Shaofeng Yin

open-vocabulary detection (2) human-object interaction detection (2) autoregressive transformer (1) video generation (1) video prediction (1) visual question answering (1) multimodal learning (1) human-object interaction (1) model-based reinforcement learning (1) vision language model (1) prompt generation (1) tool use (1) world model (1) visual-language model (1) visual planning (1) semantic enhancement (1) negative sampling (1) multi-step reasoning (1) action-conditioned prediction (1) fine-grained semantics (1)