Beyond In-Distribution Preservation: Recovering Generalization in Quantized VLAs via Vulnerability-Oriented Tuning
cs.LG, cs.RO
Submitted: 2026-10-05
Updated: 2026-10-09
Code: https://github.com/ruanruan-andy/PIVOT-Q
Terminology
Sources
- GR00T N1: An Open Foundation Model for Generalist Humanoid Robots
- $\pi_{0.5}$: a Vision-Language-Action Model with Open-World Generalization
- VITA-VLA: Efficiently Teaching Vision-Language Models to Act via Action Expert Distillation
- Distilling the Knowledge in a Neural Network
- HoloQ-VLA: Uniform W4A4 Quantization of Vision-Language-Action Models
- Quantization-Aware Distillation for NVFP4 Inference Accuracy Recovery
- ActDistill: General Action-Guided Self-Derived Distillation for Efficient Vision-Language-Action Models
- RPTQ: Reorder-based Post-training Quantization for Large Language Models
- VLA-OPD: Bridging Offline SFT and Online RL for Vision-Language-Action Models via On-Policy Distillation
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: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks