|
Rocktim Jyoti Das I am a first year Computer Science PhD student at University of Maryland, College Park working with Prof. Dinesh Manocha . My research focuses on developing physically grounded algorithms for robotic navigation and manipulation, with an emphasis on high-fidelity simulation and the estimation of material and mechanical properties. Prior to joining my PhD, I was a Research Associate II at MBZUAI in Abu Dhabi working on Robotic Manipulation and Reasoning under the supervison of Prof. Ivan Laptev and Prof. Preslav Nakov. I worked on developing intelligent agents that reason, plan and interact with the environment to solve complex tasks using the world knowledge acquired using internet scale data. I completed my undergraduate studies at the Indian Institute of Technology, Delhi, which set the foundation for my academic journey. I had the incredible opportunity to spend a year at the DAIR Lab, IIT Delhi as a Research Assistant under the supervision of Prof. Mausam. As a researcher at DAIR lab, I focused on Task-Oriented Dialog Systems and Conversation based Medical Diagnosis. |
|
News
|
Selected Research* denotes joint first authors |
|
SLAT-Phys: Fast Material Property Field Prediction from Structured 3D Latents
Rocktim Jyoti Das, Dinesh Manocha, ArXiv, 2026 🌐 Website 📄 arXiv |
|
BLAZER: Bootstrapping LLM-based Manipulation Agents with Zero-Shot Data Generation
Rocktim Jyoti Das*, Harsh Singh*, Diana Turmakhan, Mohammad Abdullah Sohail, Mingfei Han, Preslav Nakov, Fabio Pizzati, Ivan Laptev, ArXiv, 2025 🌐 Website 📄 arXiv |
|
MALMM: Multi-Agent Large Language Models for Zero-Shot Robotics Manipulation
Harsh Singh*, Rocktim Jyoti Das*, Mingfei Han, Preslav Nakov, Ivan Laptev, accepted to IROS, 2025 🌐 Website 📄 arXiv |
|
Synergizing In-context Learning with Hints for End-to-end Task-oriented Dialog Systems
Vishal Vivek Saley, Rocktim Jyoti Das, Dinesh Raghu, Mausam, accepted in EMNLP main, 2024 📄 arXiv |
|
Beyond Size: How Gradients Shape Pruning Decisions in Large Language Models
Rocktim Jyoti Das Mingjie Sun, Liqun Ma, Zhiqiang Shen, Arxiv, 2023 📄 arXiv |
|
EXAMS-V: A Multi-Discipline Multilingual Multimodal Exam Benchmark for Evaluating Vision Language Models
Rocktim Jyoti Das, Simeon Emilov Hristov, Haonan Li, Dimitar Dimitrov, Ivan Koychev, Preslav Nakov, accepted in ACL main, 2024 🌐 Website 📄 arXiv |
|
Exploring Distributional Shifts in Large Language Models for Code Analysis
Shushan Arakelyan, Rocktim Jyoti Das, Yi Mao, Xiang Ren, accepted in EMNLP main, 2023 📄 arXiv |
|
Open-Sourced Project Nanda is the leading open-sourced Hindi bilingual model for generation and reasoning, surpassing current models on safety benchmarks. Although our model is optimized for Devanagari Hindi, it also seamlessly supports Romanized and code-mixed Hindi, making it highly versatile for real-world applications. Check out the paper for more details about training, evaluation! Give our model a try!Download LLaMA-3-Nanda-10B weights from Hugging Face and see its capabilities in action: |
|
Reading Group I organize the UMD Robotics Reading Group, a weekly meeting (Tuesdays, 5–6 pm) where we read and discuss recent papers on robot learning, manipulation, and humanoid robots. See the schedule for upcoming sessions and slides. |
|
Source code from Jon Barron's website. |