49 citations · 132 across the 23 of their papers we have counts for
23 papers
Does It Tie Out? Towards Autonomous Legal Agents in Venture Capital
Pierre Colombo, Malik Boudiaf, Allyn Sweet +4
Before closing venture capital financing rounds, lawyers conduct diligence that includes tying out the capitalization table: verifying that every security (for example, shares, opt…
EOL: Transductive Few-Shot Open-Set Recognition by Enhancing Outlier Logits
Mateusz Ochal, Massimiliano Patacchiola, Malik Boudiaf +1
In Few-Shot Learning (FSL), models are trained to recognise unseen objects from a query set, given a few labelled examples from a support set. In standard FSL, models are evaluated…
SaulLM-54B & SaulLM-141B: Scaling Up Domain Adaptation for the Legal Domain
Pierre Colombo, Telmo Pires, Malik Boudiaf +7
In this paper, we introduce SaulLM-54B and SaulLM-141B, two large language models (LLMs) tailored for the legal sector. These models, which feature architectures of 54 billion and…
LP++: A Surprisingly Strong Linear Probe for Few-Shot CLIP
Yunshi Huang, Fereshteh Shakeri, Jose Dolz +3
In a recent, strongly emergent literature on few-shot CLIP adaptation, Linear Probe (LP) has been often reported as a weak baseline. This has motivated intensive research building…
SaulLM-7B: A pioneering Large Language Model for Law
Pierre Colombo, Telmo Pessoa Pires, Malik Boudiaf +8
In this paper, we introduce SaulLM-7B, a large language model (LLM) tailored for the legal domain. With 7 billion parameters, SaulLM-7B is the first LLM designed explicitly for leg…
Bag of Tricks for Fully Test-Time Adaptation
Saypraseuth Mounsaveng, Florent Chiaroni, Malik Boudiaf +2
Fully Test-Time Adaptation (TTA), which aims at adapting models to data drifts, has recently attracted wide interest. Numerous tricks and techniques have been proposed to ensure ro…
Transductive Learning for Textual Few-Shot Classification in API-based Embedding Models
Pierre Colombo, Victor Pellegrain, Malik Boudiaf +5
Proprietary and closed APIs are becoming increasingly common to process natural language, and are impacting the practical applications of natural language processing, including few…
In Search for a Generalizable Method for Source Free Domain Adaptation
Malik Boudiaf, Tom Denton, Bart van Merriënboer +2
Source-free domain adaptation (SFDA) is compelling because it allows adapting an off-the-shelf model to a new domain using only unlabelled data. In this work, we apply existing SFD…
Open-Set Likelihood Maximization for Few-Shot Learning
Malik Boudiaf, Etienne Bennequin, Myriam Tami +4
We tackle the Few-Shot Open-Set Recognition (FSOSR) problem, i.e. classifying instances among a set of classes for which we only have a few labeled samples, while simultaneously de…
A Strong Baseline for Generalized Few-Shot Semantic Segmentation
Sina Hajimiri, Malik Boudiaf, Ismail Ben Ayed +1
This paper introduces a generalized few-shot segmentation framework with a straightforward training process and an easy-to-optimize inference phase. In particular, we propose a sim…
Towards Practical Few-Shot Query Sets: Transductive Minimum Description Length Inference
Ségolène Martin, Malik Boudiaf, Emilie Chouzenoux +2
Standard few-shot benchmarks are often built upon simplifying assumptions on the query sets, which may not always hold in practice. In particular, for each task at testing time, th…
Simplex Clustering via sBeta with Applications to Online Adjustment of Black-Box Predictions
Florent Chiaroni, Malik Boudiaf, Amar Mitiche +1
We explore clustering the softmax predictions of deep neural networks and introduce a novel probabilistic clustering method, referred to as k-sBetas. In the general context of clus…
Model-Agnostic Few-Shot Open-Set Recognition
Malik Boudiaf, Etienne Bennequin, Myriam Tami +4
We tackle the Few-Shot Open-Set Recognition (FSOSR) problem, i.e. classifying instances among a set of classes for which we only have few labeled samples, while simultaneously dete…
FHIST: A Benchmark for Few-shot Classification of Histological Images
Fereshteh Shakeri, Malik Boudiaf, Sina Mohammadi +4
Few-shot learning has recently attracted wide interest in image classification, but almost all the current public benchmarks are focused on natural images. The few-shot paradigm is…
Realistic Evaluation of Transductive Few-Shot Learning
Olivier Veilleux, Malik Boudiaf, Pablo Piantanida +1
Transductive inference is widely used in few-shot learning, as it leverages the statistics of the unlabeled query set of a few-shot task, typically yielding substantially better pe…
A Differential Entropy Estimator for Training Neural Networks
Georg Pichler, Pierre Colombo, Malik Boudiaf +2
Mutual Information (MI) has been widely used as a loss regularizer for training neural networks. This has been particularly effective when learn disentangled or compressed represen…
Parameter-free Online Test-time Adaptation
Malik Boudiaf, Romain Mueller, Ismail Ben Ayed +1
Training state-of-the-art vision models has become prohibitively expensive for researchers and practitioners. For the sake of accessibility and resource reuse, it is important to f…
Mutual-Information Based Few-Shot Classification
Malik Boudiaf, Ziko Imtiaz Masud, Jérôme Rony +3
We introduce Transductive Infomation Maximization (TIM) for few-shot learning. Our method maximizes the mutual information between the query features and their label predictions fo…
Transductive Few-Shot Learning: Clustering is All You Need?
Imtiaz Masud Ziko, Malik Boudiaf, Jose Dolz +2
We investigate a general formulation for clustering and transductive few-shot learning, which integrates prototype-based objectives, Laplacian regularization and supervision constr…
Adversarial Robustness via Fisher-Rao Regularization
Marine Picot, Francisco Messina, Malik Boudiaf +3
Adversarial robustness has become a topic of growing interest in machine learning since it was observed that neural networks tend to be brittle. We propose an information-geometric…
Few-Shot Segmentation Without Meta-Learning: A Good Transductive Inference Is All You Need?
Malik Boudiaf, Hoel Kervadec, Ziko Imtiaz Masud +3
We show that the way inference is performed in few-shot segmentation tasks has a substantial effect on performances -- an aspect often overlooked in the literature in favor of the…
Transductive Information Maximization For Few-Shot Learning
Malik Boudiaf, Ziko Imtiaz Masud, Jérôme Rony +3
We introduce Transductive Infomation Maximization (TIM) for few-shot learning. Our method maximizes the mutual information between the query features and their label predictions fo…
A unifying mutual information view of metric learning: cross-entropy vs. pairwise losses
Malik Boudiaf, Jérôme Rony, Imtiaz Masud Ziko +4
Recently, substantial research efforts in Deep Metric Learning (DML) focused on designing complex pairwise-distance losses, which require convoluted schemes to ease optimization, s…