PointRL introduces a verifiable reinforcement learning framework that learns point-level vision‑language grounding from heterogeneous annotation evidence such as bounding boxes, masks, and instance labels. The method converts these annotations into pointing instructions while preserving target supports, instance membership, and set constraints as hidden verifier evidence, which a deterministic checker uses to score predictions. Evaluation on PointArena shows that PointRL improves Qwen3.5‑4B’s accuracy from 56.11% to 65.58%, and similar gains are observed on RoboSpatial, BLINK, and Ref‑Adv benchmarks.
By Jingyang Su, Pu Cao, Xiuze Jin, Longyue Zhang, Qing Song, Lu Yang
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
The paper introduces FISER, a framework that explicitly infers human goals and intentions before planning actions for AI agents to follow natural language instructions in collaborative embodied tasks. It employs Transformer-based models and is evaluated on the HandMeThat benchmark, outperforming end-to-end approaches and strong baselines such as Chain of Thought prompting. FISER achieves state‑of‑the‑art performance on this embodied social reasoning task.
By Yanming Wan, Yue Wu, Yiping Wang, Jiayuan Mao, Natasha Jaques
The paper introduces a lightweight multimodal vision‑language framework based on TinyCLIP for fine‑grained classification of early‑stage apple fruitlet anatomy (calyx, fruitlet body, peduncle) in orchard images. Using a dataset of 600 high‑resolution RGB images, the model employs domain‑specific language prompts and a sliding‑window inference strategy to produce interpretable heatmaps for whole‑image localization. Achieving macro‑F1 of 0.93 on an NVIDIA T4 GPU and maintaining accuracy after INT8 quantization, the system is optimized for edge deployment on NVIDIA Jetson hardware with model sizes around 127‑137 MB and millisecond‑level inference.
By Ranjan Sapkota, William Bu, Chen Chen, Yunjun Xu, Manoj Karkee
GaussVLA is a Vision‑Language‑Action model that enhances spatial reasoning by converting flat 2D visual tokens into compact 3D Gaussian tokens using a Gaussian Spatial Tokenizer. It further employs a Depth‑Aware Chain‑of‑Thought module to perform structured, non‑autoregressive geometric reasoning conditioned on language and flow‑time. In both simulated and real‑world tests, GaussVLA achieves high spatial‑manipulation success rates—93.5% on LIBERO and 100% on the Spatial suite—while using only 200 M parameters, outperforming SpatialVLA by 19.7% relative success.
By Md Selim Sarowar, Md Tanvir Islam, Sungho Kim, Sangtae Ahn
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
StreamPI introduces a streaming multimodal temporal modeling framework that enhances Vision‑Language‑Action models by adding temporal reasoning without extra parameters. It anchors each visual observation and language instruction pair as a temporal unit, using bidirectional attention for cross‑modal fusion and causal attention for autoregressive streaming inference. The method employs random‑interval streaming training to improve robustness and leverages the LLM backbone’s length extrapolation to inherit pretrained weights, achieving superior performance over pi0.5 on real‑robot and simulation tasks.
By Zhe Liu, Jinghua Hou, Yuxiang Lu, Zhenya Yang, Xianzhe Fan, Junwei Luo, Junyi Li, Ruihua Han, Zhi Hou, Hengshuang Zhao
Pose-Anchored Optical Flow for Low-Latency Human Action Anticipation in Human-Robot Teaming proposes PoseOFF, a representation that captures local motion around human joints by conditioning optical flow extraction on pose. This structured motion representation aligns with human kinematics and improves early action recognition accuracy across multiple datasets and backbones. PoseOFF achieves comparable or better performance while observing less of the action sequence, making it suitable for real‑time, resource‑constrained robotic systems.
By Lewis de Zoete Grundy, Chris McCarthy, Christopher Fluke
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...
Intent misinterpretation during vehicle interactions causes recurring planning failures. We study a decision layer in which a language-guided intent module reads structured descriptors, computes a smo...
Vision-Language-Action (VLA) models have demonstrated effectiveness in robot manipulation, yet state-of-the-art models such as pi0.5 operate under a single-frame paradigm, limiting their ability to re...
