructions. To address this, we start from a base model, further pre-training it on the target language, and then inject instruction-following capabilities via weight diff transfer from an instruction model. Such an approach significantly improves code generation capabilities in no-resource settings, allowing companies to cheaply deploy a specialized instruct model without dealing with the computational cost of instruction fine-tuning.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2606.16700.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yanming Zhang, Yihan Bian, Jingyuan Qi, Yuguang Yao, Lifu Huang, Tianyi Zhou</p><p><b>Upvotes:</b> 9</p><p><b>Summary:</b> While reasoning on autoregressive (AR) models is often performed by chain-of-thought reasoning and reflection, their refinement of previous outputs still relies on fully sequential generation, even when only local edits are needed. In contrast, the masking mechanism in Mask Diffusion Models (MDMs) naturally supports explicit local edits on previous outputs, allowing selective refinement without discarding previous answers and generating another from scratch. While this property more closely aligns with how humans correct mistakes by iterative local refinement, existing MDMs do not support multi-turn masking and denoising. We propose Reflective Masking (RM), which elicits such an intrinsic reasoning capability in MDMs via lightweight post-training. RM provides a native test-time scaling, where an MDM iteratively revisits and revises its prior outputs based on evolving context. To exploit insights from previous turns like AR reasoning, we further introduce History Reference, a parameter-free mechanism that leverages intermediate denoising states during revision. Our approach requires no architectural changes and is easily applicable to existing MDMs. Across diverse tasks and modalities, including text generation, Sudoku, and image editing, Reflective Masking consistently outperforms standard masking-based baselines and demonstrates strong generality, positioning RM as a fundamental primitive for reasoning on MDMs.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2606.16827</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2606.16700</guid>
|
||||||
<pubDate>Mon, 15 Jun 2026 00:00:00 +0000</pubDate>
|
<pubDate>Mon, 15 Jun 2026 00:00:00 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Taylor-Calibrate: Principled Initialization for Hybrid Linear Attention Distillation</title>
|
<title>MemSlides: A Hierarchical Memory Driven Agent Framework for Personalized Slide Generation with Multi-turn Local Revision</title>
|
||||||
<link>https://arxiv.org/abs/2606.16429</link>
|
<link>https://arxiv.org/abs/2606.17162</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2606.16429.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhongzhu Zhou, Qingyang Wu, Junxiong Wang, Mayank Mishra, Shuaiwen Leon Song, Ben Athiwaratkun, Chenfeng Xu</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> Hybrid linear attention models offer an appealing path to faster long-context inference: they reduce the quadratic cost and KV-cache burden of full softmax attention while retaining much of the quality of Transformer models. A practical way to obtain such models is to convert a pretrained Transformer instead of pretraining a new architecture from scratch, but this conversion is still brittle. Simply copying the teacher attention projections into a Gated DeltaNet (GDN) student does not specify the new recurrent decay, write, and output-gating dynamics. As a result, the converted model often starts in a poor dynamical regime and must spend many distillation tokens repairing initialization rather than learning the remaining teacher behavior. We propose Taylor-Calibrate, a lightweight initialization method for hybrid GDN students. The method uses Taylor-guided teacher attention statistics to set the value projection, memory timescale, write gates, and output gate, then applies a short per-layer alignment step to match each converted layer to the teacher output. Across four teacher settings and three retained-layer policies, Taylor-Calibrate gives substantially stronger zero-shot students, with up to an 88x improvement in a representative ablation, and reaches matched recovery targets with 4.9x--9.2x fewer training tokens than naive conversion.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2606.17162.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ye Jin, Yangyang Xu, Jun Zhu, Yibo Yang</p><p><b>Upvotes:</b> 14</p><p><b>Summary:</b> Personalized presentation generation requires more than conditioning on a current prompt or template: agents must preserve stable user preferences across tasks, retain newly introduced preferences and constraints during multi-turn revision, and carry out local edits reliably. We propose MemSlides, a hierarchical memory framework for personalized presentation agents that separates long-term memory from working memory and further divides long-term memory into user profile memory and tool memory. User profile memory stores intent-conditioned profiles for round-0 personalization, working memory carries active preferences and session constraints across revision rounds, and tool memory stores reusable execution experience for reliable localized editing. MemSlides pairs this memory design with scoped slide-local revision, so targeted updates act on the smallest affected region instead of repeatedly regenerating the full deck. In controlled experiments, user profile memory improves persona-alignment judgments on a multi-persona, multi-intent profile bank, tool-memory injection improves closed-loop modify behavior in diagnostic matched-pair settings, and qualitative cases illustrate working memory's ability to carryover preferences. Taken together, these results suggest that effective personalization in presentation authoring depends on separating persistent user profiles, session-level working memory, and reusable execution experience across generation and localized revision.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2606.16429</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2606.17162</guid>
|
||||||
<pubDate>Mon, 15 Jun 2026 00:00:00 +0000</pubDate>
|
<pubDate>Mon, 15 Jun 2026 00:00:00 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Understanding the Behaviors of Environment-aware Information Retrieval</title>
|
<title>GeneralVLA-2: Geometry-Aware Reconstruction and Governed Memory for Robot Planning</title>
|
||||||
<link>https://arxiv.org/abs/2606.16817</link>
|
<link>https://arxiv.org/abs/2606.17480</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2606.16817.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ruifeng Yuan, Chaohao Yuan, David Dai, Yu Rong, Hong Cheng, Hou Pong Chan, Chenghao Xiao</p><p><b>Upvotes:</b> 6</p><p><b>Summary:</b> Recent retrieval-augmented generation (RAG) approaches have demonstrated strong capability in handling complex queries, yet current research overlooks a critical challenge: different retrievers require fundamentally different query formulation strategies for optimal performance. In this work, we present the first systematic analysis of how LLMs can learn to adapt their query formulation strategies for different retrievers via reinforcement learning (RL). Our empirical study reveals that RL effectively teaches an LLM to tailor its queries to specific retriever characteristics. We discover that different retrievers exhibit surprisingly distinct optimal query styles (e.g., descriptive vs. question-like), suggesting strategies learned for one retriever ineffective for another. We further show that performance can be enhanced by incorporating retriever-specific human guidance and by scaling model size. To facilitate learning over multi-retrieval-step trajectories, we introduce a branching-based rollout technique that improves training stability. Our work provides the first empirical evidence and actionable insights for building truly retriever-aware RAG systems. Code and resources are available at https://github.com/LCO-Embedding/Envs-aware-Information-Retrieval.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2606.17480.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Haoyu Wang, Guoqing Ma, Zeyu Zhang, Yandong Guo, Boxin Shi, Hao Tang</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Generalist vision-language-action systems need object-centric 3D evidence and reusable manipulation experience to plan reliable robot trajectories. GeneralVLA provides a hierarchical interface for converting language and RGB-D observations into 3D end-effector paths, but two bottlenecks remain. First, monocular SAM3D-style object reconstruction can hallucinate pose and unseen geometry, while manipulation benefits from stable object shape when calibrated multi-view observations are available. Second, the original KnowledgeBank mainly retrieves semantically similar snippets and appends new knowledge, which makes it difficult to control memory quality, conflicts, confidence, and geometric relevance. To address the first challenge, we introduce GeoFuse-MV3D, a geometry-prior-guided MV-SAM3D reconstruction branch that verifies external geometry cues with input-view masks, applies soft visual-hull support, performs axis-wise refinement, and fuses only geometry while preserving appearance. To address the second challenge, we upgrade KnowledgeBank into a governed long-term memory system with explicit quality, confidence, lifecycle, verifier, and conflict metadata, together with precision-oriented retrieval. Finally, we evaluate the reconstruction branch on GSO-30 and the memory module on Terminal-Bench 2.0 and SWE-Bench Verified; GeoFuse-MV3D improves over the MV-SAM3D baseline by reducing CD and LPIPS by 2.20% and 2.02% while increasing PSNR and SSIM by 2.36% and 1.03%, and KnowledgeBank improves over ReasoningBank by 4.53% on Terminal-Bench SR and 3.73% on SWE-Bench resolve rate, while reducing AS by 4.95% and 5.65%, respectively. Code: https://github.com/AIGeeksGroup/GeneralVLA-2. Website: https://aigeeksgroup.github.io/GeneralVLA-2.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2606.16817</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2606.17480</guid>
|
||||||
<pubDate>Mon, 15 Jun 2026 00:00:00 +0000</pubDate>
|
|
||||||
</item>
|
|
||||||
<item>
|
|
||||||
<title>Thinking with Visual Grounding</title>
|
|
||||||
<link>https://arxiv.org/abs/2606.16122</link>
|
