bot: update RSS feed
This commit is contained in:
github-actions[bot]
166
feed.xml
166
feed.xml
@@ -7,146 +7,62 @@
|
||||
<docs>http://www.rssboard.org/rss-specification</docs>
|
||||
<generator>python-feedgen</generator>
|
||||
<language>en</language>
|
||||
<lastBuildDate>Mon, 12 May 2025 00:02:41 +0000</lastBuildDate>
|
||||
<lastBuildDate>Tue, 13 May 2025 00:02:43 +0000</lastBuildDate>
|
||||
<item>
|
||||
<title>BrowseComp-ZH: Benchmarking Web Browsing Ability of Large Language Models in Chinese</title>
|
||||
<link>https://arxiv.org/abs/2504.19314</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2504.19314.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Peilin Zhou, Bruce Leon, Xiang Ying, Can Zhang, Yifan Shao, Qichen Ye, Dading Chong, Zhiling Jin, Chenxuan Xie, Meng Cao, Yuxin Gu, Sixin Hong, Jing Ren, Jian Chen, Chao Liu, Yining Hua</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> As large language models (LLMs) evolve into tool-using agents, the ability to browse the web in real-time has become a critical yardstick for measuring their reasoning and retrieval competence. Existing benchmarks such as BrowseComp concentrate on English and overlook the linguistic, infrastructural, and censorship-related complexities of other major information ecosystems -- most notably Chinese. To address this gap, we introduce BrowseComp-ZH, a high-difficulty benchmark purpose-built to comprehensively evaluate LLM agents on the Chinese web. BrowseComp-ZH consists of 289 multi-hop questions spanning 11 diverse domains. Each question is reverse-engineered from a short, objective, and easily verifiable answer (e.g., a date, number, or proper noun). A two-stage quality control protocol is applied to strive for high question difficulty and answer uniqueness. We benchmark over 20 state-of-the-art language models and agentic search systems on our proposed BrowseComp-ZH. Despite their strong conversational and retrieval capabilities, most models struggle severely: a large number achieve accuracy rates below 10%, and only a handful exceed 20%. Even the best-performing system, OpenAI's DeepResearch, reaches just 42.9%. These results demonstrate the considerable difficulty of BrowseComp-ZH, where success demands not only effective retrieval strategies, but also sophisticated reasoning and information reconciliation -- capabilities that current models still struggle to master. Our dataset, construction guidelines, and benchmark results have been publicly released at https://github.com/PALIN2018/BrowseComp-ZH.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2504.19314</guid>
|
||||
<pubDate>Sun, 27 Apr 2025 17:32:43 +0000</pubDate>
|
||||
<title>Multiview Point Cloud Registration via Optimization in an Autoencoder Latent Space</title>
|
||||
<link>https://arxiv.org/abs/2504.21467</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2504.21467.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Luc Vedrenne, Sylvain Faisan, Denis Fortun</p><p><b>Upvotes:</b> 0</p><p><b>Summary:</b> Point cloud rigid registration is a fundamental problem in 3D computer vision. In the multiview case, we aim to find a set of 6D poses to align a set of objects. Methods based on pairwise registration rely on a subsequent synchronization algorithm, which makes them poorly scalable with the number of views. Generative approaches overcome this limitation, but are based on Gaussian Mixture Models and use an Expectation-Maximization algorithm. Hence, they are not well suited to handle large transformations. Moreover, most existing methods cannot handle high levels of degradations. In this paper, we introduce POLAR (POint cloud LAtent Registration), a multiview registration method able to efficiently deal with a large number of views, while being robust to a high level of degradations and large initial angles. To achieve this, we transpose the registration problem into the latent space of a pretrained autoencoder, design a loss taking degradations into account, and develop an efficient multistart optimization strategy. Our proposed method significantly outperforms state-of-the-art approaches on synthetic and real data. POLAR is available at github.com/pypolar/polar or as a standalone package which can be installed with pip install polaregistration.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2504.21467</guid>
|
||||
<pubDate>Wed, 30 Apr 2025 09:42:38 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>Sentient Agent as a Judge: Evaluating Higher-Order Social Cognition in Large Language Models</title>
|
||||
<link>https://arxiv.org/abs/2505.02847</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.02847.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Bang Zhang, Ruotian Ma, Qingxuan Jiang, Peisong Wang, Jiaqi Chen, Zheng Xie, Xingyu Chen, Yue Wang, Fanghua Ye, Jian Li, Yifan Yang, Zhaopeng Tu, Xiaolong Li</p><p><b>Upvotes:</b> 24</p><p><b>Summary:</b> Assessing how well a large language model (LLM) understands human, rather than merely text, remains an open challenge. To bridge the gap, we introduce Sentient Agent as a Judge (SAGE), an automated evaluation framework that measures an LLM's higher-order social cognition. SAGE instantiates a Sentient Agent that simulates human-like emotional changes and inner thoughts during interaction, providing a more realistic evaluation of the tested model in multi-turn conversations. At every turn, the agent reasons about (i) how its emotion changes, (ii) how it feels, and (iii) how it should reply, yielding a numerical emotion trajectory and interpretable inner thoughts. Experiments on 100 supportive-dialogue scenarios show that the final Sentient emotion score correlates strongly with Barrett-Lennard Relationship Inventory (BLRI) ratings and utterance-level empathy metrics, validating psychological fidelity. We also build a public Sentient Leaderboard covering 18 commercial and open-source models that uncovers substantial gaps (up to 4x) between frontier systems (GPT-4o-Latest, Gemini2.5-Pro) and earlier baselines, gaps not reflected in conventional leaderboards (e.g., Arena). SAGE thus provides a principled, scalable and interpretable tool for tracking progress toward genuinely empathetic and socially adept language agents.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2505.02847</guid>
|
||||
<pubDate>Thu, 01 May 2025 19:06:10 +0000</pubDate>
|
||||
<title>Bielik 11B v2 Technical Report</title>
|
||||
