The Research Desk.

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

Last Updated: Apr 17, 2026, 11:37 AM PT

AlphaXiv Trending

Neural Computers
AlphaXiv
175

Neural Computers

Mingchen Zhuge, Changsheng Zhao, Haozhe Liu

#alphaxiv
In-Place Test-Time Training
AlphaXiv
171

In-Place Test-Time Training

Guhao Feng, Shengjie Luo, Kai Hua

#machine-learning#alphaxiv
PaperOrchestra: A Multi-Agent Framework for Automated AI Research Paper Writing
AlphaXiv
124

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

Yiwen Song, Tomas Pfister

#reinforcement-learning#retrieval#alphaxiv
SkillClaw: Let Skills Evolve Collectively with Agentic Evolver
AlphaXiv
100

SkillClaw: Let Skills Evolve Collectively with Agentic Evolver

Ziyu Ma, Shidong Yang, Yuxiang Ji

#reinforcement-learning#alphaxiv
Externalization in LLM Agents: A Unified Review of Memory, Skills, Protocols and Harness Engineering
AlphaXiv
46

Externalization in LLM Agents: A Unified Review of Memory, Skills, Protocols and Harness Engineering

Chenyu Zhou, Huacan Chai, Wenteng Chen

#nlp#reinforcement-learning#alphaxiv
Learning is Forgetting: LLM Training As Lossy Compression
AlphaXiv
41

Learning is Forgetting: LLM Training As Lossy Compression

Henry C. Conklin, Tom Hosking, Tan Yi-Chern

#machine-learning#nlp#efficiency#alphaxiv

HuggingFace Daily Papers

RadAgent: A tool-using AI agent for stepwise interpretation of chest computed tomography
HuggingFace
4

RadAgent: A tool-using AI agent for stepwise interpretation of chest computed tomography

Mélanie Roschewitz, Kenneth Styppa, Yitian Tao +2 more

#reinforcement-learning
Boosting Visual Instruction Tuning with Self-Supervised Guidance
HuggingFace
4

Boosting Visual Instruction Tuning with Self-Supervised Guidance

Sophia Sirko-Galouchenko, Monika Wysoczanska, Andrei Bursuc +2 more

#computer-vision#sirkosophia
Beyond Prompts: Unconditional 3D Inversion for Out-of-Distribution Shapes
HuggingFace
4

Beyond Prompts: Unconditional 3D Inversion for Out-of-Distribution Shapes

Victoria Yue Chen, Emery Pierson, Léopold Maillard +1 more

#nlp#computer-vision
Don't Retrieve, Navigate: Distilling Enterprise Knowledge into Navigable Agent Skills for QA and RAG
HuggingFace
3

Don't Retrieve, Navigate: Distilling Enterprise Knowledge into Navigable Agent Skills for QA and RAG

Yiqun Sun, Pengfei Wei, Lawrence B. Hsieh

#reinforcement-learning#retrieval#efficiency#dukesun99
An Optimal Transport-driven Approach for Cultivating Latent Space in Online Incremental Learning
HuggingFace
0

An Optimal Transport-driven Approach for Cultivating Latent Space in Online Incremental Learning

Quyen Tran, Hai Nguyen, Hoang Phan +2 more

Three-Phase Transformer
HuggingFace
0

Three-Phase Transformer

Mohammad R. Abu Ayyash

#nlp#achelousace