Yuexiang Zhai

multimodal large language model (2) vision language model (2) reinforcement learning (2) transformer architecture (1) contrastive learning (1) self-supervised learning (1) 3d reconstruction (1) policy optimization (1) matrix factorization (1) decision making (1) sparse representation (1) curriculum learning (1) sample complexity (1) batch normalization (1) multimodal learning (1) benchmark evaluation (1) visual reasoning (1) visual grounding (1) instruction following (1) representation learning (1)