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。
Björn Engdahl, Adrian Kosowski, Jan Chorowski +6 authors
A 150M-parameter reasoning model using recurrent latent reasoning and in-context learning achieves a new cost-accuracy frontier on ARC-AGI-1.
904 篇论文 · 按点赞排序
Xuyang Liu, Shihao Wang, Xinyu Wei +5 authors
OmniCompass is a holistic benchmark for omni-modal video grounding and understanding that evaluates vision-language and audio-visual reasoning through temporal grounding, spatial grounding, and question answering tasks.
Dingjie Song, Zhiling Yan, Ziqian Zhang +2 authors
PremiseCheck improves peer review verification by decomposing comments into explicit premises checked by decision models, achieving high accuracy with lower cost and latency.
Haotian Ma, Ruqi Yang, Philip Townsend
Spectral-Spatial Interpretation assigns localized channel importance at each spatial position via conditional Shapley values, yielding full spectral-spatial attribution matrices that outperform existing methods on multispectral image tasks.
EverMind AI
Raven is an open-source multi-agent ecosystem that autonomously builds and evolves modular harnesses, enabling cross-domain collaboration and expanding reliable task coverage through composable agent units.
DeepReinforce Team, Xiaoya Li, Xiaofei Sun +4 authors
GrandCode is a multi-agent reinforcement learning system that outperforms human competitors in competitive programming challenges by orchestrating specialized agent modules and employing novel reward policy optimization techniques.
Dingjie Song, Zhiling Yan, Yuxuan Zhang +1 authors
LEV is a looped decision model that increases reasoning depth by iterating its layers without generating tokens, improving accuracy on hard questions while allowing adaptive computation via a stopper.
StreamEval Team
StreamEval benchmarks interactive streaming video generation across five tasks, revealing that reliable request execution and sustained state consistency remain major challenges despite high visual quality.
Ke Yang, Chenglong Wang, Michel Galley +4 authors
StudentSim trains personalized student simulators from sparse data to mirror learner responses and adapt to tutor guidance, outperforming existing models across chess, writing, and math.
Maijunxian Wang, Ruisi Wang, Juyi Lin +53 authors
A large-scale video reasoning dataset and benchmark are introduced to study video intelligence capabilities beyond visual quality, enabling systematic analysis of spatiotemporal reasoning and generalization across diverse tasks.
Yuhao Wu, Jingyuan Zhang, Jiajun Shi +16 authors
HarnessDev evaluates agents by measuring their ability to build and iteratively improve execution infrastructure rather than final task outputs, revealing that self-built harnesses vary widely in capability and efficiency and transfer poorly across models.
Hongyuan Adam Lu, Z. L., Victor Wei +5 authors
A novel framework for improving large language model performance through textual frequency analysis, including laws, distillation, and curriculum training approaches.
Kimi Team, Tongtong Bai, Yifan Bai +399 authors
Kimi K3 is a large-scale mixture-of-experts model with native vision and long-context capabilities that improves scaling efficiency and achieves strong performance across coding, reasoning, and agentic tasks.
Yihao Wang, Yuheng Ji, Mingyu Cao +54 authors
Orca establishes a unified world latent space through next-state-prediction modeling using multimodal data and demonstrates superior performance in downstream tasks compared to specialized baselines.
Enhan Zhao, Yongqi Tong, Xuejun Yu +6 authors
BizBench evaluates long-horizon business agents on intermediate execution validity using real-world payment procedures, revealing that frontier models frequently violate constraints despite achieving partial goal success.
Ming Qian, Tianjian Ouyang, Mingchao Sun +25 authors
ABot-Earth 0.5 generates realistic 3D environments from satellite imagery using 3D Gaussian Splatting representation, enabling fast synthesis and real-time visualization for Embodied AI applications.
Yanlin Li, Mingyang Hao, Shengqiong Wu +3 authors
Omni-IO Skills is a plug-and-play harness that enables general agents to coordinate multimodal workflows across diverse artifacts via hierarchical skills, dependency-aware orchestration, and a persistent asset registry.
Hongyuan Adam Lu, Z. L. Victor Wei, Qun Zhang +28 authors
Looped World Models introduce iterative latent state refinement through shared transformer blocks, achieving 100x parameter efficiency while adapting computational depth to prediction complexity.
