Dong Shu
9 papers · 2024–2026 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+2 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (16) π Conference Polyglot (4) π Interdisciplinary Bridge π Cross-Pollinator (15) π§ Keyword Pioneer
π£
Hot Topic Early Bird
β‘
Prolific Year
(5)
Conferences
EMNLP (4)
ACL (3)
AAAI (1)
ACML (1)
Top co-authors
Keywords
large language model
(4)
sparse autoencoder
(3)
feature extraction
(2)
in-context learning
(1)
multimodal learning
(1)
visual representation
(1)
chain-of-thought reasoning
(1)
neural network analysis
(1)
feature disentanglement
(1)
computational efficiency
(1)
class imbalance
(1)
model alignment
(1)
language model
(1)
vision-language model
(1)
mechanistic interpretability
(1)
instruction following
(1)
multimodal representation
(1)
large vision-language model
(1)
steering vector
(1)
prompt engineering
(1)
Papers
FinChart-Bench: Benchmarking Financial Chart Comprehension in Vision-Language Models
ACL 2026
FinCall-Surprise: A Large Scale Multi-modal Benchmark for Earning Surprise Prediction
ACL 2026
Comparative Analysis of Demonstration Selection Algorithms for In-Context Learning in Large Language Models (Student Abstract)
AAAI 2025
A Survey on Sparse Autoencoders: Interpreting the Internal Mechanisms of Large Language Models
EMNLP 2025
Large Vision-Language Model Alignment and Misalignment: A Survey Through the Lens of Explainability
EMNLP 2025
Improving LLM Reasoning through Interpretable Role-Playing Steering
EMNLP 2025
Beyond Input Activations: Identifying Influential Latents by Gradient Sparse Autoencoders
EMNLP 2025
Knowledge Graph Large Language Model (KG-LLM) for Link Prediction
ACML 2024
The Impact of Reasoning Step Length on Large Language Models
ACL 2024