Rob Fergus

BALROG: Benchmarking Agentic LLM and VLM Reasoning On Games ICLR 2025 Efficient Exploration and Discriminative World Model Learning with an Object-Centric Abstraction ICLR 2025 Training Language Models on Synthetic Edit Sequences Improves Code Synthesis ICLR 2025 Adaptive Retrieval and Scalable Indexing for k-NN Search with Cross-Encoders ICLR 2024 A Fresh Take on Stale Embeddings: Improving Dense Retriever Training with Corrector Networks ICML 2024 Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMs NeurIPS 2024 diff History for Neural Language Agents ICML 2024 USTAD: Unified Single-model Training Achieving Diverse Scores for Information Retrieval ICML 2024 Distilling Internet-Scale Vision-Language Models into Embodied Agents ICML 2023 Learning About Progress From Experts ICLR 2023 NetHack is Hard to Hack NeurIPS 2023 Reduce, Reuse, Recycle: Compositional Generation with Energy-Based Diffusion Models and MCMC ICML 2023 Teacher Guided Training: An Efficient Framework for Knowledge Transfer ICLR 2023 Learning to Navigate Wikipedia by Taking Random Walks NeurIPS 2022 Mastering Visual Continuous Control: Improved Data-Augmented Reinforcement Learning ICLR 2022 Automatic Data Augmentation for Generalization in Reinforcement Learning NeurIPS 2021 Decoupling Value and Policy for Generalization in Reinforcement Learning ICML 2021 Image Augmentation Is All You Need: Regularizing Deep Reinforcement Learning from Pixels ICLR 2021 Imitation by Predicting Observations ICML 2021 Improving Sample Efficiency in Model-Free Reinforcement Learning from Images AAAI 2021 Offline Reinforcement Learning with Fisher Divergence Critic Regularization ICML 2021 Reinforcement Learning with Prototypical Representations ICML 2021 Energy-based models for atomic-resolution protein conformations ICLR 2020 Fast Adaptation to New Environments via Policy-Dynamics Value Functions ICML 2020 Finding Generalizable Evidence by Learning to Convince Q&A Models EMNLP 2019 Hierarchical RL Using an Ensemble of Proprioceptive Periodic Policies ICLR 2019 Composable Planning with Attributes ICML 2018 Intrinsic Motivation and Automatic Curricula via Asymmetric Self-Play ICLR 2018 Learning by Asking Questions CVPR 2018 Modeling Others using Oneself in Multi-Agent Reinforcement Learning ICML 2018 Stochastic Video Generation with a Learned Prior ICML 2018 Learning Multiagent Communication with Backpropagation NeurIPS 2016 Learning Physical Intuition of Block Towers by Example ICML 2016 Learning Simple Algorithms from Examples ICML 2016 Beyond Frontal Faces: Improving Person Recognition Using Multiple Cues CVPR 2015 Deep Generative Image Models using a Laplacian Pyramid of Adversarial Networks NeurIPS 2015 End-to-End Integration of a Convolution Network, Deformable Parts Model and Non-Maximum Suppression CVPR 2015 End-To-End Memory Networks NeurIPS 2015 Improving Image Classification With Location Context ICCV 2015 Learning Spatiotemporal Features With 3D Convolutional Networks ICCV 2015 Predicting Depth, Surface Normals and Semantic Labels With a Common Multi-Scale Convolutional Architecture ICCV 2015 Web Scale Photo Hash Clustering on A Single Machine CVPR 2015 Depth Map Prediction from a Single Image using a Multi-Scale Deep Network NeurIPS 2014 Exploiting Linear Structure Within Convolutional Networks for Efficient Evaluation NeurIPS 2014 Learning to Discover Efficient Mathematical Identities NeurIPS 2014 Regularization of Neural Networks using DropConnect ICML 2013 Restoring an Image Taken through a Window Covered with Dirt or Rain ICCV 2013 A Hybrid Neural Network-Latent Topic Model AISTATS 2012 Facial Expression Transfer with Input-Output Temporal Restricted Boltzmann Machines NeurIPS 2011 Pose-Sensitive Embedding by Nonlinear NCA Regression NeurIPS 2010 Fast Image Deconvolution using Hyper-Laplacian Priors NeurIPS 2009 Semi-Supervised Learning in Gigantic Image Collections NeurIPS 2009 Spectral Hashing NeurIPS 2008 Object Recognition by Scene Alignment NeurIPS 2007