Skip to content
View pritamqu's full-sized avatar

Highlights

  • Pro

Block or report pritamqu

Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
pritamqu/README.md
  • 👋 Hi, I'm Pritam!
  • 🎞️ I'm interested in multimodal learning from videos. Please check my website for more information www.pritamsarkar.com.
  • ☕ I'm always open to coffee and discussing research.
  • 📷 Other than training neural networks, I'm interested photography and film making.
  • 📫 reach me: pritam[dot]sarkar[at]queensu[dot]ca.

A selected list of my open-source contributions:

Pinned Loading

  1. VCRBench VCRBench Public

    VCRBench: Exploring Long-form Causal Reasoning Capabilities of Large Video Language Models

    Python 5 1

  2. RRPO RRPO Public

    [NeurIPS 2025] Self-alignment of Large Video Language Models with Refined Regularized Preference Optimization

    Python 9

  3. HALVA HALVA Public

    [ICLR 2025] Data-Augmented Phrase-Level Alignment for Mitigating Object Hallucination

    Python 19

  4. OOD-VSSL OOD-VSSL Public

    [NeurIPS 2023 (Spotlight)] Uncovering the Hidden Dynamics of Video Self-supervised Learning under Distribution Shifts

    Python 13

  5. XKD XKD Public

    [AAAI 2024] XKD: Cross-modal Knowledge Distillation with Domain Alignment for Video Representation Learning.

    Python 15 1

  6. CrissCross CrissCross Public

    [AAAI 2023 (Oral)] CrissCross: Self-Supervised Audio-Visual Representation Learning with Relaxed Cross-Modal Synchronicity

    Python 25 2