Chengyue Huang
7 papers · 2022–2026 · 4 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 ↓
🌍
Conference Polyglot · Bronze
🌉
Interdisciplinary Bridge · Bronze
🗺️
Taxonomy Completionist
(26)
🐣
Hot Topic Early Bird
Venues
Top co-authors
Research topics
Artificial Intelligence
(6)
Deep Learning
(6)
Machine Learning
(5)
Core AI
(5)
Learning Types · Deep Learning
(5)
Learning Paradigms · Artificial Intelligence
(3)
Optimization & Theory · Machine Learning
(3)
Natural Language Processing
(2)
Application Areas
(2)
Learning Types · Machine Learning
(2)
Techniques
(2)
Applications
(1)
Learning Paradigms · Machine Learning
(1)
Optimization & Theory · Deep Learning
(1)
Resources & Methods
(1)
Keywords
out-of-distribution generalization
(4)
robust fine-tuning
(2)
distribution shift
(2)
adversarial robustness
(2)
foundation model
(2)
prompt engineering
(1)
text generation
(1)
multimodal learning
(1)
neural architecture search
(1)
neural network optimization
(1)
instruction tuning
(1)
pac-bayes theory
(1)
parameter regularization
(1)
weight decay
(1)
vision-language model
(1)
model fine-tuning
(1)
model generalization
(1)
parameter-efficient tuning
(1)
visual encoder
(1)
gradient projection
(1)
Papers
MAPS: Preserving Vision-Language Representations via Module-Wise Proximity Scheduling for Better Vision-Language-Action Generalization
CVPR 2026
The Geometry of Robustness: Optimizing Loss Landscape Curvature and Feature Manifold Alignment for Robust Finetuning of Vision-Language Models
CVPR 2026
Directional Gradient Projection for Robust Fine-Tuning of Foundation Models
ICLR 2025
FRAMES-VQA: Benchmarking Fine-Tuning Robustness across Multi-Modal Shifts in Visual Question Answering
CVPR 2025
Instances Need More Care: Rewriting Prompts for Instances with LLMs in the Loop Yields Better Zero-Shot Performance
ACL 2024
Rethinking Weight Decay for Robust Fine-Tuning of Foundation Models
NeurIPS 2024
Learning To Learn by Jointly Optimizing Neural Architecture and Weights
CVPR 2022