Sparse Autoencoders Learn Monosemantic Features in Vision-Language Models
Mateusz Pach, Shyamgopal Karthik, Quentin Bouniot, Serge Belongie, Zeynep Akata
NeurIPS, 2025
| CARVIEW |
Select Language
HTTP/2 301
server: GitHub.com
content-type: text/html
location: https://qbouniot.github.io/publications/
access-control-allow-origin: *
strict-transport-security: max-age=31556952
expires: Wed, 31 Dec 2025 01:13:37 GMT
cache-control: max-age=600
x-proxy-cache: MISS
x-github-request-id: A368:2DDCFF:A95FDE:BE7C84:69547667
accept-ranges: bytes
date: Wed, 31 Dec 2025 01:03:37 GMT
via: 1.1 varnish
age: 0
x-served-by: cache-bom-vanm7210036-BOM
x-cache: MISS
x-cache-hits: 0
x-timer: S1767143017.061786,VS0,VE203
vary: Accept-Encoding
x-fastly-request-id: e48b593cc93178204d3fd8f3642e49dd11ba3fe7
content-length: 162
HTTP/2 200
server: GitHub.com
content-type: text/html; charset=utf-8
last-modified: Fri, 03 Oct 2025 13:22:19 GMT
access-control-allow-origin: *
strict-transport-security: max-age=31556952
etag: W/"68dfce0b-3a50"
expires: Wed, 31 Dec 2025 01:13:37 GMT
cache-control: max-age=600
content-encoding: gzip
x-proxy-cache: MISS
x-github-request-id: 5316:318CF6:A8AED2:BDCC78:69547669
accept-ranges: bytes
age: 0
date: Wed, 31 Dec 2025 01:03:37 GMT
via: 1.1 varnish
x-served-by: cache-bom-vanm7210036-BOM
x-cache: MISS
x-cache-hits: 0
x-timer: S1767143017.278583,VS0,VE206
vary: Accept-Encoding
x-fastly-request-id: abd0525d9de0a9ce199f0102771548e0cd7e7c2b
content-length: 3935
Publications - Quentin Bouniot 
Quentin Bouniot
Post-Doctoral Researcher at TUM and Helmholtz Munich
- Munich, Germany
- Github
- Google Scholar
Publications
From Alexnet to Transformers: Measuring the Non-linearity of Deep Neural Networks with Affine Optimal Transport
Quentin Bouniot*, Ievgen Redko*, Anton Mallasto, Charlotte Laclau, Oliver Struckmeier, Karol Arndt, Markus Heinonen, Ville Kyrki, Samuel Kaski
CVPR, 2025
Restyling Unsupervised Concept Based Interpretable Networks with Generative Models Permalink
Jayneel Parekh*, Quentin Bouniot*, Pavlo Mozharovskyi, Alasdair Newson, Florence d'Alché-Buc
ICLR, 2025
Tailoring Mixup to Data for Calibration
Quentin Bouniot, Pavlo Mozharovskyi, Florence d'Alché-Buc
ICLR, 2025
Towards Few-Annotation Learning in Computer Vision: Application to Image Classification and Object Detection tasks
Quentin Bouniot
PhD Thesis, 2023
Proposal-Contrastive Pretraining for Object Detection from Fewer Data
Quentin Bouniot, Romaric Audigier, Angelique Loesch, Amaury Habrard
ICLR, 2023
Towards Few-Annotation Learning for Object Detection: Are Transformer-Based Models More Efficient?
Quentin Bouniot, Angélique Loesch, Romaric Audigier, Amaury Habrard
WACV, 2023
Improving Few-Shot Learning through Multi-task Representation Learning Theory
Quentin Bouniot, Ievgen Redko, Romaric Audigier, Angélique Loesch, Amaury Habrard
ECCV, 2022
Optimal Transport as a Defense Against Adversarial Attacks
Quentin Bouniot, Romaric Audigier, Angélique Loesch
ICPR, 2021
Vulnerability of Person Re-Identification Models to Metric Adversarial Attacks.
Quentin Bouniot, Romaric Audigier, Angélique Loesch
CVPRW, 2020