Leiyu Pan
8 papers · 2023–2026 · 3 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+2 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (18) π Conference Polyglot (3) π Interdisciplinary Bridge π Cross-Pollinator (15) π§ Keyword Pioneer
π£
Hot Topic Early Bird
β
The Questioner
(2)
Conferences
ACL (3)
EMNLP (3)
COLING (2)
Top co-authors
Keywords
large language model
(3)
machine translation
(2)
low-resource language
(2)
language modeling
(2)
translation robustness
(2)
mixture of expert
(2)
instruction tuning
(2)
multilingual translation
(2)
in-context learning
(1)
cross-lingual transfer
(1)
neural machine translation
(1)
adversarial training
(1)
dynamic routing
(1)
prompt learning
(1)
parameter-efficient learning
(1)
noise robustness
(1)
entropy regularization
(1)
sparse activation
(1)
proximal policy optimization
(1)
continual pre-training
(1)
Papers
From Curated Data to Scalable Models: Continual Pre-training of Dense and MoE Large Language Models for Tibetan
ACL 2026
CE-GPPO: Coordinating Entropy via Gradient-Preserving Clipping Policy Optimization in Reinforcement Learning
ACL 2026
DSMoE: Matrix-Partitioned Experts with Dynamic Routing for Computation-Efficient Dense LLMs
EMNLP 2025
LANDeRMT: Dectecting and Routing Language-Aware Neurons for Selectively Finetuning LLMs to Machine Translation
ACL 2024
FuxiTranyu: A Multilingual Large Language Model Trained with Balanced Data
EMNLP 2024
An Empirical Study on the Robustness of Massively Multilingual Neural Machine Translation
COLING 2024
Can Large Language Models Learn Translation Robustness from Noisy-Source In-context Demonstrations?
COLING 2024
Is Robustness Transferable across Languages in Multilingual Neural Machine Translation?
EMNLP 2023