83Upvotes
AI papers on 22 Oct 2026
The list as it stood that day: the papers researchers were upvoting on Hugging Face's daily papers. Papers stay on arXiv.
Updated 22 Oct 2026, 11:25 UTCSource: Hugging Face daily papers
01 · Oct 19 02 · Oct 18 SpatialScout: Can VLM Agents Actively Explore and Map 3D Scenes?
Zhaoxi Zhang, Hao Liang, Linxuan Wu and 7 more82Upvotes03 · Oct 19 Cache Engineering for Agents
Tianyu Fu, Ruoxi Wang, Zihan Min and 6 more75Upvotes04 · Oct 20 Looking Ahead: Modeling Future Evolution in Autoregressive Video Generation
Ruopeng Gao, Yukun Huang, Jiarui Hu and 4 more73Upvotes05 · Oct 18 Agent World Model in the Wild: Computer-Use Agent Environment Synthesis
Zhaoyang Wang, Qianhui Wu, Haorui Wang and 9 more59Upvotes06 · Oct 20 DONIC: Generalist Dexterous Bimanual Tracking Control from Human Demonstrations
Mingze Sun, Ziang Cao, Yuan Fei and 8 more50Upvotes07 · Oct 14 48Upvotes08 · Oct 13 PrismaCoder: Pushing the Boundaries of Open Multimodal Code Intelligence through Decomposed Rubric Synthesis
Qiushi Sun, Jingyang Gong, Yang Liu and 14 more47Upvotes09 · Oct 12 Socratic Skill Learning: Interleaving Teaching and Practice for Transferable Agent Skills
Letian Zhu, Han Li, Yifan Yao and 9 more31Upvotes10 · Oct 19 Scaling in Games: Continued Pre-Training For Embodied Agents In Diverse Virtual Worlds
Kuan Zhang, Yukun Chen, Zhihao Yang and 8 more21Upvotes11 · Oct 19 AgenticRoboRL: Bringing Coding-Agent Post-Training to Agentic Robotics
Xinxin Liu, Bingxin Xu, Wenrui Bao and 4 more18Upvotes12 · Oct 20 Memory-Centric Continual Learning for AI Agents
Dongfang Li, Zhuoen Chen, Bonian Jia and 25 more17Upvotes13 · Oct 20 16Upvotes14 · Oct 20 Multimodal Embodied Agents: A Unified Capability-centric Perspective from Computer-Use to Robot-Use
Yanzhe Chen, Ziyi Yang, Jifeng Zhu and 14 more15Upvotes15 · Oct 20 Sparsity Should Be ALLOTted by Output: Training-Free Allocation of Block-Sparse Attention for Video Diffusion Transformers
Tianze Xia, Xiaoling Zhou, Ruya Lan and 3 more13Upvotes16 · Oct 20 ALPS: Visual State Encoders for World Models
Yanqing Liu, Letian Zhang, Chengzhi Liu and 5 more12Upvotes17 · Oct 19 Building AI Research Teams for Autonomous Discovery of Linear Attention Architectures
Yujian Liu, Li An, Zelin He and 5 more12Upvotes18 · Oct 13 DeLoop: Repeated Actions as Self-Supervision for Long-Horizon Agents
Tianle Chen, Pushkar Singh, Ketan Todi and 8 more12Upvotes19 · Oct 19 Automating ML for Science: Can Frontier Agents Climb Scientific Hills in the Wild?
Ming Zhong, Stacy Li, Nicholas Carlini and 1 more11Upvotes20 · Oct 19 Training the Whole Agent, Not Just the Model
Lingxiao Tang, Wei Tao, Yiwen Guo and 1 more11Upvotes