IA
Ismail Ben Ayed
cs.CVcs.LGAlgorithmsstat.MLcs.AIeess.IVNeural Networks, ComputerArtificial IntelligenceSubtraction TechniqueDeep learning
On Valency
published · living versionsW_bz3ycuq8·v1 · currentpublished
On the Few-Shot Adaptation of Vision-Language Models: A Few Gradient Signs Are All You Need
with Nairouz Mrabah, Mahdi S. Hosseini, Eric Granger
1 version
W_6a627jgb·v2published
Preprints & journals
197 papers in the corpus · 2005–2026Test-Time Generalized Category Discovery2609.33937v1 · Shambhavi Mishra, Omprakash Chakraborty, Julio Silva-Rodriguez et al.2026 · 0 citationsarXiv
PRiSM: Prototype Regularization for Few-Shot VLMs2607.17820v2 · Ghassen Baklouti, Omprakash Chakraborty, Jose Dolz et al.2026 · 0 citationsarXiv
Quantile Adaptive Temperature Scaling for Confidence Calibration2606.21749v2 · Omprakash Chakraborty, Leo Fillioux, Ismail Ben Ayed et al.2026 · 0 citationsarXiv
Are Online Skill and Memory Modules Always Worth Their Tokens? A Budget-Constrained Study of Web Agents2606.15017v2 · Sina Hajimiri, Masih Aminbeidokhti, Jose Dolz et al.2026 · 0 citationsarXiv
MolRGen: A Training and Evaluation Setting for De Novo Molecular Generation with Reasonning Models2603.18256v2 · Philippe Formont, Maxime Darrin, Ismail Ben Ayed et al.2026 · 0 citationsarXiv
Information Maximization for Long-Tailed Semi-Supervised Domain Generalization2603.08434v1 · Leo Fillioux, Omprakash Chakraborty, Quentin Gop'ee et al.2026 · 0 citationsarXiv
Locality-Attending Vision Transformer2603.04892v1 · Sina Hajimiri, Farzad Beizaee, Fereshteh Shakeri et al.2026 · 0 citationsarXiv
ORION: ORthonormal Text Encoding for Universal VLM AdaptatION2602.19530v2 · Omprakash Chakraborty, Jose Dolz, Ismail Ben Ayed2026 · 0 citationsProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2026
Histopath-C: Towards Realistic Domain Shifts for Histopathology Vision-Language Adaptation2601.12493v1 · Mehrdad Noori, Gustavo Adolfo Vargas Hakim, David Osowiechi et al.2026 · 1 citationarXiv
Class Adaptive Conformal Training2601.09522v1 · Badr-Eddine Marani, Julio Silva-Rodriguez, Ismail Ben Ayed et al.2026 · 0 citationsarXiv
SoC: Semantic Orthogonal Calibration for Test-Time Prompt Tuning2601.08617v1 · Leo Fillioux, Omprakash Chakraborty, Ismail Ben Ayed et al.2026 · 0 citationsCVPR 2026
Learning Task-Agnostic Representations through Multi-Teacher Distillation2510.18680v1 · Philippe Formont, Maxime Darrin, Banafsheh Karimian et al.2025 · 0 citationsAdvances in Neural Information Processing Systems 38 (NeurIPS 2025)
TRUST: Test-Time Refinement using Uncertainty-Guided SSM Traverses2509.22813v2 · Sahar Dastani, Ali Bahri, Gustavo Adolfo Vargas Hakim et al.2025 · 0 citationsarXiv
Purge-Gate: Backpropagation-Free Test-Time Adaptation for Point Clouds Classification via Token Purging2509.09785v1 · Moslem Yazdanpanah, Ali Bahri, Mehrdad Noori et al.2025 · 3 citationsarXiv
Deep Learning Models Connecting Images and Text: A Primer for Radiologists.40811083 · Wu, An Ni, Kulbay, Merve, Cheng, Phillip M et al.2025 · 7 citationsRadiographics : a review publication of the Radiological Society of North America, Inc. 2025;45(9):e240103
