diff --git a/feed.xml b/feed.xml index 0f29b60..49754fa 100644 --- a/feed.xml +++ b/feed.xml @@ -7,125 +7,146 @@ http://www.rssboard.org/rss-specification python-feedgen en - Fri, 19 Sep 2025 00:02:39 +0000 + Sat, 20 Sep 2025 00:02:34 +0000 - MedReseacher-R1: Expert-Level Medical Deep Researcher via A Knowledge-Informed Trajectory Synthesis Framework - https://arxiv.org/abs/2508.14880 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.14880.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ailing Yu, Lan Yao, Jingnan Liu, Zhe Chen, Jiajun Yin, Yuan Wang, Xinhao Liao, Zhiling Ye, Ji Li, Yun Yue, Hansong Xiao, Hualei Zhou, Chunxiao Guo, Peng Wei, Jinjie Gu</p><p><b>Upvotes:</b> 9</p><p><b>Summary:</b> Recent developments in Large Language Model (LLM)-based agents have shown impressive capabilities spanning multiple domains, exemplified by deep research systems that demonstrate superior performance on complex information-seeking and synthesis tasks. While general-purpose deep research agents have shown impressive capabilities, they struggle significantly with medical domain challenges, as evidenced by leading proprietary systems achieving limited accuracy on complex medical benchmarks. The key limitations are: (1) the model lacks sufficient dense medical knowledge for clinical reasoning, and (2) the framework is constrained by the absence of specialized retrieval tools tailored for medical contexts.We present a medical deep research agent that addresses these challenges through two core innovations. First, we develop a novel data synthesis framework using medical knowledge graphs, extracting the longest chains from subgraphs around rare medical entities to generate complex multi-hop question-answer pairs. Second, we integrate a custom-built private medical retrieval engine alongside general-purpose tools, enabling accurate medical information synthesis. Our approach generates 2100+ diverse trajectories across 12 medical specialties, each averaging 4.2 tool interactions.Through a two-stage training paradigm combining supervised fine-tuning and online reinforcement learning with composite rewards, our MedResearcher-R1-32B model demonstrates exceptional performance, establishing new state-of-the-art results on medical benchmarks while maintaining competitive performance on general deep research tasks. Our work demonstrates that strategic domain-specific innovations in architecture, tool design, and training data construction can enable smaller open-source models to outperform much larger proprietary systems in specialized domains.</p> - https://arxiv.org/abs/2508.14880 - Wed, 20 Aug 2025 17:51:20 +0000 + Agentic Software Engineering: Foundational Pillars and a Research Roadmap + https://arxiv.org/abs/2509.06216 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.06216.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ahmed E. Hassan, Hao Li, Dayi Lin, Bram Adams, Tse-Hsun Chen, Yutaro Kashiwa, Dong Qiu</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Agentic Software Engineering (SE 3.0) represents a new era where intelligent agents are tasked not with simple code generation, but with achieving complex, goal-oriented SE objectives. To harness these new capabilities while ensuring trustworthiness, we must recognize a fundamental duality within the SE field in the Agentic SE era, comprising two symbiotic modalities: SE for Humans and SE for Agents. This duality demands a radical reimagining of the foundational pillars of SE (actors, processes, tools, and artifacts) which manifest differently across each modality. We propose two purpose-built workbenches to support this vision. The Agent Command Environment (ACE) serves as a command center where humans orchestrate and mentor agent teams, handling outputs such as Merge-Readiness Packs (MRPs) and Consultation Request Packs (CRPs). The Agent Execution Environment (AEE) is a digital workspace where agents perform tasks while invoking human expertise when facing ambiguity or complex trade-offs. This bi-directional partnership, which supports agent-initiated human callbacks and handovers, gives rise to new, structured engineering activities (i.e., processes) that redefine human-AI collaboration, elevating the practice from agentic coding to true agentic software engineering. This paper presents the Structured Agentic Software Engineering (SASE) vision, outlining several of the foundational pillars for the future of SE. The paper culminates in a research roadmap that identifies a few key challenges and opportunities while briefly discussing the resulting impact of this future on SE education. Our goal is not to offer a definitive solution, but to provide a conceptual scaffold with structured vocabulary to catalyze a community-wide dialogue, pushing the SE community to think beyond its classic, human-centric tenets toward a disciplined, scalable, and trustworthy agentic future.</p> + https://arxiv.org/abs/2509.06216 + Sun, 07 Sep 2025 21:40:10 +0000 - Hybrid Quantum-Classical Model for Image Classification - https://arxiv.org/abs/2509.13353 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.13353.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Muhammad Adnan Shahzad</p><p><b>Upvotes:</b> 0</p><p><b>Summary:</b> This study presents a systematic comparison between hybrid quantum-classical neural networks and purely classical models across three benchmark datasets (MNIST, CIFAR100, and STL10) to evaluate their performance, efficiency, and robustness. The hybrid models integrate parameterized quantum circuits with classical deep learning architectures, while the classical counterparts use conventional convolutional neural networks (CNNs). Experiments were conducted over 50 training epochs for each dataset, with evaluations on validation accuracy, test accuracy, training time, computational resource usage, and adversarial robustness (tested with epsilon=0.1 perturbations).Key findings demonstrate that hybrid models consistently outperform classical models in final accuracy, achieving {99.38\% (MNIST), 41.69\% (CIFAR100), and 74.05\% (STL10) validation accuracy, compared to classical benchmarks of 98.21\%, 32.25\%, and 63.76\%, respectively. Notably, the hybrid advantage scales with dataset complexity, showing the most significant gains on CIFAR100 (+9.44\%) and STL10 (+10.29\%). Hybrid models also train 5--12times faster (e.g., 21.23s vs. 108.44s per epoch on MNIST) and use 6--32\% fewer parameters} while maintaining superior generalization to unseen test data.Adversarial robustness tests reveal that hybrid models are significantly more resilient on simpler datasets (e.g., 45.27\% robust accuracy on MNIST vs. 10.80\% for classical) but show comparable fragility on complex datasets like CIFAR100 (sim1\% robustness for both). Resource efficiency analyses indicate that hybrid models consume less memory (4--5GB vs. 5--6GB for classical) and lower CPU utilization (9.5\% vs. 23.2\% on average).These results suggest that hybrid quantum-classical architectures offer compelling advantages in accuracy, training efficiency, and parameter scalability, particularly for complex vision tasks.</p> - https://arxiv.org/abs/2509.13353 - Sun, 14 Sep 2025 09:55:00 +0000 + FSG-Net: Frequency-Spatial Synergistic Gated Network for High-Resolution Remote Sensing Change Detection + https://arxiv.org/abs/2509.06482 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.06482.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhongxiang Xie, Shuangxi Miao, Yuhan Jiang, Zhewei Zhang, Jing Yao, Xuecao Li, Jianxi Huang, Pedram Ghamisi</p><p><b>Upvotes:</b> 0</p><p><b>Summary:</b> Change detection from high-resolution remote sensing images lies as a cornerstone of Earth observation applications, yet its efficacy is often compromised by two critical challenges. First, false alarms are prevalent as models misinterpret radiometric variations from temporal shifts (e.g., illumination, season) as genuine changes. Second, a non-negligible semantic gap between deep abstract features and shallow detail-rich features tends to obstruct their effective fusion, culminating in poorly delineated boundaries. To step further in addressing these issues, we propose the Frequency-Spatial Synergistic Gated Network (FSG-Net), a novel paradigm that aims to systematically disentangle semantic changes from nuisance variations. Specifically, FSG-Net first operates in the frequency domain, where a Discrepancy-Aware Wavelet Interaction Module (DAWIM) adaptively mitigates pseudo-changes by discerningly processing different frequency components. Subsequently, the refined features are enhanced in the spatial domain by a Synergistic Temporal-Spatial Attention Module (STSAM), which amplifies the saliency of genuine change regions. To finally bridge the semantic gap, a Lightweight Gated Fusion Unit (LGFU) leverages high-level semantics to selectively gate and integrate crucial details from shallow layers. Comprehensive experiments on the CDD, GZ-CD, and LEVIR-CD benchmarks validate the superiority of FSG-Net, establishing a new state-of-the-art with F1-scores of 94.16%, 89.51%, and 91.27%, respectively. The code will be made available at https://github.com/zxXie-Air/FSG-Net after a possible publication.