DP
Deepak Pathak
cs.LGcs.CVcs.AIcs.ROstat.MLcs.SYeess.SYcs.NEcs.CLcs.GR
On Valency
published · living versionsW_ber6cpqu·v1 · currentpublished
Context Encoders: Feature Learning by Inpainting
with Philipp Krahenbuhl, Jeff Donahue, Trevor Darrell, Alexei A. Efros
1 version
Preprints & journals
75 papers in the corpus · 2014–2026Solving Physics Olympiad via Reinforcement Learning on Physics Simulators2604.11805v1 · Mihir Prabhudesai, Aryan Satpathy, Yangmin Li et al.2026 · 0 citationsarXiv
ViPRA: Video Prediction for Robot Actions2511.07732v2 · Sandeep Routray, Hengkai Pan, Unnat Jain et al.2025 · 0 citationsarXiv
IFG: Internet-Scale Guidance for Functional Grasping Generation2511.09558v1 · Ray Muxin Liu, Mingxuan Li, Kenneth Shaw et al.2025 · 0 citationsarXiv
Diffusion Beats Autoregressive in Data-Constrained Settings2507.15857v7 · Mihir Prabhudesai, Mengning Wu, Amir Zadeh et al.2025 · 1 citationarXiv
Self-Questioning Language Models2508.03682v4 · Lili Chen, Mihir Prabhudesai, Katerina Fragkiadaki et al.2025 · 1 citationarXiv
Deep Reactive Policy: Learning Reactive Manipulator Motion Planning for Dynamic Environments2509.06953v1 · Jiahui Yang, Jason Jingzhou Liu, Yulong Li et al.2025 · 0 citationsarXiv
Can LLMs Lie? Investigation beyond Hallucination2509.03518v1 · Haoran Huan, Mihir Prabhudesai, Mengning Wu et al.2025 · 1 citationarXiv
Maximizing Confidence Alone Improves Reasoning2505.22660v4 · Mihir Prabhudesai, Lili Chen, Alex Ippoliti et al.2025 · 0 citationsarXiv
FACTR: Force-Attending Curriculum Training for Contact-Rich Policy Learning2502.17432v2 · Jason Jingzhou Liu, Yulong Li, Kenneth Shaw et al.2025 · 16 citationsarXiv
Unified Multimodal Discrete Diffusion2503.20853v1 · Alexander Swerdlow, Mihir Prabhudesai, Siddharth Gandhi et al.2025 · 0 citationsarXiv
Local Policies Enable Zero-shot Long-horizon Manipulation2410.22332v2 · Murtaza Dalal, Min Liu, Walter Talbott et al.2024 · 4 citationsarXiv
Bimanual Dexterity for Complex Tasks2411.13677v1 · Kenneth Shaw, Yulong Li, Jiahui Yang et al.2024 · 1 citationarXiv
GenAI-Bench: Evaluating and Improving Compositional Text-to-Visual Generation2406.13743v3 · Baiqi Li, Zhiqiu Lin, Deepak Pathak et al.2024 · 0 citationsarXiv
Continuously Improving Mobile Manipulation with Autonomous Real-World RL2409.20568v1 · Russell Mendonca, Emmanuel Panov, Bernadette Bucher et al.2024 · 0 citationsarXiv
Neural MP: A Generalist Neural Motion Planner2409.05864v1 · Murtaza Dalal, Jiahui Yang, Russell Mendonca et al.2024 · 2 citationsarXiv
Multimodality Helps Unimodality: Cross-Modal Few-Shot Learning with Multimodal Models2301.06267v5 · Zhiqiu Lin, Samuel Yu, Zhiyi Kuang et al.2023 · 129 citationsarXiv
SAPG: Split and Aggregate Policy Gradients2407.20230v1 · Jayesh Singla, Ananye Agarwal, Deepak Pathak2024 · 0 citationsarXiv
Video Diffusion Alignment via Reward Gradients2407.08737v1 · Mihir Prabhudesai, Russell Mendonca, Zheyang Qin et al.2024 · 0 citationsarXiv
Evaluating Text-to-Visual Generation with Image-to-Text Generation2404.01291v2 · Zhiqiu Lin, Deepak Pathak, Baiqi Li et al.2024 · 86 citationsarXiv
Revisiting the Role of Language Priors in Vision-Language Models2306.01879v4 · Zhiqiu Lin, Xinyue Chen, Deepak Pathak et al.2023 · 4 citationsarXiv
Designing Anthropomorphic Soft Hands through Interaction2306.04784v3 · Pragna Mannam, Kenneth Shaw, Dominik Bauer et al.2023 · 5 citations2023 IEEE-RAS 22nd International Conference on Humanoid Robots (Humanoids)
Adaptive Mobile Manipulation for Articulated Objects In the Open World2401.14403v2 · Haoyu Xiong, Russell Mendonca, Kenneth Shaw et al.2024 · 5 citationsarXiv
DEFT: Dexterous Fine-Tuning for Real-World Hand Policies2310.19797v2 · Aditya Kannan, Kenneth Shaw, Shikhar Bahl et al.2023 · 2 citationsarXiv
Dexterous Functional Grasping2312.02975v1 · Ananye Agarwal, Shagun Uppal, Kenneth Shaw et al.2023 · 0 citationsarXiv
