The Research Desk.

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

Last Brew Time: Jul 21, 2026, 10:41 AM PT

AlphaXiv Trending

NLP
AlphaXiv
174

Language model harnesses are compositional generalizers

Alex Zhang, Omar Khattab

Machine Learning
Understanding Reasoning from Pretraining to Post-Training
AlphaXiv
74

Understanding Reasoning from Pretraining to Post-Training

Jingyan Shen, Ang Li, Salman Rahman

New York University, University of California, Los Angeles, University of Illinois Urbana-Champaign, Columbia University

Loop the Loopies!
AlphaXiv
49

Loop the Loopies!

ZG, Zitian Gao, Yilong Chen, Yihao Xiao

Computer Vision
Exploration Matters for Escaping the Blur Trap in 3D Gaussian Splatting
AlphaXiv
16

Exploration Matters for Escaping the Blur Trap in 3D Gaussian Splatting

Chengbo Wang, Guozheng Ma, Jinhong Wu

Hunan University, Nanyang Technological University

Robotics
RynnBrain 1.1: Towards More Capable and Generalizable Embodied Foundation Model
AlphaXiv
11

RynnBrain 1.1: Towards More Capable and Generalizable Embodied Foundation Model

Kehan Li, Bohan Hou, Minghao Zhu

DAMO Academy, Alibaba Group, Hupan Lab, RynnBrain 1.1: Towards More Capable and Generalizable Embodied Foundation Model

HuggingFace Daily Papers

Robotics
Open-AoE: An Open Egocentric Manipulation Dataset and Toolchain for Embodied Learning
HuggingFace
23

Open-AoE: An Open Egocentric Manipulation Dataset and Toolchain for Embodied Learning

Zishuo Li, Bowen Yang, Changtao Miao, Kai Zhu, Hao Chen

inclusionAI

NLP
Do Language Models Dream of Binding Molecules? Benchmarking LLMs under Spatial Constraints
HuggingFace
11

Do Language Models Dream of Binding Molecules? Benchmarking LLMs under Spatial Constraints

Thomas MacDougall, Maksim Kuznetsov, Roman Schutski, Rim Shayakhmetov, Maxim Malkov

Insilico Medicine

Computer Vision
ReViV: Reconstructing the Viewer and the View in 4D from Monocular Egocentric Video
HuggingFace
2

ReViV: Reconstructing the Viewer and the View in 4D from Monocular Egocentric Video

Xiaozhong Lyu, Gen Li, Zhiyin Qian, Xucong Zhang, Marc Pollefeys

Computer Vision and Learning Group, ETH Zürich

NLP
Coercion and Deception in AI-to-AI Management: An Agentic Benchmark of Unprompted Escalation
HuggingFace
2

Coercion and Deception in AI-to-AI Management: An Agentic Benchmark of Unprompted Escalation

Jasmine Brazilek, Maheep Chaudhary, Zoe Lu, Miles Tidmarsh

NLP
Masked Diffusion Language Models are Strong and Steerable Text-Based World Models for Agentic RL
HuggingFace
1

Masked Diffusion Language Models are Strong and Steerable Text-Based World Models for Agentic RL

Darshan Deshpande

Patronus AI

Computer Vision
UI2App: Benchmarking Visual Interaction Inference in Executable Web Application Generation
HuggingFace
0

UI2App: Benchmarking Visual Interaction Inference in Executable Web Application Generation

Grace Man Chen, Litao Guo, Yifan Wu, Yiyu Chen, Yenchi Tseng