Paper 'VeLoRA: Memory Efficient Training using Rank-1 Sub-Token Projections' accepted to NeurIPS 2024.
Paper 'VkD: Improving Knowledge Distillation using Orthogonal Projections' accepted to CVPR 2024.
Paper 'Understanding the Role of the Projector in Knowledge Distillation' accepted to AAAI 2024.
Paper 'MobileVOS: Real-time Video Object Segmentation' accepted to CVPR 2023.
Paper 'Learning to Project for Cross-Task Knowledge Distillation' accepted to BMVC 2024.
Co-authored multiple high-impact publications in ICCV (highlight), arXiv, and other venues, focusing on knowledge distillation, efficient vision models, and visual representation learning.