Tianda Li
4 papers · 2021–2023 · 4 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 ↓
๐
Conference Polyglot ยท Bronze
๐
Interdisciplinary Bridge ยท Bronze
๐บ๏ธ
Taxonomy Completionist
(15)
โ
The Questioner
(2)
Top co-authors
Research topics
Keywords
model compression
(3)
knowledge distillation
(2)
domain generalization
(1)
transfer learning
(1)
knowledge transfer
(1)
natural language understanding
(1)
bert language model
(1)
label smoothing
(1)
hierarchical model
(1)
dialogue disentanglement
(1)
glue benchmark
(1)
context encoding
(1)
large language model
(1)
weight sparsity
(1)
label regularization
(1)
conversation structure
(1)
sparse pre-training
(1)
dense fine-tuning
(1)
adversarial robustness
(1)
Papers
Do we need Label Regularization to Fine-tune Pre-trained Language Models?
EACL 2023
SPDF: Sparse Pre-training and Dense Fine-tuning for Large Language Models
UAI 2023
Conversation- and Tree-Structure Losses for Dialogue Disentanglement
ACL 2022
How to Select One Among All ? An Empirical Study Towards the Robustness of Knowledge Distillation in Natural Language Understanding
EMNLP 2021