Pith. sign in

REVIEW 7 cited by

Copilot4D: Learning Unsupervised World Models for Autonomous Driving via Discrete Diffusion

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 2311.01017 v4 pith:WNQIGGOE submitted 2023-11-02 cs.CV cs.AIcs.LGcs.RO

classification cs.CVcs.AIcs.LGcs.RO
keywords worldmodelsdiffusiondiscretelearningcopilot4dgenerativeunsupervised
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Learning world models can teach an agent how the world works in an unsupervised manner. Even though it can be viewed as a special case of sequence modeling, progress for scaling world models on robotic applications such as autonomous driving has been somewhat less rapid than scaling language models with Generative Pre-trained Transformers (GPT). We identify two reasons as major bottlenecks: dealing with complex and unstructured observation space, and having a scalable generative model. Consequently, we propose Copilot4D, a novel world modeling approach that first tokenizes sensor observations with VQVAE, then predicts the future via discrete diffusion. To efficiently decode and denoise tokens in parallel, we recast Masked Generative Image Transformer as discrete diffusion and enhance it with a few simple changes, resulting in notable improvement. When applied to learning world models on point cloud observations, Copilot4D reduces prior SOTA Chamfer distance by more than 65% for 1s prediction, and more than 50% for 3s prediction, across NuScenes, KITTI Odometry, and Argoverse2 datasets. Our results demonstrate that discrete diffusion on tokenized agent experience can unlock the power of GPT-like unsupervised learning for robotics.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 7 Pith papers

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

  1. NeSy-Route: A Neuro-Symbolic Benchmark for Constrained Route Planning in Remote Sensing

    cs.AI 2026-03 reject novelty 6.5 of 10

    NeSy-Route supplies 10,821 optimally labeled remote-sensing route-planning tasks plus a three-level neuro-symbolic protocol that reveals major perception and planning deficits in current MLLMs.

  2. AutoWorld: Learning Multi-Agent Traffic Simulation with Self-Supervised World Models

    cs.RO 2026-03 conditional novelty 6.0 of 10

    AutoWorld learns a self-supervised LiDAR occupancy world model and conditions a diffusion-based motion generator on its forecasts, reporting the top Waymo Sim Agents realism score.

  3. Genesis: Multimodal Driving Scene Generation with Spatio-Temporal and Cross-Modal Consistency

    cs.CV 2025-06 conditional novelty 6.0 of 10

    A joint video and LiDAR generation framework for driving scenes, conditioned on shared scene layouts, VLM captions, and BEV features, achieves SOTA generation and downstream perception gains on nuScenes.

  4. Quo Vadis, World Modeling?

    cs.CV 2026-08 conditional novelty 5.0 of 10

    An agent-centric reframing of world modeling, replacing physical state prediction with 'information transitions' organized into six proxy functions and three empowerment levels.

  5. UniDrive-WM: Unified Understanding, Planning and Generation World Model for Autonomous Driving

    cs.CV 2026-01 conditional novelty 5.0 of 10

    A unified VLM for autonomous driving that couples trajectory planning with future-frame image generation improves open- and closed-loop planning metrics on Bench2Drive and nuScenes.

  6. Diffusion-Based Generative Models for 3D Occupancy Prediction in Autonomous Driving

    cs.CV 2025-05 conditional novelty 5.0 of 10

    Diffusion-based generative models, using discrete categorical diffusion conditioned on BEV features, improve 3D occupancy prediction and downstream planning for autonomous driving.

  7. Reinforcement Learning: From Algorithms To Foundation Models

    cs.AI 2026-07 conditional novelty 3.0 of 10

    A dissertation uniting the author's published results: non-exploitable Nash-DQN policies and the FightLadder benchmark for games, plus diffusion/consistency-model world models for RL — a compilation rather than new results.

Pith tools