SL
Stefan Lee
cs.CVcs.CLcs.LGcs.AIcs.ROstat.MLcs.HCcs.CYcs.DBcs.NE
On Valency
published · living versionsW_hscwa8v6·v1 · currentpublished
Computer-Use Agents Gain Little Benefit from a World Model When Conditioned on Tutorials
with Anh Nguyen, Tianyi Xu, Phat Tran, Harry Yu +1
1 version
W_3x7wtfze·v1published
Preprints & journals
78 papers in the corpus · 2015–2026Attention-based Classification for Indirect Prompt Injection2610.28988v1 · Amelia Kawasaki, Stefan Lee2026 · 0 citationsarXivon Valency
Simultaneous Translation between Sign Languages2609.35608v1 · Zetian Wu, Bowen Xie, Stefan Lee et al.2026 · 0 citationsarXiv
Visuomotor Robotic Pruning in Planar Orchards Using Hybrid Reinforcement Learning2609.24906v1 · Abhinav Jain, Cindy Grimm, Stefan Lee2026 · 0 citationsarXiv
3D Point World Models: Point Completion Enables More Accurate Dynamics Learning2607.00148v2 · Skand Peri, Hung Nguyen, Chanho Kim et al.2026 · 0 citationsarXiv
Direct Translation between Sign Languages2605.20588v2 · Zetian Wu, Bowen Xie, Wuyang Meng et al.2026 · 0 citationsarXiv
Learning Hybrid-Control Policies for High-Precision In-Contact Manipulation Under Uncertainty2604.19677v1 · Hunter L. Brown, Geoffrey Hollinger, Stefan Lee2026 · 0 citationsarXiv
Grounding Vision and Language to 3D Masks for Long-Horizon Box Rearrangement2603.23676v1 · Ashish Malik, Caleb Lowe, Aayam Shrestha et al.2026 · 0 citationsarXiv
Humanoid Hanoi: Investigating Shared Whole-Body Control for Skill-Based Box Rearrangement2602.13850v4 · Minku Kim, Kuan-Chia Chen, Aayam Shrestha et al.2026 · 0 citationsarXiv
Language-conditioned world model improves policy generalization by reading environmental descriptions2511.22904v1 · Anh Nguyen, Stefan Lee2025 · 0 citationsarXiv
Geometry-Aware Losses for Structure-Preserving Text-to-Sign Language Generation2509.23011v1 · Zetian Wu, Tianshuo Zhou, Stefan Lee et al.2025 · 0 citationsarXiv
Calibrating MLLM-as-a-judge via Multimodal Bayesian Prompt Ensembles2509.08777v1 · Eric Slyman, Mehrab Tanjim, Kushal Kafle et al.2025 · 1 citationarXiv
Non-conflicting Energy Minimization in Reinforcement Learning based Robot Control2509.01765v1 · Skand Peri, Akhil Perincherry, Bikram Pandit et al.2025 · 0 citationsarXiv
Harnessing Input-Adaptive Inference for Efficient VLN2508.09262v1 · Dongwoo Kang, Akhil Perincherry, Zachary Coalson et al.2025 · 0 citationsarXiv
Learning to Prune Branches in Modern Tree-Fruit Orchards2507.23015v1 · Abhinav Jain, Cindy Grimm, Stefan Lee2025 · 1 citationarXiv
Towards Scalable Schema Mapping using Large Language Models2505.24716v1 · Christopher Buss, Mahdis Safari, Arash Termehchy et al.2025 · 6 citationsarXiv
Do Visual Imaginations Improve Vision-and-Language Navigation Agents?2503.16394v1 · Akhil Perincherry, Jacob Krantz, Stefan Lee2025 · 7 citationsarXiv
Graph Neural Network Based Action Ranking for Planning2412.04752v4 · Rajesh Mangannavar, Stefan Lee, Alan Fern et al.2024 · 0 citationsarXiv
Hijacking Vision-and-Language Navigation Agents with Adversarial Environmental Attacks2412.02795v1 · Zijiao Yang, Xiangxi Shi, Eric Slyman et al.2024 · 1 citationarXiv
You Never Know: Quantization Induces Inconsistent Biases in Vision-Language Foundation Models2410.20265v1 · Eric Slyman, Anirudh Kanneganti, Sanghyun Hong et al.2024 · 0 citationsarXiv
Language-Informed Beam Search Decoding for Multilingual Machine Translation2408.05738v1 · Yilin Yang, Stefan Lee, Prasad Tadepalli2024 · 1 citationarXiv
Point Cloud Models Improve Visual Robustness in Robotic Learners2404.18926v1 · Skand Peri, Iain Lee, Chanho Kim et al.2024 · 7 citationsarXiv
FairDeDup: Detecting and Mitigating Vision-Language Fairness Disparities in Semantic Dataset Deduplication2404.16123v1 · Eric Slyman, Stefan Lee, Scott Cohen et al.2024 · 5 citationsarXiv
VLSlice: Interactive Vision-and-Language Slice Discovery2309.06703v1 · Eric Slyman, Minsuk Kahng, Stefan Lee2023 · 5 citations2023 IEEE/CVF International Conference on Computer Vision (ICCV)
Behavioral Analysis of Vision-and-Language Navigation Agents2307.10790v1 · Zijiao Yang, Arjun Majumdar, Stefan Lee2023 · 7 citationsIn Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 2574-2582. 2023
