Information-Theoretic Constraints for Continual Vision-Language-Action Alignment

Libang Zhao; Qixin Zeng; Hongyin Zhang; Donglin Wang

cs.CVMar 6, 2026

Information-Theoretic Constraints for Continual Vision-Language-Action Alignment

Authors: Libang Zhao, Qixin Zeng, Hongyin Zhang, Donglin Wang

Organizations: Westlake University, China · University of Southampton, UK

Abstract

When deployed in open-ended robotic environments, Vision--Language--Action (VLA) models need to continually acquire new skills, yet suffer from severe catastrophic forgetting. We observe that this degradation is related to the deterioration of cross-modal information structure, where dependencies among visual observations, language instructions, and actions progressively diffuse during continual adaptation. But existing continual learning methods fail to preserve such cross-modal information dependencies. Thus, we propose Info-VLA, an information-preserving continual learning framework that maintains cross-modal information structure through two complementary constraints. Replay Anchor Contrastive Learning constructs stable alignment anchors from a frozen teacher model, preserving cross-modal alignment in the representation space. Cross-Modal Mutual Information Maximization further preserves dependency structure between visual and language representations through mutual information constraints. By jointly preserving historical alignment and cross-modal dependency information, Info-VLA balances stability and plasticity during continual learning. Furthermore, experiments on the LIBERO show that Info-VLA significantly outperforms existing methods in both task retention and adaptation.

Figures & tables

Figure 1: Deterioration of cross-modal information structure. After Task 1 ends, compared to the same task, attention diffusion begins.

Figure 2: The proposed architecture consists of two main components. Left: this part depicts the model’s data flow, covering input feature composition, prediction generation, and the structured action space representation. Right: this section illustrates key approach, leveraging replay-anchored contrastive learning to retain historical task knowledge and vision–language mutual information regularization to enforce cross-modal structural consistency.

methods	Base	Task1		Task2		Task3		Task4		Task5		AA
		Old	All	Old	All	Old	All	Old	All	Old	All
multitask		92.4		92.4		92.4		92.4		92.4
Sequential	80.8	8.8	22.3	24.0	32.0	0.0	11.5	9.0	18.4	0.8	10.0	29.2
EWC	80.8	7.2	10.3	8.0	12.0	0.0	6.0	9.7	19.3	6.2	15.4	24.0
ER	80.8	63.6	64.3	75.6	78.0	68.3	72.3	67.0	69.8	64.0	66.6	72.0
Ours	80.8	72.8	75.0	83.3	82.3	71.4	74.5	84.7	86.0	71.0	73.6	78.7

Table 1: Performance comparison of different methods on the LIBERO-Long

B5\text{-}5N1

benchmark. Old denotes the average success rate on previously learned tasks, All denotes the average success rate over all encountered tasks, and AA summarizes average success across the entire continual learning sequence. Bold denotes best performance.

methods	Task1	Task2		Task3		Task4		Task5		AA
	All	Old	All	Old	All	Old	All	Old	All
multitask	98.4	98.4		98.4		98.4		98.4
Sequential	94.0	2.0	40.0	6.0	34.0	0.0	22.5	1.0	20.0	42.1
EWC	96.0	12.0	49.0	9.0	24.0	3.0	25.0	4.0	21.0	43.0
ER	96.0	48.0	63.0	52.0	63.3	44.7	56.0	43.0	53.6	67.2
Ours	98.0	68.0	73.0	56.0	67.3	54.7	64.0	55.0	64.0	73.3

Table 2: Performance comparison of different methods on the LIBERO-Goal

B0\text{-}5N1

benchmark. Continual learning proceeds directly from the original pre-trained model. Old denotes the average success rate on previously learned tasks, All denotes the average success rate over all encountered tasks, and AA summarizes average success across the entire continual learning sequence. Bold denotes best performance.

Figure 3: The evolution of success rates for our method compared with five baseline methods on the LIBERO-Long

B5\text{-}5N1

benchmark. Solid curves represent the average success rates across three runs with different random seeds, and the shaded areas correspond to standard deviation.

