Shiyu Chang
- Papers
- 15
Cite
Notes
Only stored in your browser.
Authored papers
15How Well Do Agentic Skills Work in the Wild: Benchmarking LLM Skill Usage in Realistic Settings
arXiv 2026
A Survey on Data Selection for Language Models
arXiv 2024
Revisiting Who's Harry Potter: Towards Targeted Unlearning from a Causal Intervention Perspective
arXiv 2024
Reversing the Forget-Retain Objectives: An Efficient LLM Unlearning Framework from Logit Difference
arXiv 2024
Fictitious Synthetic Data Can Improve LLM Factuality via Prerequisite Learning
arXiv 2024
Harnessing the Spatial-Temporal Attention of Diffusion Models for High-Fidelity Text-to-Image Synthesis
ICCV 2023 1
Correcting Diffusion Generation through Resampling
CVPR 2024 1
Towards Coherent Image Inpainting Using Denoising Diffusion Implicit Models
arXiv 2023
Robust Mixture-of-Expert Training for Convolutional Neural Networks
ICCV 2023 1
How to Robustify Black-Box ML Models? A Zeroth-Order Optimization Perspective
how-to-robustify-black-box-ml-models-a-zeroth
ContentVec: An Improved Self-Supervised Speech Representation by Disentangling Speakers
arXiv 2022
DiffCSE: Difference-based Contrastive Learning for Sentence Embeddings
NAACL 2022 7
PromptBoosting: Black-Box Text Classification with Ten Forward Passes
arXiv 2022
AUTOVC: Zero-Shot Voice Style Transfer with Only Autoencoder Loss
arXiv 2019
Self-Supervised Learning for Contextualized Extractive Summarization
self-supervised-learning-for-contextualized-1
Affiliations
Frequent co-authors
10from 15 papers