AI研究論文每日精選

Vision language models are blind

AgentInstruct: Toward Generative Teaching with Agentic Flows

Internet of Agents: Weaving a Web of Heterogeneous Agents for Collaborative Intelligence

Video-STaR: Self-Training Enables Video Instruction Tuning with Any Supervision

RodinHD: High-Fidelity 3D Avatar Generation with Diffusion Models

Adapting LLMs to Hebrew: Unveiling DictaLM 2.0 with Enhanced Vocabulary and Instruction Capabilities

MiraData: A Large-Scale Video Dataset with Long Durations and Structured Captions

BM25S: Orders of magnitude faster lexical search via eager sparse scoring

Lookback Lens: Detecting and Mitigating Contextual Hallucinations in Large Language Models Using Only Attention Maps

TheoremLlama: Transforming General-Purpose LLMs into Lean4 Experts

Knowledge Composition using Task Vectors with Learned Anisotropic Scaling

Graph-Based Captioning: Enhancing Visual Descriptions by Interconnecting Region Captions

VIMI: Grounding Video Generation through Multi-modal Instruction

From Loops to Oops: Fallback Behaviors of Language Models Under Uncertainty

How do you know that? Teaching Generative Language Models to Reference Answers to Biomedical Questions

LETS-C: Leveraging Language Embedding for Time Series Classification