SB
Shuanghao Bai
cs.ROcs.CVcs.LGcs.AIcs.CLDeep LearningDifferentiable causal discoveryHeterogeneous dataInformation theoryInformation Theory
On Valency
published · living versionsW_p6ssubkq·v1 · currentpublished
HAF-VLA: Hierarchical Action Flow Framework for Humanoid Vision-Language-Action Control
with Langzhe Gu, Chengkai Hou, Meng Li, Xinhua Wang +10
1 version
Preprints & journals
20 papers in the corpus · 2023–2026HAF-VLA: Hierarchical Action Flow Framework for Humanoid Vision-Language-Action Control2610.26584v1 · Langzhe Gu, Chengkai Hou, Meng Li et al.2026 · 0 citationsarXivon Valency
EmbodiedSmith: Scaling Embodied Data through Recursive Self-Improvement Flywheel in Simulation2610.07969v1 · Yikai Qin, Yifei Deng, Mingjian Liang et al.2026 · 0 citationsarXiv
DIDO: Distilling Interaction-Centric Dynamics into One-Step Denoising for World Action Models2609.15570v3 · Jing Lyu, Shuanghao Bai, Runze Xiao et al.2026 · 0 citationsarXiv
GraphIR: Architecture-Level Search States for LLM-Guided Neural Architecture Evolution2608.01633v1 · Zhen Liu, Wanqi Zhou, Shuanghao Bai et al.2026 · 0 citationsarXiv
BlockVLA: Accelerating Autoregressive VLA via Block Diffusion Finetuning2605.13382v1 · Ruiheng Wang, Shuanghao Bai, Haoran Zhang et al.2026 · 0 citationsarXiv
Assistance Without Interruption: A Benchmark and LLM-based Framework for Non-Intrusive Human-Robot Assistance2605.01368v1 · Yuedi Zhang, Shuanghao Bai, Wanqi Zhou et al.2026 · 0 citationsarXiv
HEX: Humanoid-Aligned Experts for Cross-Embodiment Whole-Body Manipulation2604.07993v3 · Shuanghao Bai, Meng Li, Xinyuan Lv et al.2026 · 0 citationsarXiv
Embodied Robot Manipulation in the Era of Foundation Models: Planning and Learning Perspectives2512.22983v2 · Shuanghao Bai, Wenxuan Song, Jiayi Chen et al.2025 · 0 citationsarXiv
VCoT-Grasp: Grasp Foundation Models with Visual Chain-of-Thought Reasoning for Language-driven Grasp Generation2510.05827v1 · Haoran Zhang, Shuanghao Bai, Wanqi Zhou et al.2025 · 0 citationsarXiv
Dual-Path Stable Soft Prompt Generation for Domain Generalization2505.18770v1 · Yuedi Zhang, Shuanghao Bai, Wanqi Zhou et al.2025 · 0 citationsarXiv
OpenHelix: A Short Survey, Empirical Analysis, and Open-Source Dual-System VLA Model for Robotic Manipulation2505.03912v1 · Can Cui, Pengxiang Ding, Wenxuan Song et al.2025 · 2 citationsarXiv
An information-theoretic approach for heterogeneous differentiable causal discovery.40158364 · Zhou, Wanqi, Bai, Shuanghao, Xie, Yuqing et al.2025 · 5 citationsNeural networks : the official journal of the International Neural Network Society. 2025;188:107417
VLAS: Vision-Language-Action Model With Speech Instructions For Customized Robot Manipulation2502.13508v2 · Wei Zhao, Pengxiang Ding, Min Zhang et al.2025 · 0 citationsarXiv
PromptTA: Prompt-driven Text Adapter for Source-free Domain Generalization2409.14163v1 · Haoran Zhang, Shuanghao Bai, Wanqi Zhou et al.2024 · 6 citationsarXiv
Jacobian Regularizer-based Neural Granger Causality2405.08779v1 · Wanqi Zhou, Shuanghao Bai, Shujian Yu et al.2024 · 4 citationsarXiv
Soft Prompt Generation for Domain Generalization2404.19286v2 · Shuanghao Bai, Yuedi Zhang, Wanqi Zhou et al.2024 · 24 citationsarXiv
Revisiting the Adversarial Robustness of Vision Language Models: a Multimodal Perspective2404.19287v3 · Wanqi Zhou, Shuanghao Bai, Danilo P. Mandic et al.2024 · 0 citationsarXiv
Enhancing Robot Task Planning and Execution through Multi-Layer Large Language Models.38475223 · Luan, Zhirong, Lai, Yujun, Huang, Rundong et al.2024 · 24 citationsSensors (Basel, Switzerland). 2024;24(5)
Prompt-based Distribution Alignment for Unsupervised Domain Adaptation2312.09553v2 · Shuanghao Bai, Min Zhang, Wanqi Zhou et al.2023 · 84 citationsarXiv
Improving Cross-domain Few-shot Classification with Multilayer Perceptron2312.09589v1 · Shuanghao Bai, Wanqi Zhou, Zhirong Luan et al.2023 · 5 citationsarXiv
Career total: at least 26 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.