GPU-Accelerated Quantum Error Detection
Simulated quantum circuits with stochastic Pauli error channels using cuQuantum tensor-network statevector backends, developing statistical sampling algorithms to isolate gate errors under NISQ regimes.
May 15, 2026
High-Fidelity AI Video Generation Engine (LTX-2.5)
Ultra-low-latency video generation pipeline utilizing LTX-2.5 Diffusion Transformer (DiT) on NVIDIA RTX 5080 GPU, featuring custom NVFP4 quantized GEMM kernels and asynchronous pinned-memory weight offloading.
Mar 1, 2026
Conditional Diffusion Models for Protein Trajectories (PyTAO)
Designed and trained conditional diffusion generative models to sample continuous molecular dynamics and biomolecular trajectories on Slurm HPC, bypassing expensive QM/MM simulations (published in ACS JCTC).
Jan 15, 2026
Custom AI Development IDE & Agent Runtime
Architected an extensible AI development environment integrating Model Context Protocol (MCP) to orchestrate multi-step tool-calling workflows, backed by a scalable agent runtime on AWS EC2 and optimized edge SLM inference.
Oct 1, 2025
Idea Density prediction with LLaMA
training LLaMA3.2 to predict idea density scores of text
Aug 21, 2025
Agentic GraphRAG Recommender System
Published at AAAI 2025. Architected an autonomous multi-agent recommendation engine using GraphRAG (Neo4j) and dense vector retrieval (Qdrant) to resolve combinatorial degree requirements with human-in-the-loop verification.
Mar 25, 2025
Automated Debug Assistant & Concurrency Scheduler OS
Implemented an automated LLM debugging assistant in C++ interfacing with Ollama REST APIs with mutex locks, deadlock prevention, and Dask distributed parallelization on Slurm HPC clusters.
Dec 1, 2023
Personality Detection
A research to detect big-5 personality traits from patient life-narrative interview transcripts
Oct 26, 2023