2 citations · 5 across the 20 of their papers we have counts for
21 papers
Conflict-Aware Logit Adapters for Utility-Preserving Anti-Distillation
Quoc Phong Dao, Binh Anh Nguyen, Linh Ngo Van +3
While reasoning traces improve model capability, they also provide supervision signals for downstream distillation. Initial efforts to mitigate this issue rely on decoding-time int…
Sharpness-Aware Minimization in Logit Space Efficiently Enhances Direct Preference Optimization
Haocheng Luo, Zehang Deng, Thanh-Toan Do +3
Direct Preference Optimization (DPO) has emerged as a popular algorithm for aligning pretrained large language models with human preferences, owing to its simplicity and training s…
Efficient Temporal-aware Matryoshka Adaptation for Temporal Information Retrieval
Tuan-Luc Huynh, Weiqing Wang, Trung Le +4
Retrievers are a key bottleneck in temporal Retrieval-Augmented Generation (RAG) systems: failing to retrieve temporally relevant context can degrade downstream generation, regardl…
Sharpness-Aware Data Generation for Zero-shot Quantization
Dung Hoang-Anh, Cuong Pham Trung Le, Jianfei Cai +1
Zero-shot quantization aims to learn a quantized model from a pre-trained full-precision model with no access to original real training data. The common idea in zero-shot quantizat…
MixLoRA-DSI: Dynamically Expandable Mixture-of-LoRA Experts for Rehearsal-Free Generative Retrieval over Dynamic Corpora
Tuan-Luc Huynh, Thuy-Trang Vu, Weiqing Wang +4
Continually updating model-based indexes in generative retrieval with new documents remains challenging, as full retraining is computationally expensive and impractical under resou…
Preserving Clusters in Prompt Learning for Unsupervised Domain Adaptation
Tung-Long Vuong, Hoang Phan, Vy Vo +4
Recent approaches leveraging multi-modal pre-trained models like CLIP for Unsupervised Domain Adaptation (UDA) have shown significant promise in bridging domain gaps and improving…
Optimizing Specific and Shared Parameters for Efficient Parameter Tuning
Van-Anh Nguyen, Thanh-Toan Do, Mehrtash Harandi +2
Foundation models, with a vast number of parameters and pretraining on massive datasets, achieve state-of-the-art performance across various applications. However, efficiently adap…
Enhancing Dataset Distillation via Non-Critical Region Refinement
Minh-Tuan Tran, Trung Le, Xuan-May Le +2
Dataset distillation has become a popular method for compressing large datasets into smaller, more efficient representations while preserving critical information for model trainin…
Why Domain Generalization Fail? A View of Necessity and Sufficiency
Long-Tung Vuong, Vy Vo, Hien Dang +5
Despite a strong theoretical foundation, empirical experiments reveal that existing domain generalization (DG) algorithms often fail to consistently outperform the ERM baseline. We…
AEON: Adaptive Estimation of Instance-Dependent In-Distribution and Out-of-Distribution Label Noise for Robust Learning
Arpit Garg, Cuong Nguyen, Rafael Felix +3
Robust training with noisy labels is a critical challenge in image classification, offering the potential to reduce reliance on costly clean-label datasets. Real-world datasets oft…
Coverage-Constrained Human-AI Cooperation with Multiple Experts
Zheng Zhang, Cuong Nguyen, Kevin Wells +3
Human-AI cooperative classification (HAI-CC) approaches aim to develop hybrid intelligent systems that enhance decision-making in various high-stakes real-world scenarios by levera…
Fair Distillation: Teaching Fairness from Biased Teachers in Medical Imaging
Milad Masroor, Tahir Hassan, Yu Tian +4
Deep learning has achieved remarkable success in image classification and segmentation tasks. However, fairness concerns persist, as models often exhibit biases that disproportiona…
Connective Viewpoints of Signal-to-Noise Diffusion Models
Khanh Doan, Long Tung Vuong, Tuan Nguyen +5
Diffusion models (DM) have become fundamental components of generative models, excelling across various domains such as image creation, audio generation, and complex data interpola…
MetaAug: Meta-Data Augmentation for Post-Training Quantization
Cuong Pham, Hoang Anh Dung, Cuong C. Nguyen +4
Post-Training Quantization (PTQ) has received significant attention because it requires only a small set of calibration data to quantize a full-precision model, which is more pract…
Learning to Complement and to Defer to Multiple Users
Zheng Zhang, Wenjie Ai, Kevin Wells +3
With the development of Human-AI Collaboration in Classification (HAI-CC), integrating users and AI predictions becomes challenging due to the complex decision-making process. This…
Model and Feature Diversity for Bayesian Neural Networks in Mutual Learning
Cuong Pham, Cuong C. Nguyen, Trung Le +3
Bayesian Neural Networks (BNNs) offer probability distributions for model parameters, enabling uncertainty quantification in predictions. However, they often underperform compared…
PromptDSI: Prompt-based Rehearsal-free Continual Learning for Document Retrieval
Tuan-Luc Huynh, Thuy-Trang Vu, Weiqing Wang +5
Differentiable Search Index (DSI) utilizes pre-trained language models to perform indexing and document retrieval via end-to-end learning without relying on external indexes. Howev…
Agnostic Sharpness-Aware Minimization
Van-Anh Nguyen, Quyen Tran, Tuan Truong +3
Sharpness-aware minimization (SAM) has been instrumental in improving deep neural network training by minimizing both the training loss and the sharpness of the loss landscape, lea…
Frequency Attention for Knowledge Distillation
Cuong Pham, Van-Anh Nguyen, Trung Le +3
Knowledge distillation is an attractive approach for learning compact deep neural networks, which learns a lightweight student model by distilling knowledge from a complex teacher…
DiffAugment: Diffusion based Long-Tailed Visual Relationship Recognition
Parul Gupta, Tuan Nguyen, Abhinav Dhall +3
The task of Visual Relationship Recognition (VRR) aims to identify relationships between two interacting objects in an image and is particularly challenging due to the widely-sprea…
Learning to Complement with Multiple Humans
Zheng Zhang, Cuong Nguyen, Kevin Wells +2
Real-world image classification tasks tend to be complex, where expert labellers are sometimes unsure about the classes present in the images, leading to the issue of learning with…