PL
Patrick Labatut
cs.CVcs.LGcs.AIq-bio.NCcs.CLcs.PLcs.RO
On Valency
published · living versionsW_attss5wh·v1 · currentpublished
AutoParallel: Composable, PyTorch-Native Automatic Parallelism for Production Training
with Kaijian Wang, Sanket Purandare, Aditya Venkataraman, Will Constable +7
1 version
Preprints & journals
22 papers in the corpus · 2012–2026Misalignment Between Backpropagation and the Hierarchy of Brain Responses to Images2605.28693v1 · Jos'ephine Raugel, Maximilian Seitzer, Marc Szafraniec et al.2026 · 0 citationsarXiv
VGGT-2605.15195v2 · Jianyuan Wang, Minghao Chen, Shangzhan Zhang et al.2026 · 0 citationsarXiv
AdaDINO: Context-Adaptive DINO-Distilled Vision Foundation Models for Efficient Open-Vocabulary Edge Inference2604.15622v3 · Yiwei Zhao, Yi Zheng, Huapeng Su et al.2026 · 0 citationsarXiv
Efficient Universal Perception Encoder2603.22387v2 · Chenchen Zhu, Saksham Suri, Cijo Jose et al.2026 · 0 citationsarXiv
CHMv2: Improvements in Global Canopy Height Mapping using DINOv32603.06382v1 · John Brandt, Seungeun Yi, Jamie Tolan et al.2026 · 3 citationsarXiv
Disentangling the Factors of Convergence between Brains and Computer Vision Models2508.18226v1 · Jos'ephine Raugel, Marc Szafraniec, Huy V. Vo et al.2025 · 0 citationsarXiv
DINOv32508.10104v1 · Oriane Sim'eoni, Huy V. Vo, Maximilian Seitzer et al.2025 · 41 citationsarXiv
Back to the Features: DINO as a Foundation for Video World Models2507.19468v1 · Federico Baldassarre, Marc Szafraniec, Basile Terver et al.2025 · 0 citationsarXiv
V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning2506.09985v1 · Mido Assran, Adrien Bardes, David Fan et al.2025 · 8 citationsarXiv
Accelerating Transformer Inference and Training with 2:4 Activation Sparsity2503.16672v1 · Daniel Haziza, Timothy Chou, Dhruv Choudhary et al.2025 · 0 citationsarXiv
DINOv2 Meets Text: A Unified Framework for Image- and Pixel-Level Vision-Language Alignment2412.16334v1 · Cijo Jose, Th'eo Moutakanni, Dahyun Kang et al.2024 · 49 citationsarXiv
Automatic Data Curation for Self-Supervised Learning: A Clustering-Based Approach2405.15613v2 · Huy V. Vo, Vasil Khalidov, Timoth'ee Darcet et al.2024 · 6 citationsarXiv
DINOv2: Learning Robust Visual Features without Supervision2304.07193v2 · Maxime Oquab, Timoth'ee Darcet, Th'eo Moutakanni et al.2023 · 1,077 citationsarXiv
Code Translation with Compiler Representations2207.03578v5 · Marc Szafraniec, Baptiste Roziere, Hugh Leather et al.2022 · 26 citationsarXiv
Common Objects in 3D: Large-Scale Learning and Evaluation of Real-life 3D Category Reconstruction2109.00512v1 · Jeremy Reizenstein, Roman Shapovalov, Philipp Henzler et al.2021 · 353 citationsInternational Conference on Computer Vision, 2021
DensePose 3D: Lifting Canonical Surface Maps of Articulated Objects to the Third Dimension2109.00033v1 · Roman Shapovalov, David Novotny, Benjamin Graham et al.2021 · 6 citationsarXiv
NeuroMorph: Unsupervised Shape Interpolation and Correspondence in One Go2106.09431v1 · Marvin Eisenberger, David Novotny, Gael Kerchenbaum et al.2021 · 73 citationsarXiv
Discovering Relationships between Object Categories via Universal Canonical Maps2106.09758v1 · Natalia Neverova, Artsiom Sanakoyeu, Patrick Labatut et al.2021 · 16 citationsarXiv
Unsupervised Learning of 3D Object Categories from Videos in the Wild2103.16552v1 · Philipp Henzler, Jeremy Reizenstein, Patrick Labatut et al.2021 · 0 citationsarXiv
Low Bandwidth Video-Chat Compression using Deep Generative Models2012.00328v1 · Maxime Oquab, Pierre Stock, Oran Gafni et al.2020 · 46 citationsarXiv
Continuous Surface Embeddings2011.12438v1 · Natalia Neverova, David Novotny, Vasil Khalidov et al.2020 · 51 citationsarXiv
High accuracy and visibility-consistent dense multiview stereo.21844631 · Vu, Hoang-Hiep, Labatut, Patrick, Pons, Jean-Philippe et al.2012 · 284 citationsIEEE transactions on pattern analysis and machine intelligence. 2012;34(5):889-901
Career total: 43 works. 22 are in this corpus.
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.