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

• URL: http://arxiv.org/abs/2606.00253v1
• Date: Fri, 29 May 2026 18:36:08 GMT
• Title: Per-Group Error, Not Total MSE: Fine-Tuning Vision-Language-Action Models for 11-DoF Mobile Manipulation
• Abstract summary: Per-group analysis exposes two patterns: in SmolVLA, the mobile base converges slowest and limits overall performance.<n>In expert-only fine-tuning of $_0.5$ (training only the action head, backbone frozen), total MSE drops below the baseline but arm accuracy degrades.<n>We conclude that per-group error is a more reliable signal than total MSE for checkpoint selection on robots with heterogeneous action spaces.
• Score: 4.798596809049421
• License: http://creativecommons.org/licenses/by/4.0/
• 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. We argue this is a predictable consequence of collapsing heterogeneous joint groups (arm, gripper, head, wheeled base) into a single metric, where easy-to-predict joints can mask joints that still fail. We fine-tune SmolVLA (450M, action-expert only) on the 11-DoF Toyota HSR and compare it against $π_{0.5}$ (3.3B), a stronger pretrained baseline. Per-group analysis exposes two patterns: in SmolVLA, the mobile base converges slowest and limits overall performance. In expert-only fine-tuning of $π_{0.5}$ (training only the action head, backbone frozen), total MSE drops below the baseline but arm accuracy degrades. On 60 real-robot trials (20 per model), $π_{0.5}$ 80k (4.0/4) significantly outperforms both fine-tuned variants (expert-only 3k: 3.75/4; HSR-SmolVLA: 3.5/4; Mann-Whitney $p \leq 0.010$), despite expert-only 3k having the lowest total MSE. This separation is most consistent with the offline arm-group error, not total MSE or base-group error. We conclude that per-group error is a more reliable signal than total MSE for checkpoint selection on robots with heterogeneous action spaces. Code: https://github.com/paumontagut/per-group-mse-vla

