mlsanityData to 7 Oct 2026

Emu3.5: Native Multimodal Models are World Learners

arXiv 2510.26583 ↗First posted 30 Oct 2025cs.CVcited by 119

On the map: World models → World models for language agents

Abstract (arXiv)

We introduce Emu3.5, a large-scale multimodal world model that natively predicts the next state across vision and language. Emu3.5 is pre-trained end-to-end with a unified next-token prediction objective on a corpus of vision-language interleaved data containing over 10 trillion tokens, primarily derived from sequential frames and transcripts of internet videos. The model naturally accepts interleaved vision-language inputs and generates interleaved vision-language outputs. Emu3.5 is further post-trained with large-scale reinforcement learning to enhance multimodal reasoning and generation. To improve inference efficiency, we propose Discrete Diffusion Adaptation (DiDA), which converts token-by-token decoding into bidirectional parallel prediction, accelerating per-image inference by about 20x without sacrificing performance. Emu3.5 exhibits strong native multimodal capabilities, including long-horizon vision-language generation, any-to-image (X2I) generation, and complex text-rich image generation. It also exhibits generalizable world-modeling abilities, enabling spatiotemporally consistent world exploration and open-world embodied manipulation across diverse scenarios and tasks. For comparison, Emu3.5 achieves performance comparable to Gemini 2.5 Flash Image (Nano Banana) on image generation and editing tasks and demonstrates superior results on a suite of interleaved generation tasks. We open-source Emu3.5 at https://github.com/baaivision/Emu3.5 to support community research.

Key facts. Cited by 119 papers in the map (data through 7 Oct 2026). Placed in World models for language agents, one of 11 directions in World models. Builds on 102 of its 110 references that are in the map. First posted on arXiv 30 Oct 2025.

Builds on

102 of 110 references.

References · 102

  1. 2023GPT-4 Technical Reportcited by 18,132
  2. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  3. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  4. 2020Denoising Diffusion Implicit Modelscited by 9,655
  5. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 8,851
  6. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  7. 2025Qwen3 Technical Reportcited by 8,195
  8. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,764
  9. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,146
  10. 2022Scalable Diffusion Models with Transformerscited by 5,931
  11. 2023Efficient Memory Management for Large Language Model Serving with PagedAttentioncited by 5,767
  12. 2022Flow Matching for Generative Modelingcited by 5,426
38 more
  1. 2025Qwen2.5-VL Technical Reportcited by 5,418
  2. 2021RoFormer: Enhanced Transformer with Rotary Position Embeddingcited by 4,581
  3. 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,510
  4. 2023Improved Baselines with Visual Instruction Tuningcited by 4,362
  5. 2024Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolutioncited by 4,151
  6. 2022LAION-5B: An open large-scale dataset for training next generation image-text modelscited by 4,131
  7. 2024Scaling Rectified Flow Transformers for High-Resolution Image Synthesiscited by 4,094
  8. 2022Robust Speech Recognition via Large-Scale Weak Supervisioncited by 3,972
  9. 2025Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilitiescited by 3,655
  10. 2022DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generationcited by 3,286
  11. 2020Taming Transformers for High-Resolution Image Synthesiscited by 3,229
  12. 2023Sigmoid Loss for Language Image Pre-Trainingcited by 3,048
  13. 2024LLaVA-OneVision: Easy Visual Task Transfercited by 2,669
  14. 2022InstructPix2Pix: Learning to Follow Image Editing Instructionscited by 2,591
  15. 2020RAFT: Recurrent All-Pairs Field Transforms for Optical Flowcited by 2,385
  16. 2024HybridFlow: A Flexible and Efficient RLHF Frameworkcited by 1,980
  17. 2022DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Stepscited by 1,961
  18. 2019Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelismcited by 1,829
  19. 2020GLU Variants Improve Transformercited by 1,724
  20. 2019Root Mean Square Layer Normalizationcited by 1,425
  21. 2023GQA: Training Generalized Multi-Query Transformer Models from Multi-Head Checkpointscited by 1,311
  22. 2021Conceptual 12M: Pushing Web-Scale Image-Text Pre-Training To Recognize Long-Tail Visual Conceptscited by 1,209
  23. 2021MUSIQ: Multi-scale Image Quality Transformercited by 1,058
  24. 2024Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Predictioncited by 1,005
  25. 2025Qwen-Image Technical Reportcited by 973
  26. 2024Grounding Image Matching in 3D with MASt3Rcited by 960
  27. 2025FLUX.1 Kontext: Flow Matching for In-Context Image Generation and Editing in Latent Spacecited by 960
  28. 2023GenEval: An Object-Focused Framework for Evaluating Text-to-Image Alignmentcited by 946
  29. 2024Chameleon: Mixed-Modal Early-Fusion Foundation Modelscited by 904
  30. 2025Janus-Pro: Unified Multimodal Understanding and Generation with Data and Model Scalingcited by 787
  31. 2024Emu3: Next-Token Prediction is All You Needcited by 761
  32. 2024Autoregressive Model Beats Diffusion: Llama for Scalable Image Generationcited by 760
  33. 2024Show-o: One Single Transformer to Unify Multimodal Understanding and Generationcited by 734
  34. 2024SiT: Exploring Flow and Diffusion-based Generative Models with Scalable Interpolant Transformerscited by 707
  35. 2023Scaling Vision Transformers to 22 Billion Parameterscited by 690
  36. 2024Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Thinkcited by 666
  37. 2023DataComp: In search of the next generation of multimodal datasetscited by 635
  38. 2023MagicBrush: A Manually Annotated Dataset for Instruction-Guided Image Editingcited by 615

