diff --git a/feed.xml b/feed.xml index 88597eb..56583c4 100644 --- a/feed.xml +++ b/feed.xml @@ -7,132 +7,153 @@ http://www.rssboard.org/rss-specification python-feedgen en - Wed, 17 Sep 2025 00:02:42 +0000 + Thu, 18 Sep 2025 00:02:37 +0000 - LongEmotion: Measuring Emotional Intelligence of Large Language Models in Long-Context Interaction - https://arxiv.org/abs/2509.07403 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.07403.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Weichu Liu, Jing Xiong, Yuxuan Hu, Zixuan Li, Minghuan Tan, Ningning Mao, Chenyang Zhao, Zhongwei Wan, Chaofan Tao, Wendong Xu, Hui Shen, Chengming Li, Lingpeng Kong, Ngai Wong</p><p><b>Upvotes:</b> 0</p><p><b>Summary:</b> Large language models (LLMs) make significant progress in Emotional Intelligence (EI) and long-context understanding. However, existing benchmarks tend to overlook certain aspects of EI in long-context scenarios, especially under realistic, practical settings where interactions are lengthy, diverse, and often noisy. To move towards such realistic settings, we present LongEmotion, a benchmark specifically designed for long-context EI tasks. It covers a diverse set of tasks, including Emotion Classification, Emotion Detection, Emotion QA, Emotion Conversation, Emotion Summary, and Emotion Expression. On average, the input length for these tasks reaches 8,777 tokens, with long-form generation required for Emotion Expression. To enhance performance under realistic constraints, we incorporate Retrieval-Augmented Generation (RAG) and Collaborative Emotional Modeling (CoEM), and compare them with standard prompt-based methods. Unlike conventional approaches, our RAG method leverages both the conversation context and the large language model itself as retrieval sources, avoiding reliance on external knowledge bases. The CoEM method further improves performance by decomposing the task into five stages, integrating both retrieval augmentation and limited knowledge injection. Experimental results show that both RAG and CoEM consistently enhance EI-related performance across most long-context tasks, advancing LLMs toward more practical and real-world EI applications. Furthermore, we conducted a comparative case study experiment on the GPT series to demonstrate the differences among various models in terms of EI. Code is available on GitHub at https://github.com/LongEmotion/LongEmotion, and the project page can be found at https://longemotion.github.io/.</p> - https://arxiv.org/abs/2509.07403 - Tue, 09 Sep 2025 05:32:45 +0000 + Multimodal Reasoning for Science: Technical Report and 1st Place Solution to the ICML 2025 SeePhys Challenge + https://arxiv.org/abs/2509.06079 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.06079.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Hao Liang, Ruitao Wu, Bohan Zeng, Junbo Niu, Wentao Zhang, Bin Dong</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Multimodal reasoning remains a fundamental challenge in artificial intelligence. Despite substantial advances in text-based reasoning, even state-of-the-art models such as GPT-o3 struggle to maintain strong performance in multimodal scenarios. To address this gap, we introduce a caption-assisted reasoning framework that effectively bridges visual and textual modalities. Our approach achieved 1st place in the ICML 2025 AI for Math Workshop \& Challenge 2: SeePhys, highlighting its effectiveness and robustness. Furthermore, we validate its generalization on the MathVerse benchmark for geometric reasoning, demonstrating the versatility of our method. Our code is publicly available at https://github.com/OpenDCAI/SciReasoner.</p> + https://arxiv.org/abs/2509.06079 + Sun, 07 Sep 2025 14:47:32 +0000 - Measuring Epistemic Humility in Multimodal Large Language Models - https://arxiv.org/abs/2509.09658 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.09658.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Bingkui Tong, Jiaer Xia, Sifeng Shang, Kaiyang Zhou</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> Hallucinations in multimodal large language models (MLLMs) -- where the model generates content inconsistent with the input image -- pose significant risks in real-world applications, from misinformation in visual question answering to unsafe errors in decision-making. Existing benchmarks primarily test recognition accuracy, i.e., evaluating whether models can select the correct answer among distractors. This overlooks an equally critical capability for trustworthy AI: recognizing when none of the provided options are correct, a behavior reflecting epistemic humility. We present HumbleBench, a new hallucination benchmark designed to evaluate MLLMs' ability to reject plausible but incorrect answers across three hallucination types: object, relation, and attribute. Built from a panoptic scene graph dataset, we leverage fine-grained scene graph annotations to extract ground-truth entities and relations, and prompt GPT-4-Turbo to generate multiple-choice questions, followed by a rigorous manual filtering process. Each question includes a "None of the above" option, requiring models not only to recognize correct visual information but also to identify when no provided answer is valid. We evaluate a variety of state-of-the-art MLLMs -- including both general-purpose and specialized reasoning models -- on HumbleBench and share valuable findings and insights with the community. By incorporating explicit false-option rejection, HumbleBench fills a key gap in current evaluation suites, providing a more realistic measure of MLLM reliability in safety-critical settings. Our code and dataset are released publicly and can be accessed at https://github.com/maifoundations/HumbleBench.</p> - https://arxiv.org/abs/2509.09658 - Thu, 11 Sep 2025 17:54:00 +0000 + Stable Part Diffusion 4D: Multi-View RGB and Kinematic Parts Video Generation + https://arxiv.org/abs/2509.10687 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.10687.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Hao Zhang, Chun-Han Yao, Simon Donné, Narendra Ahuja, Varun Jampani</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> We present Stable Part Diffusion 4D (SP4D), a framework for generating paired RGB and kinematic part videos from monocular inputs. Unlike conventional part segmentation methods that rely on appearance-based semantic cues, SP4D learns to produce kinematic parts - structural components aligned with object articulation and consistent across views and time. SP4D adopts a dual-branch diffusion model that jointly synthesizes RGB frames and corresponding part segmentation maps. To simplify the architecture and flexibly enable different part counts, we introduce a spatial color encoding scheme that maps part masks to continuous RGB-like images. This encoding allows the segmentation branch to share the latent VAE from the RGB branch, while enabling part segmentation to be recovered via straightforward post-processing. A Bidirectional Diffusion Fusion (BiDiFuse) module enhances cross-branch consistency, supported by a contrastive part consistency loss to promote spatial and temporal alignment of part predictions. We demonstrate that the generated 2D part maps can be lifted to 3D to derive skeletal structures and harmonic skinning weights with few manual adjustments. To train and evaluate SP4D, we construct KinematicParts20K, a curated dataset of over 20K rigged objects selected and processed from Objaverse XL (Deitke et al., 2023), each paired with multi-view RGB and part video sequences. Experiments show that SP4D generalizes strongly to diverse scenarios, including real-world videos, novel generated objects, and rare articulated poses, producing kinematic-aware outputs suitable for downstream animation and motion-related tasks.</p> + https://arxiv.org/abs/2509.10687 + Fri, 12 Sep 2025 20:39:43 +0000 - Locality in Image Diffusion Models Emerges from Data Statistics - https://arxiv.org/abs/2509.09672 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.09672.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Artem Lukoianov, Chenyang Yuan, Justin Solomon, Vincent Sitzmann</p><p><b>Upvotes:</b> 8</p><p><b>Summary:</b> Among generative models, diffusion models are uniquely intriguing due to the existence of a closed-form optimal minimizer of their training objective, often referred to as the optimal denoiser. However, diffusion using this optimal denoiser merely reproduces images in the training set and hence fails to capture the behavior of deep diffusion models. Recent work has attempted to characterize this gap between the optimal denoiser and deep diffusion models, proposing analytical, training-free models that can generate images that resemble those generated by a trained UNet. The best-performing method hypothesizes that shift equivariance and locality inductive biases of convolutional neural networks are the cause of the performance gap, hence incorporating these assumptions into its analytical model. In this work, we present evidence that the locality in deep diffusion models emerges as a statistical property of the image dataset, not due to the inductive bias of convolutional neural networks. Specifically, we demonstrate that an optimal parametric linear denoiser exhibits similar locality properties to the deep neural denoisers. We further show, both theoretically and experimentally, that this locality arises directly from the pixel correlations present in natural image datasets. Finally, we use these insights to craft an analytical denoiser that better matches scores predicted by a deep diffusion model than the prior expert-crafted alternative.