<link>https://arxiv.org/abs/2505.02410</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.02410.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Krzysztof Ociepa, Łukasz Flis, Krzysztof Wróbel, Adrian Gwoździej, Remigiusz Kinas</p><p><b>Upvotes:</b> 44</p><p><b>Summary:</b> We present Bielik 11B v2, a state-of-the-art language model optimized for Polish text processing. Built on the Mistral 7B v0.2 architecture and scaled to 11B parameters using depth up-scaling, this model demonstrates exceptional performance across Polish language benchmarks while maintaining strong cross-lingual capabilities. We introduce two key technical innovations: Weighted Instruction Cross-Entropy Loss, which optimizes learning across diverse instruction types by assigning quality-based weights to training examples, and Adaptive Learning Rate, which dynamically adjusts based on context length. Comprehensive evaluation across multiple benchmarks demonstrates that Bielik 11B v2 outperforms many larger models, including those with 2-6 times more parameters, and significantly surpasses other specialized Polish language models on tasks ranging from linguistic understanding to complex reasoning. The model's parameter efficiency and extensive quantization options enable deployment across various hardware configurations, advancing Polish language AI capabilities and establishing new benchmarks for resource-efficient language modeling in less-represented languages.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2505.02410</guid>
|
||||
<pubDate>Mon, 05 May 2025 07:03:41 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>SIMPLEMIX: Frustratingly Simple Mixing of Off- and On-policy Data in Language Model Preference Learning</title>
|
||||
<link>https://arxiv.org/abs/2505.02363</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.02363.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Tianjian Li, Daniel Khashabi</p><p><b>Upvotes:</b> 6</p><p><b>Summary:</b> Aligning language models with human preferences relies on pairwise preference datasets. While some studies suggest that on-policy data consistently outperforms off -policy data for preference learning, others indicate that the advantages of on-policy data may be task-dependent, highlighting the need for a systematic exploration of their interplay. In this work, we show that on-policy and off-policy data offer complementary strengths in preference optimization: on-policy data is particularly effective for reasoning tasks like math and coding, while off-policy data performs better on open-ended tasks such as creative writing and making personal recommendations. Guided by these findings, we introduce SIMPLEMIX, an approach to combine the complementary strengths of on-policy and off-policy preference learning by simply mixing these two data sources. Our empirical results across diverse tasks and benchmarks demonstrate that SIMPLEMIX substantially improves language model alignment. Specifically, SIMPLEMIX improves upon on-policy DPO and off-policy DPO by an average of 6.03% on Alpaca Eval 2.0. Moreover, it outperforms prior approaches that are much more complex in combining on- and off-policy data, such as HyPO and DPO-Mix-P, by an average of 3.05%.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2505.02363</guid>
|
||||
<pubDate>Mon, 05 May 2025 04:54:44 +0000</pubDate>
|
||||
<title>Bielik v3 Small: Technical Report</title>
|
||||
<link>https://arxiv.org/abs/2505.02550</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.02550.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Krzysztof Ociepa, Łukasz Flis, Remigiusz Kinas, Krzysztof Wróbel, Adrian Gwoździej</p><p><b>Upvotes:</b> 53</p><p><b>Summary:</b> We introduce Bielik v3, a series of parameter-efficient generative text models (1.5B and 4.5B) optimized for Polish language processing. These models demonstrate that smaller, well-optimized architectures can achieve performance comparable to much larger counterparts while requiring substantially fewer computational resources. Our approach incorporates several key innovations: a custom Polish tokenizer (APT4) that significantly improves token efficiency, Weighted Instruction Cross-Entropy Loss to balance learning across instruction types, and Adaptive Learning Rate that dynamically adjusts based on training progress. Trained on a meticulously curated corpus of 292 billion tokens spanning 303 million documents, these models excel across multiple benchmarks, including the Open PL LLM Leaderboard, Complex Polish Text Understanding Benchmark, Polish EQ-Bench, and Polish Medical Leaderboard. The 4.5B parameter model achieves results competitive with models 2-3 times its size, while the 1.5B model delivers strong performance despite its extremely compact profile. These advances establish new benchmarks for parameter-efficient language modeling in less-represented languages, making high-quality Polish language AI more accessible for resource-constrained applications.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2505.02550</guid>
|
||||
<pubDate>Mon, 05 May 2025 10:39:51 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>LiftFeat: 3D Geometry-Aware Local Feature Matching</title>
|
||||
<link>https://arxiv.org/abs/2505.03422</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.03422.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yepeng Liu, Wenpeng Lai, Zhou Zhao, Yuxuan Xiong, Jinchi Zhu, Jun Cheng, Yongchao Xu</p><p><b>Upvotes:</b> 7</p><p><b>Summary:</b> Robust and efficient local feature matching plays a crucial role in applications such as SLAM and visual localization for robotics. Despite great progress, it is still very challenging to extract robust and discriminative visual features in scenarios with drastic lighting changes, low texture areas, or repetitive patterns. In this paper, we propose a new lightweight network called LiftFeat, which lifts the robustness of raw descriptor by aggregating 3D geometric feature. Specifically, we first adopt a pre-trained monocular depth estimation model to generate pseudo surface normal label, supervising the extraction of 3D geometric feature in terms of predicted surface normal. We then design a 3D geometry-aware feature lifting module to fuse surface normal feature with raw 2D descriptor feature. Integrating such 3D geometric feature enhances the discriminative ability of 2D feature description in extreme conditions. Extensive experimental results on relative pose estimation, homography estimation, and visual localization tasks, demonstrate that our LiftFeat outperforms some lightweight state-of-the-art methods. Code will be released at : https://github.com/lyp-deeplearning/LiftFeat.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2505.03422</guid>
|
||||
<pubDate>Tue, 06 May 2025 10:59:23 +0000</pubDate>
|
||||
<title>Sailing AI by the Stars: A Survey of Learning from Rewards in Post-Training and Test-Time Scaling of Large Language Models</title>
|
||||
