Haowen Hou

transformer architecture (1) reinforcement learning (1) sample efficiency (1) policy optimization (1) self-supervised learning (1) knowledge distillation (1) language modeling (1) multimodal learning (1) model architecture (1) visual reasoning (1) efficient inference (1) computational efficiency (1) latent representation (1) recurrent neural network (1) multimodal large language model (1) advantage estimation (1) inference efficiency (1) long video understanding (1) linear attention (1) visual language model (1)