</p> - https://arxiv.org/abs/2509.09672 - Thu, 11 Sep 2025 17:59:08 +0000 + Struct-Bench: A Benchmark for Differentially Private Structured Text Generation + https://arxiv.org/abs/2509.10696 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.10696.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shuaiqi Wang, Vikas Raunak, Arturs Backurs, Victor Reis, Pei Zhou, Sihao Chen, Longqi Yang, Zinan Lin, Sergey Yekhanin, Giulia Fanti</p><p><b>Upvotes:</b> 0</p><p><b>Summary:</b> Differentially private (DP) synthetic data generation is a promising technique for utilizing private datasets that otherwise cannot be exposed for model training or other analytics. While much research literature has focused on generating private unstructured text and image data, in enterprise settings, structured data (e.g., tabular) is more common, often including natural language fields or components. Existing synthetic data evaluation techniques (e.g., FID) struggle to capture the structural properties and correlations of such datasets. In this work, we propose Struct-Bench, a framework and benchmark for evaluating synthetic datasets derived from structured datasets that contain natural language data. The Struct-Bench framework requires users to provide a representation of their dataset structure as a Context-Free Grammar (CFG). Our benchmark comprises 5 real-world and 2 synthetically generated datasets, each annotated with CFGs. We show that these datasets demonstrably present a great challenge even for state-of-the-art DP synthetic data generation methods. Struct-Bench also includes reference implementations of different metrics and a leaderboard, thereby providing researchers a standardized evaluation platform to benchmark and investigate privacy-preserving synthetic data generation methods. Further, we also present a case study showing how to use Struct-Bench to improve the synthetic data quality of Private Evolution (PE) on structured data. The benchmark and the leaderboard have been publicly made available at https://struct-bench.github.io.</p> + https://arxiv.org/abs/2509.10696 + Fri, 12 Sep 2025 21:18:13 +0000 - SearchInstruct: Enhancing Domain Adaptation via Retrieval-Based Instruction Dataset Creation - https://arxiv.org/abs/2509.10708 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.10708.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Iman Barati, Mostafa Amiri, Heshaam Faili</p><p><b>Upvotes:</b> 9</p><p><b>Summary:</b> Supervised Fine-Tuning (SFT) is essential for training large language models (LLMs), significantly enhancing critical capabilities such as instruction following and in-context learning. Nevertheless, creating suitable training datasets tailored for specific domains remains challenging due to unique domain constraints and data scarcity. In this paper, we propose SearchInstruct, an innovative method explicitly designed to construct high quality instruction datasets for SFT. Our approach begins with a limited set of domain specific, human generated questions, which are systematically expanded using a large language model. Subsequently, domain relevant resources are dynamically retrieved to generate accurate and contextually appropriate answers for each augmented question. Experimental evaluation demonstrates that SearchInstruct enhances both the diversity and quality of SFT datasets, leading to measurable improvements in LLM performance within specialized domains. Additionally, we show that beyond dataset generation, the proposed method can also effectively facilitate tasks such as model editing, enabling efficient updates to existing models. To facilitate reproducibility and community adoption, we provide full implementation details, the complete set of generated instruction response pairs, and the source code in a publicly accessible Git repository: [https://github.com/mostafaamiri/SearchInstruct](https://github.com/mostafaamiri/SearchInstruct)</p> - https://arxiv.org/abs/2509.10708 - Fri, 12 Sep 2025 21:50:39 +0000 + Sound Matching an Analogue Levelling Amplifier Using the Newton-Raphson Method + https://arxiv.org/abs/2509.10706 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.10706.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Chin-Yun Yu, György Fazekas</p><p><b>Upvotes:</b> 0</p><p><b>Summary:</b> Automatic differentiation through digital signal processing algorithms for virtual analogue modelling has recently gained popularity. These algorithms are typically more computationally efficient than black-box neural networks that rely on dense matrix multiplications. Due to their differentiable nature, they can be integrated with neural networks and jointly trained using gradient descent algorithms, resulting in more efficient systems. Furthermore, signal processing algorithms have significantly fewer parameters than neural networks, allowing the application of the Newton-Raphson method. This method offers faster and more robust convergence than gradient descent at the cost of quadratic storage. This paper presents a method to emulate analogue levelling amplifiers using a feed-forward digital compressor with parameters optimised via the Newton-Raphson method. We demonstrate that a digital compressor can successfully approximate the behaviour of our target unit, the Teletronix LA-2A. Different strategies for computing the Hessian matrix are benchmarked. We leverage parallel algorithms for recursive filters to achieve efficient training on modern GPUs. The resulting model is made into a VST plugin and is open-sourced at https://github.com/aim-qmul/4a2a.</p> + https://arxiv.org/abs/2509.10706 + Fri, 12 Sep 2025 21:48:30 +0000 - InternScenes: A Large-scale Simulatable Indoor Scene Dataset with Realistic Layouts - https://arxiv.org/abs/2509.10813 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.10813.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Weipeng Zhong, Peizhou Cao, Yichen Jin, Li Luo, Wenzhe Cai, Jingli Lin, Hanqing Wang, Zhaoyang Lyu, Tai Wang, Bo Dai, Xudong Xu, Jiangmiao Pang</p><p><b>Upvotes:</b> 23</p><p><b>Summary:</b> The advancement of Embodied AI heavily relies on large-scale, simulatable 3D scene datasets characterized by scene diversity and realistic layouts. However, existing datasets typically suffer from limitations in data scale or diversity, sanitized layouts lacking small items, and severe object collisions. To address these shortcomings, we introduce InternScenes, a novel large-scale simulatable indoor scene dataset comprising approximately 40,000 diverse scenes by integrating three disparate scene sources, real-world scans, procedurally generated scenes, and designer-created scenes, including 1.96M 3D objects and covering 15 common scene types and 288 object classes. We particularly preserve massive small items in the scenes, resulting in realistic and complex layouts with an average of 41.5 objects per region. Our comprehensive data processing pipeline ensures simulatability by creating real-to-sim replicas for real-world scans, enhances interactivity by incorporating interactive objects into these scenes, and resolves object collisions by physical simulations. We demonstrate the value of InternScenes with two benchmark applications: scene layout generation and point-goal navigation. Both show the new challenges posed by the complex and realistic layouts. More importantly, InternScenes paves the way for scaling up the model training for both tasks, making the generation and navigation in such complex scenes possible. We commit to open-sourcing the data, models, and benchmarks to benefit the whole community.</p> - https://arxiv.org/abs/2509.10813 - Sat, 13 Sep 2025 14:25:17 +0000 + Optimal Brain Restoration for Joint Quantization and Sparsification of LLMs + https://arxiv.org/abs/2509.11177 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.11177.