works on

From the 1 of 8 linked papers with an AI index.

collaborators

8 papers

cs.CV2026

GHR-VLM: Making Zero-Shot Transit Video Analytics Realizable with Grounded Hybrid Reasoning

Kaicong Huang, Weiheng Oh, Ruimin Ke +2

The paper introduces GHR-VLM, a framework that combines edge-based visual grounding with a vision‑language model to perform zero‑shot analytics of bus surveillance video, identifyi…

cs.RO2026

CARLA-GS: Decoupling Representation, Reasoning, and Physics Simulation for Autonomous Driving Corner-Case Synthesis

Kaicong Huang, Meng Ma, Ruimin Ke

Safety evaluation for autonomous driving is dominated by rare, safety-critical interactions, motivating simulators that can deliberately synthesize corner cases with photorealistic…

quant-ph2026

Impact-Driven Quantum Decomposition for Traffic Zone Partitioning: A Hybrid Gate-Model Framework

Ruimin Ke, Talha Azfar, Kaicong Huang +1

Partitioning transportation networks into balanced and spatially coherent traffic zones is a fundamental yet computationally challenging task in intelligent transportation systems.…

cs.CV2026

Real2Sim: A Physics-driven and Editable Gaussian Splatting Framework for Autonomous Driving Scenes

Kaicong Huang, Talha Azfar, Weisong Shi +1

Reliable autonomous driving relies on large-scale, well-labeled data and robust models. However, manual data collection is resource-intensive, and traditional simulation suffers fr…

cs.CV2026

iPay: Integrated Payment Action Recognition via Multimodal Networks and Adaptive Spatial Prior Learning

Kaicong Huang, Weiheng Oh, Thomas Guggisberg +1

Automated transit payment analysis is vital for scalable fare auditing and passenger analytics, yet practice still relies on limited manual inspection. Prior vision- and skeleton-b…

cs.CV2025

TransitReID: Transit OD Data Collection with Occlusion-Resistant Dynamic Passenger Re-Identification

Kaicong Huang, Talha Azfar, Jack Reilly +1

Transit Origin-Destination (OD) data are fundamental for optimizing public transit services, yet current collection methods, such as manual surveys, Bluetooth/WiFi tracking, and Au…