The Layer Mystery of VLA: An Information-Theoretical Analysis of VLA Latent Interface
cs.AI
Submitted: 2026-09-28
Updated: 2026-09-28
Sources
- GR00T N1: An Open Foundation Model for Generalist Humanoid Robots
- Contrastive Representation Regularization for Vision-Language-Action Models
- SmolVLA: A Vision-Language-Action Model for Affordable and Efficient Robotics
- OpenVLA: An Open-Source Vision-Language-Action Model
- Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success
- ABot-M0: VLA Foundation Model for Robotic Manipulation with Action Manifold Learning
- $\pi_0$: A Vision-Language-Action Flow Model for General Robot Control
- VLA-Adapter: An Effective Paradigm for Tiny-Scale Vision-Language-Action Model
- Layer by Layer: Uncovering Hidden Representations in Language Models
- The Tunnel Effect: Building Data Representations in Deep Neural Networks
- Intermediate Layer Classifiers for OOD generalization
- How Does Information Bottleneck Help Deep Learning?
- Representation Learning with Contrastive Predictive Coding
- Deep Variational Information Bottleneck
- On Variational Bounds of Mutual Information
- DiME: Maximizing Mutual Information by a Difference of Matrix-Based Entropies
- APT: Action Expert Pretraining Improves Instruction Generalization of Vision-Language-Action Policies
- Task adaptation of Vision-Language-Action model: 1st Place Solution for the 2025 BEHAVIOR Challenge
- ROCKET: Residual-Oriented Multi-Layer Alignment for Spatially-Aware Vision-Language-Action Models
- Cosmos World Foundation Model Platform for Physical AI
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Agents' Last Exam
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems