Yang Shi
6 indexed papers
Publications per year
Top categories
Frequent co-authors
Research Timeline
The paper establishes the first theoretical framework for analyzing the learnability of Test-Time Adaptation (TTA) under non-stationary data streams by introducing Recovery Complexity, which quantifies the long-term reliability of TTA.
The paper establishes the first theoretical framework for analyzing the learnability of Test-Time Adaptation (TTA) under non-stationary data streams by introducing Recovery Complexity, which quantifies the long-term reliability of TTA.
The paper demonstrates that audio-language models often ignore conflicting audio evidence in favor of text, and proposes a training-free decoding rule, GACL, that significantly improves faithfulness by correcting this arbitration bias.
The paper demonstrates that audio-language models often ignore conflicting audio evidence in favor of text, and proposes a training-free decoding rule, GACL, that significantly improves faithfulness by correcting this arbitration bias.
The authors present HELMSMAN, a high-performance and cost-effective clustering-based ANNS system for large-scale social networks.
This paper introduces Positive--Direction Matching (PDM), a branch-aware on-policy distillation objective to address Negative Branch Asymmetry (NBA) in diffusion models under classifier-free guidance.
Papers
Rethinking Classifier-Free Guidance in On-Policy Diffusion Distillation
Bingnan Li, Haozhe Wang, Haozhong Xiong, Fangtai Wu +4 more
This paper introduces Positive--Direction Matching (PDM), a branch-aware on-policy distillation objective to address Negative Branch Asymmetry (NBA) in diffusion models under classifier-free guidance.