Xinshuo Hu
9 papers · 2024–2025 · 6 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+3 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (29) π§ Keyword Pioneer π Conference Polyglot (6) π Cross-Pollinator (12) π Interdisciplinary Bridge
π±
Topic Pioneer
β‘
Prolific Year
(6)
β
The Questioner
Conferences
AAAI (2)
ACL (2)
EMNLP (2)
COLING (1)
NAACL (1)
NIPS (1)
Top co-authors
Keywords
large language model
(4)
retrieval-augmented generation
(3)
in-context learning
(2)
information retrieval
(2)
citation generation
(2)
attention mechanism
(1)
preference learning
(1)
catastrophic forgetting
(1)
text generation
(1)
few-shot learning
(1)
model unlearning
(1)
test-time adaptation
(1)
gradient descent
(1)
language model
(1)
hallucination detection
(1)
hallucination mitigation
(1)
knowledge editing
(1)
state vector
(1)
momentum optimization
(1)
zero-shot learning
(1)
Papers
FunnelRAG: A Coarse-to-Fine Progressive Retrieval Paradigm for RAG
NAACL 2025
CMT: A Memory Compression Method for Continual Knowledge Learning of Large Language Models
AAAI 2025
DAST: Context-Aware Compression in LLMs via Dynamic Allocation of Soft Tokens
ACL 2025
Improving Attributed Text Generation of Large Language Models via Preference Learning
ACL 2024
In-Context Learning State Vector with Inner and Momentum Optimization
NIPS 2024
Does the Generator Mind Its Contexts? An Analysis of Generative Model Faithfulness under Context Transfer
COLING 2024
Take Off the Training Wheels! Progressive In-Context Learning for Effective Alignment
EMNLP 2024
Separate the Wheat from the Chaff: Model Deficiency Unlearning via Parameter-Efficient Module Operation
AAAI 2024
TruthReader: Towards Trustworthy Document Assistant Chatbot with Reliable Attribution
EMNLP 2024