<link>https://arxiv.org/abs/2505.02686</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.02686.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xiaobao Wu</p><p><b>Upvotes:</b> 11</p><p><b>Summary:</b> Recent developments in Large Language Models (LLMs) have shifted from pre-training scaling to post-training and test-time scaling. Across these developments, a key unified paradigm has arisen: Learning from Rewards, where reward signals act as the guiding stars to steer LLM behavior. It has underpinned a wide range of prevalent techniques, such as reinforcement learning (in RLHF, DPO, and GRPO), reward-guided decoding, and post-hoc correction. Crucially, this paradigm enables the transition from passive learning from static data to active learning from dynamic feedback. This endows LLMs with aligned preferences and deep reasoning capabilities. In this survey, we present a comprehensive overview of the paradigm of learning from rewards. We categorize and analyze the strategies under this paradigm across training, inference, and post-inference stages. We further discuss the benchmarks for reward models and the primary applications. Finally we highlight the challenges and future directions. We maintain a paper collection at https://github.com/bobxwu/learning-from-rewards-llm-papers.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2505.02686</guid>
|
||||
<pubDate>Mon, 05 May 2025 14:33:49 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>X-Reasoner: Towards Generalizable Reasoning Across Modalities and Domains</title>
|
||||
<link>https://arxiv.org/abs/2505.03981</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.03981.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Qianchu Liu, Sheng Zhang, Guanghui Qin, Timothy Ossowski, Yu Gu, Ying Jin, Sid Kiblawi, Sam Preston, Mu Wei, Paul Vozila, Tristan Naumann, Hoifung Poon</p><p><b>Upvotes:</b> 13</p><p><b>Summary:</b> Recent proprietary models (e.g., o3) have begun to demonstrate strong multimodal reasoning capabilities. Yet, most existing open-source research concentrates on training text-only reasoning models, with evaluations limited to mainly mathematical and general-domain tasks. Therefore, it remains unclear how to effectively extend reasoning capabilities beyond text input and general domains. This paper explores a fundamental research question: Is reasoning generalizable across modalities and domains? Our findings support an affirmative answer: General-domain text-based post-training can enable such strong generalizable reasoning. Leveraging this finding, we introduce X-Reasoner, a vision-language model post-trained solely on general-domain text for generalizable reasoning, using a two-stage approach: an initial supervised fine-tuning phase with distilled long chain-of-thoughts, followed by reinforcement learning with verifiable rewards. Experiments show that X-Reasoner successfully transfers reasoning capabilities to both multimodal and out-of-domain settings, outperforming existing state-of-the-art models trained with in-domain and multimodal data across various general and medical benchmarks (Figure 1). Additionally, we find that X-Reasoner's performance in specialized domains can be further enhanced through continued training on domain-specific text-only data. Building upon this, we introduce X-Reasoner-Med, a medical-specialized variant that achieves new state of the art on numerous text-only and multimodal medical benchmarks.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2505.03981</guid>
|
||||
<pubDate>Tue, 06 May 2025 21:08:27 +0000</pubDate>
|
||||
<title>G-FOCUS: Towards a Robust Method for Assessing UI Design Persuasiveness</title>
|
||||
<link>https://arxiv.org/abs/2505.05026</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.05026.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jaehyun Jeon, Jang Han Yoon, Min Soo Kim, Sumin Shim, Yejin Choi, Hanbin Kim, Youngjae Yu</p><p><b>Upvotes:</b> 11</p><p><b>Summary:</b> Evaluating user interface (UI) design effectiveness extends beyond aesthetics to influencing user behavior, a principle central to Design Persuasiveness. A/B testing is the predominant method for determining which UI variations drive higher user engagement, but it is costly and time-consuming. While recent Vision-Language Models (VLMs) can process automated UI analysis, current approaches focus on isolated design attributes rather than comparative persuasiveness-the key factor in optimizing user interactions. To address this, we introduce WiserUI-Bench, a benchmark designed for Pairwise UI Design Persuasiveness Assessment task, featuring 300 real-world UI image pairs labeled with A/B test results and expert rationales. Additionally, we propose G-FOCUS, a novel inference-time reasoning strategy that enhances VLM-based persuasiveness assessment by reducing position bias and improving evaluation accuracy. Experimental results show that G-FOCUS surpasses existing inference strategies in consistency and accuracy for pairwise UI evaluation. Through promoting VLM-driven evaluation of UI persuasiveness, our work offers an approach to complement A/B testing, propelling progress in scalable UI preference modeling and design optimization. Code and data will be released publicly.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2505.05026</guid>
|
||||
<pubDate>Thu, 08 May 2025 08:00:32 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>On Path to Multimodal Generalist: General-Level and General-Bench</title>
|
||||
<link>https://arxiv.org/abs/2505.04620</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.04620.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Hao Fei, Yuan Zhou, Juncheng Li, Xiangtai Li, Qingshan Xu, Bobo Li, Shengqiong Wu, Yaoting Wang, Junbao Zhou, Jiahao Meng, Qingyu Shi, Zhiyuan Zhou, Liangtao Shi, Minghe Gao, Daoan Zhang, Zhiqi Ge, Weiming Wu, Siliang Tang, Kaihang Pan, Yaobo Ye, Haobo Yuan, Tao Zhang, Tianjie Ju, Zixiang Meng, Shilin Xu, Liyu Jia, Wentao Hu, Meng Luo, Jiebo Luo, Tat-Seng Chua, Shuicheng Yan, Hanwang Zhang</p><p><b>Upvotes:</b> 66</p><p><b>Summary:</b> The Multimodal Large Language Model (MLLM) is currently experiencing rapid growth, driven by the advanced capabilities of LLMs. Unlike earlier specialists, existing MLLMs are evolving towards a Multimodal Generalist paradigm. Initially limited to understanding multiple modalities, these models have advanced to not only comprehend but also generate across modalities. Their capabilities have expanded from coarse-grained to fine-grained multimodal understanding and from supporting limited modalities to arbitrary ones. While many benchmarks exist to assess MLLMs, a critical question arises: Can we simply assume that higher performance across tasks indicates