bot: update RSS feed
This commit is contained in:
github-actions[bot]
278
feed.xml
278
feed.xml
@@ -7,111 +7,237 @@
|
||||
<docs>http://www.rssboard.org/rss-specification</docs>
|
||||
<generator>python-feedgen</generator>
|
||||
<language>en</language>
|
||||
<lastBuildDate>Tue, 31 Mar 2026 00:07:22 +0000</lastBuildDate>
|
||||
<lastBuildDate>Wed, 01 Apr 2026 00:07:59 +0000</lastBuildDate>
|
||||
<item>
|
||||
<title>Sommelier: Scalable Open Multi-turn Audio Pre-processing for Full-duplex Speech Language Models</title>
|
||||
<link>https://arxiv.org/abs/2603.25750</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.25750.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Kyudan Jung, Jihwan Kim, Soyoon Kim, Jeongoon Kim, Jaegul Choo, Cheonbok Park</p><p><b>Upvotes:</b> 8</p><p><b>Summary:</b> As the paradigm of AI shifts from text-based LLMs to Speech Language Models (SLMs), there is a growing demand for full-duplex systems capable of real-time, natural human-computer interaction. However, the development of such models is constrained by the scarcity of high-quality, multi-speaker conversational data, as existing large-scale resources are predominantly single-speaker or limited in volume. Addressing the complex dynamics of natural dialogue, such as overlapping and back-channeling remains a challenge, with standard processing pipelines suffering from diarization errors and ASR hallucinations. To bridge this gap, we present a robust and scalable open-source data processing pipeline designed for full-duplex model.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.25750</guid>
|
||||
<pubDate>Fri, 20 Mar 2026 09:10:43 +0000</pubDate>
|
||||
<title>SEAR: Schema-Based Evaluation and Routing for LLM Gateways</title>
|
||||
<link>https://arxiv.org/abs/2603.26728</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.26728.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zecheng Zhang, Han Zheng, Yue Xu</p><p><b>Upvotes:</b> 6</p><p><b>Summary:</b> Evaluating production LLM responses and routing requests across providers in LLM gateways requires fine-grained quality signals and operationally grounded decisions. To address this gap, we present SEAR, a schema-based evaluation and routing system for multi-model, multi-provider LLM gateways. SEAR defines an extensible relational schema covering both LLM evaluation signals (context, intent, response characteristics, issue attribution, and quality scores) and gateway operational metrics (latency, cost, throughput), with cross-table consistency links across around one hundred typed, SQL-queryable columns. To populate the evaluation signals reliably, SEAR proposes self-contained signal instructions, in-schema reasoning, and multi-stage generation that produces database-ready structured outputs. Because signals are derived through LLM reasoning rather than shallow classifiers, SEAR captures complex request semantics, enables human-interpretable routing explanations, and unifies evaluation and routing in a single query layer. Across thousands of production sessions, SEAR achieves strong signal accuracy on human-labeled data and supports practical routing decisions, including large cost reductions with comparable quality.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.26728</guid>
|
||||
<pubDate>Fri, 20 Mar 2026 04:51:35 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>Diffutron: A Masked Diffusion Language Model for Turkish Language</title>
|
||||
<link>https://arxiv.org/abs/2603.20466</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.20466.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Şuayp Talha Kocabay, Talha Rüzgar Akkuş</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Masked Diffusion Language Models (MDLMs) have emerged as a compelling non-autoregressive alternative to standard large language models; however, their application to morphologically rich languages remains limited. In this paper, we introduce Diffutron, a masked diffusion language model specifically designed for Turkish. Our approach leverages a resource-efficient training pipeline, starting with LoRA-based continual pre-training of a multilingual encoder on a large-scale corpus. To enable generative capabilities, we employ a progressive instruction-tuning strategy, sequentially adapting the model on general and task-specific instruction sets. Experimental results across comprehensive benchmarks demonstrate that, despite its compact size, our model achieves competitive performance compared to existing multi-billion-parameter baselines. These findings validate the effectiveness of masked diffusion modeling combined with multi-stage tuning for non-autoregressive text generation in Turkish.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.20466</guid>
|
||||
<pubDate>Fri, 20 Mar 2026 19:52:37 +0000</pubDate>
|
||||
<title>Density-aware Soft Context Compression with Semi-Dynamic Compression Ratio</title>
|
||||
<link>https://arxiv.org/abs/2603.25926</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.25926.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yijiong Yu, Shuai Yuan, Jie Zheng, Huazheng Wang, Ji Pei</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> Soft context compression reduces the computational workload of processing long contexts in LLMs by encoding long context into a smaller number of latent tokens. However, existing frameworks apply uniform compression ratios, failing to account for the extreme variance in natural language information density. While adopting a density-aware dynamic compression ratio seems intuitive, empirical investigations reveal that models struggle intrinsically with operations parameterized by input dependent, continuous structural hyperparameters. To resolve this pitfall, we introduce Semi-Dynamic Context Compression framework. Our approach features a Discrete Ratio Selector, which predicts a compression target based on intrinsic information density and quantizes it to a predefined set of discrete compression ratios. It is efficiently jointly trained with the compressor on synthetic data, with the summary lengths as a proxy to create labels for compression ratio prediction. Extensive evaluations confirm that our density-aware framework, utilizing mean pooling as the backbone, consistently outperforms static baselines, establishing a robust Pareto frontier for context compression techniques. Our code, data and model weights are available at https://github.com/yuyijiong/semi-dynamic-context-compress</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.25926</guid>
|
||||
<pubDate>Thu, 26 Mar 2026 21:36:55 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>Lie to Me: How Faithful Is Chain-of-Thought Reasoning in Reasoning Models?</title>
|
||||
<link>https://arxiv.org/abs/2603.22582</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.22582.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Richard J. Young</p><p><b>Upvotes:</b> 0</p><p><b>Summary:</b> Chain-of-thought (CoT) reasoning has been proposed as a transparency mechanism for large language models in safety-critical deployments, yet its effectiveness depends on faithfulness (whether models accurately verbalize the factors that actually influence their outputs), a property that prior evaluations have examined in only two proprietary models, finding acknowledgment rates as low as 25% for Claude 3.7 Sonnet and 39% for DeepSeek-R1. To extend this evaluation across the open-weight ecosystem, this study tests 12 open-weight reasoning models spanning 9 architectural families (7B-685B parameters) on 498 multiple-choice questions from MMLU and GPQA Diamond, injecting six categories of reasoning hints (sycophancy, consistency, visual pattern, metadata, grader hacking, and unethical information) and measuring the rate at which models acknowledge hint influence in their CoT when hints successfully alter answers. Across 41,832 inference runs, overall faithfulness rates range from 39.7% (Seed-1.6-Flash) to 89.9% (DeepSeek-V3.2-Speciale) across model families, with consistency hints (35.5%) and sycophancy hints (53.9%) exhibiting the lowest acknowledgment rates. Training methodology and model family predict faithfulness more strongly than parameter count, and keyword-based analysis reveals a striking gap between thinking-token acknowledgment (approximately 87.5%) and answer-text acknowledgment (approximately 28.6%), suggesting that models internally recognize hint influence but systematically suppress this acknowledgment in their outputs. These findings carry direct implications for the viability of CoT monitoring as a safety mechanism and suggest that faithfulness is not a fixed property of reasoning models but varies systematically with architecture, training method, and the nature of the influencing cue.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.22582</guid>
|
||||
<pubDate>Mon, 23 Mar 2026 21:21:37 +0000</pubDate>
|
||||
<title>Think over Trajectories: Leveraging Video Generation to Reconstruct GPS Trajectories from Cellular Signaling</title>
|
||||
<link>https://arxiv.org/abs/2603.26610</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.26610.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ruixing Zhang, Hanzhang Jiang, Leilei Sun, Liangzhe Han, Jibin Wang, Weifeng Lv</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Mobile devices continuously interact with cellular base stations, generating massive volumes of signaling records that provide broad coverage for understanding human mobility. However, such records offer only coarse location cues (e.g., serving-cell identifiers) and therefore limit their direct use in applications that require high-precision GPS trajectories. This paper studies the Sig2GPS problem: reconstructing GPS trajectories from cellular signaling. Inspired by domain experts often lay the signaling trace on the map and sketch the corresponding GPS route, unlike conventional solutions that rely on complex multi-stage engineering pipelines or regress coordinates, Sig2GPS is reframed as an image-to-video generation task that directly operates in the map-visual domain: signaling traces are rendered on a map, and a video generation model is trained to draw a continuous GPS path. To support this paradigm, a paired signaling-to-trajectory video dataset is constructed to fine-tune an open-source video model, and a trajectory-aware reinforcement learning-based optimization method is introduced to improve generation fidelity via rewards. Experiments on large-scale real-world datasets show substantial improvements over strong engineered and learning-based baselines, while additional results on next GPS prediction indicate scalability and cross-city transferability. Overall, these results suggest that map-visual video generation provides a practical interface for trajectory data mining by enabling direct generation and refinement of continuous paths under map constraints.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.26610</guid>
|
||||
<pubDate>Fri, 27 Mar 2026 17:07:13 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>Know3D: Prompting 3D Generation with Knowledge from Vision-Language Models</title>
|
||||
<link>https://arxiv.org/abs/2603.22782</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.22782.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Wenyue Chen, Wenjue Chen, Peng Li, Qinghe Wang, Xu Jia, Heliang Zheng, Rongfei Jia, Yuan Liu, Ronggang Wang</p><p><b>Upvotes:</b> 9</p><p><b>Summary:</b> Recent advances in 3D generation have improved the fidelity and geometric details of synthesized 3D assets. However, due to the inherent ambiguity of single-view observations and the lack of robust global structural priors caused by limited 3D training data, the unseen regions generated by existing models are often stochastic and difficult to control, which may sometimes fail to align with user intentions or produce implausible geometries. In this paper, we propose Know3D, a novel framework that incorporates rich knowledge from multimodal large language models into 3D generative processes via latent hidden-state injection, enabling language-controllable generation of the back-view for 3D assets. We utilize a VLM-diffusion-based model, where the VLM is responsible for semantic understanding and guidance. The diffusion model acts as a bridge that transfers semantic knowledge from the VLM to the 3D generation model. In this way, we successfully bridge the gap between abstract textual instructions and the geometric reconstruction of unobserved regions, transforming the traditionally stochastic back-view hallucination into a semantically controllable process, demonstrating a promising direction for future 3D generation models.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.22782</guid>
