Revant Teotia

multimodal learning (3) visual reasoning (2) commonsense reasoning (2) multimodal transformer (2) knowledge retrieval (2) image retrieval (2) factual reasoning (2) vision language model (1) text-to-image model (1) zero-shot transfer (1) generalization capacity (1) reference-free evaluation (1) clip model (1) rationale generation (1) image search (1) visual relationship (1) translation vector (1) relationship embedding (1) image generation diversity (1) generative model benchmarking (1)