arXiv Machine Learning June 2, 2026 By Pau Montagut Bofi, Mario Garc\'ia Blasco, Tessa Pulli, Markus Vincze

Per-Group Error, Not Total MSE: Fine-Tuning Vision-Language-Action Models for 11-DoF Mobile Manipulation

Read the original on arXiv Machine Learning →

arXiv:2606. 00253v1 Announce Type: cross Abstract: Fine-tuning Vision-Language-Action (VLA) models for mobile manipulators with heterogeneous joint spaces can produce a counterintuitive result: the checkpoint with the lowest aggregate MSE is not the one that performs best on the real robot.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

arXiv AI

Aug 25

Mamba-based Selective State Space Modeling Improves the Accuracy-Complexity Tradeoff of SmolVLA Vision-Language-Action Experts

arXiv:2608.21407v1 Announce Type: cross Abstract: Vision-language-action (VLA) models face a crucial tradeoff between their task success rate and the policy-call frequency. Executing a single action...

By Farida Mohsen, Thowayba Elkaffash, Mohammad Reza Chalak Qazani, Mohamed Mabrok, Nader Meskin, Ali Safa

llms robotics multimodal benchmarks

arXiv Computer Vision

Sep 23

Sample, Simulate, Select: Physics-in-the-Loop Text-to-Motion for Humanoids Without Training

arXiv:2609.26420v1 Announce Type: cross Abstract: Text-to-motion models generate plausible human motion but do not model a robot's dynamics; whole-body tracking controllers execute robot references r...

By Raphael Memmesheimer, Sven Behnke

robotics

arXiv AI

Jun 30

Critical Interval MSE: Toward Reliable Offline Validation for Robot Manipulation Policies

arXiv:2606. 29898v1 Announce Type: cross Abstract: Real-world evaluation is the gold standard for robot policies because it tests them against the physical conditions and deployment challenges they are ultimately designed to handle.

By Haoxu Huang, Tongsam Zheng, Yifan Chen, Jiacheng You, Yang Gao

robotics safety

arXiv AI

4d ago

Spotter: Let the Embodied Model Lead, and the VLM Reflect for It

arXiv:2609.36808v1 Announce Type: cross Abstract: Current embodied models do not respond to their own failures, although what just went wrong could inform a small adjustment on the next attempt, the...

By Long Li, Qichao Zhao, Yue Yang, Fan Xu, Zhe Wang, Alan Wee-Chung Liew, Chao Qu, Heng Tao Shen, Shirui Pan

llms robotics multimodal

arXiv AI

Jul 21

First-Order Predictable but Pairwise Fragile: Local Task Adaptation in Trained Transformers

arXiv:2607. 16821v1 Announce Type: cross Abstract: Task arithmetic, sequential fine-tuning, activation steering, and first-order random search all operate through relatively small perturbations around an already trained checkpoint, and they rely on different local approximations: individual perturbations should be first-order predictable, task updates should compose with controlled interference, useful tangent structure should be stable and possible to estimate, and weight edits should have counterparts in representation space.

By Irina Piontkovskaia, Sergey Nikolenko

llms fine-tuning

arXiv AI

2d ago

MIKASA-Robo-VLA: Benchmarking Memory in VLA Models for Long-Horizon Manipulation

arXiv:2610.00604v1 Announce Type: cross Abstract: Vision-language-action policies often see only one or a few recent frames, which makes it difficult to evaluate how they use information that disappe...

By Egor Cherepanov, Nikita Kachaev, Aleksandr I. Panov, Alexey K. Kovalev

rag robotics fine-tuning multimodal benchmarks

One email a morning, machine-written

Related stories

Mamba-based Selective State Space Modeling Improves the Accuracy-Complexity Tradeoff of SmolVLA Vision-Language-Action Experts

Sample, Simulate, Select: Physics-in-the-Loop Text-to-Motion for Humanoids Without Training

Critical Interval MSE: Toward Reliable Offline Validation for Robot Manipulation Policies

Spotter: Let the Embodied Model Lead, and the VLM Reflect for It

First-Order Predictable but Pairwise Fragile: Local Task Adaptation in Trained Transformers

MIKASA-Robo-VLA: Benchmarking Memory in VLA Models for Long-Horizon Manipulation