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Hang Guo, Yawei Li, Luca Benini</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Recent advances in Large Language Model (LLM) compression, such as quantization and pruning, have achieved notable success. However, as these techniques gradually approach their respective limits, relying on a single method for further compression has become increasingly challenging. In this work, we explore an alternative solution by combining quantization and sparsity. This joint approach, though promising, introduces new difficulties due to the inherently conflicting requirements on weight distributions: quantization favors compact ranges, while pruning benefits from high variance. To attack this problem, we propose Optimal Brain Restoration (OBR), a general and training-free framework that aligns pruning and quantization by error compensation between both. OBR minimizes performance degradation on downstream tasks by building on a second-order Hessian objective, which is then reformulated into a tractable problem through surrogate approximation and ultimately reaches a closed-form solution via group error compensation. Experiments show that OBR enables aggressive W4A4KV4 quantization with 50% sparsity on existing LLMs, and delivers up to 4.72x speedup and 6.4x memory reduction compared to the FP16-dense baseline.</p> + https://arxiv.org/abs/2509.11177 + Sun, 14 Sep 2025 09:17:19 +0000 - GAPrune: Gradient-Alignment Pruning for Domain-Aware Embeddings - https://arxiv.org/abs/2509.10844 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.10844.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yixuan Tang, Yi Yang</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Domain-specific embedding models have shown promise for applications that require specialized semantic understanding, such as coding agents and financial retrieval systems, often achieving higher performance gains than general models. However, state-of-the-art embedding models are typically based on LLMs, which contain billions of parameters, making deployment challenging in resource-constrained environments. Model compression through pruning offers a promising solution, but existing pruning methods treat all parameters uniformly, failing to distinguish between general semantic representations and domain-specific patterns, leading to suboptimal pruning decisions. Thus, we propose GAPrune, a pruning framework that addresses this challenge by considering both domain importance and preserving general linguistic foundation. Our method uses Fisher Information to measure importance and general-domain gradient alignment to assess parameter behavior, then combines these signals using our Domain Alignment Importance (DAI) scoring. Lower DAI scores indicate that the parameter is either less important for the domain task or creates conflicts between domain and general objectives. Experiments on two domain benchmarks, FinMTEB and ChemTEB, show that GAPrune maintains performance within 2.5% of dense models in one-shot pruning at 50% sparsity, while outperforming all baselines. With retraining in 100 steps, GAPrune achieves +4.51% improvement on FinMTEB and +1.73% on ChemTEB, demonstrating that our pruning strategy not only preserves but enhances domain-specific capabilities. Our findings demonstrate that principled pruning strategies can achieve model compression and enhanced domain specialization, providing the research community with a new approach for development.</p> - https://arxiv.org/abs/2509.10844 - Sat, 13 Sep 2025 15:03:37 +0000 + RAPTOR: A Foundation Policy for Quadrotor Control + https://arxiv.org/abs/2509.11481 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.11481.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jonas Eschmann, Dario Albani, Giuseppe Loianno</p><p><b>Upvotes:</b> 0</p><p><b>Summary:</b> Humans are remarkably data-efficient when adapting to new unseen conditions, like driving a new car. In contrast, modern robotic control systems, like neural network policies trained using Reinforcement Learning (RL), are highly specialized for single environments. Because of this overfitting, they are known to break down even under small differences like the Simulation-to-Reality (Sim2Real) gap and require system identification and retraining for even minimal changes to the system. In this work, we present RAPTOR, a method for training a highly adaptive foundation policy for quadrotor control. Our method enables training a single, end-to-end neural-network policy to control a wide variety of quadrotors. We test 10 different real quadrotors from 32 g to 2.4 kg that also differ in motor type (brushed vs. brushless), frame type (soft vs. rigid), propeller type (2/3/4-blade), and flight controller (PX4/Betaflight/Crazyflie/M5StampFly). We find that a tiny, three-layer policy with only 2084 parameters is sufficient for zero-shot adaptation to a wide variety of platforms. The adaptation through In-Context Learning is made possible by using a recurrence in the hidden layer. The policy is trained through a novel Meta-Imitation Learning algorithm, where we sample 1000 quadrotors and train a teacher policy for each of them using Reinforcement Learning. Subsequently, the 1000 teachers are distilled into a single, adaptive student policy. We find that within milliseconds, the resulting foundation policy adapts zero-shot to unseen quadrotors. We extensively test the capabilities of the foundation policy under numerous conditions (trajectory tracking, indoor/outdoor, wind disturbance, poking, different propellers).</p> + https://arxiv.org/abs/2509.11481 + Mon, 15 Sep 2025 00:05:40 +0000 - Nav-R1: Reasoning and Navigation in Embodied Scenes - https://arxiv.org/abs/2509.10884 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.10884.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Qingxiang Liu, Ting Huang, Zeyu Zhang, Hao Tang</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> Embodied navigation requires agents to integrate perception, reasoning, and action for robust interaction in complex 3D environments. Existing approaches often suffer from incoherent and unstable reasoning traces that hinder generalization across diverse environments, and difficulty balancing long-horizon semantic reasoning with low-latency control for real-time navigation. To address these challenges, we propose Nav-R1, an embodied foundation model that unifies reasoning in embodied environments. We first construct Nav-CoT-110K, a large-scale dataset of step-by-step Chains-of-Thought (CoT) for embodied tasks, which enables cold-start initialization with structured reasoning. Building on this foundation, we design a GRPO-based reinforcement learning framework with three complementary rewards: format, understanding, and navigation, to improve structural adherence, semantic grounding, and path fidelity. Furthermore, we introduce a Fast-in-Slow reasoning paradigm, decoupling deliberate semantic reasoning from low-latency reactive control for efficient yet coherent navigation. Extensive evaluations on embodied AI benchmarks demonstrate that Nav-R1 consistently outperforms strong baselines, with over 8% average improvement in reasoning and navigation performance. Real-world deployment on a mobile robot further validates its robustness under limited onboard resources. Code: https://github.com/AIGeeksGroup/Nav-R1. Website: https://aigeeksgroup.github.io/Nav-R1.</p> - https://arxiv.org/abs/2509.10884 - Sat, 13 Sep 2025 16:31:03 +0000 + Multiple Instance Learning Framework with Masked Hard Instance Mining for Gigapixel Histopathology Image Analysis + https://arxiv.org/abs/2509.11526 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.11526.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Wenhao Tang, Sheng Huang, Heng Fang, Fengtao Zhou, Bo Liu, Qingshan Liu</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Digitizing pathological images into gigapixel Whole Slide Images (WSIs) has opened new avenues for Computational Pathology (CPath). As positive tissue comprises only a small fraction of gigapixel WSIs, existing Multiple Instance Learning (MIL) methods typically focus on identifying salient instances via attention mechanisms. However, this leads to a bias towards easy-to-classify instances while neglecting challenging ones. Recent studies have shown that hard examples are crucial for accurately modeling discriminative boundaries. Applying such an idea at the instance level, we elaborate a novel MIL framework with masked hard instance mining (MHIM-MIL), which utilizes a Siamese structure with a consistency constraint to explore the hard instances. Using a class-aware instance probability, MHIM-MIL employs a momentum teacher to mask salient instances and implicitly mine hard instances for training the student model. To obtain diverse, non-redundant hard instances, we adopt large-scale random masking while utilizing a global recycle network to mitigate the risk of losing key features. Furthermore, the student updates the teacher using an exponential moving average, which identifies new hard instances for subsequent training iterations and stabilizes optimization. Experimental results on cancer diagnosis, subtyping, survival analysis tasks, and 12 benchmarks demonstrate that MHIM-MIL outperforms the latest methods in both performance and efficiency. The code is available at: https://github.com/DearCaat/MHIM-MIL.