JD
Juncheng Diao
cs.AIcs.CLcs.CVcs.LG
On Valency
published · living versionsW_acjnt3k5·v1 · currentpublished
SAPD: Learning from Agent Experience without Environment Interaction
with Haibin Wang, Wei Shi, Yifan Ding, Qingbin Li +2
1 version
Preprints & journals
5 papers in the corpus · 2026SAPD: Learning from Agent Experience without Environment Interaction2610.27847v1 · Juncheng Diao, Haibin Wang, Wei Shi et al.2026 · 0 citationsarXivon Valency
CuraWeb: Joint Optimization of Quality, Redundancy, and Diversity for Web-Scale Pretraining Data2607.22662v1 · Peiguang Li, Yongwei Zhou, Juncheng Diao et al.2026 · 0 citationsarXiv
HIPIF: Hierarchical Planning and Information Folding for Long-Horizon LLM Agent Learning2606.10507v1 · Juncheng Diao, Zhicong Lu, Peiguang Li et al.2026 · 0 citationsarXiv
Predictable Scaling Laws of Optimal Hyperparameters for LLM Continued Pre-training2606.05610v1 · Yongwei Zhou, Juncheng Diao, Junlin Shang et al.2026 · 0 citationsarXiv
Faithful-MR1: Faithful Multimodal Reasoning via Anchoring and Reinforcing Visual Attention2605.22072v1 · Changyuan Tian, Zhicong Lu, Huaxing Liu et al.2026 · 0 citationsarXiv
Career total: 7 works. 5 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.