50 most cited of 102 All 102 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 14; 2026: 105.

119 papers.

Sort:

By area:

  1. 2026Unified 4D World Action Modeling from Video Priors with Asynchronous Denoisingcited by 65
  2. 2026Helios: Real Real-Time Long Video Generation Modelcited by 56
  3. 2025Thinking with Video: Video Generation as a Promising Multimodal Reasoning Paradigmcited by 41
  4. 2026Beyond Language Modeling: An Exploration of Multimodal Pretrainingcited by 32
  5. 2026LongCat-Next: Lexicalizing Modalities as Discrete Tokenscited by 30
  6. 2026SenseNova-U1: Unifying Multimodal Understanding and Generation with NEO-unify Architecturecited by 27
  7. 2026InternVL-U: Democratizing Unified Multimodal Models for Understanding, Reasoning, Generation and Editingcited by 23
  8. 2026Out of Sight but Not Out of Mind: Hybrid Memory for Dynamic Video World Modelscited by 20
  9. 2026Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generationcited by 17
  10. 2026NextFlow: Unified Sequential Modeling Activates Multimodal Understanding and Generationcited by 13
  11. 2026VLANeXt: Recipes for Building Strong VLA Modelscited by 12
  12. 2026LLaDA2.0-Uni: Unifying Multimodal Understanding and Generation with Diffusion Large Language Modelcited by 12
38 more
  1. 2025RealGen: Photorealistic Text-to-Image Generation via Detector-Guided Rewardscited by 11
  2. 2026VideoWorld 2: Learning Transferable Knowledge from Real-world Videoscited by 11
  3. 2026Lance: Unified Multimodal Modeling by Multi-Task Synergycited by 11
  4. 2026Bernini: Latent Semantic Planning for Video Diffusioncited by 11
  5. 2026LLaMo: Scaling Pretrained Language Models for Unified Motion Understanding and Generation with Continuous Autoregressive Tokenscited by 10
  6. 2026GenClaw: Code-Driven Agentic Image Generationcited by 10
  7. 2025VQRAE: Representation Quantization Autoencoders for Multimodal Understanding, Generation and Reconstructioncited by 9
  8. 2026UEval: A Benchmark for Unified Multimodal Generationcited by 9
  9. 2026UniM: A Unified Any-to-Any Interleaved Multimodal Benchmarkcited by 9
  10. 2026Xiaomi OneVL: One-Step Latent Reasoning and Planning with Vision-Language Explanationcited by 9
  11. 2026Autoregressive Image Generation with Masked Bit Modelingcited by 8
  12. 2026Context Unrolling in Omni Modelscited by 8
  13. 2026MemLearner: Learning to Query Context memory for Video World Modelscited by 8
  14. 2026CausalSpatial: A Benchmark for Object-Centric Causal Spatial Reasoningcited by 7
  15. 2026Covo-Audio Technical Reportcited by 7
  16. 2026RPiAE: A Representation-Pivoted Autoencoder Enhancing Both Image Generation and Editingcited by 7
  17. 2026BizGenEval: A Systematic Benchmark for Commercial Visual Content Generationcited by 7
