Dabiao Ma

2 accepted papers

2026

OUT-OF-DISTRIBUTION DETECTION BASED ON TOTAL VARIATION ESTIMATION

ICASSP 2026poster

This paper introduces a novel approach to securing machine learning model deployments against potential distribution shifts in practical applications, the Total Variation Out-of-Distribution (TV-OOD) detection method. Existing methods have produced satisfactory results, but TV-OOD improves upon thes…

Cited by 0 Source ↗PDF ↗Scholar ↗

2026

TS-PEFT: Unveiling Token-Level Redundancy in Parameter-Efficient Fine-Tuning

Dabiao Ma, Ziming Dai, Zhimin Xin, Shu Wang, Jian Yang, Haojun Fei

IJCAI 2026

Current Parameter-Efficient Fine-Tuning (PEFT) methods typically operate under an implicit assumption: once a target module is selected, every token passing through it contributes equally to the downstream task and requires a parameter update. In this paper, we challenge this convention by revealing

Cited by 0 Scholar ↗