T3R is a training‑free, two‑stage token refinement framework designed to improve the efficiency and robustness of Vision‑Language‑Action (VLA) models. The first stage uses segmentation‑guided pruning to remove irrelevant visual patches, while the second stage applies saliency‑guided attention biasing to focus on action‑critical regions and language cues. Experiments on LIBERO‑Spatial, LIBERO, SIMPLER, and RoboTwin show that T3R can eliminate 85% of visual tokens with minimal loss in success rate and even improve performance under distribution shifts, achieving up to a 3.3× speedup in large‑scale settings.
arXiv:2610.08133v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models achieve strong robotic manipulation performance but incur high computational costs from processing long token seq...
LearnPruner rethinks token pruning in vision‑language models by addressing shortcomings of attention mechanisms in vision encoders and large language models. The method uses a two‑stage approach: first a learnable pruning module removes redundant vision tokens after the vision encoder, then only task‑relevant tokens are kept in the LLM’s middle layer. Experiments show that LearnPruner retains about 95% of performance while using only 5.5% of vision tokens, achieving a 3.2× speed‑up.
arXiv:2609.05916v1 Announce Type: cross Abstract: Large vision-language models (LVLMs) achieve strong multimodal understanding, but the hundreds to thousands of visual tokens they process impose subs...
arXiv:2606. 30113v1 Announce Type: cross Abstract: Discrete action tokenization provides a compact interface for autoregressive VLA policies, but accurately recovering continuous robot actions from discrete codes remains challenging.
arXiv:2606. 27872v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models have demonstrated strong capabilities in robotic manipulation, but their performance degrades significantly in long-horizon tasks due to cumulative error propagation.
LoopVLA introduces a recurrent Vision‑Language‑Action architecture that learns to refine multimodal representations, predict actions, and estimate when further refinement is unnecessary. By iteratively applying a shared Transformer block and producing a sufficiency score at each step, it decouples refinement from fixed layer indices and aligns confidence scores with action quality through a self‑supervised objective. Experiments on LIBERO, LIBERO‑Plus, and VLA‑Arena demonstrate that LoopVLA reduces model parameters by 45% and boosts inference throughput up to 1.7× while matching or surpassing strong baselines in task success.
arXiv:2606. 29350v1 Announce Type: cross Abstract: Vision-language models and vision-language action models endow the robot with unprecedented capabilities.
Vision‑Language‑Action models (VLAs) often fail to follow language instructions because they rely on vision shortcuts learned from biased datasets. The authors introduce LIBERO‑CF, a counterfactual benchmark that tests language following by providing alternative task instructions for the same scene layouts, revealing widespread counterfactual failures. They propose Counterfactual Action Guidance (CAG), a dual‑branch inference scheme that amplifies language conditioning, which consistently improves language grounding and task success across diverse VLAs without requiring extra data or architectural changes.
arXiv:2606. 02735v1 Announce Type: cross Abstract: Generalization remains a central bottleneck for vision-language-action (VLA) models: under distractors, appearance shifts, and semantically similar tasks, the policy must often infer local execution details from coarse instructions while also deciding which parts of the image matter for control.
arXiv:2608.21247v1 Announce Type: new Abstract: Token compression has become a key technique for reducing the inference cost of large foundation models, with approaches such as token pruning and KV-c...
arXiv:2608. 07088v1 Announce Type: cross Abstract: Multimodal large language models (MLLMs) encode images as long visual token sequences, making prefilling and KV-cache storage expensive.
arXiv:2610.19361v1 Announce Type: cross Abstract: Embodied visual tracking requires a robot to identify a designated target from visual observations and control its own motion to follow that target t...