MP
Manish Prajapat
cs.LGcs.ROcs.SYeess.SYmath.OCcs.AIcs.MAAdd-on deviceArchitectural barrierscs.CV
On Valency
published · living versionsW_3h6nccpq·v1 · currentpublished
Projected Distillation: On Learning to Solve Hard Problems from Close, Correct Targets
with Shripad V. Deshmukh, Christian Bock, Kangrui Ruan, Abhijeet Awasthi +2
1 version
Preprints & journals
21 papers in the corpus · 2018–2026Projected Distillation: On Learning to Solve Hard Problems from Close, Correct Targets2610.27467v1 · Shripad V. Deshmukh, Christian Bock, Kangrui Ruan et al.2026 · 0 citationsarXivon Valency
ANTE: Anticipate, Then Execute -- Learning Internal World Models for Coding Agents from Verified Beliefs2610.15368v1 · Yi Ge, Kangrui Ruan, Jifan Chen et al.2026 · 0 citationsarXiv
Sampling-Based Safe Reinforcement Learning2605.19469v2 · Luca Vignola, Bruce D. Lee, Manish Prajapat et al.2026 · 0 citationsarXiv
Goal-oriented safe active learning for predictive control using Bayesian recurrent neural networks2604.12542v1 · Laura Boca de Giuli, Alessio La Bella, Manish Prajapat et al.2026 · 0 citationsarXiv
Safe Exploration via Policy Priors2601.19612v4 · Manuel Wendl, Yarden As, Manish Prajapat et al.2026 · 0 citationsarXiv
Safe and Near-Optimal Control with Online Dynamics Learning2509.16650v2 · Manish Prajapat, Johannes Kohler, Melanie N. Zeilinger et al.2025 · 0 citationsarXiv
Robust-Sub-Gaussian Model Predictive Control for Safe Ultrasound-Image-Guided Robotic Spinal Surgery2508.06744v1 · Yunke Ao, Manish Prajapat, Yarden As et al.2025 · 2 citationsarXiv
SonoGym: High Performance Simulation for Challenging Surgical Tasks with Robotic Ultrasound2507.01152v1 · Yunke Ao, Masoud Moghani, Mayank Mittal et al.2025 · 1 citationarXiv
Finite-Sample-Based Reachability for Safe Control with Gaussian Process Dynamics2505.07594v1 · Manish Prajapat, Johannes Kohler, Amon Lahr et al.2025 · 1 citationarXiv
Stochastic Model Predictive Control for Sub-Gaussian Noise2503.08795v2 · Yunke Ao, Johannes Kohler, Manish Prajapat et al.2025 · 0 citationsarXiv
Performance-driven Constrained Optimal Auto-Tuner for MPC2503.07127v1 · Albert Gassol Puigjaner, Manish Prajapat, Andrea Carron et al.2025 · 2 citationsarXiv
SMART: Self-learning Meta-strategy Agent for Reasoning Tasks2410.16128v1 · Rongxing Liu, Kumar Shridhar, Manish Prajapat et al.2024 · 0 citationsarXiv
Towards safe and tractable Gaussian process-based MPC: Efficient sampling within a sequential quadratic programming framework2409.08616v1 · Manish Prajapat, Amon Lahr, Johannes Kohler et al.2024 · 7 citationsarXiv
Global Reinforcement Learning: Beyond Linear and Convex Rewards via Submodular Semi-gradient Methods2407.09905v1 · Riccardo De Santi, Manish Prajapat, Andreas Krause2024 · 0 citationsarXiv
Safe Guaranteed Exploration for Non-linear Systems2402.06562v2 · Manish Prajapat, Johannes Kohler, Matteo Turchetta et al.2024 · 8 citationsarXiv
Submodular Reinforcement Learning2307.13372v2 · Manish Prajapat, Mojm'ir Mutn'y, Melanie N. Zeilinger et al.2023 · 3 citationsarXiv
Near-Optimal Multi-Agent Learning for Safe Coverage Control2210.06380v1 · Manish Prajapat, Matteo Turchetta, Melanie N. Zeilinger et al.2022 · 9 citationsarXiv
Proof-of-concept of a stair-climbing add-on device for wheelchairs.33081967 · Prajapat, Manish, Sikchi, Vishwajeet, Shaikh-Mohammed, Javeed et al.2021 · 12 citationsMedical engineering & physics. 2020;85:75-86
Competitive Policy Optimization2006.10611v1 · Manish Prajapat, Kamyar Azizzadenesheli, Alexander Liniger et al.2020 · 9 citationsarXiv
AMZ Driverless: The Full Autonomous Racing System1905.05150v1 · Juraj Kabzan, Miguel de la Iglesia Valls, Victor Reijgwart et al.2019 · 161 citationsarXiv
Redundant Perception and State Estimation for Reliable Autonomous Racing1809.10099v1 · Nikhil Bharadwaj Gosala, Andreas Buhler, Manish Prajapat et al.2018 · 24 citationsarXiv
Career total: 30 works. 21 are in this corpus.
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.