Robust Bimanual Vision-Language-Action Models via Embarrassingly Simple Modality Masking

• URL: http://arxiv.org/abs/2608.22419v1
• Date: Sun, 23 Aug 2026 13:48:57 GMT
• Title: Robust Bimanual Vision-Language-Action Models via Embarrassingly Simple Modality Masking
• Abstract summary: We show that structured training-time masking can improve robustness of query-based VLA policies for bimanual manipulation.<n>Results suggest that structured training-time masking is a practical way to improve the robustness of query-based VLA policies for bimanual manipulation.
• Score: 48.85795530951384
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Query-based Vision-Language-Action (VLA) models offer low-latency inference that is attractive for bimanual robotic manipulation, but we observe that they can still exhibit discontinuous actions and execution failures in complex dual-arm tasks. We hypothesize that unstable multi-view and language fusion is one contributing factor in these failures, often coinciding with attention spreading to distracting regions. To improve robustness, we introduce the Modality Masking Mechanism (M3), an embarrassingly simple, training-only strategy that requires no architectural changes or large-scale robot pretraining. M3 stochastically masks subsets of modality channels during training, exposing the policy to controlled partial observations and encouraging it to rely less on distracting cues and more on evidence that remains reliable. We evaluate M3 on ten bimanual tasks from RoboTwin 2.0 and on three long-horizon real-world tasks. Compared with the Adapter baseline, M3 improves average success by 21.7% in the Clean setting and 11.4% in Clean2Rand, where policies are trained on clean demonstrations and evaluated on randomized scenes, while also improving averaged real-world full-task success by over 30%. These results suggest that structured training-time masking is a practical way to improve the robustness of query-based VLA policies for bimanual manipulation.

Related papers

• SARM2: Multi-Task Stage Aware Reward Modeling for Self Improving Robotic Manipulation [57.131411215593744]
  Fine-tuning vision-language-action (VLA) policies for long-horizon manipulation still relies heavily on behavior cloning.<n>We introduce RM, a multi-task stage-aware reward model that combines an action-primitive-based stage estimator with a multi-gate Mixture-of-Experts (MMoE) value head.<n>Building on RM, we further propose SPIRAL, an on-policy reward-guided framework that improves VLA policies from cheap autonomous rollouts.
  arXiv  Detail & Related papers  (2026-06-09T01:46:23Z)
• Learning Action Manifold with Multi-view Latent Priors for Robotic Manipulation [67.16145181790522]
  This paper tackles spatial perception and manipulation challenges in Vision-Language-Action (VLA) models.<n>We propose a Geometry-Guided Gated Transformer (G3T) that aligns multi-view features under 3D geometric guidance.<n>To improve action learning efficiency, we introduce Action Manifold Learning (AML), which directly predicts actions on the valid action manifold.
  arXiv  Detail & Related papers  (2026-05-12T09:21:29Z)
• Global Prior Meets Local Consistency: Dual-Memory Augmented Vision-Language-Action Model for Efficient Robotic Manipulation [95.89924101984566]
  We introduce OptimusVLA, a dual-memory VLA framework with Global Prior Memory (GPM) and Local Consistency Memory (LCM)<n>GPM replaces Gaussian noise with task-level priors retrieved from semantically similar trajectories.<n>LCM injects a learned consistency constraint that enforces temporal coherence and smoothness of trajectory.
  arXiv  Detail & Related papers  (2026-02-22T15:39:34Z)
• Information Filtering via Variational Regularization for Robot Manipulation [2.564607372946005]
  We propose a lightweight module that imposes a timestep-conditioned Gaussian over backbone features and applies a KL-divergence regularizer.<n>Our approach improves the success rate by 6.1% on RoboTwin2.0 and by 4.1% on Adroit and MetaWorld, achieving new state-of-the-art results.
  arXiv  Detail & Related papers  (2026-01-29T16:17:42Z)
• EVOLVE-VLA: Test-Time Training from Environment Feedback for Vision-Language-Action Models [57.75717492488268]
  Vision-Language-Action (VLA) models have advanced robotic manipulation by leveraging large language models.<n>Supervised Finetuning (SFT) requires hundreds of demonstrations per task, rigidly memorizing trajectories, and failing to adapt when deployment conditions deviate from training.<n>We introduce EVOLVE-VLA, a test-time training framework enabling VLAs to continuously adapt through environment interaction with minimal or zero task-specific demonstrations.
  arXiv  Detail & Related papers  (2025-12-16T18:26:38Z)
• MDiff4STR: Mask Diffusion Model for Scene Text Recognition [59.79818820650126]
  Mask Diffusion Models (MDMs) have emerged as a promising alternative to auto-regressive models (ARMs) for vision-language tasks.<n>We show that vanilla MDM lags behind ARMs in terms of accuracy, although it improves recognition efficiency.<n>We propose MDiff4STR, a Mask Diffusion model enhanced with two key improvement strategies tailored for Scene Text Recognition.
  arXiv  Detail & Related papers  (2025-12-01T08:57:51Z)
• Token-Level Uncertainty-Aware Objective for Language Model Post-Training [2.5671111123644894]
  We connect token-level uncertainty in causal language modeling to two types of training objectives: 1) masked maximum likelihood (MLE), 2) self-distillation.<n>We show that masked MLE is effective in reducing epistemic uncertainty, and serve as an effective token-level automatic curriculum learning technique.<n>However, masked MLE is prone to overfitting and requires self-distillation regularization to improve or maintain performance on out-of-distribution tasks.
  arXiv  Detail & Related papers  (2025-03-15T00:32:14Z)
• 3D-Grounded Vision-Language Framework for Robotic Task Planning: Automated Prompt Synthesis and Supervised Reasoning [2.6670748466660523]
  Vision-language models (VLMs) have achieved remarkable success in scene understanding and perception tasks.<n>VLMs lack robust 3D scene localization capabilities, limiting their effectiveness in fine-grained robotic operations.<n>We propose a novel framework that integrates a 2D prompt synthesis module by mapping 2D images to point clouds, and incorporates a small language model (SLM) for supervising VLM outputs.
  arXiv  Detail & Related papers  (2025-02-13T02:40:19Z)
• MENTOR: Mixture-of-Experts Network with Task-Oriented Perturbation for Visual Reinforcement Learning [17.437573206368494]
  Visual deep reinforcement learning (RL) enables robots to acquire skills from visual input for unstructured tasks.<n>We present MENTOR, a method that improves both the architecture and optimization of RL agents.<n>MenTOR outperforms state-of-the-art methods across three simulation benchmarks and achieves an average of 83% success rate on three challenging real-world robotic manipulation tasks.
  arXiv  Detail & Related papers  (2024-10-19T04:31:54Z)

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.