Jiri Navratil — 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 ↗

2024

Distributional Preference Alignment of LLMs via Optimal Transport

Igor Melnyk, Youssef Mroueh, Brian Belgodere, Mattia Rigotti, Apoorva Nitsure, Mikhail Yurochkin +3

NeurIPS 2024poster

Current LLM alignment techniques use pairwise human preferences at a sample level, and as such, they do not imply an alignment on the distributional level. We propose in this paper Alignment via Optimal Transport (AOT), a novel method for distributional preference alignment of LLMs. AOT aligns LLMs…

Cited by 15 Source ↗PDF ↗Scholar ↗

2024

Larimar: Large Language Models with Episodic Memory Control

Payel Das, Subhajit Chaudhury, Elliot Nelson, Igor Melnyk, Sarathkrishna Swaminathan, Sihui Dai +6

ICML 2024poster

Efficient and accurate updating of knowledge stored in Large Language Models (LLMs) is one of the most pressing research challenges today. This paper presents Larimar - a novel, brain-inspired architecture for enhancing LLMs with a distributed episodic memory. Larimar's memory allows for dynamic, on…

Cited by 15 Source ↗PDF ↗code ↗Scholar ↗

2024

Learning Granger Causality from Instance-wise Self-attentive Hawkes Processes

Dongxia Wu, Tsuyoshi Ide, Georgios Kollias, Jiri Navratil, Aurelie Lozano, Naoki Abe +2

AISTATS 2024poster

We address the problem of learning Granger causality from asynchronous, interdependent, multi-type event sequences. In particular, we are interested in discovering instance-level causal structures in an unsupervised manner. Instance-level causality identifies causal relationships among individual ev…

Cited by 2 Source ↗PDF ↗Scholar ↗

2024

Risk Aware Benchmarking of Large Language Models

Apoorva Nitsure, Youssef Mroueh, Mattia Rigotti, Kristjan Greenewald, Brian Belgodere, Mikhail Yurochkin +3

ICML 2024poster

We propose a distributional framework for benchmarking socio-technical risks of foundation models with quantified statistical significance. Our approach hinges on a new statistical relative testing based on first and second order stochastic dominance of real random variables. We show that the second…

Cited by 1 Source ↗PDF ↗Scholar ↗

2019

Confidence Scoring Using Whitebox Meta-models with Linear Classifier Probes

Tongfei Chen, Jiri Navratil, Vijay Iyengar, Karthikeyan Shanmugam

AISTATS 2019poster

We propose a novel confidence scoring mechanism for deep neural networks based on a two-model paradigm involving a base model and a meta-model. The confidence score is learned by the meta-model observing the base model succeeding/failing at its task. As features to the meta-model, we investigate lin…

Cited by 54 Source ↗PDF ↗code ↗Scholar ↗