</p> + https://arxiv.org/abs/2509.06482 + Mon, 08 Sep 2025 09:46:33 +0000 - Image Tokenizer Needs Post-Training - https://arxiv.org/abs/2509.12474 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.12474.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Kai Qiu, Xiang Li, Hao Chen, Jason Kuen, Xiaohao Xu, Jiuxiang Gu, Yinyi Luo, Bhiksha Raj, Zhe Lin, Marios Savvides</p><p><b>Upvotes:</b> 0</p><p><b>Summary:</b> Recent image generative models typically capture the image distribution in a pre-constructed latent space, relying on a frozen image tokenizer. However, there exists a significant discrepancy between the reconstruction and generation distribution, where current tokenizers only prioritize the reconstruction task that happens before generative training without considering the generation errors during sampling. In this paper, we comprehensively analyze the reason for this discrepancy in a discrete latent space, and, from which, we propose a novel tokenizer training scheme including both main-training and post-training, focusing on improving latent space construction and decoding respectively. During the main training, a latent perturbation strategy is proposed to simulate sampling noises, \ie, the unexpected tokens generated in generative inference. Specifically, we propose a plug-and-play tokenizer training scheme, which significantly enhances the robustness of tokenizer, thus boosting the generation quality and convergence speed, and a novel tokenizer evaluation metric, \ie, pFID, which successfully correlates the tokenizer performance to generation quality. During post-training, we further optimize the tokenizer decoder regarding a well-trained generative model to mitigate the distribution difference between generated and reconstructed tokens. With a sim400M generator, a discrete tokenizer trained with our proposed main training achieves a notable 1.60 gFID and further obtains 1.36 gFID with the additional post-training. Further experiments are conducted to broadly validate the effectiveness of our post-training strategy on off-the-shelf discrete and continuous tokenizers, coupled with autoregressive and diffusion-based generators.</p> - https://arxiv.org/abs/2509.12474 - Mon, 15 Sep 2025 21:38:03 +0000 + Can Multimodal LLMs See Materials Clearly? A Multimodal Benchmark on Materials Characterization + https://arxiv.org/abs/2509.09307 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.09307.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhengzhao Lai, Youbin Zheng, Zhenyang Cai, Haonan Lyu, Jinpu Yang, Hongqing Liang, Yan Hu, Benyou Wang</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Materials characterization is fundamental to acquiring materials information, revealing the processing-microstructure-property relationships that guide material design and optimization. While multimodal large language models (MLLMs) have recently shown promise in generative and predictive tasks within materials science, their capacity to understand real-world characterization imaging data remains underexplored. To bridge this gap, we present MatCha, the first benchmark for materials characterization image understanding, comprising 1,500 questions that demand expert-level domain expertise. MatCha encompasses four key stages of materials research comprising 21 distinct tasks, each designed to reflect authentic challenges faced by materials scientists. Our evaluation of state-of-the-art MLLMs on MatCha reveals a significant performance gap compared to human experts. These models exhibit degradation when addressing questions requiring higher-level expertise and sophisticated visual perception. Simple few-shot and chain-of-thought prompting struggle to alleviate these limitations. These findings highlight that existing MLLMs still exhibit limited adaptability to real-world materials characterization scenarios. We hope MatCha will facilitate future research in areas such as new material discovery and autonomous scientific agents. MatCha is available at https://github.com/FreedomIntelligence/MatCha.</p> + https://arxiv.org/abs/2509.09307 + Thu, 11 Sep 2025 09:50:16 +0000 - PANORAMA: The Rise of Omnidirectional Vision in the Embodied AI Era - https://arxiv.org/abs/2509.12989 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.12989.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xu Zheng, Chenfei Liao, Ziqiao Weng, Kaiyu Lei, Zihao Dongfang, Haocong He, Yuanhuiyi Lyu, Lutao Jiang, Lu Qi, Li Chen, Danda Pani Paudel, Kailun Yang, Linfeng Zhang, Luc Van Gool, Xuming Hu</p><p><b>Upvotes:</b> 20</p><p><b>Summary:</b> Omnidirectional vision, using 360-degree vision to understand the environment, has become increasingly critical across domains like robotics, industrial inspection, and environmental monitoring. Compared to traditional pinhole vision, omnidirectional vision provides holistic environmental awareness, significantly enhancing the completeness of scene perception and the reliability of decision-making. However, foundational research in this area has historically lagged behind traditional pinhole vision. This talk presents an emerging trend in the embodied AI era: the rapid development of omnidirectional vision, driven by growing industrial demand and academic interest. We highlight recent breakthroughs in omnidirectional generation, omnidirectional perception, omnidirectional understanding, and related datasets. Drawing on insights from both academia and industry, we propose an ideal panoramic system architecture in the embodied AI era, PANORAMA, which consists of four key subsystems. Moreover, we offer in-depth opinions related to emerging trends and cross-community impacts at the intersection of panoramic vision and embodied AI, along with the future roadmap and open challenges. This overview synthesizes state-of-the-art advancements and outlines challenges and opportunities for future research in building robust, general-purpose omnidirectional AI systems in the embodied AI era.</p> - https://arxiv.org/abs/2509.12989 - Tue, 16 Sep 2025 11:54:37 +0000 + RecoWorld: Building Simulated Environments for Agentic Recommender Systems + https://arxiv.org/abs/2509.10397 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.10397.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Fei Liu, Xinyu Lin, Hanchao Yu, Mingyuan Wu, Jianyu Wang, Qiang Zhang, Zhuokai Zhao, Yinglong Xia, Yao Zhang, Weiwei Li, Mingze Gao, Qifan Wang, Lizhu Zhang, Benyu Zhang, Xiangjun Fan</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> We present RecoWorld, a blueprint for building simulated environments tailored to agentic recommender systems. Such environments give agents a proper training space where they can learn from errors without impacting real users. RecoWorld distinguishes itself with a dual-view architecture: a simulated user and an agentic recommender engage in multi-turn interactions aimed at maximizing user retention. The user simulator reviews recommended items, updates its mindset, and when sensing potential user disengagement, generates reflective instructions. The agentic recommender adapts its recommendations by incorporating these user instructions and reasoning traces, creating a dynamic feedback loop that actively engages users. This process leverages the exceptional reasoning capabilities of modern LLMs. We explore diverse content representations within the simulator, including text-based, multimodal, and semantic ID modeling, and discuss how multi-turn RL enables the recommender to refine its strategies through iterative interactions. RecoWorld also supports multi-agent simulations, allowing creators to simulate the responses of targeted user populations. It marks an important first step toward recommender systems where users and agents collaboratively shape personalized information streams. We envision new interaction paradigms where "user instructs, recommender responds," jointly optimizing user retention and engagement.</p> + https://arxiv.org/abs/2509.10397 + Fri, 12 Sep 2025 16:44:34 +0000 - SteeringControl: Holistic Evaluation of Alignment Steering in LLMs - https://arxiv.org/abs/2509.13450 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.13450.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Vincent Siu, Nicholas Crispino, David Park, Nathan W. Henry, Zhun Wang, Yang Liu, Dawn Song, Chenguang Wang</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> We introduce SteeringControl, a benchmark for evaluating representation steering methods across core alignment objectives--bias, harmful generation, and hallucination--and their effects on secondary behaviors such as sycophancy and commonsense morality. While prior alignment work often highlights truthfulness or reasoning ability to demonstrate the side effects of representation steering, we find there are many unexplored tradeoffs not yet understood in a systematic way. We collect a dataset of safety-relevant primary and secondary behaviors to evaluate steering effectiveness and behavioral entanglement centered around five popular steering methods. To enable this, we craft a modular steering framework based on unique components that serve as the building blocks of many existing methods. Our results on Qwen-2.5-7B and Llama-3.1-8B find that strong steering performance is dependent on the specific combination of steering method, model, and targeted behavior, and that severe concept entanglement can result from poor combinations of these three as well. We release our code here: https://github.com/wang-research-lab/SteeringControl.git.</p> - https://arxiv.org/abs/2509.13450 - Tue, 16 Sep 2025 18:36:22 +0000 + Developer-LLM Conversations: An Empirical Study of Interactions and Generated Code Quality + https://arxiv.org/abs/2509.10402 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.10402.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Suzhen Zhong, Ying Zou, Bram Adams</p><p><b>Upvotes:</b> 0</p><p><b>Summary:</b> Large Language Models (LLMs) are becoming integral to modern software development workflows, assisting developers with code generation, API explanation, and iterative problem-solving through natural language conversations. Despite widespread adoption, there is limited understanding of how developers interact with LLMs in practice and how these conversational dynamics influence task outcomes, code quality, and software engineering workflows. To address this, we leverage CodeChat, a large dataset comprising 82,845 real-world developer-LLM conversations, containing 368,506 code snippets generated across over 20 programming languages, derived from the WildChat dataset. We find that LLM responses are substantially longer than developer prompts, with a median token-length ratio of 14:1. Multi-turn conversations account for 68% of the dataset and often evolve due to shifting requirements, incomplete prompts, or clarification requests. Topic analysis identifies web design (9.6% of conversations) and neural network training (8.7% of conversations) as the most frequent LLM-assisted tasks. Evaluation across five languages (i.e., Python, JavaScript, C++, Java, and C#) reveals prevalent and language-specific issues in LLM-generated code: generated Python and JavaScript code often include undefined variables (83.4% and 75.3% of code snippets, respectively); Java code lacks required comments (75.9%); C++ code frequently omits headers (41.1%) and C# code shows unresolved namespaces (49.2%). During a conversation, syntax and import errors persist across turns; however, documentation quality in Java improves by up to 14.7%, and import handling in Python improves by 3.7% over 5 turns. Prompts that point out mistakes in code generated in prior turns and explicitly request a fix are most effective for resolving errors.</p> + https://arxiv.org/abs/2509.10402 + Fri, 12 Sep 2025 16:52:49 +0000 - AERIS: Argonne Earth Systems Model for Reliable and Skillful Predictions - https://arxiv.org/abs/2509.13523 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.13523.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Väinö Hatanpää, Eugene Ku, Jason Stock, Murali Emani, Sam Foreman, Chunyong Jung, Sandeep Madireddy, Tung Nguyen, Varuni Sastry, Ray A. O. Sinurat, Sam Wheeler, Huihuo Zheng, Troy Arcomano, Venkatram Vishwanath, Rao Kotamarthi</p><p><b>Upvotes:</b> 6</p><p><b>Summary:</b> Generative machine learning offers new opportunities to better understand complex Earth system dynamics. Recent diffusion-based methods address spectral biases and improve ensemble calibration in weather forecasting compared to deterministic methods, yet have so far proven difficult to scale stably at high resolutions. We introduce AERIS, a 1.3 to 80B parameter pixel-level Swin diffusion transformer to address this gap, and SWiPe, a generalizable technique that composes window parallelism with sequence and pipeline parallelism to shard window-based transformers without added communication cost or increased global batch size. On Aurora (10,080 nodes), AERIS sustains 10.21 ExaFLOPS (mixed precision) and a peak performance of 11.21 ExaFLOPS with 1 times 1 patch size on the 0.25{\deg} ERA5 dataset, achieving 95.5% weak scaling efficiency, and 81.6% strong scaling efficiency. AERIS outperforms the IFS ENS and remains stable on seasonal scales to 90 days, highlighting the potential of billion-parameter diffusion models for weather and climate prediction.</p> - https://arxiv.org/abs/2509.13523 - Tue, 16 Sep 2025 20:38:29 +0000 + FinSearchComp: Towards a Realistic, Expert-Level Evaluation of Financial Search and Reasoning + https://arxiv.org/abs/2509.13160 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.13160.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Liang Hu, Jianpeng Jiao, Jiashuo Liu, Yanle Ren, Zhoufutu Wen, Kaiyuan Zhang, Xuanliang Zhang, Xiang Gao, Tianci He, Fei Hu, Yali Liao, Zaiyuan Wang, Chenghao Yang, Qianyu Yang, Mingren Yin, Zhiyuan Zeng, Ge Zhang, Xinyi Zhang, Xiying Zhao, Zhenwei Zhu, Hongseok Namkoong, Wenhao Huang, Yuwen Tang</p><p><b>Upvotes:</b> 21</p><p><b>Summary:</b> Search has emerged as core infrastructure for LLM-based agents and is widely viewed as critical on the path toward more general intelligence. Finance is a particularly demanding proving ground: analysts routinely conduct complex, multi-step searches over time-sensitive, domain-specific data, making it ideal for assessing both search proficiency and knowledge-grounded reasoning. Yet no existing open financial datasets evaluate data searching capability of end-to-end agents, largely because constructing realistic, complicated tasks requires deep financial expertise and time-sensitive data is hard to evaluate. We present FinSearchComp, the first fully open-source agent benchmark for realistic, open-domain financial search and reasoning. FinSearchComp comprises three tasks -- Time-Sensitive Data Fetching, Simple Historical Lookup, and Complex Historical Investigation -- closely reproduce real-world financial analyst workflows. To ensure difficulty and reliability, we engage 70 professional financial experts for annotation and implement a rigorous multi-stage quality-assurance pipeline. The benchmark includes 635 questions spanning global and Greater China markets, and we evaluate 21 models (products) on it. Grok 4 (web) tops the global subset, approaching expert-level accuracy. DouBao (web) leads on the Greater China subset. Experimental analyses show that equipping agents with web search and financial plugins substantially improves results on FinSearchComp, and the country origin of models and tools impact performance significantly.By aligning with realistic analyst tasks and providing end-to-end evaluation, FinSearchComp offers a professional, high-difficulty testbed for complex financial search and reasoning.</p> + https://arxiv.org/abs/2509.13160 + Tue, 16 Sep 2025 15:13:13 +0000 - LLM-I: LLMs are Naturally Interleaved Multimodal Creators - https://arxiv.org/abs/2509.13642 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.13642.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zirun Guo, Feng Zhang, Kai Jia, Tao Jin</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> We propose LLM-Interleaved (LLM-I), a flexible and dynamic framework that reframes interleaved image-text generation as a tool-use problem. LLM-I is designed to overcome the "one-tool" bottleneck of current unified models, which are limited to synthetic imagery and struggle with tasks requiring factual grounding or programmatic precision. Our framework empowers a central LLM or MLLM agent to intelligently orchestrate a diverse toolkit of specialized visual tools, including online image search, diffusion-based generation, code execution, and image editing. The agent is trained to select and apply these tools proficiently via a Reinforcement Learning (RL) framework that features a hybrid reward system combining rule-based logic with judgments from LLM and MLLM evaluators. Trained on a diverse new dataset using four different model backbones, LLM-I demonstrates state-of-the-art performance, outperforming existing methods by a large margin across four benchmarks. We also introduce a novel test-time scaling strategy that provides further performance gains. Project Page: https://github.com/ByteDance-BandAI/LLM-I.</p> - https://arxiv.org/abs/2509.13642 - Wed, 17 Sep 2025 02:33:29 +0000 + EdiVal-Agent: An Object-Centric Framework for Automated, Scalable, Fine-Grained Evaluation of Multi-Turn Editing + https://arxiv.org/abs/2509.13399 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.13399.