ResearchAlpha Leak

Conferences Topics Top Authors Rankings Browse All

Home/Authors/Manli Shu

Manli Shu

Topic trends: 32,543 papers · similarity ≥ 0.4 · year ≥ 2024 · Data sourced from Semantic Scholar

34,598 papers | Abstracts: 31,650 (91.5%) | Citations: 34,598 (100.0%) | arXiv: 26,074 (75.4%)

Built: Feb 15, 2026, 5:57 AM AMS

7

papers

905

total citations

papers (7)

Test-Time Prompt Tuning for Zero-Shot Generalization in Vision-Language Models

NEURIPS 2022arXiv

On the Reliability of Watermarks for Large Language Models

On the Exploitability of Instruction Tuning

NEURIPS 2023arXiv

Battle of the Backbones: A Large-Scale Comparison of Pretrained Models across Computer Vision Tasks

NEURIPS 2023arXiv

Encoding Robustness to Image Style via Adversarial Feature Perturbations

NEURIPS 2021arXiv

Where do Models go Wrong? Parameter-Space Saliency Maps for Explainability

NEURIPS 2022arXiv

Gradient-Free Adversarial Training Against Image Corruption for Learning-based Steering