Navigating to Objects Specified by Images2304.01192v1 · Jacob Krantz, Theophile Gervet, Karmesh Yadav et al.2023 · 34 citationsarXiv
Emergence of Maps in the Memories of Blind Navigation Agents2301.13261v1 · Erik Wijmans, Manolis Savva, Irfan Essa et al.2023 · 18 citationsarXiv
Instance-Specific Image Goal Navigation: Training Embodied Agents to Find Object Instances2211.15876v1 · Jacob Krantz, Stefan Lee, Jitendra Malik et al.2022 · 7 citationsarXiv
Retrospectives on the Embodied AI Workshop2210.06849v3 · Matt Deitke, Dhruv Batra, Yonatan Bisk et al.2022 · 25 citationsarXiv
Iterative Vision-and-Language Navigation2210.03087v3 · Jacob Krantz, Shurjo Banerjee, Wang Zhu et al.2022 · 27 citationsarXiv
Sim-2-Sim Transfer for Vision-and-Language Navigation in Continuous Environments2204.09667v2 · Jacob Krantz, Stefan Lee2022 · 56 citationsarXiv
PROMPT: Learning Dynamic Resource Allocation Policies for Network Applications2201.07916v2 · Drew Penney, Bin Li, Jaroslaw Sydir et al.2022 · 5 citationsarXiv
SOAT: A Scene- and Object-Aware Transformer for Vision-and-Language Navigation2110.14143v1 · Abhinav Moudgil, Arjun Majumdar, Harsh Agrawal et al.2021 · 30 citationsarXiv
Waypoint Models for Instruction-guided Navigation in Continuous Environments2110.02207v1 · Jacob Krantz, Aaron Gokaslan, Dhruv Batra et al.2021 · 93 citationsarXiv
Improving Multilingual Translation by Representation and Gradient Regularization2109.04778v2 · Yilin Yang, Akiko Eriguchi, Alexandre Muzio et al.2021 · 17 citationsarXiv
Piecewise-constant Neural ODEs2106.06621v1 · Sam Greydanus, Stefan Lee, Alan Fern2021 · 3 citationsarXiv
Deep Convolution for Irregularly Sampled Temporal Point Clouds2105.00137v1 · Erich Merrill, Stefan Lee, Li Fuxin et al.2021 · 1 citationarXiv
Where Are You? Localization from Embodied Dialog2011.08277v2 · Meera Hahn, Jacob Krantz, Dhruv Batra et al.2020 · 24 citationsEMNLP 2020
Sim-to-Real Transfer for Vision-and-Language Navigation2011.03807v1 · Peter Anderson, Ayush Shrivastava, Joanne Truong et al.2020 · 62 citationsarXiv
Language-Conditioned Imitation Learning for Robot Manipulation Tasks2010.12083v1 · Simon Stepputtis, Joseph Campbell, Mariano Phielipp et al.2020 · 82 citationsarXiv
DeepAveragers: Offline Reinforcement Learning by Solving Derived Non-Parametric MDPs2010.08891v2 · Aayam Shrestha, Stefan Lee, Prasad Tadepalli et al.2020 · 4 citationsarXiv
On the Sub-Layer Functionalities of Transformer Decoder2010.02648v1 · Yilin Yang, Longyue Wang, Shuming Shi et al.2020 · 24 citationsarXiv
Semantic MapNet: Building Allocentric Semantic Maps and Representations from Egocentric Views2010.01191v3 · Vincent Cartillier, Zhile Ren, Neha Jain et al.2020 · 68 citationsarXiv
Integrating Egocentric Localization for More Realistic Point-Goal Navigation Agents2009.03231v1 · Samyak Datta, Oleksandr Maksymets, Judy Hoffman et al.2020 · 24 citationsarXiv
Dialog without Dialog Data: Learning Visual Dialog Agents from VQA Data2007.12750v1 · Michael Cogswell, Jiasen Lu, Rishabh Jain et al.2020 · 8 citationsarXiv
Improving Vision-and-Language Navigation with Image-Text Pairs from the Web2004.14973v2 · Arjun Majumdar, Ayush Shrivastava, Stefan Lee et al.2020 · 201 citationsarXiv
Beyond the Nav-Graph: Vision-and-Language Navigation in Continuous Environments2004.02857v2 · Jacob Krantz, Erik Wijmans, Arjun Majumdar et al.2020 · 265 citationsarXiv
Sim2Real Predictivity: Does Evaluation in Simulation Predict Real-World Performance?1912.06321v2 · Abhishek Kadian, Joanne Truong, Aaron Gokaslan et al.2019 · 201 citationsIEEE Robotics and Automation Letters (RA-L) 2020
12-in-1: Multi-Task Vision and Language Representation Learning1912.02315v2 · Jiasen Lu, Vedanuj Goswami, Marcus Rohrbach et al.2019 · 411 citationsarXiv
Question-Conditioned Counterfactual Image Generation for VQA1911.06352v1 · Jingjing Pan, Yash Goyal, Stefan Lee2019 · 11 citationsarXiv
DD-PPO: Learning Near-Perfect PointGoal Navigators from 2.5 Billion Frames1911.00357v2 · Erik Wijmans, Abhishek Kadian, Ari Morcos et al.2019 · 189 citationsarXiv
Career total: 108 works. 78 are in this corpus.Showing the 50 most recent.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.