The Research Desk.

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

Last Brew Time: Oct 31, 2026, 11:46 AM PT

AlphaXiv Trending

Proving and Improving the Platonic Representation Hypothesis with JEPAs
AlphaXiv
53

Proving and Improving the Platonic Representation Hypothesis with JEPAs

Views

Affiliation: Brown University, Affiliation: New York University, Brown University, New York University

Machine Learning
Training Foundation Models with a Single Algorithm
AlphaXiv
52

Training Foundation Models with a Single Algorithm

Views

Training Foundation Models with a Single Algorithm, Carnegie Mellon University, Johns Hopkins University

Machine Learning
Training language models in simulation for psychiatric intake
AlphaXiv
33

Training language models in simulation for psychiatric intake

Views

Affiliation: Google DeepMind, Affiliation: Google Research, Affiliation: Google for Health, Affiliation: Stanford University, Affiliation: University of California, Los Angeles

Cross-Controller Transfer via In-Context Behavior Adaptation
AlphaXiv
22

Cross-Controller Transfer via In-Context Behavior Adaptation

Views

Affiliation: Department of Computer Science Stanford University Stanford, CA, USA, Department of Computer Science, Stanford University

Computer Vision
Probing Spatial State Representations in Visual Foundation Models
AlphaXiv
20

Probing Spatial State Representations in Visual Foundation Models

Views

New York University, Nanyang Technological University, The Hong Kong University of Science and Technology, The Chinese University of Hong Kong, Keywords]visual foundation models, spatial state

Robotics
Learning to Assist: Collaborative VLAs for Implicit Human-Robot Collaboration
AlphaXiv
14

Learning to Assist: Collaborative VLAs for Implicit Human-Robot Collaboration

Views

Affiliation: University of Wisconsin–Madison, University of Wisconsin–Madison, Massachusetts Institute of Technology

HuggingFace Daily Papers

Machine Learning
Training Foundation Models with a Single Algorithm
HuggingFace
8

Training Foundation Models with a Single Algorithm

Yuda Song, Alvin Zhang, Fahim Tajwar, Daman Arora, Jeff Schneider

Carnegie Mellon University

NLP
Broken on Arrival: Non-Functional Quantized LLM Artifacts in Public Model Registries and How to Catch Them
HuggingFace
5

Broken on Arrival: Non-Functional Quantized LLM Artifacts in Public Model Registries and How to Catch Them

Aditi Patodiya

Reinforcement Learning
Matched Capabilities, Different Behaviors: A Controlled Study of MCP and CLI Interfaces for Language Agents
HuggingFace
4

Matched Capabilities, Different Behaviors: A Controlled Study of MCP and CLI Interfaces for Language Agents

Zhenning Shi, Liang Pang, Yongqi Li

ModalityDance

NLP
EPSBench: Benchmarking LLM Agents for Earnings Forecasting
HuggingFace
2

EPSBench: Benchmarking LLM Agents for Earnings Forecasting

Yanbin Yin, Chuyu Xu, Liqin Ye, Jing Peng, Chao Zhang

Georgia Institute of Technology

Reinforcement Learning
Weaken to Strengthen: Weakening-Induced On-Policy Self-Distillation for Large Reasoning Models
HuggingFace
2

Weaken to Strengthen: Weakening-Induced On-Policy Self-Distillation for Large Reasoning Models

Yecheng Wu, Song Han, Han Cai

Jet-AI

Computer Vision
Unlocking Any-Order Generation in Pretrained Autoregressive Image Models
HuggingFace
2

Unlocking Any-Order Generation in Pretrained Autoregressive Image Models

Rishav Pramanik, Marco Pedersoli, Zhaozheng Yin