nguyenvuthientrang Goto Github PK

amortizedsw

A framework using amortized optimization for seeking informative directions for sliced Wasserstein generative models.

attempt

This is the oficial repository for "Parameter-Efficient Multi-task Tuning via Attentional Mixtures of Soft Prompts" (EMNLP 2022)

boston-housing-prices

businessanalysis

coda

PyTorch code for the CVPR'23 paper: "CODA-Prompt: COntinual Decomposed Attention-based Prompting for Rehearsal-Free Continual Learning"

competesmoe

Code for this paper "CompeteSMoE - Effective Sparse Mixture of Experts Training via Competition"

continual-aspect-sentiment-analysis

cv

cvd

cyclip

dept

[ICLR 2024] This is the repository for the paper titled "DePT: Decomposed Prompt Tuning for Parameter-Efficient Fine-tuning"

dola

Official implementation for the paper "DoLa: Decoding by Contrasting Layers Improves Factuality in Large Language Models"

farming-fun

gans

generalizable-mixture-of-experts

GMoE could be the next backbone model for many kinds of generalization task.

hide

Hierarchical Decomposition of Prompt-Based Continual Learning: Rethinking Obscured Sub-optimality (NeurIPS 2023, Spotlight)

limited-transfer-gan

loftq

mmd-gan

MMD-GAN: Towards Deeper Understanding of Moment Matching Network

national-exams-results-eda-and-visualization

nguyenvuthientrang.github.io

pgp

sinkhorn-gan

Learning generative models with Sinkhorn Loss

sliding-cusum

swg

Sliced Wasserstein Generator

thesis

towards-robust-neural-networks-via-close-loop-control

tutel

Tutel MoE: An Optimized Mixture-of-Experts Implementation