Xintong Hu

EricsXt

·

https://ericsxt.github.io/

AI & ML interests

VLA and Embodied AI

Recent Activity

authored a paper 4 days ago

FineVLA: Fine-Grained Instruction Alignment for Steerable Vision-Language-Action Policies

authored a paper 4 days ago

Qwen-VLA: Unifying Vision-Language-Action Modeling across Tasks, Environments, and Robot Embodiments

authored a paper 4 days ago

MRSAudio: A Large-Scale Multimodal Recorded Spatial Audio Dataset with Refined Annotations

View all activity

Organizations

liked a model 2 months ago

xlangai/RoboFine-VLM-397B-A17B

Video-Text-to-Text • 403B • Updated Jul 5 • 209 • 8

liked a dataset 2 months ago

xlangai/RoboFine-bench

Viewer • Updated Jul 5 • 1k • 919 • 5

liked 2 datasets 7 months ago

facebook/action100m-preview

Viewer • Updated Jan 29 • 120k • 930 • 150

genrobot2025/10Kh-RealOmin-OpenData

Updated Apr 24 • 918k • 241

liked a dataset 9 months ago

lerobot/svla_so100_pickplace

Viewer • Updated 27 days ago • 19.6k • 1.74k • 7

liked a dataset 11 months ago

OpenGalaxea/Galaxea-Open-World-Dataset

Preview • Updated Apr 17 • 18.7k • 51