Context Unrolling in Omni Models

• URL: http://arxiv.org/abs/2604.21921v1
• Date: Thu, 23 Apr 2026 17:58:38 GMT
• Title: Context Unrolling in Omni Models
• Abstract summary: We present Omni, a unified multimodal model trained on diverse modalities, including text, images, videos, 3D geometry, and hidden representations.<n>We find that such training enables Context Unrolling, where the model explicitly reasons across multiple modal representations before producing predictions.
• Score: 74.990971105583
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We present Omni, a unified multimodal model natively trained on diverse modalities, including text, images, videos, 3D geometry, and hidden representations. We find that such training enables Context Unrolling, where the model explicitly reasons across multiple modal representations before producing predictions. This process enables the model to aggregate complementary information across heterogeneous modalities, facilitating a more faithful approximation of the shared multimodal knowledge manifold and improving downstream reasoning fidelity. As a result, Omni achieves strong performance on both multimodal generation and understanding benchmarks, while demonstrating advanced multimodal reasoning capabilities, including in-context generation of text, image, video, and 3D geometry.

Related papers

• Toward Native Multimodal Modeling: A Roadmap [73.2994129763275]
  Multimodal modeling represents a vital step from modality-agnostic reasoning toward world modeling.<n>Recent efforts have shifted the paradigm toward native multimodal modeling.<n>Despite its potential, the design space of native architectures remains insufficiently defined.
  arXiv  Detail & Related papers  (2026-05-25T01:57:43Z)
• ProM3E: Probabilistic Masked MultiModal Embedding Model for Ecology [19.17623860216468]
  ProM3E is a masked multimodal embedding model for any-to-any generation of multimodal representations for ecology.<n>By design, our model supports modality inversion in the embedding space.<n>We propose a novel cross-modal retrieval approach that mixes inter-modal and intra-modal similarities to achieve superior performance across all retrieval tasks.
  arXiv  Detail & Related papers  (2025-11-04T19:47:22Z)
• NExT-OMNI: Towards Any-to-Any Omnimodal Foundation Models with Discrete Flow Matching [64.10695425442164]
  We introduce NExT-OMNI, an open-source omnimodal foundation model that achieves unified modeling through discrete flow paradigms.<n>Trained on large-scale interleaved text, image, video, and audio data, NExT-OMNI delivers competitive performance on multimodal generation and understanding benchmarks.<n>To advance further research, we release training details, data protocols, and open-source both the code and model checkpoints.
  arXiv  Detail & Related papers  (2025-10-15T16:25:18Z)
• MultiSHAP: A Shapley-Based Framework for Explaining Cross-Modal Interactions in Multimodal AI Models [5.011371514152517]
  Multimodal AI models have achieved impressive performance in tasks that require integrating information from multiple modalities, such as vision and language.<n>How to explain cross-modal interactions in multimodal AI models remains a major challenge.
  arXiv  Detail & Related papers  (2025-08-01T12:19:18Z)
• Show-o2: Improved Native Unified Multimodal Models [57.34173415412808]
  Show-o2 is a native unified multimodal models that leverage autoregressive modeling and flow matching.<n>Built upon a 3D causal variational autoencoder space, unified visual representations are constructed through a dual-path of spatial (-temporal) fusion.
  arXiv  Detail & Related papers  (2025-06-18T15:39:15Z)
• OmniBench: Towards The Future of Universal Omni-Language Models [63.16606414452612]
  We introduce OmniBench, a novel benchmark designed to evaluate models' ability to recognize, interpret, and reason across visual, acoustic, and textual inputs simultaneously.<n>Our evaluation reveals that open-source OLMs show significant limitations in instruction-following and reasoning in tri-modal contexts.<n>We advocate for developing more robust tri-modal integration techniques and training strategies to enhance OLM performance.
  arXiv  Detail & Related papers  (2024-09-23T17:59:05Z)
• U3M: Unbiased Multiscale Modal Fusion Model for Multimodal Semantic Segmentation [63.31007867379312]
  We introduce U3M: An Unbiased Multiscale Modal Fusion Model for Multimodal Semantics. We employ feature fusion at multiple scales to ensure the effective extraction and integration of both global and local features. Experimental results demonstrate that our approach achieves superior performance across multiple datasets.
  arXiv  Detail & Related papers  (2024-05-24T08:58:48Z)
• Explaining latent representations of generative models with large multimodal models [5.9908087713968925]
  Learning interpretable representations of data generative latent factors is an important topic for the development of artificial intelligence. We propose a framework to comprehensively explain each latent variable in the generative models using a large multimodal model.
  arXiv  Detail & Related papers  (2024-02-02T19:28:33Z)

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.