Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:
ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Home/Authors/Yang Shi

Yang Shi

6 indexed papers

Recent (6 mo)
6
With code
0
Influential cites
0
Benchmarked
0

Publications per year

6
26

Top categories

AI×3ML×3Sound×2NLP×2Vision×1Info Retrieval×1

Frequent co-authors

Yichen Gao2×
Yiqun Zhang2×
Zijing Wang2×
Yujia Li2×
Heng Guo2×
Xi Wu2×

Research Timeline

2026
On the Learnability of Test-Time Adaptation: A Recovery Complexity Perspective

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.

On the Learnability of Test-Time Adaptation: A Recovery Complexity Perspective

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.

Beyond Text Following: Repairable Arbitration Reversals in Audio-Language Models

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.

Beyond Text Following: Repairable Arbitration Reversals in Audio-Language Models

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 Clustering Strikes Back: Building Cost-Effective and High-Performance ANNS at Scale with Helmsman

The authors present HELMSMAN, a high-performance and cost-effective clustering-based ANNS system for large-scale social networks.

Rethinking Classifier-Free Guidance in On-Policy Diffusion Distillation

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.

Highlighted terms show continued research focus across papers

Papers

cs.CVcs.AIcs.LGEmpiricalRecentJul 27, 2026

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.

View →
cs.IREmpirical
Recent
Jun 11, 2026

The Clustering Strikes Back: Building Cost-Effective and High-Performance ANNS at Scale with Helmsman

Yuchen Huang, Baiteng Ma, Yiping Sun, Yang Shi +6 more

The authors present HELMSMAN, a high-performance and cost-effective clustering-based ANNS system for large-scale social networks.

View →
cs.SDcs.CLRecentJun 3, 2026

Beyond Text Following: Repairable Arbitration Reversals in Audio-Language Models

Yichen Gao, Yiqun Zhang, Zijing Wang, Yujia Li +6 more

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 b…

View →
cs.SDcs.CLRecentJun 3, 2026

Beyond Text Following: Repairable Arbitration Reversals in Audio-Language Models

Yichen Gao, Yiqun Zhang, Zijing Wang, Yujia Li +6 more

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 b…

View →
cs.LGcs.AIRecentMay 27, 2026

On the Learnability of Test-Time Adaptation: A Recovery Complexity Perspective

Zhi Zhou, Ming Yang, Shi-Yu Tian, Kun-Yang Yu +2 more

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 quantifie…

View →
cs.LGcs.AIRecentMay 27, 2026

On the Learnability of Test-Time Adaptation: A Recovery Complexity Perspective

Zhi Zhou, Ming Yang, Shi-Yu Tian, Kun-Yang Yu +2 more

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 quantifie…

View →