Nicolas Thome

NAF: Zero-Shot Feature Upsampling via Neighborhood Attention Filtering CVPR 2026 DAFTED: Decoupled Asymmetric Fusion of Tabular and Echocardiographic Data for Cardiac Hypertension Diagnosis MIDL 2025 DIP: Unsupervised Dense In-Context Post-training of Visual Representations ICCV 2025 Reinforcement Learning for Aligning Large Language Models Agents with Interactive Environments: Quantifying and Mitigating Prompt Overfitting NAACL 2025 ViLU: Learning Vision-Language Uncertainties for Failure Prediction ICCV 2025 DiffCut: Catalyzing Zero-Shot Semantic Segmentation with Diffusion Features and Recursive Normalized Cut NeurIPS 2024 GalLop: Learning global and local prompts for vision-language models ECCV 2024 Supra-Laplacian Encoding for Transformer on Dynamic Graphs NeurIPS 2024 EAGLE: Large-scale Learning of Turbulent Fluid Dynamics with Mesh Transformers ICLR 2023 Full Contextual Attention for Multi-Resolution Transformers in Semantic Segmentation WACV 2023 Hybrid Energy Based Model in the Feature Space for Out-of-Distribution Detection ICML 2023 Complementing Brightness Constancy with Deep Networks for Optical Flow Prediction ECCV 2022 Hierarchical Average Precision Training for Pertinent Image Retrieval ECCV 2022 Augmenting Physical Models with Deep Networks for Complex Dynamics Forecasting ICLR 2021 Robust and Decomposable Average Precision for Image Retrieval NeurIPS 2021 Disentangling Physical Dynamics From Unknown Factors for Unsupervised Video Prediction CVPR 2020 Probabilistic Time Series Forecasting with Shape and Temporal Diversity NeurIPS 2020 Addressing Failure Prediction by Learning Model Confidence NeurIPS 2019 BLOCK: Bilinear Superdiagonal Fusion for Visual Question Answering and Visual Relationship Detection AAAI 2019 DiscoNet: Shapes Learning on Disconnected Manifolds for 3D Editing ICCV 2019 MUREL: Multimodal Relational Reasoning for Visual Question Answering CVPR 2019 Shape and Time Distortion Loss for Training Deep Time Series Forecasting Models NeurIPS 2019 HybridNet: Classification and Reconstruction Cooperation for Semi-Supervised Learning ECCV 2018 Manifold Learning in Quotient Spaces CVPR 2018 Revisiting Multi-Task Learning with ROCK: a Deep Residual Auxiliary Block for Visual Detection NeurIPS 2018 MUTAN: Multimodal Tucker Fusion for Visual Question Answering ICCV 2017 WILDCAT: Weakly Supervised Learning of Deep ConvNets for Image Classification, Pointwise Localization and Segmentation CVPR 2017 WELDON: Weakly Supervised Learning of Deep Convolutional Neural Networks CVPR 2016 MANTRA: Minimum Maximum Latent Structural SVM for Image Classification and Ranking ICCV 2015 Fantope Regularization in Metric Learning CVPR 2014 Dynamic Scene Classification: Learning Motion Descriptors with Slow Features Analysis CVPR 2013 JKernelMachines: A Simple Framework for Kernel Machines JMLR 2013 Quadruplet-Wise Image Similarity Learning ICCV 2013 Top-Down Regularization of Deep Belief Networks NeurIPS 2013