a stronger MLLM capability, bringing us closer to human-level AI? We argue that the answer is not as straightforward as it seems. This project introduces General-Level, an evaluation framework that defines 5-scale levels of MLLM performance and generality, offering a methodology to compare MLLMs and gauge the progress of existing systems towards more robust multimodal generalists and, ultimately, towards AGI. At the core of the framework is the concept of Synergy, which measures whether models maintain consistent capabilities across comprehension and generation, and across multiple modalities. To support this evaluation, we present General-Bench, which encompasses a broader spectrum of skills, modalities, formats, and capabilities, including over 700 tasks and 325,800 instances. The evaluation results that involve over 100 existing state-of-the-art MLLMs uncover the capability rankings of generalists, highlighting the challenges in reaching genuine AI. We expect this project to pave the way for future research on next-generation multimodal foundation models, providing a robust infrastructure to accelerate the realization of AGI. Project page: https://generalist.top/</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2505.04620</guid>
|
||||
<pubDate>Wed, 07 May 2025 17:59:32 +0000</pubDate>
|
||||
<title>A Preliminary Study for GPT-4o on Image Restoration</title>
|
||||
<link>https://arxiv.org/abs/2505.05621</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.05621.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Hao Yang, Yan Yang, Ruikun Zhang, Liyuan Pan</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> OpenAI's GPT-4o model, integrating multi-modal inputs and outputs within an autoregressive architecture, has demonstrated unprecedented performance in image generation. In this work, we investigate its potential impact on the image restoration community. We present the first systematic evaluation of GPT-4o across diverse restoration tasks. Our experiments reveal that, although restoration outputs from GPT-4o are visually appealing, they often suffer from pixel-level structural fidelity when compared to ground-truth images. Common issues are variations in image proportions, shifts in object positions and quantities, and changes in viewpoint.To address it, taking image dehazing, derainning, and low-light enhancement as representative case studies, we show that GPT-4o's outputs can serve as powerful visual priors, substantially enhancing the performance of existing dehazing networks. It offers practical guidelines and a baseline framework to facilitate the integration of GPT-4o into future image restoration pipelines. We hope the study on GPT-4o image restoration will accelerate innovation in the broader field of image generation areas. To support further research, we will release GPT-4o-restored images from over 10 widely used image restoration datasets.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2505.05621</guid>
|
||||
<pubDate>Thu, 08 May 2025 20:00:11 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>Vision-Language-Action Models: Concepts, Progress, Applications and Challenges</title>
|
||||
<link>https://arxiv.org/abs/2505.04769</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.04769.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ranjan Sapkota, Yang Cao, Konstantinos I. Roumeliotis, Manoj Karkee</p><p><b>Upvotes:</b> 7</p><p><b>Summary:</b> Vision-Language-Action (VLA) models mark a transformative advancement in artificial intelligence, aiming to unify perception, natural language understanding, and embodied action within a single computational framework. This foundational review presents a comprehensive synthesis of recent advancements in Vision-Language-Action models, systematically organized across five thematic pillars that structure the landscape of this rapidly evolving field. We begin by establishing the conceptual foundations of VLA systems, tracing their evolution from cross-modal learning architectures to generalist agents that tightly integrate vision-language models (VLMs), action planners, and hierarchical controllers. Our methodology adopts a rigorous literature review framework, covering over 80 VLA models published in the past three years. Key progress areas include architectural innovations, parameter-efficient training strategies, and real-time inference accelerations. We explore diverse application domains such as humanoid robotics, autonomous vehicles, medical and industrial robotics, precision agriculture, and augmented reality navigation. The review further addresses major challenges across real-time control, multimodal action representation, system scalability, generalization to unseen tasks, and ethical deployment risks. Drawing from the state-of-the-art, we propose targeted solutions including agentic AI adaptation, cross-embodiment generalization, and unified neuro-symbolic planning. In our forward-looking discussion, we outline a future roadmap where VLA models, VLMs, and agentic AI converge to power socially aligned, adaptive, and general-purpose embodied agents. This work serves as a foundational reference for advancing intelligent, real-world robotics and artificial general intelligence. >Vision-language-action, Agentic AI, AI Agents, Vision-language Models</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2505.04769</guid>
|
||||
<pubDate>Wed, 07 May 2025 19:46:43 +0000</pubDate>
|
||||
<title>Healthy LLMs? Benchmarking LLM Knowledge of UK Government Public Health Information</title>
|
||||
<link>https://arxiv.org/abs/2505.06046</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.06046.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Joshua Harris, Fan Grayson, Felix Feldman, Timothy Laurence, Toby Nonnenmacher, Oliver Higgins, Leo Loman, Selina Patel, Thomas Finnie, Samuel Collins, Michael Borowitz</p><p><b>Upvotes:</b> 10</p><p><b>Summary:</b> As Large Language Models (LLMs) become widely accessible, a detailed understanding of their knowledge within specific domains becomes necessary for successful real world use. This is particularly critical in public health, where failure to retrieve relevant, accurate, and current information could significantly impact UK residents. However, currently little is known about LLM knowledge of UK Government public health information. To address this issue, this paper introduces a new benchmark, PubHealthBench, with over 8000 questions for evaluating LLMs' Multiple Choice Question Answering (MCQA) and free form responses to public health queries, created via an automated pipeline. We also release a new dataset of the extracted UK Government public health guidance documents used as source text for PubHealthBench. Assessing 24 LLMs on PubHealthBench we find the latest private LLMs (GPT-4.5, GPT-4.1 and o1) have a high degree of knowledge, achieving >90% in the MCQA setup, and outperform humans with cursory search engine use. However, in the free form setup we see lower performance with no model scoring >75%. Therefore, whilst there are promising signs that state of the art (SOTA) LLMs are an increasingly accurate source of public health information, additional safeguards or tools may still be needed when providing free form responses on public health topics.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2505.06046</guid>
