The Research Desk.

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

Last Brew Time: Oct 16, 2026, 11:56 AM PT

X.com Research Buzz

AI solutions to the Grad-Shafranov equation for fusion plasma equilibrium
X.com
4677

AI solutions to the Grad-Shafranov equation for fusion plasma equilibrium

Machine Learning
QwenGyre: An Elastic Reinforcement Learning Framework for Training xLong-Horizon Agents
X.com
3649

QwenGyre: An Elastic Reinforcement Learning Framework for Training xLong-Horizon Agents

Weiqi Wang, Yuxin Zhou, Mouxiang Chen, Siyuan Zhang, Yi Zhang, Yuyan Luo, Zhiyu Yin, Chencan Wu, Jiemin Jiang, Wentao Yao, Chujie Zheng, JianWei Zhang

Alibaba Group, University of Science and Technology of China, Tsinghua University

AlphaXiv Trending

Machine Learning
AlphaXiv
78

Neural Networks Are Already Clean

3k, Views

Are We Overthinking One-Step Generation?
AlphaXiv
59

Are We Overthinking One-Step Generation?

Views

Affiliation: Seoul National University, Seoul National University, Harvard University

Reinforcement Learning
Towards Agentic Robots: Model, Data, Environment, and Harness
AlphaXiv
44

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

NLP
Generative Representation Learning for Scalable Latent Tokenization
AlphaXiv
32

Generative Representation Learning for Scalable Latent Tokenization

Views

Affiliation: Stanford University, Affiliation: Massachusetts Institute of Technology, Affiliation: University of Michigan, Stanford University, Massachusetts Institute of Technology

Machine Learning
Training Language Models to Fail Gracefully
AlphaXiv
18

Training Language Models to Fail Gracefully

Affiliation: Carnegie Mellon University, Carnegie Mellon University

Machine Learning
AutoSFT: An Agentic System for Automated Data Research in Supervised Fine-Tuning
AlphaXiv
12

AutoSFT: An Agentic System for Automated Data Research in Supervised Fine-Tuning

Views

Affiliation: University of Illinois Urbana-Champaign, Affiliation: Tsinghua University, Affiliation: Beijing University of Posts and Telecommunications, AutoSFT: An Agentic System for Automated Data Research in Supervised Fine-Tuning, University of Illinois Urbana-Champaign

HuggingFace Daily Papers

Computer Vision
LeanPRM: Lean-Grounded Process Supervision for Natural Language Proof Verification
HuggingFace
3

LeanPRM: Lean-Grounded Process Supervision for Natural Language Proof Verification

Rodney Lafuente-Mercado, Salman Rahman, Jingyan Shen, James Shiffer, Saadia Gabriel

PathFM: Fast Generative Forecasting of Multivariate Trajectories
HuggingFace
2

PathFM: Fast Generative Forecasting of Multivariate Trajectories

Jiachen Yao, Xiyuan Zhang, Annan Yu, Boran Han, Abdul Fatir Ansari

Autogluon

Reinforcement Learning
LEASH: Uncertainty-Aware Weak-to-Strong Escalation and Oversight for Computer-Use Agents
HuggingFace
1

LEASH: Uncertainty-Aware Weak-to-Strong Escalation and Oversight for Computer-Use Agents

Qingni Wang, Changdae Oh, Yuzhe Yang, Sharon Li, Jiachen Yang

Nguyenx2t
Equal CER, Unequal Damage: Severity-Weighted Character Error Rate for OCR
HuggingFace
1

Equal CER, Unequal Damage: Severity-Weighted Character Error Rate for OCR

Nguyen Nguyen, Yongyi Zang

University of Rochester

Machine Learning
Learning to Read Out: Unembedding Dynamics in Language Model Pretraining
HuggingFace
1

Learning to Read Out: Unembedding Dynamics in Language Model Pretraining

Matteo He, William F. Shen, Alex Iacob, Andrej Jovanovic, Xinchi Qiu

Reinforcement Learning
Scalable Weak-to-Strong Verifier Hardening for Agent Environments
HuggingFace
0

Scalable Weak-to-Strong Verifier Hardening for Agent Environments

Chong Zeng, Ziqian Zhong, Kexun Zhang, Ivan Bercovich, Ivgeni Segal

Stanford AI