Related papers

• Ockhamareto: Pareto-Gated Segment-Level Credit Assignment for Concise Unit-Test Generation with Reinforcement Learning [64.49364696628294]
  We introduce textbfOckhamareto, a single-shot GRPO framework for unit-test generation and selection.<n>Ockhamareto has two principal components: (i)a emphPareto-gated Bonus that rewards only rollouts non-dominated in(mutation, $-$#tests) space, and (ii)emphToken-level Segment Credit, which attributes each test's marginal mutation kills back to the tokens of its unit-test block.
  arXiv  Detail & Related papers  (2026-08-25T12:20:02Z)
• Right-Sizing LLM-Agent Decomposition in VAT Determination: A Pilot Controlled Sweep [0.3384279376065155]
  This pilot studies that choice on bounded cross-border VAT determination with reverse charge.<n>We hold the activity surface fixed (subtasks, tools, I/O schemas, validation checks, orchestrator, base model, and merge policy)<n>The program spans 4,400 runs: a 40-case, five-repeat main sweep, matched-token arms separating prompt-budget from agent-count effects, and three failure-injection arms.
  arXiv  Detail & Related papers  (2026-08-24T15:40:15Z)
• Safety, or Just Capability? A Validity Audit of Agent-Safety Benchmarks [10.839956062772792]
  Three agent-safety benchmarks rank the same 18 models differently.<n>R-Judge specificity against AgentHarm safety correlates $-0.64$ at $n=7$ and $+0.02$ at $n=18$, and a quarter of random size-7 subsets reach $|| geq 0.5$ around that near-zero value.<n>AgentHarm shows the strongest held-out association, $=+0.72$ with three-template jailbreak safety after controlling capability.
  arXiv  Detail & Related papers  (2026-07-30T03:45:10Z)
• Which Defense Closes Which Threat? Attributing OWASP-LLM-Top-10 Coverage and Its Brittleness Under Paraphrasing [51.56484100374058]
  Production LLM applications stack several defense families -- refusal-phrase filters, tokenbudget controls, model allowlists, rate limits, tool-registry authentication -- yetBAS benchmarks report a single aggregate coverage number.<n>We add four-LLM-Top-10-aware agents to a 21-agent baseline scanner and target a lattice of four synthetic LLM endpoints.
  arXiv  Detail & Related papers  (2026-06-01T19:39:25Z)
• Hidden-State Privacy Has an Empty Middle [51.56484100374058]
  We prove a complementary Fisher-ball lower bound: every full-rank Gaussian release at $O(1)$ Fisher utility admits a direction whose Mahalanobis signal grows linearly in hidden width.<n>A split-memory transformer trained from scratch reaches $G_mathrmMah in [20, 33]$ at 90M and maintains a $6$--$24times$ advantage over same-budget GPT baselines from 30M to 1B at a fixed-token language loss penalty.
  arXiv  Detail & Related papers  (2026-05-21T20:12:09Z)
• Ensembling Tabular Foundation Models - A Diversity Ceiling And A Calibration Trap [3.478921293603811]
  No single Tabular foundation models (TFMs) wins on every dataset.<n>We benchmark six ensemble strategies over six TFMs on 153 classification tasks.<n>The best ensemble, two-level cascade stacking, buys $+0.18%$ accuracy over the strongest single TFM at $253times$ the compute.
  arXiv  Detail & Related papers  (2026-05-18T17:32:57Z)
• Attributing Emergence in Million-Agent Systems [68.53670424791751]
  Large language models (LLMs) can simulate human-like reasoning and decision-making in individual agents.<n>Such studies require attributing macro emergence to individual agents.<n>We adapt Aumann--Shapley path-integral attribution to LLM-powered MAS at million-agent scale.
  arXiv  Detail & Related papers  (2026-05-12T01:49:41Z)
• The Scaling Law of Evaluation Failure: Why Simple Averaging Collapses Under Data Sparsity and Item Difficulty Gaps, and How Item Response Theory Recovers Ground Truth Across Domains [0.0]
  Benchmark evaluation across AI and safety-critical domains overwhelmingly relies on simple averaging.<n>We demonstrate that this practice produces substantially misleading rankings when two conditions co-occur.
  arXiv  Detail & Related papers  (2026-05-11T20:17:55Z)
• Hardware Validation of DAGI via a Modular "Ridge" Signature and High-Order Synergistic Information [0.0]
  DAGI (Directed Acyclic Graph Information) framework on IBM Quantum hardware.<n>Small, controlled experiment whose ideal output distribution is constrained to a low-dimensional modular manifold (a "ridge)<n>Key recovery exceeds chance: per-shot accuracy 0.1689 (chance 0.125, 95% Wilson CI [0.1610, 0.1772])<n>These results support the claim that DAGI detects and quantifies non-trivial, hardware-resilient information structure.
  arXiv  Detail & Related papers  (2026-04-16T14:16:59Z)
• DISCO: Diversifying Sample Condensation for Efficient Model Evaluation [59.01400190971061]
  Costly evaluation reduces inclusivity, slows the cycle of innovation, and worsens environmental impact.<n>We argue that promoting diversity among samples is not essential; what matters is to select samples thatmaximise diversity in model responses.<n>Our method, $textbfDiversifying Sample Condensation (DISCO)$, selects the top-k samples with the greatest model disagreements.
  arXiv  Detail & Related papers  (2025-10-09T08:53:59Z)
• Multitask Learning Can Improve Worst-Group Outcomes [76.92646345152788]
  Multitask learning (MTL) is one such widely used technique. We propose to modify standard MTL by regularizing the joint multitask representation space. We find that our regularized MTL approach emphconsistently outperforms JTT on both average and worst-group outcomes.
  arXiv  Detail & Related papers  (2023-12-05T21:38:24Z)
• Fine-Grained Gap-Dependent Bounds for Tabular MDPs via Adaptive Multi-Step Bootstrap [84.66885506098724]
  This paper presents a new model-free algorithm for episodic finite-horizon Markov Decision Processes (MDP), Adaptive Multi-step Bootstrap (AMB) We show AMB achieves a gap-dependent regret bound that only scales with the sum of the inverse of the sub-optimality gaps. We also show AMB suffers an additional $frac|Z_mul|Delta_min$ regret, where $Z_mul$ is the set of state-action pairs $(s,a)$'s satisfying $a$ is a non-unique optimal action for
  arXiv  Detail & Related papers  (2021-02-09T07:46:34Z)
• Inner Ensemble Networks: Average Ensemble as an Effective Regularizer [20.33062212014075]
  Inner Ensemble Networks (IENs) reduce the variance within the neural network itself without an increase in the model complexity. IENs utilize ensemble parameters during the training phase to reduce the network variance.
  arXiv  Detail & Related papers  (2020-06-15T11:56:11Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.