AI研究論文每日精選

Molmo and PixMo: Open Weights and Open Data for State-of-the-Art Multimodal Models

Programming Every Example: Lifting Pre-training Data Quality like Experts at Scale

Boosting Healthcare LLMs Through Retrieved Context

DreamWaltz-G: Expressive 3D Gaussian Avatars from Skeleton-Guided 2D Diffusion

AIM 2024 Sparse Neural Rendering Challenge: Dataset and Benchmark

Degradation-Guided One-Step Image Super-Resolution with Diffusion Priors

Synchronize Dual Hands for Physics-Based Dexterous Guitar Playing

HyperAgent: Generalist Software Engineering Agents to Solve Coding Tasks at Scale

NoTeeline: Supporting Real-Time Notetaking from Keypoints with Large Language Models

Game4Loc: A UAV Geo-Localization Benchmark from Game Data

TalkinNeRF: Animatable Neural Fields for Full-Body Talking Humans

Self-Supervised Any-Point Tracking by Contrastive Random Walks