AI研究論文每日精選

Fourier Position Embedding: Enhancing Attention's Periodic Extension for Length Generalization

DepthLab: From Partial to Complete

3DGraphLLM: Combining Semantic Graphs and Large Language Models for 3D Scene Understanding

DiTCtrl: Exploring Attention Control in Multi-Modal Diffusion Transformer for Tuning-Free Multi-Prompt Longer Video Generation

Ensembling Large Language Models with Process Reward-Guided Tree Search for Better Complex Reasoning

In Case You Missed It: ARC 'Challenge' Is Not That Challenging

ReMoE: Fully Differentiable Mixture-of-Experts with ReLU Routing

PartGen: Part-level 3D Generation and Reconstruction with Multi-View Diffusion Models

SKETCH: Structured Knowledge Enhanced Text Comprehension for Holistic Retrieval

Bridging the Data Provenance Gap Across Text, Speech and Video

MotiF: Making Text Count in Image Animation with Motion Focal Loss