AI研究論文デイリー

Aurora-M: The First Open Source Multilingual Language Model Red-teamed according to the U.S. Executive Order

Getting it Right: Improving Spatial Consistency in Text-to-Image Models

FlexiDreamer: Single Image-to-3D Generation with FlexiCubes

MaGRITTe: Manipulative and Generative 3D Realization from Image, Topview and Text

Measuring Style Similarity in Diffusion Models

CosmicMan: A Text-to-Image Foundation Model for Humans

Streaming Dense Video Captioning

Condition-Aware Neural Network for Controlled Image Generation

Direct Preference Optimization of Video Large Multimodal Models from Language Model Reward

WavLLM: Towards Robust and Adaptive Speech Large Language Model

Noise-Aware Training of Layout-Aware Language Models

ST-LLM: Large Language Models Are Effective Temporal Learners