Figure 4: Ablation Study on Mutual Information Structure Preservation. BASE denotes the representation structure immediately after learning the target task. ER and Ours illustrate the representation structure of the same task after subsequent training on a new task. Red boxes indicate similarity, while orange boxes indicate dissimilarity.

Figure 5: Ablation study.

\lambda_{1}

and

\lambda_{2}

are hyperparameters that balance the contributions of the RAC and CMI losses. When

\lambda_{1}

is varied,

\lambda_{2}

is fixed at 0.1 ,

\lambda_{2}

is varied,

\lambda_{1}

is fixed at 0.1. Final average accuracy with varying values of

\lambda

RAC	CMI	AUC ↑	FWT ↑	NBT ↓	FAA ↑
$\times$	$\times$	73.9	88.4	-4.3	66.6
$\surd$	$\times$	78.5	89.4	-0.4	73.5
$\times$	$\surd$	79.3	88.8	-4.1	68.6
$\surd$	$\surd$	81.0	91.2	-1.0	73.6

Table 3: Ablation study of individual components. Evaluated on the LIBERO-Long

B5\text{-}5N1

benchmark. Ablation experiments are conducted to analyze the contributions of Replay Anchor Contrastive (RAC) Learning and Cross-Modal Mutual Information (CMI) Maximization. The best success rate is marked in red.

Continual Learning for VLA Models

Continual learning for vision-language-action (VLA) models studies how robots acquire new skills without losing previously learned behaviors.

See all 23 papers

Simple Recipe Works: Vision-Language-Action Models are Natural Continual Learners with Reinforcement Learning
Mar 12, 2026Jiaheng Hu, Jay Shim, Chen Tang +4Continual Learning for VLA Models VLA Model Adaptation
UT Austin · UCLA · NTU +1
Continually Evolving Skill Knowledge in Vision Language Action Model
Nov 22, 2025Yuxuan Wu, Guangming Wang, Zhiheng Yang +4Continual Learning for VLA Models Continual Robot Learning
Shanghai Jiao Tong University · Shanghai Innovation Institute · University of Cambridge +4
Pretrained Vision-Language-Action Models are Surprisingly Resistant to Forgetting in Continual Learning
Mar 4, 2026Huihan Liu, Changyeon Kim, Bo Liu +2Continual Robot Learning Continual Learning for VLA Models
The University of Texas at Austin · KAIST · Microsoft Superintelligence.

Mar 12, 2026J/K move · Enter open · S save

Simple Recipe Works: Vision-Language-Action Models are Natural Continual Learners with Reinforcement Learning

Jiaheng Hu, Jay Shim, Chen Tang, Yoonchang Sung+3

UT Austin · UCLA · NTU+1

Continual Learning for VLA Models VLA Model Adaptation RL for VLMs Fine-Tuning

Open paper AskPDF arXiv

Continual Reinforcement Learning (CRL) for Vision-Language-Action (VLA) models is a promising direction toward self-improving embodied agents that can adapt in openended, evolving environments. However, conventional wisdom from continual learning suggests that naive Sequential Fine-Tuning (Seq. FT) leads to catastrophic forgetting, necessitating complex CRL strategies. In this work, we take a step back and conduct a systematic study of CRL for large pretrained VLAs across diverse lifelong RL benchmarks. We find that, contrary to established belief, simple Seq. FT with low-rank adaptation (LoRA) is remarkably strong: it achieves high plasticity, exhibits little to no forgetting, and retains strong zero-shot generalization, frequently outperforming more sophisticated CRL methods. Through detailed analysis, we show that this robustness arises from a synergy between the large pretrained model, parameter-efficient adaptation, and on-policy RL. Together, these components reshape the stability-plasticity trade-off, making continual adaptation both stable and scalable. Our results position Sequential Fine-Tuning as a powerful method for continual RL with VLAs and provide new insights into lifelong learning in the large model era. Code is available at https://github.com/UT-Austin-RobIn/continual-vla-rl

Abstract

Continual Learning for VLA Models

Explore similar work

Simple Recipe Works: Vision-Language-Action Models are Natural Continual Learners with Reinforcement Learning

Continually Evolving Skill Knowledge in Vision Language Action Model

Pretrained Vision-Language-Action Models are Surprisingly Resistant to Forgetting in Continual Learning