1 citations · 2 across the 26 of their papers we have counts for
28 papers
FlowBudget: Training-Free Sampling-Budget Estimation for Flow Matching Models
Zahra Dehghani, Pablo Piantanida, Mohammadhadi Shateri
Sampling from continuous flow-based generators such as flow matching models requires numerical ODE or SDE integration, making inference cost depend on the number of function evalua…
How Much Were You Told? Measuring External Information in Peer Reviews
Matthieu Dubois, Pablo Piantanida, François Yvon
Conference policies distinguish using Large Language Models (LLMs) to polish one's own review from delegating the critique, but current Artificial Text Detection (ATD) methods larg…
Source-Free Class Relearning: Diagnosing Forgetting in Class Unlearning
Zahra Dehghani, Pablo Piantanida, Mohammadhadi Shateri
Class unlearning aims to remove a model's ability to recognize designated forget classes while preserving performance on retain classes. However, low forget accuracy after unlearni…
Continuous Adversarial MeanFlow Transfer
Yara Bahram, Zahra Dehghani, Mélodie Desbos +3
Training fast generators on new domains with limited data remains challenging for two reasons. First, adapting a pretrained diffusion or flow model to a new domain leaves its costl…
STORM: Stepwise Token Optimization with Reward-Guided Beam Search
Arthur Satouf, Giulio D'Erasmo, Yuxuan Zong +3
Modern retrieval increasingly relies on dense and learned-sparse neural models that are effective but require encoding the entire corpus into a specialized index, rebuilt whenever…
ECUAS: A family of metrics for principled evaluation of uncertainty-augmented systems
Lautaro Estienne, Erik Ernst, Matías Vera +2
In high-stakes automated decision-making, access to predictive uncertainty is essential for enabling users -- human or downstream systems -- to accept or reject predictions based o…
MolRGen: A Training and Evaluation Setting for De Novo Molecular Generation with Reasonning Models
Philippe Formont, Maxime Darrin, Ismail Ben Ayed +1
Recent reasoning-based large language models have shown strong performance on tasks with verifiable outcomes, but their use in de novo molecular generation remains limited by the l…
Happiness as a Measure of Fairness
Georg Pichler, Marco Romanelli, Pablo Piantanida
In this paper, we propose a novel fairness framework grounded in the concept of happiness, a measure of the utility each group gains fromdecisionoutcomes. Bycapturingfairness throu…
QueStER: Query Specification for Generative keyword-based Retrieval
Arthur Satouf, Yuxuan Zong, Habiboulaye Amadou-Boubacar +2
Generative retrieval (GR) differs from the traditional index-then-retrieve pipeline by storing relevance in model parameters and generating retrieval cues directly from the query,…
Learning Task-Agnostic Representations through Multi-Teacher Distillation
Philippe Formont, Maxime Darrin, Banafsheh Karimian +5
Casting complex inputs into tractable representations is a critical step across various fields. Diverse embedding models emerge from differences in architectures, loss functions, i…
How Sampling Affects the Detectability of Machine-written texts: A Comprehensive Study
Matthieu Dubois, François Yvon, Pablo Piantanida
As texts generated by Large Language Models (LLMs) are ever more common and often indistinguishable from human-written content, research on automatic text detection has attracted g…
Collaborative Rational Speech Act: Pragmatic Reasoning for Multi-Turn Dialog
Lautaro Estienne, Gabriel Ben Zenou, Nona Naderi +2
As AI systems take on collaborative roles, they must reason about shared goals and beliefs-not just generate fluent language. The Rational Speech Act (RSA) framework offers a princ…
THUNDER: Tile-level Histopathology image UNDERstanding benchmark
Pierre Marza, Leo Fillioux, Sofiène Boutaj +6
Progress in a research field can be hard to assess, in particular when many concurrent methods are proposed in a short period of time. This is the case in digital pathology, where…
: A Rhetorical-Strategy-Aware Rational Speech Act Framework for Figurative Language Understanding
Cesare Spinoso-Di Piano, David Austin, Pablo Piantanida +1
Figurative language (e.g., irony, hyperbole, understatement) is ubiquitous in human communication, resulting in utterances where the literal and the intended meanings do not match.…
Rational Retrieval Acts: Leveraging Pragmatic Reasoning to Improve Sparse Retrieval
Arthur Satouf, Gabriel Ben Zenou, Benjamin Piwowarski +2
Current sparse neural information retrieval (IR) methods, and to a lesser extent more traditional models such as BM25, do not take into account the document collection and the comp…
Statistical Deficiency for Task Inclusion Estimation
Loïc Fosse, Frédéric Béchet, Benoît Favre +5
Tasks are central in machine learning, as they are the most natural objects to assess the capabilities of current models. The trend is to build general models able to address any t…
BayesAdapter: enhanced uncertainty estimation in CLIP few-shot adaptation
Pablo Morales-Álvarez, Stergios Christodoulidis, Maria Vakalopoulou +2
The emergence of large pre-trained vision-language models (VLMs) represents a paradigm shift in machine learning, with unprecedented results in a broad span of visual recognition t…
MOSAIC: Multiple Observers Spotting AI Content
Matthieu Dubois, François Yvon, Pablo Piantanida
The dissemination of Large Language Models (LLMs), trained at scale, and endowed with powerful text-generating abilities, has made it easier for all to produce harmful, toxic, fake…
Combine and Conquer: A Meta-Analysis on Data Shift and Out-of-Distribution Detection
Eduardo Dadalto, Florence Alberge, Pierre Duhamel +1
This paper introduces a universal approach to seamlessly combine out-of-distribution (OOD) detection scores. These scores encompass a wide range of techniques that leverage the sel…
Predicting Probabilities of Error to Combine Quantization and Early Exiting: QuEE
Florence Regol, Joud Chataoui, Bertrand Charpentier +3
Machine learning models can solve complex tasks but often require significant computational resources during inference. This has led to the development of various post-training com…
GLIMPSE: Pragmatically Informative Multi-Document Summarization for Scholarly Reviews
Maxime Darrin, Ines Arous, Pablo Piantanida +1
Scientific peer review is essential for the quality of academic publications. However, the increasing number of paper submissions to conferences has strained the reviewing process.…
Beyond the Norms: Detecting Prediction Errors in Regression Models
Andres Altieri, Marco Romanelli, Georg Pichler +2
This paper tackles the challenge of detecting unreliable behavior in regression algorithms, which may arise from intrinsic variability (e.g., aleatoric uncertainty) or modeling err…
When is an Embedding Model More Promising than Another?
Maxime Darrin, Philippe Formont, Ismail Ben Ayed +2
Embedders play a central role in machine learning, projecting any object into numerical representations that can, in turn, be leveraged to perform various downstream tasks. The eva…
A Strong Baseline for Molecular Few-Shot Learning
Philippe Formont, Hugo Jeannin, Pablo Piantanida +1
Few-shot learning has recently attracted significant interest in drug discovery, with a recent, fast-growing literature mostly involving convoluted meta-learning strategies. We rev…