Brain-Aligned Latent Actions: Imposing Premotor Cortex Geometry on a Robot's Action Vocabulary
cs.RO, cs.LG
Submitted: 2026-11-08
Updated: 2026-11-08
Terminology
Sources
- Distilling Neural Population Geometry into Transformers and GRUs for Motor Control
- Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation
- Lost in Reconstruction: Aligning Action Representations with Language in Vision-Language-Action Models
- Learning Additively Compositional Latent Actions for Embodied AI
- Algebraic Consistency Alone Does Not Certify Temporal Structure in Latent Action Models
- Identifying Latent Actions and Dynamics from Offline Data via Demonstrator Diversity
- Improving the Accuracy and Robustness of CNNs Using a Deep CCA Neural Data Regularizer
- Relational Geometry Forcing for World Action Models
- Brain alignment of reasoning and action representations from vision-language and action models during naturalistic gameplay
Related papers
- Rethinking Actions: Continuity-Aware Priors for World-Model Planning
- MOSAIC: Modular Obstacle and Spatial-Aware Framework for Manipulation In Cluttered Scenes
- SAGAS: Semantic-Aware Graph-Assisted Stitching for Offline Temporal Logic Planning
- DexSeed: Expanding Human Hand-Object Interactions into Robot Demonstrations for Dexterous Policy Learning
- LaST0.5: A Generalist World Action Model with Interaction-Centric Latent Reasoning
- CIALLO: Learning Shared Intent Representations for Cross-Embodiment Manipulation