4 papers · 1 filter
MixiMotion: One-Step Text-to-Motion Generation via Asymmetric Set Distillation
Hung Dinh, Binh Mai, Tran Quoc Bao Le +2
Iterative text-to-motion generation delivers high-quality and semantically aligned motions but requires multiple network evaluations, resulting in substantial inference latency. We…
SpatialQuery: Benchmarking Geometry-Grounded Multi-Instance Spatial Reasoning in Vision-Language Models
Hai Nguyen, Tung Vu, Cong Tran
Vision-language models (VLMs) achieve strong semantic understanding but remain unreliable in metric spatial reasoning, particularly when queries require comparing multiple instance…
SwiftAudio: Data-Efficient Caption-Only Distillation for One-Step Text-to-Audio Diffusion-based Generation
Binh Mai, Tran Quoc Bao Le, Hung Dinh +1
Diffusion-based text-to-audio (TTA) models achieve impressive synthesis quality but suffer from high inference latency due to iterative multi-step denoising. Existing one-step appr…
Toward Fine-Grained Speech Inpainting Forensics:A Dataset, Method, and Metric for Multi-Region Tampering Localization
Tung Vu, Yen Nguyen, Hai Nguyen +2
Recent advances in voice cloning and text-to-speech synthesis have made partial speech manipulation - where an adversary replaces a few words within an utterance to alter its meani…