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…
Introduction In models that handle long contexts, the compression operation that reduces multiple tokens to a single vector becomes a performance bottleneck. This paper…
ActionPiece: Rethinking Action Tokenization Beyond Reconstruction Error, via Physical Ranking TL;DR — In autoregressive VLA (vision-language-action) models, the action…
StepAudio 3 Gen: Unifying Speech, Song, Music, and Sound Effects with a Single Discrete Autoregressive (RVQ) Model TL;DR StepAudio 3 Gen, released by StepFun, is a fully…
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…
Janus-Pro 7B: Dual-Encoder Multimodal LLM That Outsmarts Bigger Models One-line summary (TL;DR) By fully separating the SigLIP understanding encoder from the VQ…