Guangyuan SHI
8 papers · 2021–2025 · 4 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
🌉
Interdisciplinary Bridge · Bronze
🗺️
Taxonomy Completionist
(24)
🐣
Hot Topic Early Bird
Venues
Top co-authors
Research topics
Machine Learning
(7)
Artificial Intelligence
(6)
Learning Types · Machine Learning
(5)
Deep Learning
(4)
Natural Language Processing
(4)
Core AI
(4)
Learning Paradigms
(3)
Generation
(2)
Learning Types · Deep Learning
(2)
Models
(2)
Optimization & Theory
(2)
Resources & Methods
(2)
Application Areas
(1)
Applications
(1)
Architectures
(1)
Keywords
large language model
(3)
knowledge transfer
(3)
continual learning
(3)
catastrophic forgetting
(3)
few-shot learning
(2)
multi-task learning
(2)
dialogue state tracking
(2)
model architecture
(1)
incremental learning
(1)
instruction following
(1)
intent classification
(1)
model merging
(1)
image super-resolution
(1)
diffusion model
(1)
language model
(1)
parameter importance
(1)
flat minima
(1)
task grouping
(1)
gradient conflict
(1)
cross-domain transfer
(1)
Papers
Recurrent Knowledge Identification and Fusion for Language Model Continual Learning
ACL 2025
EasyGen: Easing Multimodal Generation with BiDiffuser and LLMs
ACL 2024
TaSL: Continual Dialog State Tracking via Task Skill Localization and Consolidation
ACL 2024
Zero-shot Cross-domain Dialogue State Tracking via Context-aware Auto-prompting and Instruction-following Contrastive Decoding
EMNLP 2024
Real-World Image Super-Resolution as Multi-Task Learning
NeurIPS 2023
Recon: Reducing Conflicting Gradients From the Root For Multi-Task Learning
ICLR 2023
Effectiveness of Pre-training for Few-shot Intent Classification
EMNLP 2021
Overcoming Catastrophic Forgetting in Incremental Few-Shot Learning by Finding Flat Minima
NeurIPS 2021