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2606.16122.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Junkai Zhang, Yihe Deng, Kai-Wei Chang, Wei Wang</p><p><b>Upvotes:</b> 10</p><p><b>Summary:</b> Visual thinking should not only sound right; it should show its evidence. While recent vision-language models (VLMs) can produce natural-language reasoning traces, these traces often leave the supporting image regions implicit, making them hard to verify and difficult to supervise. We introduce visually grounded thinking, a reasoning process in which models interleave natural-language thoughts with explicit point or box groundings of the visual evidence used at each step. This lets the model express intermediate reasoning in language while grounding key objects in the image regions they refer to. To train this behavior, we construct a scalable synthesis pipeline that distills correct visual reasoning traces, extracts the visual objects required by the traces, grounds them with a SAM3-based agent, and derives aligned point and box supervision from the resulting masks. We further propose grounding-aware reinforcement learning, which combines answer correctness rewards with dense grounding rewards that score whether generated object references match the correct image evidence. Across two counting benchmarks and four spatial reasoning benchmarks, adding visually grounded thinking to Gemma3-4B-IT consistently improves performance over the original model and the non-grounded thinking baseline. On spatial reasoning, the visually grounded thinking 4B models match, and in some cases surpass, Gemma3-27B-IT from the same model family. Our analysis shows that point grounding is well suited to counting, while box grounding benefits most from explicit grounding rewards on spatial tasks. Overall, our results show that VLMs think better when their intermediate thoughts are tied to the image regions that make them true.</p></description>
|
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2606.16122</guid>
|
|
||||||
<pubDate>Mon, 15 Jun 2026 00:00:00 +0000</pubDate>
|
|
||||||
</item>
|
|
||||||
<item>
|
|
||||||
<title>Context-Aware RL for Agentic and Multimodal LLMs</title>
|
|
||||||
<link>https://arxiv.org/abs/2606.17053</link>
|
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2606.17053.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Peiyang Xu, Bangzheng Li, Sijia Liu, Karthik R. Narasimhan, Pramod Viswanath, Prateek Mittal, Xingyu Fu</p><p><b>Upvotes:</b> 10</p><p><b>Summary:</b> Large language models (LLMs) often fail when answering requires identifying a small but decisive piece of evidence within a long or complex context, such as a single line in a tool trace or a subtle detail in an image. We propose ContextRL, a context-aware reinforcement learning (RL) method that improves long-horizon reasoning and multimodal performance through an indirect auxiliary objective. Instead of supervising only the final answer, ContextRL presents the model with a query, an answer, and two highly similar contexts, and rewards it for selecting the context that supports the query--answer pair, thereby encouraging fine-grained grounding. We construct contrastive context data in two domains: for coding agents, trajectories serve as contexts, yielding 1k pairs built via condition filtering; for multimodal reasoning, images serve as contexts, yielding 7K pairs built via generative editing and similarity search. ContextRL achieves average gains of +2.2% over standard GRPO on 5 long-horizon benchmarks, and +1.8% across 12 diverse visual question answering benchmarks. To disentangle the effect of the proposed objective from that of additional data, we compare against data-augmentation baselines that repurpose the same contrastive contexts as standard query--context--answer examples. These baselines provide little to no improvement, showing that the gains arise from the proposed context-selection objective rather than from the contrastive data alone.</p></description>
|
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2606.17053</guid>
|
|
||||||
<pubDate>Mon, 15 Jun 2026 00:00:00 +0000</pubDate>
|
|
||||||
</item>
|
|
||||||
<item>
|
|
||||||
<title>LegalHalluLens: Typed Hallucination Auditing and Calibrated Multi-Agent Debate for Trustworthy Legal AI</title>
|
|
||||||
<link>https://arxiv.org/abs/2606.18021</link>
|
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2606.18021.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Lalit Yadav, Akshaj Gurugubelli</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> AI systems deployed in legal workflows hallucinate at rates that aggregate metrics report at ~52%, but this average conceals where errors concentrate and in which direction they run, leaving compliance officers without an actionable signal for trustworthy deployment. We present LegalHalluLens, an auditing framework with three components: typed hallucination profiles across four legally-motivated claim categories (numeric, temporal, obligation/entitlement, factual) over CUAD (Hendrycks et al., 2021); a Risk Direction Index (RDI) that reduces omission-versus-invention bias to a single deployment-comparable scalar; and a typed debate pipeline calibrated to both magnitudes and directions. Across 510 contracts and 249,252 clause-level instances we measure a within-model gap of approximately 38-40 pp between obligation/numeric and temporal claims that aggregate reporting hides, and show that two systems with matched 52% rates can carry opposite RDIs. The debate pipeline reduces fabricated detections by 45% with per-category gains tracking the diagnosis, matching commercial APIs with a substantially smaller backbone (4B active parameters). Typed profiles and RDI surface failure modes that aggregate metrics hide; we further show these diagnostics serve as calibration inputs for multi-agent debate pipelines, where Skeptic challenges and asymmetric gates targeted at measured failure modes outperform generically-tuned debate. The framework supports direction-aware procurement, accountability, and agent design for legal AI deployed in the wild.</p></description>
|
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2606.18021</guid>
|
|
||||||
<pubDate>Tue, 16 Jun 2026 00:00:00 +0000</pubDate>
|
<pubDate>Tue, 16 Jun 2026 00:00:00 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Adaptive Volumetric Mechanical Property Fields Invariant to Resolution</title>
|
<title>MCompassRAG: Topic Metadata as a Semantic Compass for Paragraph-Level Retrieval</title>
|
||||||
<link>https://arxiv.org/abs/2606.18231</link>
|
<link>https://arxiv.org/abs/2606.18508</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2606.18231.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Rishit Dagli, Donglai Xiang, Vismay Modi, Xuning Yang, Gavriel State, David I. W. Levin, Maria Shugrina</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> Accurate mechanical properties (or materials) Young's modulus (E), Poisson's ratio (ν) and density (ρ) are essential for reliable physics simulation of digital worlds, but most 3D assets lack this information. We propose AdaVoMP, a method for predicting accurate dense spatially-varying (E, ν, ρ) for input 3D objects across representations, improving the resolution, accuracy, and memory efficiency over the state-of-the-art. The foundation of our technique is a sparse and adaptive voxel structure SAV that efficiently represents both the input 3D shape and the material field output. We replace the fixed-voxel model of the most accurate prior method, VoMP, with a novel sparse transformer encoder-decoder model that learns to generate a unique SAV autoregressively for every input shape to represent its materials, achieving a resolution 16^3times higher than prior art. Experiments show that AdaVoMP estimates more accurate volumetric properties, even with lesser test-time compute than all prior art. This allows us to convert high-resolution complex 3D objects into simulation-ready assets, resulting in realistic deformable simulations.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2606.18508.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Amirhossein Abaskohi, Raymond Li, Gaetano Cimino, Peter West, Giuseppe Carenini, Issam H. Laradji</p><p><b>Upvotes:</b> 9</p><p><b>Summary:</b> Retrieval-augmented generation (RAG) systems depend critically on how documents are chunked and searched. Fine-grained chunks can improve retrieval precision but expand the search space, increasing latency and cost; larger chunks reduce the number of candidates but make dense similarity less reliable, as the representation for each chunk mixes multiple topics and introduces more semantic noise. This trade-off becomes especially limiting in deep research tasks, where retrieval must be both fast and precise across large, heterogeneous corpora. We introduce MCompassRAG, a metadata-guided retrieval framework that uses topic-level signals as a semantic compass for selecting relevant evidence. Instead of relying only on cosine similarity between queries and noisy chunk embeddings, MCompassRAG enriches chunk representations with topic metadata in the same embedding space and trains a lightweight retriever through LLM-teacher distillation. At inference time, MCompassRAG performs topic-aware retrieval without additional LLM calls, improving both efficiency and evidence quality. Across six complex retrieval benchmarks, MCompassRAG improves information efficiency (IE) by 8.24% on average with over 5 times lower latency than the strongest efficient RAG baselines. Code is available on https://github.com/AmirAbaskohi/MCompassRAG.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2606.18231</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2606.18508</guid>
|
||||||
<pubDate>Tue, 16 Jun 2026 00:00:00 +0000</pubDate>
|
<pubDate>Tue, 16 Jun 2026 00:00:00 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>LooseControlVideo: Directorial Video Control using Spatial Blocking</title>
|
<title>SproutRAG: Attention-Guided Tree Search with Progressive Embeddings for Long-Document RAG</title>
|
||||||
<link>https://arxiv.org/abs/2606.19495</link>
|
