arXiv Computer Vision
StateVLM: A State-Aware Vision-Language Model for Robotic Affordance Reasoning
Read the original on arXiv Computer Vision →The Flow has not summarised this story yet — read it at arXiv Computer Vision.
Related stories
arXiv AI
Jun 30
GROW$^2$: Grounding Which and Where for Robot Tool Use
arXiv:2606. 30632v1 Announce Type: cross Abstract: Can the robot use a plate to cut a cake if no knife is available?
arXiv AI
Jul 7
Token-Based Affordance Grounding with Large Vision-Language Models
arXiv:2607. 03595v1 Announce Type: cross Abstract: Affordance grounding aims to localize image regions that support a specific action, serving as a core capability for physical intelligence and embodied perception.
arXiv Computer Vision
Aug 24
AffordAny: Open-World 3D Affordance Grounding from Monocular RGB Images via Vision-Language-Guided Geometric Reasoning
arXiv:2608.20720v1 Announce Type: new Abstract: Open-world 3D affordance grounding requires localizing functional object parts in 3D given free-form language queries. Existing methods typically assum...
arXiv AI
Aug 13
SCOUT: Unlocking Enhanced Spatial Reasoning via Structured Chain-of-Thought and Multi-Objective Process Reward
arXiv:2608. 12220v1 Announce Type: cross Abstract: Existing Vision-Language Models (VLMs) exhibits a critical bottleneck in robust spatial reasoning.
arXiv AI
Jun 17
Reinforcing Dual-Path Reasoning in Spatial Vision Language Models
arXiv:2606. 17539v1 Announce Type: cross Abstract: Spatial VLMs have made substantial progress in geometric perception, yet complex spatial reasoning requiring multi-step inference over depth, distance, and scene relations remains challenging.
arXiv AI
Sep 2
Towards Generalizable Visually Grounded Exploration of Household Devices
The paper introduces VGEBench, a new benchmark for evaluating Vision‑Language Models (VLMs) on generalizable, visually grounded exploration of household devices. Unlike existing datasets that rely on static images or annotated trajectories, VGEBench employs a logic‑driven state machine to simulate multi‑turn interaction loops, requiring agents to actively perceive, act, and refine their actions to achieve goals. Experiments show that current VLMs struggle to translate semantic knowledge into physical execution and to maintain long‑horizon state tracking.