The Research Desk.

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

Last Brew Time: Oct 18, 2026, 11:05 AM PT

X.com Research Buzz

Computer Vision
Analytic non-axisymmetric 3D MHD equilibria without stellarator symmetry
X.com
4701

Analytic non-axisymmetric 3D MHD equilibria without stellarator symmetry

Opal Issan, Jonathan Citrin, Matt Landreman, Brendan Tracey

Google DeepMind, University of California San Diego, University of Maryland

AlphaXiv Trending

Machine Learning
AlphaXiv
121

Neural Networks Are Already Clean

4k, Views

NLP
Generative Representation Learning for Scalable Latent Tokenization
AlphaXiv
102

Generative Representation Learning for Scalable Latent Tokenization

2k, Views

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

Robotics
T2-z: Test-Time Optimization of Environment Latents for Robotic World Models
AlphaXiv
37

T2-z: Test-Time Optimization of Environment Latents for Robotic World Models

Views

Stanford University CMU, Toyota Research Institute University of Southern California

Machine Learning
Librarian Agents: Training LLMs to Curate Long-Context Workspaces that Anticipate Future Queries
AlphaXiv
20

Librarian Agents: Training LLMs to Curate Long-Context Workspaces that Anticipate Future Queries

Views

Affiliation: Stanford University, Affiliation: Carnegie Mellon University, Stanford University, Carnegie Mellon University

Stay CALM: Calibrated Online Aggregation for Multi-Horizon Forecasting Under Delayed, Overlapping Feedback
AlphaXiv
16

Stay CALM: Calibrated Online Aggregation for Multi-Horizon Forecasting Under Delayed, Overlapping Feedback

Views

Reinforcement Learning
Learning Self-Orchestration in Decentralized Agent Swarms
AlphaXiv
11

Learning Self-Orchestration in Decentralized Agent Swarms

Harvard University

HuggingFace Daily Papers

OpenSAE
Behavioral Compositionality of Sparse Autoencoder Representations
HuggingFace
106

Behavioral Compositionality of Sparse Autoencoder Representations

Haotian Ma, Ziye Mei, Frederic Sala

OpenSAE

Reinforcement Learning
LEASH: Uncertainty-Aware Weak-to-Strong Escalation and Oversight for Computer-Use Agents
HuggingFace
7

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

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

Safety Alignment
Mine, Sample, Render: Test-Time Diversity Alignment Of Generative Models
HuggingFace
5

Mine, Sample, Render: Test-Time Diversity Alignment Of Generative Models

Kostas Triaridis, Morris E. Sharp, Nebojsa Jojic

Computer Vision
LeanPRM: Lean-Grounded Process Supervision for Natural Language Proof Verification
HuggingFace
5

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

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

Reinforcement Learning
Scalable Weak-to-Strong Verifier Hardening for Agent Environments
HuggingFace
4

Scalable Weak-to-Strong Verifier Hardening for Agent Environments

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

Stanford AI

Diminishing Returns of Data in Sparse Autoencoders: Functional Behavior does not Guarantee Feature Reproducibility
HuggingFace
1

Diminishing Returns of Data in Sparse Autoencoders: Functional Behavior does not Guarantee Feature Reproducibility

Sambit Ghosh, Madelyn Mathai, R. Venkatesh Babu, Chirag Agarwal

Aikyam Lab