</p> + https://arxiv.org/abs/2509.11526 + Mon, 15 Sep 2025 02:31:33 +0000 - PersonaX: Multimodal Datasets with LLM-Inferred Behavior Traits - https://arxiv.org/abs/2509.11362 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.11362.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Loka Li, Wong Yu Kang, Minghao Fu, Guangyi Chen, Zhenhao Chen, Gongxu Luo, Yuewen Sun, Salman Khan, Peter Spirtes, Kun Zhang</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Understanding human behavior traits is central to applications in human-computer interaction, computational social science, and personalized AI systems. Such understanding often requires integrating multiple modalities to capture nuanced patterns and relationships. However, existing resources rarely provide datasets that combine behavioral descriptors with complementary modalities such as facial attributes and biographical information. To address this gap, we present PersonaX, a curated collection of multimodal datasets designed to enable comprehensive analysis of public traits across modalities. PersonaX consists of (1) CelebPersona, featuring 9444 public figures from diverse occupations, and (2) AthlePersona, covering 4181 professional athletes across 7 major sports leagues. Each dataset includes behavioral trait assessments inferred by three high-performing large language models, alongside facial imagery and structured biographical features. We analyze PersonaX at two complementary levels. First, we abstract high-level trait scores from text descriptions and apply five statistical independence tests to examine their relationships with other modalities. Second, we introduce a novel causal representation learning (CRL) framework tailored to multimodal and multi-measurement data, providing theoretical identifiability guarantees. Experiments on both synthetic and real-world data demonstrate the effectiveness of our approach. By unifying structured and unstructured analysis, PersonaX establishes a foundation for studying LLM-inferred behavioral traits in conjunction with visual and biographical attributes, advancing multimodal trait analysis and causal reasoning.</p> - https://arxiv.org/abs/2509.11362 - Sun, 14 Sep 2025 17:30:03 +0000 + Exact Coset Sampling for Quantum Lattice Algorithms + https://arxiv.org/abs/2509.12341 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.12341.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yifan Zhang</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> We give a simple, fully correct, and assumption-light replacement for the contested "domain-extension" in Step 9 of a recent windowed-QFT lattice algorithm with complex-Gaussian windows~chen2024quantum. The published Step~9 suffers from a periodicity/support mismatch. We present a pair-shift difference construction that coherently cancels all unknown offsets, produces an exact uniform CRT-coset state over Z_{P}, and then uses the QFT to enforce the intended modular linear relation. The unitary is reversible, uses poly(log M_2) gates, and preserves the algorithm's asymptotics. Project Page: https://github.com/yifanzhang-pro/quantum-lattice.</p> + https://arxiv.org/abs/2509.12341 + Mon, 15 Sep 2025 18:10:28 +0000 - CognitiveSky: Scalable Sentiment and Narrative Analysis for Decentralized Social Media - https://arxiv.org/abs/2509.11444 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.11444.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Gaurab Chhetri, Anandi Dutta, Subasish Das</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> The emergence of decentralized social media platforms presents new opportunities and challenges for real-time analysis of public discourse. This study introduces CognitiveSky, an open-source and scalable framework designed for sentiment, emotion, and narrative analysis on Bluesky, a federated Twitter or X.com alternative. By ingesting data through Bluesky's Application Programming Interface (API), CognitiveSky applies transformer-based models to annotate large-scale user-generated content and produces structured and analyzable outputs. These summaries drive a dynamic dashboard that visualizes evolving patterns in emotion, activity, and conversation topics. Built entirely on free-tier infrastructure, CognitiveSky achieves both low operational cost and high accessibility. While demonstrated here for monitoring mental health discourse, its modular design enables applications across domains such as disinformation detection, crisis response, and civic sentiment analysis. By bridging large language models with decentralized networks, CognitiveSky offers a transparent, extensible tool for computational social science in an era of shifting digital ecosystems.</p> - https://arxiv.org/abs/2509.11444 - Sun, 14 Sep 2025 21:37:24 +0000 + Phi: Preference Hijacking in Multi-modal Large Language Models at Inference Time + https://arxiv.org/abs/2509.12521 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.12521.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yifan Lan, Yuanpu Cao, Weitong Zhang, Lu Lin, Jinghui Chen</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Recently, Multimodal Large Language Models (MLLMs) have gained significant attention across various domains. However, their widespread adoption has also raised serious safety concerns. In this paper, we uncover a new safety risk of MLLMs: the output preference of MLLMs can be arbitrarily manipulated by carefully optimized images. Such attacks often generate contextually relevant yet biased responses that are neither overtly harmful nor unethical, making them difficult to detect. Specifically, we introduce a novel method, Preference Hijacking (Phi), for manipulating the MLLM response preferences using a preference hijacked image. Our method works at inference time and requires no model modifications. Additionally, we introduce a universal hijacking perturbation -- a transferable component that can be embedded into different images to hijack MLLM responses toward any attacker-specified preferences. Experimental results across various tasks demonstrate the effectiveness of our approach. The code for Phi is accessible at https://github.com/Yifan-Lan/Phi.</p> + https://arxiv.org/abs/2509.12521 + Mon, 15 Sep 2025 23:55:57 +0000 - Learning to Optimize Multi-Objective Alignment Through Dynamic Reward Weighting - https://arxiv.org/abs/2509.11452 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.11452.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yining Lu, Zilong Wang, Shiyang Li, Xin Liu, Changlong Yu, Qingyu Yin, Zhan Shi, Zixuan Zhang, Meng Jiang</p><p><b>Upvotes:</b> 7</p><p><b>Summary:</b> Prior works in multi-objective reinforcement learning typically use linear reward scalarization with fixed weights, which provably fail to capture non-convex Pareto fronts and thus yield suboptimal results. This limitation becomes especially critical in online preference alignment for large language models. Here, stochastic trajectories generated by parameterized policies create highly non-linear and non-convex mappings from parameters to objectives that no single static weighting scheme can find optimal trade-offs. We address this limitation by introducing dynamic reward weighting, which adaptively adjusts reward weights during the online reinforcement learning process. Unlike existing approaches that rely on fixed-weight interpolation, our dynamic weighting continuously balances and prioritizes objectives in training, facilitating effective exploration of Pareto fronts in objective space. We introduce two approaches of increasing sophistication and generalizability: (1) hypervolume-guided weight adaptation and (2) gradient-based weight optimization, offering a versatile toolkit for online multi-objective alignment. Our extensive experiments demonstrate their compatibility with commonly used online reinforcement learning algorithms (including GRPO, REINFORCE, and RLOO), effectiveness across multiple mathematical reasoning datasets, and applicability to different model families, consistently achieving Pareto dominant solutions with fewer training steps than fixed-weight linear scalarization baselines.</p> - https://arxiv.org/abs/2509.11452 - Sun, 14 Sep 2025 21:56:35 +0000 + zELO: ELO-inspired Training Method for Rerankers and Embedding Models + https://arxiv.org/abs/2509.12541 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.12541.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Nicholas Pipitone, Ghita Houir Alami, Advaith Avadhanam, Anton Kaminskyi, Ashley Khoo</p><p><b>Upvotes:</b> 0</p><p><b>Summary:</b> We introduce a novel training methodology named zELO, which optimizes retrieval performance via the analysis that ranking tasks are statically equivalent to a Thurstone model. Based on the zELO method, we use unsupervised data in order train a suite of state-of-the-art open-weight reranker models: zerank-1 and zerank-1-small. These models achieve the highest retrieval scores in multiple domains, including finance, legal, code, and STEM, outperforming closed-source proprietary rerankers on both NDCG@10 and Recall. These models also demonstrate great versatility, maintaining their 0-shot performance on out-of-domain and private customer datasets. The training data included 112,000 queries and 100 documents per query, and was trained end-to-end from unannotated queries and documents in less than 10,000 H100-hours.