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

Yufei Guo; Yinan Wu; Haoran Duan; Guiguang Ding; Jungong Han

cs.ROAug 15, 2026

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

Authors: Yufei Guo, Yinan Wu, Haoran Duan, Guiguang Ding, Jungong Han

Organizations: Tsinghua University

Abstract

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.

Figures & tables

Figure 1: Motivation for within-trajectory control-regime conditioning. A single manipulation rollout can traverse different control regimes, including approach, grasp, transport, and precise placement. We summarize these variations with two continuous descriptors: fine-control tendency $P$ and event/boundary intensity $E$ . PhaseLoRA uses these descriptors to modulate the LoRA left factor, $B(P,E)=B_{0}+P\!\cdot\!B_{P}+E\!\cdot\!B_{E}+PE\!\cdot\!B_{PE}$ , so the effective low-rank update can vary across control steps instead of remaining static throughout the rollout.

Figure 2: Overview of PhaseLoRA. A lightweight router predicts fine-control tendency $\hat{P}_{t}$ and event/boundary intensity $\hat{E}_{t}$ from the current policy context. These descriptors modulate the action-expert LoRA update through shared, descriptor-specific, and interaction components, yielding control-regime-dependent low-rank corrections within a rollout. The router is trained with weak proxy targets derived from trajectory statistics.

Method	#Params	LIBERO(%)
Method	#Params	Spatial	Object	Goal	10	Avg.
LoRA [ 10 ]	2.70%	$60.7\pm 0.6$	$41.3\pm 2.1$	$32.7\pm 1.5$	$18.7\pm 0.6$	$38.3\pm 1.2$
High-rank LoRA	4.42%	$71.0\pm 1.0$	$73.3\pm 1.2$	$55.3\pm 3.1$	$27.0\pm 4.6$	$56.7\pm 2.3$
DoRA [ 23 ]	4.42%	$72.7\pm 0.6$	$74.0\pm 2.6$	$57.3\pm 2.5$	$29.7\pm 3.5$	$58.4\pm 2.2$
LoRA-MoE [ 33 ]	4.47%	$73.3\pm 1.5$	$70.7\pm 2.5$	$58.0\pm 2.0$	$31.0\pm 4.6$	$58.3\pm 2.4$
LoRA-SP [ 17 ]	4.42%	$76.3\pm 3.2$	$72.0\pm 2.0$	$56.0\pm 1.0$	$32.3\pm 2.5$	$59.2\pm 2.3$

Table 1: Main results on LIBERO. We report success rates (%) on the four standard LIBERO suites and their overall average, together with the number of trainable parameters for each PEFT method. Results are reported as mean

\pm

standard deviation over 3 random seeds.

Method	#Params	Move	Remove	Pick	Put	Avg.
High-rank LoRA	4.42%	$60.0\pm 8.2$	$53.3\pm 4.8$	$63.3\pm 9.4$	$26.7\pm 4.7$	$50.8\pm 4.2$
Ours	4.41%	$\mathbf{66.7\pm 4.8}$	$\mathbf{70.0\pm 8.2}$	$\mathbf{90.0\pm 8.2}$	$\mathbf{50.0\pm 8.2}$	$\mathbf{69.2\pm 3.1}$

Table 2: Main results on the real-world benchmark. We report mean

\pm

standard deviation across 3 seeds, with 10 trials per task for each seed.

Method	Success (%)	Drop vs. Ours
High-rank LoRA	$71.0\pm 1.0$	14.3
Ours w/ random descriptors	$66.3\pm 3.2$	19.0
Ours w/ scalar-gated update	$73.7\pm 1.5$	11.6
Ours w/o proxy supervision	$78.7\pm 3.1$	6.6
Ours ( $P$ only)	$80.7\pm 1.5$	4.6
Ours ( $E$ only)	$81.0\pm 2.0$	4.3

Table 3: Ablations on LIBERO-Spatial. We report suite-level success rate. Random descriptors test whether arbitrary temporal modulation is sufficient, while scalar-gated updates test whether descriptor-dependent rescaling of a fixed LoRA direction recovers the gain.

Figure 3: Update-direction variation in PhaseLoRA on LIBERO-Spatial. For one representative rollout, the left panel shows the adjacent-step update-direction distance $d_{t}$ across adapted layers and timesteps. The upper-right row shows four rollout frames, and the lower-right panel overlays the per-layer distances with their across-layer median. Vertical lines indicate the displayed grasp, transport, and placement events. Large $d_{t}$ peaks are sparse and tend to occur near these transitions.

Analysis	Statistic	Spatial	Object	Goal	10
Descriptor alignment	Spearman $\rho(d_{t},\|\Delta\hat{P}_{t}\|)$	0.502	0.439	0.497	0.440
Descriptor alignment	Spearman $\rho(d_{t},\|\Delta\hat{E}_{t}\|)$	0.712	0.743	0.709	0.737
Transition enrichment	High- $d_{t}$ near transitions	21.0%	24.3%	21.8%	24.3%
	High- $d_{t}$ outside transitions	8.1%	7.9%	8.7%	9.0%
	Enrichment	2.60 $\times$	3.10 $\times$	2.52 $\times$	2.71 $\times$

Table 4: Quantitative update-direction analysis across the four LIBERO suites. For each suite, statistics are computed over 100 evaluation episodes. We report Spearman correlations between update-direction changes and descriptor changes over all valid timestep samples. High-

d_{t}

timesteps are defined as the top 10% of timesteps within each suite, and transition neighborhoods are defined as

\pm 5

timesteps around automatically detected gripper-command transitions.