|
||||
<pubDate>Tue, 24 Mar 2026 04:18:29 +0000</pubDate>
|
||||
<title>Make Geometry Matter for Spatial Reasoning</title>
|
||||
<link>https://arxiv.org/abs/2603.26639</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.26639.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shihua Zhang, Qiuhong Shen, Shizun Wang, Tianbo Pan, Xinchao Wang</p><p><b>Upvotes:</b> 21</p><p><b>Summary:</b> Empowered by large-scale training, vision-language models (VLMs) achieve strong image and video understanding, yet their ability to perform spatial reasoning in both static scenes and dynamic videos remains limited. Recent advances try to handle this limitation by injecting geometry tokens from pretrained 3D foundation models into VLMs. Nevertheless, we observe that naive token fusion followed by standard fine-tuning in this line of work often leaves such geometric cues underutilized for spatial reasoning, as VLMs tend to rely heavily on 2D visual cues. In this paper, we propose GeoSR, a framework designed to make geometry matter by encouraging VLMs to actively reason with geometry tokens. GeoSR introduces two key components: (1) Geometry-Unleashing Masking, which strategically masks portions of 2D vision tokens during training to weaken non-geometric shortcuts and force the model to consult geometry tokens for spatial reasoning; and (2) Geometry-Guided Fusion, a gated routing mechanism that adaptively amplifies geometry token contributions in regions where geometric evidence is critical. Together, these designs unleash the potential of geometry tokens for spatial reasoning tasks. Extensive experiments on both static and dynamic spatial reasoning benchmarks demonstrate that GeoSR consistently outperforms prior methods and establishes new state-of-the-art performance by effectively leveraging geometric information. The project page is available at https://suhzhang.github.io/GeoSR/.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.26639</guid>
|
||||
<pubDate>Fri, 27 Mar 2026 17:45:12 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>LongTail Driving Scenarios with Reasoning Traces: The KITScenes LongTail Dataset</title>
|
||||
<link>https://arxiv.org/abs/2603.23607</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.23607.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Royden Wagner, Omer Sahin Tas, Jaime Villa, Felix Hauser, Yinzhe Shen, Marlon Steiner, Dominik Strutz, Carlos Fernandez, Christian Kinzig, Guillermo S. Guitierrez-Cabello, Hendrik Königshof, Fabian Immel, Richard Schwarzkopf, Nils Alexander Rack, Kevin Rösch, Kaiwen Wang, Jan-Hendrik Pauls, Martin Lauer, Igor Gilitschenski, Holger Caesar, Christoph Stiller</p><p><b>Upvotes:</b> 12</p><p><b>Summary:</b> In real-world domains such as self-driving, generalization to rare scenarios remains a fundamental challenge. To address this, we introduce a new dataset designed for end-to-end driving that focuses on long-tail driving events. We provide multi-view video data, trajectories, high-level instructions, and detailed reasoning traces, facilitating in-context learning and few-shot generalization. The resulting benchmark for multimodal models, such as VLMs and VLAs, goes beyond safety and comfort metrics by evaluating instruction following and semantic coherence between model outputs. The multilingual reasoning traces in English, Spanish, and Chinese are from domain experts with diverse cultural backgrounds. Thus, our dataset is a unique resource for studying how different forms of reasoning affect driving competence. Our dataset is available at: https://hf.co/datasets/kit-mrt/kitscenes-longtail</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.23607</guid>
|
||||
<pubDate>Tue, 24 Mar 2026 18:00:08 +0000</pubDate>
|
||||
<title>TAPS: Task Aware Proposal Distributions for Speculative Sampling</title>
|
||||
<link>https://arxiv.org/abs/2603.27027</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.27027.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Mohamad Zbib, Mohamad Bazzi, Ammar Mohanna, Hasan Abed Al Kader Hammoud, Bernard Ghanem</p><p><b>Upvotes:</b> 115</p><p><b>Summary:</b> Speculative decoding accelerates autoregressive generation by letting a lightweight draft model propose future tokens that a larger target model then verifies in parallel. In practice, however, draft models are usually trained on broad generic corpora, which leaves it unclear how much speculative decoding quality depends on the draft training distribution. We study this question with lightweight HASS and EAGLE-2 drafters trained on MathInstruct, ShareGPT, and mixed-data variants, evaluated on MT-Bench, GSM8K, MATH-500, and SVAMP. Measured by acceptance length, task-specific training yields clear specialization: MathInstruct-trained drafts are strongest on reasoning benchmarks, while ShareGPT-trained drafts are strongest on MT-Bench. Mixed-data training improves robustness, but larger mixtures do not dominate across decoding temperatures. We also study how to combine specialized drafters at inference time. Naive checkpoint averaging performs poorly, whereas confidence-based routing improves over single-domain drafts and merged-tree verification yields the highest acceptance length overall for both backbones. Finally, confidence is a more useful routing signal than entropy: rejected tokens tend to have higher entropy, but confidence produces much clearer benchmark-level routing decisions. These results show that speculative decoding quality depends not only on draft architecture, but also on the match between draft training data and downstream workload, and that specialized drafters are better combined at inference time than in weight space.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.27027</guid>
|
||||
<pubDate>Fri, 27 Mar 2026 22:34:20 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>GenMask: Adapting DiT for Segmentation via Direct Mask</title>
|
||||
<link>https://arxiv.org/abs/2603.23906</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.23906.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yuhuan Yang, Xianwei Zhuang, Yuxuan Cai, Chaofan Ma, Shuai Bai, Jiangchao Yao, Ya Zhang, Junyang Lin, Yanfeng Wang</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> Recent approaches for segmentation have leveraged pretrained generative models as feature extractors, treating segmentation as a downstream adaptation task via indirect feature retrieval. This implicit use suffers from a fundamental misalignment in representation. It also depends heavily on indirect feature extraction pipelines, which complicate the workflow and limit adaptation. In this paper, we argue that instead of indirect adaptation, segmentation tasks should be trained directly in a generative manner. We identify a key obstacle to this unified formulation: VAE latents of binary masks are sharply distributed, noise robust, and linearly separable, distinct from natural image latents. To bridge this gap, we introduce timesteps sampling strategy for binary masks that emphasizes extreme noise levels for segmentation and moderate noise for image generation, enabling harmonious joint training. We present GenMask, a DiT trains to generate black-and-white segmentation masks as well as colorful images in RGB space under the original generative objective. GenMask preserves the original DiT architecture while removing the need of feature extraction pipelines tailored for segmentation tasks. Empirically, GenMask attains state-of-the-art performance on referring and reasoning segmentation benchmarks and ablations quantify the contribution of each component.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.23906</guid>
|
||||
<pubDate>Wed, 25 Mar 2026 03:52:05 +0000</pubDate>
|
||||
<title>Unified Number-Free Text-to-Motion Generation Via Flow Matching</title>
|
||||
<link>https://arxiv.org/abs/2603.27040</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.27040.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Guanhe Huang, Oya Celiktutan</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Generative models excel at motion synthesis for a fixed number of agents but struggle to generalize with variable agents. Based on limited, domain-specific data, existing methods employ autoregressive models to generate motion recursively, which suffer from inefficiency and error accumulation. We propose Unified Motion Flow (UMF), which consists of Pyramid Motion Flow (P-Flow) and Semi-Noise Motion Flow (S-Flow). UMF decomposes the number-free motion generation into a single-pass motion prior generation stage and multi-pass reaction generation stages. Specifically, UMF utilizes a unified latent space to bridge the distribution gap between heterogeneous motion datasets, enabling effective unified training. For motion prior generation, P-Flow operates on hierarchical resolutions conditioned on different noise levels, thereby mitigating computational overheads. For reaction generation, S-Flow learns a joint probabilistic path that adaptively performs reaction transformation and context reconstruction, alleviating error accumulation. Extensive results and user studies demonstrate UMF' s effectiveness as a generalist model for multi-person motion generation from text. Project page: https://githubhgh.github.io/umf/.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.27040</guid>
|
||||
<pubDate>Fri, 27 Mar 2026 23:10:56 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>Composer 2 Technical Report</title>
|
||||
<link>https://arxiv.org/abs/2603.24477</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.24477.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Cursor Research, Aaron Chan, Ahmed Shalaby, Alexander Wettig, Aman Sanger, Andrew Zhai, Anurag Ajay, Ashvin Nair, Charlie Snell, Chen Lu, Chen Shen, Emily Jia, Federico Cassano, Hanpeng Liu, Haoyu Chen, Henry Wildermuth, Jacob Jackson, Janet Li, Jediah Katz, Jiajun Yao, Joey Hejna, Josh Warner, Julius Vering, Kevin Frans, Lee Danilek, Less Wright, Lujing Cen, Luke Melas-Kyriazi, Michael Truell, Michiel de Jong, Naman Jain, Nate Schmidt, Nathan Wang, Niklas Muennighoff, Oleg Rybkin, Paul Loh, Phillip Kravtsov, Rishabh Yadav, Sahil Shah, Sam Kottler, Alexander M Rush, Shengtong Zhang, Shomil Jain, Sriram Sankar, Stefan Heule, Stuart H. Sul, Sualeh Asif, Victor Rong, Wanqi Zhu, William Lin, Yuchen Wu, Yuri Volkov, Yury Zemlyanskiy, Zack Holbrook, Zhiyuan Zhang</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> Composer 2 is a specialized model designed for agentic software engineering. The model demonstrates strong long-term planning and coding intelligence while maintaining the ability to efficiently solve problems for interactive use. The model is trained in two phases: first, continued pretraining to improve the model's knowledge and latent coding ability, followed by large-scale reinforcement learning to improve end-to-end coding performance through stronger reasoning, accurate multi-step execution, and coherence on long-horizon realistic coding problems. We develop infrastructure to support training in the same Cursor harness that is used by the deployed model, with equivalent tools and structure, and use environments that match real problems closely. To measure the ability of the model on increasingly difficult tasks, we introduce a benchmark derived from real software engineering problems in large codebases including our own. Composer 2 is a frontier-level coding model and demonstrates a process for training strong domain-specialized models. On our CursorBench evaluations the model achieves a major improvement in accuracy compared to previous Composer models (61.3). On public benchmarks the model scores 61.7 on Terminal-Bench and 73.7 on SWE-bench Multilingual in our harness, comparable to state-of-the-art systems.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.24477</guid>
