The Research Desk.

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

Last Brew Time: Oct 26, 2026, 11:56 AM PT

X.com Research Buzz

NLP
The Algorithmic Self-Portrait: Deconstructing Memory in ChatGPT
X.com
7284

The Algorithmic Self-Portrait: Deconstructing Memory in ChatGPT

Abhisek Dash, Soumi Das, Elisabeth Kirsten, Qinyuan Wu, Sai Keerthana Karnam, Krishna P. Gummadi, Thorsten Holz, Muhammad Bilal Zafar, Savvas Zannettou

Max Planck Institute for Software Systems, Ruhr University Bochum, Indian Institute of Technology Kharagpur, Max Planck Institute for Security and Privacy, Delft University of Technology

Financing the AI Buildout
X.com
6442

Financing the AI Buildout

Stijn Van Nieuwerburgh

Columbia Business School

NLP
Byte Latent Transformer: Patches Scale Better Than Tokens
X.com
5222

Byte Latent Transformer: Patches Scale Better Than Tokens

Artidoro Pagnoni, Ram Pasunuru, Pedro Rodriguez, John Nguyen, Benjamin Muller, Margaret Li, Chunting Zhou, Lili Yu, Jason Weston, Luke Zettlemoyer, Gargi Ghosh, Mike Lewis

Meta AI

AlphaXiv Trending

A Fix for Softmax and Cross-Entropy
AlphaXiv
340

A Fix for Softmax and Cross-Entropy

8k, Views

Affiliation: Google DeepMind, Google DeepMind

Reinforcement Learning
Agentic World Action Models
AlphaXiv
182

Agentic World Action Models

3k, Views

NVIDIA, University of Pennsylvania

Action Learning for Scientific Simulations
AlphaXiv
48

Action Learning for Scientific Simulations

Views

Affiliation: Kempner Institute Harvard University Microsoft Research New England Website Code, Kempner Institute, Harvard University, Microsoft Research New England

Native Real-Time Interactive Omni Intelligence: A Unified Framework
AlphaXiv
18

Native Real-Time Interactive Omni Intelligence: A Unified Framework

Views

UniAction: Unified Action Conditioning for World Models
AlphaXiv
8

UniAction: Unified Action Conditioning for World Models

Affiliation: Stanford University, Stanford University

Reinforcement Learning
Memory Tax: Dissecting the Net Value of Agent Memory
AlphaXiv
6

Memory Tax: Dissecting the Net Value of Agent Memory

HuggingFace Daily Papers

Lniehaus
KANLab: TensorFlow Playground for Kolmogorov-Arnold Networks
HuggingFace
2

KANLab: TensorFlow Playground for Kolmogorov-Arnold Networks

Lukas Niehaus, Robin Rawiel, Ulf Krumnack

Computer Vision
Judging the Justification: Decision Certificate Supervision for Generative Reward Models
HuggingFace
1

Judging the Justification: Decision Certificate Supervision for Generative Reward Models

Guiquan Sun, Bing Bai, Martin Renqiang Min, Dongjin Song

NLP
LLM2Cert: LLM Synthesis of Certificates with SMT/Lean Verification
HuggingFace
1

LLM2Cert: LLM Synthesis of Certificates with SMT/Lean Verification

Zhipeng Cao, Peiyang Song, Nikolaus Vertovec, Weiru Cui, Zhihao Yang

FormalCert-AI

Mosh0110
Predictive Closure: A Set-Level Characterization of JEPA's Feature Selection
HuggingFace
0

Predictive Closure: A Set-Level Characterization of JEPA's Feature Selection

Mosh Levy, Aly Lidayan, Yoav Goldberg

University of California, Berkeley

NLP
On the Token Collapse Phenomenon in Textual Graph Soft Prompting
HuggingFace
0

On the Token Collapse Phenomenon in Textual Graph Soft Prompting

Andrea Giuseppe Di Francesco, Rishabh Jain, Franco Maria Nardini, Nicola Tonellotto, Pietro Liò

Sapienza University of Rome

Robotics
FLORA: An Open Model Suite for Scaling Robotics Data Engines
HuggingFace
0

FLORA: An Open Model Suite for Scaling Robotics Data Engines

Sicong Leng, Yunze Man, Zhiqi Li, Jing Wang, Yuhe Zhang

NVIDIA