|
||||
<pubDate>Fri, 09 May 2025 13:42:59 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>Putting the Value Back in RL: Better Test-Time Scaling by Unifying LLM Reasoners With Verifiers</title>
|
||||
<link>https://arxiv.org/abs/2505.04842</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.04842.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Kusha Sareen, Morgane M Moss, Alessandro Sordoni, Rishabh Agarwal, Arian Hosseini</p><p><b>Upvotes:</b> 12</p><p><b>Summary:</b> Prevalent reinforcement learning~(RL) methods for fine-tuning LLM reasoners, such as GRPO or Leave-one-out PPO, abandon the learned value function in favor of empirically estimated returns. This hinders test-time compute scaling that relies on using the value-function for verification. In this work, we propose RL^V that augments any ``value-free'' RL method by jointly training the LLM as both a reasoner and a generative verifier using RL-generated data, adding verification capabilities without significant overhead. Empirically, RL^V boosts MATH accuracy by over 20\% with parallel sampling and enables 8-32times efficient test-time compute scaling compared to the base RL method. RL^V also exhibits strong generalization capabilities for both easy-to-hard and out-of-domain tasks. Furthermore, RL^V achieves 1.2-1.6times higher performance when jointly scaling parallel and sequential test-time compute with a long reasoning R1 model.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2505.04842</guid>
|
||||
<pubDate>Wed, 07 May 2025 22:41:26 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>Perception, Reason, Think, and Plan: A Survey on Large Multimodal Reasoning Models</title>
|
||||
<link>https://arxiv.org/abs/2505.04921</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.04921.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yunxin Li, Zhenyu Liu, Zitao Li, Xuanyu Zhang, Zhenran Xu, Xinyu Chen, Haoyuan Shi, Shenyuan Jiang, Xintong Wang, Jifang Wang, Shouzheng Huang, Xinping Zhao, Borui Jiang, Lanqing Hong, Longyue Wang, Zhuotao Tian, Baoxing Huai, Wenhan Luo, Weihua Luo, Zheng Zhang, Baotian Hu, Min Zhang</p><p><b>Upvotes:</b> 114</p><p><b>Summary:</b> Reasoning lies at the heart of intelligence, shaping the ability to make decisions, draw conclusions, and generalize across domains. In artificial intelligence, as systems increasingly operate in open, uncertain, and multimodal environments, reasoning becomes essential for enabling robust and adaptive behavior. Large Multimodal Reasoning Models (LMRMs) have emerged as a promising paradigm, integrating modalities such as text, images, audio, and video to support complex reasoning capabilities and aiming to achieve comprehensive perception, precise understanding, and deep reasoning. As research advances, multimodal reasoning has rapidly evolved from modular, perception-driven pipelines to unified, language-centric frameworks that offer more coherent cross-modal understanding. While instruction tuning and reinforcement learning have improved model reasoning, significant challenges remain in omni-modal generalization, reasoning depth, and agentic behavior. To address these issues, we present a comprehensive and structured survey of multimodal reasoning research, organized around a four-stage developmental roadmap that reflects the field's shifting design philosophies and emerging capabilities. First, we review early efforts based on task-specific modules, where reasoning was implicitly embedded across stages of representation, alignment, and fusion. Next, we examine recent approaches that unify reasoning into multimodal LLMs, with advances such as Multimodal Chain-of-Thought (MCoT) and multimodal reinforcement learning enabling richer and more structured reasoning chains. Finally, drawing on empirical insights from challenging benchmarks and experimental cases of OpenAI O3 and O4-mini, we discuss the conceptual direction of native large multimodal reasoning models (N-LMRMs), which aim to support scalable, agentic, and adaptive reasoning and planning in complex, real-world environments.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2505.04921</guid>
|
||||
<pubDate>Thu, 08 May 2025 03:35:23 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>Chain-of-Thought Tokens are Computer Program Variables</title>
|
||||
<link>https://arxiv.org/abs/2505.04955</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.04955.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Fangwei Zhu, Peiyi Wang, Zhifang Sui</p><p><b>Upvotes:</b> 6</p><p><b>Summary:</b> Chain-of-thoughts (CoT) requires large language models (LLMs) to generate intermediate steps before reaching the final answer, and has been proven effective to help LLMs solve complex reasoning tasks. However, the inner mechanism of CoT still remains largely unclear. In this paper, we empirically study the role of CoT tokens in LLMs on two compositional tasks: multi-digit multiplication and dynamic programming. While CoT is essential for solving these problems, we find that preserving only tokens that store intermediate results would achieve comparable performance. Furthermore, we observe that storing intermediate results in an alternative latent form will not affect model performance. We also randomly intervene some values in CoT, and notice that subsequent CoT tokens and the final answer would change correspondingly. These findings suggest that CoT tokens may function like variables in computer programs but with potential drawbacks like unintended shortcuts and computational complexity limits between tokens. The code and data are available at https://github.com/solitaryzero/CoTs_are_Variables.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2505.04955</guid>
|
||||
<pubDate>Thu, 08 May 2025 05:32:36 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>WaterDrum: Watermarking for Data-centric Unlearning Metric</title>
|
||||
