Pith. sign in

REVIEW 12 cited by

LaDi-WM: A Latent Diffusion-based World Model for Predictive Manipulation

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2505.11528 v6 pith:3CJDADMC submitted 2025-05-13 cs.RO cs.AIcs.LG

classification cs.ROcs.AIcs.LG
keywords ladi-wmlatentstatesworldmodelpolicyreal-worldspace
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Predictive manipulation has recently gained considerable attention in the Embodied AI community due to its potential to improve robot policy performance by leveraging predicted states. However, generating accurate future visual states of robot-object interactions from world models remains a well-known challenge, particularly in achieving high-quality pixel-level representations. To this end, we propose LaDi-WM, a world model that predicts the latent space of future states using diffusion modeling. Specifically, LaDi-WM leverages the well-established latent space aligned with pre-trained Visual Foundation Models (VFMs), which comprises both geometric features (DINO-based) and semantic features (CLIP-based). We find that predicting the evolution of the latent space is easier to learn and more generalizable than directly predicting pixel-level images. Building on LaDi-WM, we design a diffusion policy that iteratively refines output actions by incorporating forecasted states, thereby generating more consistent and accurate results. Extensive experiments on both synthetic and real-world benchmarks demonstrate that LaDi-WM significantly enhances policy performance by 27.9\% on the LIBERO-LONG benchmark and 20\% on the real-world scenario. Furthermore, our world model and policies achieve impressive generalizability in real-world experiments.

Discussion (0). Sign in to comment.

Forward citations

Cited by 12 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. CF-VLA: Efficient Coarse-to-Fine Action Generation for Vision-Language-Action Policies

    cs.CV 2026-04 unverdicted novelty 7.0 of 10

    CF-VLA uses a coarse initialization over endpoint velocity followed by single-step refinement to achieve strong performance with low inference steps on CALVIN, LIBERO, and real-robot tasks.

  2. DREAMSTEER: Latent World Models Can Steer VLA Policies During Deployment Without Any Finetuning

    cs.RO 2026-07 conditional novelty 6.0 of 10

    A frozen VLA plus latent world-model rollouts and a value model can raise real-robot OOD manipulation success from 23.75% to 66.25% without any target-environment finetuning.

  3. Attacking the Trusted Imagination: Oracle-Level Integrity Attacks on Imagine-then-Act World Models

    cs.LG 2026-06 unverdicted novelty 6.0 of 10

    Attacks can corrupt the latent future trajectory imagined by world-action models in VLA policies, causing failures in oracles like MPC while the reactive policy stays intact.

  4. Human Cognition in Machines: A Unified Perspective of World Models

    cs.RO 2026-04 unverdicted novelty 6.0 of 10

    The paper introduces a unified framework for world models that fully incorporates all cognitive functions from Cognitive Architecture Theory, highlights under-researched areas in motivation and meta-cognition, and pro...

  5. LDA-1B: Scaling Latent Dynamics Action Model via Universal Embodied Data Ingestion

    cs.RO 2026-02 conditional novelty 6.0 of 10

    A 1B-parameter robot policy co-trained as a latent dynamics model on 30k+ hours of heterogeneous embodied data outperforms behavior-cloning baselines and uses low-quality data that hurts them.

  6. AstraNav-World: World Model for Foresight Control and Consistency

    cs.CV 2025-12 unverdicted novelty 6.0 of 10

    AstraNav-World unifies diffusion video generation and vision-language action planning in a single bidirectional model that improves trajectory accuracy, success rates, and zero-shot real-world adaptation in embodied n...

  7. DreamVLA: A Vision-Language-Action Model Dreamed with Comprehensive World Knowledge

    cs.CV 2025-07 unverdicted novelty 6.0 of 10

    DreamVLA uses dynamic-region-guided world knowledge prediction, block-wise attention to disentangle information types, and a diffusion transformer for actions, reaching 76.7% success on real robot tasks and 4.44 avera...

  8. PhysRAG: Enhancing Physics-Awareness in Video Generation via Retrieval-Augmented Generation

    cs.CV 2026-06 unverdicted novelty 5.0 of 10

    PhysRAG curates 7K videos from WISA-80K, builds a physical video database, and injects knowledge via learnable queries into a diffusion model to reach SOTA visual quality and physical compliance on PhyGenBench and VBench.

  9. DynaMOMA: Instantaneous Prediction of Grasp Poses for Mobile Manipulation of Dynamic Objects

    cs.RO 2026-06 unverdicted novelty 5.0 of 10

    DynaMOMA uses an anchor-based diffusion predictor for temporally consistent grasp trajectories and feeds encoded features to an anticipation-guided whole-body RL policy, reporting strong simulation performance and rea...

  10. PAIWorld: A 3D-Consistent World Foundation Model for Robotic Manipulation

    cs.RO 2026-06 unverdicted novelty 5.0 of 10

    PAIWorld adds explicit geometric cross-view mechanisms and 3D distillation to DiT world models to achieve multi-view 3D consistency in robotic manipulation benchmarks.

  11. WALL-WM: Carving World Action Modeling at the Event Joints

    cs.RO 2026-06 unverdicted novelty 4.0 of 10

    WALL-WM introduces event-grounded Vision-Language-Action pretraining that uses semantic events as the atomic unit to address granularity mismatch in world action models and reports state-of-the-art generalization.

  12. StemVLA:An Open-Source Vision-Language-Action Model with Future 3D Spatial Geometry Knowledge and 4D Historical Representation

    cs.RO 2026-02 reject novelty 4.0 of 10

    StemVLA supervises a GPT-2-based VLA with predicted future 3D-geometry features (VGGT) and temporally aggregated history, reporting 86.0% on LIBERO-Long - but its CALVIN results and equations are placeholders.

Pith tools