The Research Desk.

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

Last Brew Time: May 8, 2026, 9:34 AM PT

X.com Research Buzz

NLP
Ads in AI Chatbots? An Analysis of How Large Language Models Navigate Conflicts of Interest
X.com
24561

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

NLP
Who's in Charge? Disempowerment Patterns in Real-World LLM Usage
X.com
4752

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

Mrinank Sharma, Miles McCain, Raymond Douglas, David Duvenaud

Reinforcement Learning
Agents of Chaos
X.com
4117

Agents of Chaos

Natalie Shapira, Chris Wendler, Avery Yen, Gabriele Sarti, Koyena Pal, Olivia Floody, Adam Belfki, Alex Loftus, Aditya Ratan Jannali, Nikhil Prakash, Jasmine Cui, Giordano Rogers, Jannik Brinkmann, Can Rager, Amir Zur, Michael Ripa, Aruna Sankaranarayanan, David Atkinson, Rohit Gandikota, Jaden Fiotto-Kaufman, EunJeong Hwang, Hadas Orgad, P Sam Sahil, Negev Taglicht, Tomer Shabtay, Atai Ambus, Nitay Alon, Shiri Oron, Ayelet Gordon-Tapiero, Yotam Kaplan, Vered Shwartz, Tamar Rott Shaham, Christoph Riedl, Reuth Mirsky, Maarten Sap, David Manheim, Tomer Ullman, David Bau

AlphaXiv Trending

Reasoning
MolmoAct2: Action Reasoning Models for Real-world Deployment
AlphaXiv
94

MolmoAct2: Action Reasoning Models for Real-world Deployment

Haoquan Fang, Jiafei Duan, Donovan Clay

Reinforcement Learning
On-Policy Distillation
AlphaXiv
84

On-Policy Distillation

Thinking Machines, Kevin Lu

Thinking Machines

Machine Learning
Model Spec Midtraining: Improving How Alignment Training Generalizes
AlphaXiv
74

Model Spec Midtraining: Improving How Alignment Training Generalizes

Chloe Li, Sara Price, Samuel Marks

Multimodal
Mamoda2.5: Enhancing Unified Multimodal Model with DiT-MoE
AlphaXiv
55

Mamoda2.5: Enhancing Unified Multimodal Model with DiT-MoE

ByteDance, Yangming Shi, Shixiang Zhu, Tao Shen

ByteDance

RLDX-1 Technical Report
AlphaXiv
53

RLDX-1 Technical Report

Dongyoung Kim, Huiwon Jang, Myungkyu Koo

NLP
ProgramBench: Can Language Models Rebuild Programs From Scratch?
AlphaXiv
52

ProgramBench: Can Language Models Rebuild Programs From Scratch?

John Yang, Kilian Lieret, Jeffrey Ma

HuggingFace Daily Papers

Reinforcement Learning
Beyond Semantic Similarity: Rethinking Retrieval for Agentic Search via Direct Corpus Interaction
HuggingFace
26

Beyond Semantic Similarity: Rethinking Retrieval for Agentic Search via Direct Corpus Interaction

Zhuofeng Li, Haoxiang Zhang, Cong Wei, Pan Lu, Ping Nie

Computer Vision
Audio-Visual Intelligence in Large Foundation Models
HuggingFace
13

Audio-Visual Intelligence in Large Foundation Models

You Qin, Kai Liu, Shengqiong Wu, Kai Wang, Shijian Deng

Reinforcement Learning
StraTA: Incentivizing Agentic Reinforcement Learning with Strategic Trajectory Abstraction
HuggingFace
10

StraTA: Incentivizing Agentic Reinforcement Learning with Strategic Trajectory Abstraction

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

Machine Learning
Prescriptive Scaling Laws for Data Constrained Training
HuggingFace
2

Prescriptive Scaling Laws for Data Constrained Training

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

Generative Quantum-inspired Kolmogorov-Arnold Eigensolver
HuggingFace
1

Generative Quantum-inspired Kolmogorov-Arnold Eigensolver

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

Multimodal
GeoStack: A Framework for Quasi-Abelian Knowledge Composition in VLMs
HuggingFace
1

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

Pranav Mantini, Shishir K. Shah