Publications
MLLM, LLM, MCP & Multi-Agent
M3-Bench: Multi-Modal, Multi-Hop, Multi-Threaded Tool-Using MLLM Agent Benchmark
(arXiv, Submitted on 21 Nov 2025)
LED: LLM Enhanced Open-Vocabulary Object Detection without Human Curated Data Generation
(arXiv, OpenReview Submitted)
Your Reward Function for RL is Your Best PRM for Search: Unifying RL and Search-Based TTS
(arXiv, OpenReview Submitted)
Computer Vision
A Multimodal Spatio‑Temporal GCN Model with Enhancements for Isolated Sign Recognition
(LREC‑COLING 2024)
A Review of Convolutional Neural Network Architectures and Their Optimizations
(Artificial Intelligence Review, IFÂ 9.588/Q1)
Diffusion Models for Sign Language Video Anonymization
(LREC‑COLING 2024)
Previous Work
Modeling & Data Analysis
A Multistory Building Evacuation Model Based on Multiple‑Factor Analysis
(Advances in Civil Engineering, IFÂ 1.924/Q3)
Signals & Systems
The Excitation and Detection of Lamb Waves in a Droplet‑Loaded Plate Using Air‑Coupled Ultrasonic Transducers
(Measurement, IFÂ 5.131/Q1)
Quasi‑Dispersion of Air‑Coupled Ultrasonic Signal for Angle‑Dependent Reception
(Measurement, IFÂ 5.131/Q1)
Multiphysics Model of Lamb Waves Propagation in a Plate Loaded with Droplets
(ICCARÂ 2019, IEEE)
Multiple Reflective Signal Reception in Gas Flow Measurement Using Air‑Coupled Leaky Lamb Waves
(Measurement, IFÂ 5.131/Q1)