</p> + https://arxiv.org/abs/2509.12541 + Tue, 16 Sep 2025 00:44:08 +0000 - ClaimIQ at CheckThat! 2025: Comparing Prompted and Fine-Tuned Language Models for Verifying Numerical Claims - https://arxiv.org/abs/2509.11492 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.11492.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Anirban Saha Anik, Md Fahimul Kabir Chowdhury, Andrew Wyckoff, Sagnik Ray Choudhury</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> This paper presents our system for Task 3 of the CLEF 2025 CheckThat! Lab, which focuses on verifying numerical and temporal claims using retrieved evidence. We explore two complementary approaches: zero-shot prompting with instruction-tuned large language models (LLMs) and supervised fine-tuning using parameter-efficient LoRA. To enhance evidence quality, we investigate several selection strategies, including full-document input and top-k sentence filtering using BM25 and MiniLM. Our best-performing model LLaMA fine-tuned with LoRA achieves strong performance on the English validation set. However, a notable drop in the test set highlights a generalization challenge. These findings underscore the importance of evidence granularity and model adaptation for robust numerical fact verification.</p> - https://arxiv.org/abs/2509.11492 - Mon, 15 Sep 2025 01:03:09 +0000 + EconProver: Towards More Economical Test-Time Scaling for Automated Theorem Proving + https://arxiv.org/abs/2509.12603 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.12603.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Mukai Li, Linfeng Song, Zhenwen Liang, Jiahao Xu, Shansan Gong, Qi Liu, Haitao Mi, Dong Yu</p><p><b>Upvotes:</b> 6</p><p><b>Summary:</b> Large Language Models (LLMs) have recently advanced the field of Automated Theorem Proving (ATP), attaining substantial performance gains through widely adopted test-time scaling strategies, notably reflective Chain-of-Thought (CoT) reasoning and increased sampling passes. However, they both introduce significant computational overhead for inference. Moreover, existing cost analyses typically regulate only the number of sampling passes, while neglecting the substantial disparities in sampling costs introduced by different scaling strategies. In this paper, we systematically compare the efficiency of different test-time scaling strategies for ATP models and demonstrate the inefficiency of the current state-of-the-art (SOTA) open-source approaches. We then investigate approaches to significantly reduce token usage and sample passes while maintaining the original performance. Specifically, we propose two complementary methods that can be integrated into a unified EconRL pipeline for amplified benefits: (1) a dynamic Chain-of-Thought (CoT) switching mechanism designed to mitigate unnecessary token consumption, and (2) Diverse parallel-scaled reinforcement learning (RL) with trainable prefixes to enhance pass rates under constrained sampling passes. Experiments on miniF2F and ProofNet demonstrate that our EconProver achieves comparable performance to baseline methods with only 12% of the computational cost. This work provides actionable insights for deploying lightweight ATP models without sacrificing performance.</p> + https://arxiv.org/abs/2509.12603 + Tue, 16 Sep 2025 03:00:13 +0000 - UI-S1: Advancing GUI Automation via Semi-online Reinforcement Learning - https://arxiv.org/abs/2509.11543 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.11543.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhengxi Lu, Jiabo Ye, Fei Tang, Yongliang Shen, Haiyang Xu, Ziwei Zheng, Weiming Lu, Ming Yan, Fei Huang, Jun Xiao, Yueting Zhuang</p><p><b>Upvotes:</b> 34</p><p><b>Summary:</b> Graphical User Interface (GUI) agents have demonstrated remarkable progress in automating complex user interface interactions through reinforcement learning. However, current approaches face a fundamental dilemma: offline RL enables stable training on pre-collected trajectories, but struggles with multi-step task execution for lack of trajectory-level reward signals; online RL captures these signals through environment interaction, but suffers from sparse rewards and prohibitive deployment costs. To address it, we present Semi-online Reinforcement Learning, a novel paradigm that simulates online RL on offline trajectories. During each rollout process, we preserve the original model output within the multi-turn dialogue, where a Patch Module adaptively recovers the divergence between rollout and expert trajectories. To capture long-term training signals, Semi-online RL introduces discounted future returns into the reward computation and optimizes the policy with weighted step-level and episode-level advantages. We further introduce Semi-Online Performance (SOP), a metric that aligns better with true online performance, serving as a practical and effective proxy for real-world evaluation. Experiments show that ours Semi-online RL achieves SOTA performance among 7B models across four dynamic benchmarks, with significant gains over the base model (e.g., +12.0% on AndroidWorld, +23.8% on AITW), demonstrating significant progress in bridging the gap between offline training efficiency and online multi-turn reasoning. The code is available at https://github.com/X-PLUG/MobileAgent/tree/main/UI-S1.</p> - https://arxiv.org/abs/2509.11543 - Mon, 15 Sep 2025 03:24:08 +0000 + Hunyuan3D Studio: End-to-End AI Pipeline for Game-Ready 3D Asset Generation + https://arxiv.org/abs/2509.12815 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.12815.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Biwen Lei, Yang Li, Xinhai Liu, Shuhui Yang, Lixin Xu, Jingwei Huang, Ruining Tang, Haohan Weng, Jian Liu, Jing Xu, Zhen Zhou, Yiling Zhu, Jiankai Xing, Jiachen Xu, Changfeng Ma, Xinhao Yan, Yunhan Yang, Chunshi Wang, Duoteng Xu, Xueqi Ma, Yuguang Chen, Jing Li, Mingxin Yang, Sheng Zhang, Yifei Feng, Xin Huang, Di Luo, Zebin He, Puhua Jiang, Changrong Hu, Zihan Qin, Shiwei Miao, Haolin Liu, Yunfei Zhao, Zeqiang Lai, Qingxiang Lin, Zibo Zhao, Kunhong Li, Xianghui Yang, Huiwen Shi, Xin Yang, Yuxuan Wang, Zebin Yao, Yihang Lian, Sicong Liu, Xintong Han, Wangchen Qin, Caisheng Ouyang, Jianyin Liu, Tianwen Yuan, Shuai Jiang, Hong Duan, Yanqi Niu, Wencong Lin, Yifu Sun, Shirui Huang, Lin Niu, Gu Gong, Guojian Xiao, Bojian Zheng, Xiang Yuan, Qi Chen, Jie Xiao, Dongyang Zheng, Xiaofeng Yang, Kai Liu, Jianchen Zhu, Lifu Wang, Qinglin Lu, Jie Liu, Liang Dong, Fan Jiang, Ruibin Chen, Lei Wang, Chao Zhang, Jiaxin Lin, Hao Zhang, Zheng Ye, Peng He, Runzhou Wu, Yinhe Wu, Jiayao Du, Jupeng Chen, Xinyue Mao, Dongyuan Guo, Yixuan Tang, Yulin Tsai, Yonghao Tan, Jiaao Yu, Junlin Yu, Keren Zhang, Yifan Li, Peng Chen, Tian Liu, Di Wang, Yuhong Liu, Linus, Jie Jiang, Zhuo Chen, Chunchao Guo</p><p><b>Upvotes:</b> 18</p><p><b>Summary:</b> The creation of high-quality 3D assets, a cornerstone of modern game development, has long been characterized by labor-intensive and specialized workflows. This paper presents Hunyuan3D Studio, an end-to-end AI-powered content creation platform designed to revolutionize the game production pipeline by automating and streamlining the generation of game-ready 3D assets. At its core, Hunyuan3D Studio integrates a suite of advanced neural modules (such as Part-level 3D Generation, Polygon Generation, Semantic UV, etc.) into a cohesive and user-friendly system. This unified framework allows for the rapid transformation of a single concept image or textual description into a fully-realized, production-quality 3D model complete with optimized geometry and high-fidelity PBR textures. We demonstrate that assets generated by Hunyuan3D Studio are not only visually compelling but also adhere to the stringent technical requirements of contemporary game engines, significantly reducing iteration time and lowering the barrier to entry for 3D content creation. By providing a seamless bridge from creative intent to technical asset, Hunyuan3D Studio represents a significant leap forward for AI-assisted workflows in game development and interactive media.</p> + https://arxiv.org/abs/2509.12815 + Tue, 16 Sep 2025 08:33:03 +0000 - EthicsMH: A Pilot Benchmark for Ethical Reasoning in Mental Health AI - https://arxiv.org/abs/2509.11648 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.11648.