Jesus Rios — accepted AI-conference papers

2026

Revisiting Group Relative Policy Optimization: Insights into On-Policy and Off-Policy Training

Youssef Mroueh, Nicolas Dupuis, Brian Belgodere, Apoorva Nitsure, Mattia Rigotti, Kristjan Greenewald +3

ICLR 2026poster

We revisit Group Relative Policy Optimization (GRPO) in both on-policy and off-policy optimization regimes. Our motivation comes from recent work on off-policy Proximal Policy Optimization (PPO), which improves training stability, sampling efficiency, and memory usage. In addition, a recent analysis…

Cited by 0 Source ↗Scholar ↗

2025

Contextual Value Alignment

Pierre L. Dognin, Jesus Rios, Ronny Luss, Prasanna Sattigeri, Miao Liu, Inkit Padhi +4

ICASSP 2025accepted

Developing value-aligned agents is a complex undertaking and an ongoing challenge in the field of AI. Indeed, designing Large Language Models (LLMs) that can balance multiple possibly conflicting moral values based on the context is a problem of paramount importance. In this paper, we propose a syst…

Cited by 0 Source ↗Scholar ↗

2025

Evaluating the Prompt Steerability of Large Language Models

Erik Miehling, Michael Desmond, Karthikeyan Natesan Ramamurthy, Elizabeth M. Daly, Kush R. Varshney, Eitan Farchi +5

NAACL 2025long

Building pluralistic AI requires designing models that are able to be shaped to represent a wide range of value systems and cultures. Achieving this requires first being able to evaluate the degree to which a given model is capable of reflecting various personas. To this end, we propose a benchmark…

Cited by 3 Source ↗PDF ↗code ↗Scholar ↗

2025

Sparsity May Be All You Need: Sparse Random Parameter Adaptation

Jesus Rios, Pierre Dognin, Ronny Luss, Karthikeyan Natesan Ramamurthy

EMNLP 2025

Full fine-tuning of large language models for alignment and task adaptation has become prohibitively expensive as models have grown in size. Parameter-Efficient Fine-Tuning (PEFT) methods aim at significantly reducing the computational and memory resources needed for fine-tuning these models by only

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗

2024

ComVas: Contextual Moral Values Alignment System

Inkit Padhi, Pierre Dognin, Jesus Rios, Ronny Luss, Swapnaja Achintalwar, Matthew Riemer +5

IJCAI 2024poster

In contemporary society, the integration of artificial intelligence (AI) systems into various aspects of daily life raises significant ethical concerns. One critical aspect is to ensure that AI systems align with the moral values of the endusers. To that end, we introduce the Contextual Moral Value…

Cited by 5 Source ↗PDF ↗code ↗Scholar ↗

2023

Fault Injection Based Interventional Causal Learning for Distributed Applications

Qing Wang, Jesus Rios, Saurabh Jha, Karthikeyan Shanmugam, Frank Bagehorn, Xi Yang +3

AAAI 2023technical

We apply the machinery of interventional causal learning with programmable interventions to the domain of applications management. Modern applications are modularized into interdependent components or services (e.g. microservices) for ease of development and management. The communication graph among…

Cited by 5 Source ↗PDF ↗code ↗Scholar ↗

2022

Fourier Representations for Black-Box Optimization over Categorical Variables

Hamid Dadkhahi, Jesus Rios, Karthikeyan Shanmugam, Payel Das

AAAI 2022technical

Optimization of real-world black-box functions defined over purely categorical variables is an active area of research. In particular, optimization and design of biological sequences with specific functional or structural properties have a profound impact in medicine, materials science, and biotechn…

Cited by 9 Source ↗PDF ↗Scholar ↗