85 citations · 131 across the 28 of their papers we have counts for
32 papers
DistMoE: Private-data Rehearsal-free Routing in Mixture-of-Experts for Distributed Instruction Tuning
Mainak Singha, Niccolò Biondi, Elisa Ricci +1
Multimodal Large Language Models (MLLMs) have shown strong multimodal instruction-following ability, but adapting them to diverse visual-language domains typically assumes centrali…
Predict-then-Diffuse: Adaptive Response Length for Compute-Budgeted Inference in Diffusion LLMs
Michael Rottoli, Subhankar Roy, Stefano Paraboschi
Diffusion-based Large Language Models (D-LLMs) represent a promising frontier in generative AI, offering fully parallel token generation that can lead to significant throughput adv…
ProactiveBench: Benchmarking Proactiveness in Multimodal Large Language Models
Thomas De Min, Subhankar Roy, Stéphane Lathuilière +2
Effective collaboration begins with knowing when to ask for help. For example, when trying to identify an occluded object, a human would ask someone to remove the obstruction. Can…
How (Mis)calibrated is your Federated CLIP and what to do about it?
Mainak Singha, Masih Aminbeidokhti, Paolo Casari +3
Vision-language models (VLMs) such as CLIP are increasingly adapted across decentralized data silos, yet the reliability of their predictions under federated learning (FL) remains…
LT-Soups: Bridging Head and Tail Classes via Subsampled Model Soups
Masih Aminbeidokhti, Subhankar Roy, Eric Granger +2
Real-world datasets typically exhibit long-tailed (LT) distributions, where a few head classes dominate and many tail classes are severely underrepresented. While recent work shows…
Ensembling Pruned Attention Heads For Uncertainty-Aware Efficient Transformers
Firas Gabetni, Giuseppe Curci, Andrea Pilzer +3
Uncertainty quantification (UQ) is essential for deploying deep neural networks in safety-critical settings. Although methods like Deep Ensembles achieve strong UQ performance, the…
Make me an Expert: Distilling from Generalist Black-Box Models into Specialized Models for Semantic Segmentation
Yasser Benigmim, Subhankar Roy, Khalid Oublal +4
The rise of Artificial Intelligence as a Service (AIaaS) democratizes access to pre-trained models via Application Programming Interfaces (APIs), but also raises a fundamental ques…
FedMVP: Federated Multimodal Visual Prompt Tuning for Vision-Language Models
Mainak Singha, Subhankar Roy, Sarthak Mehrotra +4
In federated learning, textual prompt tuning adapts Vision-Language Models (e.g., CLIP) by tuning lightweight input tokens (or prompts) on local client data, while keeping network…
Group-robust Machine Unlearning
Thomas De Min, Subhankar Roy, Stéphane Lathuilière +2
Machine unlearning is an emerging paradigm to remove the influence of specific training data (i.e., the forget set) from a model while preserving its knowledge of the rest of the d…
Organizing Unstructured Image Collections using Natural Language
Mingxuan Liu, Zhun Zhong, Jun Li +3
In this work, we introduce and study the novel task of Open-ended Semantic Multiple Clustering (OpenSMC). Given a large, unstructured image collection, the goal is to automatically…
Unlearning Personal Data from a Single Image
Thomas De Min, Massimiliano Mancini, Stéphane Lathuilière +2
Machine unlearning aims to erase data from a model as if the latter never saw them during training. While existing approaches unlearn information from complete or partial access to…
Democratizing Fine-grained Visual Recognition with Large Language Models
Mingxuan Liu, Subhankar Roy, Wenjing Li +3
Identifying subordinate-level categories from images is a longstanding task in computer vision and is referred to as fine-grained visual recognition (FGVR). It has tremendous signi…
Collaborating Foundation Models for Domain Generalized Semantic Segmentation
Yasser Benigmim, Subhankar Roy, Slim Essid +2
Domain Generalized Semantic Segmentation (DGSS) deals with training a model on a labeled source domain with the aim of generalizing to unseen domains during inference. Existing DGS…
Weighted Ensemble Models Are Strong Continual Learners
Imad Eddine Marouf, Subhankar Roy, Enzo Tartaglione +1
In this work, we study the problem of continual learning (CL) where the goal is to learn a model on a sequence of tasks, such that the data from the previous tasks becomes unavaila…
Enhancing Plasticity for First Session Adaptation Continual Learning
Imad Eddine Marouf, Subhankar Roy, Stéphane Lathuilière +1
The integration of large pre-trained models (PTMs) into Class-Incremental Learning (CIL) has facilitated the development of computationally efficient strategies such as First-Sessi…
The Unreasonable Effectiveness of Large Language-Vision Models for Source-free Video Domain Adaptation
Giacomo Zara, Alessandro Conti, Subhankar Roy +3
Source-Free Video Unsupervised Domain Adaptation (SFVUDA) task consists in adapting an action recognition model, trained on a labelled source dataset, to an unlabelled target datas…
Contrast, Stylize and Adapt: Unsupervised Contrastive Learning Framework for Domain Adaptive Semantic Segmentation
Tianyu Li, Subhankar Roy, Huayi Zhou +2
To overcome the domain gap between synthetic and real-world datasets, unsupervised domain adaptation methods have been proposed for semantic segmentation. Majority of the previous…
RaSP: Relation-aware Semantic Prior for Weakly Supervised Incremental Segmentation
Subhankar Roy, Riccardo Volpi, Gabriela Csurka +1
Class-incremental semantic image segmentation assumes multiple model updates, each enriching the model to segment new categories. This is typically carried out by providing expensi…
AutoLabel: CLIP-based framework for Open-set Video Domain Adaptation
Giacomo Zara, Subhankar Roy, Paolo Rota +1
Open-set Unsupervised Video Domain Adaptation (OUVDA) deals with the task of adapting an action recognition model from a labelled source domain to an unlabelled target domain that…
One-shot Unsupervised Domain Adaptation with Personalized Diffusion Models
Yasser Benigmim, Subhankar Roy, Slim Essid +2
Adapting a segmentation model from a labeled source domain to a target domain, where a single unlabeled datum is available, is one the most challenging problems in domain adaptatio…
Large-scale Pre-trained Models are Surprisingly Strong in Incremental Novel Class Discovery
Mingxuan Liu, Subhankar Roy, Zhun Zhong +2
Discovering novel concepts in unlabelled datasets and in a continuous manner is an important desideratum of lifelong learners. In the literature such problems have been partially a…
Simplifying Open-Set Video Domain Adaptation with Contrastive Learning
Giacomo Zara, Victor Guilherme Turrisi da Costa, Subhankar Roy +2
In an effort to reduce annotation costs in action recognition, unsupervised video domain adaptation methods have been proposed that aim to adapt a predictive model from a labelled…
Cooperative Self-Training for Multi-Target Adaptive Semantic Segmentation
Yangsong Zhang, Subhankar Roy, Hongtao Lu +2
In this work we address multi-target domain adaptation (MTDA) in semantic segmentation, which consists in adapting a single model from an annotated source dataset to multiple unann…
Uncertainty-guided Source-free Domain Adaptation
Subhankar Roy, Martin Trapp, Andrea Pilzer +4
Source-free domain adaptation (SFDA) aims to adapt a classifier to an unlabelled target data set by only using a pre-trained source model. However, the absence of the source data a…