AI研究論文デイリー

CoD, Towards an Interpretable Medical Agent using Chain of Diagnosis

KAN or MLP: A Fairer Comparison

MovieDreamer: Hierarchical Generation for Coherent Long Visual Sequence

OutfitAnyone: Ultra-high Quality Virtual Try-On for Any Clothing and Any Person

T2V-CompBench: A Comprehensive Benchmark for Compositional Text-to-video Generation

F-HOI: Toward Fine-grained Semantic-Aligned 3D Human-Object Interactions

INF-LLaVA: Dual-perspective Perception for High-Resolution Multimodal Large Language Model

A Simulation Benchmark for Autonomous Racing with Large-Scale Human Data

SIGMA: Sinkhorn-Guided Masked Video Modeling

PrimeGuard: Safe and Helpful LLMs through Tuning-Free Routing

Cross Anything: General Quadruped Robot Navigation through Complex Terrains