DisCo: World Models with Discrete Camera Motion Control

• URL: http://arxiv.org/abs/2606.07967v1
• Date: Sat, 06 Jun 2026 03:50:45 GMT
• Title: DisCo: World Models with Discrete Camera Motion Control
• Abstract summary: We propose DisCo, a controllable video world model that conditions generation on a compact set of discrete action primitives to improve action separability.<n>DisCo achieves significantly more reliable action following while preserving visual quality.
• Score: 79.86256515640231
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Controllable video world models target interactive world exploration, where models must faithfully execute explicit action commands while preserving visual quality and temporal coherence. However, most existing approaches rely on continuous camera trajectories as action conditions, which often lead to unreliable action following, especially under complex motion sequences. In this work, we identify action representation entanglement as a key bottleneck in controllable video generation, and show that continuous camera representations lead to high feature similarity across distinct motion patterns, degrading action controllability. Based on this insight, we propose DisCo, a controllable video world model that conditions generation on a compact set of discrete action primitives to improve action separability. We further introduce DisCoBench, a comprehensive benchmark for evaluating the ability of models in short-term, long-horizon, and highly dynamic exploration scenarios. Extensive experiments demonstrate that DisCo achieves significantly more reliable action following while preserving visual quality.

Related papers

• WorldExam: Benchmarking World Models from Apparent Appearance to Inherent Reactivity [75.96851880065331]
  We introduce WorldExam, a diagnostic benchmark spanning four levels: Visual Quality, Control Adherence, Spatial Consistency, and World Reactivity.<n>It comprises 1,474 cases across eight dedicated tasks and supports unified evaluation of camera-, action-, and language-driven model paradigms.<n> Evaluation of 20 representative models reveals a clear capability split. Camera-driven models excel at camera control, but their interfaces do not support dynamic interaction.
  arXiv  Detail & Related papers  (2026-08-03T17:59:54Z)
• ABot-M0.5: Unified Mobility-and-Manipulation World Action Model [27.262271208923995]
  ABot-M0.5 is built on the insight that mobile manipulation requires alignment at three levels: temporal granularity, action space, and train-test consistency.<n> Experiments on challenging mobile and fine-grained manipulation benchmarks demonstrate that ABot-M0.5 achieves state-of-the-art performance in both long-horizon task success and finegrained control accuracy.
  arXiv  Detail & Related papers  (2026-07-01T09:21:20Z)
• Directing the World: Fast Autoregressive Video Generation with Compositional Human-Camera Control [56.828569670698975]
  "Directing the World" is a fast autoregressive framework for controllable world-model video generation with compositional human-motion and camera-trajectory control.<n>Our key idea is to decouple control learning while preserving a unified autoregressive video prior.<n>For human motion control, we design a t-guided Dynamic Projection mechanism and a refined Motion-CFG strategy.
  arXiv  Detail & Related papers  (2026-06-26T11:08:09Z)
• ActionParty: Multi-Subject Action Binding in Generative Video Games [117.52562594944679]
  ActionParty is a controllable multi-subject world model for generative video games.<n>We demonstrate the first video world model capable of controlling up to seven players simultaneously across 46 diverse environments.
  arXiv  Detail & Related papers  (2026-04-02T17:59:58Z)
• Olaf-World: Orienting Latent Actions for Video World Modeling [100.96069208914957]
  Scaling action-controllable world models is limited by the scarcity of action labels.<n>We present Olaf-World, a pipeline that pretrains action-conditioned video world models from large-scale passive video.
  arXiv  Detail & Related papers  (2026-02-10T18:58:41Z)
• Astra: General Interactive World Model with Autoregressive Denoising [73.6594791733982]
  Astra is an interactive general world model that generates real-world futures for diverse scenarios.<n>We propose an autoregressive denoising architecture and use temporal causal attention to aggregate past observations.<n>Astra achieves interactive, consistent, and general long-term video prediction and supports various forms of interactions.
  arXiv  Detail & Related papers  (2025-12-09T18:59:57Z)
• Observe Then Act: Asynchronous Active Vision-Action Model for Robotic Manipulation [19.17977467107072]
  Our model serially connects a camera Next-Best-View (NBV) policy with a gripper Next-Best Pose (NBP) policy, and trains them in a sensor-motor coordination framework using few-shot reinforcement learning.<n>This approach allows the agent to adjust a third-person camera to actively observe the environment based on the task goal, and subsequently infer the appropriate manipulation actions.<n>The results demonstrate that our model consistently outperforms baseline algorithms, showcasing its effectiveness in handling visual constraints in manipulation tasks.
  arXiv  Detail & Related papers  (2024-09-23T10:38:20Z)
• TrackDiffusion: Tracklet-Conditioned Video Generation via Diffusion Models [75.20168902300166]
  We propose TrackDiffusion, a novel video generation framework affording fine-grained trajectory-conditioned motion control. A pivotal component of TrackDiffusion is the instance enhancer, which explicitly ensures inter-frame consistency of multiple objects. generated video sequences by our TrackDiffusion can be used as training data for visual perception models.
  arXiv  Detail & Related papers  (2023-12-01T15:24:38Z)

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.