  18. 2026LatentUM: Unleashing the Potential of Interleaved Cross-Modal Reasoning via a Latent-Space Unified Modelcited by 7
  19. 2025DuetSVG: Unified Multimodal SVG Generation with Internal Visual Guidancecited by 6
  20. 2026Re-Align: Structured Reasoning-guided Alignment for In-Context Image Generation and Editingcited by 6
  21. 2026MentisOculi: Revealing the Limits of Reasoning with Mental Imagerycited by 6
  22. 2026LaViDa-R1: Advancing Reasoning for Unified Multimodal Diffusion Language Modelscited by 6
  23. 2026CoCo: Code as CoT for Text-to-Image Preview and Rare Concept Generationcited by 6
  24. 2026WeEdit: A Dataset, Benchmark and Glyph-Guided Framework for Text-centric Image Editingcited by 6
  25. 2026Edit-Compass & EditReward-Compass: A Unified Benchmark for Image Editing and Reward Modelingcited by 6
  26. 2026Toward Native Multimodal Modeling: A Roadmapcited by 6
  27. 2026Orca: The World is in Your Mindcited by 6
  28. 2025FysicsWorld: A Unified Full-Modality Benchmark for Any-to-Any Understanding, Generation, and Reasoningcited by 5
  29. 2025TextEditBench: Evaluating Reasoning-aware Text Editing Beyond Renderingcited by 5
  30. 2025Co-GRPO: Co-Optimized Group Relative Policy Optimization for Masked Diffusion Modelcited by 5
  31. 2026OpenVision 3: A Family of Unified Visual Encoder for Both Understanding and Generationcited by 5
  32. 2025Are Image-to-Video Models Good Zero-Shot Image Editors?cited by 4
  33. 2025OpenSubject: Leveraging Video-Derived Identity and Diversity Priors for Subject-driven Image Generation and Manipulationcited by 4
  34. 2026Towards Holistic Modeling for Video Frame Interpolation with Auto-regressive Diffusion Transformerscited by 4
  35. 2026BitDance: Scaling Autoregressive Generative Models with Binary Tokenscited by 4
  36. 2026Meta-TTRL: A Metacognitive Framework for Self-Improving Test-Time Reinforcement Learning in Unified Multimodal Modelscited by 4
  37. 2026Towards Practical World Model-based Reinforcement Learning for Vision-Language-Action Modelscited by 4
  38. 2026AIBench: Evaluating Visual-Logical Consistency in Academic Illustration Generationcited by 4

50 most cited of 119 All 119 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025LaViDa: A Large Diffusion Language Model for Multimodal Understanding
  2. 2025I Think, Therefore I Diffuse: Enabling Multimodal In-Context Reasoning in Diffusion Models
  3. 2023Emu: Generative Pretraining in Multimodality
  4. 2025MMaDA: Multimodal Large Diffusion Language Models
  5. 2024Dual Diffusion for Unified Image Generation and Understanding
  6. 2025Can World Models Benefit VLMs for World Dynamics?
  7. 2025Bifrost-1: Bridging Multimodal LLMs and Diffusion Models with Patch-level CLIP Latents
  8. 2025Dual-Stream Diffusion for World-Model Augmented Vision-Language-Action Model