|
||||
<pubDate>Wed, 25 Mar 2026 16:18:37 +0000</pubDate>
|
||||
<title>MOOZY: A Patient-First Foundation Model for Computational Pathology</title>
|
||||
<link>https://arxiv.org/abs/2603.27048</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.27048.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yousef Kotp, Vincent Quoc-Huy Trinh, Christopher Pal, Mahdi S. Hosseini</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Computational pathology needs whole-slide image (WSI) foundation models that transfer across diverse clinical tasks, yet current approaches remain largely slide-centric, often depend on private data and expensive paired-report supervision, and do not explicitly model relationships among multiple slides from the same patient. We present MOOZY, a patient-first pathology foundation model in which the patient case, not the individual slide, is the core unit of representation. MOOZY explicitly models dependencies across all slides from the same patient via a case transformer during pretraining, combining multi-stage open self-supervision with scaled low-cost task supervision. In Stage 1, we pretrain a vision-only slide encoder on 77,134 public slide feature grids using masked self-distillation. In Stage 2, we align these representations with clinical semantics using a case transformer and multi-task supervision over 333 tasks from 56 public datasets, including 205 classification and 128 survival tasks across four endpoints. Across eight held-out tasks with five-fold frozen-feature probe evaluation, MOOZY achieves best or tied-best performance on most metrics and improves macro averages over TITAN by +7.37%, +5.50%, and +7.83% and over PRISM by +8.83%, +10.70%, and +9.78% for weighted F1, weighted ROC-AUC, and balanced accuracy, respectively. MOOZY is also parameter efficient with 85.77M parameters, 14x smaller than GigaPath. These results demonstrate that open, reproducible patient-level pretraining yields transferable embeddings, providing a practical path toward scalable patient-first histopathology foundation models.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.27048</guid>
|
||||
<pubDate>Fri, 27 Mar 2026 23:33:33 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>MedOpenClaw: Auditable Medical Imaging Agents Reasoning over Uncurated Full Studies</title>
|
||||
<link>https://arxiv.org/abs/2603.24649</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.24649.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Weixiang Shen, Yanzhu Hu, Che Liu, Junde Wu, Jiayuan Zhu, Chengzhi Shen, Min Xu, Yueming Jin, Benedikt Wiestler, Daniel Rueckert, Jiazhen Pan</p><p><b>Upvotes:</b> 21</p><p><b>Summary:</b> Currently, evaluating vision-language models (VLMs) in medical imaging tasks oversimplifies clinical reality by relying on pre-selected 2D images that demand significant manual labor to curate. This setup misses the core challenge of realworld diagnostics: a true clinical agent must actively navigate full 3D volumes across multiple sequences or modalities to gather evidence and ultimately support a final decision. To address this, we propose MEDOPENCLAW, an auditable runtime designed to let VLMs operate dynamically within standard medical tools or viewers (e.g., 3D Slicer). On top of this runtime, we introduce MEDFLOWBENCH, a full-study medical imaging benchmark covering multi-sequence brain MRI and lung CT/PET. It systematically evaluates medical agentic capabilities across viewer-only, tool-use, and open-method tracks. Initial results reveal a critical insight: while state-of-the-art LLMs/VLMs (e.g., Gemini 3.1 Pro and GPT-5.4) can successfully navigate the viewer to solve basic study-level tasks, their performance paradoxically degrades when given access to professional support tools due to a lack of precise spatial grounding. By bridging the gap between static-image perception and interactive clinical workflows, MEDOPENCLAW and MEDFLOWBENCH establish a reproducible foundation for developing auditable, full-study medical imaging agents.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.24649</guid>
|
||||
<pubDate>Wed, 25 Mar 2026 17:33:58 +0000</pubDate>
|
||||
<title>Text Data Integration</title>
|
||||
<link>https://arxiv.org/abs/2603.27055</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.27055.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Md Ataur Rahman, Dimitris Sacharidis, Oscar Romero, Sergi Nadal</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Data comes in many forms. From a shallow perspective, they can be viewed as being either in structured (e.g., as a relation, as key-value pairs) or unstructured (e.g., text, image) formats. So far, machines have been fairly good at processing and reasoning over structured data that follows a precise schema. However, the heterogeneity of data poses a significant challenge on how well diverse categories of data can be meaningfully stored and processed. Data Integration, a crucial part of the data engineering pipeline, addresses this by combining disparate data sources and providing unified data access to end-users. Until now, most data integration systems have leaned on only combining structured data sources. Nevertheless, unstructured data (a.k.a. free text) also contains a plethora of knowledge waiting to be utilized. Thus, in this chapter, we firstly make the case for the integration of textual data, to later present its challenges, state of the art and open problems.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.27055</guid>
|
||||
<pubDate>Sat, 28 Mar 2026 00:03:41 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>Trace2Skill: Distill Trajectory-Local Lessons into Transferable Agent Skills</title>
|
||||
<link>https://arxiv.org/abs/2603.25158</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.25158.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jingwei Ni, Yihao Liu, Xinpeng Liu, Yutao Sun, Mengyu Zhou, Pengyu Cheng, Dexin Wang, Xiaoxi Jiang, Guanjun Jiang</p><p><b>Upvotes:</b> 33</p><p><b>Summary:</b> Equipping Large Language Model (LLM) agents with domain-specific skills is critical for tackling complex tasks. Yet, manual authoring creates a severe scalability bottleneck. Conversely, automated skill generation often yields fragile or fragmented results because it either relies on shallow parametric knowledge or sequentially overfits to non-generalizable trajectory-local lessons. To overcome this, we introduce Trace2Skill, a framework that mirrors how human experts author skills: by holistically analyzing broad execution experience before distilling it into a single, comprehensive guide. Instead of reacting sequentially to individual trajectories, Trace2Skill dispatches a parallel fleet of sub-agents to analyze a diverse pool of executions. It extracts trajectory-specific lessons and hierarchically consolidates them into a unified, conflict-free skill directory via inductive reasoning. Trace2Skill supports both deepening existing human-written skills and creating new ones from scratch. Experiments in challenging domains, such as spreadsheet, VisionQA and math reasoning, show that Trace2Skill significantly improves upon strong baselines, including Anthropic's official xlsx skills. Crucially, this trajectory-grounded evolution does not merely memorize task instances or model-specific quirks: evolved skills transfer across LLM scales and generalize to OOD settings. For example, skills evolved by Qwen3.5-35B on its own trajectories improved a Qwen3.5-122B agent by up to 57.65 absolute percentage points on WikiTableQuestions. Ultimately, our results demonstrate that complex agent experience can be packaged into highly transferable, declarative skills -- requiring no parameter updates, no external retrieval modules, and utilizing open-source models as small as 35B parameters.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.25158</guid>
|
||||
<pubDate>Thu, 26 Mar 2026 08:26:38 +0000</pubDate>
|
||||
<title>ChartNet: A Million-Scale, High-Quality Multimodal Dataset for Robust Chart Understanding</title>
|
||||
<link>https://arxiv.org/abs/2603.27064</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.27064.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jovana Kondic, Pengyuan Li, Dhiraj Joshi, Isaac Sanchez, Ben Wiesel, Shafiq Abedin, Amit Alfassy, Eli Schwartz, Daniel Caraballo, Yagmur Gizem Cinar, Florian Scheidegger, Steven I. Ross, Daniel Karl I. Weidele, Hang Hua, Ekaterina Arutyunova, Roei Herzig, Zexue He, Zihan Wang, Xinyue Yu, Yunfei Zhao, Sicong Jiang, Minghao Liu, Qunshu Lin, Peter Staar, Luis Lastras, Aude Oliva, Rogerio Feris</p><p><b>Upvotes:</b> 11</p><p><b>Summary:</b> Understanding charts requires models to jointly reason over geometric visual patterns, structured numerical data, and natural language -- a capability where current vision-language models (VLMs) remain limited. We introduce ChartNet, a high-quality, million-scale multimodal dataset designed to advance chart interpretation and reasoning. ChartNet leverages a novel code-guided synthesis pipeline to generate 1.5 million diverse chart samples spanning 24 chart types and 6 plotting libraries. Each sample consists of five aligned components: plotting code, rendered chart image, data table, natural language summary, and question-answering with reasoning, providing fine-grained cross-modal alignment. To capture the full spectrum of chart comprehension, ChartNet additionally includes specialized subsets encompassing human annotated data, real-world data, safety, and grounding. Moreover, a rigorous quality-filtering pipeline ensures visual fidelity, semantic accuracy, and diversity across chart representations. Fine-tuning on ChartNet consistently improves results across benchmarks, demonstrating its utility as large-scale supervision for multimodal models. As the largest open-source dataset of its kind, ChartNet aims to support the development of foundation models with robust and generalizable capabilities for data visualization understanding. The dataset is publicly available at https://huggingface.co/datasets/ibm-granite/ChartNet</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.27064</guid>
|
||||
<pubDate>Sat, 28 Mar 2026 00:45:05 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>Out of Sight but Not Out of Mind: Hybrid Memory for Dynamic Video World Models</title>
|
||||
<link>https://arxiv.org/abs/2603.25716</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.25716.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Kaijin Chen, Dingkang Liang, Xin Zhou, Yikang Ding, Xiaoqiang Liu, Pengfei Wan, Xiang Bai</p><p><b>Upvotes:</b> 133</p><p><b>Summary:</b> Video world models have shown immense potential in simulating the physical world, yet existing memory mechanisms primarily treat environments as static canvases. When dynamic subjects hide out of sight and later re-emerge, current methods often struggle, leading to frozen, distorted, or vanishing subjects. To address this, we introduce Hybrid Memory, a novel paradigm requiring models to simultaneously act as precise archivists for static backgrounds and vigilant trackers for dynamic subjects, ensuring motion continuity during out-of-view intervals. To facilitate research in this direction, we construct HM-World, the first large-scale video dataset dedicated to hybrid memory. It features 59K high-fidelity clips with decoupled camera and subject trajectories, encompassing 17 diverse scenes, 49 distinct subjects, and meticulously designed exit-entry events to rigorously evaluate hybrid coherence. Furthermore, we propose HyDRA, a specialized memory architecture that compresses memory into tokens and utilizes a spatiotemporal relevance-driven retrieval mechanism. By selectively attending to relevant motion cues, HyDRA effectively preserves the identity and motion of hidden subjects. Extensive experiments on HM-World demonstrate that our method significantly outperforms state-of-the-art approaches in both dynamic subject consistency and overall generation quality.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.25716</guid>
