AI研究論文デイリー

Summary of a Haystack: A Challenge to Long-Context LLMs and RAG Systems

Agentless: Demystifying LLM-based Software Engineering Agents

OpenVid-1M: A Large-Scale High-Quality Dataset for Text-to-video Generation

MInference 1.0: Accelerating Pre-filling for Long-Context LLMs via Dynamic Sparse Attention

Understanding Alignment in Multimodal LLMs: A Comprehensive Study

Magic Insert: Style-Aware Drag-and-Drop

Consistency Flow Matching: Defining Straight Flows with Velocity Consistency

To Forget or Not? Towards Practical Knowledge Unlearning for Large Language Models

What Matters in Detecting AI-Generated Videos like Sora?

Revealing Fine-Grained Values and Opinions in Large Language Models

FoleyCrafter: Bring Silent Videos to Life with Lifelike and Synchronized Sounds

μ-Bench: A Vision-Language Benchmark for Microscopy Understanding