PA
Pulkit Agrawal
cs.LGcs.ROcs.AIcs.CVcs.NEcs.SYeess.SYstat.MLcs.CLcs.HC
On Valency
published · living versionsW_ukvq6f42·v1 · currentpublished
Conditional Flow Models Convert Epistemic Uncertainty into Apparent Aleatoric Variance
with Navodita Sharma, Abhishek Shetty, Max Simchowitz
1 version
Preprints & journals
129 papers in the corpus · 2014–2026Conditional Flow Models Convert Epistemic Uncertainty into Apparent Aleatoric Variance2610.29172v1 · Navodita Sharma, Abhishek Shetty, Max Simchowitz et al.2026 · 0 citationsarXivon Valency
Blind Precise Assembly: Proprioceptive Sim-to-Real Peg-in-Hole for Diverse Parts2610.23849v1 · Antonia Bronars, Younghyo Park, Kushal Kedia et al.2026 · 0 citationsarXiv
Compliant GMT: Making General Motion Tracking Compliant via Residual Reference Adaptation2610.22119v1 · Venki Parsuram, Michelle Wang, Jin-Hyuk Hong et al.2026 · 0 citationsarXiv
Contact-UAN: Unsupervised Actuator Networks as a Residual World Model for Humanoid Control2610.18991v1 · Nolan Fey, Khai Nguyen, Yash Prabhu et al.2026 · 0 citationsarXiv
Data-reflector: an agentic exploratory data analysis platform for researchers.42825291 · Sabounchi, Moein, Hazare, Nimay, Capone, Chris et al.2026 · 0 citationsJAMIA open. 2026;9(5):ooag194
Workspace Models: Lightweight Robotic Memory via Saliency-Driven Supervision2609.20820v3 · Nitish Dashora, Douglas Chen, Idan Shenfeld et al.2026 · 0 citationsarXiv
Dynamic Compression in Recurrent Networks2608.17896v1 · Jyothish Pari, Ryan Bahlous-Boldi, Pulkit Agrawal2026 · 0 citationsarXiv
Learning from Hindsight for VLA Reinforcement Learning2607.09042v2 · Iris Xu, Sunshine Jiang, John Marangola et al.2026 · 0 citationsarXiv
Prompt-Driven Exploration: Language as an Exploration Space for VLA Reinforcement Learning2607.08837v4 · Sunshine Jiang, John Marangola, David Zhang et al.2026 · 0 citationsarXiv
What Matters When Cotraining Robot Manipulation Policies on Everyday Human Videos?2606.06627v1 · Richard Li, Aditya Prakash, Andrew Wen et al.2026 · 0 citationsarXiv
Vector Policy Optimization: Training for Diversity Improves Test-Time Search2605.22817v1 · Ryan Bahlous-Boldi, Isha Puri, Idan Shenfeld et al.2026 · 0 citationsarXiv
KaRMA: A Kinematic Metric for Fine Manipulation Ability in Robotic Hands2605.15548v2 · Martin Peticco, Pulkit Agrawal2026 · 0 citationsarXiv
Tune to Learn: How Controller Gains Shape Robot Policy Learning2604.02523v1 · Antonia Bronars, Younghyo Park, Pulkit Agrawal2026 · 0 citationsarXiv
Training Language Models via Neural Cellular Automata2603.10055v1 · Dan Lee, Seungwook Han, Akarsh Kumar et al.2026 · 0 citationsarXiv
Agile asymmetric multi-legged locomotion: contact planning via geometric mechanics and spin model duality2602.09123v1 · Jackson Habala, Gabriel B. Margolis, Tianyu Wang et al.2026 · 0 citationsarXiv
Self-Distillation Enables Continual Learning2601.19897v2 · Idan Shenfeld, Mehul Damani, Jonas Hubotter et al.2026 · 0 citationsarXiv
Personalized Hemodynamic Management Using Reinforcement Learning to Prevent Persistent Acute Kidney Injury After Cardiac Surgery.41282947 · Sabounchi, Moein, Desman, Jacob M, Amit, Idan Shenfeld et al.2025 · 1 citationmedRxiv : the preprint server for health sciences. 2025
SoftMimic: Learning Compliant Whole-body Control from Examples2510.17792v1 · Gabriel B. Margolis, Michelle Wang, Nolan Fey et al.2025 · 1 citationarXiv
A multimodal robotic platform for multi-element electrocatalyst discovery.40987343 · Zhang, Zhen, Ren, Zhichu, Hsu, Chia-Wei et al.2025 · 73 citationsNature. 2025;647(8089):390-396
RL's Razor: Why Online Reinforcement Learning Forgets Less2509.04259v1 · Idan Shenfeld, Jyothish Pari, Pulkit Agrawal2025 · 0 citationsarXiv
DEXOP: A Device for Robotic Transfer of Dexterous Human Manipulation2509.04441v2 · Hao-Shu Fang, Branden Romero, Yichen Xie et al.2025 · 0 citationsarXiv
Going Beyond Heuristics by Imposing Policy Improvement as a Constraint2507.05328v1 · Chi-Chang Lee, Zhang-Wei Hong, Pulkit Agrawal2025 · 0 citationsarXiv
DexWrist: A Robotic Wrist for Constrained and Dynamic Manipulation2507.01008v4 · Martin Peticco, Gabriella Ulloa, John Marangola et al.2025 · 1 citationarXiv
Self-Adapting Language Models2506.10943v2 · Adam Zweiger, Jyothish Pari, Han Guo et al.2025 · 3 citationsarXiv
A distributional reinforcement learning model for optimal glucose control after cardiac surgery.40425725 · Desman, Jacob M, Hong, Zhang-Wei, Sabounchi, Moein et al.2025 · 15 citationsNPJ digital medicine. 2025;8(1):313