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Tianyu Chen, Yasi Zhang, Zhi Zhang, Peiyu Yu, Shu Wang, Zhendong Wang, Kevin Lin, Xiaofei Wang, Zhengyuan Yang, Linjie Li, Chung-Ching Lin, Jianwen Xie, Oscar Leong, Lijuan Wang, Ying Nian Wu, Mingyuan Zhou</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Instruction-based image editing has advanced rapidly, yet reliable and interpretable evaluation remains a bottleneck. Current protocols either (i) depend on paired reference images -- resulting in limited coverage and inheriting biases from prior generative models -- or (ii) rely solely on zero-shot vision-language models (VLMs), whose prompt-based assessments of instruction following, content consistency, and visual quality are often imprecise. To address this, we introduce EdiVal-Agent, an automated, scalable, and fine-grained evaluation framework for multi-turn instruction-based editing from an object-centric perspective, supported by a suite of expert tools. Given an image, EdiVal-Agent first decomposes it into semantically meaningful objects, then synthesizes diverse, context-aware editing instructions. For evaluation, it integrates VLMs with open-vocabulary object detectors to assess instruction following, uses semantic-level feature extractors to evaluate content consistency, and leverages human preference models to judge visual quality. We show that combining VLMs with object detectors yields stronger agreement with human judgments in instruction-following evaluation compared to using VLMs alone and CLIP-based metrics. Furthermore, the pipeline's modular design allows future tools to be seamlessly integrated, enhancing evaluation accuracy over time. Instantiating this pipeline, we build EdiVal-Bench, a multi-turn editing benchmark covering 9 instruction types and 11 state-of-the-art editing models spanning autoregressive (AR) (including Nano Banana, GPT-Image-1), flow-matching, and diffusion paradigms. We demonstrate that EdiVal-Agent can be used to identify existing failure modes, thereby informing the development of the next generation of editing models. Project page: https://tianyucodings.github.io/EdiVAL-page/.</p> + https://arxiv.org/abs/2509.13399 + Tue, 16 Sep 2025 17:45:39 +0000 - Improving Context Fidelity via Native Retrieval-Augmented Reasoning - https://arxiv.org/abs/2509.13683 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.13683.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Suyuchen Wang, Jinlin Wang, Xinyu Wang, Shiqi Li, Xiangru Tang, Sirui Hong, Xiao-Wen Chang, Chenglin Wu, Bang Liu</p><p><b>Upvotes:</b> 6</p><p><b>Summary:</b> Large language models (LLMs) often struggle with context fidelity, producing inconsistent answers when responding to questions based on provided information. Existing approaches either rely on expensive supervised fine-tuning to generate evidence post-answer or train models to perform web searches without necessarily improving utilization of the given context. We propose CARE, a novel native retrieval-augmented reasoning framework that teaches LLMs to explicitly integrate in-context evidence within their reasoning process with the model's own retrieval capabilities. Our method requires limited labeled evidence data while significantly enhancing both retrieval accuracy and answer generation performance through strategically retrieved in-context tokens in the reasoning chain. Extensive experiments on multiple real-world and counterfactual QA benchmarks demonstrate that our approach substantially outperforms supervised fine-tuning, traditional retrieval-augmented generation methods, and external retrieval solutions. This work represents a fundamental advancement in making LLMs more accurate, reliable, and efficient for knowledge-intensive tasks.</p> - https://arxiv.org/abs/2509.13683 - Wed, 17 Sep 2025 04:28:07 +0000 + Apertus: Democratizing Open and Compliant LLMs for Global Language Environments + https://arxiv.org/abs/2509.14233 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.14233.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Alejandro Hernández-Cano, Alexander Hägele, Allen Hao Huang, Angelika Romanou, Antoni-Joan Solergibert, Barna Pasztor, Bettina Messmer, Dhia Garbaya, Eduard Frank Ďurech, Ido Hakimi, Juan García Giraldo, Mete Ismayilzada, Negar Foroutan, Skander Moalla, Tiancheng Chen, Vinko Sabolčec, Yixuan Xu, Michael Aerni, Badr AlKhamissi, Ines Altemir Marinas, Mohammad Hossein Amani, Matin Ansaripour, Ilia Badanin, Harold Benoit, Emanuela Boros, Nicholas Browning, Fabian Bösch, Maximilian Böther, Niklas Canova, Camille Challier, Clement Charmillot, Jonathan Coles, Jan Deriu, Arnout Devos, Lukas Drescher, Daniil Dzenhaliou, Maud Ehrmann, Dongyang Fan, Simin Fan, Silin Gao, Miguel Gila, María Grandury, Diba Hashemi, Alexander Hoyle, Jiaming Jiang, Mark Klein, Andrei Kucharavy, Anastasiia Kucherenko, Frederike Lübeck, Roman Machacek, Theofilos Manitaras, Andreas Marfurt, Kyle Matoba, Simon Matrenok, Henrique Mendoncça, Fawzi Roberto Mohamed, Syrielle Montariol, Luca Mouchel, Sven Najem-Meyer, Jingwei Ni, Gennaro Oliva, Matteo Pagliardini, Elia Palme, Andrei Panferov, Léo Paoletti, Marco Passerini, Ivan Pavlov, Auguste Poiroux, Kaustubh Ponkshe, Nathan Ranchin, Javi Rando, Mathieu Sauser, Jakhongir Saydaliev, Muhammad Ali Sayfiddinov, Marian Schneider, Stefano Schuppli, Marco Scialanga, Andrei Semenov, Kumar Shridhar, Raghav Singhal, Anna Sotnikova, Alexander Sternfeld, Ayush Kumar Tarun, Paul Teiletche, Jannis Vamvas, Xiaozhe Yao, Hao Zhao Alexander Ilic, Ana Klimovic, Andreas Krause, Caglar Gulcehre, David Rosenthal, Elliott Ash, Florian Tramèr, Joost VandeVondele, Livio Veraldi, Martin Rajman, Thomas Schulthess, Torsten Hoefler, Antoine Bosselut, Martin Jaggi, Imanol Schlag</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> We present Apertus, a fully open suite of large language models (LLMs) designed to address two systemic shortcomings in today's open model ecosystem: data compliance and multilingual representation. Unlike many prior models that release weights without reproducible data pipelines or regard for content-owner rights, Apertus models are pretrained exclusively on openly available data, retroactively respecting robots.txt exclusions and filtering for non-permissive, toxic, and personally identifiable content. To mitigate risks of memorization, we adopt the Goldfish objective during pretraining, strongly suppressing verbatim recall of data while retaining downstream task performance. The Apertus models also expand multilingual coverage, training on 15T tokens from over 1800 languages, with ~40% of pretraining data allocated to non-English content. Released at 8B and 70B scales, Apertus approaches state-of-the-art results among fully open models on multilingual benchmarks, rivalling or surpassing open-weight counterparts. Beyond model weights, we release all scientific artifacts from our development cycle with a permissive license, including data preparation scripts, checkpoints, evaluation suites, and training code, enabling transparent audit and extension.</p> + https://arxiv.org/abs/2509.14233 + Wed, 17 Sep 2025 17:59:21 +0000 - Scrub It Out! Erasing Sensitive Memorization in Code Language Models via Machine Unlearning - https://arxiv.org/abs/2509.13755 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.13755.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhaoyang Chu, Yao Wan, Zhikun Zhang, Di Wang, Zhou Yang, Hongyu Zhang, Pan Zhou, Xuanhua Shi, Hai Jin, David Lo</p><p><b>Upvotes:</b> 12</p><p><b>Summary:</b> While Code Language Models (CLMs) have demonstrated superior performance in software engineering tasks such as code generation and summarization, recent empirical studies reveal a critical privacy vulnerability: these models exhibit unintended memorization of sensitive training data, enabling verbatim reproduction of confidential information when specifically prompted. To address this issue, several approaches, including training data de-duplication and differential privacy augmentation, have been proposed. However, these methods require full-model retraining for deployed CLMs, which incurs substantial computational costs. In this paper, we aim to answer the following research question: Can sensitive information memorized by CLMs be erased effectively and efficiently? We conduct a pioneering investigation into erasing sensitive memorization in CLMs through machine unlearning - a post-hoc modification method that removes specific information from trained models without requiring full retraining. Specifically, we first quantify the memorization risks of sensitive data within CLM training datasets and curate a high-risk dataset of 50,000 sensitive memorized samples as unlearning targets. We study two widely used gradient ascent-based unlearning approaches: the vanilla and constraint-based methods, and introduce CodeEraser, an advanced variant that selectively unlearns sensitive memorized segments in code while preserving the structural integrity and functional correctness of the surrounding code. Extensive experiments on three families of CLMs, i.e., CodeParrot, CodeGen-Mono, and Qwen2.5-Coder, validate the effectiveness and efficiency of CodeEraser in erasing targeted sensitive memorization while maintaining model utility.</p> - https://arxiv.org/abs/2509.13755 - Wed, 17 Sep 2025 07:12:35 +0000 + AToken: A Unified Tokenizer for Vision + https://arxiv.org/abs/2509.14476 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.14476.