David Hsu

10 Open Challenges Steering the Future of Vision-Language-Action Models AAAI 2026 MimicFunc: Imitating Tool Manipulation from a Single Human Video via Functional Correspondence CoRL 2025 Neuralized Markov Random Field for Interaction-Aware Stochastic Human Trajectory Prediction ICLR 2025 Robot Operating Home Appliances by Reading User Manuals CoRL 2025 “Stack It Up!”: 3D Stable Structure Generation from 2D Hand-drawn Sketch CoRL 2025 Walk in Others’ Shoes with a Single Glance: Human-Centric Visual Grounding with Top-View Perspective Transformation ACL 2025 On the Empirical Complexity of Reasoning and Planning in LLMs EMNLP 2024 Set It Up!: Functional Object Arrangement with Compositional Generative Models RSS 2024 DaxBench: Benchmarking Deformable Object Manipulation with Differentiable Physics ICLR 2023 Large Language Models as Commonsense Knowledge for Large-Scale Task Planning NeurIPS 2023 What Truly Matters in Trajectory Prediction for Autonomous Driving? NeurIPS 2023 COACH: Cooperative Robot Teaching CoRL 2022 LEADER: Learning Attention over Driving Behaviors for Planning under Uncertainty CoRL 2022 Receding Horizon Inverse Reinforcement Learning NeurIPS 2022 SZLoc: A Multi-resolution Architecture for Automated Epileptic Seizure Localization from Scalp EEG MIDL 2022 Ab Initio Particle-based Object Manipulation RSS 2021 Differentiable SLAM-Net: Learning Particle SLAM for Visual Navigation CVPR 2021 Hindsight Trust Region Policy Optimization IJCAI 2021 INVIGORATE: Interactive Visual Grounding and Grasping in Clutter RSS 2021 MAGIC: Learning Macro-Actions for Online POMDP Planning RSS 2021 Contrastive Variational Reinforcement Learning for Complex Observations CoRL 2020 Discriminative Particle Filter Reinforcement Learning for Complex Partial observations ICLR 2020 Particle Filter Recurrent Neural Networks AAAI 2020 DESPOT-Alpha: Online POMDP Planning with Large State and Observation Spaces RSS 2019 Differentiable Algorithm Networks for Composable Robot Learning RSS 2019 LeTS-Drive: Driving in a Crowd by Learning from Tree Search RSS 2019 Trust Dynamics and Transfer across Human-Robot Interaction Tasks: Bayesian and Neural Computational Models IJCAI 2019 HyP-DESPOT: A Hybrid Parallel Algorithm for Online Planning under Uncertainty RSS 2018 Interactive Visual Grounding of Referring Expressions for Human-Robot Interaction RSS 2018 Particle Filter Networks with Application to Visual Localization CoRL 2018 Push-Net: Deep Planar Pushing for Objects with Unknown Physical Properties RSS 2018 Solving the Perspective-2-Point Problem for Flying-Camera Photo Composition CVPR 2018 The Transfer of Human Trust in Robot Capabilities across Tasks RSS 2018 Intention-Net: Integrating Planning and Deep Learning for Goal-Directed Autonomous Navigation CoRL 2017 QMDP-Net: Deep Learning for Planning under Partial Observability NeurIPS 2017 XPose: Reinventing User Interaction with Flying Cameras RSS 2017 Adaptive Stochastic Optimization: From Sets to Paths NeurIPS 2015 Covering Number for Efficient Heuristic-based POMDP Planning ICML 2014 DESPOT: Online POMDP Planning with Regularization NeurIPS 2013 Integrated Perception and Planning in the Continuous Space: A POMDP Approach RSS 2013 Monte Carlo Value Iteration with Macro-Actions NeurIPS 2011 Unmanned Aircraft Collision Avoidance using Continuous-State POMDPs RSS 2011 SARSOP: Efficient Point-Based POMDP Planning by Approximating Optimally Reachable Belief Spaces RSS 2008 What makes some POMDP problems easy to approximate? NeurIPS 2007