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

Ke Liu

2 indexed papers

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

Publications per year

2
26

Top categories

AI×2Multimedia×1Sound×1

Frequent co-authors

Jiwei Wei2×
Yang Yang2×
Xiang Li1×
Yitong Qin1×
Jinyu Guo1×
Malu Zhang1×

Research Timeline

2026
From Talking to Singing: A New Challenge for Audio-Visual Deepfake Detection

The paper introduces a new dataset (SHDF) and a framework (T-AVFD) to robustly detect audio-visual deepfakes, specifically addressing the challenge posed by singing vocalizations.

eMoT: evolving Memory-of-Thought via Symbolic Anchoring and Memory Corrosion

The eMoT framework enhances multi-step reasoning in LLMs by treating reasoning as an evolving memory, stabilizing performance through symbolic computation and structured refinement.

Highlighted terms show continued research focus across papers

Papers

cs.AIRecentJun 1, 2026

eMoT: evolving Memory-of-Thought via Symbolic Anchoring and Memory Corrosion

Xiang Li, Jiwei Wei, Ke Liu, Yitong Qin +4 more

The eMoT framework enhances multi-step reasoning in LLMs by treating reasoning as an evolving memory, stabilizing performance through symbolic computation and structured refinement.

View →
cs.AIcs.MMcs.SDRecentMay 27, 2026

From Talking to Singing: A New Challenge for Audio-Visual Deepfake Detection

Ke Liu, Jiwei Wei, Wenyu Zhang, Shuchang Zhou +4 more

The paper introduces a new dataset (SHDF) and a framework (T-AVFD) to robustly detect audio-visual deepfakes, specifically addressing the challenge posed by singing vocalizations.

View →