|
||||
<pubDate>Thu, 26 Mar 2026 17:56:01 +0000</pubDate>
|
||||
<title>Story2Proposal: A Scaffold for Structured Scientific Paper Writing</title>
|
||||
<link>https://arxiv.org/abs/2603.27065</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.27065.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhuoyang Qian, Wei Shi, Xu Lin, Li Ling, Meng Luo, Ziming Wang, Zhiwei Zhang, Tengyue Xu, Gaoge Liu, Zhentao Zhang, Shuo Zhang, Ziqi Wang, Zheng Feng, Yan Luo, Shu Xu, Yongjin Chen, Zhibo Feng, Zhuo Chen, Bruce Yuan, Biao Wu, Harry Wang, Kris Chen</p><p><b>Upvotes:</b> 9</p><p><b>Summary:</b> Generating scientific manuscripts requires maintaining alignment between narrative reasoning, experimental evidence, and visual artifacts across the document lifecycle. Existing language-model generation pipelines rely on unconstrained text synthesis with validation applied only after generation, often producing structural drift, missing figures or tables, and cross-section inconsistencies. We introduce Story2Proposal, a contract-governed multi-agent framework that converts a research story into a structured manuscript through coordinated agents operating under a persistent shared visual contract. The system organizes architect, writer, refiner, and renderer agents around a contract state that tracks section structure and registered visual elements, while evaluation agents supply feedback in a generate evaluate adapt loop that updates the contract during generation. Experiments on tasks derived from the Jericho research corpus show that Story2Proposal achieved an expert evaluation score of 6.145 versus 3.963 for DirectChat (+2.182) across GPT, Claude, Gemini, and Qwen backbones. Compared with the structured generation baseline Fars, Story2Proposal obtained an average score of 5.705 versus 5.197, indicating improved structural consistency and visual alignment.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.27065</guid>
|
||||
<pubDate>Sat, 28 Mar 2026 00:46:14 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>Natural-Language Agent Harnesses</title>
|
||||
<link>https://arxiv.org/abs/2603.25723</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.25723.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Linyue Pan, Lexiao Zou, Shuo Guo, Jingchen Ni, Hai-Tao Zheng</p><p><b>Upvotes:</b> 11</p><p><b>Summary:</b> Agent performance increasingly depends on harness engineering, yet harness design is usually buried in controller code and runtime-specific conventions, making it hard to transfer, compare, and study as a scientific object. We ask whether the high-level control logic of an agent harness can instead be externalized as a portable executable artifact. We introduce Natural-Language Agent Harnesses (NLAHs), which express harness behavior in editable natural language, and Intelligent Harness Runtime (IHR), a shared runtime that executes these harnesses through explicit contracts, durable artifacts, and lightweight adapters. Across coding and computer-use benchmarks, we conduct controlled evaluations of operational viability, module ablation, and code-to-text harness migration.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.25723</guid>
|
||||
<pubDate>Thu, 26 Mar 2026 17:58:15 +0000</pubDate>
|
||||
<title>EpochX: Building the Infrastructure for an Emergent Agent Civilization</title>
|
||||
<link>https://arxiv.org/abs/2603.27304</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.27304.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Huacan Wang, Chaofa Yuan, Xialie Zhuang, Tu Hu, Shuo Zhang, Jun Han, Shi Wei, Daiqiang Li, Jingping Liu, Kunyi Wang, Zihan Yin, Zhenheng Tang, Andy Wang, Henry Peng Zou, Philip S. Yu, Sen Hu, Qizhen Lan, Ronghao Chen</p><p><b>Upvotes:</b> 39</p><p><b>Summary:</b> General-purpose technologies reshape economies less by improving individual tools than by enabling new ways to organize production and coordination. We believe AI agents are approaching a similar inflection point: as foundation models make broad task execution and tool use increasingly accessible, the binding constraint shifts from raw capability to how work is delegated, verified, and rewarded at scale. We introduce EpochX, a credits-native marketplace infrastructure for human-agent production networks. EpochX treats humans and agents as peer participants who can post tasks or claim them. Claimed tasks can be decomposed into subtasks and executed through an explicit delivery workflow with verification and acceptance. Crucially, EpochX is designed so that each completed transaction can produce reusable ecosystem assets, including skills, workflows, execution traces, and distilled experience. These assets are stored with explicit dependency structure, enabling retrieval, composition, and cumulative improvement over time. EpochX also introduces a native credit mechanism to make participation economically viable under real compute costs. Credits lock task bounties, budget delegation, settle rewards upon acceptance, and compensate creators when verified assets are reused. By formalizing the end-to-end transaction model together with its asset and incentive layers, EpochX reframes agentic AI as an organizational design problem: building infrastructures where verifiable work leaves persistent, reusable artifacts, and where value flows support durable human-agent collaboration.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.27304</guid>
|
||||
<pubDate>Sat, 28 Mar 2026 15:20:48 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>PackForcing: Short Video Training Suffices for Long Video Sampling and Long Context Inference</title>
|
||||
<link>https://arxiv.org/abs/2603.25730</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.25730.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xiaofeng Mao, Shaohao Rui, Kaining Ying, Bo Zheng, Chuanhao Li, Mingmin Chi, Kaipeng Zhang</p><p><b>Upvotes:</b> 38</p><p><b>Summary:</b> Autoregressive video diffusion models have demonstrated remarkable progress, yet they remain bottlenecked by intractable linear KV-cache growth, temporal repetition, and compounding errors during long-video generation. To address these challenges, we present PackForcing, a unified framework that efficiently manages the generation history through a novel three-partition KV-cache strategy. Specifically, we categorize the historical context into three distinct types: (1) Sink tokens, which preserve early anchor frames at full resolution to maintain global semantics; (2) Mid tokens, which achieve a massive spatiotemporal compression (32x token reduction) via a dual-branch network fusing progressive 3D convolutions with low-resolution VAE re-encoding; and (3) Recent tokens, kept at full resolution to ensure local temporal coherence. To strictly bound the memory footprint without sacrificing quality, we introduce a dynamic top-k context selection mechanism for the mid tokens, coupled with a continuous Temporal RoPE Adjustment that seamlessly re-aligns position gaps caused by dropped tokens with negligible overhead. Empowered by this principled hierarchical context compression, PackForcing can generate coherent 2-minute, 832x480 videos at 16 FPS on a single H200 GPU. It achieves a bounded KV cache of just 4 GB and enables a remarkable 24x temporal extrapolation (5s to 120s), operating effectively either zero-shot or trained on merely 5-second clips. Extensive results on VBench demonstrate state-of-the-art temporal consistency (26.07) and dynamic degree (56.25), proving that short-video supervision is sufficient for high-quality, long-video synthesis. https://github.com/ShandaAI/PackForcing</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.25730</guid>
|
||||
<pubDate>Thu, 26 Mar 2026 17:59:05 +0000</pubDate>
|
||||
<title>A Comparative Study in Surgical AI: Datasets, Foundation Models, and Barriers to Med-AGI</title>
|
||||
<link>https://arxiv.org/abs/2603.27341</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.27341.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Kirill Skobelev, Eric Fithian, Yegor Baranovski, Jack Cook, Sandeep Angara, Shauna Otto, Zhuang-Fang Yi, John Zhu, Daniel A. Donoho, X. Y. Han, Neeraj Mainkar, Margaux Masson-Forsythe</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Recent Artificial Intelligence (AI) models have matched or exceeded human experts in several benchmarks of biomedical task performance, but have lagged behind on surgical image-analysis benchmarks. Since surgery requires integrating disparate tasks -- including multimodal data integration, human interaction, and physical effects -- generally-capable AI models could be particularly attractive as a collaborative tool if performance could be improved. On the one hand, the canonical approach of scaling architecture size and training data is attractive, especially since there are millions of hours of surgical video data generated per year. On the other hand, preparing surgical data for AI training requires significantly higher levels of professional expertise, and training on that data requires expensive computational resources. These trade-offs paint an uncertain picture of whether and to-what-extent modern AI could aid surgical practice. In this paper, we explore this question through a case study of surgical tool detection using state-of-the-art AI methods available in 2026. We demonstrate that even with multi-billion parameter models and extensive training, current Vision Language Models fall short in the seemingly simple task of tool detection in neurosurgery. Additionally, we show scaling experiments indicating that increasing model size and training time only leads to diminishing improvements in relevant performance metrics. Thus, our experiments suggest that current models could still face significant obstacles in surgical use cases. Moreover, some obstacles cannot be simply ``scaled away'' with additional compute and persist across diverse model architectures, raising the question of whether data and label availability are the only limiting factors. We discuss the main contributors to these constraints and advance potential solutions.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.27341</guid>
|
||||
<pubDate>Sat, 28 Mar 2026 17:18:40 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>ShotStream: Streaming Multi-Shot Video Generation for Interactive Storytelling</title>
|
||||
<link>https://arxiv.org/abs/2603.25746</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.25746.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yawen Luo, Xiaoyu Shi, Junhao Zhuang, Yutian Chen, Quande Liu, Xintao Wang, Pengfei Wan, Tianfan Xue</p><p><b>Upvotes:</b> 110</p><p><b>Summary:</b> Multi-shot video generation is crucial for long narrative storytelling, yet current bidirectional architectures suffer from limited interactivity and high latency. We propose ShotStream, a novel causal multi-shot architecture that enables interactive storytelling and efficient on-the-fly frame generation. By reformulating the task as next-shot generation conditioned on historical context, ShotStream allows users to dynamically instruct ongoing narratives via streaming prompts. We achieve this by first fine-tuning a text-to-video model into a bidirectional next-shot generator, which is then distilled into a causal student via Distribution Matching Distillation. To overcome the challenges of inter-shot consistency and error accumulation inherent in autoregressive generation, we introduce two key innovations. First, a dual-cache memory mechanism preserves visual coherence: a global context cache retains conditional frames for inter-shot consistency, while a local context cache holds generated frames within the current shot for intra-shot consistency. And a RoPE discontinuity indicator is employed to explicitly distinguish the two caches to eliminate ambiguity. Second, to mitigate error accumulation, we propose a two-stage distillation strategy. This begins with intra-shot self-forcing conditioned on ground-truth historical shots and progressively extends to inter-shot self-forcing using self-generated histories, effectively bridging the train-test gap. Extensive experiments demonstrate that ShotStream generates coherent multi-shot videos with sub-second latency, achieving 16 FPS on a single GPU. It matches or exceeds the quality of slower bidirectional models, paving the way for real-time interactive storytelling. Training and inference code, as well as the models, are available on our</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.25746</guid>
