← Back to all news
arXiv Computer Vision By Shenglan Li, Zhendong Mi, Hengyi Zhu, Jingwu Luo, Chun Kit Chan, Geng Yuan, Yanzhi Wang, Pu Zhao, Shaoyi Huang

Imagine the Future, Internalize the Gist: Efficient VLA Reasoning via Internalized Spatiotemporal Imagination

Read the original on arXiv Computer Vision →

The paper introduces IG‑VLA, a vision‑language‑action framework that learns to imagine task‑relevant future scene evolution in a latent spatiotemporal space, guiding action prediction without generating full pixel‑level videos. It further compresses this future reasoning into a compact Scene Gist Token via Scene Gist Memory, enabling efficient inference. Experiments on LIBERO, LIBERO‑Plus, and VLABench show that IG‑VLA improves success rates by nearly 6% and speeds up inference up to 6.38× compared to strong baselines.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.

Related stories

arXiv Computer Vision
3d ago

DynamicVLA: A Vision-Language-Action Model for Dynamic Object Manipulation

DynamicVLA is a latency‑aware Vision‑Language‑Action model designed for dynamic object manipulation, featuring a compact 0.4B architecture and a convolutional vision encoder for efficient multimodal inference. It employs a continuous inference schedule that overlaps reasoning and execution, and a Latent‑aware Action Streaming mechanism that discards stale action prefixes to maintain action‑time alignment. The authors also introduce the Dynamic Object Manipulation (DOM) benchmark, comprising 200K synthetic episodes and 2K real‑world episodes, and demonstrate that DynamicVLA improves dynamic manipulation success in simulation and on real robots.

By Haozhe Xie, Beichen Wen, Jiarui Zheng, Zhaoxi Chen, Fangzhou Hong, Haiwen Diao, Ziwei Liu
roboticsmultimodalbenchmarkssafety
More like this →
arXiv AI
Jun 30

X-Mind: Efficient Visual Chain-of-Thought via Predictive World Model for End-to-End Driving

arXiv:2606. 28758v1 Announce Type: cross Abstract: Predicting future states is essential for autonomous agents, yet current Vision-Language-Action (VLA) models fundamentally lack this capability, relying instead on reactive perception-action mapping.

By Bohao Zhao, Chengrui Wei, Guangfeng Jiang, Ruixin Liu, Xuejie Lv, Liu Liang, Sutao Deng, Xiuyang Fan, Pengkun Zheng, Jinyun Zhou, Rui Guo, Hanpeng Liu, Yutong Zheng, Yi Guo, Xinlong Zheng, Qingyu Luo, Zhuangzhuang Ding, Yu Zhang, Hang Zhang, Xianming Liu
agentsdiffusionmultimodal
More like this →