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jiasen Lu, Liangchen Song, Mingze Xu, Byeongjoo Ahn, Yanjun Wang, Chen Chen, Afshin Dehghan, Yinfei Yang</p><p><b>Upvotes:</b> 11</p><p><b>Summary:</b> We present AToken, the first unified visual tokenizer that achieves both high-fidelity reconstruction and semantic understanding across images, videos, and 3D assets. Unlike existing tokenizers that specialize in either reconstruction or understanding for single modalities, AToken encodes these diverse visual inputs into a shared 4D latent space, unifying both tasks and modalities in a single framework. Specifically, we introduce a pure transformer architecture with 4D rotary position embeddings to process visual inputs of arbitrary resolutions and temporal durations. To ensure stable training, we introduce an adversarial-free training objective that combines perceptual and Gram matrix losses, achieving state-of-the-art reconstruction quality. By employing a progressive training curriculum, AToken gradually expands from single images, videos, and 3D, and supports both continuous and discrete latent tokens. AToken achieves 0.21 rFID with 82.2% ImageNet accuracy for images, 3.01 rFVD with 32.6% MSRVTT retrieval for videos, and 28.19 PSNR with 90.9% classification accuracy for 3D. In downstream applications, AToken enables both visual generation tasks (e.g., image generation with continuous and discrete tokens, text-to-video generation, image-to-3D synthesis) and understanding tasks (e.g., multimodal LLMs), achieving competitive performance across all benchmarks. These results shed light on the next-generation multimodal AI systems built upon unified visual tokenization.</p> + https://arxiv.org/abs/2509.14476 + Wed, 17 Sep 2025 23:11:18 +0000 - THOR: Tool-Integrated Hierarchical Optimization via RL for Mathematical Reasoning - https://arxiv.org/abs/2509.13761 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.13761.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Qikai Chang, Zhenrong Zhang, Pengfei Hu, Jiefeng Ma, Yicheng Pan, Jianshu Zhang, Jun Du, Quan Liu, Jianqing Gao</p><p><b>Upvotes:</b> 7</p><p><b>Summary:</b> Large Language Models (LLMs) have made remarkable progress in mathematical reasoning, but still continue to struggle with high-precision tasks like numerical computation and formal symbolic manipulation. Integrating external tools has emerged as a promising approach to bridge this gap. Despite recent advances, existing methods struggle with three key challenges: constructing tool-integrated reasoning data, performing fine-grained optimization, and enhancing inference. To overcome these limitations, we propose THOR (Tool-Integrated Hierarchical Optimization via RL). First, we introduce TIRGen, a multi-agent actor-critic-based pipeline for constructing high-quality datasets of tool-integrated reasoning paths, aligning with the policy and generalizing well across diverse models. Second, to perform fine-grained hierarchical optimization, we introduce an RL strategy that jointly optimizes for both trajectory-level problem solving and step-level code generation. This is motivated by our key insight that the success of an intermediate tool call is a strong predictor of the final answer's correctness. Finally, THOR incorporates a self-correction mechanism that leverages immediate tool feedback to dynamically revise erroneous reasoning paths during inference. Our approach demonstrates strong generalization across diverse models, performing effectively in both reasoning and non-reasoning models. It further achieves state-of-the-art performance for models of a similar scale on multiple mathematical benchmarks, while also delivering consistent improvements on code benchmarks. Our code will be publicly available at https://github.com/JingMog/THOR.</p> - https://arxiv.org/abs/2509.13761 - Wed, 17 Sep 2025 07:16:12 +0000 + MultiEdit: Advancing Instruction-based Image Editing on Diverse and Challenging Tasks + https://arxiv.org/abs/2509.14638 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.14638.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Mingsong Li, Lin Liu, Hongjun Wang, Haoxing Chen, Xijun Gu, Shizhan Liu, Dong Gong, Junbo Zhao, Zhenzhong Lan, Jianguo Li</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> Current instruction-based image editing (IBIE) methods struggle with challenging editing tasks, as both editing types and sample counts of existing datasets are limited. Moreover, traditional dataset construction often contains noisy image-caption pairs, which may introduce biases and limit model capabilities in complex editing scenarios. To address these limitations, we introduce MultiEdit, a comprehensive dataset featuring over 107K high-quality image editing samples. It encompasses 6 challenging editing tasks through a diverse collection of 18 non-style-transfer editing types and 38 style transfer operations, covering a spectrum from sophisticated style transfer to complex semantic operations like person reference editing and in-image text editing. We employ a novel dataset construction pipeline that utilizes two multi-modal large language models (MLLMs) to generate visual-adaptive editing instructions and produce high-fidelity edited images, respectively. Extensive experiments demonstrate that fine-tuning foundational open-source models with our MultiEdit-Train set substantially improves models' performance on sophisticated editing tasks in our proposed MultiEdit-Test benchmark, while effectively preserving their capabilities on the standard editing benchmark. We believe MultiEdit provides a valuable resource for advancing research into more diverse and challenging IBIE capabilities. Our dataset is available at https://huggingface.co/datasets/inclusionAI/MultiEdit.</p> + https://arxiv.org/abs/2509.14638 + Thu, 18 Sep 2025 05:33:38 +0000 - Hala Technical Report: Building Arabic-Centric Instruction & Translation Models at Scale - https://arxiv.org/abs/2509.14008 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.14008.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Hasan Abed Al Kader Hammoud, Mohammad Zbeeb, Bernard Ghanem</p><p><b>Upvotes:</b> 66</p><p><b>Summary:</b> We present Hala, a family of Arabic-centric instruction and translation models built with our translate-and-tune pipeline. We first compress a strong ARleftrightarrowEN teacher to FP8 (yielding sim2times higher throughput with no quality loss) and use it to create high-fidelity bilingual supervision. A lightweight language model LFM2-1.2B is then fine-tuned on this data and used to translate high-quality English instruction sets into Arabic, producing a million-scale corpus tailored to instruction following. We train Hala models at 350M, 700M, 1.2B, and 9B parameters, and apply slerp merging to balance Arabic specialization with base-model strengths. On Arabic-centric benchmarks, Hala achieves state-of-the-art results within both the "nano" (leq2B) and "small" (7-9B) categories, outperforming their bases. We release models, data, evaluation, and recipes to accelerate research in Arabic NLP.</p> - https://arxiv.org/abs/2509.14008 - Wed, 17 Sep 2025 14:19:28 +0000 + Reasoning over Boundaries: Enhancing Specification Alignment via Test-time Delibration + https://arxiv.org/abs/2509.14760 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.14760.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Haoran Zhang, Yafu Li, Xuyang Hu, Dongrui Liu, Zhilin Wang, Bo Li, Yu Cheng</p><p><b>Upvotes:</b> 43</p><p><b>Summary:</b> Large language models (LLMs) are increasingly applied in diverse real-world scenarios, each governed by bespoke behavioral and safety specifications (spec) custom-tailored by users or organizations. These spec, categorized into safety-spec and behavioral-spec, vary across scenarios and evolve with changing preferences and requirements. We formalize this challenge as specification alignment, focusing on LLMs' ability to follow dynamic, scenario-specific spec from both behavioral and safety perspectives. To address this challenge, we propose Align3, a lightweight method that employs Test-Time Deliberation (TTD) with hierarchical reflection and revision to reason over the specification boundaries. We further present SpecBench, a unified benchmark for measuring specification alignment, covering 5 scenarios, 103 spec, and 1,500 prompts. Experiments on 15 reasoning and 18 instruct models with several TTD methods, including Self-Refine, TPO, and MoreThink, yield three key findings: (i) test-time deliberation enhances specification alignment; (ii) Align3 advances the safety-helpfulness trade-off frontier with minimal overhead; (iii) SpecBench effectively reveals alignment gaps. These results highlight the potential of test-time deliberation as an effective strategy for reasoning over the real-world specification boundaries.</p> + https://arxiv.org/abs/2509.14760 + Thu, 18 Sep 2025 09:08:53 +0000 - Quantum Variational Activation Functions Empower Kolmogorov-Arnold Networks - https://arxiv.org/abs/2509.14026 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.14026.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jiun-Cheng Jiang, Morris Yu-Chao Huang, Tianlong Chen, Hsi-Sheng Goan</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Variational quantum circuits (VQCs) are central to quantum machine learning, while recent progress in Kolmogorov-Arnold networks (KANs) highlights the power of learnable activation functions. We unify these directions by introducing quantum variational activation functions (QVAFs), realized through single-qubit data re-uploading circuits called DatA Re-Uploading ActivatioNs (DARUANs). We show that DARUAN with trainable weights in data pre-processing possesses an exponentially growing frequency spectrum with data repetitions, enabling an exponential reduction in parameter size compared with Fourier-based activations without loss of expressivity. Embedding DARUAN into KANs yields quantum-inspired KANs (QKANs), which retain the interpretability of KANs while improving their parameter efficiency, expressivity, and generalization. We further introduce two novel techniques to enhance scalability, feasibility and computational efficiency, such as layer extension and hybrid QKANs (HQKANs) as drop-in replacements of multi-layer perceptrons (MLPs) for feed-forward networks in large-scale models. We provide theoretical analysis and extensive experiments on function regression, image classification, and autoregressive generative language modeling, demonstrating the efficiency and scalability of QKANs. DARUANs and QKANs offer a promising direction for advancing quantum machine learning on both noisy intermediate-scale quantum (NISQ) hardware and classical quantum simulators.