Cover Image

SEM: Sparse Embedding Modulation for Post-Hoc Debiasing of Vision-Language Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Guimard, Quentin, Bartsch, Federico, Caldarella, Simone, Aljundi, Rahaf, Ricci, Elisa, Mancini, Massimiliano
Format:	Preprint
Published:	2026
Subjects:	Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

The Phantom Menace: Unmasking Privacy Leakages in Vision-Language Models
by: Caldarella, Simone, et al.
Published: (2024)

Incremental Object-Based Novelty Detection with Feedback Loop
by: Caldarella, Simone, et al.
Published: (2023)

Classifier-to-Bias: Toward Unsupervised Automatic Bias Detection for Visual Classifiers
by: Guimard, Quentin, et al.
Published: (2025)

Ego: Embedding-Guided Personalization of Vision-Language Models
by: Seifi, Soroush, et al.
Published: (2026)

Online In-Context Distillation for Low-Resource Vision Language Models
by: Kang, Zhiqi, et al.
Published: (2025)

Rethinking Few-Shot Adaptation of Vision-Language Models in Two Stages
by: Farina, Matteo, et al.
Published: (2025)

Frustratingly Easy Test-Time Adaptation of Vision-Language Models
by: Farina, Matteo, et al.
Published: (2024)

Not Only Text: Exploring Compositionality of Visual Representations in Vision-Language Models
by: Berasi, Davide, et al.
Published: (2025)

Annotation Free Semantic Segmentation with Vision Foundation Models
by: Seifi, Soroush, et al.
Published: (2024)

Efficient Few-Shot Continual Learning in Vision-Language Models
by: Panos, Aristeidis, et al.
Published: (2025)

MULTIFLOW: Shifting Towards Task-Agnostic Vision-Language Pruning
by: Farina, Matteo, et al.
Published: (2024)

Personalization Toolkit: Training Free Personalization of Large Vision Language Models
by: Seifi, Soroush, et al.
Published: (2025)

Harnessing Large Language Models for Training-free Video Anomaly Detection
by: Zanella, Luca, et al.
Published: (2024)

Imperfect Vision Encoders: Efficient and Robust Tuning for Vision-Language Models
by: Panos, Aristeidis, et al.
Published: (2024)

ProactiveBench: Benchmarking Proactiveness in Multimodal Large Language Models
by: De Min, Thomas, et al.
Published: (2026)

Large Multimodal Models as General In-Context Classifiers
by: Garosi, Marco, et al.
Published: (2026)

Overcoming Generic Knowledge Loss with Selective Parameter Update
by: Zhang, Wenxuan, et al.
Published: (2023)

Can Text-to-Video Generation help Video-Language Alignment?
by: Zanella, Luca, et al.
Published: (2025)

One VLM to Keep it Learning: Generation and Balancing for Data-free Continual Visual Question Answering
by: Das, Deepayan, et al.
Published: (2024)

Training-Free Personalization via Retrieval and Reasoning on Fingerprints
by: Das, Deepayan, et al.
Published: (2025)

Compositional Caching for Training-free Open-vocabulary Attribute Detection
by: Garosi, Marco, et al.
Published: (2025)

Training-free Online Video Step Grounding
by: Zanella, Luca, et al.
Published: (2025)

On Large Multimodal Models as Open-World Image Classifiers
by: Conti, Alessandro, et al.
Published: (2025)

Test-time Vocabulary Adaptation for Language-driven Object Detection
by: Liu, Mingxuan, et al.
Published: (2025)

Recurrent Attention-based Token Selection for Efficient Streaming Video-LLMs
by: Dorovatas, Vaggelis, et al.
Published: (2025)

Evaluating the Impact of Post-Training Quantization on Reliable VQA with Multimodal LLMs
by: Kurz, Paul Jonas, et al.
Published: (2026)

Unlearning Personal Data from a Single Image
by: De Min, Thomas, et al.
Published: (2024)

Vision-by-Language for Training-Free Compositional Image Retrieval
by: Karthik, Shyamgopal, et al.
Published: (2023)

Vocabulary-free Image Classification and Semantic Segmentation
by: Conti, Alessandro, et al.
Published: (2024)

Vocabulary-free Image Classification
by: Conti, Alessandro, et al.
Published: (2023)

On Background Bias of Post-Hoc Concept Embeddings in Computer Vision DNNs
by: Schwalbe, Gesina, et al.
Published: (2025)

From Weights to Concepts: Data-Free Interpretability of CLIP via Singular Vector Decomposition
by: Gentile, Francesco, et al.
Published: (2026)

Less is more: Summarizing Patch Tokens for efficient Multi-Label Class-Incremental Learning
by: De Min, Thomas, et al.
Published: (2024)

First Session Adaptation: A Strong Replay-Free Baseline for Class-Incremental Learning
by: Panos, Aristeidis, et al.
Published: (2023)

BendVLM: Test-Time Debiasing of Vision-Language Embeddings
by: Gerych, Walter, et al.
Published: (2024)

Training-Free Semantic Multi-Object Tracking with Vision-Language Models
by: Bonat, Laurence, et al.
Published: (2026)

Attention Debiasing for Token Pruning in Vision Language Models
by: Zhao, Kai, et al.
Published: (2025)

Memo: Training Memory-Efficient Embodied Agents with Reinforcement Learning
by: Gupta, Gunshi, et al.
Published: (2025)

Conceptualizing Embeddings: Sparse Disentanglement for Vision-Language Models
by: Kubaty, Piotr, et al.
Published: (2026)

Debiased Prompt Tuning in Vision-Language Model without Annotations
by: Jiang, Chaoquan, et al.
Published: (2025)