Home

Hello! I am Arkaprava Sinha, a Graduate Research Assistant pursuing a Ph.D. in Computer Science at the University of North Carolina, Charlotte. I am advised by Prof. Srijan Das. My research lies in the intersection of Multimodal Vision Language Models, Long Context Video Understanding, Temporal Modeling and Agentic Systems with a focus on building scalable and reliable algorithms for Long Video Understanding.

Prior to my Ph.D., I worked as a Data Scientist, where I contributed to projects in Computer Vision, Natural Language Processing, and large-scale Machine Learning systems across industry and research settings.

Research

My research focuses on building efficient multimodal AI systems for long-horizon video understanding, egocentric perception, and visual reasoning. I design scalable temporal architectures and representation learning methods that help models reason over long, untrimmed videos, align video with language, motion, and structured visual cues, and operate efficiently in real-world settings.

I am particularly interested in agentic video understanding, where systems actively search for relevant evidence, reason over temporal context, and verify answers using multimodal foundation models instead of exhaustively processing entire videos. Broadly, my work connects long video understanding, Vision-Language Models, Multimodal LLMs, diffusion-based generation, and embodied AI, with applications in robotics, AR/VR, intelligent assistants, assistive technology, and safety-critical video analytics.

News

Feb 2026 - MS-Temba accepted to CVPR 2026.
Feb 2025 - LLAVIDAL accepted to CVPR 2025.
Dec 2024 - SKI Models accepted to AAAI 2025.
Oct 2024 - 2 papers accepted to NeurIPS 2024 workshops. Early version of LLAVIDAL is presented in NeurIPS 2024 workshop on Video-Language Models and Multimodal Algorithmic Reasoning.

Selected Publications

• TimeProVe: Propose, then Verify for Efficient Long Video Temporal Reasoning in Activities of Daily Living
  Preprint, 2026
  Arkaprava Sinha, Dominick Reilly, Siddharth Krishnan, Hieu Le, Srijan Das
  Paper | Website

• UniEgo: Proxies as Mediators for Unified Egocentric Video Representation Learning
  Preprint, 2026
  Wenhao Chi, Arkaprava Sinha, Dominick Reilly, Hieu Le, Srijan Das
  Paper

• MS-Temba: Multi-Scale Temporal Mamba for Understanding Long Untrimmed Videos
  The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2026
  Arkaprava Sinha, Monish Soundar Raj, Pu Wang, Ahmed Helmy, Hieu Le, Srijan Das
  Paper | Code | Website

• LLAVIDAL: A Large Language Vision Model for Daily Activities of Living
  The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025
  Dominick Reilly, Rajatsubhra Chakraborty, Arkaprava Sinha, Manish Kumar Govind, Pu Wang, Francois Bremond, Le Xue, Srijan Das
  Paper | Code | Website

• SKI Models: Skeleton Induced Vision-Language Embeddings for Understanding Activities of Daily Living
  The 39th Annual AAAI Conference on Artificial Intelligence (AAAI), 2025
  Arkaprava Sinha, Dominick Reilly, Francois Bremond, Pu Wang, Srijan Das
  Paper | Code

• DiffSwap++: 3D Latent-Controlled Diffusion for Identity-Preserving Face Swapping
  Preprint
  Weston Bondurant, Arkaprava Sinha, Hieu Le, Srijan Das, Stephanie Schuckers
  Paper

• Quo Vadis, Video Understanding with Vision-Language Foundation Models?
  NeurIPS Workshop on Video-Language Models, 2024
  Mahmoud Ali, Di Yang, Arkaprava Sinha, Dominick Reilly, Srijan Das, Gianpiero Francesca, Francois Bremond
  Paper