|
||||
<pubDate>Thu, 26 Mar 2026 17:59:59 +0000</pubDate>
|
||||
<title>On Token's Dilemma: Dynamic MoE with Drift-Aware Token Assignment for Continual Learning of Large Vision Language Models</title>
|
||||
<link>https://arxiv.org/abs/2603.27481</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.27481.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Chongyang Zhao, Mingsong Li, Haodong Lu, Dong Gong</p><p><b>Upvotes:</b> 27</p><p><b>Summary:</b> Multimodal Continual Instruction Tuning aims to continually enhance Large Vision Language Models (LVLMs) by learning from new data without forgetting previously acquired knowledge. Mixture of Experts (MoE) architectures naturally facilitate this by incrementally adding new experts and expanding routers while keeping the existing ones frozen. However, despite expert isolation, MoE-based continual learners still suffer from forgetting due to routing-drift: old-task tokens become mistakenly attracted to newly added experts, degrading performance on prior tasks. We analyze the failure mode at the token level and reveal the token's dilemma: ambiguous and old tokens in new-task data offer minimal learning benefit yet induce forgetting when routed to new experts, due to their ambiguous routing assignment during training. Motivated by this, we propose LLaVA-DyMoE, a dynamic MoE framework that incrementally expands the MoE with drift-aware token assignment. We characterize token types via their routing score distributions and apply targeted regularization. Specifically, a token-level assignment guidance steers ambiguous and old tokens away from new experts to preserve established routing patterns and alleviate routing-drift, while complementary routing score regularizations enforce expert-group separation and promote new-expert specialization. Extensive experiments demonstrate that our LLaVA-DyMoE effectively mitigates routing-drift-induced forgetting, achieving over a 7% gain in mean final accuracy and a 12% reduction in forgetting compared to baselines. The project page is https://zhaoc5.github.io/DyMoE.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.27481</guid>
|
||||
<pubDate>Sun, 29 Mar 2026 02:30:55 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>RealChart2Code: Advancing Chart-to-Code Generation with Real Data and Multi-Task Evaluation</title>
|
||||
<link>https://arxiv.org/abs/2603.25804</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.25804.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jiajun Zhang, Yuying Li, Zhixun Li, Xingyu Guo, Jingzhuo Wu, Leqi Zheng, Yiran Yang, Jianke Zhang, Qingbin Li, Shannan Yan, Zhetong Li, Changguo Jia, Junfei Wu, Zilei Wang, Qiang Liu, Liang Wang</p><p><b>Upvotes:</b> 16</p><p><b>Summary:</b> Vision-Language Models (VLMs) have demonstrated impressive capabilities in code generation across various domains. However, their ability to replicate complex, multi-panel visualizations from real-world data remains largely unassessed. To address this gap, we introduce \texttt{RealChart2Code}, a new large-scale benchmark with over 2,800 instances grounded in authentic datasets and featuring tasks with clear analytical intent. Crucially, it is the first benchmark to systematically evaluate chart generation from large-scale raw data and assess iterative code refinement in a multi-turn conversational setting. Our comprehensive evaluation of 14 leading VLMs on RealChart2Code reveals significant performance degradation compared to simpler benchmarks, highlighting their struggles with complex plot structures and authentic data. Our analysis uncovers a substantial performance gap between proprietary and open-weight models and confirms that even state-of-the-art VLMs often fail to accurately replicate intricate, multi-panel charts. These findings provide valuable insights into the current limitations of VLMs and guide future research directions. We release the benchmark and code at https://github.com/Speakn0w/RealChart2Code.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.25804</guid>
|
||||
<pubDate>Thu, 26 Mar 2026 18:11:46 +0000</pubDate>
|
||||
<title>STRIDE: When to Speak Meets Sequence Denoising for Streaming Video Understanding</title>
|
||||
<link>https://arxiv.org/abs/2603.27593</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.27593.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Junho Kim, Hosu Lee, James M. Rehg, Minsu Kim, Yong Man Ro</p><p><b>Upvotes:</b> 0</p><p><b>Summary:</b> Recent progress in video large language models (Video-LLMs) has enabled strong offline reasoning over long and complex videos. However, real-world deployments increasingly require streaming perception and proactive interaction, where video frames arrive online and the system must decide not only what to respond, but also when to respond. In this work, we revisit proactive activation in streaming video as a structured sequence modeling problem, motivated by the observation that temporal transitions in streaming video naturally form span-structured activation patterns. To capture this span-level structure, we model activation signals jointly over a sliding temporal window and update them iteratively as new frames arrive. We propose STRIDE (Structured Temporal Refinement with Iterative DEnoising), which employs a lightweight masked diffusion module at the activation interface to jointly predict and progressively refine activation signals across the window. Extensive experiments on diverse streaming benchmarks and downstream models demonstrate that STRIDE shows more reliable and temporally coherent proactive responses, significantly improving when-to-speak decision quality in online streaming scenarios.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.27593</guid>
|
||||
<pubDate>Sun, 29 Mar 2026 09:23:45 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>Learning to Commit: Generating Organic Pull Requests via Online Repository Memory</title>
|
||||
<link>https://arxiv.org/abs/2603.26664</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.26664.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Mo Li, L. H. Xu, Qitai Tan, Ting Cao, Yunxin Liu</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Large language model (LLM)-based coding agents achieve impressive results on controlled benchmarks yet routinely produce pull requests that real maintainers reject. The root cause is not functional incorrectness but a lack of organicity: generated code ignores project-specific conventions, duplicates functionality already provided by internal APIs, and violates implicit architectural constraints accumulated over years of development. Simply exposing an agent to the latest repository snapshot is not enough: the snapshot reveals the final state of the codebase, but not the repository-specific change patterns by which that state was reached. We introduce Learning to Commit, a framework that closes this gap through Online Repository Memory. Given a repository with a strict chronological split, the agent performs supervised contrastive reflection on earlier commits: it blindly attempts to resolve each historical issue, compares its prediction against the oracle diff, and distils the gap into a continuously growing set of skills-reusable patterns capturing coding style, internal API usage, and architectural invariants. When a new PR description arrives, the agent conditions its generation on these accumulated skills, producing changes grounded in the project's own evolution rather than generic pretraining priors. Evaluation is conducted on genuinely future, merged pull requests that could not have been seen during the skill-building phase, and spans multiple dimensions including functional correctness, code-style consistency, internal API reuse rate, and modified-region plausibility. Experiments on an expert-maintained repository with rich commit history show that Online Repository Memory effectively improves organicity scores on held-out future tasks.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.26664</guid>
|
||||
<pubDate>Fri, 27 Mar 2026 17:58:56 +0000</pubDate>
|
||||
<title>PRBench: End-to-end Paper Reproduction in Physics Research</title>
|
||||
<link>https://arxiv.org/abs/2603.27646</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.27646.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shi Qiu, Junyi Deng, Yiwei Deng, Haoran Dong, Jieyu Fu, Mao Li, Zeyu Li, Zhaolong Zhang, Huiwen Zheng, Leidong Bao, Anqi Lv, Zihan Mo, Yadi Niu, Yiyang Peng, Yu Tian, Yili Wang, Ziyu Wang, Zi-Yu Wang, Jiashen Wei, Liuheng Wu, Aoran Xue, Leyi Yang, Guanglu Yuan, Xiarui Zhan, Jingjun Zhang, Zifan Zheng, Pengfei Liu, Linrui Zhen, Kaiyang Li, Qichang Li, Ziheng Zhou, Guo-En Nian, Yunwei Xiao, Qing-Hong Cao, Linjie Dai, Xu Feng, Peng Gao, Ying Gu, Chang Liu, Jia Liu, Ming-xing Luo, Yan-Qing Ma, Liang-You Peng, Huichao Song, Shufeng Wang, Chenxu Wang, Tao Wang, Yi-Nan Wang, Chengyin Wu, Pengwei Zhao, Hua Xing Zhu</p><p><b>Upvotes:</b> 23</p><p><b>Summary:</b> AI agents powered by large language models exhibit strong reasoning and problem-solving capabilities, enabling them to assist scientific research tasks such as formula derivation and code generation. However, whether these agents can reliably perform end-to-end reproduction from real scientific papers remains an open question. We introduce PRBench, a benchmark of 30 expert-curated tasks spanning 11 subfields of physics. Each task requires an agent to comprehend the methodology of a published paper, implement the corresponding algorithms from scratch, and produce quantitative results matching the original publication. Agents are provided only with the task instruction and paper content, and operate in a sandboxed execution environment. All tasks are contributed by domain experts from over 20 research groups at the School of Physics, Peking University, each grounded in a real published paper and validated through end-to-end reproduction with verified ground-truth results and detailed scoring rubrics. Using an agentified assessment pipeline, we evaluate a set of coding agents on PRBench and analyze their capabilities across key dimensions of scientific reasoning and execution. The best-performing agent, OpenAI Codex powered by GPT-5.3-Codex, achieves a mean overall score of 34%. All agents exhibit a zero end-to-end callback success rate, with particularly poor performance in data accuracy and code correctness. We further identify systematic failure modes, including errors in formula implementation, inability to debug numerical simulations, and fabrication of output data. Overall, PRBench provides a rigorous benchmark for evaluating progress toward autonomous scientific research.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.27646</guid>
|
||||
<pubDate>Sun, 29 Mar 2026 11:44:57 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>KAT-Coder-V2 Technical Report</title>
|
||||
