JL
Jiangran Lyu
cs.ROcs.CVcs.AIcs.LGcs.CLcs.MM
On Valency
published · living versionsW_anmet6z8·v1 · currentpublished
HumanoidNDM: Closing the Training-Deployment Gap of Motion Tracking via Humanoid Neural Dynamics Model
with Chao Chen, Zhenrong Wang, Jilong Wang, Yusen Feng +2
1 version
Preprints & journals
20 papers in the corpus · 2023–2026Uni-PNP: Unified Prehensile and Non-prehensile Policy Learning for Generalizable Object Pose Reaching2610.21735v1 · Wenxuan Zhu, Yuze Wang, Jiangran Lyu et al.2026 · 0 citationsarXiv
What Visual Representations Do World Action Models Need?2610.13024v1 · Kai Liu, Jiangran Lyu, Tingyu Deng et al.2026 · 0 citationsarXiv
S-Space: Exploring Spatial Workspace in Multimodal Language Models2610.13527v1 · Zhiyuan Shi, Xiang Li, Xingzhuo Guo et al.2026 · 0 citationsarXiv
Discovering Visual Co-occurrence for Fine-grained Image Retrieval.42848545 · Wang, Shijie, Li, Haojie, Lyu, Jiangran et al.2026 · 0 citationsIEEE transactions on pattern analysis and machine intelligence. 2026;PP
DualWAM: Dual-System World Action Models for Asynchronous Global Planning and Local Refinement2609.24868v1 · Yixin Zheng, Jiangran Lyu, Yuntian Deng et al.2026 · 0 citationsarXiv
GIF: Agentic Generation of Interactive and Functional Object Compositions for Robot Learning2609.05927v2 · Long Xu, Zhiqi Zhang, Mi Yan et al.2026 · 0 citationsarXiv
ZETA: A Controlled Study of Zero-Shot Cross-Embodiment VLA Transfer for Tabletop Manipulation2609.02546v3 · Mi Yan, Wenhao Zhang, Zhiqi Zhang et al.2026 · 0 citationsarXiv
Code as Worlds: Agentic Discovery of Executable World Representations for Physical Reasoning2608.27549v2 · Hanyang Wang, Yimo Cai, Weiliang Chen et al.2026 · 0 citationsarXiv
HarnessEval-W: Agentifying the Evaluation of Visual Worlds2608.16859v2 · Weiliang Chen, Haowen Sun, Jun Gao et al.2026 · 0 citationsarXiv
WAM-TTT: Steering World-Action Models by Watching Human Play at Test Time2607.06988v3 · Yusen Feng, Bingchen Han, Jiangran Lyu et al.2026 · 0 citationsarXiv
KPGrasp: Scalable Keypoint Flow Matching for Dexterous Grasp Generation2606.09314v2 · Yuansen Huang, Jiayi Chen, Haoran Liu et al.2026 · 0 citationsarXiv
Cosmos 3: Omnimodal World Models for Physical AI2606.02800v4 · NVIDIA: Aditi, Niket Agarwal, Arslan Ali et al.2026 · 1 citationarXiv
BiDexGrasp: Coordinated Bimanual Dexterous Grasps across Object Geometries and Sizes2604.06589v2 · Mu Lin, Yi-Lin Wei, Jiaxuan Chen et al.2026 · 0 citationsarXiv
Emerging Extrinsic Dexterity in Cluttered Scenes via Dynamics-aware Policy Learning2603.09882v2 · Yixin Zheng, Jiangran Lyu, Yifan Zhang et al.2026 · 0 citationsarXiv
LDA-1B: Scaling Latent Dynamics Action Model via Universal Embodied Data Ingestion2602.12215v2 · Jiangran Lyu, Kai Liu, Xuheng Zhang et al.2026 · 0 citationsarXiv
RoboVerse: Towards a Unified Platform, Dataset and Benchmark for Scalable and Generalizable Robot Learning2504.18904v1 · Haoran Geng, Feishi Wang, Songlin Wei et al.2025 · 1 citationarXiv
Towards Robust Probabilistic Modeling on SO(3) via Rotation Laplace Distribution.40031200 · Yin, Yingda, Lyu, Jiangran, Wang, Yang et al.2025 · 5 citationsIEEE transactions on pattern analysis and machine intelligence. 2025;47(5):3469-3486
DyWA: Dynamics-adaptive World Action Model for Generalizable Non-prehensile Manipulation2503.16806v2 · Jiangran Lyu, Ziming Li, Xuesong Shi et al.2025 · 2 citationsarXiv
RoboHanger: Learning Generalizable Robotic Hanger Insertion for Diverse Garments2412.01083v4 · Yuxing Chen, Songlin Wei, Bowen Xiao et al.2024 · 2 citationsarXiv
ScissorBot: Learning Generalizable Scissor Skill for Paper Cutting via Simulation, Imitation, and Sim2Real2409.13966v2 · Jiangran Lyu, Yuxing Chen, Tao Du et al.2024 · 0 citationsarXiv
Career total: 21 works. 20 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.