- 2025: Achieved 2nd place in research track at UC Berkeley’s AgentX challenge
- 2025: Paper “Aurelia: Test-time Reasoning Distillation in Audio-Visual LLMs” accepted at ICCV 2025
- 2025: Paper “VideoGLaMM: A Large Multimodal Model for Pixel-Level Visual Grounding in Videos” accepted at CVPR 2025
- 2025: Paper “VANE-Bench: Video Anomaly Evaluation Benchmark for Conversational LMMs” accepted at NAACL 2025
- 2024: One paper accepted at COLING 2025
- 2024: One paper accepted at IEEE/CVF WACV 2025
- 2024: Paper “MedContext: Learning Contextual Cues for Efficient Volumetric Medical Segmentation” accepted at MICCAI 2024
- 2024: One paper accepted at IEEE ICIP 2024
- 2024: Awarded ICLR 2024 Travel Grant
- 2024: Paper “LLM Blueprint: Enabling Text-to-Image Generation with Complex and Detailed Prompts” accepted at ICLR 2024
- 2023: Awarded NeurIPS 2023 Travel Grant
- 2023: Paper “Align your Prompts: Test-Time Prompting with Distribution Alignment for Zero-Shot Generalization” accepted at NeurIPS 2023
- 2023: US patent about training Vision Transformers on small-scale datasets approved for filing
Research Experience
- 2025-Present: University of California, San Diego (UCSD)
- 2021-Present: Mohamed Bin Zayed University of Artificial Intelligence (MBZUAI)
- 2023: Visiting Student at KAUST, under Prof. Peter Wonka
- 2018-2021: Samsung
Education
- PhD: University of California, San Diego (UCSD), Computer Science, advised by Prof. Manmohan Chandraker
- Master's: Mohamed Bin Zayed University of Artificial Intelligence (MBZUAI), Machine Learning, advised by Prof. Salman Khan, co-advised by Prof. Fahad Khan, and mentored by Prof. Muzammal Naseer
- Bachelor's: NIT Srinagar, 2014-2018
Background
PhD student and Powell Fellow in Computer Science. Research interests include multimodal learning, generative AI, and embodied intelligence.