<link>https://arxiv.org/abs/2606.18381</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2606.19495.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shariq Farooq Bhat, Niloy J. Mitra, Kalyan Sunkavalli</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> Precise 3D spatial orchestration in text-to-video generation remains a significant challenge, particularly for multi-object scenes where semantic layout and temporal dynamics are often entangled. While existing depth-conditioned models achieve good structural fidelity, they necessitate dense, frame-accurate guidance that is labor-intensive to author for dynamic events involving deformable objects. We present LooseControlVideo, a framework that enables intuitive and expressive control by using sparse, oriented 3D boxes as a "blocking" proxy. This allows users to author high-level layout and trajectory while leveraging a video generative model to generate realistic occlusions, dynamics and interactions. We achieve this by fine-tuning a Wan 2.2 backbone on a video dataset annotated with DNOCS, a novel encoding for 3D size, orientation and depth-ordered occlusions. Furthermore, our method allows for localized refinement, such as adjusting a jump trajectory or adding an interaction, with minimal disruption to the global scene context. Extensive evaluations on the nuScenes, HO-3D, and BEHAVE benchmarks demonstrate that LooseControlVideo significantly outperforms existing 2D-box and flow-based baselines. Our findings indicate a 1.2x to 3x improvement in Trajectory Error; 2x improvement in Rigid Motion Consistency; and a 1.5x to 2x increase in Occlusion Accuracy over current state-of-the-art layout-conditioned models, demonstrating that oriented 3D primitives provide good geometric prior for complex, multi-agent video authoring.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2606.18381.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Amirhossein Abaskohi, Issam H. Laradji, Peter West, Giuseppe Carenini</p><p><b>Upvotes:</b> 8</p><p><b>Summary:</b> Retrieval-augmented generation (RAG) systems must balance retrieval granularity with contextual coherence, a challenge that existing methods address through LLM-guided chunking, single-level context expansion, or hierarchical summarization. These approaches variously depend on costly LLM calls during indexing or retrieval, limit context aggregation to a single granularity level, or introduce information loss through summarization. We present SproutRAG, an attention-guided hierarchical RAG framework that addresses this trade-off by organizing sentence-level chunks into progressively larger but semantically coherent units, using learned inter-sentence attention to construct a binary chunking tree. Unlike prior approaches that rely on external LLMs, fixed context expansion, or lossy summarization, SproutRAG learns which attention heads and layers best capture semantic document structure, enabling multi-granularity retrieval without additional LLM calls or compressed summaries. At retrieval time, SproutRAG uses hierarchical beam search to retrieve candidates at multiple granularities, capturing multi-sentence relevance beyond flat retrieval. The framework is trained end-to-end with a joint objective that improves both embeddings and tree structure. Experiments across four benchmarks spanning scientific, legal, and open-domain settings demonstrate that SproutRAG improves information efficiency (IE) by 6.1% on average over the strongest baseline. Code is available on https://github.com/AmirAbaskohi/SproutRAG.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2606.19495</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2606.18381</guid>
|
||||||
|
<pubDate>Tue, 16 Jun 2026 18:28:00 +0000</pubDate>
|
||||||
|
</item>
|
||||||
|
<item>
|
||||||
|
<title>Characterizing Narrative Content in Web-scale LLM Pretraining Data</title>
|
||||||
|
<link>https://arxiv.org/abs/2606.19468</link>
|
||||||
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2606.19468.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Teagan Johnson, Elliott Ash, Andrew Piper, Maria Antoniak</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> The narrative composition of web-scale LLM pretraining corpora remains largely unexplored even though narrative is a fundamental mode of human communication. We present the first fine-grained study of narrative features in Dolma, a 3-trillion-token open pretraining corpus. Drawing on narrative theory, we design a framework spanning three core narrative elements (agency, setting, and events) operationalized as 11 interpretable dimensions. After sampling and annotating a diverse set of 400 passages, we finetune and validate NarraBERT, a RoBERTa-based model for fine-grained narrative prediction. We apply NarraBERT to 3M passages, resulting in a new dataset, NarraDolma. We find (i) narrative structure is measurable at scale across extremely heterogeneous data, (ii) we uncover a continuous, multidimensional narrative structure underlying web text, and (iii) narrative qualities are unequally distributed across pretraining sources and topics in ways that current curation practices neither measure nor account for. Our framework, dataset, and analyses provide a foundation for understanding how narrative qualities are distributed in LLM pretraining data and for studying how data composition affects narrative reasoning tasks. We publicly release NarraDolma and NarraBERT.</p></description>
|
||||||
|
<guid isPermaLink="false">https://arxiv.org/abs/2606.19468</guid>
|
||||||
<pubDate>Wed, 17 Jun 2026 00:00:00 +0000</pubDate>
|
<pubDate>Wed, 17 Jun 2026 00:00:00 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Configurable Clinical Information Extraction with Agentic RAG: What Works, What Breaks, and Why</title>
|
<title>WorldLines: Benchmarking and Modeling Long-Horizon Stateful Embodied Agents</title>
|
||||||
<link>https://arxiv.org/abs/2606.19602</link>
|
<link>https://arxiv.org/abs/2606.18847</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2606.19602.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Osman Alperen Çinar-Koraş, Marie Bauer, Sameh Khattab, Merlin Engelke, Moon Kim, Stephan Settelmeier, Shigeyasu Sugawara, Fabian Freisleben, Felix Nensa, Jens Kleesiek</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> Patient contexts span hundreds of heterogeneous documents and thousands of structured data points, yet the document-level metadata that AI systems need for retrieval and triage is absent or incomplete. Standard retrieval-augmented generation fails on this data, mishandling temporal reasoning, cross-document dependencies, and missing metadata. We deploy ACIE (Agentic Clinical Information Extraction) at University Medicine Essen: an on-premise agentic RAG pipeline that reasons over complete patient contexts and grounds every answer in source passages for clinician verification. We quantify the metadata gap, trace the architectural decisions it shaped, and evaluate extraction alongside an independent retrospective lymphoma registry study, in which nuclear-medicine physicians verify every extracted value against its cited sources. Across 7,326 judgments, clinicians accepted 96.5\% of extractions, with per-type acceptance ranging from 80\% to 99\%.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2606.18847.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yehang Zhang, Jianchong Su, Haojian Huang, Yifan Chang, Tianhao Zhou, Xinli Xu, Yingjie Xu, Yinchuan Li, Zexi Li, Ying-Cong Chen</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> To assist humans over extended periods in real homes, embodied agents must remember user routines, world states, and past interactions. Existing long-term memory benchmarks mainly evaluate language-centric retrieval and question answering, while embodied benchmarks often focus on short-horizon task execution without testing long-term memory use in dynamic environments. We introduce WorldLines, a project-driven benchmark for long-horizon embodied household assistance. It constructs temporally extended household traces with dialogues, actions, execution feedback, object and device state changes, and converts them into evidence-linked samples for Memory QA and Embodied Task Planning. We further propose ObsMem, an observer-grounded memory framework that maintains visibility-aware memories and action-native state trails for state-aware decisions. Experiments reveal persistent challenges in partial observability, overwritten world states, and translating long-term memory into embodied plans, while ObsMem offers a stronger reference architecture for this setting.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2606.19602</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2606.18847</guid>
|
||||||
<pubDate>Wed, 17 Jun 2026 00:00:00 +0000</pubDate>
|
<pubDate>Wed, 17 Jun 2026 00:00:00 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Freeing the Law with LOCUS: A Local Ordinance Corpus for the United States</title>
|
<title>BrainG3N: A Dual-Purpose Tokenizer for Controllable 3D Brain MRI Generation</title>
|
||||||
<link>https://arxiv.org/abs/2606.19334</link>
|
<link>https://arxiv.org/abs/2606.19651</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2606.19334.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Denis Peskoff, Joe Barrow, Christopher Vu, Diag Davenport</p><p><b>Upvotes:</b> 6</p><p><b>Summary:</b> Progress in legal AI increasingly depends on access to authoritative legal text at scale. Yet one of the most consequential layers of American law remains largely absent from existing machine-readable corpora: local ordinances. Local codes govern zoning, housing, business licensing, public health, noise, animal control, and many other domains of everyday regulation, but they are fragmented across vendor platforms designed for human browsing rather than bulk research access. We introduce LOCUS - the Local Ordinance Corpus for the United States - a comprehensive corpus and county-harmonized access layer for U.S. municipal and county ordinance codes. The raw corpus, available for release to researchers, represents nearly all publicly available municipal and county ordinance codes. The resulting raw corpus contains codes from 9,239 cities and counties. A smaller county-harmonized LOCUS access layer provides coverage for the largest 2,309 of 3,144 U.S. counties, accounting for a majority of the population. We use OCR to handle the myriad of document formats that have kept the law from being a public resource. We release the corpus with coverage metadata to support reproducibility, downstream legal AI research, and the incremental expansion of machine-readable access to local law. We train a collection of ModernBERT-based classifiers and scorers to facilitate analyzing U.S. local law among several dimensions, such as opacity and paternalism, that have not previously been studied at this scale. LOCUS-v1 and its derivative models are available at: https://huggingface.co/datasets/LocalLaws/LOCUS-v1</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2606.19651.