AI research papers from labs and universities, explained in plain English

Strengthening our defenses against distillation attacks

Multi-Token Prediction Done Right

Nested Sparsity for Scalable Pretraining and Continual Learning

Speculative Diffusion is a Tale of Two Tradeoffs

Every Weight Is a Path of Shared Discrete Decisions

Looped Uniform Diffusion Language Models

Diffusion Language Models Change Speed Across Tasks and Languages

Hugging Face Papers

PhysSkin++: Real-Time and Generalizable Physics-Based Animation via Self-Supervised Neural Skinning

Hugging Face Papers

When the KV Cache Is Slower Than the GPU: Scaling Remote KV Tiers for Context-Parallel Prefill

Hugging Face Papers

Lexical Reference Frames: Interpreting LM Residual Streams in Native Semantics

Hugging Face Papers

LEV: Thinking Fast and Deep with Looped Decision Models

Hugging Face Papers