AI研究论文每日精选

SRMT: Shared Memory for Multi-agent Lifelong Pathfinding

Improving Video Generation with Human Feedback

Sigma: Differential Rescaling of Query, Key and Value for Efficient Language Models

Can We Generate Images with CoT? Let's Verify and Reinforce Image Generation Step by Step

Video-MMMU: Evaluating Knowledge Acquisition from Multi-Discipline Professional Videos

Temporal Preference Optimization for Long-Form Video Understanding

IMAGINE-E: Image Generation Intelligence Evaluation of State-of-the-art Text-to-Image Models

Step-KTO: Optimizing Mathematical Reasoning through Stepwise Binary Feedback

DiffuEraser: A Diffusion Model for Video Inpainting

Hallucinations Can Improve Large Language Models in Drug Discovery

One-Prompt-One-Story: Free-Lunch Consistent Text-to-Image Generation Using a Single Prompt

EchoVideo: Identity-Preserving Human Video Generation by Multimodal Feature Fusion

Debate Helps Weak-to-Strong Generalization

EmbodiedEval: Evaluate Multimodal LLMs as Embodied Agents

Evolution and The Knightian Blindspot of Machine Learning

Control LLM: Controlled Evolution for Intelligence Retention in LLM

GSTAR: Gaussian Surface Tracking and Reconstruction