Trung Le

Assistant Professor@Monash University·澳大利亚·OpenReview

研究方向

Adversarial Machine Learning · meta-learning · Deep learning for Cyber security · Optimal transport · Generative model · generative adversarial network · VAE · deep domain adaptation · Online learning · Kernel methods · optimisation

Trung Le

Gradient-Aligned Calibration for Post-Training Quantization of Diffusion Models

On the Mechanisms of Collaborative Learning in VAE Recommenders

Antibody: Strengthening Defense Against Harmful Fine-Tuning for Large Language Models via Attenuating Harmful Gradient Influence

Align-SAM: Seeking Flatter Minima for Better Cross-Subset Alignment

Sharpness-Aware Minimization in Logit Space Efficiently Enhances Direct Preference Optimization

Beyond Uniformity: Sample and Frequency Meta Weighting for Post-Training Quantization of Diffusion Models

Mitigating Semantic Collapse in Generative Personalization with Test-Time Embedding Adjustment

DistillMoE: Multi-Faceted Knowledge Distillation for Cross-Tokenizer Embedding Models

K-Gen: Unlocking High-Resolution Data-Free Knowledge Distillation via Key Region Generation

Reflecting and Linking knowledge: Dynamic Label Structures for Prompt-based Continual Learning

Unlearn In a Blink

Free Lunch at Inference: Test-Time Refinement for Diffusion Models

Layer-Wise High-Impact Parameter Ratio Optimization in Post-Training Quantization for Large Language Models

STAR: Next-Scaled Autoregressive Model for Time Series Forecasting

Adaptive Layer-Wise Transformations for Post-Training Quantization of Large Language Models

Rethinking Output Alignment for 1-bit Post-Training Quantization of Large Language Models

Token-Regulated Group Relative Policy Optimization for Stable Reinforcement Learning in Large Language Models

Improving Generalization with Flat Hilbert Bayesian Inference

Geometry-Aware Collaborative Multi-Solutions Optimizer for Model Fine-Tuning with Parameter Efficiency

Unveiling m-Sharpness Through the Structure of Stochastic Gradient Noise

RepLoRA: Reparameterizing Low-rank Adaptation via the Perspective of Mixture of Experts

Improved Training Technique for Latent Consistency Models

Revisiting Prefix-tuning: Statistical Benefits of Reparameterization among Prompts

Token-Level Self-Play with Importance-Aware Guidance for Large Language Models

Zero-shot Mixed Precision Quantization via Joint Optimization of Data Generation and Bit Allocation

Fantastic Targets for Concept Erasure in Diffusion Models and Where To Find Them

Improving Generalization with Flat Hilbert Bayesian Inference

Promoting Ensemble Diversity with Interactive Bayesian Distributional Robustness for Fine-tuning Foundation Models

Boosting Multiple Views for pretrained-based Continual Learning

Exploiting Hierarchical Taxonomies in Pretrained Continual Learning

Optimization on Manifolds with Riemannian Jacobian Regularization

EraseDiff: Erasing Data Influence in Diffusion Models

Unified Perspectives on Signal-to-Noise Diffusion Models

SUN: Training-free Machine Unlearning via Subspace

Understanding Domain Generalization: A View of Necessity and Sufficiency

Agnostic Sharpness-Aware Minimization

Unified Deep Discrete Representation Learning Framework