The Research Desk.

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

Last Updated: Apr 4, 2026, 5:33 AM PT

X.com Research Buzz

Sycophantic Chatbots Cause Delusional Spiraling, Even in Ideal Bayesians
X.com
49973

Sycophantic Chatbots Cause Delusional Spiraling, Even in Ideal Bayesians

Kartik Chandra, Max Kleiman-Weiner, Jonathan Ragan-Kelley +1 more

From Labor to Attention: A Token-Economic Framework for the AI Era
X.com
23790

From Labor to Attention: A Token-Economic Framework for the AI Era

#cPenNetwork

AlphaXiv Trending

Meta-Harness: End-to-End Optimization of Model Harnesses
AlphaXiv
209

Meta-Harness: End-to-End Optimization of Model Harnesses

Yoonho Lee, Roshen Nair, Qizheng Zhang

#efficiency#alphaxiv
Think Anywhere in Code Generation
AlphaXiv
50

Think Anywhere in Code Generation

Xue Jiang, Tianyu Zhang, Ge Li

#reasoning#alphaxiv
Screening Is Enough
AlphaXiv
30

Screening Is Enough

Ken M. Nakanishi

#alphaxiv
SKILL0: In-Context Agentic Reinforcement Learning for Skill Internalization
AlphaXiv
25

SKILL0: In-Context Agentic Reinforcement Learning for Skill Internalization

Zhengxi Lu, Zhiyuan Yao, Jinyang Wu

#reinforcement-learning#alphaxiv
Understanding Transformers and Attention Mechanisms: An Introduction for Applied Mathematicians
AlphaXiv
22

Understanding Transformers and Attention Mechanisms: An Introduction for Applied Mathematicians

Michel Fabrice Serret

#nlp#alphaxiv
The Latent Space: Foundation, Evolution, Mechanism, Ability, and Outlook
AlphaXiv
19

The Latent Space: Foundation, Evolution, Mechanism, Ability, and Outlook

Xinlei Yu, Zhangquan Chen, Yongbo He

#alphaxiv

HuggingFace Daily Papers

CORAL: Towards Autonomous Multi-Agent Evolution for Open-Ended Discovery
HuggingFace
31

CORAL: Towards Autonomous Multi-Agent Evolution for Open-Ended Discovery

Ao Qu, Han Zheng, Zijian Zhou +2 more

#reinforcement-learning#robotics#Human-Agent-Society
Video Models Reason Early: Exploiting Plan Commitment for Maze Solving
HuggingFace
7

Video Models Reason Early: Exploiting Plan Commitment for Maze Solving

Kaleb Newman, Tyler Zhu, Olga Russakovsky

#computer-vision
Forecasting Supply Chain Disruptions with Foresight Learning
HuggingFace
4

Forecasting Supply Chain Disruptions with Foresight Learning

Benjamin Turtel, Paul Wilczewski, Kris Skotheim

Signals: Trajectory Sampling and Triage for Agentic Interactions
HuggingFace
1

Signals: Trajectory Sampling and Triage for Agentic Interactions

Shuguang Chen, Adil Hafeez, Salman Paracha

#reinforcement-learning#katanemo
LOME: Learning Human-Object Manipulation with Action-Conditioned Egocentric World Model
HuggingFace
0

LOME: Learning Human-Object Manipulation with Action-Conditioned Egocentric World Model

Quankai Gao, Jiawei Yang, Qiangeng Xu +2 more

#robotics#Zerg-Overmind
An Empirical Recipe for Universal Phone Recognition
HuggingFace
0

An Empirical Recipe for Universal Phone Recognition

Shikhar Bharadwaj, Chin-Jou Li, Kwanghee Choi +2 more

#changelinglab