PP
Patrick Pérez
cs.CVcs.LGcs.AIcs.ROstat.MLcs.CLcs.GRAlgorithmscs.SDeess.AS
On Valency
published · living versionsW_4tf2r79f·v1 · currentpublished
Rethinking Neural Thickets Without Weight Perturbations
with Nicolas Dufour, Elouan Gardès, Amil Dravid, Loic Landrieu
1 version
W_ssnhu7t7·v1published
Preprints & journals
129 papers in the corpus · 1998–2026Rethinking Video Autoencoders for Interactive World Models2610.30129v1 · Adrien Ramanana Rahary, Yutong Bai, Nicolas Dufour et al.2026 · 0 citationsarXivon Valency
Diffusable Latents from Structure-Agnostic Distillation2609.39657v1 · Adrien Ramanana Rahary, Nicolas Dufour, Patrick P'erez et al.2026 · 0 citationsarXiv
Multiplayer Interactive World Models with Representation Autoencoders2607.05352v2 · Anthony Hu, V'aclav Volhejn, Adrien Ramanana Rahary et al.2026 · 0 citationsarXiv
The FID Lottery: Quantifying Hidden Randomness in Generative-Model Evaluation2606.20536v1 · Nicolas Dufour, Alexei A. Efros, Patrick P'erez2026 · 0 citationsarXiv
Understanding Data Temporality Impact on Large Language Models Pre-training2605.22769v2 · Hippolyte Pilchen, Romain Fabre, Franck Signe Talla et al.2026 · 0 citationsarXiv
One View Is Enough: In-the-Wild Monocular Pretraining for Novel View Generation2603.23488v3 · Adrien Ramanana Rahary, Nicolas Dufour, Patrick Perez et al.2026 · 0 citationsarXiv
CASA: Cross-Attention over Self-Attention for Efficient Vision-Language Fusion2512.19535v2 · Moritz Bohle, Am'elie Royer, Juliette Marrie et al.2025 · 0 citationsarXiv
ARC-Encoder: learning compressed text representations for large language models2510.20535v2 · Hippolyte Pilchen, Edouard Grave, Patrick P'erez2025 · 0 citationsTransactions on Machine Learning Research 2026 (https://openreview.net/forum?id=lU1P9dsqfn)
Streaming Sequence-to-Sequence Learning with Delayed Streams Modeling2509.08753v2 · Neil Zeghidour, Eugene Kharitonov, Manu Orsini et al.2025 · 1 citationarXiv
Multiple Choice Learning of Low-Rank Adapters for Language Modeling2507.10419v3 · Victor Letzelter, Hugo Malard, Mathieu Fontaine et al.2025 · 0 citationsarXiv
Vision-Speech Models: Teaching Speech Models to Converse about Images2503.15633v1 · Am'elie Royer, Moritz Bohle, Gabriel de Marmiesse et al.2025 · 0 citationsarXiv
High-Fidelity Simultaneous Speech-To-Speech Translation2502.03382v2 · Tom Labiausse, Laurent Mazar'e, Edouard Grave et al.2025 · 0 citationsarXiv
Domain Adaptation with a Single Vision-Language Embedding2410.21361v2 · Mohammad Fahes, Tuan-Hung Vu, Andrei Bursuc et al.2024 · 0 citationsarXiv
CLIP's Visual Embedding Projector is a Few-shot Cornucopia2410.05270v4 · Mohammad Fahes, Tuan-Hung Vu, Andrei Bursuc et al.2024 · 1 citationarXiv
Moshi: a speech-text foundation model for real-time dialogue2410.00037v2 · Alexandre D'efossez, Laurent Mazar'e, Manu Orsini et al.2024 · 9 citationsarXiv
Winner-takes-all learners are geometry-aware conditional density estimators2406.04706v1 · Victor Letzelter, David Perera, C'edric Rommel et al.2024 · 0 citationsarXiv
