X.com
45471
Sakana Fugu
Sakana AI Labs
The Research Desk.
The most upvoted and starred AI research crossing the community today.
Last Brew Time: Jun 25, 2026, 7:39 AM PT
X.com Research Buzz
X.com
24509
Jalapeño
OpenAI, Broadcom
AlphaXiv Trending
Reinforcement Learning
AlphaXiv
166
Tmax: A simple recipe for terminal agents
Hamish Ivison, Junjie Oscar Yin, Rulin Shao
Reinforcement Learning
AlphaXiv
83
Qwen-AgentWorld: Language World Models for General Agents
Yuxin Zuo, Zikai Xiao, Li Sheng
AlphaXiv
77
Unlimited OCR Works
Youyang Yin, Huanhuan Liu, Qunyi Xie
NLP
AlphaXiv
49
Tapered Language Models
Universite de Montreal, Reza Bayat, Ali Behrouz, Aaron Courville
Cornell University
NLP
AlphaXiv
37
ParallelKernelBench: Can LLMs Write Fast Multi-GPU Kernels?
Willy Chan, Nathan Paek, Simon Guo
Stanford University, University of California, San Diego
Reinforcement Learning
AlphaXiv
33
Agent-as-a-Router: Agentic Model Routing for Coding Tasks
Pengfei Zhou, Zhiwei Tang, Yixing Ma
calc,positioning,shapes,arrows.meta,fit,backgrounds, National University of Singapore, DAMO Academy, Alibaba Group, Hupan Lab, University of California, Berkeley
HuggingFace Daily Papers
Computer Vision
HuggingFace
24
MVTrack4Gen: Multi-View Point Tracking as Geometric Supervision for 4D Video Generation
JoungBin Lee, Jaewoo Jung, Jongmin Lee, Tongmin Kim, Hyunsung Kim
KAIST AI
NLP
HuggingFace
5
ReNIO: Reweighting Negative Trajectory Importance for LLM On-Policy Distillation
Chen Lin, Kedi Chen, Wei Zhang
East China Normal University
Safety Alignment
HuggingFace
3
What Intermediate Layers Know: Detecting Jailbreaks from Entropy Dynamics
Sofiia Nikolenko, Michele Papucci, Mina Rezaei, Shireen Kudukkil Manchingal
NLP
HuggingFace
2
PrivacyAlign: Contextual Privacy Alignment for LLM Agents
Manveer Singh Tamber, Abhay Puri, Marc-Etienne Brunet, Perouz Taslakian, Jimmy Lin
Efficiency
HuggingFace
1
Distill Once, Adapt Life-Long: Exploring Dataset Distillation for Continual Test-Time Adaptation
Hyun-Kurl Jang, Jihun Kim, Hyeokjun Kweon, Kuk-Jin Yoon
NLP
HuggingFace
0
Constraint Tax in Open-Weight LLMs: An Empirical Study of Tool Calling Suppression Under Structured Output Constraints
Fangzheng Li, Aimin Zhang, Chen Lv