Artigos de Pesquisa em IA Diários

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

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

ReasonIR: Training Retrievers for Reasoning Tasks

Toward Evaluative Thinking: Meta Policy Optimization with Evolving Reward Models

TesserAct: Learning 4D Embodied World Models

YoChameleon: Personalized Vision and Language Generation

Certified Mitigation of Worst-Case LLM Copyright Infringement

The Leaderboard Illusion

ISDrama: Immersive Spatial Drama Generation through Multimodal Prompting

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

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

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