Problem: Why It's Hard to Unify Understanding and Generation in One Representation There have been many attempts to merge image understanding and image generation into a…
ActionPiece: Rethinking Action Tokenization Beyond Reconstruction Error, via Physical Ranking TL;DR — In autoregressive VLA (vision-language-action) models, the action…
Programmable World Model — Embedding "Executable State" into Generative Worlds One-Line Summary (TL;DR) Video world models are producing increasingly realistic…
CoVeR: Coverage-Based Pruning That Cuts Visual Tokens of Multi-View 3D Reasoning by up to 92% Using Geometry Alone One-Line Summary (TL;DR) Rendering a 3D scene into…
Why Are Video LLMs Still So Expensive? — A Four-Stage Guide to Inference Efficiency Mechanisms TL;DR — This paper classifies 125 VideoLLM inference efficiency studies…
One-line summary (TL;DR) JanusFlow achieves state-of-the-art performance in both image understanding and generation (FID 9.51 / GenEval 0.63 / MMBench 74.9) with a single…