JS
Jinbo Su
cs.AIcs.CLcs.CVcs.IRcs.LGcs.MMcs.RO
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, Ke Wang +4
1 version
W_4r4rzy3z·v1published
W_3s9v4h9m·v1published
Preprints & journals
11 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
Selm: Self-Evolving Library Management for Multi-Skill Agent Optimization2610.24630v1 · Mengxi Hu, Yuxuan Hu, Jinbo Su et al.2026 · 0 citationsarXivon Valency
SciLENS: RL-Driven Autonomous Agents for Scientific Localized Evidence Navigation and Synthesis2609.03338v1 · Leqi Zheng, Jinbo Su, Yuying Li et al.2026 · 0 citationsarXivon Valency
Gradients Know What Outcomes Don't: Unlocking Reinforcement Learning for LLM Reasoning with Gradient-Aligned Rewards2609.03342v1 · Leqi Zheng, Jinbo Su, Fang Niu et al.2026 · 0 citationsarXiv
CARA: Concept-Aware Risk Attention for Interpretable Collision Anticipation2607.22494v2 · Zhishan Tao, Ruoyu Wang, Yucheng Wu et al.2026 · 0 citationsarXiv
Visual-Seeker: Towards Visual-Native Multimodal Agentic Search via Active Visual Reasoning2606.15231v1 · Zhengbo Zhang, Changtao Miao, Jinbo Su et al.2026 · 0 citationsarXiv
MemGround: Long-Term Memory Evaluation Kit for Large Language Models in Gamified Scenarios2604.14158v1 · Yihang Ding, Wanke Xia, Yiting Zhao et al.2026 · 0 citationsarXiv
VisBrowse-Bench: Benchmarking Visual-Native Search for Multimodal Browsing Agents2603.16289v2 · Zhengbo Zhang, Jinbo Su, Zhaowen Zhou et al.2026 · 0 citationsarXiv
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
Enhancing Agentic Textual Graph Retrieval with Synthetic Stepwise Supervision2510.03323v3 · Ge Chang, Jinbo Su, Jiacheng Liu et al.2025 · 0 citationsarXiv
KG-Retriever: Efficient Knowledge Indexing for Retrieval-Augmented Large Language Models2412.05547v2 · Weijie Chen, Ting Bai, Jinbo Su et al.2024 · 4 citationsarXiv
Career total: 13 works. 11 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.