SAMBAR: Selective Anchoring via Method of Multipliers for Balanced Knowledge Acquisition and Retention in Vision-Language-Action Models
cs.LG, cs.RO
Submitted: 2026-09-26
Updated: 2026-09-26
Project page: https://iconlab.negarmehr.com/SAMBAR
Terminology
Sources
- $\pi_{0.5}$: a Vision-Language-Action Model with Open-World Generalization
- MolmoAct: Action Reasoning Models that can Reason in Space
- On Tiny Episodic Memories in Continual Learning
- Scaling Laws for Forgetting during Finetuning with Pretraining Data Injection
- Pretrained Vision-Language-Action Models are Surprisingly Resistant to Forgetting in Continual Learning
- Can Vision-Language-Action Models Learn from Real-World Data Continually without Forgetting?
- PriorVLA: Prior-Preserving Adaptation for Vision-Language-Action Models
- Breaking Lock-In: Preserving Steerability under Low-Data VLA Post-Training
- Towards Long-Lived Robots: Continual Learning VLA Models via Reinforcement Fine-Tuning
- CRL-VLA: Continual Vision-Language-Action Learning
- Simple Recipe Works: Vision-Language-Action Models are Natural Continual Learners with Reinforcement Learning
- Robust Finetuning of Vision-Language-Action Robot Policies via Parameter Merging
- Memory Aware Synapses: Learning what (not) to forget
- DataMIL: Selecting Data for Robot Imitation Learning with Datamodels
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