REFLECT: Rectified Flows for Efficient Brain Anomaly Correction Transport2508.02889v1 · Farzad Beizaee, Sina Hajimiri, Ismail Ben Ayed et al.2025 · 2 citationsarXiv
Regularized Low-Rank Adaptation for Few-Shot Organ Segmentation2507.15793v1 · Ghassen Baklouti, Julio Silva-Rodr'iguez, Jose Dolz et al.2025 · 3 citationsarXiv
ViLU: Learning Vision-Language Uncertainties for Failure Prediction2507.07620v4 · Marc Lafon, Yannis Karmim, Julio Silva-Rodr'iguez et al.2025 · 1 citationInternational Conference on Computer Vision, ICCV 2025
Few-Shot, Now for Real: Medical VLMs Adaptation without Balanced Sets or Validation2506.17500v1 · Julio Silva-Rodr'iguez, Fereshteh Shakeri, Houda Bahig et al.2025 · 1 citationarXiv
Trustworthy Few-Shot Transfer of Medical VLMs through Split Conformal Prediction2506.17503v1 · Julio Silva-Rodr'iguez, Ismail Ben Ayed, Jose Dolz2025 · 0 citationsarXiv
Full Conformal Adaptation of Medical Vision-Language Models2506.06076v1 · Julio Silva-Rodr'iguez, Leo Fillioux, Paul-Henry Cournede et al.2025 · 2 citationsarXiv
Vocabulary-free few-shot learning for Vision-Language Models2506.04005v1 · Maxime Zanella, Cl'ement Fuchs, Ismail Ben Ayed et al.2025 · 1 citationarXiv
Conformal Prediction for Zero-Shot Models2505.24693v1 · Julio Silva-Rodr'iguez, Ismail Ben Ayed, Jose Dolz2025 · 5 citationsarXiv
Test-Time Adaptation of Vision-Language Models for Open-Vocabulary Semantic Segmentation2505.21844v2 · Mehrdad Noori, David Osowiechi, Gustavo Adolfo Vargas Hakim et al.2025 · 1 citationarXiv
Recovering Fairness Directly from Modularity: a New Way for Fair Community Partitioning2505.22684v1 · Yufeng Wang, Yiguang Bai, Tianqing Zhu et al.2025 · 0 citationsarXiv
SMART-PC: Skeletal Model Adaptation for Robust Test-Time Training in Point Clouds2505.19546v1 · Ali Bahri, Moslem Yazdanpanah, Sahar Dastani et al.2025 · 0 citationsarXiv
Towards Foundation Models and Few-Shot Parameter-Efficient Fine-Tuning for Volumetric Organ Segmentation.40347917 · Silva-Rodríguez, Julio, Dolz, Jose, Ben Ayed, Ismail2025 · 11 citationsMedical image analysis. 2025;103:103596
Sparsity Outperforms Low-Rank Projections in Few-Shot Adaptation2504.12436v2 · Nairouz Mrabah, Nicolas Richet, Ismail Ben Ayed et al.2025 · 0 citationsarXiv
Analyzing the Impact of Low-Rank Adaptation for Cross-Domain Few-Shot Object Detection in Aerial Images2504.06330v1 · Hicham Talaoubrid, Anissa Mokraoui, Ismail Ben Ayed et al.2025 · 1 citationarXiv
A Reality Check of Vision-Language Pre-training in Radiology: Have We Progressed Using Text?2504.05227v1 · Julio Silva-Rodr'iguez, Jose Dolz, Ismail Ben Ayed2025 · 2 citationsarXiv
Spectral Informed Mamba for Robust Point Cloud Processing2503.04953v2 · Ali Bahri, Moslem Yazdanpanah, Mehrdad Noori et al.2025 · 14 citationsarXiv
Neighbor-aware calibration of segmentation networks with penalty-based constraints.39978014 · Murugesan, Balamurali, Adiga Vasudeva, Sukesh, Liu, Bingyuan et al.2025 · 6 citationsMedical image analysis. 2025;101:103501
