Skip to content
AI Atlas
PaperActive

FiberTune: Preserving Action-Fiber Visual Residuals in Vision-Language-Action Fine-Tuning

arxiv.org/abs/2606.08653

Updated 52 min ago · first seen 11 Sept 2026

paper_01M294GQ5VC97PYAG67M64AC2W

Published
11 Sept 2026
T1 · 52 min ago
arXiv
2606.08653
T1 · 52 min ago
Category
cs.CV
T1 · 52 min ago

Abstract

-cross Abstract: Action-supervised fine-tuning of vision-language-action (VLA) policies fits demonstrations effectively but constrains only the directions that change predicted actions, leaving visual structure consistent across action-equivalent states free to collapse. We formalize this as residual visual collapse along local action fibers and propose FiberTune, a training-time objective that preserves teacher-structured visual residuals without adding inference-time overhead. FiberTune uses an online action probe to estimate action-predictive feature directions, filters them from intermediate visual-token representations, and aligns the resulting probe-filtered residuals to a frozen visual teacher while regularizing their effective rank. Under identical training conditions, FiberTune improves over task-loss-only fine-tuning in every one of six controlled simulation settings spanning two benchmarks and two architectures (pi_0.5 and OpenVLA-OFT), as well as on physical SO-101 pick-place; representative gains include +10.7 percentage points SR(5) on long-horizon CALVIN ABC-to-D and physical SO-101 task success rising from 72.7% to 78.1%. Residual diagnostics show that these gains coincide with increased probe-filtered residual teacher alignment and effective rank, consistent with the action-fiber motivation.

Authors 10

Haihao Lin, Xiangsheng Huang, Xiao Yang, Weibang Zhou, Yiqi Zhang, Bo Yang, Simin Zeng, Jiawei Yang, Zhengyang Wang, Jiahui Du

Specification

Official page

Source:arXiv (Atom API + RSS)T1observed 52 min agohigh

Arxiv announce type
replace

Source:arXiv (Atom API + RSS)T1observed 52 min agohigh

arXiv id
2606.08653

Source:arXiv (Atom API + RSS)T1observed 52 min agohigh

Categories
cs.CV, cs.AI, cs.LG, cs.RO

Source:arXiv (Atom API + RSS)T1observed 52 min agohigh

PDF

Source:arXiv (Atom API + RSS)T1observed 52 min agohigh

Primary category
cs.CV

Source:arXiv (Atom API + RSS)T1observed 52 min agohigh

Published
11 Sept 2026

Source:arXiv (Atom API + RSS)T1observed 52 min agohigh

Each value shows its source, tier and observation time. Conflicting claims are kept side by side and flagged — never averaged. How AI Atlas records facts →

Provenance

Attributed facts

9

Source tiers

T19

Freshest observation

52 min ago

Conflicts

None