Xinshuo Hu
9 papers · 2024–2025 · 6 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 ↓+1 more ↓ Show less ↑
🌍 Conference Polyglot · Silver 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (27) ❓ The Questioner ⚡ Prolific Year · Productive
📈
Trend Setter
Top co-authors
Research topics
Artificial Intelligence
(7)
Deep Learning
(6)
Machine Learning
(6)
Core AI
(6)
Learning Types · Machine Learning
(5)
Natural Language Processing
(4)
Applications
(4)
Models
(4)
Application Areas
(3)
Learning Types · Deep Learning
(3)
Generation
(2)
Learning Paradigms
(2)
Optimization & Theory · Machine Learning
(1)
Optimization & Theory · Deep Learning
(1)
Resources & Methods
(1)
Keywords
large language model
(4)
retrieval-augmented generation
(3)
information retrieval
(2)
in-context learning
(2)
citation generation
(2)
knowledge editing
(1)
attention mechanism
(1)
zero-shot learning
(1)
model unlearning
(1)
parametric memory
(1)
test-time adaptation
(1)
gradient descent
(1)
language model
(1)
hallucination mitigation
(1)
preference learning
(1)
momentum optimization
(1)
state vector
(1)
text generation
(1)
hallucination detection
(1)
few-shot learning
(1)
Papers
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
FunnelRAG: A Coarse-to-Fine Progressive Retrieval Paradigm for RAG
NAACL 2025
Does the Generator Mind Its Contexts? An Analysis of Generative Model Faithfulness under Context Transfer
COLING 2024
Improving Attributed Text Generation of Large Language Models via Preference Learning
ACL 2024
In-Context Learning State Vector with Inner and Momentum Optimization
NeurIPS 2024
Separate the Wheat from the Chaff: Model Deficiency Unlearning via Parameter-Efficient Module Operation
AAAI 2024
Take Off the Training Wheels! Progressive In-Context Learning for Effective Alignment
EMNLP 2024
TruthReader: Towards Trustworthy Document Assistant Chatbot with Reliable Attribution
EMNLP 2024