collaborators

5 papers

cs.LG2026

Exemplar-Free Continual Learning for State Space Models

Isaac Ning Lee, Leila Mahmoodi, Trung Le +1

State-Space Models (SSMs) excel at capturing long-range dependencies with structured recurrence, making them well-suited for sequence modeling. However, their evolving internal sta…

cs.LG2026

Diverse Image Priors for Black-box Data-free Knowledge Distillation

Tri-Nhan Vo, Dang Nguyen, Trung Le +2

Knowledge distillation (KD) represents a vital mechanism to transfer expertise from complex teacher networks to efficient student models. However, in decentralized or secure AI eco…

cs.LG2026

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…

cs.LG2026

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

Quoc Minh Nguyen, Trung Le, Jing Wu +2

Fine-tuning-as-a-service introduces a threat to Large Language Models' safety when service providers fine-tune their models on poisoned user-submitted datasets, a process known as…

cs.CV2024

Erasing Undesirable Influence in Diffusion Models

Jing Wu, Trung Le, Munawar Hayat +1

Diffusion models are highly effective at generating high-quality images but pose risks, such as the unintentional generation of NSFW (not safe for work) content. Although various t…