21 citations · 57 across the 21 of their papers we have counts for
21 papers
TransPrune: Token Transition Pruning for Efficient Large Vision-Language Model
Ao Li, Yuxiang Duan, Jinghui Zhang +5
Large Vision-Language Models (LVLMs) have advanced multimodal learning but face high computational costs due to the large number of visual tokens, motivating token pruning to impro…
Kalman Filter Enhanced GRPO for Reinforcement Learning-Based Language Model Reasoning
Hu Wang, Congbo Ma, Ian Reid +1
The advantage function is a central concept in RL that helps reduce variance in policy gradient estimates. For language modeling, Group Relative Policy Optimization (GRPO) was prop…
In-Model Merging for Enhancing the Robustness of Medical Imaging Classification Models
Hu Wang, Ibrahim Almakky, Congbo Ma +2
Model merging is an effective strategy to merge multiple models for enhancing model performances, and more efficient than ensemble learning as it will not introduce extra computati…
Rethinking Weight-Averaged Model-merging
Hu Wang, Congbo Ma, Ibrahim Almakky +3
Model merging, particularly through weight averaging, has shown surprising effectiveness in saving computations and improving model performance without any additional training. How…
Human-AI Collaborative Multi-modal Multi-rater Learning for Endometriosis Diagnosis
Hu Wang, David Butler, Yuan Zhang +5
Endometriosis, affecting about 10% of individuals assigned female at birth, is challenging to diagnose and manage. Diagnosis typically involves the identification of various signs…
Rethinking Transformer-based Multi-document Summarization: An Empirical Investigation
Congbo Ma, Wei Emma Zhang, Dileepa Pitawela +2
The utilization of Transformer-based models prospers the growth of multi-document summarization (MDS). Given the huge impact and widespread adoption of Transformer-based models in…
Disentangling Specificity for Abstractive Multi-document Summarization
Congbo Ma, Wei Emma Zhang, Hu Wang +2
Multi-document summarization (MDS) generates a summary from a document set. Each document in a set describes topic-relevant concepts, while per document also has its unique content…
Meta-Learned Modality-Weighted Knowledge Distillation for Robust Multi-Modal Learning with Missing Data
Hu Wang, Salma Hassan, Yuyuan Liu +12
In multi-modal learning, some modalities are more influential than others, and their absence can have a significant impact on classification/segmentation accuracy. Addressing this…
Learnable Cross-modal Knowledge Distillation for Multi-modal Learning with Missing Modality
Hu Wang, Congbo Ma, Jianpeng Zhang +4
The problem of missing modalities is both critical and non-trivial to be handled in multi-modal models. It is common for multi-modal tasks that certain modalities contribute more c…
Multi-modal Learning with Missing Modality via Shared-Specific Feature Modelling
Hu Wang, Yuanhong Chen, Congbo Ma +3
The missing modality issue is critical but non-trivial to be solved by multi-modal models. Current methods aiming to handle the missing modality problem in multi-modal tasks, eithe…
Document-aware Positional Encoding and Linguistic-guided Encoding for Abstractive Multi-document Summarization
Congbo Ma, Wei Emma Zhang, Pitawelayalage Dasun Dileepa Pitawela +3
One key challenge in multi-document summarization is to capture the relations among input documents that distinguish between single document summarization (SDS) and multi-document…
Uncertainty-aware Multi-modal Learning via Cross-modal Random Network Prediction
Hu Wang, Jianpeng Zhang, Yuanhong Chen +4
Multi-modal learning focuses on training models by equally combining multiple input data modalities during the prediction process. However, this equal combination can be detrimenta…
Dependency Structure for News Document Summarization
Congbo Ma, Wei Emma Zhang, Hu Wang +2
In this work, we develop a neural network based model which leverages dependency parsing to capture cross-positional dependencies and grammatical structures. With the help of lingu…
Data Hiding with Deep Learning: A Survey Unifying Digital Watermarking and Steganography
Zihan Wang, Olivia Byrnes, Hu Wang +5
The advancement of secure communication and identity verification fields has significantly increased through the use of deep learning techniques for data hiding. By embedding infor…
Kernel Adversarial Learning for Real-world Image Super-resolution
Hu Wang, Congbo Ma, Jianpeng Zhang +2
Current deep image super-resolution (SR) approaches aim to restore high-resolution images from down-sampled images or by assuming degradation from simple Gaussian kernels and addit…
Multi-intersection Traffic Optimisation: A Benchmark Dataset and a Strong Baseline
Hu Wang, Hao Chen, Qi Wu +3
The control of traffic signals is fundamental and critical to alleviate traffic congestion in urban areas. However, it is challenging since traffic dynamics are complicated in real…
The 10 Research Topics in the Internet of Things
Wei Emma Zhang, Quan Z. Sheng, Adnan Mahmood +7
Since the term first coined in 1999 by Kevin Ashton, the Internet of Things (IoT) has gained significant momentum as a technology to connect physical objects to the Internet and to…
Multi-document Summarization via Deep Learning Techniques: A Survey
Congbo Ma, Wei Emma Zhang, Mingyu Guo +2
Multi-document summarization (MDS) is an effective tool for information aggregation that generates an informative and concise summary from a cluster of topic-related documents. Our…
Multi-label Thoracic Disease Image Classification with Cross-Attention Networks
Congbo Ma, Hu Wang, Steven C. H. Hoi
Automated disease classification of radiology images has been emerging as a promising technique to support clinical diagnosis and treatment planning. Unlike generic image classific…
Randomized Online CP Decomposition
Congbo Ma, Xiaowei Yang, Hu Wang
CANDECOMP/PARAFAC (CP) decomposition has been widely used to deal with multi-way data. For real-time or large-scale tensors, based on the ideas of randomized-sampling CP decomposit…
Unsupervised Representation Learning by Predicting Random Distances
Hu Wang, Guansong Pang, Chunhua Shen +1
Deep neural networks have gained tremendous success in a broad range of machine learning tasks due to its remarkable capability to learn semantic-rich features from high-dimensiona…