</p> - https://arxiv.org/abs/2509.14026 - Wed, 17 Sep 2025 14:28:42 +0000 + EchoVLM: Dynamic Mixture-of-Experts Vision-Language Model for Universal Ultrasound Intelligence + https://arxiv.org/abs/2509.14977 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.14977.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Chaoyin She, Ruifang Lu, Lida Chen, Wei Wang, Qinghua Huang</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Ultrasound imaging has become the preferred imaging modality for early cancer screening due to its advantages of non-ionizing radiation, low cost, and real-time imaging capabilities. However, conventional ultrasound diagnosis heavily relies on physician expertise, presenting challenges of high subjectivity and low diagnostic efficiency. Vision-language models (VLMs) offer promising solutions for this issue, but existing general-purpose models demonstrate limited knowledge in ultrasound medical tasks, with poor generalization in multi-organ lesion recognition and low efficiency across multi-task diagnostics. To address these limitations, we propose EchoVLM, a vision-language model specifically designed for ultrasound medical imaging. The model employs a Mixture of Experts (MoE) architecture trained on data spanning seven anatomical regions. This design enables the model to perform multiple tasks, including ultrasound report generation, diagnosis and visual question-answering (VQA). The experimental results demonstrated that EchoVLM achieved significant improvements of 10.15 and 4.77 points in BLEU-1 scores and ROUGE-1 scores respectively compared to Qwen2-VL on the ultrasound report generation task. These findings suggest that EchoVLM has substantial potential to enhance diagnostic accuracy in ultrasound imaging, thereby providing a viable technical solution for future clinical applications. Source code and model weights are available at https://github.com/Asunatan/EchoVLM.</p> + https://arxiv.org/abs/2509.14977 + Thu, 18 Sep 2025 14:07:53 +0000 - SAIL-VL2 Technical Report - https://arxiv.org/abs/2509.14033 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.14033.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Weijie Yin, Yongjie Ye, Fangxun Shu, Yue Liao, Zijian Kang, Hongyuan Dong, Haiyang Yu, Dingkang Yang, Jiacong Wang, Han Wang, Wenzhuo Liu, Xiao Liang, Shuicheng Yan, Chao Feng</p><p><b>Upvotes:</b> 29</p><p><b>Summary:</b> We introduce SAIL-VL2, an open-suite vision-language foundation model (LVM) for comprehensive multimodal understanding and reasoning. As the successor to SAIL-VL, SAIL-VL2 achieves state-of-the-art performance at the 2B and 8B parameter scales across diverse image and video benchmarks, demonstrating strong capabilities from fine-grained perception to complex reasoning. Three core innovations drive its effectiveness. First, a large-scale data curation pipeline with scoring and filtering strategies enhances both quality and distribution across captioning, OCR, QA, and video data, improving training efficiency. Second, a progressive training framework begins with a powerful pre-trained vision encoder (SAIL-ViT), advances through multimodal pre-training, and culminates in a thinking-fusion SFT-RL hybrid paradigm that systematically strengthens model capabilities. Third, architectural advances extend beyond dense LLMs to efficient sparse Mixture-of-Experts (MoE) designs. With these contributions, SAIL-VL2 demonstrates competitive performance across 106 datasets and achieves state-of-the-art results on challenging reasoning benchmarks such as MMMU and MathVista. Furthermore, on the OpenCompass leaderboard, SAIL-VL2-2B ranks first among officially released open-source models under the 4B parameter scale, while serving as an efficient and extensible foundation for the open-source multimodal community.</p> - https://arxiv.org/abs/2509.14033 - Wed, 17 Sep 2025 14:34:02 +0000 + Mind the Gap: A Closer Look at Tokenization for Multiple-Choice Question Answering with LLMs + https://arxiv.org/abs/2509.15020 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.15020.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Mario Sanz-Guerrero, Minh Duc Bui, Katharina von der Wense</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> When evaluating large language models (LLMs) with multiple-choice question answering (MCQA), it is common to end the prompt with the string "Answer:" to facilitate automated answer extraction via next-token probabilities. However, there is no consensus on how to tokenize the space following the colon, often overlooked as a trivial choice. In this paper, we uncover accuracy differences of up to 11% due to this (seemingly irrelevant) tokenization variation as well as reshuffled model rankings, raising concerns about the reliability of LLM comparisons in prior work. Surprisingly, we are able to recommend one specific strategy -- tokenizing the space together with the answer letter -- as we observe consistent and statistically significant performance improvements. Additionally, it improves model calibration, enhancing the reliability of the model's confidence estimates. Our findings underscore the importance of careful evaluation design and highlight the need for standardized, transparent evaluation protocols to ensure reliable and comparable results.</p> + https://arxiv.org/abs/2509.15020 + Thu, 18 Sep 2025 14:47:58 +0000 - Wan-Animate: Unified Character Animation and Replacement with Holistic Replication - https://arxiv.org/abs/2509.14055 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.14055.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Gang Cheng, Xin Gao, Li Hu, Siqi Hu, Mingyang Huang, Chaonan Ji, Ju Li, Dechao Meng, Jinwei Qi, Penchong Qiao, Zhen Shen, Yafei Song, Ke Sun, Linrui Tian, Feng Wang, Guangyuan Wang, Qi Wang, Zhongjian Wang, Jiayu Xiao, Sheng Xu, Bang Zhang, Peng Zhang, Xindi Zhang, Zhe Zhang, Jingren Zhou, Lian Zhuo</p><p><b>Upvotes:</b> 6</p><p><b>Summary:</b> We introduce Wan-Animate, a unified framework for character animation and replacement. Given a character image and a reference video, Wan-Animate can animate the character by precisely replicating the expressions and movements of the character in the video to generate high-fidelity character videos. Alternatively, it can integrate the animated character into the reference video to replace the original character, replicating the scene's lighting and color tone to achieve seamless environmental integration. Wan-Animate is built upon the Wan model. To adapt it for character animation tasks, we employ a modified input paradigm to differentiate between reference conditions and regions for generation. This design unifies multiple tasks into a common symbolic representation. We use spatially-aligned skeleton signals to replicate body motion and implicit facial features extracted from source images to reenact expressions, enabling the generation of character videos with high controllability and expressiveness. Furthermore, to enhance environmental integration during character replacement, we develop an auxiliary Relighting LoRA. This module preserves the character's appearance consistency while applying the appropriate environmental lighting and color tone. Experimental results demonstrate that Wan-Animate achieves state-of-the-art performance. We are committed to open-sourcing the model weights and its source code.</p> - https://arxiv.org/abs/2509.14055 - Wed, 17 Sep 2025 15:00:57 +0000 + WorldForge: Unlocking Emergent 3D/4D Generation in Video Diffusion Model via Training-Free Guidance + https://arxiv.org/abs/2509.15130 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.15130.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Chenxi Song, Yanming Yang, Tong Zhao, Ruibo Li, Chi Zhang</p><p><b>Upvotes:</b> 6</p><p><b>Summary:</b> Recent video diffusion models demonstrate strong potential in spatial intelligence tasks due to their rich latent world priors. However, this potential is hindered by their limited controllability and geometric inconsistency, creating a gap between their strong priors and their practical use in 3D/4D tasks. As a result, current approaches often rely on retraining or fine-tuning, which risks degrading pretrained knowledge and incurs high computational costs. To address this, we propose WorldForge, a training-free, inference-time framework composed of three tightly coupled modules. Intra-Step Recursive Refinement introduces a recursive refinement mechanism during inference, which repeatedly optimizes network predictions within each denoising step to enable precise trajectory injection. Flow-Gated Latent Fusion leverages optical flow similarity to decouple motion from appearance in the latent space and selectively inject trajectory guidance into motion-related channels. Dual-Path Self-Corrective Guidance compares guided and unguided denoising paths to adaptively correct trajectory drift caused by noisy or misaligned structural signals. Together, these components inject fine-grained, trajectory-aligned guidance without training, achieving both accurate motion control and photorealistic content generation. Extensive experiments across diverse benchmarks validate our method's superiority in realism, trajectory consistency, and visual fidelity. This work introduces a novel plug-and-play paradigm for controllable video synthesis, offering a new perspective on leveraging generative priors for spatial intelligence.