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Sai Kartheek Reddy Kasu</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> The deployment of large language models (LLMs) in mental health and other sensitive domains raises urgent questions about ethical reasoning, fairness, and responsible alignment. Yet, existing benchmarks for moral and clinical decision-making do not adequately capture the unique ethical dilemmas encountered in mental health practice, where confidentiality, autonomy, beneficence, and bias frequently intersect. To address this gap, we introduce Ethical Reasoning in Mental Health (EthicsMH), a pilot dataset of 125 scenarios designed to evaluate how AI systems navigate ethically charged situations in therapeutic and psychiatric contexts. Each scenario is enriched with structured fields, including multiple decision options, expert-aligned reasoning, expected model behavior, real-world impact, and multi-stakeholder viewpoints. This structure enables evaluation not only of decision accuracy but also of explanation quality and alignment with professional norms. Although modest in scale and developed with model-assisted generation, EthicsMH establishes a task framework that bridges AI ethics and mental health decision-making. By releasing this dataset, we aim to provide a seed resource that can be expanded through community and expert contributions, fostering the development of AI systems capable of responsibly handling some of society's most delicate decisions.</p> - https://arxiv.org/abs/2509.11648 - Mon, 15 Sep 2025 07:35:35 +0000 + ROOM: A Physics-Based Continuum Robot Simulator for Photorealistic Medical Datasets Generation + https://arxiv.org/abs/2509.13177 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.13177.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Salvatore Esposito, Matías Mattamala, Daniel Rebain, Francis Xiatian Zhang, Kevin Dhaliwal, Mohsen Khadem, Subramanian Ramamoorthy</p><p><b>Upvotes:</b> 0</p><p><b>Summary:</b> Continuum robots are advancing bronchoscopy procedures by accessing complex lung airways and enabling targeted interventions. However, their development is limited by the lack of realistic training and test environments: Real data is difficult to collect due to ethical constraints and patient safety concerns, and developing autonomy algorithms requires realistic imaging and physical feedback. We present ROOM (Realistic Optical Observation in Medicine), a comprehensive simulation framework designed for generating photorealistic bronchoscopy training data. By leveraging patient CT scans, our pipeline renders multi-modal sensor data including RGB images with realistic noise and light specularities, metric depth maps, surface normals, optical flow and point clouds at medically relevant scales. We validate the data generated by ROOM in two canonical tasks for medical robotics -- multi-view pose estimation and monocular depth estimation, demonstrating diverse challenges that state-of-the-art methods must overcome to transfer to these medical settings. Furthermore, we show that the data produced by ROOM can be used to fine-tune existing depth estimation models to overcome these challenges, also enabling other downstream applications such as navigation. We expect that ROOM will enable large-scale data generation across diverse patient anatomies and procedural scenarios that are challenging to capture in clinical settings. Code and data: https://github.com/iamsalvatore/room.</p> + https://arxiv.org/abs/2509.13177 + Tue, 16 Sep 2025 15:30:02 +0000 - Dr.V: A Hierarchical Perception-Temporal-Cognition Framework to Diagnose Video Hallucination by Fine-grained Spatial-Temporal Grounding - https://arxiv.org/abs/2509.11866 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.11866.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Meng Luo, Shengqiong Wu, Liqiang Jing, Tianjie Ju, Li Zheng, Jinxiang Lai, Tianlong Wu, Xinya Du, Jian Li, Siyuan Yan, Jiebo Luo, William Yang Wang, Hao Fei, Mong-Li Lee, Wynne Hsu</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Recent advancements in large video models (LVMs) have significantly enhance video understanding. However, these models continue to suffer from hallucinations, producing content that conflicts with input videos. To address this issue, we propose Dr.V, a hierarchical framework covering perceptive, temporal, and cognitive levels to diagnose video hallucination by fine-grained spatial-temporal grounding. Dr.V comprises of two key components: a benchmark dataset Dr.V-Bench and a satellite video agent Dr.V-Agent. Dr.V-Bench includes 10k instances drawn from 4,974 videos spanning diverse tasks, each enriched with detailed spatial-temporal annotation. Dr.V-Agent detects hallucinations in LVMs by systematically applying fine-grained spatial-temporal grounding at the perceptive and temporal levels, followed by cognitive level reasoning. This step-by-step pipeline mirrors human-like video comprehension and effectively identifies hallucinations. Extensive experiments demonstrate that Dr.V-Agent is effective in diagnosing hallucination while enhancing interpretability and reliability, offering a practical blueprint for robust video understanding in real-world scenarios. All our data and code are available at https://github.com/Eurekaleo/Dr.V.</p> - https://arxiv.org/abs/2509.11866 - Mon, 15 Sep 2025 12:39:19 +0000 + Single-stream Policy Optimization + https://arxiv.org/abs/2509.13232 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.13232.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhongwen Xu, Zihan Ding</p><p><b>Upvotes:</b> 23</p><p><b>Summary:</b> We revisit policy-gradient optimization for Large Language Models (LLMs) from a single-stream perspective. Prevailing group-based methods like GRPO reduce variance with on-the-fly baselines but suffer from critical flaws: frequent degenerate groups erase learning signals, and synchronization barriers hinder scalability. We introduce Single-stream Policy Optimization (SPO), which eliminates these issues by design. SPO replaces per-group baselines with a persistent, KL-adaptive value tracker and normalizes advantages globally across the batch, providing a stable, low-variance learning signal for every sample. Being group-free, SPO enables higher throughput and scales effectively in long-horizon or tool-integrated settings where generation times vary. Furthermore, the persistent value tracker naturally enables an adaptive curriculum via prioritized sampling. Experiments using Qwen3-8B show that SPO converges more smoothly and attains higher accuracy than GRPO, while eliminating computation wasted on degenerate groups. Ablation studies confirm that SPO's gains stem from its principled approach to baseline estimation and advantage normalization, offering a more robust and efficient path for LLM reasoning. Across five hard math benchmarks with Qwen3 8B, SPO improves the average maj@32 by +3.4 percentage points (pp) over GRPO, driven by substantial absolute point gains on challenging datasets, including +7.3 pp on BRUMO 25, +4.4 pp on AIME 25, +3.3 pp on HMMT 25, and achieves consistent relative gain in pass@k across the evaluated k values. SPO's success challenges the prevailing trend of adding incidental complexity to RL algorithms, highlighting a path where fundamental principles, not architectural workarounds, drive the next wave of progress in LLM reasoning.</p> + https://arxiv.org/abs/2509.13232 + Tue, 16 Sep 2025 16:39:11 +0000 - Lost in Embeddings: Information Loss in Vision-Language Models - https://arxiv.org/abs/2509.11986 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.11986.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Wenyan Li, Raphael Tang, Chengzu Li, Caiqi Zhang, Ivan Vulić, Anders Søgaard</p><p><b>Upvotes:</b> 7</p><p><b>Summary:</b> Vision--language models (VLMs) often process visual inputs through a pretrained vision encoder, followed by a projection into the language model's embedding space via a connector component. While crucial for modality fusion, the potential information loss induced by this projection step and its direct impact on model capabilities remain understudied. We introduce two complementary approaches to examine and quantify this loss by analyzing the latent representation space. First, we evaluate semantic information preservation by analyzing changes in k-nearest neighbor relationships between image representations, before and after projection. Second, we directly measure information loss by reconstructing visual embeddings from the projected representation, localizing loss at an image patch level. Experiments reveal that connectors substantially distort the local geometry of visual representations, with k-nearest neighbors diverging by 40--60\% post-projection, correlating with degradation in retrieval performance. The patch-level embedding reconstruction provides interpretable insights for model behavior on visually grounded question-answering tasks, finding that areas of high information loss reliably predict instances where models struggle.</p> - https://arxiv.org/abs/2509.11986 - Mon, 15 Sep 2025 14:38:06 +0000 + WebSailor-V2: Bridging the Chasm to Proprietary Agents via Synthetic Data and Scalable Reinforcement Learning + https://arxiv.org/abs/2509.13305 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.13305.