<link>https://arxiv.org/abs/2505.05064</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.05064.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xinyang Lu, Xinyuan Niu, Gregory Kang Ruey Lau, Bui Thi Cam Nhung, Rachael Hwee Ling Sim, Fanyu Wen, Chuan-Sheng Foo, See-Kiong Ng, Bryan Kian Hsiang Low</p><p><b>Upvotes:</b> 7</p><p><b>Summary:</b> Large language model (LLM) unlearning is critical in real-world applications where it is necessary to efficiently remove the influence of private, copyrighted, or harmful data from some users. However, existing utility-centric unlearning metrics (based on model utility) may fail to accurately evaluate the extent of unlearning in realistic settings such as when (a) the forget and retain set have semantically similar content, (b) retraining the model from scratch on the retain set is impractical, and/or (c) the model owner can improve the unlearning metric without directly performing unlearning on the LLM. This paper presents the first data-centric unlearning metric for LLMs called WaterDrum that exploits robust text watermarking for overcoming these limitations. We also introduce new benchmark datasets for LLM unlearning that contain varying levels of similar data points and can be used to rigorously evaluate unlearning algorithms using WaterDrum. Our code is available at https://github.com/lululu008/WaterDrum and our new benchmark datasets are released at https://huggingface.co/datasets/Glow-AI/WaterDrum-Ax.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2505.05064</guid>
|
||||
<pubDate>Thu, 08 May 2025 08:56:46 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>FG-CLIP: Fine-Grained Visual and Textual Alignment</title>
|
||||
<link>https://arxiv.org/abs/2505.05071</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.05071.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Chunyu Xie, Bin Wang, Fanjing Kong, Jincheng Li, Dawei Liang, Gengshen Zhang, Dawei Leng, Yuhui Yin</p><p><b>Upvotes:</b> 16</p><p><b>Summary:</b> Contrastive Language-Image Pre-training (CLIP) excels in multimodal tasks such as image-text retrieval and zero-shot classification but struggles with fine-grained understanding due to its focus on coarse-grained short captions. To address this, we propose Fine-Grained CLIP (FG-CLIP), which enhances fine-grained understanding through three key innovations. First, we leverage large multimodal models to generate 1.6 billion long caption-image pairs for capturing global-level semantic details. Second, a high-quality dataset is constructed with 12 million images and 40 million region-specific bounding boxes aligned with detailed captions to ensure precise, context-rich representations. Third, 10 million hard fine-grained negative samples are incorporated to improve the model's ability to distinguish subtle semantic differences. Corresponding training methods are meticulously designed for these data. Extensive experiments demonstrate that FG-CLIP outperforms the original CLIP and other state-of-the-art methods across various downstream tasks, including fine-grained understanding, open-vocabulary object detection, image-text retrieval, and general multimodal benchmarks. These results highlight FG-CLIP's effectiveness in capturing fine-grained image details and improving overall model performance. The related data, code, and models are available at https://github.com/360CVGroup/FG-CLIP.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2505.05071</guid>
|
||||
<pubDate>Thu, 08 May 2025 09:06:53 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>PlaceIt3D: Language-Guided Object Placement in Real 3D Scenes</title>
|
||||
<link>https://arxiv.org/abs/2505.05288</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.05288.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ahmed Abdelreheem, Filippo Aleotti, Jamie Watson, Zawar Qureshi, Abdelrahman Eldesokey, Peter Wonka, Gabriel Brostow, Sara Vicente, Guillermo Garcia-Hernando</p><p><b>Upvotes:</b> 10</p><p><b>Summary:</b> We introduce the novel task of Language-Guided Object Placement in Real 3D Scenes. Our model is given a 3D scene's point cloud, a 3D asset, and a textual prompt broadly describing where the 3D asset should be placed. The task here is to find a valid placement for the 3D asset that respects the prompt. Compared with other language-guided localization tasks in 3D scenes such as grounding, this task has specific challenges: it is ambiguous because it has multiple valid solutions, and it requires reasoning about 3D geometric relationships and free space. We inaugurate this task by proposing a new benchmark and evaluation protocol. We also introduce a new dataset for training 3D LLMs on this task, as well as the first method to serve as a non-trivial baseline. We believe that this challenging task and our new benchmark could become part of the suite of benchmarks used to evaluate and compare generalist 3D LLM models.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2505.05288</guid>
|
||||
<pubDate>Thu, 08 May 2025 14:29:11 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>Scalable Chain of Thoughts via Elastic Reasoning</title>
|
||||
<link>https://arxiv.org/abs/2505.05315</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.05315.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yuhui Xu, Hanze Dong, Lei Wang, Doyen Sahoo, Junnan Li, Caiming Xiong</p><p><b>Upvotes:</b> 20</p><p><b>Summary:</b> Large reasoning models (LRMs) have achieved remarkable progress on complex tasks by generating extended chains of thought (CoT). However, their uncontrolled output lengths pose significant challenges for real-world deployment, where inference-time budgets on tokens, latency, or compute are strictly constrained. We propose Elastic Reasoning, a novel framework for scalable chain of thoughts that explicitly separates reasoning into two phases--thinking and solution--with independently allocated budgets. At test time, Elastic Reasoning prioritize that completeness of solution segments, significantly improving reliability under tight resource constraints. To train models that are robust to truncated thinking, we introduce a lightweight budget-constrained rollout strategy, integrated into GRPO, which teaches the model to reason adaptively when the thinking process is cut short and generalizes effectively to unseen budget constraints without additional training. Empirical results on mathematical (AIME, MATH500) and programming (LiveCodeBench, Codeforces) benchmarks demonstrate that Elastic Reasoning performs robustly under strict budget constraints, while incurring significantly lower training cost than baseline methods. Remarkably, our approach also produces more concise and efficient reasoning even in unconstrained settings. Elastic Reasoning offers a principled and practical solution to the pressing challenge of controllable reasoning at scale.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2505.05315</guid>
