Shizhan Gong
5 papers · 2024–2026 · 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
(15)
Top co-authors
Research topics
Artificial Intelligence
(5)
Core AI · Artificial Intelligence
(5)
Machine Learning
(3)
Deep Learning
(2)
Core Methods
(2)
Computer Vision
(1)
Architectures
(1)
Core AI · Computer Vision
(1)
Learning Types · Machine Learning
(1)
Learning Types · Deep Learning
(1)
Optimization & Theory · Machine Learning
(1)
Optimization & Theory · Deep Learning
(1)
Techniques
(1)
Keywords
clip
(2)
saliency map
(2)
adversarial training
(1)
visual representation
(1)
neural network interpretability
(1)
group sparsity
(1)
norm regularization
(1)
multimodal large language model
(1)
concept extraction
(1)
visual encoder
(1)
concept bottleneck model
(1)
sparsity regularization
(1)
feature sparsity
(1)
group relative policy optimization
(1)
adversarial fine-tuning
(1)
gradient-based saliency
(1)
sparse decomposition
(1)
neural network
(1)
vision-language reasoning
(1)
gradient-based saliency map
(1)
Papers
Concepts from Representations: Post-hoc Concept Bottleneck Models via Sparse Decomposition of Visual Representations
AAAI 2026
Saliency-R1: Enforcing Interpretable and Faithful Vision-language Reasoning via Saliency-map Alignment Reward
CVPR 2026
Boosting the visual interpretability of CLIP via adversarial fine-tuning
ICLR 2025
Kernel-based Unsupervised Embedding Alignment for Enhanced Visual Representation in Vision-language Models
ICML 2025
Structured Gradient-based Interpretations via Norm-Regularized Adversarial Training
CVPR 2024