X.com
6522
Navier–Stokes lost in translation – Why Lean verification of AI autoformalisation does not guarantee correct natural language proofs
A. Bastounis, F. Circelli, A. C. Hansen
King's College London, University of Cambridge
The Research Desk.
The most upvoted and starred AI research crossing the community today.
Last Brew Time: Oct 15, 2026, 12:29 PM PT
X.com Research Buzz
AlphaXiv Trending
Computer Vision
AlphaXiv
56
VideoJev: System One Model for Video Understanding and Interaction
Views
Reinforcement Learning
AlphaXiv
47
Hybrid Reasoning Agents
Views
Affiliation: Stanford University, Affiliation: Meta, Affiliation: Stanford University Affiliation: Together AI, Affiliation: Meta Affiliation: Project Lead Affiliation: Core Contributor, Stanford University
Machine Learning
AlphaXiv
28
Neural Networks Are Already Clean
Reinforcement Learning
AlphaXiv
21
Towards Agentic Robots: Model, Data, Environment, and Harness
Views
Affiliation: MMLab, The Chinese University of Hong Kong, Affiliation: Fudan University, Affiliation: Tsinghua University, Affiliation: Zhejiang University, Affiliation: Sun Yat-sen University
Computer Vision
AlphaXiv
12
Any Time, Any Space: A World-State-Centric Framework for Agentic Video Generation
Views
Zhejiang University, Monash University, Adelaide University
AlphaXiv
11
Are We Overthinking One-Step Generation?
Affiliation: Seoul National University, Seoul National University, Harvard University
HuggingFace Daily Papers
HuggingFace
9
History Replays Itself: Unleashing Long-Context Capability in Linear Attention
Li Nanbo, Firas Laakom, Yilan Zhang, Piotr Piękos, Yimeng Chen
KAUST Center of Excellence in Generative AI
Reinforcement Learning
HuggingFace
4
PreciseCoder: Faithful and Generalizable Debugging Beyond Unit-Test Rewards
Yunkai Zhan, Miaosen Chai, Shangshang Wang, Jike Zhong, Yuqing Yang
UC Berkeley
Nicolascc1
HuggingFace
2
When Left Is Right? Camera-Motion Understanding beyond Screen
Chong Cheng, Ran Zhang, Xinyuan Li, Alan Zhao, Hao Wang
Tencent
Robotics
HuggingFace
1
Drive3R: Block-wise Streaming Geometric Foundation Models for Autonomous Driving
Tianyi Yang, Haojun Yang, Jipeng Xiao, Xuesong Chen, Shaoshuai Shi
AutoLab
NLP
HuggingFace
1
Next-Concept Modeling: Fast, Parallel Coarse-to-Fine Text Generation
Hermann Kumbong, Ishan S. Khare, Iddah Mlauzi, Andrew Woen, Charles Ding
Stanford University
Reinforcement Learning
HuggingFace
1
Cortex: Measurement-Gated Evolution and Pruning of Coding-Agent Skills and Rules
Samuele Giampieri