Stefan Lee

Calibrating MLLM-as-a-judge via Multimodal Bayesian Prompt Ensembles ICCV 2025 Harnessing Input-Adaptive Inference for Efficient VLN ICCV 2025 Hijacking Vision-and-Language Navigation Agents with Adversarial Environmental Attacks WACV 2025 Do Visual Imaginations Improve Vision-and-Language Navigation Agents? CVPR 2025 Non-conflicting Energy Minimization in Reinforcement Learning based Robot Control CORL 2025 Viewpoint-Aware Visual Grounding in 3D Scenes CVPR 2024 Simple Masked Training Strategies Yield Control Policies That Are Robust to Sensor Failure CORL 2024 Language-Informed Beam Search Decoding for Multilingual Machine Translation ACL 2024 Benchmarking Out-of-Distribution Detection in Visual Question Answering WACV 2024 FairDeDup: Detecting and Mitigating Vision-Language Fairness Disparities in Semantic Dataset Deduplication CVPR 2024 Navigating to Objects Specified by Images ICCV 2023 Emergence of Maps in the Memories of Blind Navigation Agents ICLR 2023 VLSlice: Interactive Vision-and-Language Slice Discovery ICCV 2023 Iterative Vision-and-Language Navigation CVPR 2023 Behavioral Analysis of Vision-and-Language Navigation Agents CVPR 2023 Sim-2-Sim Transfer for Vision-and-Language Navigation in Continuous Environments ECCV 2022 SOAT: A Scene- and Object-Aware Transformer for Vision-and-Language Navigation NIPS 2021 THDA: Treasure Hunt Data Augmentation for Semantic Navigation ICCV 2021 Improving Multilingual Translation by Representation and Gradient Regularization EMNLP 2021 Semantic MapNet: Building Allocentric Semantic Maps and Representations from Egocentric Views AAAI 2021 Waypoint Models for Instruction-Guided Navigation in Continuous Environments ICCV 2021 DeepAveragers: Offline Reinforcement Learning By Solving Derived Non-Parametric MDPs ICLR 2021 Auxiliary Tasks for Efficient Learning of Point-Goal Navigation WACV 2021 Language-Conditioned Imitation Learning for Robot Manipulation Tasks NIPS 2020 DD-PPO: Learning Near-Perfect PointGoal Navigators from 2.5 Billion Frames ICLR 2020 Sim-to-Real Transfer for Vision-and-Language Navigation CORL 2020 Integrating Egocentric Localization for More Realistic Point-Goal Navigation Agents CORL 2020 12-in-1: Multi-Task Vision and Language Representation Learning CVPR 2020 Improving Vision-and-Language Navigation with Image-Text Pairs from the Web ECCV 2020 Beyond the Nav-Graph: Vision-and-Language Navigation in Continuous Environments ECCV 2020 Where Are You? Localization from Embodied Dialog EMNLP 2020 On the Sub-layer Functionalities of Transformer Decoder EMNLP 2020 Dialog without Dialog Data: Learning Visual Dialog Agents from VQA Data NIPS 2020 Chasing Ghosts: Instruction Following as Bayesian State Tracking NIPS 2019 ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks NIPS 2019 Audio Visual Scene-Aware Dialog CVPR 2019 Probabilistic Neural Symbolic Models for Interpretable Visual Question Answering ICML 2019 Trainable Decoding of Sets of Sequences for Neural Sequence Models ICML 2019 Taking a HINT: Leveraging Explanations to Make Vision and Language Models More Grounded ICCV 2019 nocaps: novel object captioning at scale ICCV 2019 Embodied Question Answering in Photorealistic Environments With Point Cloud Perception CVPR 2019 Counterfactual Visual Explanations ICML 2019 Proceedings of the Second Workshop on Shortcomings in Vision and Language NAACL 2019 Sunny and Dark Outside?! Improving Answer Consistency in VQA through Entailed Question Generation IJCNLP 2019 Sunny and Dark Outside?! Improving Answer Consistency in VQA through Entailed Question Generation EMNLP 2019 Neural Modular Control for Embodied Question Answering CORL 2018 Visual Curiosity: Learning to Ask Questions to Learn Visual Recognition CORL 2018 Choose Your Neuron: Incorporating Domain Knowledge through Neuron-Importance ECCV 2018 Graph R-CNN for Scene Graph Generation ECCV 2018 Embodied Question Answering CVPR 2018 Learn from Your Neighbor: Learning Multi-modal Mappings from Sparse Annotations ICML 2018 Overcoming Language Priors in Visual Question Answering with Adversarial Regularization NIPS 2018 Natural Language Does Not Emerge ‘Naturally’ in Multi-Agent Dialog EMNLP 2017 The Promise of Premise: Harnessing Question Premises in Visual Question Answering EMNLP 2017 Bidirectional Beam Search: Forward-Backward Inference in Neural Sequence Models for Fill-In-The-Blank Image Captioning CVPR 2017 Learning Cooperative Visual Dialog Agents With Deep Reinforcement Learning ICCV 2017 Stochastic Multiple Choice Learning for Training Diverse Deep Ensembles NIPS 2016 Lending A Hand: Detecting Hands and Recognizing Activities in Complex Egocentric Interactions ICCV 2015