activity
20242026
most citedExploration vs. Fixation: Scaffolding Divergent and Convergent Thinking for Human-AI Co-Creation with Generative Models

1 citations · 1 across the 11 of their papers we have counts for

collaborators
Showing cs.LGShow all

15 papers · 1 filter

cs.LG2026

Corruption Robust Offline Reinforcement Learning with Human Feedback

Debmalya Mandal, Andi Nika, Parameswaran Kamalaruban +2

We study data corruption robustness for reinforcement learning with human feedback (RLHF) in an offline setting. Given an offline dataset of pairs of trajectories along with feedba…

cs.LG2026

MaMa: A Game-Theoretic Approach for Designing Safe Agentic Systems

Jonathan Nöther, Adish Singla, Goran Radanovic

LLM-based multi-agent systems have demonstrated impressive capabilities, but they also introduce significant safety risks when individual agents fail or behave adversarially. In th…

cs.LG2026

Corruption-robust Offline Multi-agent Reinforcement Learning From Human Feedback

Andi Nika, Debmalya Mandal, Parameswaran Kamalaruban +2

We consider robustness against data corruption in offline multi-agent reinforcement learning from human feedback (MARLHF) under a strong-contamination model: given a dataset of…

cs.LG2026

Learning Half-Spaces from Perturbed Contrastive Examples

Aryan Alavi Razavi Ravari, Farnam Mansouri, Yuxin Chen +3

We study learning under a two-step contrastive example oracle, as introduced by Mansouri et. al. (2025), where each queried (or sampled) labeled example is paired with an additiona…

cs.LG2025

Inference-Time Personalized Alignment with a Few User Preference Queries

Victor-Alexandru Pădurean, Parameswaran Kamalaruban, Nachiket Kotalwar +2

We study the problem of aligning a generative model's response with a user's preferences. Recent works have proposed several different formulations for personalized alignment; howe…

cs.LG2025

Curriculum Design for Trajectory-Constrained Agent: Compressing Chain-of-Thought Tokens in LLMs

Georgios Tzannetos, Parameswaran Kamalaruban, Adish Singla

Training agents to operate under strict constraints during deployment, such as limited resource budgets or stringent safety requirements, presents significant challenges, especiall…