Ravindran, Balaraman

Adaptive Action Duration with Contextual Bandits for Deep Reinforcement Learning in Dynamic Environments
AQUA: Attention via QUery mAgnitudes for Memory and Compute Efficient Inference in LLMs
Generalized Adaptive Transfer Network: Enhancing Transfer Learning in Reinforcement Learning Across Domains
Learning from Observation: A Survey of Recent Advances
mFARM: Towards Multi-Faceted Fairness Assessment based on HARMs in Clinical Decision Support
Multilinguality in LLM-Designed Reward Functions for Restless Bandits: Effects on Task Performance and Fairness
SafeMIL: Learning Offline Safe Imitation Policy from Non-Preferred Trajectories
SWAN: Sparse Winnowed Attention for Reduced Inference Memory via Decompression-Free KV-Cache Compression
Where Should I Study? Biased Language Models Decide! Evaluating Fairness in LMs for Academic Recommendations
InSaAF: Incorporating Safety through Accuracy and Fairness | Are LLMs ready for the Indian Legal Domain?
Language Models can Subtly Deceive Without Lying: A Case Study on Strategic Phrasing in Legislation
Participatory Approaches in AI Development and Governance: A Principled Approach
Participatory Approaches in AI Development and Governance: Case Studies
QuAKE: Speeding up Model Inference Using Quick and Approximate Kernels for Exponential Non-Linearities