AI研究論文每日精選

GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection

SaulLM-7B: A pioneering Large Language Model for Law

ShortGPT: Layers in Large Language Models are More Redundant Than You Expect

PixArt-Σ: Weak-to-Strong Training of Diffusion Transformer for 4K Text-to-Image Generation

Learning to Decode Collaboratively with Multiple Language Models

Enhancing Vision-Language Pre-training with Rich Supervisions

Stop Regressing: Training Value Functions via Classification for Scalable Deep RL

Caduceus: Bi-Directional Equivariant Long-Range DNA Sequence Modeling

3D Diffusion Policy

Backtracing: Retrieving the Cause of the Query