Seeing Space and Motion: Enhancing Latent Actions with Spatial and Dynamic Awareness for VLA
- URL: http://arxiv.org/abs/2509.26251v1
- Date: Tue, 30 Sep 2025 13:41:43 GMT
- Title: Seeing Space and Motion: Enhancing Latent Actions with Spatial and Dynamic Awareness for VLA
- Authors: Zhejia Cai, Yandan Yang, Xinyuan Chang, Shiyi Liang, Ronghan Chen, Feng Xiong, Mu Xu, Ruqi Huang,
- Abstract summary: Latent Action Models (LAMs) enable Vision- Language-Action systems to learn semantic action rep- resentations from large-scale unannotated data.<n>We propose Farsighted-LAM, a latent action framework with geometry- aware spatial encoding and multi-scale temporal modeling.<n>We further propose SSM-VLA, an end- to-end VLA framework built upon Farsighted-LAM, which integrates structured perception with a visual Chain-of-Thought module.
- Score: 21.362682837521632
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Latent Action Models (LAMs) enable Vision- Language-Action (VLA) systems to learn semantic action rep- resentations from large-scale unannotated data. Yet, we identify two bottlenecks of LAMs: 1) the commonly adopted end-to-end trained image encoder suffers from poor spatial understanding; 2) LAMs can be fragile when input frames are distant, leading to limited temporal perception. Such factors inevitably hinder stable and clear action modeling. To this end, we propose Farsighted-LAM, a latent action framework with geometry- aware spatial encoding and multi-scale temporal modeling, capturing structural priors and dynamic motion patterns from consecutive frames. We further propose SSM-VLA, an end- to-end VLA framework built upon Farsighted-LAM, which integrates structured perception with a visual Chain-of-Thought module to explicitly reason about environmental dynamics, enhancing decision consistency and interpretability. We validate SSM-VLA on multiple VLA tasks in both simulation and real- world settings, and achieve state-of-the-art performance. Our results demonstrate that our strategy of combining geometry- aware modeling, temporal coherence, and explicit reasoning is effective in enhancing the robustness and generalizability of embodied intelligence.
Related papers
- Chain of World: World Model Thinking in Latent Motion [24.24061036481793]
Vision-Language-Action (VLA) models often overlook the predictive and temporal-causal structure underlying visual dynamics.<n>We introduce CoWVLA, a new "Chain of World" paradigm that unifies world-model temporal reasoning with a disentangled latent motion representation.<n>CoWVLA outperforms existing world-model and latent-action approaches and achieves moderate computational efficiency.
arXiv Detail & Related papers (2026-03-03T17:52:06Z) - Dream-SLAM: Dreaming the Unseen for Active SLAM in Dynamic Environments [62.70468717776612]
We propose a novel monocular active SLAM method, Dream-SLAM.<n>It is based on dreaming cross-spatio-temporal images and semantically plausible structures of partially observed dynamic environments.<n>Experiments on both public and self-collected datasets demonstrate that Dream-SLAM outperforms state-of-the-art methods in localization accuracy, mapping quality, and exploration efficiency.
arXiv Detail & Related papers (2026-02-25T14:48:49Z) - From Perception to Action: An Interactive Benchmark for Vision Reasoning [51.11355591375073]
Causal Hierarchy of Actions and Interactions (CHAIN) benchmark designed to evaluate whether models can understand, plan, and execute structured action sequences grounded in physical constraints.<n> CHAIN shifts evaluation from passive perception to active problem solving, spanning tasks such as interlocking mechanical puzzles and 3D stacking and packing.<n>Our results show that top-performing models still struggle to internalize physical structure and causal constraints, often failing to produce reliable long-horizon plans and cannot robustly translate perceived structure into effective actions.
