The Research Desk.

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

Last Brew Time: Aug 1, 2026, 10:41 AM PT

X.com Research Buzz

NLP
LLMs can't jump
X.com
5819

LLMs can't jump

Tom Zahavy

Google DeepMind

SITUATIONAL AWARENESS: The Decade Ahead
X.com
3150

SITUATIONAL AWARENESS: The Decade Ahead

Leopold Aschenbrenner

AlphaXiv Trending

Kimi K3: Open Frontier Intelligence
AlphaXiv
543

Kimi K3: Open Frontier Intelligence

Kimi Team, Tongtong Bai, Yifan Bai

Pangram 4 Technical Report
AlphaXiv
55

Pangram 4 Technical Report

Ben Glickenhaus, Katherine Thai, Jenna Russell

Reinforcement Learning
Weak-to-Strong On-Policy Distillation
AlphaXiv
55

Weak-to-Strong On-Policy Distillation

Fangxu Yu, Zinan Lin, Xiaodong Liu

University of Maryland, College Park, Microsoft Research

Computer Vision
TurboVLA: Real-Time Vision-Language-Action Model at 32 Hz on an RTX 4090 with <1 GB VRAM
AlphaXiv
50

TurboVLA: Real-Time Vision-Language-Action Model at 32 Hz on an RTX 4090 with <1 GB VRAM

Hengyi Xie, Chenfei Yao, Xianjin Wu

Huazhong University of Science and Technology, Huawei Technologies Co. Ltd, China

Metis: Memory Foundation Model
AlphaXiv
43

Metis: Memory Foundation Model

Zeyu Zhang, Ziliang Guo, Yihang Sun

Renmin University of China, National University of Singapore, Shanghai Jiao Tong University, Tongji University, Metis: Memory Foundation Model

Reinforcement Learning
Can AI agents conduct open-ended AI research? Early evidence from two case studies
AlphaXiv
29

Can AI agents conduct open-ended AI research? Early evidence from two case studies

Peter Kirgis, Sayash Kapoor, Andrew Schwartz

HuggingFace Daily Papers

Computer Vision
See2Think: Do Multimodal Models Really Use Intermediate Visual States?
HuggingFace
22

See2Think: Do Multimodal Models Really Use Intermediate Visual States?

Siyu Yan, Zhuoran Yan, Haiying Xu, Panhao Zhou, Jingyu Chen

Machine Learning
β-OPSD: Deriving with Policy Optimization, Training with Self-Distillation
HuggingFace
17

β-OPSD: Deriving with Policy Optimization, Training with Self-Distillation

Jiawei Xu, Minghui Liu, Juzheng Zhang, Tom Goldstein, Furong Huang

Furong Huang's Lab at UMD

NLP
Σ-Mem: An Online Reliability Memory for LLM-based Multi-Agent Systems
HuggingFace
12

Σ-Mem: An Online Reliability Memory for LLM-based Multi-Agent Systems

Peilin Feng, Suorong Yang, Soujanya Poria

Nanyang Technological University

NLP
OmniScope: Modality-Decoupled Token Compression for Omnimodal Large Language Models
HuggingFace
3

OmniScope: Modality-Decoupled Token Compression for Omnimodal Large Language Models

Jinsen Su, Yongdong Luo, Yuexiao Ma, Yibo Hu, Meiguang Jin

Beyond Geometric Complementarity: Coherent Overlap in Sparse Mixture-of-Experts Routing
HuggingFace
2

Beyond Geometric Complementarity: Coherent Overlap in Sparse Mixture-of-Experts Routing

Huiyuan Tian, Bonan Xu, Shijian Li

Efficiency
Fairness Pruning: Locating Demographic Bias in GLU-MLP Layers via Differential Activations
HuggingFace
2

Fairness Pruning: Locating Demographic Bias in GLU-MLP Layers via Differential Activations

Pere Martra, Eugenio Martínez Cámara, Alfonso Ureña López