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Max Van Puyvelde, Ibrahim Gulluk, Wim Van Criekinge, Olivier Gevaert</p><p><b>Upvotes:</b> 7</p><p><b>Summary:</b> Three-dimensional (3D) brain MRI is central to clinical neurology and neuro-oncology, where generative models could augment under-represented cohorts, simulate disease trajectories, and support privacy-preserving data sharing. Latent diffusion has been the go-to solution for modeling imaging data, but it places two competing demands on the tokenizer: encoder embeddings must retain the clinical information that downstream tasks act on, and the decoder must reconstruct anatomically faithful volumes. Existing reconstruction-driven tokenizers achieve the second at the expense of the first. To address this, we introduce a fully volumetric masked-autoencoder (MAE) based tokenizer for 3D brain MRI latent diffusion, decoupling encoder and decoder: a frozen 3D MAE encoder produces clinically informative embeddings, while a dedicated CNN decoder reconstructs voxels from a linear projection of those embeddings. We pretrain the encoder on 35,309 volumes from 18 public cohorts spanning four modalities, ten disease categories, and 200+ acquisition sites, and demonstrate its dual utility in two settings. First, on a 23-task linear-probing benchmark, the encoder outperforms or matches SOTA models (i.e., BrainIAC, BrainSegFounder, and MedicalNet) on 21 of 23 tasks. Second, a conditional diffusion transformer (DiT) trained on these clinically informative embeddings supports both conditional generation across six variables and patient-specific longitudinal forecasting. Together these results establish a single 3D brain-MRI embedding space capable of both downstream clinical tasks and controllable generation.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2606.19334</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2606.19651</guid>
|
||||||
<pubDate>Wed, 17 Jun 2026 00:00:00 +0000</pubDate>
|
<pubDate>Wed, 17 Jun 2026 00:00:00 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>FAPO: Fully Autonomous Prompt Optimization of Multi-Step LLM Pipelines</title>
|
<title>GateMem: Benchmarking Memory Governance in Multi-Principal Shared-Memory Agents</title>
|
||||||
<link>https://arxiv.org/abs/2606.19605</link>
|
<link>https://arxiv.org/abs/2606.18829</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2606.19605.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Paul Kassianik, Baturay Saglam, Huaibo Zhao, Blaine Nelson, Supriti Vijay, Aman Priyanshu, Amin Karbasi</p><p><b>Upvotes:</b> 10</p><p><b>Summary:</b> Multi-step LLM pipelines fail through interactions among retrieval, reasoning, and formatting steps, so prompt-only optimization can miss bottlenecks in the chain. We present FAPO (Fully Autonomous Prompt Optimization), a framework that lets Claude Code optimize an LLM pipeline inside a standardized codebase. FAPO evaluates a pipeline, inspects intermediate steps, diagnoses failures, proposes scoped changes, and validates variants repeatedly to optimize against a score function. It first tries prompt edits and, only when prompt optimization appears insufficient, changes chain structure within the permitted scope when attribution identifies a structural bottleneck. Across six benchmarks and three task models, FAPO beats the baseline GEPA in 15 of 18 model-benchmark comparisons. In 11 model-benchmark comparisons, FAPO wins with non-overlapping mean pm trial-standard-deviation ranges, and the mean FAPO-GEPA gain is +14.1 pp. In the six HoVer and IFBench comparisons where prompt-first search escalated to structural changes, FAPO wins all six with a mean gain of +33.8 pp. FAPO also improves performance on security tasks: on CTIBench-RCM, a security CVE-to-CWE task, prompt-only FAPO lifts test accuracy by +4.0 pp on GPT-5, +7.1 pp on Foundation-Sec-8B-Instruct, and +2.0 pp on Foundation-Sec-8B-Reasoning. These results position FAPO as a state-of-the-art pipeline optimization technique for both general-purpose and security-focused tasks.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2606.18829.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhe Ren, Yibo Yang, Yimeng Chen, Zijun Zhao, Benshuo Fu, Zhihao Shu, Bingjie Zhang, Yangyang Xu, Dandan Guo, Shuicheng Yan</p><p><b>Upvotes:</b> 13</p><p><b>Summary:</b> Memory benchmarks for LLM agents largely assume single-user settings, leaving shared assistants for hospitals, workplaces, campuses, and households understudied. In these deployments, multiple principals write to a common memory pool and query it under different roles, scopes, and relationships, so memory quality requires governance as well as recall. We introduce GateMem, a benchmark for multi-principal shared-memory agents. GateMem jointly evaluates utility for legitimate long-horizon requests with state updates, access control across contextual authorization boundaries, and agent-facing active forgetting after explicit deletion requests. It spans medical, office, education, and household domains, with long-form multi-party episodes, incremental memory injection, hidden checkpoints, structured judging, and leak-target annotations. Across diverse baselines and backbone models, no method simultaneously achieves strong utility, robust access control, and reliable forgetting. Long-context prompting often yields the best governance score at high token cost, while retrieval-based and external-memory methods reduce cost yet still leak unauthorized or deleted information. These results show current memory agents remain far from reliable shared institutional deployment.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2606.19605</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2606.18829</guid>
|
||||||
<pubDate>Wed, 17 Jun 2026 00:00:00 +0000</pubDate>
|
<pubDate>Wed, 17 Jun 2026 00:00:00 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>ImageWAM: Do World Action Models Really Need Video Generation, or Just Image Editing?</title>
|
<title>PerceptionDLM: Parallel Region Perception with Multimodal Diffusion Language Models</title>
|
||||||
<link>https://arxiv.org/abs/2606.19531</link>
|
<link>https://arxiv.org/abs/2606.19534</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2606.19531.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yuyang Zhang, Wenyao Zhang, Zekun Qi, He Zhang, Haitao Lin, Jingbo Zhang, Yao Mu, Xiaokang Yang, Wenjun Zeng, Xin Jin</p><p><b>Upvotes:</b> 14</p><p><b>Summary:</b> World Action Models (WAMs) commonly rely on video generation to bridge visual world modeling and robot control. However, video-based WAMs face three coupled limitations: dense multi-frame future tokens make inference costly, full video prediction spends capacity on action-irrelevant temporal and appearance details, and long-horizon future imagination may introduce errors that mislead action prediction. These issues raise a simple question: Does world action model really need video generation? We propose ImageWAM, a simple WAM framework that repurposes pretrained image editing models for robot action prediction. In contrast to video generation, image editing provides a better-matched prior: it only needs to model a target-frame transformation, focuses on action-relevant current-to-target visual differences, and grounds task instructions to localized visual changes through edit pretraining. In practice, ImageWAM does not decode the target frame at inference time; instead, it conditions a flow-matching action expert on the KV caches produced by image-editing denoising, using them as a compact world-action context. ImageWAM outperforms standard VLA baselines and matching competitive WAMs without additional policy pretraining across different simulator and real-world experiments. It also reduces FLOPs to 1/6 and latency to 1/4 of video-based WAMs. Attention analysis further shows that editing caches focus on task-relevant change regions, supporting image editing as an effective alternative to video-based world-action modeling.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2606.19534.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yueyi Sun, Yuhao Wang, Jason Li, Ye Tian, Tao Zhang, Jacky Mai, Yihan Wang, Haochen Wang, Jinbin Bai, Ling Yang, Yunhai Tong</p><p><b>Upvotes:</b> 50</p><p><b>Summary:</b> Multimodal large language models (MLLMs) have achieved remarkable progress in visual understanding tasks. However, most existing MLLMs rely on autoregressive generation, which limits their efficiency for perception tasks that require captioning multiple regions. In this work, we propose PerceptionDLM, a multimodal diffusion language model optimized for efficient parallel region perception. Built upon PerceptionDLM-Base, a strong foundational baseline that achieves state-of-the-art performance among open-source diffusion MLLMs, our architecture fully leverages the parallel decoding nature of DLMs. Specifically, we introduce efficient prompting and structured attention masking to enable simultaneous perception of multiple masked regions, allowing the model to generate region descriptions in parallel at both the sequence and token levels. This design significantly improves inference efficiency compared with existing approaches that process regions sequentially. To systematically evaluate the parallelism property of visual perception capability for DLMs, we construct a new Parallel Detailed Localized Captioning Benchmark (ParaDLC-Bench) by scaling the DLC-Bench to include multiple region masks per image, enabling joint evaluation of both caption quality and inference efficiency. Experiments demonstrate that PerceptionDLM maintains competitive performance in region captioning while achieving substantial speed improvements for multi-region perception tasks. Our results highlight the potential of multimodal diffusion language models for efficient, parallel visual perception. To the best of our knowledge, we are the first to achieve parallel region caption and perception by leveraging the advantages of diffusion language models. Code, models, and datasets are released.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2606.19531</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2606.19534</guid>
|
||||||
<pubDate>Wed, 17 Jun 2026 00:00:00 +0000</pubDate>
|
<pubDate>Wed, 17 Jun 2026 00:00:00 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Playful Agentic Robot Learning</title>
|
<title>When, Where, and How: Adaptive Binning for Tabular Self-Supervised Learning</title>
|
||||||
<link>https://arxiv.org/abs/2606.19419</link>
|
