1:23RD-VLA Scales Robot Reasoning in Latent Space@DJiafei · 20 views · 2026-02-10VLALatent ReasoningRecurrent Networks
TemporalFlow-VLA: Learning Physically Grounded Execution History for Long-Horizon Robot ManipulationVision-language-action (VLA) models leverage pretrained vision-language representations for robot control, yet simply adding historical frames does not reliably capture recent physical change. This is especially problematic in multi-stage manipulation, where visually similar states may require different actions depending on prior execution. To address this challenge, we present TemporalFlow-VLA, which learns compact execution history through physically grounded temporal supervision. Using recorded robot states, robot geometry, and calibrated cameras, we construct robot-surface temporal flow as a training-only target and supervise two execution-aligned temporal queries that provide structured history to the action expert. The geometric supervision path is not evaluated at deployment. TemporalFlow-VLA achieves 97.63 +/- 0.26% average success on LIBERO, including 96.60 +/- 0.87% on LIBERO Long, and 85.5%/84.2% Clean/Randomized success across 12 RoboTwin tasks. It shows its clearest advantage over prior methods on longer-horizon, multi-stage manipulation. Controlled history interventions show that action prediction depends on both historical content and temporal order. With asynchronous feature caching, temporal conditioning maintains single-frame-level server-side sampling latency without additional historical-encoding overhead. Overall, TemporalFlow-VLA provides a compact, physically grounded interface for exploiting ordered execution history without explicit motion estimation or geometric processing at deployment.Jiarui Yang, Yehao Lu, Yuning Su·Aug 27, 2026VLATemporal FlowLong-Horizon ManipulationAug 27, 2026
Per-Group Error, Not Total MSE: Fine-Tuning Vision-Language-Action Models for 11-DoF Mobile ManipulationFine-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 ≤ 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-vlaPau Montagut Bofi, Mario García Blasco, Tessa Pulli·May 29, 2026VLA ModelMobile ManipulationFine-tuningMay 29, 2026
1:23
