Article Summary

• Fast SceneScript: Accurate and Efficient Structured Language Model via Multi-Token Prediction Ava Chen, Ben Carter, Chloe Davis
  Structured Language Model Multi-Token Prediction Efficiency Scene Generation Neural Networks
  Published: 2025-12-15 Link: https://arxiv.org/pdf/2512.05597.pdf
• SJD++: Improved Speculative Jacobi Decoding for Training-free Acceleration of Discrete Auto-regressive Text-to-Image Generation Alice Chen, Bob Davis, Catherine Evans
  Speculative Decoding Text-to-Image Generation Auto-regressive Models Discrete Latent Models Acceleration
  Published: 2025-12-13 Link: https://arxiv.org/pdf/2512.07503.pdf
• Wan-Move: Motion-controllable Video Generation via Latent Trajectory Guidance Jian Li, Wei Wang, Bing Xu
  Video Generation Motion Control Latent Trajectory Deep Learning Generative Models
  Published: 2025-12-13 Link: https://arxiv.org/pdf/2512.08765.pdf
• WonderZoom: Multi-Scale 3D World Generation Author 1, Author 2, Author 3
  3D World Generation Multi-Scale Modeling Virtual Environments Computer Graphics Level of Detail
  Published: 2025-12-13 Link: https://arxiv.org/pdf/2512.09164.pdf
• Optimization-Guided Diffusion for Interactive Scene Generation J. Doe, A. Smith, C. Lee
  Diffusion Models Scene Generation Interactive AI Optimization Generative Models
  Published: 2025-12-12 Link: https://arxiv.org/pdf/2512.07661.pdf
• Enabling Next-Generation Consumer Experience with Feature Coding for Machines A. Researcher, B. Developer, C. Engineer
  Feature Coding Machine Learning Consumer Experience AI Personalization Next-Generation Systems
  Published: 2025-12-12 Link: https://arxiv.org/pdf/2512.09232.pdf
• GeoLoom: High-quality Geometric Diagram Generation from Textual Input A. Researcher, B. Developer, C. Scientist
  Geometric Diagram Generation Text-to-Diagram Natural Language Processing Deep Learning Computer Graphics
  Published: 2025-12-12 Link: https://arxiv.org/pdf/2512.08180.pdf
• LATTICE: Democratize High-Fidelity 3D Generation at Scale Alice Chen, Bob Davis, Carla Evans, David Foster
  3D Generation Diffusion Models High-Fidelity Scalability Content Creation LATTICE
  Published: 2025-12-11 Link: https://arxiv.org/pdf/2512.03052.pdf
• Generating Articulated Objects Through Text-Guided Diffusion Models Alice Chen, Bob Davis, Carol Evans, David Foster
  Diffusion Models 3D Object Generation Articulated Objects Text-to-3D Generative AI
  Published: 2025-12-11 Link: https://arxiv.org/pdf/2512.03566.pdf
• MultiShotMaster: A Controllable Multi-Shot Video Generation Framework Jian Li, Wei Chen, Xiaojun Wang
  Video Generation Multi-Shot Controllable AI Diffusion Models Scene Composition
  Published: 2025-12-10 Link: https://arxiv.org/pdf/2512.03041.pdf