AI研究論文每日精選

Autoregressive Model Beats Diffusion: Llama for Scalable Image Generation

Husky: A Unified, Open-Source Language Agent for Multi-Step Reasoning

Vript: A Video Is Worth Thousands of Words

Towards a Personal Health Large Language Model

Lighting Every Darkness with 3DGS: Fast Training and Real-Time Rendering for HDR View Synthesis

Tx-LLM: A Large Language Model for Therapeutics

VALL-E 2: Neural Codec Language Models are Human Parity Zero-Shot Text to Speech Synthesizers

Margin-aware Preference Optimization for Aligning Diffusion Models without Reference

ShiftAddLLM: Accelerating Pretrained LLMs via Post-Training Multiplication-Less Reparameterization

Unified Text-to-Image Generation and Retrieval

IllumiNeRF: 3D Relighting without Inverse Rendering

MLCM: Multistep Consistency Distillation of Latent Diffusion Model

ExtraNeRF: Visibility-Aware View Extrapolation of Neural Radiance Fields with Diffusion Models

GTR: Improving Large 3D Reconstruction Models through Geometry and Texture Refinement