Xiyuan Yang, Sheikh Sarwar, Jingru Cheng +8 authors
World Model RL replaces costly environment execution with a learned world model and applies debiasing and denoising to accelerate post-training of autonomous research agents.
SenseNova, Joint Research Team, Zhongang Cai +59 authors
GPT-6-Astra achieves high performance across diverse robotic tasks via in-context learning, yet real-world deployment reveals gaps in demonstration cost, execution time, and practical embodied intelligence.
NeoHorse Team, Guoliang Cao, Guohao Dai +34 authors
NeoHorse-1 uses agentic post-training with intelligent routing, structured feedback loops, and curriculum-based distillation to improve model capabilities across agent benchmarks.
Jianlyu Chen, Yuyang Hu, Hongjin Qian +8 authors
DisCo is a research agent that distills operational knowledge into reusable skills, significantly improving autonomous ML research performance across benchmarks.
Ziheng Qin, Yaxin Lu, Zhangyang Atlas Wang +1 authors
StateM is a runtime system that improves long-horizon agent execution through durable states, recoverable runbooks, and enforceable procedural controls without altering model weights.
Qi Li, Xinchao Wang
Jeva is a decision-native architecture that jointly enforces null-awareness, permutation invariance, option scalability, and cross-request caching for structured decision-making.
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.
Jingqi Tong, Mingzhe Li, Hangcheng Li +20 authors
Great scientists have strong judgement and foresight, closely tied to what we call scientific taste. Here, we use the term to refer to the capacity to judge and propose research ideas with high potential impact. However, most relative research focuses on improving an AI scientist's executive capability, while enhancing an AI's scientific taste remains underexplored. In this work, we propose Reinforcement Learning from Community Feedback (RLCF), a training paradigm that uses large-scale community signals as supervision, and formulate scientific taste learning as a preference modeling and alignment problem. For preference modeling, we train Scientific Judge on 700K field- and time-matched pairs of high- vs. low-citation papers to judge ideas. For preference alignment, using Scientific Judge as a reward model, we train a policy model, Scientific Thinker, to propose research ideas with high potential impact. Experiments show Scientific Judge outperforms SOTA LLMs (e.g., GPT-5.2, Gemini 3 Pro) and generalizes to future-year test, unseen fields, and peer-review preference. Furthermore, Scientific Thinker proposes research ideas with higher potential impact than baselines. Our findings show that AI can learn scientific taste, marking a key step toward reaching human-level AI scientists.
Zhe Qian, Ziyang Gong, Zhongxing Xu +9 authors
LoopVL extends Loop Transformers to vision-language modeling by iteratively updating a shared multimodal state, improving reasoning and revealing dynamic visual attention shifts.
Luozheng Qin, Yuhan Zhu, Changhai Zhou +9 authors
MJev-Spatial is a fast multimodal decision model that unifies spatial reasoning tasks into a single-pass classification framework, improving speed and accuracy over autoregressive vision-language models.
Yuhao Wu, Jingyuan Zhang, Jiajun Shi +18 authors
ASPIRE introduces a benchmark for self-evolving LLM agents from vague natural-language goals, revealing challenges in goal interpretation, data selection, and stable weight-level improvement.
Dingjie Song, Hanrong Zhang, Dawei Liu +10 authors
Command-line coding agents (e.g., Claude Code, Gemini CLI) can already read and write files and sustain long sessions, yet end-to-end research still fragments across chat tools, IDEs, terminals, and writing environments, and the decisions that make it auditable are rarely preserved. We present Dr. Claw, an open-source workspace that wraps existing coding-agent executors in a controllable and auditable human-in-the-loop workflow rather than introducing another autonomous agent. Persistent state objects, a reusable skill library, and multi-executor coordination link human decisions to AI execution, turning planning, execution, and writing into one traceable, recoverable loop. We demonstrate Dr. Claw through an interactive three-view scenario and a failure-recovery walkthrough, and evaluate it against a bare command-line agent sharing the same backend executor, so the comparison contrasts the whole orchestration layer (task graph, state objects, and skill library) with the agent it wraps. Holding the executor fixed, Dr. Claw scores higher on research completeness while persisting an auditable, recoverable process trail. Demo access: repository https://github.com/OpenLAIR/dr-claw, released under AGPL-3.0 with GPL-3.0 upstream components.
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