ST
Shubham Tulsiani
cs.CVcs.LGcs.ROcs.AIcs.GRstat.MLeess.IV
On Valency
published · living versionsW_767kv7nv·v1 · currentpublished
CS-Pi: Constraint-Satisfying Flow Policy Sampling
with Soumojit Bhattacharya, Oliver Kroemer
1 version
W_734wmyny·v1published
Preprints & journals
83 papers in the corpus · 2014–2026Learning Adaptable Dexterous Skills via Hybrid Dexterous Mimicking2610.28628v1 · Yuxuan Kuang, Jiashun Wang, Yixuan Sun et al.2026 · 0 citationsarXivon Valency
An Empirical Study on What Matters for Viewpoint-Generalizable Policies in Visual Imitation Learning2609.32762v1 · Mino Nakura, Sriram Krishna, Yufei Wang et al.2026 · 0 citationsarXiv
Point4D: Long-range 4D Motion Reconstruction2609.09145v1 · Minsik Jeon, Jay Karhade, Deva Ramanan et al.2026 · 0 citationsarXiv
: Reactive Real-time Flow Policies2607.26055v1 · Sungjae Park, Shubham Tulsiani2026 · 0 citationsarXiv
Lift4D: Harmonizing Single-View 3D Estimation for 4D Reconstruction In-the-Wild2606.23688v1 · Yehonathan Litman, Xiaoxuan Ma, Manan Shah et al.2026 · 0 citationsarXiv
GHOST: Hierarchical Sub-Goal Policies for Generalizing Robot Manipulation2606.10025v1 · Sriram Krishna, Ben Eisner, Haotian Zhan et al.2026 · 0 citationsarXiv
Flow3r: Factored Flow Prediction for Scalable Visual Geometry Learning2602.20157v1 · Zhongxiao Cong, Qitao Zhao, Minsik Jeon et al.2026 · 0 citationsarXiv
Dex4D: Task-Agnostic Point Track Policy for Zero-Shot Dexterous Manipulation2602.15828v2 · Yuxuan Kuang, Sungjae Park, Katerina Fragkiadaki et al.2026 · 0 citationsarXiv
EditCtrl: Disentangled Local and Global Control for Real-Time Generative Video Editing2602.15031v2 · Yehonathan Litman, Shikun Liu, Dario Seyb et al.2026 · 0 citationsarXiv
RayRoPE: Projective Ray Positional Encoding for Multi-view Attention2601.15275v3 · Yu Wu, Minsik Jeon, Jen-Hao Rick Chang et al.2026 · 1 citationarXiv
CRISP: Contact-Guided Real2Sim from Monocular Video with Planar Scene Primitives2512.14696v3 · Zihan Wang, Jiashun Wang, Jeff Tan et al.2025 · 0 citationsarXiv
E-RayZer: Self-supervised 3D Reconstruction as Spatial Visual Pre-training2512.10950v2 · Qitao Zhao, Hao Tan, Qianqian Wang et al.2025 · 1 citationarXiv
Temporal Score Rescaling for Temperature Sampling in Diffusion and Flow Models2510.01184v2 · Yanbo Xu, Yu Wu, Sungjae Park et al.2025 · 0 citationsarXiv
LightSwitch: Multi-view Relighting with Material-guided Diffusion2508.06494v1 · Yehonathan Litman, Fernando De la Torre, Shubham Tulsiani2025 · 2 citationsarXiv
DemoDiffusion: One-Shot Human Imitation using pre-trained Diffusion Policy2506.20668v3 · Sungjae Park, Homanga Bharadhwaj, Shubham Tulsiani2025 · 0 citationsarXiv
UniPhy: Learning a Unified Constitutive Model for Inverse Physics Simulation2505.16971v1 · Himangi Mittal, Peiye Zhuang, Hsin-Ying Lee et al.2025 · 1 citationarXiv
DiffusionSfM: Predicting Structure and Motion via Ray Origin and Endpoint Diffusion2505.05473v1 · Qitao Zhao, Amy Lin, Jeff Tan et al.2025 · 3 citationsarXiv
Web2Grasp: Learning Functional Grasps from Web Images of Hand-Object Interactions2505.05517v3 · Hongyi Chen, Yunchao Yao, Yufei Ye et al.2025 · 0 citationsarXiv
AerialMegaDepth: Learning Aerial-Ground Reconstruction and View Synthesis2504.13157v1 · Khiem Vuong, Anurag Ghosh, Deva Ramanan et al.2025 · 15 citationsarXiv
Accenture-NVS1: A Novel View Synthesis Dataset2503.18711v2 · Thomas Sugg, Kyle O'Brien, Lekh Poudel et al.2025 · 0 citationsarXiv
Predicting 4D Hand Trajectory from Monocular Videos2501.08329v1 · Yufei Ye, Yao Feng, Omid Taheri et al.2025 · 1 citationarXiv
Diverse Score Distillation2412.06780v2 · Yanbo Xu, Jayanth Srinivasa, Gaowen Liu et al.2024 · 0 citationsarXiv
Turbo3D: Ultra-fast Text-to-3D Generation2412.04470v1 · Hanzhe Hu, Tianwei Yin, Fujun Luan et al.2024 · 9 citationsarXiv
Sparse-view Pose Estimation and Reconstruction via Analysis by Generative Synthesis2412.03570v1 · Qitao Zhao, Shubham Tulsiani2024 · 1 citationarXiv
SceneFactor: Factored Latent 3D Diffusion for Controllable 3D Scene Generation2412.01801v2 · Alexey Bokhovkin, Quan Meng, Shubham Tulsiani et al.2024 · 9 citationsarXiv
