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

Miao Liu

2 indexed papers

Recent (6 mo)
2
With code
0
Influential cites
0
Benchmarked
0

Publications per year

2
26

Top categories

AI×2Vision×1Software Eng.×1NLP×1Crypto×1

Frequent co-authors

Yueyi Liu1×
Chi Zhang1×
Sen Cui1×
Simiao Liu1×
Fang Liu1×
Li Zhang1×

Research Timeline

2026
ContraFix: Agentic Vulnerability Repair via Differential Runtime Evidence and Skill Reuse

ContraFix is an agentic framework that improves automated vulnerability repair by using differential runtime evidence to pinpoint the root cause of bugs, achieving state-of-the-art performance on major benchmarks.

ElasticTTT: Prior-Preserving Test-Time Tuning for Video Editing

This paper introduces ElasticTTT, a framework to preserve the generative prior in Test-Time Tuning (TTT) of pretrained diffusion models for video editing, preventing Prior Collapse.

Highlighted terms show continued research focus across papers

Papers

cs.CVcs.AIEmpiricalRecentJul 23, 2026

ElasticTTT: Prior-Preserving Test-Time Tuning for Video Editing

Yueyi Liu, Chi Zhang, Sen Cui, Miao Liu

This paper introduces ElasticTTT, a framework to preserve the generative prior in Test-Time Tuning (TTT) of pretrained diffusion models for video editing, preventing Prior Collapse.

View →
cs.SEcs.AIcs.CLRecent
May 17, 2026

ContraFix: Agentic Vulnerability Repair via Differential Runtime Evidence and Skill Reuse

Simiao Liu, Fang Liu, Li Zhang, Yang Liu +1 more

ContraFix is an agentic framework that improves automated vulnerability repair by using differential runtime evidence to pinpoint the root cause of bugs, achieving state-of-the-art performance on majo…

View →