Explore · 每周精选
发现最受关注的研究论文,追踪研究趋势,订阅感兴趣的期刊与关键词。
Jeffrey Amico, Gabriel Passamani Andrade, John Donaghy +12 authors
Swarm sAmpling Policy Optimization (SAPO) is a decentralized and asynchronous RL algorithm that enhances post-training language models without supervised fine-tuning, achieving significant reward gains and scalability across diverse hardware.
50 篇论文 · 按点赞排序
Keke Lian, Bin Wang, Lei Zhang +18 authors
A.S.E is a repository-level benchmark for evaluating the security of AI-generated code, highlighting challenges in secure coding and the limitations of LLMs in real-world scenarios.
Yihao Wang, Pengxiang Ding, Lingxiao Li +13 authors
VLA-Adapter reduces reliance on large-scale VLMs and extensive pre-training by using a lightweight Policy module with Bridge Attention, achieving state-of-the-art performance and fast inference speed with minimal computational resources.
Guibin Zhang, Hejia Geng, Xiaohang Yu +22 authors
Agentic reinforcement learning transforms large language models into autonomous decision-making agents by leveraging temporally extended POMDPs, enhancing capabilities like planning and reasoning through reinforcement learning.
Yang Wang, Chenghao Xiao, Chia-Yi Hsiao +4 authors
LLMs struggle with understanding the nuanced, context-dependent meanings of Drivelological text, which appears nonsensical but contains deeper semantic layers.
Adam Tauman Kalai, Ofir Nachum, Santosh S. Vempala +1 authors
Language models produce incorrect statements due to training and evaluation procedures that reward guessing over acknowledging uncertainty, leading to a need for socio-technical changes in benchmark scoring.
Kaiyan Zhang, Yuxin Zuo, Bingxiang He +36 authors
Reinforcement Learning enhances Large Language Models for complex reasoning tasks, facing challenges in scalability and infrastructure as the field advances.
Shuai Yang, Wei Huang, Ruihang Chu +9 authors
LongLive is a frame-level autoregressive framework for real-time and interactive long video generation, addressing efficiency and quality challenges through causal attention, KV-recache, streaming long tuning, and short window attention.
Junbo Niu, Zheng Liu, Zhuangcheng Gu +58 authors
MinerU2.5, a 1.2B-parameter document parsing vision-language model, achieves state-of-the-art recognition accuracy with computational efficiency through a coarse-to-fine parsing strategy.
Jin Xu, Zhifang Guo, Hangrui Hu +35 authors
Qwen3-Omni, a multimodal model, achieves state-of-the-art performance across text, image, audio, and video, using a Thinker-Talker MoE architecture and a lightweight causal ConvNet for efficient streaming synthesis.
Haozhe Wang, Haoran Que, Qixin Xu +9 authors
REER, a new paradigm for deep reasoning, uses reverse engineering to discover step-by-step reasoning processes, enabling a model to perform competitively on open-ended tasks.
Ming Hu, Chenglong Ma, Wei Li +100 authors
Sci-LLMs are evolving through a co-development with scientific data, addressing unique challenges like multimodal and domain-specific information, and are moving towards autonomous, closed-loop systems in scientific research.
Xu Wujiang, Wentian Zhao, Zhenting Wang +6 authors
Entropy-regularized Policy Optimization (EPO) addresses exploration-exploitation challenges in multi-turn environments with sparse rewards, improving performance in tasks like ScienceWorld and ALFWorld.
Khalil Hennara, Muhammad Hreden, Mohamed Motasim Hamed +4 authors
Baseer, a vision-language model fine-tuned for Arabic document OCR, achieves state-of-the-art performance using a decoder-only strategy and a large-scale dataset, outperforming existing solutions with a WER of 0.25.
Liyang Chen, Tianxiang Ma, Jiawei Liu +7 authors
HuMo is a unified framework for human-centric video generation that addresses challenges in multimodal control through a two-stage training paradigm and novel strategies for subject preservation and audio-visual synchronization.
Jane Luo, Xin Zhang, Steven Liu +11 authors
A graph-driven framework called ZeroRepo uses the Repository Planning Graph (RPG) to generate complete software repositories from scratch, significantly outperforming existing baselines in terms of code size, functional coverage, and test pass rate.
Haoming Wang, Haoyang Zou, Huatong Song +103 authors
UI-TARS-2, a native GUI-centered agent model, addresses challenges in data scalability, multi-turn reinforcement learning, and environment stability, achieving significant improvements over its predecessor and strong baselines across various benchmarks.
Guochao Jiang, Wenfeng Feng, Guofeng Quan +4 authors
A curriculum reinforcement learning framework dynamically adjusts training sample difficulty based on reward variance, improving LLM performance on mathematical reasoning tasks.
Jintao Zhang, Haoxu Wang, Kai Jiang +10 authors
SLA, a trainable attention method combining sparse and linear attention, accelerates Diffusion Transformer models for video generation with minimal quality loss.
Junkang Wu, Kexin Huang, Jiancan Wu +3 authors
Quantile Advantage Estimation stabilizes reinforcement learning with verifiable rewards by addressing entropy issues and improving performance on large language models.
Xuekai Zhu, Daixuan Cheng, Dinghuai Zhang +20 authors
FlowRL enhances LLM reinforcement learning by matching the full reward distribution through flow balancing, improving diversity and performance over reward-maximizing methods.
Liangcai Su, Zhen Zhang, Guangyu Li +19 authors
AgentFounder, a deep research agent model incorporating Agentic Continual Pre-training, achieves state-of-the-art performance in agentic tasks while maintaining strong tool-use ability.
Zhaoyang Liu, JingJing Xie, Zichen Ding +18 authors
ScaleCUA, a large-scale dataset and model for computer use agents, achieves state-of-the-art performance across multiple platforms and tasks by leveraging data-driven scaling.
Jie Jiang, Qi Yang, Bolin Ni +3 authors
R-4B, an auto-thinking multimodal large language model, uses bi-mode annealing and Bi-mode Policy Optimization to adaptively decide on problem-solving strategies, achieving state-of-the-art performance with lower computational cost.
Zijian Li, Xin Guan, Bo Zhang +9 authors
WebWeaver, a dual-agent framework, addresses open-ended deep research challenges by integrating adaptive planning and focused synthesis to produce high-quality, reliable reports.
Yang Zhou, Yifan Wang, Jianjun Zhou +16 authors
OmniWorld, a large-scale, multi-domain, multi-modal dataset, addresses the limitations of existing 4D world modeling datasets and benchmarks, enabling significant performance improvements in 4D reconstruction and video generation.
Tong Zheng, Hongming Zhang, Wenhao Yu +8 authors
Parallel-R1, a reinforcement learning framework, enhances large language models' reasoning capabilities by enabling parallel thinking through a progressive curriculum, leading to significant performance improvements on math benchmarks.
Sicong Leng, Jing Wang, Jiaxi Li +12 authors
Variance-Aware Sampling and large-scale CoT data improve multimodal reasoning models by stabilizing RL fine-tuning and enhancing performance on benchmarks.
Yang Xiao, Mohan Jiang, Jie Sun +18 authors
LIMI demonstrates that sophisticated agentic intelligence can emerge from minimal, strategically curated demonstrations, outperforming data-intensive models on agency benchmarks.
Yizhou Wang, Chen Tang, Han Deng +29 authors
A scientific reasoning foundation model pre-trained on diverse scientific data supports multiple tasks and enhances cross-domain generalization and fidelity through specialized training techniques.
北京市昌平区探索星信息技术及软件开发工作室
京ICP备2026059466号