Manli Shu
11 papers · 2021–2025 · 3 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+3 more ↓ Show less ↑
🐣 Hot Topic Early Bird 🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (33) 🗃️ Keyword Collector (66)
💎
Century Club · Bronze
🔥
Unstoppable · Bronze
❓
The Questioner
Venues
Top co-authors
Research topics
Artificial Intelligence
(8)
Deep Learning
(8)
Machine Learning
(8)
Core AI · Artificial Intelligence
(8)
Learning Types · Deep Learning
(7)
Learning Types · Machine Learning
(6)
Application Areas
(4)
Models
(4)
Computer Vision
(2)
Architectures
(2)
Core AI · Computer Vision
(2)
Techniques
(2)
Analysis
(1)
Core Methods
(1)
Optimization & Theory
(1)
Keywords
vision-language model
(4)
self-supervised learning
(2)
neural network
(2)
multimodal learning
(2)
adversarial training
(2)
domain generalization
(2)
data poisoning
(2)
transfer learning
(1)
question answering
(1)
adversarial learning
(1)
batch normalization
(1)
distribution shift
(1)
test-time adaptation
(1)
knowledge distillation
(1)
model alignment
(1)
instruction tuning
(1)
ai safety
(1)
sensitivity analysis
(1)
computer vision
(1)
model security
(1)
Papers
LATTE: Learning to Think with Vision Specialists
EMNLP 2025
MINT-1T: Scaling Open-Source Multimodal Data by 10x: A Multimodal Dataset with One Trillion Tokens
NeurIPS 2024
On the Reliability of Watermarks for Large Language Models
ICLR 2024
Shadowcast: Stealthy Data Poisoning Attacks Against Vision-Language Models
NeurIPS 2024
Battle of the Backbones: A Large-Scale Comparison of Pretrained Models across Computer Vision Tasks
NeurIPS 2023
On the Exploitability of Instruction Tuning
NeurIPS 2023
Test-Time Prompt Tuning for Zero-Shot Generalization in Vision-Language Models
NeurIPS 2022
The Close Relationship Between Contrastive Learning and Meta-Learning
ICLR 2022
Where do Models go Wrong? Parameter-Space Saliency Maps for Explainability
NeurIPS 2022
Encoding Robustness to Image Style via Adversarial Feature Perturbations
NeurIPS 2021
Gradient-Free Adversarial Training Against Image Corruption for Learning-based Steering
NeurIPS 2021