Focused Omni-Modal GUI Agents
Fuyao Zhang, Wenwen He, Jiaming Zhang and 6 more88Upvotes
AI papers on 21 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 21 Oct 2026, 06:23 UTCSource: Hugging Face daily papers
01 · Oct 18 02 · Oct 19 Sage-A1.5: From Long-Horizon Execution to Scientific Exploration with Capability Composition
Wenjie Lou, Tianshuo Peng, Shiyang Feng and 96 more50Upvotes03 · Oct 19 PAR: Progress-Aligned Recurrence for Length Generalization in State Tracking
Pan Wang, Yihao Hu, Guangyuan Dong and 8 more39Upvotes04 · Oct 19 Learning the 4D World through Point Trajectory Forecasting
Byungwoo Jeon, Sunghwan Hong, Dohyeon Kim and 10 more34Upvotes05 · Oct 19 SolarRenderer: Few-Step Generative Reference Rendering
Guian Fang, Shengju Qian, Dongyue Lu and 6 more33Upvotes06 · Oct 17 VLA-Rolling: Fewer Denoising Steps, Better Control via Adaptive Action Reuse
Sicheng He, Yi Pan, Qiuting Yu and 10 more25Upvotes07 · Oct 18 SWIFT: Self-guided Weak-to-strong dIFfusion models via Target extrapolation
Yanjin He, Cuifeng Shen, Wanzhou Lei and 5 more23Upvotes08 · Oct 13 Correction Training for Diffusion Models
Donghoon Ahn, Runqian Wang, Alexei A. Efros and 2 more21Upvotes09 · Oct 18 Ropedia W0: Scaling Loco-Manipulation World Models across Embodiments with Human Experience
Tianqi Liu, Hanfei Zhao, Qifeng Liang and 12 more16Upvotes10 · Oct 19 MMEnterprise-Bench: Evaluating Enterprise Agents over Evolving Multimodal Records
Seohyun Lee, Jongha Kim, Dohwan Ko and 4 more15Upvotes11 · Oct 18 PhysSkin++: Real-Time and Generalizable Physics-Based Animation via Self-Supervised Neural Skinning
Yuanhang Lei, Baofei Liu, Xingxuan Li and 9 more14Upvotes12 · Oct 17 CoEvo-RSI: When Harnesses Evolve, Which Models Should Follow?
Jiaqi Su, Guibin Zhang, Jie-Jing Shao and 5 more14Upvotes13 · Oct 18 Breaking Diffusion: Parallel Reasoning with Draft Refinement
Jaesang Yu, Seoyeon Byun, Yun Wang and 2 more11Upvotes14 · Oct 14 ACEdit: Stable Multi-Turn Image Editing via Asymmetric Conditioning
Sara Dorfman, Nir Goren, Gal Barak and 2 more11Upvotes15 · Oct 18 From Short Clips to Real-Time Streams: Identity-Aware Supervision and Context-Efficient Generation for Video Face Swapping
Zekai Luo, Yuwei Liang, Ruiqi Ma and 8 more10Upvotes16 · Oct 17 StopLoss: Teaching Agents to Predict Failure and Stop Early
Jiarong Liang, Xueguang Ma, Dongfu Jiang and 3 more8Upvotes17 · Oct 16 EdgeKernelBench: Unified LLM-Driven Kernel Generation for Edge Backends
Yuhua Zheng, Xueyi Chen, Xinze Zou and 3 more8Upvotes18 · Oct 16 Progress-Aware Distillation for Mitigating Stagnation in Small Language Model Agents
Yuanpu Cao, Saket Sathe, Hanyu Wang and 3 more8Upvotes19 · Oct 19 S-Agent 2.0: Spatial Reasoning with a General Coding Agent
Rui Gong, Ruoyu Wang, Yalun Dai and 9 more7Upvotes20 · Oct 17 Painting Change Map as guidance for generating painting processes
Markus Pobitzer, Chang Liu, Niccolò Biondi and 1 more5Upvotes