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...
By Owen Du, Yang Yue, Jie Zhang, Jiaqi Pi, Chi Bene Chen, Gao Huang
The paper introduces Action–Future Coupled Effect Learning (AFCE), a method that shifts the primary prediction target of vision‑language‑action (VLA) policies from action chunks to future‑grounded physical Effects. AFCE constructs temporally ordered Effect tokens from demonstrations, robot responses, and visual transitions, and uses reconstruction objectives to preserve executable detail and physical change. On the DexJoCo benchmark, AFCE achieves a 50.97% overall success rate, outperforming baseline policies by 11.82 and 15.21 percentage points and excelling on all five bimanual tasks, underscoring the benefit of Effect supervision for coordinated dexterous manipulation.
By Min Lin, Bokai Zhou, Jianqi Lin, Kaiyuan Yang, Yicheng Chang, Junjie Yu, Xiaofan Liu, Jianhua Han, Rui Li, Shen Zhao, Xiaodan Liang
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.
By Tengyue Jiang, Chunpu Xu, Jiayue Kang, Yao Mu
arXiv:2511. 18960v4 Announce Type: replace Abstract: Vision-Language-Action (VLA) models have shown remarkable progress in embodied tasks recently, but most methods process visual observations independently at each timestep.
By Lei Xiao, Jifeng Li, Juntao Gao, Feiyang Ye, Yan Jin, Jingjing Qian, Jing Zhang, Yong Wu, Xiaoyuan Yu
HIL-UMI is a policy-guided Universal Manipulation Interface that enables robot‑free, human‑in‑the‑loop post‑training of vision‑language‑action models. By querying the current policy during handheld demonstrations and using an Energy Score to detect out‑of‑distribution states, it selectively collects new data and refines a progress‑based advantage estimator. The updated estimator then drives advantage‑conditioned behavioral cloning, improving performance on long‑horizon and precise manipulation tasks while reducing per‑frame collection time compared to HG‑DAgger.
By Zimu Han, Yiming Zeng, Jiyao Zhang, Zihao Zhao, Yuanfei Wang, Yixiang Jin, Shiqi Li, Shuangben Chen, Wei Huang, Ruodai Li, Hui Shen, Hao Dong
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.
By Mohammed Hassan (Celine), Zhenyang Chen (Celine), Zheng Wang (Celine), Zhixin Zhu (Celine), Tianlong Chen (Celine), Yingyan (Celine), Lin, Chaojian Li
arXiv:2607. 18236v1 Announce Type: cross Abstract: Pretrained dense visual features from Vision Transformers (ViTs) are powerful yet have been underutilized in robot learning.
By Gaoyue Zhou, Zichen Jeff Cui, Ada Langford, Bowen Tan, Yann LeCun, Lerrel Pinto
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.
By Boyang Shen, Kaixiang Yang, Hao Wang, Qiuyu Yu, Qiang Xie, Qiang Li, Zhiwei Wang
The paper introduces Interaction‑Aligned Pruning (IAprune), a training‑free method for visual token pruning in embodied manipulation tasks. IAprune jointly decides per‑frame budget and token selection, using semantic‑motion spatial agreement to choose between conservative and aggressive coverage, and applies geometric residual correction to focus on under‑represented boundaries. Experiments on four policies, three simulation benchmarks, and a real‑robot platform show that IAprune matches unpruned performance on LIBERO while achieving up to 1.54× speed‑up and 1.48× acceleration on a real robot.
By Jintao Cheng, Weibin Li, Haozhe Wang, Gang Wang, Yipu Zhang, Xiaoyu Tang, Jin Wu, Xieyuanli Chen, Yunhui Liu, Wei Zhang
arXiv:2507. 05116v5 Announce Type: replace-cross Abstract: Recent large-scale Vision Language Action (VLA) models have shown superior performance in robotic manipulation tasks guided by natural language.
By Juyi Lin, Amir Taherin, Arash Akbari, Arman Akbari, Lei Lu, Guangyu Chen, Taskin Padir, Xiaomeng Yang, Weiwei Chen, Yiqian Li, Xue Lin, David Kaeli, Pu Zhao, Yanzhi Wang
The paper introduces a dual‑stream memory architecture for vision‑language‑action policies, separating a task‑agnostic temporal compressor from a task‑conditioned visual retriever. The temporal compressor uses a Gated DeltaNet to condense history into a single token, while the retriever keeps frames above a relevance threshold and fuses them into spatial tokens. Evaluated on sixteen RoboMME tasks and four real‑robot tasks, the combined model outperforms the FrameSamp+Modul baseline, achieving higher mean success rates and notable gains on tasks requiring execution‑stage discrimination.
By Yang Wang, Ping Liu, Ruiyu Wang, Xuhua Chen, Lingfeng Zhang, Tao Zhang
La‑JEPA introduces a compact world‑action model that trains a policy transformer from scratch in the feature space of a pretrained V‑JEPA encoder, learning to predict future features jointly with actions during training but generating only actions at inference. The approach achieves state‑of‑the‑art performance on RoboTwin 2.0 and LIBERO‑Plus while using far fewer parameters and running faster than comparable methods such as Fast‑WAM, LeapBot‑WA, and JEPA‑WAM. A design study shows that JEPA features outperform video VAE latents, especially out‑of‑distribution, and that training‑time future‑prediction choices significantly influence policy performance even when future prediction is omitted at inference.
By Mateo Cl\'emente, George Z. Xue, Amin Abyaneh, Liheng Ma, Rui Heng Yang, Tongtong Cao, Zhanguang Zhang, Yingxue Zhang