1 citations · 1 across the 10 of their papers we have counts for
10 papers
Dynamic Alignment Compensation for Hallucination Mitigation in Large Vision-Language Models
Kairong Yu, Zixin Zhu, Le Yu +1
Large Vision-Language Models (LVLMs) remain prone to hallucinations, producing responses that are irrelevant or inconsistent with the multimodal input. Existing mitigation methods…
TEAMMix: Taxonomy Enrichment Augmentation and Minority-augmented Mixing Strategy for LLM-enhanced Weak-Supervised Hierarchical Text Classification
Jian Zhang, Zhuohao Yang, Songlin Lei +6
Hierarchical Text Classification (HTC), as a critical text mining task, faces challenges such as complex label hierarchies and class imbalance. Existing methods based on large lang…
Self-Knowledge Retrieval Augmented Generation Framework for Patent Matching
Jian Zhang, Songlin Lei, Zhuohao Yang +6
Patent retrieval and matching based on large language models (LLMs) play a vital role in intellectual property protection. However, due to the complex structure of patent documents…
Head-Tail-Aware KL Divergence in Knowledge Distillation for Spiking Neural Networks
Tianqing Zhang, Zixin Zhu, Kairong Yu +1
Spiking Neural Networks (SNNs) have emerged as a promising approach for energy-efficient and biologically plausible computation. However, due to limitations in existing training me…
TS-SNN: Temporal Shift Module for Spiking Neural Networks
Kairong Yu, Tianqing Zhang, Qi Xu +2
Spiking Neural Networks (SNNs) are increasingly recognized for their biological plausibility and energy efficiency, positioning them as strong alternatives to Artificial Neural Net…
Temporal Separation with Entropy Regularization for Knowledge Distillation in Spiking Neural Networks
Kairong Yu, Chengting Yu, Tianqing Zhang +5
Spiking Neural Networks (SNNs), inspired by the human brain, offer significant computational efficiency through discrete spike-based information transfer. Despite their potential t…
STAA-SNN: Spatial-Temporal Attention Aggregator for Spiking Neural Networks
Tianqing Zhang, Kairong Yu, Xian Zhong +3
Spiking Neural Networks (SNNs) have gained significant attention due to their biological plausibility and energy efficiency, making them promising alternatives to Artificial Neural…
EIoU-EMC: A Novel Loss for Domain-specific Nested Entity Recognition
Jian Zhang, Tianqing Zhang, Qi Li +1
In recent years, research has mainly focused on the general NER task. There still have some challenges with nested NER task in the specific domains. Specifically, the scenarios of…
DA-LIF: Dual Adaptive Leaky Integrate-and-Fire Model for Deep Spiking Neural Networks
Tianqing Zhang, Kairong Yu, Jian Zhang +1
Spiking Neural Networks (SNNs) are valued for their ability to process spatio-temporal information efficiently, offering biological plausibility, low energy consumption, and compat…
FSTA-SNN:Frequency-based Spatial-Temporal Attention Module for Spiking Neural Networks
Kairong Yu, Tianqing Zhang, Hongwei Wang +1
Spiking Neural Networks (SNNs) are emerging as a promising alternative to Artificial Neural Networks (ANNs) due to their inherent energy efficiency. Owing to the inherent sparsity…