Junfei Liu
9 papers · 2020–2026 · 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 ↓
🌍
Conference Polyglot · Silver
🏃
Academic Marathon · Sprint
🌉
Interdisciplinary Bridge · Bronze
🗺️
Taxonomy Completionist
(17)
Top co-authors
Research topics
Machine Learning
(7)
Artificial Intelligence
(5)
Natural Language Processing
(4)
Application Areas
(3)
Core AI
(3)
Core Methods
(3)
Generation
(3)
Learning Types · Machine Learning
(3)
Learning Paradigms · Artificial Intelligence
(2)
Optimization & Theory
(2)
Deep Learning
(1)
Applications
(1)
Learning Paradigms · Machine Learning
(1)
Learning Types · Deep Learning
(1)
Keywords
abstractive summarization
(3)
exposure bia
(2)
text generation
(2)
knowledge distillation
(2)
self-paced learning
(1)
adversarial training
(1)
reading comprehension
(1)
markov process
(1)
token classification
(1)
mahalanobis distance
(1)
feature attribution
(1)
gaussian mixture model
(1)
autoregressive model
(1)
language model
(1)
mechanistic interpretability
(1)
noisy label
(1)
sparse autoencoder
(1)
teacher-student framework
(1)
sequence tagging
(1)
dialogue generation
(1)
Papers
Detecting Emotional Dynamic Trajectories: An Evaluation Framework for Emotional Support in Language Models
AAAI 2026
Efficient Transcoder Adaptation for Fine-Tuned Models: Revealing Medical Reasoning Mechanisms in Large Language Models
AAAI 2026
Verifiable LLM-Generated Text Detection via Projected Semantic-Structural Distributions
ACL 2026
Alleviating Exposure Bias in Abstractive Summarization via Sequentially Generating and Revising
COLING 2024
Global Learning with Triplet Relations in Abstractive Summarization
CoNLL 2024
Prophecy Distillation for Boosting Abstractive Summarization
COLING 2024
Combining Curriculum Learning and Knowledge Distillation for Dialogue Generation
EMNLP 2021
MedAI at SemEval-2021 Task 5: Start-to-end Tagging Framework for Toxic Spans Detection
SemEval 2021
Learn with Noisy Data via Unsupervised Loss Correction for Weakly Supervised Reading Comprehension
COLING 2020