SL
Sijia Luo
cs.CLcs.AIcs.LGcs.SECarbon cycleClimate changecs.ROHydrology
On Valency
published · living versionsW_uqwnkgk8·v1 · currentpublished
Replan for Error Recovery: Training Embodied VLMs through Verifiable Interaction with Action-Grouped Turn-GSPO
with Zhuoran Wang, Keqing Fan, Yang Li, Jinbo Su +4
1 version
W_mceynmvy·v1published
Preprints & journals
8 papers in the corpus · 2024–2026Replan for Error Recovery: Training Embodied VLMs through Verifiable Interaction with Action-Grouped Turn-GSPO2610.27003v2 · Zhuoran Wang, Keqing Fan, Yang Li et al.2026 · 0 citationsarXivon Valency
EG-GRPO: Evidence-Guided Step-level Credit Assignment for Deep Search Agents2610.25269v1 · Sijia Luo, Mengjie Gao, Yuxiao He et al.2026 · 0 citationsarXivon Valency
Sparse-RL: Breaking the Memory Wall in LLM Reinforcement Learning via Stable Sparse Rollouts2601.10079v2 · Sijia Luo, Xiaokang Zhang, Yuxuan Hu et al.2026 · 0 citationsarXiv
Multilayer soil moisture depletion intensifies drought impacts on global ecosystems.42851439 · Gu, Xihui, Wang, Ruijie, Chen, Deliang et al.2026 · 0 citationsNature geoscience. 2026;19(10):1205-1212
CoT-based Synthesizer: Enhancing LLM Performance through Answer Synthesis2501.01668v2 · Bohan Zhang, Xiaokang Zhang, Jing Zhang et al.2025 · 2 citationsarXiv
Dynamic Scaling of Unit Tests for Code Reward Modeling2501.01054v1 · Zeyao Ma, Xiaokang Zhang, Jing Zhang et al.2025 · 1 citationarXiv
SpreadsheetBench: Towards Challenging Real World Spreadsheet Manipulation2406.14991v2 · Zeyao Ma, Bohan Zhang, Jing Zhang et al.2024 · 4 citationsarXiv
TableLLM: Enabling Tabular Data Manipulation by LLMs in Real Office Usage Scenarios2403.19318v3 · Xiaokang Zhang, Sijia Luo, Bohan Zhang et al.2024 · 24 citationsarXiv
Career total: 18 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.