AI研究論文デイリー

LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models

Mora: Enabling Generalist Video Generation via A Multi-Agent Framework

Evolutionary Optimization of Model Merging Recipes

SceneScript: Reconstructing Scenes With An Autoregressive Structured Language Model

When Do We Not Need Larger Vision Models?

IDAdapter: Learning Mixed Features for Tuning-Free Personalization of Text-to-Image Models

RewardBench: Evaluating Reward Models for Language Modeling

RadSplat: Radiance Field-Informed Gaussian Splatting for Robust Real-Time Rendering with 900+ FPS

ZigMa: Zigzag Mamba Diffusion Model

HyperLLaVA: Dynamic Visual and Language Expert Tuning for Multimodal Large Language Models

DepthFM: Fast Monocular Depth Estimation with Flow Matching

Magic Fixup: Streamlining Photo Editing by Watching Dynamic Videos

Reverse Training to Nurse the Reversal Curse

Be-Your-Outpainter: Mastering Video Outpainting through Input-Specific Adaptation

VSTAR: Generative Temporal Nursing for Longer Dynamic Video Synthesis

Towards 3D Molecule-Text Interpretation in Language Models

Compress3D: a Compressed Latent Space for 3D Generation from a Single Image

Evaluating Frontier Models for Dangerous Capabilities