The Research Desk.

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

Last Brew Time: May 10, 2026, 7:24 AM PT

X.com Research Buzz

NLP
Ads in AI Chatbots? An Analysis of How Large Language Models Navigate Conflicts of Interest
X.com
33953

Ads in AI Chatbots? An Analysis of How Large Language Models Navigate Conflicts of Interest

Addison J. Wu, Ryan Liu, Shuyue Stella Li, Yulia Tsvetkov, Thomas L. Griffiths

Princeton University

NLP
Who's in Charge? Disempowerment Patterns in Real-World LLM Usage
X.com
4749

Who's in Charge? Disempowerment Patterns in Real-World LLM Usage

Mrinank Sharma, Miles McCain, Raymond Douglas, David Duvenaud

Anthropic

AlphaXiv Trending

Reasoning
MolmoAct2: Action Reasoning Models for Real-world Deployment
AlphaXiv
127

MolmoAct2: Action Reasoning Models for Real-world Deployment

Haoquan Fang, Jiafei Duan, Donovan Clay

University of Washington, National University of Singapore

Reinforcement Learning
On-Policy Distillation
AlphaXiv
127

On-Policy Distillation

Thinking Machines, Kevin Lu

Thinking Machines

NLP
ProgramBench: Can Language Models Rebuild Programs From Scratch?
AlphaXiv
78

ProgramBench: Can Language Models Rebuild Programs From Scratch?

John Yang, Kilian Lieret, Jeffrey Ma

RLDX-1 Technical Report
AlphaXiv
76

RLDX-1 Technical Report

Dongyoung Kim, Huiwon Jang, Myungkyu Koo

NLP
Continuous Latent Diffusion Language Model
AlphaXiv
63

Continuous Latent Diffusion Language Model

Hongcan Guo, Qinyu Zhao, Yian Zhao

Machine Learning
Manifold Steering Reveals the Shared Geometry of Neural Network Representation and Behavior
AlphaXiv
48

Manifold Steering Reveals the Shared Geometry of Neural Network Representation and Behavior

Daniel Wurgaft, Can Rager, Matthew Kowal

HuggingFace Daily Papers

Reinforcement Learning
StraTA: Incentivizing Agentic Reinforcement Learning with Strategic Trajectory Abstraction
HuggingFace
17

StraTA: Incentivizing Agentic Reinforcement Learning with Strategic Trajectory Abstraction

Xiangyuan Xue, Yifan Zhou, Zidong Wang, Shengji Tang, Philip Torr

Machine Learning
EMO: Pretraining Mixture of Experts for Emergent Modularity
HuggingFace
6

EMO: Pretraining Mixture of Experts for Emergent Modularity

Ryan Wang, Akshita Bhagia, Sewon Min

Ai2

Ilya16
PianoCoRe: Combined and Refined Piano MIDI Dataset
HuggingFace
4

PianoCoRe: Combined and Refined Piano MIDI Dataset

Ilya Borovik

SyMuPe

Machine Learning
Prescriptive Scaling Laws for Data Constrained Training
HuggingFace
4

Prescriptive Scaling Laws for Data Constrained Training

Justin Lovelace, Christian Belardi, Srivatsa Kundurthy, Shriya Sudhakar, Kilian Q. Weinberger

Multimodal
GeoStack: A Framework for Quasi-Abelian Knowledge Composition in VLMs
HuggingFace
2

GeoStack: A Framework for Quasi-Abelian Knowledge Composition in VLMs

Pranav Mantini, Shishir K. Shah

University of Houston

Generative Quantum-inspired Kolmogorov-Arnold Eigensolver
HuggingFace
2

Generative Quantum-inspired Kolmogorov-Arnold Eigensolver

Yu-Cheng Lin, Yu-Chao Hsu, I-Shan Tsai, Chun-Hua Lin, Kuo-Chung Peng