Institution profile

University of Technology Sydney

Academic institutionaustralasia · au
Official website
Research library774linked papers
Opportunities0open roles
Selected work

Representative Papers

MAD: Multi-Alignment MEG-to-Text Decoding

Jun 03, 2024arXiv.org

Current non-invasive BCI-based language decoding faces three key bottlenecks: underutilization of magnetoencephalography (MEG) signals, poor cross-sentence generalization, and absence of multimodal fusion. Method: We propose the first end-to-end, multi-aligned MEG-to-text framework for natural language reconstruction from entirely unseen sentences. Our approach introduces a Transformer-based architecture that jointly aligns neural time series, phonemes, and semantics, integrating self-supervised pretraining with cross-modal contrastive learning to systematically unify speech, semantic, and dynamic temporal information. Results: On the Gwilliams dataset, our method achieves a BLEU-1 score of 10.44—improving by 4.95 (+93%) over the strongest baseline—demonstrating substantially enhanced open-vocabulary text generation capability. This work breaks critical limitations in generalizability and multimodal integration for non-invasive brain–computer interface–based language reconstruction.

18 citations3 influentialRead paper

ConjNorm: Tractable Density Estimation for Out-of-Distribution Detection

Feb 27, 2024International Conference on Learning Representations

Existing post-hoc out-of-distribution (OOD) detection methods rely on logits, distance metrics, or strong distributional assumptions, limiting their ability to accurately model true data density. To address this, we propose a unified density modeling framework based on Bregman divergences, reformulating density estimation as a differentiable optimization problem for the optimal norm coefficient $ p $. We first uncover a novel paradigm for exponential-family density modeling under conjugate constraints, leading to ConjNorm—a method that achieves unbiased, analytically differentiable density estimation without restrictive distributional assumptions. ConjNorm integrates Bregman divergence theory, exponential-family modeling, and Monte Carlo importance sampling. On CIFAR-100 and ImageNet-1K, it reduces false positive rate at 95% true positive rate (FPR95) by 13.25% and 28.19%, respectively, over prior state-of-the-art methods, significantly improving both OOD detection accuracy and robustness.

18 citations1 influentialRead paper

MVGS: Multi-view-regulated Gaussian Splatting for Novel View Synthesis

Oct 02, 2024arXiv.org

To address overfitting in 3D Gaussian Splatting (3DGS) under single-view supervision—leading to artifacts in novel-view synthesis and inaccurate geometric reconstruction—this paper proposes a multi-view collaborative optimization framework. Our method introduces three key innovations: (1) a novel multi-view regularization paradigm that jointly enforces consistency across multiple views; (2) an intrinsic-cross-guided coarse-to-fine training strategy integrating multi-scale geometric and appearance priors; and (3) ray-intersection-driven cross-view densification coupled with view-difference-aware adaptive densification. While preserving real-time rendering performance, our approach significantly improves both novel-view image fidelity and 3D geometric accuracy. Extensive experiments demonstrate strong generalization across diverse scenes and mainstream 3DGS variants, outperforming existing single-view methods in both qualitative and quantitative evaluations.

15 citations1 influentialRead paper

When Machine Unlearning Meets Retrieval-Augmented Generation (RAG): Keep Secret or Forget Knowledge?

Oct 20, 2024arXiv.org

Existing machine unlearning methods for large language models (LLMs) suffer from high computational overhead, poor generalizability, or catastrophic forgetting—posing significant ethical and legal risks due to residual sensitive information in model parameters. Method: We propose a lightweight, non-invasive RAG-based unlearning framework that formulates unlearning as a constrained optimization problem under dynamic knowledge base editing. Crucially, we introduce RAG as a plug-and-play unlearning interface—the first approach enabling effective unlearning on proprietary LLMs (e.g., ChatGPT, Gemini). Contribution/Results: The framework is systematically evaluated across five mainstream LLMs—including closed-source models—and fully satisfies the five core unlearning desiderata: effectiveness, universality, harmlessness, simplicity, and robustness. It further supports seamless extension to multimodal LLMs and LLM-based agents, offering a practical, scalable solution for responsible AI deployment.

8 citations1 influentialRead paper

TransFR: Transferable Federated Recommendation with Pre-trained Language Models

Feb 02, 2024arXiv.org

Traditional federated recommendation systems (FRS) suffer from three critical bottlenecks: poor cross-domain transferability, ineffectiveness under cold-start conditions, and privacy leakage. To address these challenges, this paper proposes the first transferable framework integrating general-purpose textual representations with federated learning. Our method leverages pre-trained language models (e.g., BERT) to generate domain-agnostic item semantic embeddings—eliminating reliance on discrete item IDs—and jointly optimizes a federated fine-tuning procedure with locally personalized prediction heads to enhance cold-start robustness. Furthermore, we incorporate differential privacy into the training process to ensure user-level privacy protection. Extensive experiments on multiple benchmark datasets demonstrate that our approach significantly outperforms state-of-the-art methods, achieving substantial improvements in recommendation accuracy, cross-domain transferability, and cold-start performance, while rigorously preserving privacy guarantees.

4 citations2 influentialRead paper
Recent publications

Latest Papers