<link>https://arxiv.org/abs/2606.19827</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2606.19419.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Junyi Zhang, Jiaxin Ge, Hanjun Yoo, Letian Fu, Zihan Yang, Yaowei Liu, Raj Saravanan, Shaofeng Yin, Justin Yu, Dantong Niu, Zirui Wang, Roei Herzig, Ken Goldberg, Yutong Bai, David M. Chan, Ion Stoica, Angjoo Kanazawa, Jiahui Lei, Haiwen Feng, Trevor Darrell</p><p><b>Upvotes:</b> 43</p><p><b>Summary:</b> Current agentic robot systems can write executable Code-as-Policy programs, observe feedback, and revise behavior across multiple attempts, but they remain largely task-driven: reusable skills are acquired only after explicit instructions. We study Playful Agentic Robot Learning, where an embodied coding agent uses self-directed play as a continual skill-learning stage before downstream tasks arrive. We introduce RATs, Robotics Agent Teams designed for play-time skill acquisition. During play, RATs proposes novel yet learnable exploratory tasks, plans and executes robot-code policies, verifies intermediate progress, diagnoses failures, retries with dense, step-level feedback, and distills successful executions into a persistent code skill library. At test time, the agent reuses relevant skills from this frozen library to help solve new tasks. Experiments in LIBERO-PRO and MolmoSpaces show that play-learned skills improve held-out downstream tasks over no-play and random-play baselines, with 20.6 and 17.0 percentage-point gains over CaP-Agent0 on LIBERO-PRO and MolmoSpaces, respectively. Moreover, the learned skills can be plugged into other inference-time Code-as-Policy agents by simply retrieving them into the context, improving RoboSuite and real-world transfer by 8.9 and 8.8 points, respectively, without finetuning the underlying model.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2606.19827.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Daehwan Kim, Haejun Chung, Ikbeom Jang</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Medical tabular data are ubiquitous in clinical research, but deep learning for tables remains underexplored because reliable labels often require costly expert adjudication, even though structured clinical variables are routinely available in tabular form. Self-supervised learning can leverage these unlabeled tables, and recent binning-based pretexts offer a promising inductive bias, but existing objectives fix a single global quantile discretization and apply feature-agnostic supervision. We propose Adaptive Binning, a training-adaptive discretization pretext for tabular SSL that couples discretization to learning through a feature-wise coarse-to-fine curriculum. Motivated by the spectral bias of neural networks and the principles of curriculum learning, our method progressively refines discretization per feature upon plateau detection and selects representation-aware splits to jointly improve value-space concentration and representation-space coherence. A heterogeneity-aware objective unifies categorical reconstruction with ordinal supervision for numerical features, and experiments on public medical tabular datasets under unified evaluation protocols show consistent gains for linear probing and fine-tuning without dataset-specific discretization tuning. We further introduce a medical tabular SSL benchmark with standardized protocols to support reproducible progress in this underexplored domain. Our code is available at https://github.com/labhai/Adaptive-Binning.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2606.19419</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2606.19827</guid>
|
||||||
<pubDate>Wed, 17 Jun 2026 00:00:00 +0000</pubDate>
|
|
||||||
</item>
|
|
||||||
<item>
|
|
||||||
<title>Moebius: 0.2B Lightweight Image Inpainting Framework with 10B-Level Performance</title>
|
|
||||||
<link>https://arxiv.org/abs/2606.19195</link>
|
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2606.19195.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Kangsheng Duan, Ziyang Xu, Wenyu Liu, Xiaohu Ruan, Xiaoxin Chen, Xinggang Wang</p><p><b>Upvotes:</b> 113</p><p><b>Summary:</b> While 10B-level industrial foundation models have pushed the boundaries of image inpainting, their prohibitive computational costs severely hinder practical deployment. Constructing a highly optimized task-specific specialist offers a promising solution; however, extreme structural compression inevitably triggers a severe representation bottleneck. To conquer this, we propose Moebius, a highly efficient lightweight inpainting framework. We systematically reconstruct the diffusion backbone by introducing the Local-λ Mix Interaction (LλMI) block. Comprising Local-λ and Interactive-λ modules, it elegantly summarizes spatial contexts and global semantic priors into fixed-size linear matrices, preserving complex latent interactions while drastically shedding parameters. Furthermore, to unlock the full representational capacity of this highly compact architecture, we synergistically pair it with an adaptive multi-granularity distillation strategy. Operating strictly within the latent space to avoid expensive pixel-space decoding, this strategy dynamically balances multiple gradient-based losses to achieve high-fidelity alignment. Extensive experiments across natural and portrait benchmarks demonstrate that this optimal synergy enables Moebius to rival or even surpass the generation quality of the 10B-level industrial generalist FLUX.1-Fill-Dev. Remarkably, Moebius achieves this using less than 2\% of the parameters (0.22B vs. 11.9B) while delivering a >15times acceleration in total inference time, setting a new efficiency standard for high-fidelity inpainting. Project page at https://hustvl.github.io/Moebius.</p></description>
|
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2606.19195</guid>
|
|
||||||
<pubDate>Wed, 17 Jun 2026 00:00:00 +0000</pubDate>
|
|
||||||
</item>
|
|
||||||
<item>
|
|
||||||
<title>JAMER: Project-Level Code Framework Dataset and Benchmark on Professional Game Engines</title>
|
|
||||||
<link>https://arxiv.org/abs/2606.19830</link>
|
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2606.19830.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jianwen Sun, Chuanhao Li, Zizhen Li, Yukang Feng, Fanrui Zhang, Yifei Huang, Yu Dai, Kaipeng Zhang</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Current AI-driven game development has made substantial progress in asset generation, gameplay design, and web-based game coding, yet project-level code engineering on professional game engines remains largely unexplored due to the absence of large-scale datasets and deterministic evaluation methods. We present JamSet and JamBench, the first project-level game code framework dataset and benchmark built on a professional game engine. Our key insight is that Game Jam competitions, community events where developers build complete games under tight time constraints, yield thousands of open-source projects suitable for this purpose. Building on the Godot engine's text-based format and headless execution mode, we design a deterministic verification pipeline from file integrity to runtime behavior collection, distilling 8,133 verified projects from over 240,000 repositories. Of these, 300 manually verified projects form JamBench; the rest constitute JamSet. JamBench defines theme-driven generation and code completion tasks, evaluated through a pipeline combining compilation pass rates, Structural Completeness Score (SCS), and Behavioral Alignment Score (BAS). Evaluation of 9 frontier models reveals a capability cliff as project scale increases, with runtime pass rates dropping from 80.4% on small projects to 5.7% on large ones (Task2a). Code Agents improve compilation rates yet yield no gains in runtime behavioral quality, indicating that the bottleneck lies in architectural design rather than syntactic correctness. Experiments validate JamSet as effective training data. All data and code are publicly available.</p></description>
|
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2606.19830</guid>
|
|
||||||
<pubDate>Thu, 18 Jun 2026 00:00:00 +0000</pubDate>
|
<pubDate>Thu, 18 Jun 2026 00:00:00 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>The FID Lottery: Quantifying Hidden Randomness in Generative-Model Evaluation</title>
|
<title>StylisticBias: A Few Human Visual Cues Drive Most Social Biases in MLLMs</title>
|
||||||
<link>https://arxiv.org/abs/2606.20536</link>
|
<link>https://arxiv.org/abs/2606.20527</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2606.20536.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Nicolas Dufour, Alexei A. Efros, Patrick Pérez</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> The Frechet Inception Distance (FID) is the de facto arbiter of image generation, yet most papers report just a single number from a single trained model using a single sampling seed. How reproducible is that number if we retrain the model, or merely resample from it? In this paper, we treat FID as a random variable on a two-axis panel of training and generation seeds, and measure its variance directly on several hundred SiT networks trained on class-conditional ImageNet 256x256. We report surprising findings: (a) Retraining the model using the same recipe with a different seed moves FID 3.2x more (in Inception feature space) than redrawing samples from a fixed network. (b) That gap is driven by three factors: random initialisation, data ordering, and the per-step Gaussian noise of the flow-matching loss. (c) Increasing compute or model size barely tightens the spread, holding the FID coefficient of variation (CoV) inside a 1-2% band. (d) Per-cell classifier-free-guidance tuning halves the spread but reshuffles which seeds work best, and a lucky training seed reaches the same FID with up to 2x less compute than an unlucky one. Based on these findings, we recommend a new FID evaluation protocol: evaluate under per-cell optimal guidance, treat any FID gap below the empirically measured ~1.3% CoV as inconclusive, and report an error bar over several training seeds rather than a single FID number.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2606.20527.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shaghayegh Kolli, Timo Cavelius, Nafiseh Nikeghbal, Samantha Dalal, Jana Diesner</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Multimodal large language models (MLLMs) are increasingly deployed in personally and societally consequential settings, yet the visual cues that shape how these models judge people remain poorly understood. Prior work often compares different (groups of) individuals, making it difficult to separate appearance effects from identity differences. We introduce StylisticBias, a controlled benchmark for evaluating attribute-level social bias in MLLMs. We generate 500 photorealistic base faces and create about 50 single-attribute variations per face, producing about 25K images. This design keeps identity fixed and changes one visual attribute at a time. It lets us measure how specific cues shift model judgments. We evaluate six MLLMs across 25 binary social judgment scenarios. We find that age and body type dominate identity-level effects, while fashion style and other visual cues drive the largest attribute-level shifts. We further find that about 15 attributes account for nearly 80\% of the total variation, showing that bias is concentrated in a small set of visual cues. Sensitivity is strongest in judgments that are semantically aligned with appearance, especially socioeconomic and style-related judgments. We release StylisticBias as a benchmark for fine-grained bias evaluation in multimodal models. Code and dataset: https://github.com/timo-cavelius/StylisticBias and https://hf.co/datasets/shaghayegh/stylistic-bias-dataset.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2606.20536</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2606.20527</guid>
