← Search

Yubin Qin

2 accepted papers

2026

Hidden in Plain Tokens: Simply Robust, Gradient-Free Watermark for Synthetic Audio

ICML 2026poster

As policy catches up with the capabilities of generative AI, watermarking is central to content provenance efforts. Inference-time watermarks for autoregressive models are unfit for continuous modalities due to discretization inconsistencies. Existing methods overcome this by finetuning the modality…

Cited by 0SourceScholar
2025

VideoHallu: Evaluating and Mitigating Multi-modal Hallucinations on Synthetic Video Understanding

NeurIPS 2025poster

Vision Language models (VLMs) have achieved remarkable success in video understanding tasks. Yet, a key question remains: Do they comprehend visual information or merely learn superficial mappings between visual and textual patterns? Understanding visual cues, particularly those related to physics…

Cited by 0SourcecodeScholar