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。
686 篇论文 · 按点赞排序
Tianjie Ju, Zheng Wu, Yueqing Sun +15 authors
UrbanGround evaluates whether multimodal language model agents can sustain reliable navigation and spatial reasoning in a realistic 3D city replica, revealing that local perceptual skills fail to compose into extended goal-directed behavior.
V Team, Wenyi Hong, Xiaotao Gu +75 authors
GLM-5V-Turbo integrates multimodal perception as a core reasoning component for agentic tasks, demonstrating strong performance in multimodal coding and visual tool use while maintaining text-only capabilities.
Qiming Shi, Yulong Tao, Linbo Jin +10 authors
MerchantBench evaluates long-term coherence of LLM agents in a year-long e-commerce simulation requiring persistent decision-making across sourcing, pricing, and cash-flow management with mixed feedback delays.
Yunheng Li, Guohong Mu, Hao Li +4 authors
OraRL improves reinforcement learning post-training for video multimodal language models by integrating oracle rollouts with decoupled advantage estimation and sign-balanced pruning, achieving higher sample efficiency and scalability without chain-of-thought generation.
Dong Chen, Fangyun Wei, Ziyu Wan +18 authors
Lens is a compact 3.8B-parameter text-to-image model achieving superior performance with reduced training compute through dense caption datasets, multi-resolution batching, efficient architecture, and optimization techniques.
Chao Xu, Maohua Li, Qirui Li +9 authors
Diffusion Transformers suffer from inefficient cross-layer information flow that traditional residual connections cannot address, prompting the introduction of a learnable, timestep-adaptive routing mechanism that improves training efficiency and model quality.
Seokju Cho, Ryo Hachiuma, Abhishek Badki +8 authors
SpatialClaw is a training-free framework that uses code as an action interface to enable flexible, stateful spatial reasoning in vision-language models, achieving superior performance across diverse 3D/4D spatial reasoning tasks.
Hao Fei, Yiran Zhao
Mental World Modeling integrates hidden mental states into predictive world models to improve action forecasting by jointly simulating physical scenes and agent beliefs.
Songchun Zhang, Zeyue Xue, Siming Fu +6 authors
Astrolabe is an efficient online reinforcement learning framework for distilled autoregressive video models that improves generation quality through forward-process RL formulation and streaming training with multi-reward objectives.
Yijing Tu, Shaojin Wu, Mengqi Huang +4 authors
Stream-T1 enables efficient test-time video generation through streaming synthesis with temporal guidance, achieving improved consistency and quality over existing diffusion-based methods.
Zongchuang Zhao, Xin Zhou, Tianyang Xu +5 authors
SimWAM trains a lightweight action planner using video generation as a training signal, enabling efficient trajectory prediction without future generation at inference and supporting reinforcement learning optimization.
Yubo Wang, Jiarong Liang, Yuxuan Zhang +5 authors
Function-aware fill-in-the-middle mid-training on code improves coding-agent tool integration and mitigates capability erosion from agentic post-training.
Zhi Zheng, Rongsheng Chen, Yunpeng Ba +3 authors
Agentic ESOpt uses evolution strategies for scalable full-parameter fine-tuning of long-horizon LLM agents via trajectory-level reward-weighted updates and parameter-context co-evolution.
Haoran Zhang, Luxin Xu, Zhilin Wang +11 authors
Proactive assistance in personal agent systems requires identifying hidden user intents through sustained multi-turn interactions, which current benchmarks fail to adequately evaluate.
Shengbang Tong, David Fan, John Nguyen +18 authors
Controlled multimodal pretraining experiments reveal key insights about unified visual representations, data complementarity, world modeling emergence, and efficient scaling through mixture-of-experts architectures.
Zhiheng Song, Jingshuai Zhang, Chuan Qin +6 authors
MobileBench is a scalable benchmark for evaluating LLM-based route-planning agents in real-world scenarios, featuring anonymized user queries and a deterministic sandbox for reproducible testing.
Tao Feng, Fangxu Yu, Haozhen Zhang +9 authors
LLM routing is formalized as a sequential decision process with a unified benchmark and modular infrastructure to compare and improve cost-effective model selection.
Wanli Li, Bowen Zhou, Yunyao Yu +4 authors
WeaveBench presents a comprehensive benchmark for evaluating computer-use agents across multiple interfaces, revealing significant challenges in long-horizon task orchestration and highlighting the limitations of traditional performance assessment methods.
Jinyang Wu, Shuo Yang, Zhengxi Lu +8 authors
SEED improves long-horizon agent training by extracting hindsight skills from completed trajectories and distilling them into dense token-level supervision alongside outcome-based reinforcement learning.
Shuang Chen, Kaituo Feng, Hangting Chen +7 authors
OpenSearch-VL presents an open-source framework for training advanced multimodal search agents using reinforcement learning, featuring specialized data curation, diverse tool environments, and a novel training algorithm that improves performance across multiple benchmarks.
Qinsi Wang, Jing Shi, Huazheng Wang +8 authors
RLSVR extends reinforcement learning with verifiable rewards to open-ended tasks by transforming them into self-verifiable proxy environments, demonstrated via a multi-agent spy game that yields automatic rewards for text generation and reasoning.
Jing Xiong, Qi Han, Yunta Hsieh +11 authors
MMFormalizer enables multimodal autoformalization by integrating visual perception with formal mathematical reasoning, supporting complex physical domains from classical mechanics to quantum mechanics.
Yuchao Gu, Guian Fang, Yuxin Jiang +4 authors
AnyFlow introduces a novel any-step video diffusion distillation framework that improves upon consistency distillation by optimizing full ODE sampling trajectories through flow-map transition learning and backward simulation techniques.
Yicheng Xiao, Wenxun Dai, Xinran Qin +22 authors
JoyAI-Video-Edit is a 16B-parameter autoregressive diffusion framework that enables real-time, open-ended video editing with high source fidelity and long-term temporal consistency on a single GPU.
Hong Liu, Jiaqi Zhang, Chao Wang +13 authors
Embedding scaling offers superior sparsity scaling compared to expert scaling in large language models, enabling efficient inference through system optimizations and speculative decoding.
Kaining Ying, Hengrui Hu, Siyu Ren +6 authors
WBench presents a comprehensive multi-turn benchmark for evaluating interactive world models across five dimensions using 289 test cases and 1,058 interaction turns with diverse scenarios and interaction types.
Hao Yu, Haotong Lin, Jiawei Wang +7 authors
InfiniDepth represents depth as neural implicit fields using a local implicit decoder, enabling continuous 2D coordinate querying for arbitrary-resolution depth estimation and superior performance in fine-detail regions.
Haozhe Wang, Cong Wei, Weiming Ren +3 authors
Training reward models to generate multi-dimensional critiques improves visual generation through both enhanced reinforcement learning rewards and test-time refinement loops, achieving state-of-the-art performance with reduced training data requirements.
Junyao Gao, Sibo Liu, Jiaxing Li +6 authors
MegaStyle presents a scalable data curation pipeline for creating high-quality, style-consistent datasets using large generative models and proposes style-supervised contrastive learning for effective style representation extraction.
Zheng-Hui Huang, Zhixiang Wang, Jiaming Tan +6 authors
A large-scale dynamic dataset derived from AAA games is introduced to improve generative inverse and forward rendering, featuring high-resolution synchronized RGB and G-buffer data alongside a novel VLM-based evaluation method that correlates well with human judgment.
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