The Research Desk.

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

Last Brew Time: May 29, 2026, 7:35 AM PT

X.com Research Buzz

StoryScope: Investigating idiosyncrasies in AI fiction
X.com
4019

StoryScope: Investigating idiosyncrasies in AI fiction

Jenna Russell, Rishanth Rajendhran, Chau Minh Pham, Mohit Iyyer, John Wieting

Computer Vision
LocateAnything: Fast and High-Quality Vision-Language Grounding with Parallel Box Decoding
X.com
1940

LocateAnything: Fast and High-Quality Vision-Language Grounding with Parallel Box Decoding

NVIDIA

AlphaXiv Trending

NLP
Do Language Models Need Sleep? Offline Recurrence for Improved Online Inference
AlphaXiv
137

Do Language Models Need Sleep? Offline Recurrence for Improved Online Inference

Sangyun Lee, Sean McLeish, Tom Goldstein

Carnegie Mellon University, University of Maryland

Reinforcement Learning
SkillOpt: Executive Strategy for Self-Evolving Agent Skills
AlphaXiv
127

SkillOpt: Executive Strategy for Self-Evolving Agent Skills

Yifan Yang, Ziyang Gong, Weiquan Huang

Microsoft, Shanghai Jiao Tong University, Tongji University, Fudan University

When Does LeJEPA Learn a World Model?
AlphaXiv
72

When Does LeJEPA Learn a World Model?

David Klindt, Yann LeCun, Randall Balestriero

Cold Spring Harbor Laboratory, New York University, Brown University

The MiniMax-M2 Series: Mini Activations Unleashing Max Real-World Intelligence
AlphaXiv
60

The MiniMax-M2 Series: Mini Activations Unleashing Max Real-World Intelligence

MiniMax, Aili Chen, Aonian Li

Retrieval
Gemini Embedding 2: A Native Multimodal Embedding Model from Gemini
AlphaXiv
52

Gemini Embedding 2: A Native Multimodal Embedding Model from Gemini

Madhuri Shanbhogue, Zhe Li, Shanfeng Zhang

Reinforcement Learning
MUSE-Autoskill: Self-Evolving Agents via Skill Creation, Memory, Management, and Evaluation
AlphaXiv
47

MUSE-Autoskill: Self-Evolving Agents via Skill Creation, Memory, Management, and Evaluation

Huawei Lin, Peng Li, Jie Song

ByteDance Inc, Rochester Institute of Technology, Huawei Lin

HuggingFace Daily Papers

Computer Vision
EarlyTom: Early Token Compression Completes Fast Video Understanding
HuggingFace
22

EarlyTom: Early Token Compression Completes Fast Video Understanding

Hesong Wang, Xin Jin, Lu Lu, Chenhaowen Li, Jian Chen

Retrieval
Xetrieval: Mechanistically Explaining Dense Retrieval
HuggingFace
14

Xetrieval: Mechanistically Explaining Dense Retrieval

Zhixin Cai, Jun Bai, Yang Liu, Jiaqi Li, Yichi Zhang

Beihang University

Computer Vision
Multi-view Consistent 3D Gaussian Head Avatars 'without' Multi-view Generation
HuggingFace
1

Multi-view Consistent 3D Gaussian Head Avatars 'without' Multi-view Generation

Aviral Chharia, Fernando De la Torre

Carnegie Mellon University

Parsa Mz
REPOT: Recoverable Program-of-Thought via Checkpoint Repair
HuggingFace
1

REPOT: Recoverable Program-of-Thought via Checkpoint Repair

Parsa Mazaheri

Machine Learning
CoHyDE: Iterative Co-Training of LLM Rewriter & Dense Encoder for Tool Retrieval
HuggingFace
1

CoHyDE: Iterative Co-Training of LLM Rewriter & Dense Encoder for Tool Retrieval

Vaishali Senthil, Ashutosh Hathidara, Sebastian Schreiber

SAP

Computer Vision
Uniform Diffusion Models Revisited: Leave-One-Out Denoiser and Absorbing State Reformulation
HuggingFace
1

Uniform Diffusion Models Revisited: Leave-One-Out Denoiser and Absorbing State Reformulation

Samson Gourevitch, Yazid Janati, Dario Shariatian, Umut Simsekli, Eric Moulines