The Research Desk.

The most upvoted and starred AI research crossing the community today.

Last Updated: Mar 29, 2026, 5:42 AM PT

X.com Research Buzz

A wireless subdural-contained brain–computer interface with 65,536 electrodes and 1,024 channels
X.com
3625

A wireless subdural-contained brain–computer interface with 65,536 electrodes and 1,024 channels

Konstantin Willeke, Denise Oswalt, Gabrielle J. Rodriguez +3 more

#klshepard

AlphaXiv Trending

Attention Residuals
AlphaXiv
531

Attention Residuals

Kimi Team, Guangyu Chen, Yu Zhang

#alphaxiv
AVO: Agentic Variation Operators for Autonomous Evolutionary Search
AlphaXiv
83

AVO: Agentic Variation Operators for Autonomous Evolutionary Search

Terry Chen, Zhifan Ye, Bing Xu

#reinforcement-learning#robotics#retrieval#alphaxiv
Why Does Self-Distillation (Sometimes) Degrade the Reasoning Capability of LLMs?
AlphaXiv
71

Why Does Self-Distillation (Sometimes) Degrade the Reasoning Capability of LLMs?

Jeonghye Kim, Xufang Luo, Minbeom Kim

#nlp#efficiency#reasoning#alphaxiv
Claudini: Autoresearch Discovers State-of-the-Art Adversarial Attack Algorithms for LLMs
AlphaXiv
38

Claudini: Autoresearch Discovers State-of-the-Art Adversarial Attack Algorithms for LLMs

Alexander Panfilov, Peter Romov, Igor Shilov

#nlp#retrieval#alphaxiv
UI-Voyager: A Self-Evolving GUI Agent Learning via Failed Experience
AlphaXiv
25

UI-Voyager: A Self-Evolving GUI Agent Learning via Failed Experience

Zichuan Lin, Feiyu Liu, Yijun Yang

#reinforcement-learning#alphaxiv
Intern-S1-Pro: Scientific Multimodal Foundation Model at Trillion Scale
AlphaXiv
24

Intern-S1-Pro: Scientific Multimodal Foundation Model at Trillion Scale

Yicheng Zou, Dongsheng Zhu, Lin Zhu

#multimodal#alphaxiv

HuggingFace Daily Papers

VFIG: Vectorizing Complex Figures in SVG with Vision-Language Models
HuggingFace
11

VFIG: Vectorizing Complex Figures in SVG with Vision-Language Models

Qijia He, Xunmei Liu, Hammaad Memon +2 more

#nlp#computer-vision#retrieval#RAIVNLab
AVO: Agentic Variation Operators for Autonomous Evolutionary Search
HuggingFace
5

AVO: Agentic Variation Operators for Autonomous Evolutionary Search

Terry Chen, Zhifan Ye, Bing Xu +2 more

#reinforcement-learning#robotics#retrieval
Pixel-level Scene Understanding in One Token: Visual States Need What-is-Where Composition
HuggingFace
2

Pixel-level Scene Understanding in One Token: Visual States Need What-is-Where Composition

Seokmin Lee, Yunghee Lee, Byeonghyun Pak +1 more

#computer-vision#SeokminLee-Chris
Can MLLMs Read Students' Minds? Unpacking Multimodal Error Analysis in Handwritten Math
HuggingFace
2

Can MLLMs Read Students' Minds? Unpacking Multimodal Error Analysis in Handwritten Math

Dingjie Song, Tianlong Xu, Yi-Fan Zhang +2 more

#nlp#multimodal#ai-for-edu
Reaching Beyond the Mode: RL for Distributional Reasoning in Language Models
HuggingFace
2

Reaching Beyond the Mode: RL for Distributional Reasoning in Language Models

Isha Puri, Mehul Damani, Idan Shenfeld +2 more

#nlp#reinforcement-learning#reasoning#ishapuri
WAFT-Stereo: Warping-Alone Field Transforms for Stereo Matching
HuggingFace
1

WAFT-Stereo: Warping-Alone Field Transforms for Stereo Matching

Yihan Wang, Jia Deng

#princeton-vl