Get started
Author

Wenxuan Song

Xiaomi-Robotics-1: Scaling Vision-Language-Action Models with over 100K Hours of Real-World Trajectories
2026 · Xiaomi Robotics Team, Guo, Jun, et al. · arXiv (Cornell University) · 58
PDF
RoboMemArena: A Comprehensive and Challenging Robotic Memory Benchmark
2026 · Lei, Huashuo, Song, Wenxuan, et al. · arXiv (Cornell University) · 43
PDF
4D-WAM: Infusing Spatiotemporal Awareness into World Action Models through Trajectory Fields
2026 · Yang, Lishan, Song, Wenxuan, et al. · arXiv (Cornell University) · 31
PDF
FRAPPE: Infusing World Modeling into Generalist Policies via Multiple Future Representation Alignment
2026 · Zhao, Han, Wang, Jingbo, et al. · arXiv (Cornell University) · 19
PDF
MMaDA-VLA: Large Diffusion Vision-Language-Action Model with Unified Multi-Modal Instruction and Generation
2026 · Yang Liu, Pengxiang Ding, et al. · ACM International Conference on Multimedia (ACM MM) · 13
Revisiting Embodied Chain-of-Thought for Generalizable Robot Manipulation
2026 · Sun, Nan, Zhang, Yuan, et al. · arXiv (Cornell University) · 13
PDF
IPIBench: Evaluating Interactive Proactive Intelligence of MLLMs under Continuous Streams
2026 · Li, Jinzhao, Chen, Yinuo, et al. · arXiv (Cornell University) · 12
PDF
Robust-WAM: Bridging Generative Pretraining and Semantic Foresight in World-Action Models
2026 · Yan, Haodong, Li, Junfeng, et al. · arXiv (Cornell University) · 11
PDF
Rethinking the Practicality of Vision-language-action Model: A Comprehensive Benchmark and An Improved Baseline
2026 · Wenxuan Song, Jiayi Chen, et al. · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · 10
PDF
Fast-dVLA: Accelerating Discrete Diffusion VLA to Real-Time Performance
2026 · Wenxuan Song, Jiayi Chen, et al. · Lecture notes in computer science · 10
PDF
DFM-VLA: Iterative Action Refinement for Robot Manipulation via Discrete Flow Matching
2026 · Chen, Jiayi, Song, Wenxuan, et al. · arXiv (Cornell University) · 7
PDF
VAMPO: Policy Optimization for Improving Visual Dynamics in Video Action Models
2026 · Ge, Zirui, Ding, Pengxiang, et al. · arXiv (Cornell University) · 5
PDF
MobileWAM: Bridging World Action Models to Mobile Manipulation with Chain-of-Foresight
2026 · Fan, Zehua, He, Junjie, et al. · arXiv (Cornell University) · 4
PDF
SEDualVLN: A Spatially-Enhanced Dual-System Framework for Vision-Language Navigation
2026 · Huang, Jingzhi, Huang, Junkai, et al. · arXiv (Cornell University) · 4
PDF
DreamTrajectory: Trajectory-Guided Action Generation with World Model Alignment for Mobile Manipulation
2026 · Yang, Zheng, Zhang, Wenjie, et al. · arXiv (Cornell University) · 3
PDF
MoWorld: A Flash World Model
2026 · Moxin, Team, Ji, Deyi, et al. · arXiv (Cornell University) · 3
PDF
ActiveScale: Scaling Active Perception for Robots across Model, Data, and Hardware
2026 · Zhou, Shuai, Pang, Kaisheng, et al. · arXiv (Cornell University) · 1
PDF
PIVOTS-Bench: Evaluating Fine-Grained Interpersonal Relationship Reasoning in Multimodal Large Language Models
2026 · Shuxiang Zhang, Ciossa Yin, et al. · Conference on Empirical Methods in Natural Language Processing (EMNLP) · 1
PDF
CapVector: Learning Transferable Capability Vectors in Parametric Space for Vision-Language-Action Models
2026 · Song, Wenxuan, Zhao, Han, et al. · arXiv (Cornell University)
PDF
VLA-Adapter: An Effective Paradigm for Tiny-Scale Vision-Language-Action Model
2026 · Association for Artificial Intelligence 2026, Cui, Can, et al. · Underline Science Inc.
1294 - VLA-Adapter: An Effective Paradigm for Tiny-Scale Vision-Language-Action Model
2026 · Association for Artificial Intelligence 2026, Cui, Can, et al. · Underline Science Inc.
Works count: 21
Citation count: 248
H-index: 10
I10-index: 10
Year
Topic
Type