AI研究論文每日精選

MM1: Methods, Analysis & Insights from Multimodal LLM Pre-training

Quiet-STaR: Language Models Can Teach Themselves to Think Before Speaking

Unlocking the conversion of Web Screenshots into HTML Code with the WebSight Dataset

GiT: Towards Generalist Vision Transformer through Universal Language Interface

StreamMultiDiffusion: Real-Time Interactive Generation with Region-Based Semantic Control

Video Editing via Factorized Diffusion Distillation

BurstAttention: An Efficient Distributed Attention Framework for Extremely Long Sequences

Glyph-ByT5: A Customized Text Encoder for Accurate Visual Text Rendering

Griffon v2: Advancing Multimodal Perception with High-Resolution Scaling and Visual-Language Co-Referring

Video Mamba Suite: State Space Model as a Versatile Alternative for Video Understanding

3D-VLA: A 3D Vision-Language-Action Generative World Model

VisionGPT-3D: A Generalized Multimodal Agent for Enhanced 3D Vision Understanding

Veagle: Advancements in Multimodal Representation Learning

LocalMamba: Visual State Space Model with Windowed Selective Scan