Liyuan Liu
25 papers · 2017–2025 · 8 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 ↓+9 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (51) π Conference Polyglot Β· Silver π Academic Marathon Β· Sprint π Interdisciplinary Bridge Β· Bronze π£ Hot Topic Early Bird
π
Grand Slam
π§¬
Topic Evolution
π€
Dynamic Duo
(11)
π
Conference Pioneer
π₯
Unstoppable Β· Bronze
β‘
Prolific Year Β· Productive
π
Century Club Β· Bronze
π
Trend Setter
ποΈ
Keyword Collector
(127)
Top co-authors
Research topics
Machine Learning
(21)
Natural Language Processing
(14)
Deep Learning
(10)
Learning Types
(9)
Artificial Intelligence
(8)
Optimization & Theory Β· Machine Learning
(8)
Application Areas
(6)
Applications
(6)
Core AI
(6)
Core Methods
(6)
Understanding
(5)
Optimization & Theory Β· Deep Learning
(4)
Architectures
(3)
Learning Paradigms
(3)
Resources & Methods
(3)
Keywords
relation extraction
(4)
named entity recognition
(4)
distant supervision
(4)
sequence labeling
(4)
knowledge distillation
(4)
large language model
(3)
label distribution
(2)
representation learning
(2)
rademacher complexity
(2)
adaptive learning rate
(2)
multi-instance learning
(2)
attention mechanism
(2)
attention head
(2)
knowledge base
(2)
model compression
(2)
adversarial training
(2)
neural network optimization
(2)
label noise
(2)
weakly supervised learning
(1)
network architecture
(1)
Papers
On the Generalization Ability of Next-Token-Prediction Pretraining
ICML 2025
Trajectory-Dependent Generalization Bounds for Pairwise Learning with Ο-mixing Samples
IJCAI 2025
Vector-ICL: In-context Learning with Continuous Vector Representations
ICLR 2025
Fast-ELECTRA for Efficient Pre-training
ICLR 2024
Model Tells You What to Discard: Adaptive KV Cache Compression for LLMs
ICLR 2024
Tell Your Model Where to Attend: Post-hoc Attention Steering for LLMs
ICLR 2024
Toward Student-oriented Teacher Network Training for Knowledge Distillation
ICLR 2024
Bridging Discrete and Backpropagation: Straight-Through and Beyond
NeurIPS 2023
Understand and Modularize Generator Optimization in ELECTRA-style Pretraining
ICML 2023
Label Noise in Adversarial Training: A Novel Perspective to Study Robust Overfitting
NeurIPS 2022
Empower Distantly Supervised Relation Extraction with Collaborative Adversarial Training
AAAI 2021
On the Transformer Growth for Progressive BERT Training
NAACL 2021
Facet-Aware Evaluation for Extractive Summarization
ACL 2020
Learning to Contextually Aggregate Multi-Source Supervision for Sequence Labeling
ACL 2020
On the Variance of the Adaptive Learning Rate and Beyond
ICLR 2020
Towards Adaptive Residual Network Training: A Neural-ODE Perspective
ICML 2020
Understanding the Difficulty of Training Transformers
EMNLP 2020
Arabic Named Entity Recognition: What Works and Whatβs Next
ACL 2019
Cross-Relation Cross-Bag Attention for Distantly-Supervised Relation Extraction
AAAI 2019
CrossWeigh: Training Named Entity Tagger from Imperfect Annotations
EMNLP 2019
Looking Beyond Label Noise: Shifted Label Distribution Matters in Distantly Supervised Relation Extraction
EMNLP 2019
Reliability-aware Dynamic Feature Composition for Name Tagging
ACL 2019
Efficient Contextualized Representation: Language Model Pruning for Sequence Labeling
EMNLP 2018
Learning Named Entity Tagger using Domain-Specific Dictionary
EMNLP 2018
Heterogeneous Supervision for Relation Extraction: A Representation Learning Approach
EMNLP 2017