Pith. sign in

REVIEW 8 cited by

MiLA: Multi-view Intensive-fidelity Long-term Video Generation World Model for Autonomous Driving

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 2503.15875 v1 pith:3OGDTXPJ submitted 2025-03-20 cs.CV

classification cs.CV
keywords milavideogenerationvideosautonomousdatadenoisingdriving
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

In recent years, data-driven techniques have greatly advanced autonomous driving systems, but the need for rare and diverse training data remains a challenge, requiring significant investment in equipment and labor. World models, which predict and generate future environmental states, offer a promising solution by synthesizing annotated video data for training. However, existing methods struggle to generate long, consistent videos without accumulating errors, especially in dynamic scenes. To address this, we propose MiLA, a novel framework for generating high-fidelity, long-duration videos up to one minute. MiLA utilizes a Coarse-to-Re(fine) approach to both stabilize video generation and correct distortion of dynamic objects. Additionally, we introduce a Temporal Progressive Denoising Scheduler and Joint Denoising and Correcting Flow modules to improve the quality of generated videos. Extensive experiments on the nuScenes dataset show that MiLA achieves state-of-the-art performance in video generation quality. For more information, visit the project website: https://github.com/xiaomi-mlab/mila.github.io.

Discussion (0). Sign in to comment.

Forward citations

Cited by 8 Pith papers

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

  1. Pondering the Way: Spatial-perceiving World Action Model for Embodied Navigation

    cs.RO 2026-06 unverdicted novelty 7.0 of 10

    SWAM jointly generates intermediate RGB-D sequences and action trajectories from monocular RGB start/goal observations for embodied navigation.

  2. OmniDrive: An LLM-Choreographed Multi-Agent World Model with Unified Latent Co-Compression for Multi-View Driving Video Generation

    cs.CV 2026-06 unverdicted novelty 7.0 of 10

    DRIVE-CHOREO uses three LLM agents to create a unified position-aware token sequence co-compressed with multi-view video, achieving SOTA BEV mAP of 21.6 and +2.4 NDS improvement on nuScenes.

  3. Video Generation Models as World Models: Efficient Paradigms, Architectures and Algorithms

    eess.IV 2026-03 unverdicted novelty 6.0 of 10

    Video generation models can function as world simulators if efficiency gaps in spatiotemporal modeling are bridged via organized paradigms, architectures, and algorithms.

  4. DriveLaW:Unifying Planning and Video Generation in a Latent Driving World

    cs.CV 2025-12 unverdicted novelty 6.0 of 10

    DriveLaW unifies video world modeling and trajectory planning by injecting video-generator latents into a diffusion planner, achieving SOTA video prediction and a new record on the NAVSIM planning benchmark.

  5. A Comprehensive Survey on World Models for Embodied AI

    cs.CV 2025-10 conditional novelty 6.0 of 10

    A unified three-axis taxonomy — functionality, temporal modeling, spatial representation — organizes the world-model literature for embodied AI.

  6. UNIVERSE: Unified Video Action Models for Autonomous Driving with Flexible Mask-Modulated Modality Generation

    cs.CV 2026-07 conditional novelty 5.0 of 10

    A single mask-modulated DiT that co-trains future video and trajectories yields stronger autonomous-driving action generalization and 4.3× faster trajectory-only inference than dual-DiT designs.

  7. ReWorld: Learning Better Representations for World Action Models

    cs.CV 2026-06 unverdicted novelty 5.0 of 10

    ReWorld applies future-predictive, cross-modal, and hard-negative supervision directly to intermediate representations in Video and Action DiTs for WAMs, reporting 23.9% FVD improvement and PDMS rise from 89.1 to 90.4...

  8. Video Generation Models as World Models: Efficient Paradigms, Architectures and Algorithms

    eess.IV 2026-03 conditional novelty 5.0 of 10

    In twisted bilayer nodal d-wave superconductors, interlayer hopping creates nodes on the C2 axis and Bogoliubov flat bands when the single-layer Berry connection is parallel to that axis.

Pith tools