5 papers
Preference Conditioned Multi-Objective Reinforcement Learning: Decomposed, Diversity-Driven Policy Optimization
Tanmay Ambadkar, Sourav Panda, Shreyash Kale +2
Multi-objective reinforcement learning (MORL) seeks to train agents capable of balancing conflicting objectives. While single preference-conditioned policies offer a highly scalabl…
Two-Bridge: Exclusive Objectives and Extended Horizon StarCraft II Benchmark
Sourav Panda, Tanmay Ambadkar, Shreyash Kale +2
The research community lacks a middle ground between StarCraft II full game and its mini-games. The full-game's sprawling state-action space renders reward signals sparse and noisy…
Attention Is Where You Attack
Aviral Srivastava, Sourav Panda
Safety-aligned large language models rely on RLHF and instruction tuning to refuse harmful requests, yet the internal mechanisms implementing safety behavior remain poorly understo…
Signed, Sealed,... Confused: Exploring the Understandability and Severity of Policy Documents
Shikha Soneji, Sourav Panda, Sameer Neve +1
In general, Terms of Service (ToS) and other policy documents are verbose and full of legal jargon, which poses challenges for users to understand. To improve user accessibility an…
A Formal Framework for Assessing and Mitigating Emergent Security Risks in Generative AI Models: Bridging Theory and Dynamic Risk Mitigation
Aviral Srivastava, Sourav Panda
As generative AI systems, including large language models (LLMs) and diffusion models, advance rapidly, their growing adoption has led to new and complex security risks often overl…