9 papers
NSR-Boost: A Neuro-Symbolic Residual Boosting Framework for Industrial Legacy Models
Ziming Dai, Dabiao Ma, Jinle Tong +5
Although the Gradient Boosted Decision Trees (GBDTs) dominate industrial tabular applications, upgrading legacy models in high-concurrency production environments still faces prohi…
TS-PEFT: Unveiling Token-Level Redundancy in Parameter-Efficient Fine-Tuning
Dabiao Ma, Ziming Dai, Zhimin Xin +3
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…
Out-of-Distribution Detection Based on Total Variation Estimation
Dabiao Ma, Zhiba Su, Jian Yang +1
This paper introduces a novel approach to securing machine learning model deployments against potential distribution shifts in practical applications, the Total Variation Out-of-Di…
QvTAD: Differential Relative Attribute Learning for Voice Timbre Attribute Detection
Zhiyu Wu, Jingyi Fang, Yufei Tang +3
Voice Timbre Attribute Detection (vTAD) plays a pivotal role in fine-grained timbre modeling for speech generation tasks. However, it remains challenging due to the inherently subj…
Leveraging MLLM Embeddings and Attribute Smoothing for Compositional Zero-Shot Learning
Xudong Yan, Songhe Feng, Yang Zhang +3
Compositional zero-shot learning (CZSL) aims to recognize novel compositions of attributes and objects learned from seen compositions. Previous works disentangle attributes and obj…
Qieemo: Speech Is All You Need in the Emotion Recognition in Conversations
Jinming Chen, Jingyi Fang, Yuanzhong Zheng +2
Emotion recognition plays a pivotal role in intelligent human-machine interaction systems. Multimodal approaches benefit from the fusion of diverse modalities, thereby improving th…