AI研究論文每日精選

LLaVA-o1: Let Vision Language Models Reason Step-by-Step

GaussianAnything: Interactive Point Cloud Latent Diffusion for 3D Generation

Region-Aware Text-to-Image Generation via Hard Binding and Soft Refinement

The Dawn of GUI Agent: A Preliminary Case Study with Claude 3.5 Computer Use

Xmodel-1.5: An 1B-scale Multilingual LLM

Number it: Temporal Grounding Videos like Flipping Manga

MARS: Unleashing the Power of Variance Reduction for Training Large Models