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。
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.
50 篇论文 · 按点赞排序
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.
Fan Jiang, Zhaoxu Sun, Mengchao Wang +38 authors
ABot-World-0 is a real-time action-conditioned video world model that uses progressive distillation, long-horizon alignment, and a co-designed streaming stack to enable efficient, long-horizon interactive world generation.
Hanzhang Zhou, Panrong Tong, Xu Zhang +13 authors
Qwen-UI-Agent is a foundation GUI agent that integrates mobile, computer, web, and search environments with CLI execution, long-horizon online reinforcement learning, and autonomous data generation to achieve state-of-the-art real-world device performance.
Wentao Zhang, Liliana Hotsko, Woojeong Kim +3 authors
Fuzzy-function programming compiles natural-language specifications into compact neural artifacts using a 4B compiler and 0.6B interpreter, achieving efficient, local execution with reduced memory usage and faster inference.
Bing Yan, Gregory Wolfe, Stefano Martiniani +1 authors
Chemistry literature synthesis often requires assembling specific findings scattered across many publications, yet existing literature-search systems primarily return ranked document lists. As a result, scientists and AI agents need to locate relevant information, verify their provenance, and assemble cross-paper answers manually. We present AskChem, a claim-centered infrastructure for cross-paper chemistry search. AskChem changes the unit of retrieval from the paper to the provenance-carrying claim: each paper is converted into atomic, typed claims, each grounded by a source DOI and a verbatim quote or an explicit evidence locator. Over this shared claim store, AskChem exposes complementary structures for search and synthesis: a stabilized faceted taxonomy for hierarchical retrieval and browsing, an evidence graph linking claims through relations, and an exploratory living taxonomy that situates indexed papers under scientific principles. AskChem currently indexes 2.4M claims from 147K papers and provides a web interface, as well as REST, SDK, and MCP access for AI agents. On AskChem-Bench, grounding a GPT-5.5 reader in AskChem yields 100% resolvable DOIs, compared with 88.3% without retrieval, and the highest citation density among five tested systems. AskChem is live at https://askchem.org.
Zeyu Zhang, Ziliang Guo, Yihang Sun +14 authors
Metis introduces memory foundation models that embed persistent, dynamically evolving native memory states and autonomous storage procedures directly into foundation models via memory attention and gradient-free updates.
Ruhan Wang, Yucheng Shi, Zongxia Li +7 authors
The Harness Handbook and Behavior-Guided Progressive Disclosure automatically map agent behaviors to source code, improving localization and edit planning for evolving AI harnesses.
Changhai Zhou, Kieran Liu, Yuhua Zhou +17 authors
LongStraw is an execution framework that enables million-token reinforcement learning post-training with fixed GPU resources by reducing live training graphs through replay and selective state retention.
Kehan Li, Bohan Hou, Minghao Zhu +27 authors
RynnBrain 1.1 is a family of embodied foundation models that integrates spatio-temporal and physical grounding with contact-point prediction, 3D grounding, and cross-embodiment action spaces to improve robot perception, reasoning, and manipulation.
Jianshu Zhang, Keliang Wu, Haoran Lu +8 authors
A survey unifies progress reward modeling for robotic learning by analyzing model interfaces, internal construction methods, and evaluation benchmarks.
Junlin Yang, Che Jiang, Yu Fu +21 authors
OpenMLE enables recursive self-improvement in machine learning engineering via a full-stack system combining execution-grounded operator learning and long-horizon evolutionary search, significantly boosting benchmark performance with a 35B model.
Shuyao Shang, Yuqi Wang, Ruopeng Gao +4 authors
PhiZero learns a discrete physical-language representation from videos to explicitly reason about world dynamics before rendering future frames, improving coherence and enabling interactive simulation.
Xinhao Li, Yuhan Zhu, Xiangyu Zeng +24 authors
VideoChat3 is an open, efficient generalist video-language model that uses an inflated 3D vision transformer and adaptive frame resolution for efficient spatiotemporal modeling, alongside curated synthetic datasets, to achieve broad video understanding with only 4B parameters.
Jing Liang, Hongyao Tang, Yi Ma +9 authors
Training-inference mismatch in reinforcement learning for large language models leads to instability, which is addressed through a new policy optimization objective and framework that ensures consistent policy improvements between training and inference phases.
Yuhan Zhu, Changlian Ma, Xiangyu Zeng +12 authors
TimeLens2 improves video temporal grounding by treating evidence as interval sets with robust multi-span supervision and a Wasserstein-based reward, achieving strong results across benchmarks.
Simple AI, Yuteng Wei, Jinming Ma +15 authors
High-fidelity robot-free UMI data enables direct real-robot deployment without teleoperation anchors, improving manipulation policy accuracy and success rates.
Shuqi Lu, Chaofan Li, Kun Luo +21 authors
AREX is a recursively self-improving deep research agent that verifies answers constraint-wise, compresses verified evidence into a compact state, and uses targeted follow-up research to refine results over long horizons.
Mikhail Komarov, Ivan Bondarenko, Stanislav Shtuka +5 authors
RAGU is a modular GraphRAG engine that separates knowledge extraction from consolidation and uses a small language-optimized model to build cleaner graphs, improving retrieval and synthesis over existing systems.
Jintao Zhang, Kai Jiang, Jintao Chen +24 authors
Vidu S1 is a real-time interactive video generation model that supports voice-controlled digital character animation with infinite-length output and high frame rate on consumer hardware.
Shiyuan Feng, Huan-ang Gao, Haohan Chi +7 authors
Direct On-Policy Distillation transfers reinforcement learning improvements from smaller to larger models by using the policy shift induced by RL as an implicit reward signal, enabling efficient scaling of training without re-running expensive RL on the target model.
Runming He, Zhen Hao Wong, Hao Liang +4 authors
DataFlow-Harness guides LLM agents to build persistent, editable data pipelines via incremental mutations and live platform grounding, achieving high reliability with lower cost and latency.
Yijia Fan, Zonglin Di, Zimo Wen +8 authors
RESOURCE2SKILL converts diverse multimedia tutorials and artifacts into structured, executable skills for software agents, improving performance through hierarchical retrieval, composition, and online acquisition.
Guoxuan Chen, Chufeng Xiao, Haoran Yang +30 authors
Boogu-Image-0.1 is an open-source unified multimodal model family that achieves strong text-to-image generation, editing, and bilingual rendering with low training cost by improving multimodal understanding, data quality, and agentic inference scaling.
Hengyi Xie, Chenfei Yao, Xianjin Wu +7 authors
TurboVLA replaces the LLM-centric vision-language-action pipeline with direct vision-language interaction and a compact decoder to cut inference costs while maintaining high robotic manipulation performance.
Yunlong Lin, Zixu Lin, Zhaohu Xing +23 authors
JarvisHub is a canvas-based agent framework that supports sustained, inspectable multimodal creative production through editable project states and progressive agent planning.
Wenhao Zeng, Yuling Shi, Xiaodong Gu +10 authors
A Dockerless environment-free agentic patch verifier improves code patch evaluation accuracy and enables effective post-training without execution-based verification costs.
Xinlei Yu, Gen Li, Qingyi Si +13 authors
DOPD addresses privilege illusion in on-policy distillation by dynamically routing token-level supervision between teacher and student policies based on advantage gaps and probabilities, improving capability transfer in large and vision-language models.
Zhongming Yu, Hengjia Yu, Boqin Yuan +12 authors
CodeNib provides reusable multi-view repository indexing with faster updates and reduced context tokens while maintaining accurate navigation across code edits.
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.
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