Zeyu Huang
12 papers · 2022–2025 · 7 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+3 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (22) π§ Keyword Pioneer π Renaissance Researcher (5) π Interdisciplinary Bridge π Conference Polyglot (7)
π
Cross-Pollinator
(8)
π
Century Club
(12)
β‘
Prolific Year
(5)
Conferences
ICLR (3)
ACL (2)
EMNLP (2)
NAACL (2)
CVPR (1)
ECCV (1)
NIPS (1)
Top co-authors
Keywords
mixture of expert
(3)
large language model
(3)
attention mechanism
(2)
data augmentation
(1)
point cloud
(1)
model architecture
(1)
conditional computation
(1)
neural network optimization
(1)
class imbalance
(1)
surface reconstruction
(1)
sparse activation
(1)
model scaling
(1)
parameter efficiency
(1)
implicit field
(1)
expert specialization
(1)
multi-head attention
(1)
load balancing
(1)
weighted loss function
(1)
pre-trained transformer
(1)
tutor identification
(1)
Papers
Layerwise Recurrent Router for Mixture-of-Experts
ICLR 2025
SYSUpporter Team at BEA 2025 Shared Task: Class Compensation and Assignment Optimization for LLM-generated Tutor Identification
ACL 2025
Post-hoc Reward Calibration: A Case Study on Length Bias
ICLR 2025
A Closer Look into Mixture-of-Experts in Large Language Models
NAACL 2025
Demons in the Detail: On Implementing Load Balancing Loss for Training Specialized Mixture-of-Expert Models
ACL 2025
Unlocking Continual Learning Abilities in Language Models
EMNLP 2024
FRI-Net: Floorplan Reconstruction via Room-wise Implicit Representation
ECCV 2024
Stacking Your Transformers: A Closer Look at Model Growth for Efficient LLM Pre-Training
NIPS 2024
Unlocking Emergent Modularity in Large Language Models
NAACL 2024
ARO-Net: Learning Implicit Fields From Anchored Radial Observations
CVPR 2023
Transformer-Patcher: One Mistake Worth One Neuron
ICLR 2023
Mixture of Attention Heads: Selecting Attention Heads Per Token
EMNLP 2022