Realistic Test-Time Adaptation of Vision-Language Models2501.03729v1 · Maxime Zanella, Cl'ement Fuchs, Christophe De Vleeschouwer et al.2025 · 5 citationsarXiv
UNEM: UNrolled Generalized EM for Transductive Few-Shot Learning2412.16739v2 · Long Zhou, Fereshteh Shakeri, Aymen Sadraoui et al.2024 · 2 citationsarXiv
Are foundation models for computer vision good conformal predictors?2412.06082v3 · Leo Fillioux, Julio Silva-Rodr'iguez, Ismail Ben Ayed et al.2024 · 0 citationsarXiv
Semantic Anchor Transport: Robust Test-Time Adaptation for Vision-Language Models2411.17002v3 · Shambhavi Mishra, Julio Silva-Rodriguez, Ismail Ben Ayed et al.2024 · 0 citationsarXiv
Test-Time Adaptation in Point Clouds: Leveraging Sampling Variation with Weight Averaging2411.01116v2 · Ali Bahri, Moslem Yazdanpanah, Mehrdad Noori et al.2024 · 4 citationsarXiv
A Foundation Language-Image Model of the Retina (FLAIR): encoding expert knowledge in text supervision.39418828 · Silva-Rodríguez, Julio, Chakor, Hadi, Kobbi, Riadh et al.2024 · 107 citationsMedical image analysis. 2025;99:103357
Few-shot Adaptation of Medical Vision-Language Models2409.03868v1 · Fereshteh Shakeri, Yunshi Huang, Julio Silva-Rodr'iguez et al.2024 · 25 citationsarXiv
Boosting Vision-Language Models for Histopathology Classification: Predict all at once2409.01883v1 · Maxime Zanella, Fereshteh Shakeri, Yunshi Huang et al.2024 · 7 citationsarXiv
Enhancing Remote Sensing Vision-Language Models for Zero-Shot Scene Classification2409.00698v2 · Karim El Khoury, Maxime Zanella, Benoit G'erin et al.2024 · 12 citationsarXiv
Robust Calibration of Large Vision-Language Adapters2407.13588v1 · Balamurali Murugesan, Julio Silva-Rodriguez, Ismail Ben Ayed et al.2024 · 11 citationsarXiv
FDS: Feedback-guided Domain Synthesis with Multi-Source Conditional Diffusion Models for Domain Generalization2407.03588v3 · Mehrdad Noori, Milad Cheraghalikhani, Ali Bahri et al.2024 · 3 citationsarXiv
WATT: Weight Average Test-Time Adaptation of CLIP2406.13875v2 · David Osowiechi, Mehrdad Noori, Gustavo Adolfo Vargas Hakim et al.2024 · 8 citationsarXiv
When is an Embedding Model More Promising than Another?2406.07640v2 · Maxime Darrin, Philippe Formont, Ismail Ben Ayed et al.2024 · 1 citationarXiv
Boosting Vision-Language Models with Transduction2406.01837v1 · Maxime Zanella, Benoit G'erin, Ismail Ben Ayed2024 · 11 citationsarXiv
Low-Rank Few-Shot Adaptation of Vision-Language Models2405.18541v2 · Maxime Zanella, Ismail Ben Ayed2024 · 93 citationsarXiv
GeoMask3D: Geometrically Informed Mask Selection for Self-Supervised Point Cloud Learning in 3D2405.12419v2 · Ali Bahri, Moslem Yazdanpanah, Mehrdad Noori et al.2024 · 0 citationsarXiv
On the test-time zero-shot generalization of vision-language models: Do we really need prompt learning?2405.02266v1 · Maxime Zanella, Ismail Ben Ayed2024 · 28 citationsarXiv
CLIPArTT: Adaptation of CLIP to New Domains at Test Time2405.00754v2 · Gustavo Adolfo Vargas Hakim, David Osowiechi, Mehrdad Noori et al.2024 · 1 citationarXiv
Career total: 357 works. 197 are in this corpus.Showing the 50 most recent.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.