Di Liang
17 papers · 2018–2026 · 5 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 ↓+6 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (46) π Academic Marathon Β· Sprint π Conference Polyglot Β· Silver π Interdisciplinary Bridge Β· Bronze π£ Hot Topic Early Bird
π
Keyword Champion
(2)
ποΈ
Keyword Collector
(81)
π
Trend Setter
π
Century Club Β· Bronze
π₯
Unstoppable Β· Bronze
β‘
Prolific Year Β· Productive
Venues
Top co-authors
Research topics
Deep Learning
(12)
Machine Learning
(11)
Artificial Intelligence
(10)
Natural Language Processing
(9)
Applications
(9)
Core AI
(9)
Learning Types Β· Deep Learning
(7)
Learning Types Β· Machine Learning
(7)
Core Methods
(5)
Architectures
(4)
Optimization & Theory Β· Machine Learning
(4)
Application Areas
(3)
Optimization & Theory Β· Deep Learning
(2)
Techniques
(2)
Generation
(1)
Keywords
semantic matching
(3)
large language model
(3)
knowledge graph
(2)
graph neural network
(2)
catastrophic forgetting
(2)
natural language inference
(2)
multi-hop reasoning
(2)
language model
(2)
parameter isolation
(2)
domain adaptation
(2)
task interference
(2)
supervised fine-tuning
(2)
temporal reasoning
(1)
benchmark evaluation
(1)
attention mechanism
(1)
optimal transport
(1)
lottery ticket hypothesis
(1)
multimodal learning
(1)
transfer learning
(1)
reinforcement learning
(1)
Papers
DeCoRL: Decoupling Reasoning Chains via Parallel Sub-Step Generation and Cascaded Reinforcement for Interpretable and Scalable RLHF
AAAI 2026
Learning from Contrasts: Synthesizing Reasoning Paths from Diverse Search Trajectories
ACL 2026
Parameter Importance is Not Static: Evolving Parameter Isolation for Supervised Fine-Tuning
ACL 2026
Why Supervised Fine-Tuning Fails to Learn: A Systematic Study of Incomplete Learning in Large Language Models
ACL 2026
Not All Parameters Are Created Equal: Smart Isolation Boosts Fine-Tuning Performance
EMNLP 2025
Structural Reward Model: Enhancing Interpretability, Efficiency, and Scalability in Reward Modeling
EMNLP 2025
TableBench: A Comprehensive and Complex Benchmark for Table Question Answering
AAAI 2025
Question Calibration and Multi-Hop Modeling for Temporal Question Answering
AAAI 2024
Resolving Word Vagueness with Scenario-guided Adapter for Natural Language Inference
IJCAI 2024
Local and Global: Temporal Question Answering via Information Fusion
IJCAI 2023
CQG: A Simple and Effective Controlled Generation Framework for Multi-hop Question Generation
ACL 2022
DABERT: Dual Attention Enhanced BERT for Semantic Matching
COLING 2022
Improving Semantic Matching through Dependency-Enhanced Pre-trained Model with Adaptive Fusion
EMNLP 2022
Robust Lottery Tickets for Pre-trained Language Models
ACL 2022
Searching for Optimal Subword Tokenization in Cross-domain NER
IJCAI 2022
Asynchronous Deep Interaction Network for Natural Language Inference
EMNLP 2019
Transferring from Formal Newswire Domain with Hypernet for Twitter POS Tagging
EMNLP 2018