|
||||
<pubDate>Thu, 08 May 2025 15:01:06 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>ICon: In-Context Contribution for Automatic Data Selection</title>
|
||||
<link>https://arxiv.org/abs/2505.05327</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.05327.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yixin Yang, Qingxiu Dong, Linli Yao, Fangwei Zhu, Zhifang Sui</p><p><b>Upvotes:</b> 11</p><p><b>Summary:</b> Data selection for instruction tuning is essential for improving the performance of Large Language Models (LLMs) and reducing training cost. However, existing automated selection methods either depend on computationally expensive gradient-based measures or manually designed heuristics, which may fail to fully exploit the intrinsic attributes of data. In this paper, we propose In-context Learning for Contribution Measurement (ICon), a novel gradient-free method that takes advantage of the implicit fine-tuning nature of in-context learning (ICL) to measure sample contribution without gradient computation or manual indicators engineering. ICon offers a computationally efficient alternative to gradient-based methods and reduces human inductive bias inherent in heuristic-based approaches. ICon comprises three components and identifies high-contribution data by assessing performance shifts under implicit learning through ICL. Extensive experiments on three LLMs across 12 benchmarks and 5 pairwise evaluation sets demonstrate the effectiveness of ICon. Remarkably, on LLaMA3.1-8B, models trained on 15% of ICon-selected data outperform full datasets by 5.42% points and exceed the best performance of widely used selection methods by 2.06% points. We further analyze high-contribution samples selected by ICon, which show both diverse tasks and appropriate difficulty levels, rather than just the hardest ones.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2505.05327</guid>
|
||||
<pubDate>Thu, 08 May 2025 15:17:37 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>Crosslingual Reasoning through Test-Time Scaling</title>
|
||||
<link>https://arxiv.org/abs/2505.05408</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.05408.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zheng-Xin Yong, M. Farid Adilazuarda, Jonibek Mansurov, Ruochen Zhang, Niklas Muennighoff, Carsten Eickhoff, Genta Indra Winata, Julia Kreutzer, Stephen H. Bach, Alham Fikri Aji</p><p><b>Upvotes:</b> 8</p><p><b>Summary:</b> Reasoning capabilities of large language models are primarily studied for English, even when pretrained models are multilingual. In this work, we investigate to what extent English reasoning finetuning with long chain-of-thoughts (CoTs) can generalize across languages. First, we find that scaling up inference compute for English-centric reasoning language models (RLMs) improves multilingual mathematical reasoning across many languages including low-resource languages, to an extent where they outperform models twice their size. Second, we reveal that while English-centric RLM's CoTs are naturally predominantly English, they consistently follow a quote-and-think pattern to reason about quoted non-English inputs. Third, we discover an effective strategy to control the language of long CoT reasoning, and we observe that models reason better and more efficiently in high-resource languages. Finally, we observe poor out-of-domain reasoning generalization, in particular from STEM to cultural commonsense knowledge, even for English. Overall, we demonstrate the potentials, study the mechanisms and outline the limitations of crosslingual generalization of English reasoning test-time scaling. We conclude that practitioners should let English-centric RLMs reason in high-resource languages, while further work is needed to improve reasoning in low-resource languages and out-of-domain contexts.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2505.05408</guid>
|
||||
<pubDate>Thu, 08 May 2025 16:50:06 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>StreamBridge: Turning Your Offline Video Large Language Model into a Proactive Streaming Assistant</title>
|
||||
<link>https://arxiv.org/abs/2505.05467</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.05467.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Haibo Wang, Bo Feng, Zhengfeng Lai, Mingze Xu, Shiyu Li, Weifeng Ge, Afshin Dehghan, Meng Cao, Ping Huang</p><p><b>Upvotes:</b> 13</p><p><b>Summary:</b> We present StreamBridge, a simple yet effective framework that seamlessly transforms offline Video-LLMs into streaming-capable models. It addresses two fundamental challenges in adapting existing models into online scenarios: (1) limited capability for multi-turn real-time understanding, and (2) lack of proactive response mechanisms. Specifically, StreamBridge incorporates (1) a memory buffer combined with a round-decayed compression strategy, supporting long-context multi-turn interactions, and (2) a decoupled, lightweight activation model that can be effortlessly integrated into existing Video-LLMs, enabling continuous proactive responses. To further support StreamBridge, we construct Stream-IT, a large-scale dataset tailored for streaming video understanding, featuring interleaved video-text sequences and diverse instruction formats. Extensive experiments show that StreamBridge significantly improves the streaming understanding capabilities of offline Video-LLMs across various tasks, outperforming even proprietary models such as GPT-4o and Gemini 1.5 Pro. Simultaneously, it achieves competitive or superior performance on standard video understanding benchmarks.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2505.05467</guid>
|
||||
<pubDate>Thu, 08 May 2025 17:57:40 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>Generating Physically Stable and Buildable LEGO Designs from Text</title>
|
||||
<link>https://arxiv.org/abs/2505.05469</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.05469.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ava Pun, Kangle Deng, Ruixuan Liu, Deva Ramanan, Changliu Liu, Jun-Yan Zhu</p><p><b>Upvotes:</b> 17</p><p><b>Summary:</b> We introduce LegoGPT, the first approach for generating physically stable LEGO brick models from text prompts. To achieve this, we construct a large-scale, physically stable dataset of LEGO designs, along with their associated captions, and train an autoregressive large language model to predict the next brick to add via next-token prediction. To improve the stability of the resulting designs, we employ an efficient validity check and physics-aware rollback during autoregressive inference, which prunes infeasible token predictions using physics laws and assembly constraints. Our experiments show that LegoGPT produces stable, diverse, and aesthetically pleasing LEGO designs that align closely with the input text prompts. We also develop a text-based LEGO texturing method to generate colored and textured designs. We show that our designs can be assembled manually by humans and automatically by robotic arms. We also release our new dataset, StableText2Lego, containing over 47,000 LEGO structures of over 28,000 unique 3D objects accompanied by detailed captions, along with our code and models at the project website: https://avalovelace1.github.io/LegoGPT/.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2505.05469</guid>
