Multiverse: Language-Conditioned Multi-Game Level Blending via Shared Representation

• URL: http://arxiv.org/abs/2603.26782v2
• Date: Tue, 31 Mar 2026 04:21:21 GMT
• Title: Multiverse: Language-Conditioned Multi-Game Level Blending via Shared Representation
• Abstract summary: We propose a language-conditioned multi-game level generator that enables cross-game level blending through textual specifications.<n>Experiments show that the learned representation supports controllable cross-game level blending and significantly improves blending quality within the same game genre.
• Score: 3.29640587147404
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Text-to-level generation aims to translate natural language descriptions into structured game levels, enabling intuitive control over procedural content generation. While prior text-to-level generators are typically limited to a single game domain, extending language-conditioned generation to multiple games requires learning representations that capture structural relationships across domains. We propose Multiverse, a language-conditioned multi-game level generator that enables cross-game level blending through textual specifications. The model learns a shared latent space aligning textual instructions and level structures, while a threshold-based multi-positive contrastive supervision links semantically related levels across games. This representation allows language to guide which structural characteristics should be preserved when combining content from different games, enabling controllable blending through latent interpolation and zero-shot generation from compositional textual prompts. Experiments show that the learned representation supports controllable cross-game level blending and significantly improves blending quality within the same game genre, while providing a unified representation for language-conditioned multi-game content generation.

Related papers

• UniTranslator: A Unified Multi-modal Framework for End-to-end In-Image Machine Translation [23.787128107000374]
  In-Image Machine Translation (IIMT) aims to translate scene text in an image and render the translated text back into the original regions while preserving the overall visual appearance.<n>Recent unified multimodal models provide a promising solution by combining visual-text understanding and image generation within a single framework.<n>We present UniTranslator, a unified multimodal framework for IIMT that tightly couples translation understanding and text editing.
  arXiv  Detail & Related papers  (2026-06-23T09:11:24Z)
• TextLDM: Language Modeling with Continuous Latent Diffusion [89.69255520673248]
  Diffusion Transformers (DiT) trained with flow matching in a VAE latent space have unified visual generation across images and videos.<n>We propose TextLDM, which transfers the visual latent diffusion recipe to text generation with minimal architectural modification.
  arXiv  Detail & Related papers  (2026-05-08T13:54:34Z)
• Language-Grounded Multi-Domain Image Translation via Semantic Difference Guidance [15.370194308451495]
  Multi-domain image-to-image translation re quires grounding semantic differences ex pressed in natural language prompts into corresponding visual transformations.<n>We propose LACE (Language-grounded Attribute Controllable Translation), built on two compo nents.<n>Experiments on CelebA(Dialog) and BDD100K demonstrate that LACE achieves high visual fidelity, structural preservation, and interpretable domain-specific control.
  arXiv  Detail & Related papers  (2026-01-12T05:36:15Z)
• ConsistCompose: Unified Multimodal Layout Control for Image Composition [56.909072845166264]
  We present ConsistCompose, a unified framework that embeds layout coordinates directly into language prompts.<n>We show that ConsistCompose substantially improves spatial accuracy over layout-controlled baselines.
  arXiv  Detail & Related papers  (2025-11-23T08:14:53Z)
• Joint Level Generation and Translation Using Gameplay Videos [0.9645196221785693]
  Procedural Content Generation via Machine Learning (PCGML) faces a significant hurdle that sets it apart from other fields, such as image or text generation. Many existing methods for procedural level generation via machine learning require a secondary representation besides level images. We develop a novel multi-tail framework that learns to perform simultaneous level translation and generation.
  arXiv  Detail & Related papers  (2023-06-29T03:46:44Z)
• MGDoc: Pre-training with Multi-granular Hierarchy for Document Image Understanding [53.03978356918377]
  spatial hierarchical relationships between content at different levels of granularity are crucial for document image understanding tasks. Existing methods learn features from either word-level or region-level but fail to consider both simultaneously. We propose MGDoc, a new multi-modal multi-granular pre-training framework that encodes page-level, region-level, and word-level information at the same time.
  arXiv  Detail & Related papers  (2022-11-27T22:47:37Z)
• Unsupervised Image-to-Image Translation with Generative Prior [103.54337984566877]
  Unsupervised image-to-image translation aims to learn the translation between two visual domains without paired data. We present a novel framework, Generative Prior-guided UN Image-to-image Translation (GP-UNIT), to improve the overall quality and applicability of the translation algorithm.
  arXiv  Detail & Related papers  (2022-04-07T17:59:23Z)
• Integrating Visuospatial, Linguistic and Commonsense Structure into Story Visualization [81.26077816854449]
  We first explore the use of constituency parse trees for encoding structured input. Second, we augment the structured input with commonsense information and study the impact of this external knowledge on the generation of visual story. Third, we incorporate visual structure via bounding boxes and dense captioning to provide feedback about the characters/objects in generated images.
  arXiv  Detail & Related papers  (2021-10-21T00:16:02Z)
• VECO: Variable and Flexible Cross-lingual Pre-training for Language Understanding and Generation [77.82373082024934]
  We plug a cross-attention module into the Transformer encoder to explicitly build the interdependence between languages. It can effectively avoid the degeneration of predicting masked words only conditioned on the context in its own language. The proposed cross-lingual model delivers new state-of-the-art results on various cross-lingual understanding tasks of the XTREME benchmark.
  arXiv  Detail & Related papers  (2020-10-30T03:41:38Z)
• Video Game Level Repair via Mixed Integer Linear Programming [20.815591392882716]
  The proposed framework constructs levels using a generative adversarial network (GAN) trained with human-authored examples and repairs them using a mixed-integer linear program (MIP) with playability constraints. Results show that the proposed framework generates a diverse range of playable levels, that capture the spatial relationships between objects exhibited in the human-authored levels.
  arXiv  Detail & Related papers  (2020-10-13T18:37:58Z)
• Interactive Fiction Game Playing as Multi-Paragraph Reading Comprehension with Reinforcement Learning [94.50608198582636]
  Interactive Fiction (IF) games with real human-written natural language texts provide a new natural evaluation for language understanding techniques. We take a novel perspective of IF game solving and re-formulate it as Multi-Passage Reading (MPRC) tasks.
  arXiv  Detail & Related papers  (2020-10-05T23:09:20Z)

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.