works on

From the 1 of 7 linked papers with an AI index.

activity
20242026
collaborators

7 papers

cs.RO2026

DiMaS: Distribution Matching for Steering Vision-Language-Action Models

Pegah Khayatan, Sara Meziane, Jayneel Parekh +1

The paper introduces DiMaS, a distribution‑matching steering technique that adjusts the internal representations of flow‑matching vision‑language‑action models to achieve fine‑grai…

cs.CV2026

When Prompts Override Vision: Prompt-Induced Hallucinations in LVLMs

Pegah Khayatan, Jayneel Parekh, Arnaud Dapogny +3

Despite impressive progress in capabilities of large vision-language models (LVLMs), these systems remain vulnerable to hallucinations, i.e., outputs that are not grounded in the v…

cs.LG2025

Learning to Steer: Input-dependent Steering for Multimodal LLMs

Jayneel Parekh, Pegah Khayatan, Mustafa Shukor +3

Steering has emerged as a practical approach to enable post-hoc guidance of LLMs towards enforcing a specific behavior. However, it remains largely underexplored for multimodal LLM…

cs.AI2025

Analyzing Finetuning Representation Shift for Multimodal LLMs Steering

Pegah Khayatan, Mustafa Shukor, Jayneel Parekh +2

Multimodal LLMs (MLLMs) have reached remarkable levels of proficiency in understanding multimodal inputs. However, understanding and interpreting the behavior of such complex model…

stat.ML2025

One Wave To Explain Them All: A Unifying Perspective On Feature Attribution

Gabriel Kasmi, Amandine Brunetto, Thomas Fel +1

Feature attribution methods aim to improve the transparency of deep neural networks by identifying the input features that influence a model's decision. Pixel-based heatmaps have b…

cs.CV2025

Restyling Unsupervised Concept Based Interpretable Networks with Generative Models

Jayneel Parekh, Quentin Bouniot, Pavlo Mozharovskyi +2

Developing inherently interpretable models for prediction has gained prominence in recent years. A subclass of these models, wherein the interpretable network relies on learning hi…