Xuansheng Wu
9 papers · 2023–2026 · 7 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 · Silver
🌉
Interdisciplinary Bridge · Bronze
🗺️
Taxonomy Completionist
(14)
Top co-authors
Research topics
Keywords
large language model
(4)
sparse autoencoder
(3)
model steering
(2)
feature extraction
(1)
medical imaging
(1)
instruction following
(1)
neural network analysis
(1)
feature disentanglement
(1)
instruction tuning
(1)
backdoor attack
(1)
diffusion model
(1)
latent representation
(1)
adversarial defense
(1)
language model
(1)
vision-language model
(1)
model explanation
(1)
feed-forward network
(1)
mechanistic interpretability
(1)
linear probing
(1)
latent feature
(1)
Papers
AutoSCORE: Enhancing Automated Scoring with Multi-Agent Large Language Models via Structured Component Recognition
AAAI 2026
Denoising Concept Vectors with Sparse Autoencoders for Improved Language Model Steering
EACL 2026
A Survey on Sparse Autoencoders: Interpreting the Internal Mechanisms of Large Language Models
EMNLP 2025
Beyond Input Activations: Identifying Influential Latents by Gradient Sparse Autoencoders
EMNLP 2025
Concept-Centric Token Interpretation for Vector-Quantized Generative Models
ICML 2025
LMOD: A Large Multimodal Ophthalmology Dataset and Benchmark for Large Vision-Language Models
NAACL 2025
From Language Modeling to Instruction Following: Understanding the Behavior Shift in LLMs after Instruction Tuning
NAACL 2024
InFoBench: Evaluating Instruction Following Ability in Large Language Models
ACL 2024
Black-box Backdoor Defense via Zero-shot Image Purification
NeurIPS 2023