AI研究論文デイリー

Morph: A Motion-free Physics Optimization Framework for Human Motion Generation

LongKey: Keyphrase Extraction for Long Documents

SelfSplat: Pose-Free and 3D Prior-Free Generalizable 3D Gaussian Splatting

Free^2Guide: Gradient-Free Path Integral Control for Enhancing Text-to-Video Generation with Large Vision-Language Models

Critic-V: VLM Critics Help Catch VLM Errors in Multimodal Reasoning

TryOffDiff: Virtual-Try-Off via High-Fidelity Garment Reconstruction using Diffusion Models

AfriMed-QA: A Pan-African, Multi-Specialty, Medical Question-Answering Benchmark Dataset

ChatGen: Automatic Text-to-Image Generation From FreeStyle Chatting