-
Jayneel Parekh
- Team: MLIA
Publications
- Jayneel Parekh, Pegah Khayatan, Mustafa Shukor, Arnaud Dapogny, Alasdair Newson, et al.. Learning to Steer: Input-dependent Steering for Multimodal LLMs. 39th Conference on Neural Information Processing Systems (NeurIPS 2025), Nov 2025, San Diego (CA), United States. ⟨hal-05462808⟩
- Pegah Khayatan, Mustafa Shukor, Jayneel Parekh, Arnaud Dapogny, Matthieu Cord. Analyzing Finetuning Representation Shift for Multimodal LLMs Steering. IEEE/CVF International Conference on Computer Vision (ICCV), Oct 2025, Honoloulu, Hawaii, United States. ⟨hal-05462785⟩
- Jayneel Parekh, Quentin Bouniot, Pavlo Mozharovskyi, Alasdair Newson, Florence d'Alché-Buc. Restyling Unsupervised Concept Based Interpretable Networks with Generative Models. The Thirteenth International Conference on Learning Representations (ICLR 2025), Apr 2025, Singapore, Singapore. ⟨hal-05271340⟩
- Gabriel Kasmi, Amandine Brunetto, Thomas Fel, Jayneel Parekh. One Wave to Explain Them All: A Unifying Perspective on Feature Attribution. Forty Second International Conference on Machine Learning, Jul 2025, Vancouver (BC), Canada. ⟨10.48550/arXiv.2410.01482⟩. ⟨hal-04843893v2⟩
- Jayneel Parekh, Pegah Khayatan, Mustafa Shukor, Alasdair Newson, Matthieu Cord. A Concept-Based Explainability Framework for Large Multimodal Models. Advances in Neural Information Processing Systems 37, Dec 2024, Vancouver, Canada. pp.135783-135818, ⟨10.52202/079017-4312⟩. ⟨hal-05462746⟩
