At Lossfunk, a research lab, I’m working on self-driving intelligence, reasoning and hierarchical agents, using reinforcement learning and world models. I’m building symbolic reference policies, fast control and a detailed CARLA testbed. I also study continual learning for game-playing agents. Research blog: From reasoning to the road.
Research on knowledge distillation, representation learning, world models, and interpretability in a student-founded lab. Read more.
Agentic RAG, document intelligence, an internal MCP server, gesture recognition, and supply-chain AI for aerospace. Read more.
Department-led research across language models, autonomous drones, humanoid robotics, and medical AI. See all DSU work.
Worked on robot software with ROS, Raspberry Pi, and NVIDIA Jetson boards. Learned ROS 2 development while helping migrate existing systems from ROS 1 to ROS 2.
Built a portfolio of 24 Python projects: data visualisations, Tkinter GUIs, and an end-to-end chatbot, with project management on GitHub and Notion.
I fine-tune 0.5B-7B LLMs with QLoRA and 4/8-bit quantization, including deployment on Jetson Nano. I’m also testing diffusion language models and compression (PTQ/QAT/AWQ/GPTQ/pruning) for Indic text generation.
Mechanistic interpretability with SAEs: attention circuits, feature attribution, and the full SAE gallery from the KD paper. See the gallery.
Study of 18 vision models for PCOS ultrasound. A hybrid CNN-ViT performed best, and a three-stage deduplication pipeline cleaned much of the public dataset. Read more.
Four results on 1 GPU: a 1 µs chignolin fold, titin I27 force-pulling, an 8-protein ESMFold sweep in 12.9 s, and ESMFold calibration. Read more.
Object detection and computer vision for autonomous drone navigation.
Teleoperated robotic arm focused on low-latency control and precise manipulation.
Artificial Intelligence and Robotics Engineering (2023-2027). Designed and taught the LLM Engineering curriculum and lab manuals in my 5th semester, published on the university website - read the manual.
A student-founded lab where I worked on knowledge distillation and world models. Read more.
I lead the technical work at E-Cell DSU, from infrastructure to software for student ventures.
I served on the core committee of the Institution of Engineering and Technology (IET) DSU chapter and Roboverse. I helped run 10+ talks, workshops and hackathons on AI and robotics.
Executive Committee, IEEE RAS and IEEE CIS at DSU. 50+ workshops, talks, and hackathons. RAS & CIS Exceptional Volunteering Award, 2025, given to the top 10% of undergraduate researchers at the university.
NVIDIA Deep Learning Institute course on transformer fundamentals: attention, tokenization, and downstream NLP tasks.
AWS Cloud Practitioner EssentialsFoundational AWS knowledge: core services, security, billing, and the shared-responsibility model.
AWS Technical EssentialsHands-on coverage of compute, storage, databases, networking, and security on AWS.
Microsoft Learn: Benefits of Cloud ArchitectureCloud-architecture fundamentals: design principles, trade-offs, and Azure mappings.
Kaggle: Intro to Machine LearningKaggle's foundational ML course: model fitting, evaluation, and validation on tabular problems.
Altair RapidMiner Certified Data Science ProfessionalProfessional certification covering end-to-end data-science workflows on the Altair RapidMiner platform.
Symbolic driving policies and a physical testbed: Astra-authored code, inspectable CARLA decisions, local recordings and ongoing surface-physics work.
Research at ErdősInside Erdős AI Lab, the day-to-day research stack: knowledge distillation, mechanistic interpretability (SAEs), world models, and protein structure prediction. Includes a KD paper and the full SAE experiment gallery.
AI × Bio: Protein FoldingFour experiments on real proteins, all on 1 GPU: a 1 µs chignolin fold, titin I27 force-pulling, an 8-protein ESMFold sweep, and ESMFold calibration. Reproducible from the linked code.
India AI Impact Summit 2026I represented DSU in New Delhi, spoke with 250+ companies, and presented our work on LLM architecture, medical AI and autonomous drones.
SAE Experiments: KD paperToy-model validation of the KD minimum-width theorem plus three real-LM trials on Pythia-410M (24 layers × 6 checkpoints, full sparsity sweep) published on Hugging Face.
Language Modeling ExperimentationFine-tuning Qwen 0.5B-7B for low-resource Indic languages; deploying Gemma 3 1B on Jetson Nano. Diffusion-LM and compression threads now live.
Medical AI: PCOS DetectionBenchmark of 18 vision models on PCOS ultrasound. A hybrid CNN-ViT hit 99.81%. A three-stage dedup pipeline cleaned 70% of the public dataset.
If you’re working on reinforcement learning, world models or self-driving, I’d like to hear from you.
nileshsarkar.cs@gmail.comIf you’re working on reinforcement learning, world models or self-driving, I’d like to hear from you.