|
||||||
<pubDate>Thu, 18 Jun 2026 00:00:00 +0000</pubDate>
|
|
||||||
</item>
|
|
||||||
<item>
|
|
||||||
<title>Holo-World: Unified Camera, Object and Weather Control for Video World Model</title>
|
|
||||||
<link>https://arxiv.org/abs/2606.20083</link>
|
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2606.20083.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xiangchen Yin, Wenzhang Sun, Jiahui Yuan, Zijie Liu, Yinda Chen, Wei Li, Dachun Kai, Chunfeng Wang, Xiaoyan Sun</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> Video world models are moving toward preserving an observed world under controllable camera and object motion while allowing its environmental state to change. Yet these controls remain isolated, and weather generation typically relies on a source video or reconstructed scene that already specifies future structure. We study a first-frame-anchored source-to-state setting, where the model starts from a single image and follows explicit camera and object controls and an optional weather instruction, then generates a video that either preserves the source world or transfers it to a target weather state. To address these challenges, we first build HoloStateData, a state video dataset that turns diverse videos into unified control samples for camera, object, and weather supervision. Second, we introduce Holo-World, a unified controllable video world model that jointly controls scene from a single image. Its Unified Scene Adapter factorizes world preservation and weather transfer into distinct parameter subspaces, using rendered background, geometry buffers, and object controls to maintain controlled scene structure while modeling weather-dependent appearance and particle effects. Additionally, Scene-Weather Decomposed CFG guides scene and weather residuals separately, strengthening target weather effects without over-amplifying the full condition. Quantitative and qualitative experiments demonstrate that Holo-World maintains precise camera and object control with consistent scene structure while transferring scenes into diverse target weather state, outperforming video-to-video weather editing baselines on weather-state generation. Our project page is available at https://xiangchenyin.github.io/Holo-World/.</p></description>
|
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2606.20083</guid>
|
|
||||||
<pubDate>Thu, 18 Jun 2026 00:00:00 +0000</pubDate>
|
|
||||||
</item>
|
|
||||||
<item>
|
|
||||||
<title>HumanScale: Egocentric Human Video Can Outperform Real-Robot Data for Embodied Pretraining</title>
|
|
||||||
<link>https://arxiv.org/abs/2606.20521</link>
|
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2606.20521.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Juncheng Ma, Jianxin Bi, Yufan Deng, Xuanran Zhai, Kewei Zhang, Ye Huang, Bo Liang, Shukai Gong, Jiankai Tu, Xiaotian Tang, Jiaxin Li, Kaiqi Chen, Duomin Wang, Yuqi Wang, Bingyi Kang, Eric Huang, Zhiyang Dou, Zhen Dong, Enze Xie, Wojciech Matusik, Tat-Seng Chua, Daquan Zhou</p><p><b>Upvotes:</b> 6</p><p><b>Summary:</b> Embodied foundation models are expected to benefit from data scaling like large language models, but face a much tighter data bottleneck. Teleoperated real-robot trajectories remain the dominant pretraining source due to their precise action supervision and embodiment alignment, yet their scalability is limited by high collection cost, acquisition difficulty, and low behavioral and environmental diversity. These limitations have sparked interest in egocentric human video as a scalable, substantially lower-cost, and more diverse alternative for embodied model pretraining. However, its effectiveness compared to teleoperated real-robot data remains underexplored. To address this question, we conduct a systematic study comparing egocentric human video and teleoperated real-robot trajectories as pretraining data sources for embodied foundation models, under fixed post-training and validation protocols. Surprisingly, we find that egocentric data, when processed through a carefully designed filtering and labeling pipeline, is not merely a viable substitute for model pretraining but can lead to superior performance. With the same amount of pretraining data, models pretrained on egocentric data achieve a 24% lower validation loss on real-robot action prediction, as well as 52.5% and 90% higher success rates on in-distribution and out-of-distribution real-robot task execution, respectively. This finding verifies a scalable paradigm for embodied foundation models: pretrain on egocentric human video to learn diverse world representations, then adapt with a small amount of labeled real-robot data for action-space alignment. We hope this study encourages broader exploration of egocentric data and offers guidance for data quality assessment before costly robot data collection.</p></description>
|
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2606.20521</guid>
|
|
||||||
<pubDate>Thu, 18 Jun 2026 00:00:00 +0000</pubDate>
|
|
||||||
</item>
|
|
||||||
<item>
|
|
||||||
<title>Rethinking Shrinkage Bias in LLM FP4 Pretraining: Geometric Origin, Systemic Impact, and UFP4 Recipe</title>
|
|
||||||
<link>https://arxiv.org/abs/2606.20381</link>
|
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2606.20381.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Qian Zhao, Kunlong Chen, Changxin Tian, Zhonghui Jiang, Haitao Zhang, Chaofan Yu, Peijie Jiang, Mingliang Gong, Jia Liu, Ziqi Liu, Zhiqiang Zhang, Jun Zhou</p><p><b>Upvotes:</b> 6</p><p><b>Summary:</b> FP4 training promises substantial reductions in memory and computation cost for LLM pretraining, yet current FP4 hardware paths and recipes, including NVIDIA Blackwell/Rubin-class systems and AMD MI350-series GPUs, remain centered on E2M1 data elements. In this study, we identify a fundamental limitation of that choice: non-uniform formats such as E2M1 inherently suffer from Shrinkage Bias, a systematic negative rounding error caused by the geometric asymmetry of their representable bins. We show that this bias accumulates multiplicatively across layers and is amplified by the Random Hadamard Transform (RHT), providing a unified explanation for the training instability observed in existing E2M1-based FP4 recipes. In contrast, uniform grids (E1M2/INT4) bypass this grid-geometry error and better convert the improved bucket utilization from RHT into higher quantization quality. Based on this finding, we propose UFP4, a uniform 4-bit training recipe that applies RHT to all three training GEMMs while restricting stochastic rounding to dY alone. On Dense 1.5B, MoE 7.9B, and MoE 124B long-run pretraining, UFP4 consistently achieves lower BF16-relative loss degradation than strong E2M1-based baselines, supported by scaling-law analysis and ablation studies. Our results suggest that future accelerators should support E1M2/INT4-style uniform 4-bit grids as first-class training primitives alongside E2M1.</p></description>
|
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2606.20381</guid>
|
|
||||||
<pubDate>Thu, 18 Jun 2026 00:00:00 +0000</pubDate>
|
|
||||||
</item>
|
|
||||||
<item>
|
|
||||||
<title>LedgerAgent: Structured State for Policy-Adherent Tool-Calling Agents</title>
|
|
||||||
<link>https://arxiv.org/abs/2606.20529</link>
|
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2606.20529.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Md Nayem Uddin, Amir Saeidi, Eduardo Blanco, Chitta Baral</p><p><b>Upvotes:</b> 6</p><p><b>Summary:</b> Policy-adherent tool-calling agents in customer-service domains must maintain task states across turns while calling tools and obeying domain policies. Task states consist of relevant facts, identifiers, constraints, and conditions observed through user interaction and tool calls. In standard agents, task states are not represented separately. Observations, tool returns, and policy instructions are placed in the prompt, leaving agents to reconstruct the relevant states from the prompt each time they decide what to do next. This design makes state management implicit, creating two common failure modes. An agent may retrieve the right facts but later ground its decision in stale, missing, or incorrect information; and a syntactically valid tool call may still violate a domain policy that depends on the current task state. We introduce LedgerAgent, an inference-time method for tool-calling agents that maintains observed task states in a separate ledger and renders the states into the prompt. The ledger is also used to check state-dependent policy constraints before environment-changing tool calls are executed, blocking policy violations. Across four customer-service domains and a mixed panel of open- and closed-weight models, LedgerAgent improves average passk over a standard prompt-based tool-calling approach, with the largest gains under stricter multi-trial consistency metrics.</p></description>
|
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2606.20529</guid>
|
|
||||||
<pubDate>Thu, 18 Jun 2026 00:00:00 +0000</pubDate>
|
|
||||||
</item>
|
|
||||||
<item>
|
|
||||||
<title>ENPIRE: Agentic Robot Policy Self-Improvement in the Real World</title>
|
|
||||||
<link>https://arxiv.org/abs/2606.19980</link>
|
