DS
Du Su
cs.CLcs.AIcs.IRcs.LGcs.CRcs.CYDeep LearningDNNs’ inherent characteristicsNeural Networks, ComputerSample-free
On Valency
published · living versionsW_z79fk6fr·v1 · currentpublished
MemBubble: Benchmarking How Agent Memory Shapes LLM Response Diversity
with Jiajun Tan, Fei Sun, Xinyu Ma, Shixuan Zhang +4
1 version
Preprints & journals
9 papers in the corpus · 2020–2026MemBubble: Benchmarking How Agent Memory Shapes LLM Response Diversity2610.25127v1 · Jiajun Tan, Fei Sun, Xinyu Ma et al.2026 · 0 citationsarXivon Valency
Strong yet Controllable LLM Abstention without Learning to Abstain2610.16318v2 · Junwei Zhang, Yifei Wang, Wanli Yang et al.2026 · 0 citationsarXiv
Beyond Reasoning: Reinforcement Learning Unlocks Parametric Knowledge in LLMs2605.07153v1 · Wanli Yang, Hongyu Zang, Junwei Zhang et al.2026 · 0 citationsarXiv
PersonaAct: Simulating Short-Video Users with Personalized Agents for Counterfactual Filter Bubble Auditing2601.22547v1 · Shilong Zhao, Qinggang Yang, Zhiyi Yin et al.2026 · 0 citationsarXiv
The answer lies within: Detecting Trojans from DNNs' inherent characteristics.41534332 · Liu, Xuchao, Cao, Qi, Zhang, Kaike et al.2026 · 0 citationsNeural networks : the official journal of the International Neural Network Society. 2026;198:108573
The 1st Workshop on Human-Centered Recommender Systems2411.14760v1 · Kaike Zhang, Yunfan Wu, Yougang lyu et al.2024 · 2 citationsarXiv
Understanding the Collapse of LLMs in Model Editing2406.11263v2 · Wanli Yang, Fei Sun, Jiajun Tan et al.2024 · 0 citationsarXiv
Unlink to Unlearn: Simplifying Edge Unlearning in GNNs2402.10695v2 · Jiajun Tan, Fei Sun, Ruichen Qiu et al.2024 · 14 citationsarXiv
Prob2Vec: Mathematical Semantic Embedding for Problem Retrieval in Adaptive Tutoring2003.10838v1 · Du Su, Ali Yekkehkhany, Yi Lu et al.2020 · 0 citationsarXiv
Career total: 20 works. 9 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.