Papers by Tianwen Wei
Masks Can be Learned as an Alternative to Experts (2025.acl-long)
Copied to clipboard
| Challenge: | a recent study shows that sparse activation techniques can reduce inference performance without sacrificing performance. |
| Approach: | They propose to sparsify a pre-trained dense large language model into a mixture-of-experts architecture for faster inference. |
| Outcome: | The proposed approach is more efficient than one-shot sparsification techniques . it achieves 97% performance retention on downstream tasks with only 50% of parameters activated . |
A Flexible Multi-Task Model for BERT Serving (2022.acl-short)
Copied to clipboard
| Challenge: | a proposed BERT-based multi-task framework is suitable for iterative and incremental development of the tasks. |
| Approach: | They propose an efficient BERT-based multi-task framework that is suitable for iterative and incremental development of the tasks. |
| Outcome: | The proposed framework achieves 99.6% of performance of the full fine-tuning method while reducing up to two thirds of its overhead. |
Masked Conditional Random Fields for Sequence Labeling (2021.naacl-main)
Copied to clipboard
| Challenge: | Conditional Random Fields (CRF) based neural models are among the most performant for sequence labeling problems, but they can sometimes generate illegal sequences of tags. |
| Approach: | They propose a conditional random field-based model that imposes restrictions on candidate paths during both training and decoding phases. |
| Outcome: | The proposed method improves on existing CRF models with near zero additional cost. |