Shusen Liu

4 papers · 2018–2026 · 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 ↓

🌍 Conference Polyglot · Bronze 🏃 Academic Marathon · Sprint 🐣 Hot Topic Early Bird 📈 Trend Setter

Venues

CVPR (2) ACL (1) EMNLP (1)

Top co-authors

Peer-Timo Bremer (2) Xuxi Chen (1) Bhavya Kailkhura (1) Vivek Srikumar (1) Zhimin Li (1) Tao Li (1) Matthew L. Olson (1) Vivek Narayanaswamy (1) Tsui-Wei Weng (1) Jayaraman J. Thiagarajan (1)

Research topics

Artificial Intelligence (2) Deep Learning (2) Machine Learning (2) Application Areas (2) Core AI (2) Architectures (1) Models (1)

Keywords

unsupervised learning (1) attention mechanism (1) natural language inference (1) model merging (1) model interpretability (1) generative adversarial network (1) vision-language model (1) concept bottleneck (1) mechanistic interpretability (1) sparse autoencoder (1) machine comprehension (1) model auditing (1) attention visualization (1) model steering (1) fine-tuned model (1) semantic attribute (1) visual analytics (1) attribute detection (1) weight change magnitude (1) module-wise integration (1)

Papers

Interpretable and Steerable Concept Bottleneck Sparse Autoencoders CVPR 2026 RankMean: Module-Level Importance Score for Merging Fine-tuned LLM Models ACL 2024 Cross-GAN Auditing: Unsupervised Identification of Attribute Level Similarities and Differences Between Pretrained Generative Models CVPR 2023 Visual Interrogation of Attention-Based Models for Natural Language Inference and Machine Comprehension EMNLP 2018