Reasoning in language allows foundation models to spend more test-time compute on hard problems, such as those requiring decomposition, constraint tracking, and prediction of future consequences. Whet...
Action-conditioned world models have become an important foundation for embodied prediction, planning, and synthetic data generation, but their errors under new task and scene distributions are often...
Human-robot interaction (HRI) requires robots to interpret human actions early in their execution in order to respond safely, efficiently, and naturally. However, many existing approaches to human act...
PonderPounce introduces a two‑stage system that leverages a multimodal large language model (MLLM) as an episode‑context engine for robot control. The System2 component, Ponder, accumulates observations, demonstrations, and prior cognition in its native causal context, producing subgoal text and reasoning. The System1 component, Pounce, uses the current observation, instruction, and proprioception, receiving only the newest cognition token and its age from Ponder; the pair is jointly trained end‑to‑end without a separate memory module, achieving real‑time action playback and outperforming baseline methods on RoboMME and RoboCasa‑DC benchmarks.
By Suhwan Choi, Jaeyoon Jung, Sungkyung Kim, Yunsung Lee, Youngjae Yu
The paper surveys the evolution of smart glasses from simple capture devices to first‑person intelligence platforms that integrate human perception, context, and action. It introduces a unified framework that formalizes data flow, hardware capabilities, and seven foundational capabilities, and presents an L0‑L5 hierarchy for capture to embodied action. The study also maps nine application scenes, proposes a nine‑dimensional deployment framework, and outlines an evidence ladder for evaluation and trustworthiness.
By Jiangning Zhang, Haojun Chen, Yong Liu
The paper introduces ARLI, a latency‑aware framework that enables reinforcement learning fine‑tuning of large generalist robot policies despite inference delays. ARLI combines asynchronous inference with state augmentations—incorporating committed actions and mid‑inference observations—to restore near‑Markovian dynamics and maintain reactivity. Experiments on simulated and real‑world manipulation tasks show that ARLI allows effective policy improvement under latency, outperforming standard RL even in no‑latency scenarios.
By Brian Zhu (Siemens), Momen Khalil (Siemens), E Harrison (UC Berkeley), Emanuele Poggi (Siemens), Philipp Schmitt (Siemens), Bernd Kast (Siemens), Philine Meister (Siemens), Pranav Atreya (UC Berkeley), Qiyang Li (UC Berkeley), Finn Ferchau (Siemens), Cesar Colmenero (Siemens), Yash Shahapurkar (Siemens), Gokul Narayanan (Siemens), Melih Erdogan (Siemens), Kai Wurm (Siemens), Georg von Wichert (Siemens), Oier Mees (Microsoft, ETH Zurich, UC Berkeley), Eugen Solowjow (Siemens), Andrew Wagenmaker (UC Berkeley), Sergey Levine (UC Berkeley)
arXiv:2608.23835v1 Announce Type: new
Abstract: Real-world decision-making in public health and social science can greatly benefit from predictive models, yet translating predictions into effective i...
By Mulin Tian, Ajitesh Srivastava
The paper introduces Pivot-and-Station Multi-Agent Path Finding (PS‑MAPF), a variant of MAPF where a subset of agents must visit interchangeable pivots before all agents occupy anonymous stations. It provides a full solvability characterization: every instance on a 2‑edge‑connected graph is solvable, and for arbitrary connected graphs a structural effective‑distance measure relative to unoccupied vertices gives a necessary and sufficient condition. The authors prove that minimizing station‑makespan or station‑flowtime is NP‑hard even with a single pivot, and present three algorithms—a complete baseline, a SAT‑based optimal solver, and Pivot‑Prioritized Planning (PPP), which solves 74‑89% of benchmark instances with significantly lower makespan and flowtime than the baseline.
By Andrea Di Nezza, Mihir Patel, Fabio Fagnani, Sara Bernardini
arXiv:2510.13394v4 Announce Type: replace
Abstract: Spatial reasoning ability is crucial for Vision Language Models (VLMs) to support real-world applications in diverse domains including robotics, au...
By Xinmiao Huang, Qisong He, Zhenglin Huang, Boxuan Wang, Zhuoyun Li, Guangliang Cheng, Yi Dong, Xiaowei Huang