Manli Shu
11 papers · 2021–2025 · 3 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+5 more ↓ Show less ↑
π Cross-Pollinator (12) πΊοΈ Taxonomy Completionist (32) π Interdisciplinary Bridge π£ Hot Topic Early Bird π Conference Polyglot (3)
π§
Keyword Pioneer
π₯
Unstoppable
(5)
π
Century Club
(11)
β
The Questioner
ποΈ
Keyword Collector
(59)
Conferences
NIPS (8)
ICLR (2)
EMNLP (1)
Top co-authors
Keywords
vision-language model
(4)
data poisoning
(2)
neural network
(2)
multimodal learning
(2)
adversarial training
(2)
domain generalization
(2)
computer vision
(1)
transfer learning
(1)
model security
(1)
question answering
(1)
saliency map
(1)
test-time adaptation
(1)
batch normalization
(1)
ai safety
(1)
sensitivity analysis
(1)
knowledge distillation
(1)
model alignment
(1)
distribution shift
(1)
instruction tuning
(1)
self-supervised learning
(1)
Papers
LATTE: Learning to Think with Vision Specialists
EMNLP 2025
On the Reliability of Watermarks for Large Language Models
ICLR 2024
MINT-1T: Scaling Open-Source Multimodal Data by 10x: A Multimodal Dataset with One Trillion Tokens
NIPS 2024
Shadowcast: Stealthy Data Poisoning Attacks Against Vision-Language Models
NIPS 2024
On the Exploitability of Instruction Tuning
NIPS 2023
Battle of the Backbones: A Large-Scale Comparison of Pretrained Models across Computer Vision Tasks
NIPS 2023
Where do Models go Wrong? Parameter-Space Saliency Maps for Explainability
NIPS 2022
Test-Time Prompt Tuning for Zero-Shot Generalization in Vision-Language Models
NIPS 2022
The Close Relationship Between Contrastive Learning and Meta-Learning
ICLR 2022
Gradient-Free Adversarial Training Against Image Corruption for Learning-based Steering
NIPS 2021
Encoding Robustness to Image Style via Adversarial Feature Perturbations
NIPS 2021