pith. sign in

Pulkit Agrawal

Identifiers

  • name variant Pulkit Agrawal 0.60 · backfill

Papers (24)

  1. Fine-Tuning and Serving Gemma 4 31B on Google Cloud TPU: A Technical Comparison with GPU Baselines cs.DC · 2026 · author #4
  2. Vector Policy Optimization: Training for Diversity Improves Test-Time Search cs.LG · 2026 · author #9
  3. KaRMA: A Kinematic Metric for Fine Manipulation Ability in Robotic Hands cs.RO · 2026 · author #2
  4. Tune to Learn: How Controller Gains Shape Robot Policy Learning cs.RO · 2026 · author #3
  5. Self-Distillation Enables Continual Learning cs.LG · 2026 · author #4
  6. RL's Razor: Why Online Reinforcement Learning Forgets Less cs.LG · 2025 · author #3
  7. DexWrist: A Robotic Wrist for Constrained and Dynamic Manipulation cs.RO · 2025 · author #5
  8. Diffusion Policy Policy Optimization cs.RO · 2024 · author #5
  9. Is Conditional Generative Modeling all you need for Decision-Making? cs.LG · 2022 · author #6
  10. Superposition of many models into one cs.LG · 2019 · author #4
  11. Learning Instance Segmentation by Interaction cs.CV · 2018 · author #4
  12. Zero-Shot Visual Imitation cs.LG · 2018 · author #4
  13. Investigating Human Priors for Playing Video Games cs.AI · 2018 · author #2
  14. A Computer Vision Pipeline for Automated Determination of Cardiac Structure and Function and Detection of Disease by Two-Dimensional Echocardiography cs.CV · 2017 · author #3
  15. Curiosity-driven Exploration by Self-supervised Prediction cs.LG · 2017 · author #2
  16. Combining Self-Supervised Learning and Imitation for Vision-Based Rope Manipulation cs.CV · 2017 · author #3
  17. Learning to Perform Physics Experiments via Deep Reinforcement Learning stat.ML · 2016 · author #2
  18. What makes ImageNet good for transfer learning? cs.CV · 2016 · author #2
  19. Learning to Poke by Poking: Experiential Learning of Intuitive Physics cs.CV · 2016 · author #1
  20. Learning Visual Predictive Models of Physics for Playing Billiards cs.CV · 2015 · author #2
  21. Human Pose Estimation with Iterative Error Feedback cs.CV · 2015 · author #2
  22. Learning to See by Moving cs.CV · 2015 · author #1
  23. Pixels to Voxels: Modeling Visual Representation in the Human Brain q-bio.NC · 2014 · author #1
  24. Analyzing the Performance of Multilayer Neural Networks for Object Recognition cs.CV · 2014 · author #1

Mentions

  • 1407.1610 #1 · backfill · confidence 0.70 Pulkit Agrawal
  • 2605.25645 #4 · arxiv_oai · confidence 0.70 Pulkit Agrawal
  • 2605.22817 #9 · arxiv_oai · confidence 0.70 Pulkit Agrawal
  • 2605.15548 #2 · arxiv_oai · confidence 0.70 Pulkit Agrawal
  • 2509.04259 #3 · arxiv_oai · confidence 0.70 Pulkit Agrawal
  • 2409.00588 #5 · arxiv_oai · confidence 0.70 Pulkit Agrawal
  • 2211.15657 #6 · arxiv_oai · confidence 0.70 Pulkit Agrawal

Frequent Coauthors