</p> + https://arxiv.org/abs/2509.15130 + Thu, 18 Sep 2025 16:40:47 +0000 - MARS2 2025 Challenge on Multimodal Reasoning: Datasets, Methods, Results, Discussion, and Outlook - https://arxiv.org/abs/2509.14142 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.14142.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Peng Xu, Shengwu Xiong, Jiajun Zhang, Yaxiong Chen, Bowen Zhou, Chen Change Loy, David A. Clifton, Kyoung Mu Lee, Luc Van Gool, Ruiming He, Ruilin Yao, Xinwei Long, Jirui Huang, Kai Tian, Sa Yang, Yihua Shao, Jin Feng, Yue Zhong, Jiakai Zhou, Cheng Tang, Tianyu Zou, Yifang Zhang, Junming Liang, Guoyou Li, Zhaoxiang Wang, Qiang Zhou, Yichen Zhao, Shili Xiong, Hyeongjin Nam, Jaerin Lee, Jaeyoung Chung, JoonKyu Park, Junghun Oh, Kanggeon Lee, Wooseok Lee, Juneyoung Ro, Turghun Osman, Can Hu, Chaoyang Liao, Cheng Chen, Chengcheng Han, Chenhao Qiu, Chong Peng, Cong Xu, Dailin Li, Feiyu Wang, Feng Gao, Guibo Zhu, Guopeng Tang, Haibo Lu, Han Fang, Han Qi, Hanxiao Wu, Haobo Cheng, Hongbo Sun, Hongyao Chen, Huayong Hu, Hui Li, Jiaheng Ma, Jiang Yu, Jianing Wang, Jie Yang, Jing He, Jinglin Zhou, Jingxuan Li, Josef Kittler, Lihao Zheng, Linnan Zhao, Mengxi Jia, Muyang Yan, Nguyen Thanh Thien, Pu Luo, Qi Li, Shien Song, Shijie Dong, Shuai Shao, Shutao Li, Taofeng Xue, Tianyang Xu, Tianyi Gao, Tingting Li, Wei Zhang, Weiyang Su, Xiaodong Dong, Xiao-Jun Wu, Xiaopeng Zhou, Xin Chen, Xin Wei, Xinyi You, Xudong Kang, Xujie Zhou, Xusheng Liu, Yanan Wang, Yanbin Huang, Yang Liu, Yang Yang, Yanglin Deng, Yashu Kang, Ye Yuan, Yi Wen, Yicen Tian, Yilin Tao, Yin Tang, Yipeng Lin, Yiqing Wang, Yiting Xi, Yongkang Yu, Yumei Li, Yuxin Qin, Yuying Chen, Yuzhe Cen, Zhaofan Zou, Zhaohong Liu, Zhehao Shen, Zhenglin Du, Zhengyang Li, Zhenni Huang, Zhenwei Shao, Zhilong Song, Zhiyong Feng, Zhiyu Wang, Zhou Yu, Ziang Li, Zihan Zhai, Zijian Zhang, Ziyang Peng, Ziyun Xiao, Zongshu Li</p><p><b>Upvotes:</b> 6</p><p><b>Summary:</b> This paper reviews the MARS2 2025 Challenge on Multimodal Reasoning. We aim to bring together different approaches in multimodal machine learning and LLMs via a large benchmark. We hope it better allows researchers to follow the state-of-the-art in this very dynamic area. Meanwhile, a growing number of testbeds have boosted the evolution of general-purpose large language models. Thus, this year's MARS2 focuses on real-world and specialized scenarios to broaden the multimodal reasoning applications of MLLMs. Our organizing team released two tailored datasets Lens and AdsQA as test sets, which support general reasoning in 12 daily scenarios and domain-specific reasoning in advertisement videos, respectively. We evaluated 40+ baselines that include both generalist MLLMs and task-specific models, and opened up three competition tracks, i.e., Visual Grounding in Real-world Scenarios (VG-RS), Visual Question Answering with Spatial Awareness (VQA-SA), and Visual Reasoning in Creative Advertisement Videos (VR-Ads). Finally, 76 teams from the renowned academic and industrial institutions have registered and 40+ valid submissions (out of 1200+) have been included in our ranking lists. Our datasets, code sets (40+ baselines and 15+ participants' methods), and rankings are publicly available on the MARS2 workshop website and our GitHub organization page https://github.com/mars2workshop/, where our updates and announcements of upcoming events will be continuously provided.</p> - https://arxiv.org/abs/2509.14142 - Wed, 17 Sep 2025 16:21:34 +0000 + Unleashing the Potential of Multimodal LLMs for Zero-Shot Spatio-Temporal Video Grounding + https://arxiv.org/abs/2509.15178 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.15178.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zaiquan Yang, Yuhao Liu, Gerhard Hancke, Rynson W. H. Lau</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Spatio-temporal video grounding (STVG) aims at localizing the spatio-temporal tube of a video, as specified by the input text query. In this paper, we utilize multimodal large language models (MLLMs) to explore a zero-shot solution in STVG. We reveal two key insights about MLLMs: (1) MLLMs tend to dynamically assign special tokens, referred to as grounding tokens, for grounding the text query; and (2) MLLMs often suffer from suboptimal grounding due to the inability to fully integrate the cues in the text query (e.g., attributes, actions) for inference. Based on these insights, we propose a MLLM-based zero-shot framework for STVG, which includes novel decomposed spatio-temporal highlighting (DSTH) and temporal-augmented assembling (TAS) strategies to unleash the reasoning ability of MLLMs. The DSTH strategy first decouples the original query into attribute and action sub-queries for inquiring the existence of the target both spatially and temporally. It then uses a novel logit-guided re-attention (LRA) module to learn latent variables as spatial and temporal prompts, by regularizing token predictions for each sub-query. These prompts highlight attribute and action cues, respectively, directing the model's attention to reliable spatial and temporal related visual regions. In addition, as the spatial grounding by the attribute sub-query should be temporally consistent, we introduce the TAS strategy to assemble the predictions using the original video frames and the temporal-augmented frames as inputs to help improve temporal consistency. We evaluate our method on various MLLMs, and show that it outperforms SOTA methods on three common STVG benchmarks. The code will be available at https://github.com/zaiquanyang/LLaVA_Next_STVG.</p> + https://arxiv.org/abs/2509.15178 + Thu, 18 Sep 2025 17:35:50 +0000 - Synthesizing Behaviorally-Grounded Reasoning Chains: A Data-Generation Framework for Personal Finance LLMs - https://arxiv.org/abs/2509.14180 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.14180.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Akhil Theerthala</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Personalized financial advice requires consideration of user goals, constraints, risk tolerance, and jurisdiction. Prior LLM work has focused on support systems for investors and financial planners. Simultaneously, numerous recent studies examine broader personal finance tasks, including budgeting, debt management, retirement, and estate planning, through agentic pipelines that incur high maintenance costs, yielding less than 25% of their expected financial returns. In this study, we introduce a novel and reproducible framework that integrates relevant financial context with behavioral finance studies to construct supervision data for end-to-end advisors. Using this framework, we create a 19k sample reasoning dataset and conduct a comprehensive fine-tuning of the Qwen-3-8B model on the dataset. Through a held-out test split and a blind LLM-jury study, we demonstrate that through careful data curation and behavioral integration, our 8B model achieves performance comparable to significantly larger baselines (14-32B parameters) across factual accuracy, fluency, and personalization metrics while incurring 80% lower costs than the larger counterparts.</p> - https://arxiv.org/abs/2509.14180 - Wed, 17 Sep 2025 17:12:38 +0000 + Understand Before You Generate: Self-Guided Training for Autoregressive Image Generation + https://arxiv.org/abs/2509.15185 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.15185.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xiaoyu Yue, Zidong Wang, Yuqing Wang, Wenlong Zhang, Xihui Liu, Wanli Ouyang, Lei Bai, Luping Zhou</p><p><b>Upvotes:</b> 22</p><p><b>Summary:</b> Recent studies have demonstrated the importance of high-quality visual representations in image generation and have highlighted the limitations of generative models in image understanding. As a generative paradigm originally designed for natural language, autoregressive models face similar challenges. In this work, we present the first systematic investigation into the mechanisms of applying the next-token prediction paradigm to the visual domain. We identify three key properties that hinder the learning of high-level visual semantics: local and conditional dependence, inter-step semantic inconsistency, and spatial invariance deficiency. We show that these issues can be effectively addressed by introducing self-supervised objectives during training, leading to a novel training framework, Self-guided Training for AutoRegressive models (ST-AR). Without relying on pre-trained representation models, ST-AR significantly enhances the image understanding ability of autoregressive models and leads to improved generation quality. Specifically, ST-AR brings approximately 42% FID improvement for LlamaGen-L and 49% FID improvement for LlamaGen-XL, while maintaining the same sampling strategy.