# PhaseLoRA: Control-Regime-Conditioned Low-Rank Adaptation for Continuous-Action Vision-Language-Action Policies

arXiv: https://arxiv.org/abs/2608.15285 · HTML: https://mlsanity.com/paper/2608.15285/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Reinforcement learning and post-training, one of 13 directions in Vision-language-action models.
- Builds on 32 of its 36 references that are in the map.
- First posted on arXiv 15 Aug 2026.

## Placed in

- Vision-language-action models / [Reinforcement learning and post-training](https://mlsanity.com/vla/reinforcement-learning-and-post-training/)

## Builds on (most cited first, 30 of 32)

- [RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control](https://mlsanity.com/paper/2307.15818/) (2023)
- [OpenVLA: An Open-Source Vision-Language-Action Model](https://mlsanity.com/paper/2406.09246/) (2024)
- [PaLM-E: An Embodied Multimodal Language Model](https://mlsanity.com/paper/2303.03378/) (2023)
- [RT-1: Robotics Transformer for Real-World Control at Scale](https://mlsanity.com/paper/2212.06817/) (2022)
- [π0.5: a Vision-Language-Action Model with Open-World Generalization](https://mlsanity.com/paper/2504.16054/) (2025)
- [Octo: An Open-Source Generalist Robot Policy](https://mlsanity.com/paper/2405.12213/) (2024)
- [LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learning](https://mlsanity.com/paper/2306.03310/) (2023)
- [Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success](https://mlsanity.com/paper/2502.19645/) (2025)
- [DoRA: Weight-Decomposed Low-Rank Adaptation](https://mlsanity.com/paper/2402.09353/) (2024)
- [RDT-1B: a Diffusion Foundation Model for Bimanual Manipulation](https://mlsanity.com/paper/2410.07864/) (2024)
- [Perceiver-Actor: A Multi-Task Transformer for Robotic Manipulation](https://mlsanity.com/paper/2209.05451/) (2022)
- [BC-Z: Zero-Shot Task Generalization with Robotic Imitation Learning](https://mlsanity.com/paper/2202.02005/) (2022)
- [AdaLoRA: Adaptive Budget Allocation for Parameter-Efficient Fine-Tuning](https://mlsanity.com/paper/2303.10512/) (2023)
- [DyLoRA: Parameter Efficient Tuning of Pre-trained Models using Dynamic Search-Free Low-Rank Adaptation](https://mlsanity.com/paper/2210.07558/) (2022)
- [Mixture of LoRA Experts](https://mlsanity.com/paper/2404.13628/) (2024)
- [ForceVLA: Enhancing VLA Models with a Force-aware MoE for Contact-rich Manipulation](https://mlsanity.com/paper/2505.22159/) (2025)
- [LeRobot: An Open-Source Library for End-to-End Robot Learning](https://mlsanity.com/paper/2602.22818/) (2026)
- [VLA-RFT: Vision-Language-Action Reinforcement Fine-tuning with Verified Rewards in World Simulators](https://mlsanity.com/paper/2510.00406/) (2025)
- [TLA: Tactile-Language-Action Model for Contact-Rich Manipulation](https://mlsanity.com/paper/2503.08548/) (2025)
- [X-LoRA: Mixture of Low-Rank Adapter Experts, a Flexible Framework for Large Language Models with Applications in Protein Mechanics and Molecular Design](https://mlsanity.com/paper/2402.07148/) (2024)
- [CO-RFT: Efficient Fine-Tuning of Vision-Language-Action Models through Chunked Offline Reinforcement Learning](https://mlsanity.com/paper/2508.02219/) (2025)
- [HINT: Hypernetwork Instruction Tuning for Efficient Zero- & Few-Shot Generalisation](https://mlsanity.com/paper/2212.10315/) (2022)
- [Simple Recipe Works: Vision-Language-Action Models are Natural Continual Learners with Reinforcement Learning](https://mlsanity.com/paper/2603.11653/) (2026)
- [Conditional LoRA Parameter Generation](https://mlsanity.com/paper/2408.01415/) (2024)
- [Touch begins where vision ends: Generalizable policies for contact-rich manipulation](https://mlsanity.com/paper/2506.13762/) (2025)
- [RoboInter: A Holistic Intermediate Representation Suite Towards Robotic Manipulation](https://mlsanity.com/paper/2602.09973/) (2026)
- [The Art of Imitation: Learning Long-Horizon Manipulation Tasks from Few Demonstrations](https://mlsanity.com/paper/2407.13432/) (2024)
- [HapticVLA: Contact-Rich Manipulation via Vision-Language-Action Model without Inference-Time Tactile Sensing](https://mlsanity.com/paper/2603.15257/) (2026)
- [MokA: Multimodal Low-Rank Adaptation for MLLMs](https://mlsanity.com/paper/2506.05191/) (2025)
- [Adaptive Capacity Allocation for Vision Language Action Fine-tuning](https://mlsanity.com/paper/2603.07404/) (2026)

## Built on by (most cited first, 1 of 1)

- [MorphAct: Robot Policies Morphing with the Worlds They Act In](https://mlsanity.com/paper/2610.20019/) (2026)

## Abstract (arXiv)

Parameter-efficient fine-tuning (PEFT) is a natural way to adapt pretrained vision-language-action (VLA) policies, but most adapter designs apply temporally static updates throughout a control rollout, overlooking the phase-dependent nature of continuous-action manipulation. Such policies traverse distinct regimes, including approach, contact transition, grasping, transport, and placement, each requiring different adaptation behaviors. We propose PhaseLoRA, a lightweight LoRA parameterization that conditions adaptation at each action-chunk prediction step using two weakly supervised descriptors: fine-control tendency and event/boundary intensity. PhaseLoRA modulates the LoRA left factor in the action expert, allowing the effective low-rank update direction to vary over time while keeping the backbone largely frozen. On LIBERO, PhaseLoRA improves average success rate by 12.2 points over a matched-parameter high-rank LoRA baseline and outperforms stronger LoRA variants. Ablations show that random temporal modulation and scalar gating do not reproduce the performance of the full model, while update-direction analyses reveal structured temporal variation associated with the predicted control descriptors. These results establish within-trajectory conditioning as an effective lightweight PEFT axis for continuous-action VLA policies.