AI researcher at Delhi Technological University, working on world models for embodied AI, safer generative systems, and AI safety research.
Available for research & engineering roles
About
I work at the intersection of deep learning and real-world systems — deploying vision pipelines on drones and embedded platforms, and researching 6-DoF spacecraft pose estimation and safe text-to-image diffusion models.
- Education
- B.Tech, Computer Science & Engineering — Delhi Technological University.
- Affiliations
- UAS-DTU · ML Research Lab, DTU · Pragya Lab, BITS Goa.
Skills
- Languages
- Python
- C/C++
- SQL
- Frameworks
- PyTorch
- Scikit-Learn
- HuggingFace
- mmcv
- Docker
- Linux
- CUDA
- Git
- Hardware
- Jetson Orin
- Jetson Nano
- Raspberry Pi
- Arduino
- Pixhawk Cube
Experience
- May 2025 – PresentAdvisor: Dr. Anil Parihar · Hybrid
Deep Learning Researcher
Machine Learning Research Lab, DTU- ISRO-sponsored project on 6D spacecraft pose estimation using vision transformers.
- Built T.A.R.S — a 100K-image synthetic spacecraft pose dataset across orbital + illumination conditions.
- Mar 2026 – May 2026Advisor: Dr. Amitava Das · Remote
Research Intern
Pragya Lab, BITS Goa- Research on diffusion-based T2I models, AI safety and decoding-time alignment.
- Adversarial jailbreak attacks, RL control policies, localized inpainting for safe generation.
- Aug 2024 – Nov 2025On-Site
Robotics & Software Engineer
Unmanned Aerial Systems Lab, DTU- Deployed real-time CV pipelines on UAV/UGV embedded hardware with Docker + TensorRT.
- Self-refining VLM trauma detection pipeline — ~80% accuracy on DARPA emergency dataset.
Projects
Llava-Lens
Logit-Lens interpretability for VLMs. Prompt-free transformer classifier over VLM logits — 83% on DARPA dataset.
- PyTorch
- Transformers
- VLMs
ViT 6-DoF Pose
ViT-from-scratch on CIFAR-10 (76.5%). CLS-token 6D satellite pose via ViT-B transfer. Jetson Orin + TensorRT @ 17ms.
- PyTorch
- TensorRT
- Docker
- Jetson Orin
Wirefall
BERT-based web firewall trained on 2M safe HTTP requests · 98% accuracy. Novel KD-LoRA continual learning. 45ms inference.
- BERT
- LoRA
- FastAPI
- NGINX
- Docker
Research
SPACE-HOP: Spacecraft 6-DoF Pose Estimation using Embedding-Predictive Pretraining and Hopf Map
JEPA pre-training for 6-DoF pose. Sub-degree accuracy via classification+refinement with discrete Hopf grid and continuous Lie offsets.
GuardPaint: Speculative Safety Decoding for Text-to-Image Generation
Decoding-time alignment combining timestep-aware localized inpainting with a REINFORCE diffusion policy over CFG, noise jitter and DDIM inversion.
Achievements
- $210K2nd Prize · DARPA Triage Challenge 2024 & 2025 (UAS-DTU)
- TOP 5Finalist · Smart India Hackathon 2025 (ISRO PS)
- TOP 12National Finalist · NCIIPC–AICTE Pentathon 2025
- 2NDVisionxAI Hackathon · DL-based CCTV tracking
Contact
Open to research collaborations and full-time opportunities. Reach out anytime.
arshabbas636@gmail.com