ATA: Bridging Implicit Reasoning with Attention-Guided and Action-Guided Inference for Vision-Language Action Models

Cheng Yang, Jianhao Jiao, Lingyi Huang, Jinqi Xiao, Zhexiang Tang, Yu Gong, Yibiao Ying, Yang Sui, Jintian Lin, Wen Huang, Bo Yuan

BibTeX
@misc{yang2026ata,
  author = {Cheng Yang and Jianhao Jiao and Lingyi Huang and Jinqi Xiao and Zhexiang Tang and Yu Gong and Yibiao Ying and Yang Sui and Jintian Lin and Wen Huang and Bo Yuan},
  title = {{ATA: Bridging Implicit Reasoning with Attention-Guided and Action-Guided Inference for Vision-Language Action Models}},
  year = {2026},
  eprint = {2603.01490},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2603.01490},
}

Loading related content...

Figure