Plus more about VFlash, you don't need long context, and Together Compiler
/
Nov 10, 2026
plus more about Training Models with a Single Algorithm, How to Loop Your Transformer, MTP done right, and Evolving Agent Teams
weekly papers recap
Nov 3, 2026
Nov 17, 2026
plus more about weight-space programming, Energy-Based Perspective on ML, and Latent Feedback Is a Compute and Data Amplifier
Subscribe to our newsletter
plus more about BeNice, Large Flow LM, and Why is AI-generated language so hard to understand?
Oct 27, 2026
plus more about Generative Representation Learning, Understanding LLM Parameter Update Sparsity, and Depth Memory
Oct 20, 2026
Jun 17, 2025
Plus more about "The Diffusion Duality" and "Reinforcement Pre-Training"
Jun 3, 2025
Read about "Rethinking Training Signals in RLVR", why LLMs are headless chickens, and "Learning to Reason without External Rewards"
Premium Insights
Jun 6, 2025
Premium Insights: A recap of popular AI research papers and research trends in May 2025
May 19, 2025
Premium Insights: A closer look into the DeepSeek Prover series
Jan 28, 2025
Plus more about Transformer2 and Kimi k1.5
Oct 13, 2026
Plus more about Looped Transformers Memory and Multi-Agent Self-Supervision
Oct 6, 2026
Looped DiT, Looped Models Done Right, Looped For Free, and Triadic Linear Attention
Sep 29, 2026
Plus more about Memory Attention, JEPA-Anything, and Contrastive World Models