AI研究論文デイリー

In-Context Edit: Enabling Instructional Image Editing with In-Context Generation in Large Scale Diffusion Transformer

Certified Mitigation of Worst-Case LLM Copyright Infringement

Disentangle Identity, Cooperate Emotion: Correlation-Aware Emotional Talking Portrait Generation

YoChameleon: Personalized Vision and Language Generation

UniversalRAG: Retrieval-Augmented Generation over Multiple Corpora with Diverse Modalities and Granularities

X-Fusion: Introducing New Modality to Frozen Large Language Models

Toward Evaluative Thinking: Meta Policy Optimization with Evolving Reward Models

ReasonIR: Training Retrievers for Reasoning Tasks

The Leaderboard Illusion

TesserAct: Learning 4D Embodied World Models

ISDrama: Immersive Spatial Drama Generation through Multimodal Prompting

TreeHop: Generate and Filter Next Query Embeddings Efficiently for Multi-hop Question Answering

Reinforcement Learning for Reasoning in Large Language Models with One Training Example

A Review of 3D Object Detection with Vision-Language Models