OccFeat: Self-supervised Occupancy Feature Prediction for Pretraining BEV Segmentation Networks2404.14027v3 · Sophia Sirko-Galouchenko, Alexandre Boulch, Spyros Gidaris et al.2024 · 14 citationsarXiv
POP-3D: Open-Vocabulary 3D Occupancy Prediction from Images2401.09413v1 · Antonin Vobecky, Oriane Sim'eoni, David Hurych et al.2024 · 8 citationsarXiv
Manipulating Trajectory Prediction with Backdoors2312.13863v2 · Kaouther Messaoud, Kathrin Grosse, Mickael Chen et al.2023 · 2 citationsarXiv
CLIP-DINOiser: Teaching CLIP a few DINO tricks for open-vocabulary semantic segmentation2312.12359v2 · Monika Wysocza'nska, Oriane Sim'eoni, Michael Ramamonjisoa et al.2023 · 40 citationsarXiv
Reliability in Semantic Segmentation: Can We Use Synthetic Data?2312.09231v2 · Thibaut Loiseau, Tuan-Hung Vu, Mickael Chen et al.2023 · 18 citationsarXiv
Regularizing Self-supervised 3D Scene Flows with Surface Awareness and Cyclic Consistency2312.08879v3 · Patrik Vacek, David Hurych, Karel Zimmermann et al.2023 · 0 citationsarXiv
ManiPose: Manifold-Constrained Multi-Hypothesis 3D Human Pose Estimation2312.06386v2 · C'edric Rommel, Victor Letzelter, Nermin Samet et al.2023 · 4 citationsarXiv
PointBeV: A Sparse Approach to BeV Predictions2312.00703v2 · Loick Chambon, Eloi Zablocki, Mickael Chen et al.2023 · 24 citationsarXiv
A Simple Recipe for Language-guided Domain Generalized Segmentation2311.17922v2 · Mohammad Fahes, Tuan-Hung Vu, Andrei Bursuc et al.2023 · 26 citationsarXiv
ToddlerDiffusion: Interactive Structured Image Generation with Cascaded Schrödinger Bridge2311.14542v2 · Eslam Abdelrahman, Liangbing Zhao, Vincent Tao Hu et al.2023 · 1 citationarXiv
Resilient Multiple Choice Learning: A learned scoring scheme with application to audio scene analysis2311.01052v2 · Victor Letzelter, Mathieu Fontaine, Mickael Chen et al.2023 · 2 citationsAdvances in neural information processing systems, Dec 2023, New Orleans, United States
Three Pillars improving Vision Foundation Model Distillation for Lidar2310.17504v2 · Gilles Puy, Spyros Gidaris, Alexandre Boulch et al.2023 · 24 citationsarXiv
Unsupervised Object Localization in the Era of Self-Supervised ViTs: A Survey2310.12904v3 · Oriane Sim'eoni, 'Eloi Zablocki, Spyros Gidaris et al.2023 · 11 citationsarXiv
Decaf: Monocular Deformation Capture for Face and Hand Interactions2309.16670v2 · Soshi Shimada, Vladislav Golyanik, Patrick P'erez et al.2023 · 13 citationsarXiv
T-UDA: Temporal Unsupervised Domain Adaptation in Sequential Point Clouds2309.08302v1 · Awet Haileslassie Gebrehiwot, David Hurych, Karel Zimmermann et al.2023 · 5 citationsarXiv
DiffHPE: Robust, Coherent 3D Human Pose Lifting with Diffusion2309.01575v1 · C'edric Rommel, Eduardo Valle, Mickael Chen et al.2023 · 17 citationsarXiv
MOCA: Self-supervised Representation Learning by Predicting Masked Online Codebook Assignments2307.09361v2 · Spyros Gidaris, Andrei Bursuc, Oriane Simeoni et al.2023 · 1 citationarXiv
Butterfly factorization by algorithmic identification of rank-one blocks2307.00820v1 · L'eon Zheng (OCKHAM), Gilles Puy, Elisa Riccietti (OCKHAM) et al.2023 · 0 citationsarXiv
