Zihao Yue (岳子豪)PhD Student @ AIM3 Lab School of Information Renmin University of China Email: yzihao [at] ruc.edu.cn |
![]() |
Partial Vocabulary Learning for Neural Text Generation |
Learning Descriptive Image Captioning via Semipermeable Maximum Likelihood Estimation |
Less is More: Mitigating Multimodal Hallucination from an EOS Decision Perspective |
MiMo-VL Technical Report |
R1-V: Reinforcing Super Generalization Ability in Vision Language Models |
Time-R1: Post-Training Large Vision Language Model for Temporal Video Grounding |
Seg-Zero: Reasoning-Chain Guided Segmentation via Cognitive Reinforcement |
VideoOrion: Tokenizing Object Dynamics in Videos |
Unified Multimodal Understanding via Byte-Pair Visual Encoding |
Movie101: A new movie understanding benchmark |
Movie101v2: Improved Movie Narration Benchmark |
Video to Text Description @ TRECVID 2024, 1st Place
Video to Text Description @ TRECVID 2023, 1st Place
Video to Text Description @ TRECVID 2022, 1st Place |