CLaD: Planning with Grounded Foresight via Cross-Modal Latent Dynamics

• URL: http://arxiv.org/abs/2603.29409v1
• Date: Tue, 31 Mar 2026 08:13:45 GMT
• Title: CLaD: Planning with Grounded Foresight via Cross-Modal Latent Dynamics
• Abstract summary: We propose CLaD, a framework that models how proprioceptive and semantic states jointly evolve under actions.<n>CLaD predicts grounded latent foresights via self-supervised objectives with EMA target encoders and auxiliary reconstruction losses.<n>On LIBERO-LONG benchmark, CLaD achieves 94.7% success rate, competitive with large VLAs with significantly fewer parameters.
• Score: 25.518388341069492
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Robotic manipulation involves kinematic and semantic transitions that are inherently coupled via underlying actions. However, existing approaches plan within either semantic or latent space without explicitly aligning these cross-modal transitions. To address this, we propose CLaD, a framework that models how proprioceptive and semantic states jointly evolve under actions through asymmetric cross-attention that allows kinematic transitions to query semantic ones. CLaD predicts grounded latent foresights via self-supervised objectives with EMA target encoders and auxiliary reconstruction losses, preventing representation collapse while anchoring predictions to observable states. Predicted foresights are modulated with observations to condition a diffusion policy for action generation. On LIBERO-LONG benchmark, CLaD achieves 94.7\% success rate, competitive with large VLAs with significantly fewer parameters.

