Demonstration venue · read-only. Every page can be browsed; the buttons that would change it are switched off. Create an account to run TaxoReview on your own data. A simulation from public publication records: the people listed were not invited and did not agree to review.
? Tutorial for this page
Demo Data from VLDB 2026 / reviewers in the wild / expert

Wenhao Teng

dblp:426/9761 · DBLP profile ↗
← Back
2ranked-venue papers
0as first author
2since 2021 · last 2026
—ORCID · none

Domains — the database's venue-derived domains; a paper can count in several

Artificial intelligence and machine learning · 2 · 2 since 2021

Expertise — from the expertise taxonomy: the topics of the expert's papers under the CCF categories. A weight counts papers with recency: 1 for a paper about the topic, 0.3 when the topic is its context, halved every five years.

Artificial intelligence
2 papers
Learning paradigms · 83% Efficient and distributed learning · 8% Language models and text generation · 8%

Topics — the 5 heaviest of 5, each with the papers that count most for it

TopicWeightPapersLastEvidence papers
Machine learning › Learning paradigms
continual learning		 1.012026
Spectral Disentanglement: Rank-Aware Task Adaptation for Rehearsal-free Continual Learning in LLMs · ACL (1) 2026
Machine learning › Learning paradigms › continual learning › pre-trained model continual learning
continual learning for language models		 1.012026
Harmonizing the Past, Present, and Future: A Null-Space Constrained Region-Specific Method for Continual Learning in LLMs · ACL (1) 2026
Machine learning › Learning paradigms › continual learning
rehearsal-free continual learning		 1.012026
Spectral Disentanglement: Rank-Aware Task Adaptation for Rehearsal-free Continual Learning in LLMs · ACL (1) 2026
Natural language and speech › Language models and text generation
large language model		 0.312026
Spectral Disentanglement: Rank-Aware Task Adaptation for Rehearsal-free Continual Learning in LLMs · ACL (1) 2026
Machine learning › Efficient and distributed learning
model compression		 0.312026
Harmonizing the Past, Present, and Future: A Null-Space Constrained Region-Specific Method for Continual Learning in LLMs · ACL (1) 2026

Methods — techniques the papers use, named apart from their topics

spectral disentanglement · 1.0region-specific parameter isolation · 1.0rank-aware task adaptation · 1.0null space projection · 1.0
YearPublicationVenuePosition
2026 Harmonizing the Past, Present, and Future: A Null-Space Constrained Region-Specific Method for Continual Learning in LLMs
abstract
Jinhui Chen, Shizhu He, Xingchang Yang, Huanxuan Liao, Yequan Wang, Xiangwen Liao, Wenhao Teng, Kang Liu, Jun Zhao. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.
Shizhu He, Xingchang Yang, Huanxuan Liao, Yequan Wang, Xiangwen Liao, Wenhao Teng, Kang Liu 0001, Jun Zhao 0001
 ACL (1)7
2026 Spectral Disentanglement: Rank-Aware Task Adaptation for Rehearsal-free Continual Learning in LLMs
abstract
Huanxuan Liao, Shizhu He, Yupu Hao, Yequan Wang, Wenhao Teng, Xiangwen Liao, Jun Zhao, Kang Liu. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.
Huanxuan Liao, Shizhu He, Yupu Hao, Yequan Wang, Wenhao Teng, Xiangwen Liao, Jun Zhao 0001, Kang Liu 0001
 ACL (1)5