WG
Weinan Gan
cs.AIcs.IRcs.CL
On Valency
published · living versionsW_cgnsvegp·v1 · currentpublished
Select-TTT: Query-Conditioned Selective Fast Weight Updates for In-Place Test-Time Training
with Yue Wu, Yang Zhang, Chongming Gao, Xinsen Guo +2
1 version
Preprints & journals
8 papers in the corpus · 2023–2026FineSID: Scalable and Efficient Semantic Identifier Learning for Generative Recommendation2609.36670v2 · Song-Li Wu, Weinan Gan, Zhaocheng Du et al.2026 · 0 citationsarXiv
FairDiff: Mitigating the Self-Reinforcing Matthew Effect in Diffusion Recommender Models2609.36671v2 · Song-Li Wu, Xianquan Wang, Zhaocheng Du et al.2026 · 0 citationsarXiv
CodeSkill: Latent Skill Abstraction for Long-Horizon Code Agents2609.33243v2 · Song-Li Wu, Jingyi Wang, Zhaocheng Du et al.2026 · 0 citationsarXiv
ActiveMem: Dynamic Latent Memory Trees for Long-Horizon Agents2609.33244v2 · Song-Li Wu, Jingyi Wang, Zhaocheng Du et al.2026 · 0 citationsarXiv
How Does Personalized Memory Shape LLM Behavior? Benchmarking Rational Preference Utilization in Personalized Assistants2601.16621v1 · Xueyang Feng, Weinan Gan, Xu Chen et al.2026 · 0 citationsarXiv
Don't Start Over: A Cost-Effective Framework for Migrating Personalized Prompts Between LLMs2601.12034v1 · Ziyi Zhao, Chongming Gao, Yang Zhang et al.2026 · 0 citationsarXiv
Personalize Before Retrieve: LLM-based Personalized Query Expansion for User-Centric Retrieval2510.08935v2 · Yingyi Zhang, Pengyue Jia, Derong Xu et al.2025 · 4 citationsarXiv
T2Ranking: A large-scale Chinese Benchmark for Passage Ranking2304.03679v1 · Xiaohui Xie, Qian Dong, Bingning Wang et al.2023 · 18 citationsarXiv
Career total: 15 works. 8 are in this corpus.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.