activity
20212026
most citedRevisiting Prefix-tuning: Statistical Benefits of Reparameterization among Prompts

1 citations · 2 across the 7 of their papers we have counts for

collaborators
Showing cs.LGShow all

11 papers · 1 filter

cs.LG2026

Spectral-Aware Analytic Class-Incremental Learning for Long-Tailed Distributions

Quyen Tran, Hai Nguyen, Quan Dao +4

Analytic Continual Learning (ACL) offers a computationally efficient alternative to gradient-based approaches. Recent ACL methods are based on Recursive Least Squares (RLS) and hav…

cs.LG2025

One-Prompt Strikes Back: Sparse Mixture of Experts for Prompt-based Continual Learning

Minh Le, Bao-Ngoc Dao, Huy Nguyen +3

Prompt-based methods have recently gained prominence in Continual Learning (CL) due to their strong performance and memory efficiency. A prevalent strategy in this paradigm assigns…

cs.LG2025

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

Ngoc-Quan Pham, Tuan Truong, Quyen Tran +3

We introduce Interactive Bayesian Distributional Robustness (IBDR), a novel Bayesian inference framework that allows modeling the interactions between particles, thereby enhancing…

cs.LG2024

Leveraging Hierarchical Taxonomies in Prompt-based Continual Learning

Quyen Tran, Hoang Phan, Minh Le +6

Humans perceive the world as a series of sequential events, which can be hierarchically organized with different levels of abstraction based on conceptual knowledge. Drawing inspir…

cs.LG2024

Improving Generalization with Flat Hilbert Bayesian Inference

Tuan Truong, Quyen Tran, Quan Pham-Ngoc +3

We introduce Flat Hilbert Bayesian Inference (FHBI), an algorithm designed to enhance generalization in Bayesian inference. Our approach involves an iterative two-step procedure wi…

cs.LG20241 cited

Revisiting Prefix-tuning: Statistical Benefits of Reparameterization among Prompts

Minh Le, Chau Nguyen, Huy Nguyen +3

Prompt-based techniques, such as prompt-tuning and prefix-tuning, have gained prominence for their efficiency in fine-tuning large pre-trained models. Despite their widespread adop…