Lei Shu
26 papers · 2016–2026 · 9 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 ↓+8 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (57) π Academic Marathon Β· Half π Conference Polyglot Β· Silver π Interdisciplinary Bridge Β· Bronze π£ Hot Topic Early Bird
π
Keyword Champion
(2)
π§¬
Topic Evolution
π€
Dynamic Duo
(15)
β‘
Prolific Year Β· Productive
π₯
Unstoppable Β· Silver
π
Century Club Β· Bronze
ποΈ
Keyword Collector
(127)
π
Trend Setter
Top co-authors
Research topics
Machine Learning
(18)
Natural Language Processing
(17)
Deep Learning
(13)
Artificial Intelligence
(12)
Learning Types Β· Machine Learning
(12)
Core AI
(8)
Learning Types Β· Deep Learning
(8)
Resources & Methods
(8)
Applications
(7)
Generation
(7)
Application Areas
(6)
Learning Paradigms
(6)
Core Methods
(4)
Models
(4)
Architectures
(3)
Keywords
transfer learning
(5)
language model
(5)
domain adaptation
(5)
knowledge distillation
(3)
text generation
(3)
representation learning
(3)
aspect-based sentiment analysis
(2)
word embedding
(2)
text rewriting
(2)
pre-trained model
(2)
continual learning
(2)
out-of-distribution detection
(2)
instruction tuning
(2)
aspect extraction
(2)
sequence labeling
(2)
lifelong learning
(2)
text classification
(2)
task-oriented dialogue
(2)
policy model
(2)
open-world classification
(2)
Papers
Ego2Web: A Web Agent Benchmark Grounded in Egocentric Videos
CVPR 2026
Accelerating Inference of Retrieval-Augmented Generation via Sparse Context Selection
ICLR 2025
Enhancing Reinforcement Learning with Dense Rewards from Language Model Critic
EMNLP 2024
Fusion-Eval: Integrating Assistant Evaluators with LLMs
EMNLP 2024
RewriteLM: An Instruction-Tuned Large Language Model for Text Rewriting
AAAI 2024
Towards an On-device Agent for Text Rewriting
NAACL 2024
An Efficient Conversational Smart Compose System
ACL 2023
Adapting a Language Model While Preserving its General Knowledge
EMNLP 2022
Continual Training of Language Models for Few-Shot Learning
EMNLP 2022
Measuring and Reducing Model Update Regression in Structured Prediction for NLP
NeurIPS 2022
Multi-Task Pre-Training for Plug-and-Play Task-Oriented Dialogue System
ACL 2022
TaCL: Improving BERT Pre-training with Token-aware Contrastive Learning
NAACL 2022
Zero-Shot Out-of-Distribution Detection Based on the Pre-trained Model CLIP
AAAI 2022
Achieving Forgetting Prevention and Knowledge Transfer in Continual Learning
NeurIPS 2021
CLASSIC: Continual and Contrastive Learning of Aspect Sentiment Classification Tasks
EMNLP 2021
ODIST: Open World Classification via Distributionally Shifted Instances
EMNLP 2021
Controllable Text Generation with Focused Variation
EMNLP 2020
DomBERT: Domain-oriented Language Model for Aspect-based Sentiment Analysis
EMNLP 2020
Understanding Pre-trained BERT for Aspect-based Sentiment Analysis
COLING 2020
BERT Post-Training for Review Reading Comprehension and Aspect-based Sentiment Analysis
NAACL 2019
Modeling Multi-Action Policy for Task-Oriented Dialogues
EMNLP 2019
Double Embeddings and CNN-based Sequence Labeling for Aspect Extraction
ACL 2018
Lifelong Domain Word Embedding via Meta-Learning
IJCAI 2018
DOC: Deep Open Classification of Text Documents
EMNLP 2017
Lifelong Learning CRF for Supervised Aspect Extraction
ACL 2017
Lifelong-RL: Lifelong Relaxation Labeling for Separating Entities and Aspects in Opinion Targets
EMNLP 2016