Xisen Jin
14 papers · 2018–2024 · 6 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+9 more ↓ Show less ↑
π Interdisciplinary Bridge π Renaissance Researcher (6) π Conference Polyglot (6) π Academic Marathon (6) πΊοΈ Taxonomy Completionist (26)
π§
Keyword Pioneer
π£
Hot Topic Early Bird
π
Conference Polyglot
(6)
π€
Dynamic Duo
(12)
β
The Questioner
π
Century Club
(14)
π
Trend Setter
π₯
Unstoppable
(5)
ποΈ
Keyword Collector
(56)
Conferences
ACL (4)
EMNLP (3)
ICLR (2)
NAACL (2)
NIPS (2)
ICML (1)
Top co-authors
Keywords
continual learning
(6)
catastrophic forgetting
(4)
knowledge distillation
(2)
language model pretraining
(2)
bias detection
(1)
transfer learning
(1)
few-shot learning
(1)
lifelong learning
(1)
link prediction
(1)
multimodal learning
(1)
text classification
(1)
model pretraining
(1)
visual grounding
(1)
task-oriented dialogue
(1)
compositional generalization
(1)
dialogue state tracking
(1)
belief tracking
(1)
learning rate scheduling
(1)
domain adaptation
(1)
reinforcement learning
(1)
Papers
What Will My Model Forget? Forecasting Forgotten Examples in Language Model Refinement
ICML 2024
Overcoming Catastrophic Forgetting in Massively Multilingual Continual Learning
ACL 2023
Dataless Knowledge Fusion by Merging Weights of Language Models
ICLR 2023
Lifelong Pretraining: Continually Adapting Language Models to Emerging Corpora
NAACL 2022
Lifelong Pretraining: Continually Adapting Language Models to Emerging Corpora
ACL 2022
Refining Language Models with Compositional Explanations
NIPS 2021
Gradient-based Editing of Memory Examples for Online Task-free Continual Learning
NIPS 2021
Learn Continually, Generalize Rapidly: Lifelong Knowledge Accumulation for Few-shot Learning
EMNLP 2021
On Transferability of Bias Mitigation Effects in Language Model Fine-Tuning
NAACL 2021
Towards Hierarchical Importance Attribution: Explaining Compositional Semantics for Neural Sequence Models
ICLR 2020
Visually Grounded Continual Learning of Compositional Phrases
EMNLP 2020
Contextualizing Hate Speech Classifiers with Post-hoc Explanation
ACL 2020
Recurrent Event Network: Autoregressive Structure Inferenceover Temporal Knowledge Graphs
EMNLP 2020
Sequicity: Simplifying Task-oriented Dialogue Systems with Single Sequence-to-Sequence Architectures
ACL 2018