The Research Desk.

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

Last Brew Time: Jun 16, 2026, 7:39 AM PT

X.com Research Buzz

AI models collapse when trained on recursively generated data
X.com
25270

AI models collapse when trained on recursively generated data

Ilia Shumailov, Zakhar Shumaylov, Yiren Zhao, Yarin Gal, Nicolas Papernot, Ross Anderson

University of Oxford, University of Cambridge, Imperial College London, University of Toronto

AlphaXiv Trending

From AGI to ASI
AlphaXiv
151

From AGI to ASI

Tim Genewein, Matija Franklin, Alexander Lerchner

Google DeepMind, University of Waterloo (work conducted while at Google DeepMind, Australian National University, University College London, Google DeepMind University of Waterloo (work conducted while at Google DeepMind

MiniMax Sparse Attention
AlphaXiv
120

MiniMax Sparse Attention

Xunhao Lai, Weiqi Xu, Yufeng Yang

Peking University, NVIDIA, Zhejiang University, Huazhong University of Science and Technology, Nanjing University

NLP
EvoArena: Tracking Memory Evolution for Robust LLM Agents in Dynamic Environments
AlphaXiv
50

EvoArena: Tracking Memory Evolution for Robust LLM Agents in Dynamic Environments

Jundong Xu, Qingchuan Li, Jiaying Wu

Equal ContributionWork Partially Done at Salesforce AI Research, National University of Singapore, Singapore Management University, University of Washington, University College London

AlphaXiv
47

Unsafe AI or Consolidated Power: AI’s False Dichotomy

Parth Asawa, Joseph E. Gonzalez

Computer Vision
Dense Supervision, Sparse Updates: On the Sparsity and Geometry of On-Policy Distillation
AlphaXiv
43

Dense Supervision, Sparse Updates: On the Sparsity and Geometry of On-Policy Distillation

Guo Yu, Wenlin Liu, Yulan Hu

School of Artificial Intelligence, Nanjing University, National Key Laboratory for Novel Software Technology, Nanjing University, Amap, Alibaba Group

HuggingFace Daily Papers

Reinforcement Learning
Ling and Ring 2.6 Technical Report: Efficient and Instant Agentic Intelligence at Trillion-Parameter Scale
HuggingFace
6

Ling and Ring 2.6 Technical Report: Efficient and Instant Agentic Intelligence at Trillion-Parameter Scale

Ang Li, Ben Liu, Bin Han, Bin Hu, Bin Jing

inclusionAI

Unstable Features, Reproducible Subspaces: Understanding Seed Dependence in Sparse Autoencoders
HuggingFace
5

Unstable Features, Reproducible Subspaces: Understanding Seed Dependence in Sparse Autoencoders

Gleb Gerasimov, Timofei Rusalev, Nikita Balagansky, Daniil Laptev, Vadim Kurochkin

T-Tech

Computer Vision
MVEB: Massive Video Embedding Benchmark
HuggingFace
2

MVEB: Massive Video Embedding Benchmark

Adnan El Assadi, Roman Solomatin, Isaac Chung, Chenghao Xiao, Deep Shah

Massive Text Embedding Benchmark

Computer Vision
EgoPhys: Learning Generalizable Physics Models of Deformable Objects from Egocentric Video
HuggingFace
1

EgoPhys: Learning Generalizable Physics Models of Deformable Objects from Egocentric Video

Hyunjin Kim, Ri-Zhao Qiu, Guangqi Jiang, Xiaolong Wang

University of California at San Diego

Robotics
LaWAM: Latent World Action Models for Efficient Dynamics-Aware Robot Policies
HuggingFace
1

LaWAM: Latent World Action Models for Efficient Dynamics-Aware Robot Policies

Jialei Chen, Kai Wang, Kang Chen, Shuaihang Chen, Feng Gao

RLinf

KevinyWu
Human Universal Grasping
HuggingFace
0

Human Universal Grasping

Kevin Yuanbo Wu, Tianxing Zhou, Isaac Tu, Billy Yan, Irmak Guzey

New York University