Mattia Rigotti — 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 ↗

2026

SPARC: Separating Perception And Reasoning Circuits for Test-time Scaling of VLMs

Niccolò Avogaro, Nayanika Debnath, Li Mi, Thomas Frick, Junling Wang, Zexue He +3

ICML 2026poster

Despite recent successes, *test-time scaling* $-$i.e., dynamically expanding the token budget during inference as needed$-$ remains brittle for vision-language models (VLMs): unstructured chains-of-thought about images entangle perception and reasoning, leading to long, disorganized contexts where s…

Cited by 0 Source ↗Scholar ↗

2025

Eliciting Reasoning in Language Models with Cognitive Tools

Brown Ebouky, Andrea Bartezzaghi, Mattia Rigotti

NeurIPS 2025poster

The recent advent of reasoning models like OpenAI's o1 was met with excited speculation by the AI community about the mechanisms underlying these capabilities in closed models, followed by a rush of replication efforts, particularly from the open source community. These speculations were largely set…

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

Multivariate Stochastic Dominance via Optimal Transport and Applications to Models Benchmarking

Gabriel Rioux, Apoorva Nitsure, Mattia Rigotti, Kristjan Greenewald, Youssef Mroueh

NeurIPS 2024poster

Stochastic dominance is an important concept in probability theory, econometrics and social choice theory for robustly modeling agents' preferences between random outcomes. While many works have been dedicated to the univariate case, little has been done in the multivariate scenario, wherein an age…

Cited by 1 Source ↗PDF ↗Scholar ↗

2024

On the generalization capacity of neural networks during generic multimodal reasoning

Takuya Ito, Soham Dan, Mattia Rigotti, James Kozloski, Murray Campbell

ICLR 2024poster

The advent of the Transformer has led to the development of large language models (LLM), which appear to demonstrate human-like capabilities. To assess the generality of this class of models and a variety of other base neural network architectures to multimodal domains, we evaluated and compared the…

Cited by 2 Source ↗PDF ↗code ↗Scholar ↗

2024

Probabilistic Feature Matching for Fast Scalable Visual Prompting

Thomas Frick, Cezary Skura, Filip M. Janicki, Roy Assaf, Niccolo Avogaro, Daniel Caraballo +13

IJCAI 2024poster

In this work, we propose a novel framework for image segmentation guided by visual prompting which leverages the power of vision foundation models. Inspired by recent advancements in computer vision, our approach integrates multiple large-scale pretrained models to address the challenges of segment…

Cited by 1 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 ↗

2024

Unraveling the Key Components of OOD Generalization via Diversification

Harold Luc Benoit, Liangze Jiang, Andrei Atanov, Oguzhan Fatih Kar, Mattia Rigotti, Amir Zamir

ICLR 2024poster

Supervised learning datasets may contain multiple cues that explain the training set equally well, i.e., learning any of them would lead to the correct predictions on the training data. However, many of them can be spurious, i.e., lose their predictive power under a distribution shift and consequent…

Cited by 2 Source ↗PDF ↗Scholar ↗

2023

DARE: Towards Robust Text Explanations in Biomedical and Healthcare Applications

Adam Ivankay, Mattia Rigotti, Pascal Frossard

ACL 2023long

Along with the successful deployment of deep neural networks in several application domains, the need to unravel the black-box nature of these networks has seen a significant increase recently. Several methods have been introduced to provide insight into the inference process of deep neural networks…

Cited by 1 Source ↗PDF ↗code ↗Scholar ↗

2022

Attention-based Interpretability with Concept Transformers

Mattia Rigotti, Christoph Miksovic, Ioana Giurgiu, Thomas Gschwind, Paolo Scotton

ICLR 2022poster

Attention is a mechanism that has been instrumental in driving remarkable performance gains of deep neural network models in a host of visual, NLP and multimodal tasks. One additional notable aspect of attention is that it conveniently exposes the ``reasoning'' behind each particular output generate…

Cited by 85 Source ↗PDF ↗code ↗Scholar ↗

2022

Compositional generalization through abstract representations in human and artificial neural networks

Takuya Ito, Tim Klinger, Doug H Schultz, John D Murray, Michael Cole, Mattia Rigotti

NeurIPS 2022accept

Humans have a remarkable ability to rapidly generalize to new tasks that is difficult to reproduce in artificial learning systems. Compositionality has been proposed as a key mechanism supporting generalization in humans, but evidence of its neural implementation and impact on behavior is still scar…

Cited by 51 Source ↗PDF ↗Scholar ↗

2021

Deep Bandits Show-Off: Simple and Efficient Exploration with Deep Networks

Rong Zhu, Mattia Rigotti

NeurIPS 2021poster

Designing efficient exploration is central to Reinforcement Learning due to the fundamental problem posed by the exploration-exploitation dilemma. Bayesian exploration strategies like Thompson Sampling resolve this trade-off in a principled way by modeling and updating the distribution of the para…

Cited by 8 Source ↗PDF ↗code ↗Scholar ↗

2021

Self-correcting Q-learning

Rong Zhu, Mattia Rigotti

AAAI 2021technical

The Q-learning algorithm is known to be affected by the maximization bias, i.e. the systematic overestimation of action values, an important issue that has recently received renewed attention. Double Q-learning has been proposed as an efficient algorithm to mitigate this bias. However, this comes at…

Cited by 27 Source ↗PDF ↗code ↗Scholar ↗

2021

Tabular Transformers for Modeling Multivariate Time Series

Inkit Padhi, Yair Schiff, Igor Melnyk, Mattia Rigotti, Youssef Mroueh, Pierre L. Dognin +3

ICASSP 2021accepted

Tabular datasets are ubiquitous in data science applications. Given their importance, it seems natural to apply state-of-the-art deep learning algorithms in order to fully unlock their potential. Here we propose neural network models that represent tabular time series that can optionally leverage th…

Cited by 0 Source ↗Scholar ↗

2020

Unbalanced Sobolev Descent

Youssef Mroueh, Mattia Rigotti

NeurIPS 2020poster

We introduce Unbalanced Sobolev Descent (USD), a particle descent algorithm for transporting a high dimensional source distribution to a target distribution that does not necessarily have the same mass. We define the Sobolev-Fisher discrepancy between distributions and show that it relates to advect…

Cited by 15 Source ↗PDF ↗code ↗Scholar ↗

2019

Beyond Backprop: Online Alternating Minimization with Auxiliary Variables

Anna Choromanska, Benjamin Cowen, Sadhana Kumaravel, Ronny Luss, Mattia Rigotti, Irina Rish +5

ICML 2019oral

Despite significant recent advances in deep neural networks, training them remains a challenge due to the highly non-convex nature of the objective function. State-of-the-art methods rely on error backpropagation, which suffers from several well-known issues, such as vanishing and exploding gradient…

Cited by 78 Source ↗PDF ↗code ↗Scholar ↗

2019

Sobolev Independence Criterion

Youssef Mroueh, Tom Sercu, Mattia Rigotti, Inkit Padhi, Cicero Nogueira dos Santos

NeurIPS 2019poster

We propose the Sobolev Independence Criterion (SIC), an interpretable dependency measure between a high dimensional random variable X and a response variable Y. SIC decomposes to the sum of feature importance scores and hence can be used for nonlinear feature selection. SIC can be seen as a gradient…

Cited by 7 Source ↗PDF ↗code ↗Scholar ↗