The Research Desk.

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

Last Updated: Apr 25, 2026, 9:24 AM PT

X.com Research Buzz

Agents of Chaos
X.com
3466

Agents of Chaos

Natalie Shapira, Chris Wendler, Avery Yen +35 more

#reinforcement-learning
Recursive Language Models
X.com
2450

Recursive Language Models

Alex L. Zhang, Tim Kraska, Omar Khattab

#nlp#alexzhang13

AlphaXiv Trending

Agent-World: Scaling Real-World Environment Synthesis for Evolving General Agent Intelligence
AlphaXiv
160

Agent-World: Scaling Real-World Environment Synthesis for Evolving General Agent Intelligence

Guanting Dong, Junting Lu, Junjie Huang

#reinforcement-learning#alphaxiv
Image Generators are Generalist Vision Learners
AlphaXiv
135

Image Generators are Generalist Vision Learners

Valentin Gabeur, Shangbang Long, Songyou Peng

#computer-vision#alphaxiv
Neural Garbage Collection: Learning to Forget while Learning to Reason
AlphaXiv
70

Neural Garbage Collection: Learning to Forget while Learning to Reason

Michael Y. Li, Jubayer Ibn Hamid, Emily B. Fox

#alphaxiv
DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence
AlphaXiv
68

DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence

DeepSeek-AI

#efficiency#alphaxiv
Scaling Self-Play with Self-Guidance
AlphaXiv
42

Scaling Self-Play with Self-Guidance

Luke Bailey, Kaiyue Wen, Kefan Dong

#alphaxiv
LLaDA2.0-Uni: Unifying Multimodal Understanding and Generation with Diffusion Large Language Model
AlphaXiv
40

LLaDA2.0-Uni: Unifying Multimodal Understanding and Generation with Diffusion Large Language Model

Inclusion AI, Tiwei Bie, Haoxing Chen

#nlp#computer-vision#multimodal#alphaxiv

HuggingFace Daily Papers

LLaTiSA: Towards Difficulty-Stratified Time Series Reasoning from Visual Perception to Semantics
HuggingFace
79

LLaTiSA: Towards Difficulty-Stratified Time Series Reasoning from Visual Perception to Semantics

Yueyang Ding, HaoPeng Zhang, Rui Dai +2 more

#computer-vision#reasoning#RainingNovember
Vista4D: Video Reshooting with 4D Point Clouds
HuggingFace
7

Vista4D: Video Reshooting with 4D Point Clouds

Kuan Heng Lin, Zhizheng Liu, Pablo Salamanca +2 more

#computer-vision#Eyeline-Labs
Temporally Extended Mixture-of-Experts Models
HuggingFace
3

Temporally Extended Mixture-of-Experts Models

Zeyu Shen, Peter Henderson

#princeton-polaris-lab
Coevolving Representations in Joint Image-Feature Diffusion
HuggingFace
2

Coevolving Representations in Joint Image-Feature Diffusion

Theodoros Kouzelis, Spyros Gidaris, Nikos Komodakis

#computer-vision#zelaki
Encoder-Free Human Motion Understanding via Structured Motion Descriptions
HuggingFace
1

Encoder-Free Human Motion Understanding via Structured Motion Descriptions

Yao Zhang, Zhuchenyang Liu, Thomas Ploetz +1 more

#yaozhang182
3D-VCD: Hallucination Mitigation in 3D-LLM Embodied Agents through Visual Contrastive Decoding
HuggingFace
0

3D-VCD: Hallucination Mitigation in 3D-LLM Embodied Agents through Visual Contrastive Decoding

Makanjuola Ogunleye, Eman Abdelrahman, Ismini Lourentzou

#nlp#computer-vision#reinforcement-learning