<link>https://arxiv.org/abs/2603.27703</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.27703.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Fengxiang Li, Han Zhang, Haoyang Huang, Jinghui Wang, Jinhua Hao, Kun Yuan, Mengtong Li, Minglei Zhang, Pengcheng Xu, Wenhao Zhuang, Yizhen Shao, Zongxian Feng, Can Tang, Chao Wang, Chengxiao Tong, Fan Yang, Gang Xiong, Haixuan Gao, Han Gao, Hao Wang, Haochen Liu, Hongliang Sun, Jiabao Li, Jingwen Chang, Jun Du, Junyi Peng, Leizhen Cui, Meimei Jing, Mingqi Wu, Shangpeng Yan, Shaotong Qi, Suzhe Xu, Wenxuan Zhao, Xianda Sun, Xuan Xie, Yanbo Wang, Yao Xia, Yinghan Cui, Yingpeng Chen, Yong Wang, Yuze Shi, Zhiwei Shen, Ziyu Wang, Ming Sun, Lin Ye, Bin Chen</p><p><b>Upvotes:</b> 0</p><p><b>Summary:</b> We present KAT-Coder-V2, an agentic coding model developed by the KwaiKAT team at Kuaishou. KAT-Coder-V2 adopts a "Specialize-then-Unify" paradigm that decomposes agentic coding into five expert domains - SWE, WebCoding, Terminal, WebSearch, and General - each undergoing independent supervised fine-tuning and reinforcement learning, before being consolidated into a single model via on-policy distillation. We develop KwaiEnv, a modular infrastructure sustaining tens of thousands of concurrent sandbox instances, and scale RL training along task complexity, intent alignment, and scaffold generalization. We further propose MCLA for stabilizing MoE RL training and Tree Training for eliminating redundant computation over tree-structured trajectories with up to 6.2x speedup. KAT-Coder-V2 achieves 79.6% on SWE-bench Verified (vs. Claude Opus 4.6 at 80.8%), 88.7 on PinchBench (surpassing GLM-5 and MiniMax M2.7), ranks first across all three frontend aesthetics scenarios, and maintains strong generalist scores on Terminal-Bench Hard (46.8) and tau^2-Bench (93.9). Our model is publicly available at https://streamlake.com/product/kat-coder.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.27703</guid>
|
||||
<pubDate>Sun, 29 Mar 2026 14:01:35 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>Emergent Social Intelligence Risks in Generative Multi-Agent Systems</title>
|
||||
<link>https://arxiv.org/abs/2603.27771</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.27771.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yue Huang, Yu Jiang, Wenjie Wang, Haomin Zhuang, Xiaonan Luo, Yuchen Ma, Zhangchen Xu, Zichen Chen, Nuno Moniz, Zinan Lin, Pin-Yu Chen, Nitesh V Chawla, Nouha Dziri, Huan Sun, Xiangliang Zhang</p><p><b>Upvotes:</b> 41</p><p><b>Summary:</b> Multi-agent systems composed of large generative models are rapidly moving from laboratory prototypes to real-world deployments, where they jointly plan, negotiate, and allocate shared resources to solve complex tasks. While such systems promise unprecedented scalability and autonomy, their collective interaction also gives rise to failure modes that cannot be reduced to individual agents. Understanding these emergent risks is therefore critical. Here, we present a pioneer study of such emergent multi-agent risk in workflows that involve competition over shared resources (e.g., computing resources or market share), sequential handoff collaboration (where downstream agents see only predecessor outputs), collective decision aggregation, and others. Across these settings, we observe that such group behaviors arise frequently across repeated trials and a wide range of interaction conditions, rather than as rare or pathological cases. In particular, phenomena such as collusion-like coordination and conformity emerge with non-trivial frequency under realistic resource constraints, communication protocols, and role assignments, mirroring well-known pathologies in human societies despite no explicit instruction. Moreover, these risks cannot be prevented by existing agent-level safeguards alone. These findings expose the dark side of intelligent multi-agent systems: a social intelligence risk where agent collectives, despite no instruction to do so, spontaneously reproduce familiar failure patterns from human societies.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.27771</guid>
|
||||
<pubDate>Sun, 29 Mar 2026 17:10:28 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>MuSEAgent: A Multimodal Reasoning Agent with Stateful Experiences</title>
|
||||
<link>https://arxiv.org/abs/2603.27813</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.27813.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shijian Wang, Jiarui Jin, Runhao Fu, Zexuan Yan, Xingjian Wang, Mengkang Hu, Eric Wang, Xiaoxi Li, Kangning Zhang, Li Yao, Wenxiang Jiao, Xuelian Cheng, Yuan Lu, Zongyuan Ge</p><p><b>Upvotes:</b> 16</p><p><b>Summary:</b> Research agents have recently achieved significant progress in information seeking and synthesis across heterogeneous textual and visual sources. In this paper, we introduce MuSEAgent, a multimodal reasoning agent that enhances decision-making by extending the capabilities of research agents to discover and leverage stateful experiences. Rather than relying on trajectory-level retrieval, we propose a stateful experience learning paradigm that abstracts interaction data into atomic decision experiences through hindsight reasoning. These experiences are organized into a quality-filtered experience bank that supports policy-driven experience retrieval at inference time. Specifically, MuSEAgent enables adaptive experience exploitation through complementary wide- and deep-search strategies, allowing the agent to dynamically retrieve multimodal guidance across diverse compositional semantic viewpoints. Extensive experiments demonstrate that MuSEAgent consistently outperforms strong trajectory-level experience retrieval baselines on both fine-grained visual perception and complex multimodal reasoning tasks. These results validate the effectiveness of stateful experience modeling in improving multimodal agent reasoning.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.27813</guid>
|
||||
<pubDate>Sun, 29 Mar 2026 18:54:31 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>ImagenWorld: Stress-Testing Image Generation Models with Explainable Human Evaluation on Open-ended Real-World Tasks</title>
|
||||
<link>https://arxiv.org/abs/2603.27862</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.27862.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Samin Mahdizadeh Sani, Max Ku, Nima Jamali, Matina Mahdizadeh Sani, Paria Khoshtab, Wei-Chieh Sun, Parnian Fazel, Zhi Rui Tam, Thomas Chong, Edisy Kin Wai Chan, Donald Wai Tong Tsang, Chiao-Wei Hsu, Ting Wai Lam, Ho Yin Sam Ng, Chiafeng Chu, Chak-Wing Mak, Keming Wu, Hiu Tung Wong, Yik Chun Ho, Chi Ruan, Zhuofeng Li, I-Sheng Fang, Shih-Ying Yeh, Ho Kei Cheng, Ping Nie, Wenhu Chen</p><p><b>Upvotes:</b> 17</p><p><b>Summary:</b> Advances in diffusion, autoregressive, and hybrid models have enabled high-quality image synthesis for tasks such as text-to-image, editing, and reference-guided composition. Yet, existing benchmarks remain limited, either focus on isolated tasks, cover only narrow domains, or provide opaque scores without explaining failure modes. We introduce ImagenWorld, a benchmark of 3.6K condition sets spanning six core tasks (generation and editing, with single or multiple references) and six topical domains (artworks, photorealistic images, information graphics, textual graphics, computer graphics, and screenshots). The benchmark is supported by 20K fine-grained human annotations and an explainable evaluation schema that tags localized object-level and segment-level errors, complementing automated VLM-based metrics. Our large-scale evaluation of 14 models yields several insights: (1) models typically struggle more in editing tasks than in generation tasks, especially in local edits. (2) models excel in artistic and photorealistic settings but struggle with symbolic and text-heavy domains such as screenshots and information graphics. (3) closed-source systems lead overall, while targeted data curation (e.g., Qwen-Image) narrows the gap in text-heavy cases. (4) modern VLM-based metrics achieve Kendall accuracies up to 0.79, approximating human ranking, but fall short of fine-grained, explainable error attribution. ImagenWorld provides both a rigorous benchmark and a diagnostic tool to advance robust image generation.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.27862</guid>
|
||||
<pubDate>Sun, 29 Mar 2026 20:42:05 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>MolmoPoint: Better Pointing for VLMs with Grounding Tokens</title>
|
||||
<link>https://arxiv.org/abs/2603.28069</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.28069.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Christopher Clark, Yue Yang, Jae Sung Park, Zixian Ma, Jieyu Zhang, Rohun Tripathi, Mohammadreza Salehi, Sangho Lee, Taira Anderson, Winson Han, Ranjay Krishna</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Grounding has become a fundamental capability of vision-language models (VLMs). Most existing VLMs point by generating coordinates as part of their text output, which requires learning a complicated coordinate system and results in a high token count. Instead, we propose a more intuitive pointing mechanism that directly selects the visual tokens that contain the target concept. Our model generates a special pointing token that cross-attends to the input image or video tokens and selects the appropriate one. To make this model more fine-grained, we follow these pointing tokens with an additional special token that selects a fine-grained subpatch within the initially selected region, and then a third token that specifies a location within that subpatch. We further show that performance improves by generating points sequentially in a consistent order, encoding the relative position of the previously selected point, and including a special no-more-points class when selecting visual tokens. Using this method, we set a new state-of-the-art on image pointing (70.7% on PointBench), set a new state-of-the-art among fully open models on GUI pointing (61.1% on ScreenSpotPro), and improve video pointing (59.1% human preference win rate vs. a text coordinate baseline) and tracking (+6.3% gain on Molmo2Track). We additionally show that our method achieves much higher sample efficiency and discuss the qualitative differences that emerge from this design change.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.28069</guid>
|
||||
<pubDate>Mon, 30 Mar 2026 06:15:06 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>Kernel-Smith: A Unified Recipe for Evolutionary Kernel Optimization</title>
|
||||
<link>https://arxiv.org/abs/2603.28342</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.28342.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> He Du, Qiming Ge, Jiakai Hu, Aijun Yang, Zheng Cai, Zixian Huang, Sheng Yuan, Qinxiu Cheng, Xinchen Xie, Yicheng Chen, Yining Li, Jiaxing Xie, Huanan Dong, Yaguang Wu, Xiangjun Huang, Jian Yang, Hui Wang, Bowen Zhou, Bowen Li, Qipeng Guo, Kai Chen</p><p><b>Upvotes:</b> 15</p><p><b>Summary:</b> We present Kernel-Smith, a framework for high-performance GPU kernel and operator generation that combines a stable evaluation-driven evolutionary agent with an evolution-oriented post-training recipe. On the agent side, Kernel-Smith maintains a population of executable candidates and iteratively improves them using an archive of top-performing and diverse programs together with structured execution feedback on compilation, correctness, and speedup. To make this search reliable, we build backend-specific evaluation services for Triton on NVIDIA GPUs and Maca on MetaX GPUs. On the training side, we convert long-horizon evolution trajectories into step-centric supervision and reinforcement learning signals by retaining correctness-preserving, high-gain revisions, so that the model is optimized as a strong local improver inside the evolutionary loop rather than as a one-shot generator. Under a unified evolutionary protocol, Kernel-Smith-235B-RL achieves state-of-the-art overall performance on KernelBench with Nvidia Triton backend, attaining the best average speedup ratio and outperforming frontier proprietary models including Gemini-3.0-pro and Claude-4.6-opus. We further validate the framework on the MetaX MACA backend, where our Kernel-Smith-MACA-30B surpasses large-scale counterparts such as DeepSeek-V3.2-think and Qwen3-235B-2507-think, highlighting potential for seamless adaptation across heterogeneous platforms. Beyond benchmark results, the same workflow produces upstream contributions to production systems including SGLang and LMDeploy, demonstrating that LLM-driven kernel optimization can transfer from controlled evaluation to practical deployment.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.28342</guid>
|
||||
