Nicolas Ballas

28 papers · 2013–2026 · 7 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

+11 more ↓

🗺️ Taxonomy Completionist (57) 🏃 Academic Marathon · Half 🌍 Conference Polyglot · Silver 🌉 Interdisciplinary Bridge · Silver 🐣 Hot Topic Early Bird

👥 Mega-Team · Squad 🌟 Keyword Trendsetter Combo (4) 🏆 Keyword Champion 🧭 Keyword Pioneer 👑 Triple Crown 🌈 Renaissance Researcher (6) 🔥 Unstoppable · Silver 🚀 Conference Pioneer 💎 Century Club · Bronze 📈 Trend Setter 🗃️ Keyword Collector (132)

Venues

ICML (7) ICLR (6) ICCV (5) CVPR (4) NeurIPS (3) ECCV (2) CLeaR (1)

Top co-authors

Michael Rabbat (8) Aaron Courville (7) Pascal Vincent (7) Yoshua Bengio (5) Mahmoud Assran (5) Mido Assran (5) Ishan Misra (4) Piotr Bojanowski (4) Stanisław Jastrzebski (3) Yann LeCun (3)

Research topics

Deep Learning (20) Machine Learning (20) Artificial Intelligence (10) Learning Types · Machine Learning (10) Learning Types · Deep Learning (9) Computer Vision (8) Architectures (8) Core AI (8) Optimization & Theory · Machine Learning (8) Techniques (6) Analysis (5) Models (5) Learning Paradigms (4) Core Methods (3) Optimization & Theory · Deep Learning (3)

Keywords

representation learning (4) self-supervised learning (4) stochastic gradient descent (3) image classification (3) multimodal learning (3) contrastive learning (2) distributed learning (2) out-of-distribution generalization (2) video prediction (2) attention mechanism (2) gossip algorithm (2) action recognition (1) few-shot learning (1) variational inference (1) adversarial robustness (1) generative modeling (1) vision transformer (1) semi-supervised learning (1) video generation (1) gradient-based optimization (1)

Papers

Inference-time Physics Alignment of Video Generative Models with Latent World Models CVPR 2026 LOCATE 3D: Real-World Object Localization via Self-Supervised Learning in 3D ICML 2025 Scaling Language-Free Visual Representation Learning ICCV 2025 VEDIT: Latent Prediction Architecture For Procedural Video Representation Learning ICLR 2025 Discovering Environments with XRM ICML 2024 Jack of All Tasks Master of Many: Designing General-Purpose Coarse-to-Fine Vision-Language Model CVPR 2024 Modeling Caption Diversity in Contrastive Vision-Language Pretraining ICML 2024 Stochastic positional embeddings improve masked image modeling ICML 2024 ImageNet-X: Understanding Model Mistakes with Factor of Variation Annotations ICLR 2023 Self-Supervised Learning From Images With a Joint-Embedding Predictive Architecture CVPR 2023 The hidden uniform cluster prior in self-supervised learning ICLR 2023 Masked Siamese Networks for Label-Efficient Learning ECCV 2022 Neural Attentive Circuits NeurIPS 2022 VIM: Variational Independent Modules for Video Prediction CLeaR 2022 Semi-Supervised Learning of Visual Features by Non-Parametrically Predicting View Assignments With Support Samples ICCV 2021 Proposal-based Video Completion ECCV 2020 SlowMo: Improving Communication-Efficient Distributed SGD with Slow Momentum ICLR 2020 Gossip-based Actor-Learner Architectures for Deep Reinforcement Learning NeurIPS 2019 Improved Conditional VRNNs for Video Prediction ICCV 2019 On the Relation Between the Sharpest Directions of DNN Loss and the SGD Step Length ICLR 2019 Stochastic Gradient Push for Distributed Deep Learning ICML 2019 Fast Approximate Natural Gradient Descent in a Kronecker Factored Eigenbasis NeurIPS 2018 Residual Connections Encourage Iterative Inference ICLR 2018 A Closer Look at Memorization in Deep Networks ICML 2017 A Dataset and Exploration of Models for Understanding Video Data Through Fill-In-The-Blank Question-Answering CVPR 2017 Dynamic Capacity Networks ICML 2016 Describing Videos by Exploiting Temporal Structure ICCV 2015 Space-Time Robust Representation for Action Recognition ICCV 2013