Papers
2
Total Citations
9
H-Index
2
About
Dr. Soujanya Poria is a leading researcher in multimodal AI, natural language processing, and affective computing, with a focus on bridging vision and language. His work advances how machines interpret and interact with the physical world through mental simulation and knowledge-enriched reasoning. Notably, his 2022 paper “PIP: Physical Interaction Prediction via Mental Simulation with Span Selection” introduces a novel framework for predicting physical interactions between objects in images, leveraging cognitive-inspired mental simulation to achieve precise spatial reasoning. This work has garnered 5 citations, reflecting its foundational impact on embodied AI. In 2023, his paper “Language Guided Visual Question Answering: Elevate Your Multimodal Language Model Using Knowledge-Enriched Prompts” (4 citations) pushes the boundaries of visual question answering (VQA) by integrating external knowledge into multimodal language models, enabling more accurate and context-aware responses. Dr. Poria’s contributions are pivotal in developing AI systems that understand complex visual scenes and human intentions, with applications ranging from robotics to assistive technologies. His research continues to inspire new directions in multimodal learning and human-AI interaction.
Research Focus
Key Achievements
Top Papers
- 1
- 2