<pubDate>Mon, 30 Mar 2026 12:12:49 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>Marco DeepResearch: Unlocking Efficient Deep Research Agents via Verification-Centric Design</title>
|
||||
<link>https://arxiv.org/abs/2603.28376</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.28376.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Bin Zhu, Qianghuai Jia, Tian Lan, Junyang Ren, Feng Gu, Feihu Jiang, Longyue Wang, Zhao Xu, Weihua Luo</p><p><b>Upvotes:</b> 10</p><p><b>Summary:</b> Deep research agents autonomously conduct open-ended investigations, integrating complex information retrieval with multi-step reasoning across diverse sources to solve real-world problems. To sustain this capability on long-horizon tasks, reliable verification is critical during both training and inference. A major bottleneck in existing paradigms stems from the lack of explicit verification mechanisms in QA data synthesis, trajectory construction, and test-time scaling. Errors introduced at each stage propagate downstream and degrade the overall agent performance. To address this, we present Marco DeepResearch, a deep research agent optimized with a verification-centric framework design at three levels: (1)~QA Data Synthesis: We introduce verification mechanisms to graph-based and agent-based QA synthesis to control question difficulty while ensuring answers are unique and correct; (2)~Trajectory Construction: We design a verification-driven trajectory synthesis method that injects explicit verification patterns into training trajectories; and (3)~Test-time scaling: We use Marco DeepResearch itself as a verifier at inference time and effectively improve performance on challenging questions. Extensive experimental results demonstrate that our proposed Marco DeepResearch agent significantly outperforms 8B-scale deep research agents on most challenging benchmarks, such as BrowseComp and BrowseComp-ZH. Crucially, under a maximum budget of 600 tool calls, Marco DeepResearch even surpasses or approaches several 30B-scale agents, like Tongyi DeepResearch-30B.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.28376</guid>
|
||||
<pubDate>Mon, 30 Mar 2026 12:42:02 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>HISA: Efficient Hierarchical Indexing for Fine-Grained Sparse Attention</title>
|
||||
<link>https://arxiv.org/abs/2603.28458</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.28458.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yufei Xu, Fanxu Meng, Fan Jiang, Yuxuan Wang, Ruijie Zhou, Jiexi Wu, Zhixin Pan, Zhaohui Wang, Xiaojuan Tang, Wenjie Pei, Tongxuan Liu, Di yin, Xing Sun, Muhan Zhang</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Token-level sparse attention mechanisms, exemplified by DeepSeek Sparse Attention (DSA), achieve fine-grained key selection by scoring every historical token for each query using a lightweight indexer, and then computing attention only over the selected subset. While the downstream sparse attention scales efficiently, the indexer still scans the entire prefix for every query, introducing an O(L^2) per-layer bottleneck that becomes prohibitive as context length grows. We propose HISA (Hierarchical Indexed Sparse Attention), a drop-in replacement for the indexer that transforms the search process from a flat token scan into a two-stage hierarchical procedure. First, a block-level coarse filter scores pooled block representatives to prune irrelevant regions. Then, a token-level refinement applies the original indexer only within the remaining candidate blocks. HISA preserves the exact token-level top-k sparsity pattern required by the downstream Sparse MLA operator and requires no additional training. On kernel-level benchmarks, HISA achieves a 2times speedup at 32K context length and 4times at 128K. On Needle-in-a-Haystack and LongBench, we directly replace the indexer in DeepSeek-V3.2 with HISA, without any fine-tuning. HISA closely matches the original DSA in quality while significantly outperforming block-sparse baselines. Moreover, the token selection sets produced by HISA and the original DSA exhibit a mean IoU greater than 99%, indicating that the efficiency gains come with virtually no impact on selection fidelity.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.28458</guid>
|
||||
<pubDate>Mon, 30 Mar 2026 13:59:51 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>INSID3: Training-Free In-Context Segmentation with DINOv3</title>
|
||||
<link>https://arxiv.org/abs/2603.28480</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.28480.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Claudia Cuttano, Gabriele Trivigno, Christoph Reich, Daniel Cremers, Carlo Masone, Stefan Roth</p><p><b>Upvotes:</b> 0</p><p><b>Summary:</b> In-context segmentation (ICS) aims to segment arbitrary concepts, e.g., objects, parts, or personalized instances, given one annotated visual examples. Existing work relies on (i) fine-tuning vision foundation models (VFMs), which improves in-domain results but harms generalization, or (ii) combines multiple frozen VFMs, which preserves generalization but yields architectural complexity and fixed segmentation granularities. We revisit ICS from a minimalist perspective and ask: Can a single self-supervised backbone support both semantic matching and segmentation, without any supervision or auxiliary models? We show that scaled-up dense self-supervised features from DINOv3 exhibit strong spatial structure and semantic correspondence. We introduce INSID3, a training-free approach that segments concepts at varying granularities only from frozen DINOv3 features, given an in-context example. INSID3 achieves state-of-the-art results across one-shot semantic, part, and personalized segmentation, outperforming previous work by +7.5 % mIoU, while using 3x fewer parameters and without any mask or category-level supervision. Code is available at https://github.com/visinf/INSID3 .</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.28480</guid>
|
||||
<pubDate>Mon, 30 Mar 2026 14:16:37 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>GEditBench v2: A Human-Aligned Benchmark for General Image Editing</title>
|
||||
<link>https://arxiv.org/abs/2603.28547</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.28547.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhangqi Jiang, Zheng Sun, Xianfang Zeng, Yufeng Yang, Xuanyang Zhang, Yongliang Wu, Wei Cheng, Gang Yu, Xu Yang, Bihan Wen</p><p><b>Upvotes:</b> 26</p><p><b>Summary:</b> Recent advances in image editing have enabled models to handle complex instructions with impressive realism. However, existing evaluation frameworks lag behind: current benchmarks suffer from narrow task coverage, while standard metrics fail to adequately capture visual consistency, i.e., the preservation of identity, structure and semantic coherence between edited and original images. To address these limitations, we introduce GEditBench v2, a comprehensive benchmark with 1,200 real-world user queries spanning 23 tasks, including a dedicated open-set category for unconstrained, out-of-distribution editing instructions beyond predefined tasks. Furthermore, we propose PVC-Judge, an open-source pairwise assessment model for visual consistency, trained via two novel region-decoupled preference data synthesis pipelines. Besides, we construct VCReward-Bench using expert-annotated preference pairs to assess the alignment of PVC-Judge with human judgments on visual consistency evaluation. Experiments show that our PVC-Judge achieves state-of-the-art evaluation performance among open-source models and even surpasses GPT-5.1 on average. Finally, by benchmarking 16 frontier editing models, we show that GEditBench v2 enables more human-aligned evaluation, revealing critical limitations of current models, and providing a reliable foundation for advancing precise image editing.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.28547</guid>
|
||||
<pubDate>Mon, 30 Mar 2026 15:08:32 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>Towards a Medical AI Scientist</title>
|
||||
<link>https://arxiv.org/abs/2603.28589</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.28589.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Hongtao Wu, Boyun Zheng, Dingjie Song, Yu Jiang, Jianfeng Gao, Lei Xing, Lichao Sun, Yixuan Yuan</p><p><b>Upvotes:</b> 64</p><p><b>Summary:</b> Autonomous systems that generate scientific hypotheses, conduct experiments, and draft manuscripts have recently emerged as a promising paradigm for accelerating discovery. However, existing AI Scientists remain largely domain-agnostic, limiting their applicability to clinical medicine, where research is required to be grounded in medical evidence with specialized data modalities. In this work, we introduce Medical AI Scientist, the first autonomous research framework tailored to clinical autonomous research. It enables clinically grounded ideation by transforming extensively surveyed literature into actionable evidence through clinician-engineer co-reasoning mechanism, which improves the traceability of generated research ideas. It further facilitates evidence-grounded manuscript drafting guided by structured medical compositional conventions and ethical policies. The framework operates under 3 research modes, namely paper-based reproduction, literature-inspired innovation, and task-driven exploration, each corresponding to a distinct level of automated scientific inquiry with progressively increasing autonomy. Comprehensive evaluations by both large language models and human experts demonstrate that the ideas generated by the Medical AI Scientist are of substantially higher quality than those produced by commercial LLMs across 171 cases, 19 clinical tasks, and 6 data modalities. Meanwhile, our system achieves strong alignment between the proposed method and its implementation, while also demonstrating significantly higher success rates in executable experiments. Double-blind evaluations by human experts and the Stanford Agentic Reviewer suggest that the generated manuscripts approach MICCAI-level quality, while consistently surpassing those from ISBI and BIBM. The proposed Medical AI Scientist highlights the potential of leveraging AI for autonomous scientific discovery in healthcare.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.28589</guid>
|
||||
<pubDate>Mon, 30 Mar 2026 15:37:25 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>ResAdapt: Adaptive Resolution for Efficient Multimodal Reasoning</title>
|
||||
<link>https://arxiv.org/abs/2603.28610</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.28610.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Huanxuan Liao, Zhongtao Jiang, Yupu Hao, Yuqiao Tan, Shizhu He, Jun Zhao, Kun Xu, Kang Liu</p><p><b>Upvotes:</b> 14</p><p><b>Summary:</b> Multimodal Large Language Models (MLLMs) achieve stronger visual understanding by scaling input fidelity, yet the resulting visual token growth makes jointly sustaining high spatial resolution and long temporal context prohibitive. We argue that the bottleneck lies not in how post-encoding representations are compressed but in the volume of pixels the encoder receives, and address it with ResAdapt, an Input-side adaptation framework that learns how much visual budget each frame should receive before encoding. ResAdapt couples a lightweight Allocator with an unchanged MLLM backbone, so the backbone retains its native visual-token interface while receiving an operator-transformed input. We formulate allocation as a contextual bandit and train the Allocator with Cost-Aware Policy Optimization (CAPO), which converts sparse rollout feedback into a stable accuracy-cost learning signal. Across budget-controlled video QA, temporal grounding, and image reasoning tasks, ResAdapt improves low-budget operating points and often lies on or near the efficiency-accuracy frontier, with the clearest gains on reasoning-intensive benchmarks under aggressive compression. Notably, ResAdapt supports up to 16x more frames at the same visual budget while delivering over 15% performance gain. Code is available at https://github.com/Xnhyacinth/ResAdapt.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.28610</guid>