DressRecon: Freeform 4D Human Reconstruction from Monocular Video2409.20563v2 · Jeff Tan, Donglai Xiang, Shubham Tulsiani et al.2024 · 6 citationsarXiv
Gen2Act: Human Video Generation in Novel Scenarios enables Generalizable Robot Manipulation2409.16283v1 · Homanga Bharadhwaj, Debidatta Dwibedi, Abhinav Gupta et al.2024 · 1 citationarXiv
MaterialFusion: Enhancing Inverse Rendering with Material Diffusion Priors2409.15273v2 · Yehonathan Litman, Or Patashnik, Kangle Deng et al.2024 · 9 citationsarXiv
Track2Act: Predicting Point Tracks from Internet Videos enables Generalizable Robot Manipulation2405.01527v2 · Homanga Bharadhwaj, Roozbeh Mottaghi, Abhinav Gupta et al.2024 · 45 citationsarXiv
G-HOP: Generative Hand-Object Prior for Interaction Reconstruction and Grasp Synthesis2404.12383v1 · Yufei Ye, Abhinav Gupta, Kris Kitani et al.2024 · 22 citationsarXiv
MVD-Fusion: Single-view 3D via Depth-consistent Multi-view Generation2404.03656v1 · Hanzhe Hu, Zhizhuo Zhou, Varun Jampani et al.2024 · 16 citationsarXiv
Cameras as Rays: Pose Estimation via Ray Diffusion2402.14817v3 · Jason Y. Zhang, Amy Lin, Moneish Kumar et al.2024 · 10 citationsarXiv
UpFusion: Novel View Diffusion from Unposed Sparse View Observations2312.06661v2 · Bharath Raj Nagoor Kani, Hsin-Ying Lee, Sergey Tulyakov et al.2023 · 2 citationsarXiv
Towards Generalizable Zero-Shot Manipulation via Translating Human Interaction Plans2312.00775v1 · Homanga Bharadhwaj, Abhinav Gupta, Vikash Kumar et al.2023 · 20 citationsarXiv
Diffusion-Guided Reconstruction of Everyday Hand-Object Interaction Clips2309.05663v1 · Yufei Ye, Poorvi Hebbar, Abhinav Gupta et al.2023 · 40 citationsarXiv
RoboAgent: Generalization and Efficiency in Robot Manipulation via Semantic Augmentations and Action Chunking2309.01918v1 · Homanga Bharadhwaj, Jay Vakil, Mohit Sharma et al.2023 · 82 citationsarXiv
Visual Affordance Prediction for Guiding Robot Exploration2305.17783v1 · Homanga Bharadhwaj, Abhinav Gupta, Shubham Tulsiani2023 · 11 citationsarXiv
RelPose++: Recovering 6D Poses from Sparse-view Observations2305.04926v2 · Amy Lin, Jason Y. Zhang, Deva Ramanan et al.2023 · 51 citationsarXiv
Analogy-Forming Transformers for Few-Shot 3D Parsing2304.14382v2 · Nikolaos Gkanatsios, Mayank Singh, Zhaoyuan Fang et al.2023 · 0 citationsarXiv
Mesh2Tex: Generating Mesh Textures from Image Queries2304.05868v1 · Alexey Bokhovkin, Shubham Tulsiani, Angela Dai2023 · 23 citationsarXiv
Affordance Diffusion: Synthesizing Hand-Object Interactions2303.12538v3 · Yufei Ye, Xueting Li, Abhinav Gupta et al.2023 · 69 citationsarXiv
Manipulate by Seeing: Creating Manipulation Controllers from Pre-Trained Representations2303.08135v4 · Jianren Wang, Sudeep Dasari, Mohan Kumar Srirama et al.2023 · 8 citationsarXiv
Zero-Shot Robot Manipulation from Passive Human Videos2302.02011v1 · Homanga Bharadhwaj, Abhinav Gupta, Shubham Tulsiani et al.2023 · 9 citationsarXiv
Geometry-biased Transformers for Novel View Synthesis2301.04650v1 · Naveen Venkat, Mayank Agarwal, Maneesh Singh et al.2023 · 0 citationsarXiv
SparseFusion: Distilling View-conditioned Diffusion for 3D Reconstruction2212.00792v3 · Zhizhuo Zhou, Shubham Tulsiani2022 · 174 citationsarXiv
Multi-View Supervision for Single-View Reconstruction via Differentiable Ray Consistency.30762530 · Tulsiani, Shubham, Zhou, Tinghui, Efros, Alexei A et al.2022 · 526 citationsIEEE transactions on pattern analysis and machine intelligence. 2022;44(12):8754-8765
Monocular Dynamic View Synthesis: A Reality Check2210.13445v1 · Hang Gao, Ruilong Li, Shubham Tulsiani et al.2022 · 65 citationsarXiv
RelPose: Predicting Probabilistic Relative Rotation for Single Objects in the Wild2208.05963v2 · Jason Y. Zhang, Deva Ramanan, Shubham Tulsiani2022 · 69 citationsarXiv
What's in your hands? 3D Reconstruction of Generic Objects in Hands2204.07153v1 · Yufei Ye, Abhinav Gupta, Shubham Tulsiani2022 · 79 citationsarXiv
Pre-train, Self-train, Distill: A simple recipe for Supersizing 3D Reconstruction2204.03642v1 · Kalyan Vasudev Alwala, Abhinav Gupta, Shubham Tulsiani2022 · 24 citationsarXiv
Career total: 95 works. 83 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.