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Kuan Li, Zhongwang Zhang, Huifeng Yin, Rui Ye, Yida Zhao, Liwen Zhang, Litu Ou, Dingchu Zhang, Xixi Wu, Jialong Wu, Xinyu Wang, Zile Qiao, Zhen Zhang, Yong Jiang, Pengjun Xie, Fei Huang, Jingren Zhou</p><p><b>Upvotes:</b> 52</p><p><b>Summary:</b> Transcending human cognitive limitations represents a critical frontier in LLM training. Proprietary agentic systems like DeepResearch have demonstrated superhuman capabilities on extremely complex information-seeking benchmarks such as BrowseComp, a feat previously unattainable. We posit that their success hinges on a sophisticated reasoning pattern absent in open-source models: the ability to systematically reduce extreme uncertainty when navigating vast information landscapes. Based on this insight, we introduce WebSailor, a complete post-training methodology designed to instill this crucial capability. Our approach involves generating novel, high-uncertainty tasks through structured sampling and information obfuscation, RFT cold start, and an efficient agentic RL training algorithm, Duplicating Sampling Policy Optimization (DUPO). With this integrated pipeline, WebSailor significantly outperforms all open-source agents in complex information-seeking tasks, matching proprietary agents' performance and closing the capability gap.</p> + https://arxiv.org/abs/2509.13305 + Tue, 16 Sep 2025 17:57:03 +0000 - Look Again, Think Slowly: Enhancing Visual Reflection in Vision-Language Models - https://arxiv.org/abs/2509.12132 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.12132.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Pu Jian, Junhong Wu, Wei Sun, Chen Wang, Shuo Ren, Jiajun Zhang</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Recent advances in text-only "slow-thinking" reasoning have prompted efforts to transfer this capability to vision-language models (VLMs), for training visual reasoning models (VRMs). owever, such transfer faces critical challenges: Effective "slow thinking" in VRMs requires visual reflection, the ability to check the reasoning process based on visual information. Through quantitative analysis, we observe that current VRMs exhibit limited visual reflection, as their attention to visual information diminishes rapidly with longer generated responses. To address this challenge, we propose a new VRM Reflection-V, which enhances visual reflection based on reasoning data construction for cold-start and reward design for reinforcement learning (RL). Firstly, we construct vision-centered reasoning data by leveraging an agent that interacts between VLMs and reasoning LLMs, enabling cold-start learning of visual reflection patterns. Secondly, a visual attention based reward model is employed during RL to encourage reasoning based on visual information. Therefore, Reflection-V demonstrates significant improvements across multiple visual reasoning benchmarks. Furthermore, Reflection-V maintains a stronger and more consistent reliance on visual information during visual reasoning, indicating effective enhancement in visual reflection capabilities.</p> - https://arxiv.org/abs/2509.12132 - Mon, 15 Sep 2025 16:57:25 +0000 + WebResearcher: Unleashing unbounded reasoning capability in Long-Horizon Agents + https://arxiv.org/abs/2509.13309 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.13309.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zile Qiao, Guoxin Chen, Xuanzhong Chen, Donglei Yu, Wenbiao Yin, Xinyu Wang, Zhen Zhang, Baixuan Li, Huifeng Yin, Kuan Li, Rui Min, Minpeng Liao, Yong Jiang, Pengjun Xie, Fei Huang, Jingren Zhou</p><p><b>Upvotes:</b> 47</p><p><b>Summary:</b> Recent advances in deep-research systems have demonstrated the potential for AI agents to autonomously discover and synthesize knowledge from external sources. In this paper, we introduce WebResearcher, a novel framework for building such agents through two key components: (1) WebResearcher, an iterative deep-research paradigm that reformulates deep research as a Markov Decision Process, where agents periodically consolidate findings into evolving reports while maintaining focused workspaces, overcoming the context suffocation and noise contamination that plague existing mono-contextual approaches; and (2) WebFrontier, a scalable data synthesis engine that generates high-quality training data through tool-augmented complexity escalation, enabling systematic creation of research tasks that bridge the gap between passive knowledge recall and active knowledge construction. Notably, we find that the training data from our paradigm significantly enhances tool-use capabilities even for traditional mono-contextual methods. Furthermore, our paradigm naturally scales through parallel thinking, enabling concurrent multi-agent exploration for more comprehensive conclusions. Extensive experiments across 6 challenging benchmarks demonstrate that WebResearcher achieves state-of-the-art performance, even surpassing frontier proprietary systems.</p> + https://arxiv.org/abs/2509.13309 + Tue, 16 Sep 2025 17:57:17 +0000 - OmniWorld: A Multi-Domain and Multi-Modal Dataset for 4D World Modeling - https://arxiv.org/abs/2509.12201 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.12201.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yang Zhou, Yifan Wang, Jianjun Zhou, Wenzheng Chang, Haoyu Guo, Zizun Li, Kaijing Ma, Xinyue Li, Yating Wang, Haoyi Zhu, Mingyu Liu, Dingning Liu, Jiange Yang, Zhoujie Fu, Junyi Chen, Chunhua Shen, Jiangmiao Pang, Kaipeng Zhang, Tong He</p><p><b>Upvotes:</b> 73</p><p><b>Summary:</b> The field of 4D world modeling - aiming to jointly capture spatial geometry and temporal dynamics - has witnessed remarkable progress in recent years, driven by advances in large-scale generative models and multimodal learning. However, the development of truly general 4D world models remains fundamentally constrained by the availability of high-quality data. Existing datasets and benchmarks often lack the dynamic complexity, multi-domain diversity, and spatial-temporal annotations required to support key tasks such as 4D geometric reconstruction, future prediction, and camera-control video generation. To address this gap, we introduce OmniWorld, a large-scale, multi-domain, multi-modal dataset specifically designed for 4D world modeling. OmniWorld consists of a newly collected OmniWorld-Game dataset and several curated public datasets spanning diverse domains. Compared with existing synthetic datasets, OmniWorld-Game provides richer modality coverage, larger scale, and more realistic dynamic interactions. Based on this dataset, we establish a challenging benchmark that exposes the limitations of current state-of-the-art (SOTA) approaches in modeling complex 4D environments. Moreover, fine-tuning existing SOTA methods on OmniWorld leads to significant performance gains across 4D reconstruction and video generation tasks, strongly validating OmniWorld as a powerful resource for training and evaluation. We envision OmniWorld as a catalyst for accelerating the development of general-purpose 4D world models, ultimately advancing machines' holistic understanding of the physical world.</p> - https://arxiv.org/abs/2509.12201 - Mon, 15 Sep 2025 17:59:19 +0000 + Scaling Agents via Continual Pre-training + https://arxiv.org/abs/2509.13310 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.13310.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Liangcai Su, Zhen Zhang, Guangyu Li, Zhuo Chen, Chenxi Wang, Maojia Song, Xinyu Wang, Kuan Li, Jialong Wu, Xuanzhong Chen, Zile Qiao, Zhongwang Zhang, Huifeng Yin, Shihao Cai, Runnan Fang, Zhengwei Tao, Wenbiao Yin, Chenxiong Qian, Yong Jiang, Pengjun Xie, Fei Huang, Jingren Zhou</p><p><b>Upvotes:</b> 61</p><p><b>Summary:</b> Large language models (LLMs) have evolved into agentic systems capable of autonomous tool use and multi-step reasoning for complex problem-solving. However, post-training approaches building upon general-purpose foundation models consistently underperform in agentic tasks, particularly in open-source implementations. We identify the root cause: the absence of robust agentic foundation models forces models during post-training to simultaneously learn diverse agentic behaviors while aligning them to expert demonstrations, thereby creating fundamental optimization tensions. To this end, we are the first to propose incorporating Agentic Continual Pre-training (Agentic CPT) into the deep research agents training pipeline to build powerful agentic foundational models. Based on this approach, we develop a deep research agent model named AgentFounder. We evaluate our AgentFounder-30B on 10 benchmarks and achieve state-of-the-art performance while retains strong tool-use ability, notably 39.9% on BrowseComp-en, 43.3% on BrowseComp-zh, and 31.5% Pass@1 on HLE.</p> + https://arxiv.org/abs/2509.13310 + Tue, 16 Sep 2025 17:57:19 +0000 - LazyDrag: Enabling Stable Drag-Based Editing on Multi-Modal Diffusion Transformers via Explicit Correspondence - https://arxiv.org/abs/2509.12203 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.12203.