The Research Desk.

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

Last Brew Time: May 18, 2026, 7:23 AM PT

AlphaXiv Trending

ELF: Embedded Language Flows
AlphaXiv
267

ELF: Embedded Language Flows

Yiyang Lu, Keya Hu, Linlu Qiu

MIT

Robotics
World Action Models: The Next Frontier in Embodied AI
AlphaXiv
136

World Action Models: The Next Frontier in Embodied AI

Siyin Wang, Junhao Shi, Zhaoyang Fu

VGGT- Ω Ω
AlphaXiv
105

VGGT- Ω Ω

Jianyuan Wang, Minghao Chen, Shangzhan Zhang

Reinforcement Learning
Self-Distilled Agentic Reinforcement Learning
AlphaXiv
99

Self-Distilled Agentic Reinforcement Learning

Zhengxi Lu, Zhiyuan Yao, Zhuowen Han

Zhejiang University, Tsinghua University

NLP
𝛿 δ-mem: Efficient Online Memory for Large Language Models
AlphaXiv
98

𝛿 δ-mem: Efficient Online Memory for Large Language Models

Jingdi Lei, Di Zhang, Junxian Li

NLP
SANA-WM: Efficient Minute-Scale World Modeling with Hybrid Linear Diffusion Transformer
AlphaXiv
89

SANA-WM: Efficient Minute-Scale World Modeling with Hybrid Linear Diffusion Transformer

Haoyi Zhu, Haozhe Liu, Yuyang Zhao

NVIDIA

HuggingFace Daily Papers

Computer Vision
CM-EVS: Sparse Panoramic RGB-D-Pose Data for Complete Scene Coverage
HuggingFace
8

CM-EVS: Sparse Panoramic RGB-D-Pose Data for Complete Scene Coverage

Jiale Liu, Jungang Li, Jieming Yu, Xinglin Yu, Zihao Dongfang

Fpv Labs
MobileEgo Anywhere: Open Infrastructure for long horizon egocentric data on commodity hardware
HuggingFace
5

MobileEgo Anywhere: Open Infrastructure for long horizon egocentric data on commodity hardware

Senthil Palanisamy, Abhishek Anand, Satpal Singh Rathor, Pratyush Patnaik, Shubhanshu Khatana

FPV Labs

Machine Learning
Sparse Autoencoders enable Robust and Interpretable Fine-tuning of CLIP models
HuggingFace
4

Sparse Autoencoders enable Robust and Interpretable Fine-tuning of CLIP models

Fabian Morelli, Arnas Uselis, Ankit Sonthalia, Seong Joon Oh

NLP
Steered LLM Activations are Non-Surjective
HuggingFace
2

Steered LLM Activations are Non-Surjective

Aayush Mishra, Daniel Khashabi, Anqi Liu

Johns Hopkins University

Computer Vision
Efficient Image Synthesis with Sphere Latent Encoder
HuggingFace
2

Efficient Image Synthesis with Sphere Latent Encoder

Tung Do, Thuan Hoang Nguyen, Hao Li

Mohamed Bin Zayed University of Artificial Intelligence

Blaz R
ChangeFlow -- Latent Rectified Flow for Change Detection in Remote Sensing
HuggingFace
2

ChangeFlow -- Latent Rectified Flow for Change Detection in Remote Sensing

Blaž Rolih, Matic Fučka, Filip Wolf, Luka Čehovin Zajc