arXiv Detail & Related papers (2026-02-24T15:33:02Z) - PosA-VLA: Enhancing Action Generation via Pose-Conditioned Anchor Attention [92.85371254435074]
PosA-VLA framework anchors visual attention via pose-conditioned supervision, consistently guiding the model's perception toward task-relevant regions.<n>We show that our method executes embodied tasks with precise and time-efficient behavior across diverse robotic manipulation benchmarks.
arXiv Detail & Related papers (2025-12-03T12:14:29Z) - Bridge Thinking and Acting: Unleashing Physical Potential of VLM with Generalizable Action Expert [60.88976842557026]
Vision-Language Models (VLM) have demonstrated impressive planning and reasoning capabilities.<n>Recent dual-system approaches attempt to decouple "thinking" from "acting"<n>We introduce a framework centered around a generalizable action expert.
arXiv Detail & Related papers (2025-10-04T18:33:27Z) - SAMPO:Scale-wise Autoregression with Motion PrOmpt for generative world models [42.814012901180774]
textbfSAMPO is a hybrid framework that combines visual autoregressive modeling for intra-frame generation with causal modeling for next-frame generation.<n>We show that SAMPO achieves competitive performance in action-conditioned video prediction and model-based control.<n>We also evaluate SAMPO's zero-shot generalization and scaling behavior, demonstrating its ability to generalize to unseen tasks.
arXiv Detail & Related papers (2025-09-19T02:41:37Z) - VLM4D: Towards Spatiotemporal Awareness in Vision Language Models [66.833085504228]
We introduce V4DLM, the first benchmark specifically designed to evaluate visual language models (VLMs)<n>Our benchmark comprises diverse real-world and synthetic videos accompanied by carefully curated question-answer pairs.<n>We identify significant performance gaps compared to human baselines, highlighting fundamental deficiencies in existing models.
arXiv Detail & Related papers (2025-08-04T06:06:06Z) - DreamVLA: A Vision-Language-Action Model Dreamed with Comprehensive World Knowledge [41.030494146004806]
We propose DreamVLA, a novel VLA framework that integrates comprehensive world knowledge forecasting to enable inverse dynamics modeling.<n>DreamVLA introduces a dynamic-region-guided world knowledge prediction, integrated with the spatial and semantic cues, which provide compact yet comprehensive representations for action planning.<n>Experiments on both real-world and simulation environments demonstrate that DreamVLA achieves 76.7% success rate on real robot tasks.
arXiv Detail & Related papers (2025-07-06T16:14:29Z) - SP-VLA: A Joint Model Scheduling and Token Pruning Approach for VLA Model Acceleration [69.54069477520534]
Vision-Language-Action (VLA) models have attracted increasing attention for their strong control capabilities.<n>Their high computational cost and low execution frequency hinder their suitability for real-time tasks such as robotic manipulation and autonomous navigation.<n>We propose SP-VLA, a unified framework that accelerates VLA models by jointly scheduling models and pruning tokens.
arXiv Detail & Related papers (2025-06-15T05:04:17Z) - EmbodiedVSR: Dynamic Scene Graph-Guided Chain-of-Thought Reasoning for Visual Spatial Tasks [24.41705039390567]
EmbodiedVSR (Embodied Visual Spatial Reasoning) is a novel framework that integrates dynamic scene graph-guided Chain-of-Thought (CoT) reasoning.<n>Our method enables zero-shot spatial reasoning without task-specific fine-tuning.<n>Experiments demonstrate that our framework significantly outperforms existing MLLM-based methods in accuracy and reasoning coherence.
arXiv Detail & Related papers (2025-03-14T05:06:07Z) - Efficient High-Resolution Visual Representation Learning with State Space Model for Human Pose Estimation [60.80423207808076]
Capturing long-range dependencies while preserving high-resolution visual representations is crucial for dense prediction tasks such as human pose estimation.<n>We propose the Dynamic Visual State Space (DVSS) block, which augments visual state space models with multi-scale convolutional operations.<n>We build HRVMamba, a novel model for efficient high-resolution representation learning.
arXiv Detail & Related papers (2024-10-04T06:19:29Z)
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.