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2606.19980.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Wenli Xiao, Jia Xie, Tonghe Zhang, Haotian Lin, Letian "Max" Fu, Haoru Xue, Jalen Lu, Yi Yang, Cunxi Dai, Zi Wang, Jimmy Wu, Guanzhi Wang, S. Shankar Sastry, Ken Goldberg, Linxi "Jim" Fan, Yuke Zhu, Guanya Shi</p><p><b>Upvotes:</b> 10</p><p><b>Summary:</b> Achieving dexterous robotic manipulation in the real world heavily relies on human supervision and algorithm engineering, which becomes a central bottleneck in the pursuit of general physical intelligence. Although emerging coding agents can generate code to automate algorithm search, their successes remain largely confined in digital environments. We conjecture that the missing abstraction to automate robotics research is a repeatable feedback loop for real-world policy improvement: reset the scene, execute a policy, verify the outcome, and refine the next iteration. To bridge this gap, we introduce ENPIRE, a harness framework for coding agents that instantiates this physical feedback routine with four core modules: an Environment module (EN) for automatic reset and verification, a Policy Improvement module (PI) that launches policy refinement, a Rollout module (R) to evaluate policies with one or multiple physical robots operating in parallel, and an Evolution module (E) in which coding agents analyze logs, consult literature, improve training infrastructure and algorithm code to address failure modes. This closed-loop system transforms real-world manipulation learning into a controllable optimization procedure, minimizing human effort while allowing fair ablations across training recipe and agent variants. Powered by ENPIRE, frontier coding agents can autonomously train a policy to achieve a 99% success rate on challenging, dexterous manipulation tasks, such as organizing a pin box, fastening a zip tie, and tool use, a process that further accelerates when we dispatch an agent team on a robot fleet. Our results suggest a practical and scalable path toward deploying coding agents to autonomously advancing robotics in the physical world.</p></description>
|
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2606.19980</guid>
|
|
||||||
<pubDate>Thu, 18 Jun 2026 00:00:00 +0000</pubDate>
|
|
||||||
</item>
|
|
||||||
<item>
|
|
||||||
<title>Current World Models Lack a Persistent State Core</title>
|
|
||||||
<link>https://arxiv.org/abs/2606.20545</link>
|
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2606.20545.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jinpeng Lu, Dexu Zhu, Haoyuan Shi, Linghan Cai, Guo Tang, Yinda Chen, Jie Cao, Duyu Tang, Yi Zhang, Yong Dai, Xiaozhu Ju</p><p><b>Upvotes:</b> 11</p><p><b>Summary:</b> World models are increasingly regarded as a decisive step toward artificial general intelligence, yet modeling the physical world demands more than rendering convincing frames on demand: it requires an internal world state that keeps evolving over time, decoupled from observation, so that objects endure and events run to their conclusions whether or not a camera is watching, much as the moon holds to its orbit when no one is looking. This requirement is a blind spot of existing benchmarks, which reward surface properties such as fidelity, motion, and camera controllability while never asking whether a generated world keeps evolving once it is unobserved. We introduce WRBench, the first systematic diagnostic benchmark that treats camera motion as an intervention on observability and resolves evaluation into a human-calibrated chain that asks whether the camera executes the requested interaction, whether the scene stays continuous and identifiable while in view, and whether a returning target remains consistent with the event that was set in motion. Across 9{,}600 videos from 23 models spanning four control paradigms, one finding proves stubborn: current systems maintain the observed world as a tracking shot, resuming a returning target in the state at which it was abandoned rather than advancing the event while it went unseen. Because this failure recurs across control paradigms, model families, and increments of scale, robust world-state evolution does not follow from cleaner imagery, tighter control, richer geometric priors, or sheer parameter count We therefore argue that the stability of the physical state kernel and the consistency of worldlines under viewpoint intervention should become first-class objectives of world-model design, so that a world model captures how the world will unfold rather than how the next frame appears.</p></description>
|
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2606.20545</guid>
|
|
||||||
<pubDate>Thu, 18 Jun 2026 00:00:00 +0000</pubDate>
|
|
||||||
</item>
|
|
||||||
<item>
|
|
||||||
<title>JanusMesh: Fast and Zero-Shot 3D Visual Illusion Generation via Cross-Space Denoising</title>
|
|
||||||
<link>https://arxiv.org/abs/2606.20563</link>
|
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2606.20563.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Siang-Ling Zhang, Huai-Hsun Cheng, Tsung-Ju Yang, Yu-Lun Liu</p><p><b>Upvotes:</b> 19</p><p><b>Summary:</b> Creating 3D visual illusions, a single 3D mesh that reveals entirely different semantics from various viewing angles, is a fascinating but tough challenge. Existing optimization-based methods are slow and can produce oversaturated colors. In contrast, naive stitching approaches fail to produce geometrically coherent objects. This results in visible unnatural seams and semantic leaks. In this paper, we present a fast and training-free framework for generating text-driven 3D visual illusions. Our approach decouples the generation into two stages. First, we propose a cross-space dual-branch denoising process. This process dynamically decodes 3D latents into voxel space for CLIP-guided orientation alignment and Signed Distance Field (SDF) blending, which ensures seamless geometric fusion. Second, we introduce a view-conditioned texture synthesis module that projects and aggregates view-specific 2D diffusion priors onto the fused geometry. Extensive experiments demonstrate that our method generates highly realistic, dual-semantic 3D illusions in just 3-5 minutes. It significantly outperforms existing methods in geometric integrity, semantic recognizability, and efficiency. Project page: https://siang1105.github.io/JanusMesh.github.io/</p></description>
|
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2606.20563</guid>
|
|
||||||
<pubDate>Thu, 18 Jun 2026 00:00:00 +0000</pubDate>
|
|
||||||
</item>
|
|
||||||
<item>
|
|
||||||
<title>FlowBender: Feedback-Aware Training for Self-Correcting Conditional Flows</title>
|
|
||||||
<link>https://arxiv.org/abs/2606.20404</link>
|
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2606.20404.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Daniel Gilo, Sven Elflein, Ido Sobol, Or Litany</p><p><b>Upvotes:</b> 19</p><p><b>Summary:</b> Conditional diffusion and flow models routinely fail to satisfy the very constraints that define their task. For instance, a depth-conditioned model often produces images whose re-extracted depth disagrees with the input, even though the forward operator--the depth predictor defining the constraint--is available during both training and inference. Existing approaches generally fall into two categories: supervised models that treat the conditioning signal as a static cue and ignore alignment information at inference, and guidance-based methods that consult it through hand-tuned linear updates, typically trading fidelity to the condition against the plausibility of the generated sample. We argue that the fundamental gap in both paradigms is that the model is never trained to utilize its own alignment error. We introduce FlowBender, a closed-loop framework that treats this error as a first-class input, training the network to learn a correction policy conditioned on inference-time feedback. At each step, an unguided look-ahead pass estimates the clean signal, a task-specific deviation is computed via the forward operator, and a refinement pass consumes this signal to produce a corrected velocity. We propose several variants of FlowBender, including a gradient-based formulation for differentiable operators and a zero-order variant for non-differentiable settings such as JPEG compression. For efficient sampling, we introduce a prior-step shortcut that enables closed-loop correction at a minimal additional computational cost. Across image-to-image translation, restoration, and 3D mesh texturing, FlowBender consistently outperforms standard supervised baselines, alignment-loss-augmented training, and state-of-the-art inference-time guidance, improving fidelity and plausibility simultaneously rather than trading them against each other. Project page: https://flow-bender.github.io/</p></description>
|
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2606.20404</guid>
|
|
||||||
<pubDate>Thu, 18 Jun 2026 00:00:00 +0000</pubDate>
|
|
||||||
</item>
|
|
||||||
<item>
|
|
||||||
<title>FreeStyle: Free Control of Style-Content Dual-Reference Generation from Community LoRA Mining</title>
|
|
||||||
<link>https://arxiv.org/abs/2606.20506</link>
|
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2606.20506.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jinghong Lan, Wei Cheng, Yunuo Chen, Ziqi Ye, Peng Xing, Yixiao Fang, Rui Wang, Yufeng Yang, Xuanyang Zhang, Xianfang Zeng, Difan Zou, Gang Yu, Chi Zhang</p><p><b>Upvotes:</b> 25</p><p><b>Summary:</b> Style-content dual-reference generation aims to synthesize an image that preserves the structure and semantics of a content reference while adopting the style of a separate style reference.Despite recent progress, this setting remains challenging because models must balance content fidelity, style alignment, and instruction following avoiding semantic leakage from the style reference.A key bottleneck is the lack of large-scale triplet data with clean content-style separation and broad long-tail style coverage.In this work, we propose FreeStyle, a scalable dual-reference generation framework based on community LoRA mining.We treat community LoRAs as compositional anchors for style and content, and design a rigorous generation and filtering pipeline to construct large-scale Style-Reference and Content-Reference triplets across multiple base models.To address content leakage, we adopt a two-stage curriculum with stage-specific disentanglement mechanisms: an attention-level enrichment constraint that suppresses style-reference leakage in the style-transfer stage, and a frequency-aware RoPE modulation strategy that targets positional-correspondence-based leakage in the harder dual-reference stage.We also introduce a benchmark covering both style-reference and dual-reference generation, with evaluations on style similarity, content preservation, aesthetics, instruction following, and leakage rejection. The benchmark incorporates a style-invariant Content Alignment Score (CAS) and introduces a calibrated VLM-based Rejection Score for evaluating generation reliability and leakage suppression.Extensive experiments show that our model achieves a strong balance among style alignment, content preservation, and leakage suppression.</p></description>