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zixin Yin, Xili Dai, Duomin Wang, Xianfang Zeng, Lionel M. Ni, Gang Yu, Heung-Yeung Shum</p><p><b>Upvotes:</b> 9</p><p><b>Summary:</b> The reliance on implicit point matching via attention has become a core bottleneck in drag-based editing, resulting in a fundamental compromise on weakened inversion strength and costly test-time optimization (TTO). This compromise severely limits the generative capabilities of diffusion models, suppressing high-fidelity inpainting and text-guided creation. In this paper, we introduce LazyDrag, the first drag-based image editing method for Multi-Modal Diffusion Transformers, which directly eliminates the reliance on implicit point matching. In concrete terms, our method generates an explicit correspondence map from user drag inputs as a reliable reference to boost the attention control. This reliable reference opens the potential for a stable full-strength inversion process, which is the first in the drag-based editing task. It obviates the necessity for TTO and unlocks the generative capability of models. Therefore, LazyDrag naturally unifies precise geometric control with text guidance, enabling complex edits that were previously out of reach: opening the mouth of a dog and inpainting its interior, generating new objects like a ``tennis ball'', or for ambiguous drags, making context-aware changes like moving a hand into a pocket. Additionally, LazyDrag supports multi-round workflows with simultaneous move and scale operations. Evaluated on the DragBench, our method outperforms baselines in drag accuracy and perceptual quality, as validated by VIEScore and human evaluation. LazyDrag not only establishes new state-of-the-art performance, but also paves a new way to editing paradigms.</p> - https://arxiv.org/abs/2509.12203 - Mon, 15 Sep 2025 17:59:47 +0000 + Towards General Agentic Intelligence via Environment Scaling + https://arxiv.org/abs/2509.13311 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.13311.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Runnan Fang, Shihao Cai, Baixuan Li, Jialong Wu, Guangyu Li, Wenbiao Yin, Xinyu Wang, Xiaobin Wang, Liangcai Su, Zhen Zhang, Shibin Wu, Zhengwei Tao, Yong Jiang, Pengjun Xie, Fei Huang, Jingren Zhou</p><p><b>Upvotes:</b> 49</p><p><b>Summary:</b> Advanced agentic intelligence is a prerequisite for deploying Large Language Models in practical, real-world applications. Diverse real-world APIs demand precise, robust function-calling intelligence, which needs agents to develop these capabilities through interaction in varied environments. The breadth of function-calling competence is closely tied to the diversity of environments in which agents are trained. In this work, we scale up environments as a step towards advancing general agentic intelligence. This gives rise to two central challenges: (i) how to scale environments in a principled manner, and (ii) how to effectively train agentic capabilities from experiences derived through interactions with these environments. To address these, we design a scalable framework that automatically constructs heterogeneous environments that are fully simulated, systematically broadening the space of function-calling scenarios. We further adapt a two-phase agent fine-tuning strategy: first endowing agents with fundamental agentic capabilities, then specializing them for domain-specific contexts. Extensive experiments on agentic benchmarks, tau-bench, tau2-Bench, and ACEBench, demonstrate that our trained model, AgentScaler, significantly enhances the function-calling capability of models.</p> + https://arxiv.org/abs/2509.13311 + Tue, 16 Sep 2025 17:57:20 +0000 + + + WebWeaver: Structuring Web-Scale Evidence with Dynamic Outlines for Open-Ended Deep Research + https://arxiv.org/abs/2509.13312 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.13312.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zijian Li, Xin Guan, Bo Zhang, Shen Huang, Houquan Zhou, Shaopeng Lai, Ming Yan, Yong Jiang, Pengjun Xie, Fei Huang, Jun Zhang, Jingren Zhou</p><p><b>Upvotes:</b> 74</p><p><b>Summary:</b> This paper tackles open-ended deep research (OEDR), a complex challenge where AI agents must synthesize vast web-scale information into insightful reports. Current approaches are plagued by dual-fold limitations: static research pipelines that decouple planning from evidence acquisition and one-shot generation paradigms that easily suffer from long-context failure issues like "loss in the middle" and hallucinations. To address these challenges, we introduce WebWeaver, a novel dual-agent framework that emulates the human research process. The planner operates in a dynamic cycle, iteratively interleaving evidence acquisition with outline optimization to produce a comprehensive, source-grounded outline linking to a memory bank of evidence. The writer then executes a hierarchical retrieval and writing process, composing the report section by section. By performing targeted retrieval of only the necessary evidence from the memory bank for each part, it effectively mitigates long-context issues. Our framework establishes a new state-of-the-art across major OEDR benchmarks, including DeepResearch Bench, DeepConsult, and DeepResearchGym. These results validate our human-centric, iterative methodology, demonstrating that adaptive planning and focused synthesis are crucial for producing high-quality, reliable, and well-structured reports.</p> + https://arxiv.org/abs/2509.13312 + Tue, 16 Sep 2025 17:57:21 +0000 + + + ReSum: Unlocking Long-Horizon Search Intelligence via Context Summarization + https://arxiv.org/abs/2509.13313 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.13313.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xixi Wu, Kuan Li, Yida Zhao, Liwen Zhang, Litu Ou, Huifeng Yin, Zhongwang Zhang, Yong Jiang, Pengjun Xie, Fei Huang, Minhao Cheng, Shuai Wang, Hong Cheng, Jingren Zhou</p><p><b>Upvotes:</b> 43</p><p><b>Summary:</b> Large Language Model (LLM)-based web agents demonstrate strong performance on knowledge-intensive tasks but are hindered by context window limitations in paradigms like ReAct. Complex queries involving multiple entities, intertwined relationships, and high uncertainty demand extensive search cycles that rapidly exhaust context budgets before reaching complete solutions. To overcome this challenge, we introduce ReSum, a novel paradigm that enables indefinite exploration through periodic context summarization. ReSum converts growing interaction histories into compact reasoning states, maintaining awareness of prior discoveries while bypassing context constraints. For paradigm adaptation, we propose ReSum-GRPO, integrating GRPO with segmented trajectory training and advantage broadcasting to familiarize agents with summary-conditioned reasoning. Extensive experiments on web agents of varying scales across three benchmarks demonstrate that ReSum delivers an average absolute improvement of 4.5\% over ReAct, with further gains of up to 8.2\% following ReSum-GRPO training. Notably, with only 1K training samples, our WebResummer-30B (a ReSum-GRPO-trained version of WebSailor-30B) achieves 33.3\% Pass@1 on BrowseComp-zh and 18.3\% on BrowseComp-en, surpassing existing open-source web agents.</p> + https://arxiv.org/abs/2509.13313 + Tue, 16 Sep 2025 17:57:22 +0000 + + + 3D Aware Region Prompted Vision Language Model + https://arxiv.org/abs/2509.13317 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.13317.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> An-Chieh Cheng, Yang Fu, Yukang Chen, Zhijian Liu, Xiaolong Li, Subhashree Radhakrishnan, Song Han, Yao Lu, Jan Kautz, Pavlo Molchanov, Hongxu Yin, Xiaolong Wang, Sifei Liu</p><p><b>Upvotes:</b> 8</p><p><b>Summary:</b> We present Spatial Region 3D (SR-3D) aware vision-language model that connects single-view 2D images and multi-view 3D data through a shared visual token space. SR-3D supports flexible region prompting, allowing users to annotate regions with bounding boxes, segmentation masks on any frame, or directly in 3D, without the need for exhaustive multi-frame labeling. We achieve this by enriching 2D visual features with 3D positional embeddings, which allows the 3D model to draw upon strong 2D priors for more accurate spatial reasoning across frames, even when objects of interest do not co-occur within the same view. Extensive experiments on both general 2D vision language and specialized 3D spatial benchmarks demonstrate that SR-3D achieves state-of-the-art performance, underscoring its effectiveness for unifying 2D and 3D representation space on scene understanding. Moreover, we observe applicability to in-the-wild videos without sensory 3D inputs or ground-truth 3D annotations, where SR-3D accurately infers spatial relationships and metric measurements.</p> + https://arxiv.org/abs/2509.13317 + Tue, 16 Sep 2025 17:59:06 +0000