Efficient Learning

Reducing the compute and data cost of vision models, from test-time training to low-resolution robustness.

References

2025

  1. T2L: Efficient Zero-Shot Action Recognition with Temporal Token Learning
    Shahzad Ahmad, Sukalpa Chanda, and Yogesh S. Rawat
    Transactions on Machine Learning Research (TMLR), 2025
  2. LR0.FM: Low-Resolution Zero-Shot Classification Benchmark for Foundation Models
    Priyank Pathak, Shyam Marjit, Shruti Vyas, and Yogesh S. Rawat
    In International Conference on Learning Representations (ICLR), 2025

2024

  1. Asynchronous Perception Machine for Efficient Test-Time-Training
    Rajat Modi and Yogesh Rawat
    In Advances in Neural Information Processing Systems (NeurIPS), 2024

2023

  1. EZ-CLIP: Efficient Zero-shot Video Action Recognition
    Shahzad Ahmad, Sukalpa Chanda, and Yogesh S Rawat
    arXiv preprint arXiv:2312.08010, 2023