Diffusion-TTA: Test-time Adaptation of Discriminative Models via Generative Feedback2311.16102v2 · Mihir Prabhudesai, Tsung-Wei Ke, Alexander C. Li et al.2023 · 5 citationsarXiv
Your Diffusion Model is Secretly a Zero-Shot Classifier2303.16203v3 · Alexander C. Li, Mihir Prabhudesai, Shivam Duggal et al.2023 · 145 citationsarXiv
LEAP Hand: Low-Cost, Efficient, and Anthropomorphic Hand for Robot Learning2309.06440v1 · Kenneth Shaw, Ananye Agarwal, Deepak Pathak2023 · 101 citationsarXiv
Internet Explorer: Targeted Representation Learning on the Open Web2302.14051v2 · Alexander C. Li, Ellis Brown, Alexei A. Efros et al.2023 · 4 citationsarXiv
Efficient RL via Disentangled Environment and Agent Representations2309.02435v1 · Kevin Gmelin, Shikhar Bahl, Russell Mendonca et al.2023 · 0 citationsarXiv
Structured World Models from Human Videos2308.10901v1 · Russell Mendonca, Shikhar Bahl, Deepak Pathak2023 · 34 citationsarXiv
Affordances from Human Videos as a Versatile Representation for Robotics2304.08488v1 · Shikhar Bahl, Russell Mendonca, Lili Chen et al.2023 · 114 citationsarXiv
Legs as Manipulator: Pushing Quadrupedal Agility Beyond Locomotion2303.11330v2 · Xuxin Cheng, Ashish Kumar, Deepak Pathak2023 · 52 citationsarXiv
ALAN: Autonomously Exploring Robotic Agents in the Real World2302.06604v1 · Russell Mendonca, Shikhar Bahl, Deepak Pathak2023 · 4 citationsarXiv
Continual Learning with Evolving Class Ontologies2210.04993v4 · Zhiqiu Lin, Deepak Pathak, Yu-Xiong Wang et al.2022 · 5 citationsarXiv
VideoDex: Learning Dexterity from Internet Videos2212.04498v1 · Kenneth Shaw, Shikhar Bahl, Deepak Pathak2022 · 7 citationsarXiv
Legged Locomotion in Challenging Terrains using Egocentric Vision2211.07638v1 · Ananye Agarwal, Ashish Kumar, Jitendra Malik et al.2022 · 27 citationsarXiv
Understanding Collapse in Non-Contrastive Siamese Representation Learning2209.15007v2 · Alexander C. Li, Alexei A. Efros, Deepak Pathak2022 · 25 citationsarXiv
RB2: Robotic Manipulation Benchmarking with a Twist2203.08098v2 · Sudeep Dasari, Jianren Wang, Joyce Hong et al.2022 · 1 citationarXiv
Deep Whole-Body Control: Learning a Unified Policy for Manipulation and Locomotion2210.10044v1 · Zipeng Fu, Xuxin Cheng, Deepak Pathak2022 · 26 citationsarXiv
Adapting Rapid Motor Adaptation for Bipedal Robots2205.15299v2 · Ashish Kumar, Zhongyu Li, Jun Zeng et al.2022 · 69 citationsarXiv
Coupling Vision and Proprioception for Navigation of Legged Robots2112.02094v2 · Zipeng Fu, Ashish Kumar, Ananye Agarwal et al.2021 · 43 citationsarXiv
Robotic Telekinesis: Learning a Robotic Hand Imitator by Watching Humans on Youtube2202.10448v2 · Aravind Sivakumar, Kenneth Shaw, Deepak Pathak2022 · 5 citationsarXiv
The CLEAR Benchmark: Continual LEArning on Real-World Imagery2201.06289v3 · Zhiqiu Lin, Jia Shi, Deepak Pathak et al.2022 · 15 citationsarXiv
Topologically-Aware Deformation Fields for Single-View 3D Reconstruction2205.06267v2 · Shivam Duggal, Deepak Pathak2022 · 34 citationsarXiv
Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agents2201.07207v2 · Wenlong Huang, Pieter Abbeel, Deepak Pathak et al.2022 · 155 citationsarXiv
FLAVR: Flow-Agnostic Video Representations for Fast Frame Interpolation2012.08512v3 · Tarun Kalluri, Deepak Pathak, Manmohan Chandraker et al.2020 · 151 citationsarXiv
Differentiable Spatial Planning using Transformers2112.01010v1 · Devendra Singh Chaplot, Deepak Pathak, Jitendra Malik2021 · 5 citationsarXiv
Interesting Object, Curious Agent: Learning Task-Agnostic Exploration2111.13119v1 · Simone Parisi, Victoria Dean, Deepak Pathak et al.2021 · 4 citationsarXiv
Generalization in Dexterous Manipulation via Geometry-Aware Multi-Task Learning2111.03062v1 · Wenlong Huang, Igor Mordatch, Pieter Abbeel et al.2021 · 23 citationsarXiv
Minimizing Energy Consumption Leads to the Emergence of Gaits in Legged Robots2111.01674v1 · Zipeng Fu, Ashish Kumar, Jitendra Malik et al.2021 · 44 citationsarXiv
Career total: 116 works. 75 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.