Pulse Energy Eu
X.com
6061
SlopShape: Identifying AI-Generated Commercial Web Content
Jochen Madler
Sitefire
The Research Desk.
The most upvoted and starred AI research crossing the community today.
Last Brew Time: Sep 30, 2026, 11:21 AM PT
X.com Research Buzz
X.com
5048
AI models collapse when trained on recursively generated data
I. Shumailov, et al.
University of Oxford, University of Cambridge
NLP
X.com
4588
Large-scale online deanonymization with LLMs
Simon Lermen, Daniel Paleka, Joshua Swanson, Michael Aerni, Nicholas Carlini, Florian Tramèr
MATS, ETH Zurich, Anthropic
AlphaXiv Trending
Reinforcement Learning
AlphaXiv
43
MatToolBench: Benchmarking Multimodal Agents in Real-World Materials Science Workflows
Reinforcement Learning
AlphaXiv
31
DexAgent: An Agentic Human2Sim2Robot Framework for Dexterous Manipulation with Self-Evolving Tool Library
Affiliation: Stanford University, Affiliation: Columbia University, Stanford University, Columbia University
Robotics
AlphaXiv
28
AD-E2E-JEPA: A Joint-Embedding Predictive Architecture For End-to-End Autonomous Driving
Affiliation: New York University, New York University
NLP
AlphaXiv
18
Context Language Models
Affiliation: University of Washington, Affiliation: Meta Superintelligence Labs, Affiliation: University of Washington Affiliation: Meta Superintelligence Labs, University of Washington, Meta Superintelligence Labs
Robotics
AlphaXiv
2
T 2 2 Mem: Learning Test-Time Memory for Robotics
Affiliation: Stanford University, Affiliation: NVIDIA, Affiliation: University of Michigan, Ann Arbor, Stanford University, NVIDIA
HuggingFace Daily Papers
Efficiency
HuggingFace
41
Periodic Weak Spots: Phase Sensitivity from Chunked KV-Cache Compression
Xingyu Zhu, Pu, Yi, Ziheng Cheng, Ang Lv
ByteDance Seed
NLP
HuggingFace
9
Scheduling Recursive Reasoning in Looped Transformers
Boyuan Wang, Chengyao Yu, Jiaxi Ren, Hongxin Wei, Bingyi Jing
Reinforcement Learning
HuggingFace
3
Can Agents Design Libraries for Agents?
Gabriel Orlanski, Alex L. Zhang, Avi Trost, Vincent Sunn Chen, Frederic Sala
University of Wisconsin - Madison
Reinforcement Learning
HuggingFace
2
Scaling Properties of Same-Family On-Policy Distillation
Yuntai Bao, Qinfeng Li, Guoqing Jiang, Liwei Chen, Zhiheng Qin
Zhejiang University
Computer Vision
HuggingFace
1
Org-Agent: Beyond Personal Assistants Towards Organizational Agents
Luyao Zhuang, Yujing Zhang, Zijin Hong, Yilin Xiao, Xiao Huang
The Hong Kong Polytechnic University
Joshua Ren
HuggingFace
1
Learning Dynamics of Continual Learning: A Unified View of Data Attribution, Forgetting, and Plasticity Loss
Yi Ren, Wenlong Deng, Guanzhe Hong, Clare Lyle, Yarin Gal