|
||||
<pubDate>Mon, 30 Mar 2026 15:57:32 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>Superintelligence and Law</title>
|
||||
<link>https://arxiv.org/abs/2603.28669</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.28669.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Noam Kolt</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> The prospect of artificial superintelligence -- AI agents that can generally outperform humans in cognitive tasks and economically valuable activities -- will transform the legal order as we know it. Operating autonomously or under only limited human oversight, AI agents will assume a growing range of roles in the legal system. First, in making consequential decisions and taking real-world actions, AI agents will become de facto subjects of law. Second, to cooperate and compete with other actors (human or non-human), AI agents will harness conventional legal instruments and institutions such as contracts and courts, becoming consumers of law. Third, to the extent AI agents perform the functions of writing, interpreting, and administering law, they will become producers and enforcers of law. These developments, whenever they ultimately occur, will call into question fundamental assumptions in legal theory and doctrine, especially to the extent they ground the legitimacy of legal institutions in their human origins. Attempts to align AI agents with extant human law will also face new challenges as AI agents will not only be a primary target of law, but a core user of law and contributor to law. To contend with the advent of superintelligence, lawmakers -- new and old -- will need to be clear-eyed, recognizing both the opportunity to shape legal institutions as society braces for superintelligence and the reality that, in the longer run, this may be a joint human-AI endeavor.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.28669</guid>
|
||||
<pubDate>Mon, 30 Mar 2026 16:51:51 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>AdaptToken: Entropy-based Adaptive Token Selection for MLLM Long Video Understanding</title>
|
||||
<link>https://arxiv.org/abs/2603.28696</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.28696.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Haozhe Qi, Kevin Qu, Mahdi Rad, Rui Wang, Alexander Mathis, Marc Pollefeys</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Long video understanding remains challenging for Multi-modal Large Language Models (MLLMs) due to high memory costs and context-length limits. Prior approaches mitigate this by scoring and selecting frames/tokens within short clips, but they lack a principled mechanism to (i) compare relevance across distant video clips and (ii) stop processing once sufficient evidence has been gathered. We propose AdaptToken, a training-free framework that turns an MLLM's self-uncertainty into a global control signal for long-video token selection. AdaptToken splits a video into groups, extracts cross-modal attention to rank tokens within each group, and uses the model's response entropy to estimate each group's prompt relevance. This entropy signal enables a global token budget allocation across groups and further supports early stopping (AdaptToken-Lite), skipping the remaining groups when the model becomes sufficiently certain. Across four long-video benchmarks (VideoMME, LongVideoBench, LVBench, and MLVU) and multiple base MLLMs (7B-72B), AdaptToken consistently improves accuracy (e.g., +6.7 on average over Qwen2.5-VL 7B) and continues to benefit from extremely long inputs (up to 10K frames), while AdaptToken-Lite reduces inference time by about half with comparable performance. Project page: https://haozheqi.github.io/adapt-token</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.28696</guid>
|
||||
<pubDate>Mon, 30 Mar 2026 17:14:15 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>DreamLite: A Lightweight On-Device Unified Model for Image Generation and Editing</title>
|
||||
<link>https://arxiv.org/abs/2603.28713</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.28713.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Kailai Feng, Yuxiang Wei, Bo Chen, Yang Pan, Hu Ye, Songwei Liu, Chenqian Yan, Yuan Gao</p><p><b>Upvotes:</b> 9</p><p><b>Summary:</b> Diffusion models have made significant progress in both text-to-image (T2I) generation and text-guided image editing. However, these models are typically built with billions of parameters, leading to high latency and increased deployment challenges. While on-device diffusion models improve efficiency, they largely focus on T2I generation and lack support for image editing. In this paper, we propose DreamLite, a compact unified on-device diffusion model (0.39B) that supports both T2I generation and text-guided image editing within a single network. DreamLite is built on a pruned mobile U-Net backbone and unifies conditioning through in-context spatial concatenation in the latent space. It concatenates images horizontally as input, using a (target | blank) configuration for generation tasks and (target | source) for editing tasks. To stabilize the training of this compact model, we introduce a task-progressive joint pretraining strategy that sequentially targets T2I, editing, and joint tasks. After high-quality SFT and reinforcement learning, DreamLite achieves GenEval (0.72) for image generation and ImgEdit (4.11) for image editing, outperforming existing on-device models and remaining competitive with several server-side models. By employing step distillation, we further reduce denoising processing to just 4 steps, enabling our DreamLite could generate or edit a 1024 x 1024 image in less than 1s on a Xiaomi 14 smartphone. To the best of our knowledge, DreamLite is the first unified on-device diffusion model that supports both image generation and image editing.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.28713</guid>
|
||||
<pubDate>Mon, 30 Mar 2026 17:30:25 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>On-the-fly Repulsion in the Contextual Space for Rich Diversity in Diffusion Transformers</title>
|
||||
<link>https://arxiv.org/abs/2603.28762</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.28762.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Omer Dahary, Benaya Koren, Daniel Garibi, Daniel Cohen-Or</p><p><b>Upvotes:</b> 16</p><p><b>Summary:</b> Modern Text-to-Image (T2I) diffusion models have achieved remarkable semantic alignment, yet they often suffer from a significant lack of variety, converging on a narrow set of visual solutions for any given prompt. This typicality bias presents a challenge for creative applications that require a wide range of generative outcomes. We identify a fundamental trade-off in current approaches to diversity: modifying model inputs requires costly optimization to incorporate feedback from the generative path. In contrast, acting on spatially-committed intermediate latents tends to disrupt the forming visual structure, leading to artifacts. In this work, we propose to apply repulsion in the Contextual Space as a novel framework for achieving rich diversity in Diffusion Transformers. By intervening in the multimodal attention channels, we apply on-the-fly repulsion during the transformer's forward pass, injecting the intervention between blocks where text conditioning is enriched with emergent image structure. This allows for redirecting the guidance trajectory after it is structurally informed but before the composition is fixed. Our results demonstrate that repulsion in the Contextual Space produces significantly richer diversity without sacrificing visual fidelity or semantic adherence. Furthermore, our method is uniquely efficient, imposing a small computational overhead while remaining effective even in modern "Turbo" and distilled models where traditional trajectory-based interventions typically fail.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.28762</guid>
|
||||
<pubDate>Mon, 30 Mar 2026 17:59:13 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>HandX: Scaling Bimanual Motion and Interaction Generation</title>
|
||||
<link>https://arxiv.org/abs/2603.28766</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.28766.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zimu Zhang, Yucheng Zhang, Xiyan Xu, Ziyin Wang, Sirui Xu, Kai Zhou, Bing Zhou, Chuan Guo, Jian Wang, Yu-Xiong Wang, Liang-Yan Gui</p><p><b>Upvotes:</b> 9</p><p><b>Summary:</b> Synthesizing human motion has advanced rapidly, yet realistic hand motion and bimanual interaction remain underexplored. Whole-body models often miss the fine-grained cues that drive dexterous behavior, finger articulation, contact timing, and inter-hand coordination, and existing resources lack high-fidelity bimanual sequences that capture nuanced finger dynamics and collaboration. To fill this gap, we present HandX, a unified foundation spanning data, annotation, and evaluation. We consolidate and filter existing datasets for quality, and collect a new motion-capture dataset targeting underrepresented bimanual interactions with detailed finger dynamics. For scalable annotation, we introduce a decoupled strategy that extracts representative motion features, e.g., contact events and finger flexion, and then leverages reasoning from large language models to produce fine-grained, semantically rich descriptions aligned with these features. Building on the resulting data and annotations, we benchmark diffusion and autoregressive models with versatile conditioning modes. Experiments demonstrate high-quality dexterous motion generation, supported by our newly proposed hand-focused metrics. We further observe clear scaling trends: larger models trained on larger, higher-quality datasets produce more semantically coherent bimanual motion. Our dataset is released to support future research.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.28766</guid>
|
||||
<pubDate>Mon, 30 Mar 2026 17:59:49 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>Gen-Searcher: Reinforcing Agentic Search for Image Generation</title>
|
||||
<link>https://arxiv.org/abs/2603.28767</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.28767.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Kaituo Feng, Manyuan Zhang, Shuang Chen, Yunlong Lin, Kaixuan Fan, Yilei Jiang, Hongyu Li, Dian Zheng, Chenyang Wang, Xiangyu Yue</p><p><b>Upvotes:</b> 43</p><p><b>Summary:</b> Recent image generation models have shown strong capabilities in generating high-fidelity and photorealistic images. However, they are fundamentally constrained by frozen internal knowledge, thus often failing on real-world scenarios that are knowledge-intensive or require up-to-date information. In this paper, we present Gen-Searcher, as the first attempt to train a search-augmented image generation agent, which performs multi-hop reasoning and search to collect the textual knowledge and reference images needed for grounded generation. To achieve this, we construct a tailored data pipeline and curate two high-quality datasets, Gen-Searcher-SFT-10k and Gen-Searcher-RL-6k, containing diverse search-intensive prompts and corresponding ground-truth synthesis images. We further introduce KnowGen, a comprehensive benchmark that explicitly requires search-grounded external knowledge for image generation and evaluates models from multiple dimensions. Based on these resources, we train Gen-Searcher with SFT followed by agentic reinforcement learning with dual reward feedback, which combines text-based and image-based rewards to provide more stable and informative learning signals for GRPO training. Experiments show that Gen-Searcher brings substantial gains, improving Qwen-Image by around 16 points on KnowGen and 15 points on WISE. We hope this work can serve as an open foundation for search agents in image generation, and we fully open-source our data, models, and code.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.28767</guid>
|
||||
<pubDate>Mon, 30 Mar 2026 17:59:56 +0000</pubDate>
|
||||
</item>
|
||||
</channel>
|
||||
</rss>
|
||||
|
||||
Reference in New Issue
Block a user