|
||||
<pubDate>Thu, 08 May 2025 17:58:18 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>Flow-GRPO: Training Flow Matching Models via Online RL</title>
|
||||
<link>https://arxiv.org/abs/2505.05470</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.05470.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jie Liu, Gongye Liu, Jiajun Liang, Yangguang Li, Jiaheng Liu, Xintao Wang, Pengfei Wan, Di Zhang, Wanli Ouyang</p><p><b>Upvotes:</b> 51</p><p><b>Summary:</b> We propose Flow-GRPO, the first method integrating online reinforcement learning (RL) into flow matching models. Our approach uses two key strategies: (1) an ODE-to-SDE conversion that transforms a deterministic Ordinary Differential Equation (ODE) into an equivalent Stochastic Differential Equation (SDE) that matches the original model's marginal distribution at all timesteps, enabling statistical sampling for RL exploration; and (2) a Denoising Reduction strategy that reduces training denoising steps while retaining the original inference timestep number, significantly improving sampling efficiency without performance degradation. Empirically, Flow-GRPO is effective across multiple text-to-image tasks. For complex compositions, RL-tuned SD3.5 generates nearly perfect object counts, spatial relations, and fine-grained attributes, boosting GenEval accuracy from 63% to 95%. In visual text rendering, its accuracy improves from 59% to 92%, significantly enhancing text generation. Flow-GRPO also achieves substantial gains in human preference alignment. Notably, little to no reward hacking occurred, meaning rewards did not increase at the cost of image quality or diversity, and both remained stable in our experiments.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2505.05470</guid>
|
||||
<pubDate>Thu, 08 May 2025 17:58:45 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>3D Scene Generation: A Survey</title>
|
||||
<link>https://arxiv.org/abs/2505.05474</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.05474.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Beichen Wen, Haozhe Xie, Zhaoxi Chen, Fangzhou Hong, Ziwei Liu</p><p><b>Upvotes:</b> 13</p><p><b>Summary:</b> 3D scene generation seeks to synthesize spatially structured, semantically meaningful, and photorealistic environments for applications such as immersive media, robotics, autonomous driving, and embodied AI. Early methods based on procedural rules offered scalability but limited diversity. Recent advances in deep generative models (e.g., GANs, diffusion models) and 3D representations (e.g., NeRF, 3D Gaussians) have enabled the learning of real-world scene distributions, improving fidelity, diversity, and view consistency. Recent advances like diffusion models bridge 3D scene synthesis and photorealism by reframing generation as image or video synthesis problems. This survey provides a systematic overview of state-of-the-art approaches, organizing them into four paradigms: procedural generation, neural 3D-based generation, image-based generation, and video-based generation. We analyze their technical foundations, trade-offs, and representative results, and review commonly used datasets, evaluation protocols, and downstream applications. We conclude by discussing key challenges in generation capacity, 3D representation, data and annotations, and evaluation, and outline promising directions including higher fidelity, physics-aware and interactive generation, and unified perception-generation models. This review organizes recent advances in 3D scene generation and highlights promising directions at the intersection of generative AI, 3D vision, and embodied intelligence. To track ongoing developments, we maintain an up-to-date project page: https://github.com/hzxie/Awesome-3D-Scene-Generation.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2505.05474</guid>
|
||||
<pubDate>Thu, 08 May 2025 17:59:54 +0000</pubDate>
|
||||
<title>UniVLA: Learning to Act Anywhere with Task-centric Latent Actions</title>
|
||||
<link>https://arxiv.org/abs/2505.06111</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.06111.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Qingwen Bu, Yanting Yang, Jisong Cai, Shenyuan Gao, Guanghui Ren, Maoqing Yao, Ping Luo, Hongyang Li</p><p><b>Upvotes:</b> 17</p><p><b>Summary:</b> A generalist robot should perform effectively across various environments. However, most existing approaches heavily rely on scaling action-annotated data to enhance their capabilities. Consequently, they are often limited to single physical specification and struggle to learn transferable knowledge across different embodiments and environments. To confront these limitations, we propose UniVLA, a new framework for learning cross-embodiment vision-language-action (VLA) policies. Our key innovation is to derive task-centric action representations from videos with a latent action model. This enables us to exploit extensive data across a wide spectrum of embodiments and perspectives. To mitigate the effect of task-irrelevant dynamics, we incorporate language instructions and establish a latent action model within the DINO feature space. Learned from internet-scale videos, the generalist policy can be deployed to various robots through efficient latent action decoding. We obtain state-of-the-art results across multiple manipulation and navigation benchmarks, as well as real-robot deployments. UniVLA achieves superior performance over OpenVLA with less than 1/20 of pretraining compute and 1/10 of downstream data. Continuous performance improvements are observed as heterogeneous data, even including human videos, are incorporated into the training pipeline. The results underscore UniVLA's potential to facilitate scalable and efficient robot policy learning.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2505.06111</guid>
|
||||
<pubDate>Fri, 09 May 2025 15:11:13 +0000</pubDate>
|
||||
</item>
|
||||
</channel>
|
||||
</rss>
|
||||
|
||||
Reference in New Issue
Block a user