Artigos de Pesquisa em IA Diários

PhysGen: Rigid-Body Physics-Grounded Image-to-Video Generation

MinerU: An Open-Source Solution for Precise Document Content Extraction

VPTQ: Extreme Low-bit Vector Post-Training Quantization for Large Language Models

A Survey on the Honesty of Large Language Models

Modulated Intervention Preference Optimization (MIPO): Keep the Easy, Refine the Difficult

MIO: A Foundation Model on Multimodal Tokens

MSI-Agent: Incorporating Multi-Scale Insight into Embodied Agents for Superior Planning and Decision-Making

HDFlow: Enhancing LLM Complex Problem-Solving with Hybrid Thinking and Dynamic Workflows

LML: Language Model Learning a Dataset for Data-Augmented Prediction

Emu3: Next-Token Prediction is All You Need