← Search

Zhifeng Han

2 accepted papers

2026

Flow2GAN: Hybrid Flow Matching and GAN with Multi-Resolution Network for One-/Two-step High-Fidelity Audio Generation

ICLR 2026poster

Existing dominant methods for audio generation include Generative Adversarial Networks (GANs) and diffusion-based methods like Flow Matching. GANs suffer from slow convergence and potential mode collapse during training, while diffusion methods require multi-step inference that introduces considerab…

Cited by 0SourcecodeScholar
2026

Speech-Audio Compositional Attacks on Multimodal LLMs and Their Defense with SALMONN-Guard

ICML 2026poster

Recent progress in large language models (LLMs) has enabled understanding of both speech and non-speech audio, but has also exposed new safety risks arising from complex audio inputs that are inadequately handled by current safeguards. We introduce SACRED-Bench (Speech–Audio Composition for RED-team…

Cited by 0SourceScholar