学者档案2024-2026
Ziquan Liu
Queen Mary University of London
8论文数
0末位作者
27合作者人数
1一作
0独著
一作与末位作者按论文署名顺序统计,部分顶会采用姓氏字母顺序署名。
近期论文8
- Confidence Should Be Calibrated More Than One Turn Deep第 5 位,共 6 位作者ACL 2026 · 2 次引用
- GrACE: A Generative Approach to Better Confidence Elicitation and Efficient Test-Time Scaling in Large Language Models第 2 位,共 3 位作者ACL 2026
- V-STaR: Benchmarking Video-LLMs on Video Spatio-Temporal Reasoning第 3 位,共 6 位作者CVPR Findings 2026
- PROSAC: Provably Safe Certification for Machine Learning Models under Adversarial Attacks第 2 位,共 6 位作者AAAI 2025 · 15 次引用
- ConformalSAM: Unlocking the Potential of Foundational Segmentation Models in Semi-Supervised Semantic Segmentation with Conformal Prediction第 2 位,共 7 位作者ICCV 2025 · 3 次引用
- Temporal Unlearnable Examples: Preventing Personal Video Data from Unauthorized Exploitation by Object Tracking第 4 位,共 8 位作者ICCV 2025 · 2 次引用
- AIM-Fair: Advancing Algorithmic Fairness via Selectively Fine-Tuning Biased Models with Contextual Synthetic Data第 2 位,共 3 位作者CVPR 2025
- The Pitfalls and Promise of Conformal Inference Under Adversarial Attacks第 1 位,共 7 位作者ICML 2024 · 9 次引用
