2 papers
cs.LG2025
Matryoshka Model Learning for Improved Elastic Student Models
Chetan Verma, Aditya Srinivas Timmaraju, Cho-Jui Hsieh +7
Industry-grade ML models are carefully designed to meet rapidly evolving serving constraints, which requires significant resources for model development. In this paper, we propose…
cs.CL2024
Unpacking the Resilience of SNLI Contradiction Examples to Attacks
Chetan Verma, Archit Agarwal
Pre-trained models excel on NLI benchmarks like SNLI and MultiNLI, but their true language understanding remains uncertain. Models trained only on hypotheses and labels achieve hig…