arXiv AI
ActiveArena: Benchmarking and Understanding Active Perception in Robotic Manipulation
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv Machine Learning
Sep 17
ActiveScale: Scaling Active Perception for Robots across Model, Data, and Hardware
ActiveScale is a framework that enhances active perception for robots by integrating model, data, and hardware innovations. It augments vision‑language‑action models with historical video observations and explicit camera‑pose supervision, and introduces a scalable human‑robot mid‑training recipe using 1000 hours of egocentric and robotic data. The Active‑perception Mobile‑manipulation Platform (AMP) enables single‑operator teleoperation for scalable demonstration collection, leading to improved success rates on active‑perception tasks.
arXiv AI
Aug 18
GaussMemory: Task-Driven 3D Gaussian Scene Memory for Long-Horizon Robotic Manipulation
arXiv:2608. 14986v1 Announce Type: cross Abstract: Long-horizon robotic manipulation fundamentally relies on persistent spatial memory.
arXiv AI
Jun 9
ACTIVE-o3: Empowering MLLMs with Active Perception via Pure Reinforcement Learning
arXiv:2505. 21457v2 Announce Type: replace-cross Abstract: Active vision, also known as active perception, refers to actively selecting where and how to look in order to gather task-relevant information.
arXiv AI
Aug 6
Explicit Language Memory for Long-Horizon Planning in Vision-Language-Action Models
arXiv:2608. 04765v1 Announce Type: cross Abstract: Vision-language-action (VLA) models provide a unified paradigm for connecting visual perception, language understanding, and robotic control.
arXiv Machine Learning
Jun 16
AVA-VLA: Improving Vision-Language-Action models with Active Visual Attention
arXiv:2511. 18960v4 Announce Type: replace Abstract: Vision-Language-Action (VLA) models have shown remarkable progress in embodied tasks recently, but most methods process visual observations independently at each timestep.
arXiv AI
Sep 18
JEPA-WAM: Connecting Generated Visual Instructions to World Action Models through JEPA Latent Representations
JEPA-WAM enhances World Action Models (WAMs) by pairing text instructions with stochastically generated visual cues, using a text-to-image generator and a frozen V‑JEPA encoder to create dense goal representations. These representations are compressed into goal tokens that condition both video and action experts via cross‑attention, enabling the model to better ground instructions. On a new real‑robot benchmark, JEPA‑WAM attains 87.3%, 74.5%, and 80.9% success rates across in‑distribution, out‑of‑distribution scenes, and out‑of‑distribution instructions, outperforming prior methods by significant margins.