Harsh Agrawal

object detection (3) embodied ai (2) multimodal large language model (2) data augmentation (2) multimodal learning (2) vision-language navigation (1) image generation (1) reinforcement learning (1) visual question answering (1) image-to-image translation (1) knowledge distillation (1) few-shot learning (1) dialogue generation (1) scene understanding (1) depth estimation (1) image captioning (1) visual grounding (1) transfer learning (1) zero-shot learning (1) contrastive learning (1)