AI.info

Min Zhang

Explore Min Zhang on AI.info.

• Generative Retrieval for Unsupervised Text-Based Person Search
• Dynamics Within Latent Chain-of-Thought: An Empirical Study of Causal Structure
• CASTLE: A Comprehensive Benchmark for Evaluating Student-Tailored Personalized Safety in Large Language Models
• LycheeDecode: Accelerating Long-Context LLM Inference via Hybrid-Head Sparse Decoding
• Decoupling Skeleton and Flesh: Efficient Multimodal Table Reasoning with Disentangled Alignment and Structure-aware Guidance
• VC-Bench: Pioneering the Video Connecting Benchmark with a Dataset and Evaluation Metrics
• FutureOmni: Evaluating Future Forecasting from Omni-Modal Context for Multimodal LLMs
• Knowledge Completes the Vision: A Multimodal Entity-aware Retrieval-Augmented Generation Framework for News Image Captioning
• SMRC: Aligning Large Language Models with Student Reasoning for Mathematical Error Correction
• Uni-MoE-2.0-Omni: Scaling Language-Centric Omnimodal Large Model with Advanced MoE, Training and Data
• UCO: A Multi-Turn Interactive Reinforcement Learning Method for Adaptive Teaching with Large Language Models
• Towards Fine-Grained Code-Switch Speech Translation with Semantic Space Alignment
• Understanding New-Knowledge-Induced Factual Hallucinations in LLMs: Analysis and Interpretation
• LoCoT2V-Bench: Benchmarking Long-Form and Complex Text-to-Video Generation
• FAPO: Flawed-Aware Policy Optimization for Efficient and Reliable Reasoning
• MMLongCite: A Benchmark for Evaluating Fidelity of Long-Context Vision-Language Models
• EduDial: Constructing a Large-scale Multi-turn Teacher-Student Dialogue Corpus