Cheng-Yu Hsieh
- Papers
- 8
Cite
Notes
Only stored in your browser.
Authored papers
8NVILA: Efficient Frontier Visual Language Models
CVPR 2025 1
Lookback Lens: Detecting and Mitigating Contextual Hallucinations in Large Language Models Using Only Attention Maps
arXiv 2024
Graph-Based Captioning: Enhancing Visual Descriptions by Interconnecting Region Captions
arXiv 2024
The Unmet Promise of Synthetic Training Images: Using Retrieved Real Images Performs Better
arXiv 2024
Distilling Step-by-Step! Outperforming Larger Language Models with Less Training Data and Smaller Model Sizes
arXiv 2023
SugarCrepe: Fixing Hackable Benchmarks for Vision-Language Compositionality
sugarcrepe-fixing-hackable-benchmarks-for
A Survey on Programmatic Weak Supervision
arXiv 2022
On the (In)fidelity and Sensitivity for Explanations
arXiv 2019
Affiliations
Frequent co-authors
10from 8 papers