Appendix figures & tables2 assets

Supplementary material from the paper’s appendix.

Appendix

Panel of Figure 4 — Figure 4: Real-world benchmark setup. (a) Piper robotic arm with a two-finger gripper and a wrist-mounted RGB camera. (b) Full tabletop setup with a fixed external RGB camera, lighting, task objects, and the robot workspace. (c) Example external-camera observation showing the plates, objects, and distractors used in evaluation. The policy uses two RGB views and language instructions, without proprioceptive, force, or tactile inputs.

Panel of Figure 5 — Figure 5: Additional update-direction visualizations for the remaining LIBERO suites. Each row shows one representative rollout from LIBERO-Object, LIBERO-Goal, or LIBERO-10. In each row, the left panel shows the adjacent-step update-direction distance $d_{t}$ across adapted layers and timesteps, the upper-right row shows four rollout frames, and the lower-right panel overlays the per-layer distances with their across-layer median. Vertical lines indicate the displayed grasp, transport, and placement events. As in the main-text LIBERO-Spatial example, large $d_{t}$ peaks are sparse and tend to occur near these transitions.

Low-Rank Adaptation

Low-rank adaptation (LoRA) fine-tunes pretrained models with compact weight updates, reducing trainable parameters and deployment costs.

See all 511 papers

Adaptive Capacity Allocation for Vision Language Action Fine-tuning
Mar 8, 2026Donghoon Kim, Minji Bae, Unghui Nam +4Parameter-Efficient Fine-Tuning Low-Rank Adaptation
Department of Electrical and Computer Engineering, Seoul National University, Seoul 08826, Republic of Korea · Department of Computer Science and Engineering, Sungkyunkwan University, Suwon 16419, Republic of Korea
PHASER: Phase-Aware and Semantic Experience Replay for Vision-Language-Action Models
Jun 2, 2026Ziyang Chen, Shaoguang Wang, Weiyu Guo +5Continual Learning for VLA Models Robotic Manipulation
Thrust of AI, HKUST(Guangzhou), Guangzhou, China · AI2 Robotics, Shenzhen, China
VLA-GSE: Boosting Parameter-Efficient Fine-Tuning in VLA with Generalized and Specialized Experts
May 7, 2026Yuhua Jiang, Junjie Lu, Xinyao Qin +4Fine-Tuning Vision-Language-Action Models
Microsoft Research Asia · Tsinghua University

Mar 8, 2026J/K move · Enter open · S save

Adaptive Capacity Allocation for Vision Language Action Fine-tuning

Donghoon Kim, Minji Bae, Unghui Nam, Gyeonghun Kim+3

Department of Electrical and Computer Engineering, Seoul National University, Seoul 08826, Republic of Korea · Department of Computer Science and Engineering, Sungkyunkwan University, Suwon 16419, Republic of Korea

Parameter-Efficient Fine-Tuning Low-Rank Adaptation Vision-Language-Action Models Robotics

Open paper AskPDF arXiv

Vision language action models (VLAs) are increasingly used for Physical AI, but deploying a pre-trained VLA model to unseen environments, embodiments, or tasks still requires adaptation. Parameter-efficient fine-tuning (PEFT), especially LoRA, is common for VLA policies, yet the exposed capacity knob, the rank, does not transfer uniformly: robotics transfer exhibits a higher and task-varying intrinsic rank than language fine-tuning. Small ranks suffice for LLMs (e.g.,

r \in \{4, 8\}

), while spectral analyses indicate VLAs may require much larger ranks (e.g.,

r \approx 128

) or near-full rank, a mismatch that worsens in multi-task settings. We present LoRA-SP (Select-Prune), a rank-adaptive fine-tuning method that replaces fixed-rank updates with input- and layer-wise capacity. LoRA-SP uses an SVD-style parameterization with a small router whose nonnegative scores act as singular values over a shared vector bank. The active set is chosen by an energy target on the cumulative squared scores

E(k) \ge η

, providing a direct link to approximation error via our spectral analysis. During training,

η

concentrates energy on a few directions and teaches the router to rely on fewer vectors while preserving accuracy. This yields compact adapters that reduce cross-task interference and improve generalization. On four real-robot manipulation tasks collected on an unseen AgileX PiPER arm, across two VLA backbones (

π_0

and SmolVLA), LoRA-SP matches or exceeds full fine-tuning with far fewer trainable parameters, and improves multi-task success by up to 31.6% over standard LoRA while remaining robust to rank choice.

Abstract

Low-Rank Adaptation

Explore similar work

Adaptive Capacity Allocation for Vision Language Action Fine-tuning

PHASER: Phase-Aware and Semantic Experience Replay for Vision-Language-Action Models

VLA-GSE: Boosting Parameter-Efficient Fine-Tuning in VLA with Generalized and Specialized Experts