Open source
Code & datasets
We are strong proponents of reproducible research and open source. Upcoming projects by the group are released at the RIPL GitHub.
Datasets
- Dataset AirSim-MAP — multi-agent perception dataset based on AirSim. No longer available; this dataset is defunct.
- Dataset PCB component detection — datasets from our WACV 2019 paper. Available here.
General frameworks
- Framework Continual learning framework — from our NeurIPS Continual Learning Workshop paper.
- Framework Learning with weaker pair-wise information
Code for publications
- ECCV 2026 FindingDory: A Benchmark to Evaluate Memory in Embodied Agents
- CVPR 2026 MAPS: Preserving Vision-Language Representations via Module-Wise Proximity Scheduling
- ICRA 2026 Sim2real Image Translation for Viewpoint-Robust Policies from Fixed-Camera Datasets
- CVPR 2025 FRAMES-VQA: Benchmarking Fine-Tuning Robustness across Multi-Modal Shifts in Visual Question Answering
- TMLR 2024 HePCo: Continual Adaptation of Vision Transformers for Federated Learning
- ECCV 2024 NeRF-MAE: Masked AutoEncoders for Self-Supervised 3D Representation Learning for Neural Radiance Fields
- CVPR 2024 Diffuse, Attend, and Segment: Unsupervised Zero-Shot Segmentation using Stable Diffusion
- CVPR 2024 Seeing the Unseen: Visual Common Sense for Semantic Placement
- CVPR 2024 GOAT-Bench: A Benchmark for Multi-modal Lifelong Navigation
- WACV 2023 Missing Modality Robustness in Semi-Supervised Multi-Modal Semantic Segmentation
- NeurIPS 2023 Fast Trainable Projection for Robust Fine-tuning
- NeurIPS 2023 DAMEX: Dataset-aware Mixture-of-Experts for visual understanding of mixture-of-datasets
- NeurIPS 2023 Training Energy-Based Normalizing Flow with Score-Matching Objectives
- CoRL 2023 HomeRobot: Open-Vocabulary Mobile Manipulation
- ICCV 2023 NeO 360: Neural Fields for Sparse View Synthesis of Outdoor Scenes
- CVPR 2023 Trainable Projected Gradient Method for Robust Fine-tuning
- CVPR 2023 CODA-Prompt: COntinual Decomposed Attention-based Prompting for Rehearsal-Free Continual Learning
- CVPR 2023 HAAV: Hierarchical Aggregation of Augmented Views for Image Captioning
- CVPR 2023 ConStruct-VL: Data-Free Continual Structured VL Concepts Learning
- ECCV 2022 ShAPO: Implicit Representations for Multi-Object Shape, Appearance, and Pose Optimization
- CVPR 2022 Beyond a Pre-Trained Object Detector: Cross-Modal Textual and Visual Context for Image Captioning
- CVPR 2022 Unbiased Teacher v2: Semi-supervised Object Detection for Anchor-free and Anchor-based Detectors
- ICRA 2022 Striking the Right Balance: Recall Loss for Semantic Segmentation
- ICRA 2022 CenterSnap: Single-Shot Multi-Object 3D Shape Reconstruction and Categorical 6D Pose and Size Estimation
- NeurIPS 2021 A Geometric Perspective towards Neural Calibration via Sensitivity Decomposition
- ICCV 2021 Always Be Dreaming: A New Approach for Data-Free Class-Incremental Learning
- IJCNN 2021 Memory-Efficient Semi-Supervised Continual Learning: The World is its Own Replay Buffer
- ICRA 2021 Hierarchical Cross-Modal Agent for Robotics Vision-and-Language Navigation
- ICRA 2021 LRGNet: Learnable Region Growing for Class-Agnostic Point Cloud Segmentation
- ICLR 2021 Unbiased Teacher for Semi-Supervised Object Detection
- NeurIPS 2020 Posterior Re-calibration for Imbalanced Datasets
- ECCV 2020 FeatMatch: Feature-Based Augmentation for Semi-Supervised Learning
- ECCV 2020 Learning to Generate Grounded Image Captions without Localization Supervision
- CVPR 2020 When2com: Multi-agent Perception via Communication Graph Grouping
- CVPR 2019 Action Segmentation with Joint Self-Supervised Temporal Domain Adaptation
- ICCV 2019 TA3N: Temporal Attentive Alignment for Video Domain Adaptation
- ICLR 2019 Self-Monitoring Navigation Agent via Auxiliary Progress Estimation
- CVPR 2019 The Regretful Agent: Heuristic-Aided Navigation through Progress Estimation
- ICLR 2019 A Closer Look at Few-shot Classification — few-shot learning framework, with VT (project page)
- Journal 2019 TS-LSTM and Temporal-Inception: Exploiting Spatiotemporal Dynamics for Activity Recognition
- NeurIPS-W 2018 Continual Learning Benchmark
- ICLR 2018 L2C: Neural network clustering and learning with pair-wise constraints (PyTorch)
- ICLR-W 2016 NNclustering: clustering with pairwise constraints (lua torch)
- DRAGAN How to Train Your DRAGAN — notebook example