The Research Desk.

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

Last Brew Time: May 12, 2026, 7:25 AM PT

X.com Research Buzz

NLP
Ads in AI Chatbots? An Analysis of How Large Language Models Navigate Conflicts of Interest
X.com
34124

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

Safety Alignment
Marked Pedagogies: Examining Linguistic Biases in Personalized Automated Writing Feedback
X.com
3585

Marked Pedagogies: Examining Linguistic Biases in Personalized Automated Writing Feedback

Mei Tan, Lena Phalen, Dorottya Demszky

Stanford University, Stanford Graduate School of Education

Attention Is All You Need
X.com
1501

Attention Is All You Need

Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Łukasz Kaiser, Illia Polosukhin

Google Brain, Google Research, University of Toronto

AlphaXiv Trending

NLP
Continuous Latent Diffusion Language Model
AlphaXiv
158

Continuous Latent Diffusion Language Model

Hongcan Guo, Qinyu Zhao, Yian Zhao

Reinforcement Learning
SkillOS: Learning Skill Curation for Self-Evolving Agents
AlphaXiv
111

SkillOS: Learning Skill Curation for Self-Evolving Agents

Siru Ouyang, Jun Yan, Yanfei Chen

Robotics
Reconstruction or Semantics? What Makes a Latent Space Useful for Robotic World Models
AlphaXiv
74

Reconstruction or Semantics? What Makes a Latent Space Useful for Robotic World Models

Nilaksh, Saurav Jha, Artem Zholus

Reinforcement Learning
Skill1: Unified Evolution of Skill-Augmented Agents via Reinforcement Learning
AlphaXiv
60

Skill1: Unified Evolution of Skill-Augmented Agents via Reinforcement Learning

Yaorui Shi, Yuxin Chen, Zhengxi Lu

Reinforcement Learning
Rubric-based On-policy Distillation
AlphaXiv
53

Rubric-based On-policy Distillation

Junfeng Fang, Zhepei Hong, Mao Zheng

Machine Learning
Demystifying Manifold Constraints in LLM Pre-training
AlphaXiv
51

Demystifying Manifold Constraints in LLM Pre-training

Kang An, Jiaxiang Li, Donald Goldfarb

HuggingFace Daily Papers

Recursal
Key-Value Means
HuggingFace
10

Key-Value Means

Daniel Goldstein, Eugene Cheah

NLP
Prompt-Activation Duality: Improving Activation Steering via Attention-Level Interventions
HuggingFace
4

Prompt-Activation Duality: Improving Activation Steering via Attention-Level Interventions

Diancheng Kang, Zheyuan Liu, Ningshan Ma, Yue Huang, Zhaoxuan Tan

University of Notre Dame

ELF: Embedded Language Flows
HuggingFace
2

ELF: Embedded Language Flows

Keya Hu, Linlu Qiu, Yiyang Lu, Hanhong Zhao, Tianhong Li

Queryable LoRA: Instruction-Regularized Routing Over Shared Low-Rank Update Atoms
HuggingFace
1

Queryable LoRA: Instruction-Regularized Routing Over Shared Low-Rank Update Atoms

Omatharv Bharat Vaidya, Connor T. Jerzak, Nhat Ho, Chandrajit Bajaj

Jerzak Labs

Reinforcement Learning
Safe, or Simply Incapable? Rethinking Safety Evaluation for Phone-Use Agents
HuggingFace
0

Safe, or Simply Incapable? Rethinking Safety Evaluation for Phone-Use Agents

Zhengyang Tang, Yi Zhang, Chenxin Li, Xin Lai, Pengyuan Lyu

A Closed-Form Upper Bound for Admissible Learning-Rate Steps in Belief-Space Dynamics
HuggingFace
0

A Closed-Form Upper Bound for Admissible Learning-Rate Steps in Belief-Space Dynamics

Zixi Li, Youzhen Li