The Linear Representation Hypothesis for Vision-Language-Action Models
cs.LG, cs.AI
Submitted: 2026-09-25
Updated: 2026-09-25
Terminology
Sources
- Understanding intermediate layers using linear classifier probes
- V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning
- Decoding Task Progress from VLA Representations
- RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control
- Observing and Controlling Features in Vision-Language-Action Models
- World Models
- Contrastive Conceptor Activation Steering (COAST): Unlocking Vision-Language-Action Models through Hidden States
- Steering Language Models With Activation Engineering
- What Frozen VLAs Already Know About Success: A Probing Study of Value-Like Structure in Foundation Robot Policies
- Representation Engineering: A Top-Down Approach to AI Transparency
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks