AI研究論文デイリー

RAFT: Adapting Language Model to Domain Specific RAG

Uni-SMART: Universal Science Multimodal Analysis and Research Transformer

VideoAgent: Long-form Video Understanding with Large Language Model as Agent

Alignment Studio: Aligning Large Language Models to Particular Contextual Regulations

Recurrent Drafter for Fast Speculative Decoding in Large Language Models

MusicHiFi: Fast High-Fidelity Stereo Vocoding

FDGaussian: Fast Gaussian Splatting from Single Image via Geometric-aware Diffusion Model

EfficientVMamba: Atrous Selective Scan for Light Weight Visual Mamba

Isotropic3D: Image-to-3D Generation Based on a Single CLIP Embedding

Controllable Text-to-3D Generation via Surface-Aligned Gaussian Splatting

NeuFlow: Real-time, High-accuracy Optical Flow Estimation on Robots Using Edge Devices