【ICLR'26】Latent Speech-Text Transformer
【ICLR'26】AnyUp: Universal Feature Upsampling
【ICLR'26】LLMs Get Lost In Multi-Turn Conversation
【ICLR'26】RealUID
【ICLR'26】Energy-Based Transformers are Scalable Learners and Thinkers
We've Been Doing Attention Wrong (2-Line Fix)
【NeurIPS'25】Why Diffusion Models Don't Memorize
Yann LeCun's Billion Dollar Bet
The Moment that Reset Robotics
【双语】Variational Autoencoders
Dual Diffusion Implicit Bridges for Image-to-Image Translation
【ICLR'26】From Physics to AI to Materials; A Journey from Foundations to Impact
Engram: How LLMs Finally Get Scalable Memory
Yann LeCun's $1B Bet Against LLMs [Part 2]
Meta Flow Maps enable scalable reward alignment | Peter Potaptchik
【NeurIPS 2024 Tutorial】Flow Matching for Generative Modeling
【双语】Attention Residuals, Visually Explained
Stochastic Interpolants: A Unifying Framework for Flows and Diffusions
How to build a consistency model: Learning flow maps via self-distillation
【双语】Stable Diffusion from Scratch in PyTorch - Conditional LDM
