7 papers
PRISM: PRIvileged Sibling-guided Multi-Agent Topology Design
Phuong Tuan Dat, Qi Li, Xinchao Wang
Multi-agent systems (MAS) based on large language models (LLMs) have become a powerful way to address complex problems, and their effectiveness depends critically on the collaborat…
Disentangled Global-Local Feature Learning with E-Branchformer for Audio Deepfake Detection
Phuong Tuan Dat, Ho Bao Thu, Nguyen Tran Trung +2
The rapid advancement of voice synthesis technologies such as text-to-speech and voice conversion poses significant threats to speech-based authentication systems, necessitating ro…
KanAdapter: A Kolmogorov-Arnold Network-based Plug-and-Play Module for Efficient Fine-tuning of Foundation Speech Models
Phuong Tuan Dat, Phuong Khai Minh, Tran Huy Dat
Fully fine-tuning self-supervised learning (SSL) speech models for downstream tasks is computationally prohibitive, and existing parameter-efficient fine-tuning approaches predomin…
dOPSD: On-Policy Self-Distillation for Diffusion Language Models
Phuong Tuan Dat, Qi Li, Xinchao Wang
Diffusion large language models (dLLMs) generate text by iteratively denoising a masked sequence, offering a parallel alternative to autoregressive models, but eliciting strong rea…
VieSpeaker: A Large-Scale Vietnamese Speaker Recognition Dataset Beyond Visual Dependency
Viet Hoang Pham, Tran Trung Nguyen, Bao Thu Ho +2
Speaker recognition has advanced rapidly with large-scale training datasets, yet Vietnamese remains under-resourced, with existing corpora limited in scale and acoustic diversity.…
TACT-ful: Multi-Channel Terrain Affordance and Compliance Training for Payload-Robust Perceptive Humanoid Locomotion
Thanh Ly, Truong-Duy Dang, Chien Le +5
Foothold selection on structured terrain requires explicit reasoning about contact planarity, surface steepness, and kinematic reachability, properties not captured by a single hei…
VoxVietnam: a Large-Scale Multi-Genre Dataset for Vietnamese Speaker Recognition
Hoang Long Vu, Phuong Tuan Dat, Pham Thao Nhi +2
Recent research in speaker recognition aims to address vulnerabilities due to variations between enrolment and test utterances, particularly in the multi-genre phenomenon where the…