AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Embodied Representation Alignment with Mirror Neurons

Wentao Zhu, Zhining Zhang, Yuwei Ren, Yin Huang, Hao Xu, Yizhou Wang

ICCV 2025 · Label-efficient and robust learning › Recognition and long-tail · approach: Contrastive representation theory · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add mirror-neuron representation alignment (contrastive loss) to action recognition trainingViCLIP · RLBench action recognition (18 tasks)accuracy: 71.6 -> 74.9Improved
add mirror-neuron alignment to embodied execution trainingARP · RLBench multi-task manipulation (18 tasks)success rate: 85.3 -> 88.8Improved
add mirror-neuron alignment, fine-grained task Sort ShapeARP · RLBench multi-task manipulation (18 tasks) - Sort Shapesuccess rate: 49.3 -> 66.7Improved
add mirror-neuron alignment, task Stack BlockARP · RLBench multi-task manipulation (18 tasks) - Stack Blocksuccess rate: 56.0 -> 72.0Improved
add mirror-neuron alignment, task Sort ShapeViCLIP · RLBench action recognition (18 tasks) - Sort Shapeaccuracy: 77.3 -> 85.3Improved
fine-tune ViCLIP on object manipulation data versus zero-shotViCLIP · RLBench action recognition (18 tasks)accuracy: 10.4 -> 71.6Improved
use positive pairs by instruction instead of by class (tau 0.1) (ablation)MN alignment · RLBench multi-task manipulation (18 tasks) (alignment ablation)success rate: 85.7 -> 88.8Improved
use positive pairs by instruction instead of by class (tau 0.1) (ablation)MN alignment · RLBench action recognition (18 tasks) (alignment ablation)accuracy: 71.6 -> 74.9Improved
use positive pairs by instruction instead of by episode (tau 0.1) (ablation)MN alignment · RLBench action recognition (18 tasks) (alignment ablation)accuracy: 72.9 -> 74.9Improved
raise temperature from 0.1 to 0.2 with by-instruction positives (ablation)MN alignment · RLBench action recognition (18 tasks) (alignment ablation)accuracy: 74.9 -> 77.1Improved
raise temperature from 0.1 to 0.2 with by-instruction positives (ablation)MN alignment · RLBench multi-task manipulation (18 tasks) (alignment ablation)success rate: 88.8 -> 87.0Hurt
lower temperature from 0.1 to 0.02 with by-class positives (ablation)MN alignment · RLBench multi-task manipulation (18 tasks) (alignment ablation)success rate: 85.7 -> 86.9Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy