|
Samyak Parajuli I'm currently a PhD student at UT Austin advised by Amy Zhang. I'm broadly interested in multimodal learning and self-supervised learning within decision-making contexts. My work is supported by the NSF CSGrad4US Fellowship. Previously, I worked as a research engineer at Perplexity AI, focusing on pretraining, retrieval, and RLHF for LLMs, and at Scale AI, where I specialized in multimodal generative models, semantic search, and interpretability. I recieved a Master's and Bachelor's degree from UC Berkeley, where I researched multi-agent and unsupervised reinforcement learning working with Alexandre Bayen and Sergey Levine. |
 |
Research |
 |
RL Zero: Zero-Shot Language to Behaviors without any Supervision Harshit Sikchi*, Siddhant Agarwal*, Samyak Parajuli*, Pranaya Jagoo*, Caleb Chuck*, Max Rudolph*, Peter Stone, Amy Zhang, Scott Niekum ICML 2025 Towards Robots with Human-Level Abilities Workshop |
 |
AMAGO-2: Breaking the Multi-Task Barrier in Meta-Reinforcement Learning with Transformers Jake Grigsby, Samyak Parajuli, Justin Sasek, Daniel Adebi, Amy Zhang, Yuke Zhu NeurIPS 2024 |
 |
DreamGarden: A Designer Assistant for Growing Games from a Single Prompt Sam Earle, Samyak Parajuli, Andrzej Banburski-Fahey CHI 2025 Best Paper |
 |
Learning Generalizable Multi-Lane Mixed-Autonomy Behaviors in Single Lane Representations of Traffic Abdul Rahman Kriedieh*, Yibo Zhao*, Samyak Parajuli*, Alexandre Bayen AAMAS 2022 |
 |
Explore and Control with Adversarial Surprise Arnaud Fickinger*, Natasha Jaques*, Samyak Parajuli, Michael Chang, Nicholas Rhinehart, Glen Berseth, Stuart Russell, Sergey Levine ICML 2021 Unsupervised RL Workshop |
 |
The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization Dan Hendrycks, Steven Basart, Norman Mu, Saurav Kadavath, Frank Wang, Evan Dorundo, Rahul Desai, Tyler Zhu, Samyak Parajuli, Mike Guo, Dawn Song, Jacob Steinhardt, Justin Gilmer ICCV 2021, ICML 2021 Uncertainty and Robustness in Deep Learning Workshop |
 |
Dynamically Throttleable Neural Networks (TNN) Hengyue Liu*, Samyak Parajuli*, Jesse Hostetler, Sek Chai, Bir Bhanu Journal of Machine Vision and Applications 2022 |
 |
Inter-Level Cooperation in Hierarchical Reinforcement Learning Abdul Rahman Kriedieh, Glen Berseth, Brandon Trabucco*, Samyak Parajuli*, Sergey Levine, Alexandre Bayen NeurIPS 2020 Deep Reinforcement Learning Workshop |
 |
Generalized Ternary Connect: End-to-End Learning and Compression of Multiplication-Free Deep Neural Networks Samyak Parajuli, Aswin Raghavan, Sek Chai Arxiv 2018 |
Template adapted from Jon Barron's site.