arXiv Machine Learning
Part Grounding, Not Action Knowledge: Locating the Bottleneck in VLM Affordance Prediction
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv Machine Learning
3d ago
GroundBench: A Factorized, Counterfactual Benchmark for Locating VLM Affordance Failures
arXiv:2609.13308v1 Announce Type: cross Abstract: A companion evaluation found that naming the target part in a manipulation prompt increased action accuracy by 0.32-0.63 across eight vision-language...
arXiv Computer Vision
22h ago
VABench: Measuring Embodied Spatial Intelligence through Visual Demonstrations, Active Perception, and Metric Control
arXiv:2609.19554v1 Announce Type: cross Abstract: Spatial intelligence requires more than describing object locations. Under incomplete observation, models must identify and acquire missing evidence,...
arXiv AI
Jul 1
Position: Vision-Language-Action Models Cannot Be Verified to Perform Physical Reasoning
arXiv:2606. 30686v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) systems, built on pretrained vision-language models (VLMs), have shown rapidly improving performance on robot manipulation benchmarks.
arXiv Machine Learning
Jun 18
Does VLA Even Know the Basics? Measuring Commonsense and World Knowledge Retention in Vision-Language-Action Models
arXiv:2606. 19297v1 Announce Type: new Abstract: Embodied Vision-Language-Action (VLA) models are typically obtained by fine-tuning powerful pretrained VLMs on robotics data, yet it is unclear how much commonsense and factual knowledge they retain after adaptation.
Hugging Face Trending Papers
Jun 17
Does VLA Even Know the Basics? Measuring Commonsense and World Knowledge Retention in Vision-Language-Action Models
Embodied Vision-Language-Action (VLA) models are typically obtained by fine-tuning powerful pretrained VLMs on robotics data, yet it is unclear how much commonsense and factual knowledge they retain after adaptation. Failures on knowledge-sensitive tasks are ambiguous, conflating missing knowledge with poor generalization of low-level control.
arXiv AI
Jul 29
CoTinyVLA: Chain-of-Thought Distillation for a Sub-Billion-Parameter Vision-Language-Action Model
arXiv:2607. 25487v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models translate natural-language commands into robot action sequences, but leading systems on the LIBERO-Plus robustness benchmark use three- to seven-billion-parameter backbones whose memory demands can exceed embedded robotic budgets.