The Research Desk.

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

Last Brew Time: Apr 13, 2026, 12:18 PM PT

AlphaXiv Trending

Machine Learning
In-Place Test-Time Training
AlphaXiv
154

In-Place Test-Time Training

Guhao Feng, Shengjie Luo, Kai Hua

Neural Computers
AlphaXiv
150

Neural Computers

Mingchen Zhuge, Changsheng Zhao, Haozhe Liu

Reinforcement Learning
PaperOrchestra: A Multi-Agent Framework for Automated AI Research Paper Writing
AlphaXiv
102

PaperOrchestra: A Multi-Agent Framework for Automated AI Research Paper Writing

Yiwen Song, Tomas Pfister

Reinforcement Learning
SkillClaw: Let Skills Evolve Collectively with Agentic Evolver
AlphaXiv
65

SkillClaw: Let Skills Evolve Collectively with Agentic Evolver

Ziyu Ma, Shidong Yang, Yuxiang Ji

Reinforcement Learning
HY-Embodied-0.5: Embodied Foundation Models for Real-World Agents
AlphaXiv
33

HY-Embodied-0.5: Embodied Foundation Models for Real-World Agents

Tencent Robotics X, HY Vision Team, Xumin Yu

NLP
Your Agent Is Mine: Measuring Malicious Intermediary Attacks on the LLM Supply Chain
AlphaXiv
33

Your Agent Is Mine: Measuring Malicious Intermediary Attacks on the LLM Supply Chain

Hanzhi Liu, Chaofan Shou, Hongbo Wen

HuggingFace Daily Papers

NLP
Multi-User Large Language Model Agents
HuggingFace
9

Multi-User Large Language Model Agents

Shu Yang, Shenzhe Zhu, Hao Zhu, José Ramón Enríquez, Di Wang

Computer Vision
Envisioning the Future, One Step at a Time
HuggingFace
3

Envisioning the Future, One Step at a Time

Stefan Andreas Baumann, Jannik Wiese, Tommaso Martorella, Mahdi M. Kalayeh, Björn Ommer

Reasoning
Robust Reasoning Benchmark
HuggingFace
1

Robust Reasoning Benchmark

Pavel Golikov, Evgenii Opryshko, Gennady Pekhimenko, Mark C. Jeffrey

Reinforcement Learning
Process Reward Agents for Steering Knowledge-Intensive Reasoning
HuggingFace
1

Process Reward Agents for Steering Knowledge-Intensive Reasoning

Jiwoong Sohn, Tomasz Sternal, Kenneth Styppa, Torsten Hoefler, Michael Moor

Efficiency
Cactus: Accelerating Auto-Regressive Decoding with Constrained Acceptance Speculative Sampling
HuggingFace
0

Cactus: Accelerating Auto-Regressive Decoding with Constrained Acceptance Speculative Sampling

Yongchang Hao, Lili Mou

NLP
EquiformerV3: Scaling Efficient, Expressive, and General SE(3)-Equivariant Graph Attention Transformers
HuggingFace
0

EquiformerV3: Scaling Efficient, Expressive, and General SE(3)-Equivariant Graph Attention Transformers

Yi-Lun Liao, Alexander J. Hoffman, Sabrina C. Shen, Alexandre Duval, Sam Walton Norwood