Related papers

• CST-WM: A Causally Structured World Model for Embodied Visual Tracking [9.902564083063973]
  Embodied visual tracking requires a robot to choose actions that preserve or recover future evidence of a moving target.<n>CST-WM decomposes the latent state into target-evidence, robot, and observation branches.<n>It supports both stable following and temporary target re-acquisition in one planning framework.
  arXiv  Detail & Related papers  (2026-09-05T23:24:32Z)
• SLIM-0.5B: Learning Action-Grounded Predictive Latents for Robot Manipulation [35.54319311306262]
  We present SLIM, a compact latent interaction policy.<n>It learns representations through self-supervised masked trajectory prediction.<n>SLIM matches or exceeds representative large-scale VLA and world-action-model baselines with fewer parameters.
  arXiv  Detail & Related papers  (2026-08-10T15:58:39Z)
• DLAM: Distributional Latent Actions with Temporal Constraints [25.743937994244902]
  We introduce DLAM, a distributional latent-action model that represents each transition as a diagonal Gaussian.<n>For downstream policy learning, we freeze the encoder and train a flow-matching policy to jointly generate mean transition sequences and robot actions.<n>On held-out transitions, DLAM learns more temporally consistent latent dynamics than existing latent-action baselines and achieves stronger direct and cumulative reconstruction on held-out videos.
  arXiv  Detail & Related papers  (2026-07-29T17:09:48Z)
• SegDiff: Segmented Trajectory Diffusion for Consistent and Adaptive Robot Manipulation [65.81476183180527]
  We introduce SegDiff, a closed-loop visuomotor policy that integrates the strengths of both paradigms.<n>SegDiff decomposes demonstrations into motion segments between keyposes and learns to predict the continuous trajectory from the current state to the next keypose.<n>SegDiff demonstrates significant performance gains over existing approaches across various simulated and real-world scenarios.
  arXiv  Detail & Related papers  (2026-07-13T02:48:03Z)
• DeSeG: Decoupling Semantic Intent and Geometric Constraints for Physically Plausible Human-Scene Interaction [50.06148080975928]
  We propose DeSeG, a hierarchical framework that explicitly decouples semantic intent from geometric constraints.<n>DeSeG achieves state-of-the-art performance, reducing mean scene penetration by 47% and improving semantic alignment by 29% over the SOTA baselines.
  arXiv  Detail & Related papers  (2026-07-07T03:21:08Z)
• Pondering the Way: Spatial-perceiving World Action Model for Embodied Navigation [24.310993695214094]
  We propose SWAM (Spatial-perceiving World Action Model), a task-centric joint observation-action generation framework.<n>Given start and goal RGB observations, SWAM performs single-pass inference to simultaneously generate intermediate RGB-D sequences and corresponding action trajectories.<n>We show that SWAM significantly outperforms state-of-the-art two-stage planners in success rate, trajectory accuracy, and inference efficiency.
  arXiv  Detail & Related papers  (2026-06-29T07:43:47Z)
• From Imagined Futures to Executable Actions: Mixture of Latent Actions for Robot Manipulation [88.39072412680633]
  We propose MoLA, a control-oriented interface that transforms imagined future videos into executable representations.<n>We evaluate our approach on simulated benchmarks and real-world robot manipulation tasks.
  arXiv  Detail & Related papers  (2026-05-12T14:15:16Z)
• FutureVLA: Joint Visuomotor Prediction for Vision-Language-Action Model [73.03346643967309]
  We argue that effective joint visuomotor predictive modeling requires both temporal continuity and visually-conditioned supervision decoupling.<n>FutureVLA is designed to extract joint visuomotor embeddings by first decoupling visual and motor information.<n>In the post-training stage, we employ a latent embeddings alignment strategy, enabling diverse downstream VLA models to internalize these temporal priors.
  arXiv  Detail & Related papers  (2026-03-11T12:39:55Z)
• SGHA-Attack: Semantic-Guided Hierarchical Alignment for Transferable Targeted Attacks on Vision-Language Models [73.19044613922911]
  Large vision-language models (VLMs) are vulnerable to transfer-based adversarial perturbations.<n>We propose SGHA-Attack, a framework that adopts multiple target references and enforces intermediate-layer consistency.<n>Experiments on open-source and commercial black-box VLMs show that SGHA-Attack achieves stronger targeted transferability than prior methods.
  arXiv  Detail & Related papers  (2026-02-02T03:10:41Z)
• \textsc{NaVIDA}: Vision-Language Navigation with Inverse Dynamics Augmentation [50.027425808733994]
  textscNaVIDA is a unified VLN framework that couples policy learning with action-grounded visual dynamics and adaptive execution.<n>textscNaVIDA augments training with chunk-based inverse-dynamics supervision to learn causal relationship between visual changes and corresponding actions.<n>Experiments show that textscNaVIDA achieves superior navigation performance compared to state-of-the-art methods with fewer parameters.
  arXiv  Detail & Related papers  (2026-01-26T06:16:17Z)
• Intention-Aware Diffusion Model for Pedestrian Trajectory Prediction [15.151965172049271]
  We propose a diffusion-based pedestrian trajectory prediction framework that incorporates both short-term and long-term motion intentions.<n>The proposed framework is evaluated on the widely used ETH, UCY, and SDD benchmarks, demonstrating competitive results against state-of-the-art methods.
  arXiv  Detail & Related papers  (2025-08-10T02:36:33Z)
• Trajectory Mamba: Efficient Attention-Mamba Forecasting Model Based on Selective SSM [16.532357621144342]
  This paper introduces Trajectory Mamba, a novel efficient trajectory prediction framework based on the selective state-space model (SSM)<n>To address the potential reduction in prediction accuracy resulting from modifications to the attention mechanism, we propose a joint polyline encoding strategy.<n>Our model achieves state-of-the-art results in terms of inference speed and parameter efficiency on both the Argoverse 1 and Argoverse 2 datasets.
  arXiv  Detail & Related papers  (2025-03-13T21:31:12Z)
• HybridVLA: Collaborative Diffusion and Autoregression in a Unified Vision-Language-Action Model [54.64088247291416]
  A fundamental objective of manipulation policy design is to endow robots to comprehend human instructions, reason about scene cues, and execute generalized actions in dynamic environments.<n>Recent autoregressive vision-language-action (VLA) methods inherit common-sense reasoning capabilities from vision-language models (VLMs) for next action-token prediction.<n>We introduce HybridVLA, a unified framework that absorbs the continuous nature of diffusion-based actions and the contextual reasoning of autoregression.
  arXiv  Detail & Related papers  (2025-03-13T17:59:52Z)
• Learning Semantic Latent Directions for Accurate and Controllable Human Motion Prediction [25.965711897002016]
  We introduce Semantic Latent Directions (SLD) as a solution to this challenge. SLD constrains the latent space to learn meaningful motion semantics. We showcase the superiority of our method in accurately predicting motions while maintaining a balance of realism and diversity.
  arXiv  Detail & Related papers  (2024-07-16T08:31:59Z)
• DESTINE: Dynamic Goal Queries with Temporal Transductive Alignment for Trajectory Prediction [8.25651323214656]
  We propose Dynamic goal quErieS with temporal Transductive alIgNmEnt (DESTINE) method. We show that our method achieves state-of-the-art performance on various metrics.
  arXiv  Detail & Related papers  (2023-10-11T12:41:32Z)
• Motion-Scenario Decoupling for Rat-Aware Video Position Prediction: Strategy and Benchmark [49.58762201363483]
  We introduce RatPose, a bio-robot motion prediction dataset constructed by considering the influence factors of individuals and environments. We propose a Dual-stream Motion-Scenario Decoupling framework that effectively separates scenario-oriented and motion-oriented features. We demonstrate significant performance improvements of the proposed textitDMSD framework on different difficulty-level tasks.
  arXiv  Detail & Related papers  (2023-05-17T14:14:31Z)
• SGCN:Sparse Graph Convolution Network for Pedestrian Trajectory Prediction [64.16212996247943]
  We present a Sparse Graph Convolution Network(SGCN) for pedestrian trajectory prediction. Specifically, the SGCN explicitly models the sparse directed interaction with a sparse directed spatial graph to capture adaptive interaction pedestrians. visualizations indicate that our method can capture adaptive interactions between pedestrians and their effective motion tendencies.
  arXiv  Detail & Related papers  (2021-04-04T03:17:42Z)

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.