UniTrackPLA introduces a unified panorama-language-action model that simultaneously handles instruction‑guided navigation and dynamic person tracking for embodied robots. Its Panoramic‑Aware Encoding preserves azimuthal and temporal structure, allowing a shared vision‑language backbone to generate continuous waypoint chunks for both tasks. The model also employs World‑Action Consistency to predict future visual states and verify waypoint prefixes, enabling reliable action reuse and replanning when inconsistencies arise. A new OmniTrackNav‑Bench dataset and extensive real‑world experiments demonstrate significant performance gains over prior methods.
By Pengfei Qi, Haoran Lin, Sizhuang Chen, Kai Luo, Sirui Zhang, Xinqi Liu, Fei Cheng, Wenrui Chen, Liming Yin, Kailun Yang
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
CST‑WM is a causally structured world model designed for embodied visual tracking, where a robot must keep a moving target visible and recover it after occlusion or drift. The model separates state into target‑evidence, robot, and observation branches, removing direct action‑to‑target‑evidence edges to prevent causal hallucination and instead letting actions influence evidence through robot motion and resulting views. Evaluated on EVT‑Bench, Habitat 3.0, and real‑world trials with a Unitree Go2 quadruped, CST‑WM outperforms reactive trackers and other world‑model baselines in following, distance control, safety, and re‑acquisition, achieving 20 of 30 successful real‑world recoveries versus 14 for TrackVLA.
By Junyi Hu, Shuaihang Yuan, Jiazhao Liang, Yi Fang
The paper introduces GTA‑VLA, an interactive Vision‑Language‑Action framework that lets users guide robot policies with explicit visual cues such as affordance points, boxes, and traces. Unlike traditional direct sense‑to‑act models, GTA‑VLA incorporates a spatial‑visual Chain‑of‑Thought that blends human guidance with internal task planning, and couples this reasoning module with a lightweight reactive action head for efficient execution. Experiments on the SimplerEnv WidowX benchmark show a state‑of‑the‑art 81.2 % success rate, and the framework significantly improves task success under out‑of‑domain visual shifts and spatial ambiguities, demonstrating the benefit of interactive reasoning for failure recovery in embodied control.
By Yiran Ling, Qing Lian, Jinghang Li, Qing Jiang, Tianming Zhang, Xiaoke Jiang, Chuanxiu Liu, Jie Liu, Lei Zhang
Zero-WAM introduces a causal video-action model that enables robots to perform unseen manipulation tasks by following in-context human video guidance. The authors create HumanGen, a dataset of 74.2K human-robot ICL pairs across 8.6K tasks, and propose an in-context future chunk prediction objective to prevent shortcut learning. In simulation, Zero-WAM attains a 47.0% success rate on seven unseen tasks, outperforming the best video-action baseline by 29.5 percentage points, and demonstrates real‑world generalization to complex, long‑horizon, and fine‑grained tasks.
By Jiaming Zhou, Qihang Zhang, Gangwei Xu, Cunxin Fan, Yujie Zhao, Ruilin Wang, Yiming Luo, Shuai Yang, Xing Zhu, Yujun Shen, Junwei Liang, Yinghao Xu
Zero-shot cross-task generalization, where a policy must execute manipulation tasks never seen during training, remains a central challenge in robot learning. In large language models, a novel task ca...
The paper introduces VLAct, a Vision‑Language‑Action model that focuses on representation‑centric continued pre‑training rather than merely scaling robot data. VLAct is trained on diverse, multi‑embodiment robot data and preserves a broad VLM prior while encouraging shared action semantics across embodiments. Experiments across simulation, real‑world, and unseen‑embodiment settings show that VLAct consistently outperforms existing industrial VLA systems, achieving high success rates with only a modest compute budget and open‑source data.
By Senqiao Yang, Chengyao Wang, Yuxin Chen, Zixuan Wang, Longxiang Tang, Haokun Gui, Jinhui Ye, Changsheng Lu, Xiaoyang Wu, Mingkang Zhu, Pengguang Chen, Shu Liu, Zhuotao Tian, Hengshuang Zhao, Bei Yu, Jiaya Jia
arXiv:2606. 12550v1 Announce Type: cross Abstract: Open-world mapless navigation from sparse language instructions requires resolving underspecified goals and inferring which environmental cues are relevant for reaching the goal.
By Arthur Zhang, Carl Qi, Donne Su, Xiangyun Meng, Amy Zhang, Joydeep Biswas
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.
By Yueh-Hua Wu, Tatsuya Matsushima, Kei Ota
CondenseVLA introduces a learnable history‑condensation module that distills short‑term visual context into a fixed set of slot tokens via learnable queries and cross‑attention, reducing redundancy and improving action decoding. The approach achieves notable gains on several robot manipulation benchmarks, raising Simpler‑WidowX success from 58.7% to 69.8%, reaching 97.2% on LIBERO, 52.8% on real‑world tasks, and 21.6% on memory‑dependent RMBench tasks.
By Feiyang Hong, Yujie Wei, Bo Zhao, Xiu Su, Hongxun Yao, Shuo Yang
The paper introduces Intention Distillation (INDI), a method that injects behavior-level intent into Vision‑Language‑Action (VLA) model decoders by leveraging a frozen teacher vision‑language model to interpret demonstrations. During training, the teacher processes the current observation, instruction, coarse action summary, and execution video, producing a multimodal intent representation that the VLA decoder uses alongside trajectory and execution features to predict actions. Experiments on SimplerEnv‑Bridge, RoboCasa Kitchen, and real‑world tasks show that INDI consistently improves success rates, especially on longer‑horizon tasks, demonstrating that explicit modeling of semantic intent benefits action decoders.
By Sangoh Lee, Sangwoo Mo, Wook-Shin Han
Dynin‑Robotics introduces an omnimodal masked‑diffusion backbone, Dynin‑Omni, that jointly represents language, visual observations, goals, and actions as discrete tokens. By conditioning on different spans, the same model learns action prediction, next‑observation prediction, goal‑state prediction, and trajectory‑to‑instruction reconstruction, enabling test‑time scaling through goal prediction and action‑candidate evaluation. The system, pretrained on 1.33 million trajectories from 48 Open X‑Embodiment datasets, achieves competitive performance on LIBERO, zero‑shot LIBERO‑Plus, and a 78.4 % success rate on a Franka Research 3 robot, while a block‑parallel implementation speeds up action decoding by up to 29.2×.
By Hoeun Lee, Jaeik Kim, Jusang Oh, Jinhyeok Kim, Geon Choi, Hyeonggeun Kim, Jaeyoung Do