</p> + https://arxiv.org/abs/2509.15185 + Thu, 18 Sep 2025 17:47:40 +0000 - GenExam: A Multidisciplinary Text-to-Image Exam - https://arxiv.org/abs/2509.14232 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.14232.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhaokai Wang, Penghao Yin, Xiangyu Zhao, Changyao Tian, Yu Qiao, Wenhai Wang, Jifeng Dai, Gen Luo</p><p><b>Upvotes:</b> 16</p><p><b>Summary:</b> Exams are a fundamental test of expert-level intelligence and require integrated understanding, reasoning, and generation. Existing exam-style benchmarks mainly focus on understanding and reasoning tasks, and current generation benchmarks emphasize the illustration of world knowledge and visual concepts, neglecting the evaluation of rigorous drawing exams. We introduce GenExam, the first benchmark for multidisciplinary text-to-image exams, featuring 1,000 samples across 10 subjects with exam-style prompts organized under a four-level taxonomy. Each problem is equipped with ground-truth images and fine-grained scoring points to enable a precise evaluation of semantic correctness and visual plausibility. Experiments show that even state-of-the-art models such as GPT-Image-1 and Gemini-2.5-Flash-Image achieve less than 15% strict scores, and most models yield almost 0%, suggesting the great challenge of our benchmark. By framing image generation as an exam, GenExam offers a rigorous assessment of models' ability to integrate knowledge, reasoning, and generation, providing insights on the path to general AGI.</p> - https://arxiv.org/abs/2509.14232 - Wed, 17 Sep 2025 17:59:14 +0000 + Evolving Language Models without Labels: Majority Drives Selection, Novelty Promotes Variation + https://arxiv.org/abs/2509.15194 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.15194.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yujun Zhou, Zhenwen Liang, Haolin Liu, Wenhao Yu, Kishan Panaganti, Linfeng Song, Dian Yu, Xiangliang Zhang, Haitao Mi, Dong Yu</p><p><b>Upvotes:</b> 29</p><p><b>Summary:</b> Large language models (LLMs) are increasingly trained with reinforcement learning from verifiable rewards (RLVR), yet real-world deployment demands models that can self-improve without labels or external judges. Existing label-free methods, confidence minimization, self-consistency, or majority-vote objectives, stabilize learning but steadily shrink exploration, causing an entropy collapse: generations become shorter, less diverse, and brittle. Unlike prior approaches such as Test-Time Reinforcement Learning (TTRL), which primarily adapt models to the immediate unlabeled dataset at hand, our goal is broader: to enable general improvements without sacrificing the model's inherent exploration capacity and generalization ability, i.e., evolving. We formalize this issue and propose EVolution-Oriented and Label-free Reinforcement Learning (EVOL-RL), a simple rule that couples stability with variation under a label-free setting. EVOL-RL keeps the majority-voted answer as a stable anchor (selection) while adding a novelty-aware reward that favors responses whose reasoning differs from what has already been produced (variation), measured in semantic space. Implemented with GRPO, EVOL-RL also uses asymmetric clipping to preserve strong signals and an entropy regularizer to sustain search. This majority-for-selection + novelty-for-variation design prevents collapse, maintains longer and more informative chains of thought, and improves both pass@1 and pass@n. EVOL-RL consistently outperforms the majority-only TTRL baseline; e.g., training on label-free AIME24 lifts Qwen3-4B-Base AIME25 pass@1 from TTRL's 4.6% to 16.4%, and pass@16 from 18.5% to 37.9%. EVOL-RL not only prevents diversity collapse but also unlocks stronger generalization across domains (e.g., GPQA). Furthermore, we demonstrate that EVOL-RL also boosts performance in the RLVR setting, highlighting its broad applicability.</p> + https://arxiv.org/abs/2509.15194 + Thu, 18 Sep 2025 17:50:04 +0000 + + + FlowRL: Matching Reward Distributions for LLM Reasoning + https://arxiv.org/abs/2509.15207 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.15207.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xuekai Zhu, Daixuan Cheng, Dinghuai Zhang, Hengli Li, Kaiyan Zhang, Che Jiang, Youbang Sun, Ermo Hua, Yuxin Zuo, Xingtai Lv, Qizheng Zhang, Lin Chen, Fanghao Shao, Bo Xue, Yunchong Song, Zhenjie Yang, Ganqu Cui, Ning Ding, Jianfeng Gao, Xiaodong Liu, Bowen Zhou, Hongyuan Mei, Zhouhan Lin</p><p><b>Upvotes:</b> 68</p><p><b>Summary:</b> We propose FlowRL: matching the full reward distribution via flow balancing instead of maximizing rewards in large language model (LLM) reinforcement learning (RL). Recent advanced reasoning models adopt reward-maximizing methods (\eg, PPO and GRPO), which tend to over-optimize dominant reward signals while neglecting less frequent but valid reasoning paths, thus reducing diversity. In contrast, we transform scalar rewards into a normalized target distribution using a learnable partition function, and then minimize the reverse KL divergence between the policy and the target distribution. We implement this idea as a flow-balanced optimization method that promotes diverse exploration and generalizable reasoning trajectories. We conduct experiments on math and code reasoning tasks: FlowRL achieves a significant average improvement of 10.0% over GRPO and 5.1% over PPO on math benchmarks, and performs consistently better on code reasoning tasks. These results highlight reward distribution-matching as a key step toward efficient exploration and diverse reasoning in LLM reinforcement learning.</p> + https://arxiv.org/abs/2509.15207 + Thu, 18 Sep 2025 17:56:36 +0000 + + + RynnVLA-001: Using Human Demonstrations to Improve Robot Manipulation + https://arxiv.org/abs/2509.15212 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.15212.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yuming Jiang, Siteng Huang, Shengke Xue, Yaxi Zhao, Jun Cen, Sicong Leng, Kehan Li, Jiayan Guo, Kexiang Wang, Mingxiu Chen, Fan Wang, Deli Zhao, Xin Li</p><p><b>Upvotes:</b> 12</p><p><b>Summary:</b> This paper presents RynnVLA-001, a vision-language-action(VLA) model built upon large-scale video generative pretraining from human demonstrations. We propose a novel two-stage pretraining methodology. The first stage, Ego-Centric Video Generative Pretraining, trains an Image-to-Video model on 12M ego-centric manipulation videos to predict future frames conditioned on an initial frame and a language instruction. The second stage, Human-Centric Trajectory-Aware Modeling, extends this by jointly predicting future keypoint trajectories, thereby effectively bridging visual frame prediction with action prediction. Furthermore, to enhance action representation, we propose ActionVAE, a variational autoencoder that compresses sequences of actions into compact latent embeddings, reducing the complexity of the VLA output space. When finetuned on the same downstream robotics datasets, RynnVLA-001 achieves superior performance over state-of-the-art baselines, demonstrating that the proposed pretraining strategy provides a more effective initialization for VLA models.</p> + https://arxiv.org/abs/2509.15212 + Thu, 18 Sep 2025 17:58:02 +0000 + + + ScaleCUA: Scaling Open-Source Computer Use Agents with Cross-Platform Data + https://arxiv.org/abs/2509.15221 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.15221.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhaoyang Liu, JingJing Xie, Zichen Ding, Zehao Li, Bowen Yang, Zhenyu Wu, Xuehui Wang, Qiushi Sun, Shi Liu, Weiyun Wang, Shenglong Ye, Qingyun Li, Zeyue Tian, Gen Luo, Xiangyu Yue, Biqing Qi, Kai Chen, Bowen Zhou, Yu Qiao, Qifeng Chen, Wenhai Wang</p><p><b>Upvotes:</b> 79</p><p><b>Summary:</b> Vision-Language Models (VLMs) have enabled computer use agents (CUAs) that operate GUIs autonomously, showing great potential, yet progress is limited by the lack of large-scale, open-source computer use data and foundation models. In this work, we introduce ScaleCUA, a step toward scaling open-source CUAs. It offers a large-scale dataset spanning 6 operating systems and 3 task domains, built via a closed-loop pipeline uniting automated agents with human experts. Trained on this scaled-up data, ScaleCUA can operate seamlessly across platforms. Specifically, it delivers strong gains over baselines (+26.6 on WebArena-Lite-v2, +10.7 on ScreenSpot-Pro) and sets new state-of-the-art results (94.4% on MMBench-GUI L1-Hard, 60.6% on OSWorld-G, 47.4% on WebArena-Lite-v2). These findings underscore the power of data-driven scaling for general-purpose computer use agents. We will release data, models, and code to advance future research: https://github.com/OpenGVLab/ScaleCUA.</p> + https://arxiv.org/abs/2509.15221 + Thu, 18 Sep 2025 17:59:22 +0000