Towards Motion Forecasting with Real-World Perception Inputs: Are End-to-End Approaches Competitive?2306.09281v4 · Yihong Xu, Loick Chambon, 'Eloi Zablocki et al.2023 · 17 citationsarXiv
Diverse Probabilistic Trajectory Forecasting with Admissibility Constraints2302.03462v1 · Laura Calem, Hedi Ben-Younes, Patrick P'erez et al.2023 · 3 citationsInternational Conference on Pattern Recognition (ICPR) 2022
Cross-Modal Learning for Domain Adaptation in 3D Semantic Segmentation.35298372 · Jaritz, Maximilian, Vu, Tuan-Hung, de Charette, Raoul et al.2023 · 73 citationsIEEE transactions on pattern analysis and machine intelligence. 2023;45(2):1533-1544
Unsupervised Object Localization: Observing the Background to Discover Objects2212.07834v2 · Oriane Sim'eoni, Chlo'e Sekkat, Gilles Puy et al.2022 · 74 citationsarXiv
PØDA: Prompt-driven Zero-shot Domain Adaptation2212.03241v3 · Mohammad Fahes, Tuan-Hung Vu, Andrei Bursuc et al.2022 · 1 citationarXiv
OCTET: Object-aware Counterfactual Explanations2211.12380v2 · Mehdi Zemni, Mickael Chen, 'Eloi Zablocki et al.2022 · 38 citationsarXiv
Confidence Estimation via Auxiliary Models.34086561 · Corbiere, Charles, Thome, Nicolas, Saporta, Antoine et al.2022 · 56 citationsIEEE transactions on pattern analysis and machine intelligence. 2022;44(10):6043-6055
Take One Gram of Neural Features, Get Enhanced Group Robustness2208.12625v2 · Simon Roburin, Charles Corbiere, Gilles Puy et al.2022 · 0 citationsarXiv
Self-supervised learning with rotation-invariant kernels2208.00789v4 · L'eon Zheng (DANTE), Gilles Puy, Elisa Riccietti (DANTE) et al.2022 · 1 citationThe Eleventh International Conference on Learning Representations, May 2023, Kigali, Rwanda
Active Learning Strategies for Weakly-supervised Object Detection2207.12112v1 · Huy V. Vo, Oriane Sim'eoni, Spyros Gidaris et al.2022 · 24 citationsarXiv
Teachers in concordance for pseudo-labeling of 3D sequential data2207.06079v2 · Awet Haileslassie Gebrehiwot, Patrik Vacek, David Hurych et al.2022 · 8 citationsin IEEE Robotics and Automation Letters, vol. 8, no. 2, pp. 536-543, Feb. 2023
LaRa: Latents and Rays for Multi-Camera Bird's-Eye-View Semantic Segmentation2206.13294v2 · Florent Bartoccioni, 'Eloi Zablocki, Andrei Bursuc et al.2022 · 17 citationsCoRL 2022 https://openreview.net/forum?id=abd_D-iVjk0
HULC: 3D Human Motion Capture with Pose Manifold Sampling and Dense Contact Guidance2205.05677v4 · Soshi Shimada, Vladislav Golyanik, Zhi Li et al.2022 · 22 citationsarXiv
Multi-Head Distillation for Continual Unsupervised Domain Adaptation in Semantic Segmentation2204.11667v1 · Antoine Saporta, Arthur Douillard, Tuan-Hung Vu et al.2022 · 24 citationsarXiv
Drive&Segment: Unsupervised Semantic Segmentation of Urban Scenes via Cross-modal Distillation2203.11160v2 · Antonin Vobecky, David Hurych, Oriane Sim'eoni et al.2022 · 16 citationsarXiv
Raw High-Definition Radar for Multi-Task Learning2112.10646v3 · Julien Rebut, Arthur Ouaknine, Waqas Malik et al.2021 · 126 citationsCVPR2022
Career total: 467 works. 129 are in this corpus.Showing the 50 most recent.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.