7 papers
DP-OPD: Differentially Private On-Policy Distillation for Language Models
Fatemeh Khadem, Sajad Mousavi, Yi Fang +1
Large language models (LLMs) are increasingly adapted to proprietary and domain-specific corpora that contain sensitive information, creating a tension between formal privacy guara…
Robustness Evaluation for Video Models with Reinforcement Learning
Ashwin Ramesh Babu, Sajad Mousavi, Vineet Gundecha +5
Evaluating the robustness of Video classification models is very challenging, specifically when compared to image-based models. With their increased temporal dimension, there is a…
Coordinated Robustness Evaluation Framework for Vision-Language Models
Ashwin Ramesh Babu, Sajad Mousavi, Vineet Gundecha +5
Vision-language models, which integrate computer vision and natural language processing capabilities, have demonstrated significant advancements in tasks such as image captioning a…
Carbon Footprint Reduction for Sustainable Data Centers in Real-Time
Soumyendu Sarkar, Avisek Naug, Ricardo Luna +6
As machine learning workloads significantly increase energy consumption, sustainable data centers with low carbon emissions are becoming a top priority for governments and corporat…
SustainDC: Benchmarking for Sustainable Data Center Control
Avisek Naug, Antonio Guillen, Ricardo Luna +8
Machine learning has driven an exponential increase in computational demand, leading to massive data centers that consume significant amounts of energy and contribute to climate ch…
Reinforcement Learning Platform for Adversarial Black-box Attacks with Custom Distortion Filters
Soumyendu Sarkar, Ashwin Ramesh Babu, Sajad Mousavi +5
We present a Reinforcement Learning Platform for Adversarial Black-box untargeted and targeted attacks, RLAB, that allows users to select from various distortion filters to create…