Through the first systematic study of TTA for dense depth regression (eight baselines), it is shown that existing TTA methods consistently fail in this setting: entropy-based methods degrade regardless of the number of adapted parameters, and temporal-photometric adaptation diverges on non-rigid tissue.
Sheng-Yao Wang, Jun-Pei Xue, Xin Zhong et al.· IEEE Transactions on Medical...· 1 citation
Neural audio watermarks are increasingly deployed in commercial speech generation systems to make AI-generated speech traceable, yet their robustness has been studied mainly under conventional signal distortions. Since a watermark can be regarded as imperceptible noise added to the speech signal, a natural question is...
Xin Zhong, Sheng-Yao Wang, Ling-Feng Yao et al.· 0 citations
SMem is presented, an architecture whose context representation is a cache by construction whose context representation is a cache by construction, keeping perplexity comparable while making the cache exactly composable and editable.
Proxy Manifold Alignment (PMA), a novel attack against E2EO in privacy-preserving LLMs, which employs Word2Vec to model the co-occurrence patterns within the obfuscated stream and the public corpus independently, and constructs two proxy vector embeddings.
Si-Cong Li, Ling-Feng Yao, Xing-Ke Yang et al.· 0 citations
PhysWave unifies natural-language and trajectory control through a shared waypoint-caption representation, and augments diffusion training with two differentiable acoustic priors: spherical-harmonic direction consistency and inverse-square distance consistency that help generate spatially consistent FOA audio while mai...
Ling-Feng Yao, Chenpei Huang, Xing-Ke Yang et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
