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。
Fangfu Liu, Kai He, Tianchang Shen +7 authors
A generative multi-agent world model is presented that uses simplex rotary agent encoding and sparse hub attention to enable scalable, permutation-symmetric interaction between multiple agents in interactive video generation.
50 篇论文 · 按点赞排序
Yifan Yang, Ziyang Gong, Weiquan Huang +12 authors
SkillOpt introduces a systematic text-space optimizer for agent skills that trains skills as external agent state with stable updates and zero deployment inference overhead, achieving superior performance across multiple benchmarks and execution environments.
Dongrui Liu, Yu Li, Zhonghao Yang +47 authors
A lightweight and scalable agent safety alignment framework is proposed to address emerging threats from advanced AI models, featuring taxonomy-guided training with minimal samples and efficient deployment in real-world scenarios.
Qiuyue Wang, Mingsheng Li, Jian Guan +37 authors
A unified vision-language-action model is presented that integrates diverse embodied decision-making tasks through a shared architecture and training approach, demonstrating strong performance across manipulation, navigation, and trajectory prediction with generalization across different robot platforms and environments.
Shihao Wang, Shilong Liu, Yuanguo Kuang +10 authors
Parallel Box Decoding enables efficient and accurate unified visual grounding and detection by decoding geometric elements as atomic units, improving both throughput and localization quality.
Guochao Jiang, Jingyi Song, Guofeng Quan +3 authors
Dynamic Variance-adaptive Advantage Optimization (DVAO) addresses training instability in multi-reward reinforcement learning by adaptively weighting objectives based on empirical reward variance, maintaining bounded advantage magnitudes and improving multi-objective performance.
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.
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.
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.
Minki Kang, Shizhe Diao, Ryo Hachiuma +4 authors
Agents using vision-language models with extended reasoning face challenges in tool utilization, which are addressed through AXPO, a method that improves performance by optimizing thinking prefixes and tool call resampling.
Hongru Hou, Tiehua Mei, Denghui Geng +5 authors
Proactive recommender systems using reinforcement learning face challenges with gradient estimation bias and variance, which are addressed through stepwise reward centering and position-specific advantage estimation mechanisms.
Fancy Kong, Congjie Zheng, Murphy Zhuang +8 authors
Generative UI models enable personal agents to synthesize dynamic interfaces with lightweight executable actions for enhanced interaction beyond text-only formats.
Songlin Yang, Haobin Zhong, Ruilin Zhang +23 authors
EvalVerse presents a comprehensive evaluation framework for generative video models that bridges the gap between human aesthetic judgment and machine scoring through expert-calibrated vision-language models and multi-stage cinematic assessment.
Bang Liu, Yongfeng Gu, Jiayi Zhang +26 authors
Autonomous agents are moving from tools into a layer of social infrastructure: they browse, purchase, deploy software, manage systems, and increasingly interact with one another. As these systems scale, the bottleneck shifts away from raw model capability toward coordination. Agents need to form reliable relationships, organize multi-agent work, exchange value, support an AI economy, and stay safe and accountable under real-world oversight. This paper introduces the Foundation Protocol (FP), a graph-first coordination layer for an emerging human-AI society. FP unifies heterogeneous entities, including agents, tools, resources, humans, institutions, and organizations, and supports native multi-party organization and event-based collaboration. It also provides economic primitives for metering, receipts, and settlement, and treats policy, provenance, and audit as first-class concerns. FP is designed to wrap and bridge existing protocols rather than replace them, enabling incremental adoption while reducing integration and governance overhead. The aim is to keep autonomous agency composable while keeping accountability non-negotiable, so that coordination itself can become shared infrastructure for a human-AI society that is open, pluralistic, and governable.
Jinheon Baek, Soyeong Jeong, Sangwoo Park +5 authors
OmniRetrieval is a framework that handles diverse knowledge sources by identifying appropriate repositories and dispatching native queries to their respective execution engines, outperforming single-source approaches across multiple dataset types.
Haiwen Diao, Jiahao Wang, Penghao Wu +18 authors
NEO-ov is a native vision-language model that end-to-end learns cross-frame and pixel-word correspondences without modular components, enabling unified spatiotemporal modeling and competitive performance in visual perception tasks.
Haosong Peng, Hao Li, Jiaqi Chen +10 authors
SpatialBench presents a comprehensive benchmark for evaluating spatial foundation models across diverse domains and tasks, revealing limitations in current models and introducing DA-Next-5M and DA-Next to advance spatial representation learning.
Dingbang Wu, Rui Hao, Haiyang Wang +8 authors
MobileGym presents a browser-based mobile environment enabling deterministic evaluation and scalable reinforcement learning through JSON-based state management and parallel execution.
Guowei Xu, Zhenting Qi, Huangyuan Su +4 authors
Bidirectional Evolutionary Search combines forward candidate evolution with backward goal decomposition to improve language model generation by overcoming limitations of traditional search methods.
Fangtai Wu, Hailong Guo, Shijie Huang +7 authors
CollectionLoRA enables efficient deployment of multiple customized image editing effects by distilling numerous LoRAs into a single model through multi-teacher distillation and specialized mechanisms for concept isolation and generation.
Min Zhao, Hongzhou Zhu, Bokai Yan +9 authors
A comprehensive framework is presented for converting bidirectional video diffusion models into real-time interactive world models with controllable, causal, and low-latency capabilities through fine-tuning and distillation techniques.
Shuofei Qiao, Yunxiang Wei, Jiazheng Fan +8 authors
SciAtlas presents a large-scale, multi-disciplinary knowledge graph that enables structured topological reasoning for academic research by integrating millions of papers and entities to support automated scientific discovery.
Cheolhong Min, Jaeyun Jung, Daeun Lee +5 authors
Vision-language models exhibit entangled spatial representations that correlate vertical image position with distance, impacting reasoning robustness and performance across benchmarks.
You-Zhe Xie, Yu-Hsuan Li, Jie-Ying Lee +3 authors
Video diffusion models exhibit arrow-of-time perception without true causal understanding, as demonstrated by a novel benchmark measuring causal cognition through reverse surprise and visual language model analysis.
Weijie Wang, Zimu Li, Jinchuan Shi +5 authors
TriSplat is a feed-forward 3D reconstruction network that uses oriented triangle primitives to directly generate simulation-ready meshes from single images, bypassing expensive post-processing steps.
Guijin Son, Seungyeop Yi, Minju Gwak +3 authors
ResearchMath-14k dataset and ResearchMath-Reasoning trajectories are introduced to advance research-level mathematical reasoning in language models, demonstrating that filtered open-problem attempts provide useful supervision for model improvement.
Bin Lin, Bo Zhao, Boyong Wu +98 authors
StepAudio 2.5 is a unified audio-language model that matches specialized systems in ASR, TTS, and real-time spoken interaction by using task-tailored reinforcement learning from human feedback to optimize shared representations across different operational modes.
Caijun Xu, Changyi Xiao, Zhongyuan Peng +1 authors
DenoiseRL is a reinforcement learning framework that enhances reasoning in large language models by learning from incorrect traces through failure-oriented optimization, improving scalability and reducing dependence on external supervision.
Jian Xie, Tianhe Lin, Zilu Wang +16 authors
QUEST is an open-family of deep research agents trained with synthesized data and reinforcement learning to perform well across diverse long-horizon search tasks.
Yifan Lu, Qi Wu, Jay Zhangjie Wu +4 authors
PiD introduces a pixel diffusion decoder that reformulates latent decoding as conditional pixel diffusion, enabling fast and high-quality image synthesis at high resolutions with reduced computational requirements.
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