The Research Desk.

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

Last Brew Time: Jun 11, 2026, 11:07 AM PT

X.com Research Buzz

AI models collapse when trained on recursively generated data
X.com
17627

AI models collapse when trained on recursively generated data

Ilia Shumailov, Zakhar Shumaylov, Yiren Zhao, Yarin Gal, Nicolas Papernot, Ross Anderson

OATML, Department of Computer Science, University of Oxford, University of Cambridge

Memory Caching: RNNs with Growing Memory
X.com
6816

Memory Caching: RNNs with Growing Memory

Ali Behrouz, Zeman Li, Yuan Deng, Peilin Zhong, Meisam Razaviyayn, Vahab Mirrokni

Google Research, Cornell University

AlphaXiv Trending

Reinforcement Learning
OPRD: On-Policy Representation Distillation
AlphaXiv
197

OPRD: On-Policy Representation Distillation

Ant Group, Shenzhi Yang, Guangcheng Zhu, Bowen Song

Zhejiang University

Reinforcement Learning
Agents' Last Exam
AlphaXiv
196

Agents' Last Exam

Siqi Zhu

Reasoning
Latent Reasoning with Normalizing Flows
AlphaXiv
141

Latent Reasoning with Normalizing Flows

Guancheng Tu, Xiangjun Fu, Suhao Yu

Meta, University of California, San Diego

Computer Vision
Latent Spatial Memory for Video World Models
AlphaXiv
86

Latent Spatial Memory for Video World Models

Weijie Wang, Haoyu Zhao, Yifan Yang

Monash University, Zhejiang University

FlashMemory-DeepSeek-V4: Lightning Index Ultra-Long Context via Lookahead Sparse Attention
AlphaXiv
66

FlashMemory-DeepSeek-V4: Lightning Index Ultra-Long Context via Lookahead Sparse Attention

Yan Wang, Qifan Zhang, Jiachen Yu

Tsinghua University, The Hong Kong University of Science and Technology (Guangzhou)

Self-Harness: Harnesses That Improve Themselves
AlphaXiv
60

Self-Harness: Harnesses That Improve Themselves

Hangfan Zhang, Shao Zhang, Kangcong Li

Shanghai Artificial Intelligence Laboratory

HuggingFace Daily Papers

NLP
Reroute, Don't Remove: Recoverable Visual Token Routing for Vision-Language Models
HuggingFace
13

Reroute, Don't Remove: Recoverable Visual Token Routing for Vision-Language Models

Cheng-Yu Yang, Shao-Yuan Lo, Yu-Lun Liu

NLP
DRIFT: A Residual Flow Adapter for Decoding Continuous Outputs in Vision-Language Models
HuggingFace
2

DRIFT: A Residual Flow Adapter for Decoding Continuous Outputs in Vision-Language Models

Zhuoming Liu, Jinhong Lin, Kwan Man Cheng, Lin Zhang, Shayok Bagchi

University of Wisconsin - Madison

NLP
Adaptive Multi-Resolution Procedural Knowledge Compression for Large Language Models
HuggingFace
2

Adaptive Multi-Resolution Procedural Knowledge Compression for Large Language Models

Changyue Wang, Weihang Su, Qingyao Ai, Yichen Tang, Runzhong Qiao

Qingyao Ai

APEX: A Network-Native Time-Series Foundation Model for Forecasting and Anomaly Detection for Wireless Edge Operations
HuggingFace
1

APEX: A Network-Native Time-Series Foundation Model for Forecasting and Anomaly Detection for Wireless Edge Operations

Swadhin Pradhan, Niloo Bahadori, Peiman Amini

Cisco

NLP
Towards Diverse Scientific Hypothesis Search with Large Language Models
HuggingFace
1

Towards Diverse Scientific Hypothesis Search with Large Language Models

Haorui Wang, Parshin Shojaee, Kazem Meidani, Kunyang Sun, José Miguel Hernández-Lobato

Reinforcement Learning
τ-Rec: A Verifiable Benchmark for Agentic Recommender Systems
HuggingFace
1

τ-Rec: A Verifiable Benchmark for Agentic Recommender Systems

Bharath Sivaram Narasimhan, Karthik R Narasimhan