ORAKLE: Optimal Risk prediction for mAke30 in patients with sepsis associated AKI using deep LEarning.40420108 · Oh, Wonsuk, Veshtaj, Marinela, Sawant, Ashwin et al.2025 · 15 citationsCritical care (London, England). 2025;29(1):212
Language Model Personalization via Reward Factorization2503.06358v1 · Idan Shenfeld, Felix Faltings, Pulkit Agrawal et al.2025 · 0 citationsarXiv
General Intelligence Requires Reward-based Pretraining2502.19402v3 · Seungwook Han, Jyothish Pari, Samuel J. Gershman et al.2025 · 0 citationsarXiv
Hovering Flight of Soft-Actuated Insect-Scale Micro Aerial Vehicles using Deep Reinforcement Learning2502.12355v1 · Yi-Hsuan Hsiao, Wei-Tung Chen, Yun-Sheng Chang et al.2025 · 0 citationsarXiv
Bridging the Sim-to-Real Gap for Athletic Loco-Manipulation2502.10894v1 · Nolan Fey, Gabriel B. Margolis, Martin Peticco et al.2025 · 6 citationsarXiv
Known Unknowns: Out-of-Distribution Property Prediction in Materials and Molecules2502.05970v1 · Nofit Segal, Aviv Netanyahu, Kevin P. Greenman et al.2025 · 29 citationsarXiv
ORAKLE: Optimal Risk prediction for mAke30 in patients with acute Kidney injury using deep LEarning10.1101/2025.01.18.25320769v1 · Oh, W., Veshtaj, M., Sawant, A. et al.2025 · 0 citationsmedRxiv
Efficient Diffusion Transformer Policies with Mixture of Expert Denoisers for Multitask Learning2412.12953v1 · Moritz Reuss, Jyothish Pari, Pulkit Agrawal et al.2024 · 1 citationarXiv
Emergence and Effectiveness of Task Vectors in In-Context Learning: An Encoder Decoder Perspective2412.12276v3 · Seungwook Han, Jinyeop Song, Jeff Gore et al.2024 · 0 citationsarXiv
Robot Learning with Super-Linear Scaling2412.01770v3 · Marcel Torne, Arhan Jain, Jiayi Yuan et al.2024 · 2 citationsarXiv
Embodied Red Teaming for Auditing Robotic Foundation Models2411.18676v2 · Sathwik Karnik, Zhang-Wei Hong, Nishant Abhangi et al.2024 · 0 citationsarXiv
Few-Shot Task Learning through Inverse Generative Modeling2411.04987v2 · Aviv Netanyahu, Yilun Du, Antonia Bronars et al.2024 · 1 citationarXiv
Collective Model Intelligence Requires Compatible Specialization2411.02207v1 · Jyothish Pari, Samy Jelassi, Pulkit Agrawal2024 · 0 citationsarXiv
DexHub and DART: Towards Internet Scale Robot Data Collection2411.02214v1 · Younghyo Park, Jagdeep Singh Bhatia, Lars Ankile et al.2024 · 0 citationsarXiv
Learning to Look Around: Enhancing Teleoperation and Learning with a Human-like Actuated Neck2411.00704v1 · Bipasha Sen, Michelle Wang, Nandini Thakur et al.2024 · 1 citationarXiv
Large Pretraining Datasets Don't Guarantee Robustness after Fine-Tuning in Image Classification2410.21582v4 · Jaedong Hwang, Brian Cheung, Zhang-Wei Hong et al.2024 · 0 citationsarXiv
ORSO: Accelerating Reward Design via Online Reward Selection and Policy Optimization2410.13837v3 · Chen Bo Calvin Zhang, Zhang-Wei Hong, Aldo Pacchiano et al.2024 · 0 citationsarXiv
Diffusion Policy Policy Optimization2409.00588v3 · Allen Z. Ren, Justin Lidard, Lars L. Ankile et al.2024 · 2 citationsarXiv
EyeSight Hand: Design of a Fully-Actuated Dexterous Robot Hand with Integrated Vision-Based Tactile Sensors and Compliant Actuation2408.06265v1 · Branden Romero, Hao-Shu Fang, Pulkit Agrawal et al.2024 · 20 citationsarXiv
Everyday Finger: A Robotic Finger that Meets the Needs of Everyday Interactive Manipulation2408.04142v1 · Rub'en Castro Ornelas, Tom'as Cant'u, Isabel Sperandio et al.2024 · 2 citationsarXiv
Automatic Environment Shaping is the Next Frontier in RL2407.16186v1 · Younghyo Park, Gabriel B. Margolis, Pulkit Agrawal2024 · 0 citationsarXiv
From Imitation to Refinement -- Residual RL for Precise Assembly2407.16677v4 · Lars Ankile, Anthony Simeonov, Idan Shenfeld et al.2024 · 15 citationsarXiv
Random Latent Exploration for Deep Reinforcement Learning2407.13755v3 · Srinath Mahankali, Zhang-Wei Hong, Ayush Sekhari et al.2024 · 1 citationarXiv
Vegetable Peeling: A Case Study in Constrained Dexterous Manipulation2407.07884v1 · Tao Chen, Eric Cousineau, Naveen Kuppuswamy et al.2024 · 7 citationsarXiv
ROER: Regularized Optimal Experience Replay2407.03995v1 · Changling Li, Zhang-Wei Hong, Pulkit Agrawal et al.2024 · 1 citationReinforcement Learning Journal, vol. 4, 2024, pp. 1598-1618
Career total: 158 works. 129 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.