|
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2606.20506</guid>
|
|
||||||
<pubDate>Thu, 18 Jun 2026 00:00:00 +0000</pubDate>
|
|
||||||
</item>
|
|
||||||
<item>
|
|
||||||
<title>Beyond Static Leaderboards: Predictive Validity for the Evaluation of LLM Agents</title>
|
|
||||||
<link>https://arxiv.org/abs/2606.19704</link>
|
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2606.19704.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Dhaval C. Patel, Kaoutar El Maghraoui, Shuxin Lin, Yusheng Li, Tianjun Feng, Chun-Yi Tsai, Yihan Sun, Wei Alexander Xin, Akshat Bhandari, Tanisha Rathod, Aaron Fan, Sanskruti Vijay Shejwal, Tomas Pasiecznik, Sagar Chethan Kumar, Tanmay Agarwal, Rohith Kanathur, Sam Colman, Amaan Sheikh, Dev Bahl, Ann Li, Krish Veera, Alimurtaza Mustafa Merchant, Shambhawi Baswaraj Bhure, Sajal Kumar Goyla, Chengrui Li, Kirthana Natarajan, Rui Li, Thomas Ajai, Rujing Li, Vivek G. Iyer, Sanjaii Vijayakumar, Yitong Bai, Ayal Yakobe, Darief Maes, Yassine Jebbouri, Tianyang Xu, Thai Quoc On, Vera Mazeeva, Winston Li, Yuval Shemla, Yeshitha Bhuvanesh, Rushin Bhatt, Siddharth Chethan Gowda, Alisha Vinod, Caroline Cahill, Shriya Aishani Rachakonda, Yunfeng Chen, Aryaman Agrawal, Aman Upganlawar, Mao Le Jonathan Ang, Yubin Sally Go, Madhav Rajkondawar, Yang-Jung Chen, Trisha Maturi, Ananya Kapoor, Andrew Li, Shrey Arora, Mana Abbaszadeh, Shen Li, Charles Xu, Byeolah Kwon</p><p><b>Upvotes:</b> 29</p><p><b>Summary:</b> Agent benchmarks are growing fast, but no single benchmark touches more than four or five of the dimensions that deployment exposes. This paper aggregates the largest coordinated deep-dive of one MCP-based industrial-agent benchmark to date: fourteen parallel implementation studies covering new asset classes (including a multi-modal visual extension), alternative orchestrations, retrieval strategies, reasoning modes, infrastructure optimizations, and evaluation-methodology probes. Consolidating those studies with seven prior agent benchmarks, we argue that aggregate-score leaderboards systematically underspecify deployed-agent evaluation. Rankings derived from aggregate scores do not transfer to out-of-distribution settings; recent public-to-hidden competition retrospectives provide direct empirical evidence of this rank instability. We propose ranking configurations by predictive validity, the correlation between in-sample and out-of-sample rank, rather than in-sample mean, and report a twelve-tier measurement apparatus that exposes the deployment-relevant dimensions HELM and its agent-era successors collapse. The position is operationalized through three falsifiable out-of-distribution criteria with explicit thresholds; existing evidence partly supports it but is too thin to confirm. We close with a pre-registered pilot design and a field-level vision for what the next generation of agentic benchmarks should report.</p></description>
|
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2606.19704</guid>
|
|
||||||
<pubDate>Thu, 18 Jun 2026 00:00:00 +0000</pubDate>
|
|
||||||
</item>
|
|
||||||
<item>
|
|
||||||
<title>DF3DV-1K: A Large-Scale Dataset and Benchmark for Distractor-Free Novel View Synthesis</title>
|
|
||||||
<link>https://arxiv.org/abs/2604.13416</link>
|
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.13416.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Cheng-You Lu, Yi-Shan Hung, Wei-Ling Chi, Hao-Ping Wang, Charlie Li-Ting Tsai, Yu-Cheng Chang, Yu-Lun Liu, Thomas Do, Chin-Teng Lin</p><p><b>Upvotes:</b> 29</p><p><b>Summary:</b> Advances in radiance fields have enabled photorealistic novel view synthesis. In several domains, large-scale real-world datasets have been developed to support comprehensive benchmarking and to facilitate progress beyond scene-specific reconstruction. However, for distractor-free radiance fields, a large-scale dataset with clean and cluttered images per scene remains lacking, limiting the development. To address this gap, we introduce DF3DV-1K, a large-scale real-world dataset comprising 1,048 scenes, each providing clean and cluttered image sets for benchmarking. In total, the dataset contains 89,924 images captured using consumer cameras to mimic casual capture, spanning 128 distractor types and 161 scene themes across indoor and outdoor environments. A curated subset of 41 scenes, DF3DV-41, is systematically designed to evaluate the robustness of distractor-free radiance field methods under challenging scenarios. Using DF3DV-1K, we benchmark nine recent distractor-free radiance field methods and 3D Gaussian Splatting, identifying the most robust methods and the most challenging scenarios. Beyond benchmarking, we demonstrate an application of DF3DV-1K by fine-tuning a diffusion-based 2D enhancer to improve radiance field methods, achieving average improvements of 0.96 dB PSNR and 0.057 LPIPS on the held-out set (e.g., DF3DV-41) and the On-the-go dataset. We hope DF3DV-1K facilitates the development of distractor-free vision and promotes progress beyond scene-specific approaches. The dataset and leaderboard are available at https://johnnylu305.github.io/df3dv1k_web/.</p></description>
|
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2604.13416</guid>
|
|
||||||
<pubDate>Thu, 18 Jun 2026 00:00:00 +0000</pubDate>
|
|
||||||
</item>
|
|
||||||
<item>
|
|
||||||
<title>S-Agent: Spatial Tool-Use Elicits Reasoning for Spatial Intelligence</title>
|
|
||||||
<link>https://arxiv.org/abs/2606.20515</link>
|
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2606.20515.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yalun Dai, Hao Li, Shulin Tian, Runmao Yao, Yuhao Dong, Fangzhou Hong, Zhaoxi Chen, Fangfu Liu, Baoliang Tian, Dingwen Zhang, Tao Wang, Kim-Hui Yap, Ziwei Liu</p><p><b>Upvotes:</b> 35</p><p><b>Summary:</b> Real-world spatial intelligence requires reasoning over a continuous and evolving 3D world, yet existing VLMs and tool-augmented agents largely remain tied to static, stateless inference from isolated visual observations. We introduce \textsc{S-Agent}, a spatial tool-use agentic paradigm for understanding and reasoning over continuous multi-view images and videos. By formulating spatial reasoning as spatio-temporal evidence accumulation rather than isolated frame-level prediction, S-Agent reshapes spatial perception into scene-centric understanding beyond frame-centric recognition. Specifically, S-Agent casts the VLM as a semantic planner that decides what evidence is needed, while a hierarchy of spatial tools and experts grounds objects in 2D, lifts them into 3D geometric evidence, and aggregates this evidence into high-level spatial knowledge (e.g., counting, measurement, orientation, and relative position). Additionally, a temporal memory mechanism, including Scene Memory for maintaining the evolving scene state and Agent Memory for accumulating reasoning context, enables evidence integration across frames and reasoning steps. Comprehensive experiments on multi-view and video spatial reasoning benchmarks show that S-Agent consistently improves both open-source and closed-source VLMs in a training-free manner. Beyond inference-time augmentation, supervised fine-tuning (SFT) on S-Agent-generated spatial trajectories S-300K yields S-Agent-8B, a compact spatial agent that significantly surpasses similar-scale baselines (e.g., Qwen3-VL-8B) and performs comparably to advanced closed-source models (e.g., GPT-5.4 and Gemini 3).</p></description>
|
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2606.20515</guid>
|
|
||||||
<pubDate>Thu, 18 Jun 2026 00:00:00 +0000</pubDate>
|
|
||||||
</item>
|
|
||||||
<item>
|
|
||||||
<title>Multi-LCB: Extending LiveCodeBench to Multiple Programming Languages</title>
|
|
||||||
<link>https://arxiv.org/abs/2606.20517</link>
|
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2606.20517.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Maria Ivanova, Pavel Zadorozhny, Rodion Levichev, Ivan Petrov, Adamenko Pavel, Ivan Lopatin, Alexey Kutalev, Dmitrii Babaev</p><p><b>Upvotes:</b> 49</p><p><b>Summary:</b> LiveCodeBench (LCB) has recently become a widely adopted benchmark for evaluating large language models (LLMs) on code-generation tasks. By curating competitive programming problems, constantly adding fresh problems to the set, and filtering them by release dates, LCB provides contamination-aware evaluation and offers a holistic view of coding capability. However, LCB remains restricted to Python, leaving open the question of whether LLMs can generalize across the diverse programming languages required in real-world software engineering. We introduce Multi-LCB, a benchmark for evaluating LLMs across twelve programming languages, including Python. Multi-LCB transforms Python tasks from the LCB dataset into equivalent tasks in other languages while preserving LCB's contamination controls and evaluation protocol. Because it is fully compatible with the original LCB format, Multi-LCB will automatically track future LCB updates, enabling systematic assessment of cross-language code generation competence and requiring models to sustain performance well beyond Python. We evaluated 24 LLMs for instruction and reasoning on Multi-LCB, uncovering evidence of Python overfitting, language-specific contamination, and substantial disparities in multilingual performance. Our results establish Multi-LCB as a rigorous new benchmark for multi-programming-language code evaluation, directly addressing LCB's primary limitation and exposing critical gaps in current LLM capabilities.</p></description>
|
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2606.20517</guid>
|
|
||||||
<pubDate>Thu, 18 Jun 2026 00:00:00 +0000</pubDate>
|
<pubDate>Thu, 18 Jun 2026 00:00:00 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
</channel>
|
</channel>
|
||||||
|
|||||||
Reference in New Issue
Block a user