Interests in adaptive decision-making under partial observability, spanning reinforcement learning, multimodal sensing, and large-scale AI systems. Extensive experience deploying AI systems in real-world and resource-constrained environments, using ML training and inference performance improvements, with scalable resource-efficient architectures and optimizations (exploiting quantization / distillation / heuristics), over collected, curated, and existing multimodal data.
Research Works
AAAI’26:
Self-Regulating Cars: Automating Traffic Control in Free Flow Road Networks
Paper
NeurIPS’23:
AirDelhi: Fine-Grained Spatio-Temporal Particulate Matter Dataset From Delhi For ML based Modeling
Paper Code
NeurIPS’20:
EcoLight: Intersection Control in Developing Regions Under Extreme Budget and Network Constraints
Paper Code
ACM-JCSS’24:
FrugalLight: Symmetry-Aware Cyclic Heterogeneous Intersection Control using Deep RL with Model Compression, Distillation & Domain Knowledge
Paper Code
ACM-COMPASS’24:
WebLight: Deep RL based Multi-modal Intersection Control in Developing Countries without Reliable Cameras
Paper Code
ACM-COMPASS’22:
DynCNN: Application Dynamism and Ambient Temperature Aware Neural Network Scheduler in Edge Devices for Traffic Control
Paper
NeurIPS’23 (Workshop on Computational Sustainability)
RealLight: DRL based Intersection Control in Developing Countries without Traffic Simulators Paper