collaborators

6 papers

cs.LG2026

Perturb and Recover: Fine-tuning for Effective Backdoor Removal from CLIP

Naman Deep Singh, Francesco Croce, Matthias Hein

Vision-Language models like CLIP have been shown to be highly effective at linking visual perception and natural language understanding, enabling sophisticated image-text capabilit…

cs.CV2026

On the Adversarial Robustness of Discrete Image Tokenizers

Rishika Bhagwatkar, Irina Rish, Nicolas Flammarion +1

Discrete image tokenizers encode visual inputs as sequences of tokens from a finite vocabulary and are gaining popularity in multimodal systems, including encoder-only, encoder-dec…

cs.LG2026

On the Out-of-Distribution Generalization of Reasoning in Multimodal LLMs for Simple Visual Planning Tasks

Yannic Neuhaus, Nicolas Flammarion, Matthias Hein +1

Integrating reasoning in large language models and large vision-language models has recently led to significant improvement of their capabilities. However, the generalization of re…

cs.LG2025

Unlearning That Lasts: Utility-Preserving, Robust, and Almost Irreversible Forgetting in LLMs

Naman Deep Singh, Maximilian Müller, Francesco Croce +1

Unlearning in large language models (LLMs) involves precisely removing specific information from a pre-trained model. This is crucial to ensure safety of LLMs by deleting private d…

cs.CV2025

FuseLIP: Multimodal Embeddings via Early Fusion of Discrete Tokens

Christian Schlarmann, Francesco Croce, Nicolas Flammarion +1

Contrastive language-image pre-training aligns features of text-image pairs in a common latent space via distinct encoders for each modality. While this approach achieves impressiv…

cs.CV2025

Adversarially Robust CLIP Models Can Induce Better (Robust) Perceptual Metrics

Francesco Croce, Christian Schlarmann, Naman Deep Singh +1

Measuring perceptual similarity is a key tool in computer vision. In recent years perceptual metrics based on features extracted from neural networks with large and diverse trainin…