RankE co-evolves AR policy and decoder via alternating ranking optimization, improving both FID and CLIP scores on LlamaGen-XL and Janus-Pro where policy-only RL degrades FID.
hub Canonical reference
Transfusion: Predict the Next Token and Diffuse Images with One Multi-Modal Model
Canonical reference. 79% of citing Pith papers cite this work as background.
50
Pith papers citing it
Background
79% of classified citations
abstract
We introduce Transfusion, a recipe for training a multi-modal model over discrete and continuous data. Transfusion combines the language modeling loss function (next token prediction) with diffusion to train a single transformer over mixed-modality sequences. We pretrain multiple Transfusion models up to 7B parameters from scratch on a mixture of text and image data, establishing scaling laws with respect to a variety of uni- and cross-modal benchmarks. Our experiments show that Transfusion scales significantly better than quantizing images and training a language model over discrete image tokens. By introducing modality-specific encoding and decoding layers, we can further improve the performance of Transfusion models, and even compress each image to just 16 patches. We further demonstrate that scaling our Transfusion recipe to 7B parameters and 2T multi-modal tokens produces a model that can generate images and text on a par with similar scale diffusion models and language models, reaping the benefits of both worlds.
hub tools
citation-role summary
background 15
baseline 3
method 1
citation-polarity summary
representative citing papers
SaaS-Bench provides 106 realistic professional tasks across 23 deployable SaaS platforms to evaluate LLM-based agents, finding that even the strongest models complete fewer than 4% of tasks end-to-end.
INSET embeds images as native tokens in interleaved instructions, outperforming prior methods on multi-image consistency and text alignment as complexity grows.
MoSS augments VLAs with decoupled modality streams for multiple physical signals, achieving synergistic gains in real-world robot tasks via joint attention and auxiliary future-signal prediction.
LangFlow is the first continuous diffusion language model to rival discrete diffusion on perplexity and generative perplexity while exceeding autoregressive baselines on several zero-shot tasks.
Process-driven image generation decomposes text-to-image synthesis into interleaved cycles of textual planning, visual drafting, textual reflection, and visual refinement with dense consistency supervision.
LASAGNA produces layered images with integrated visual effects in a single pass, enabling drift-free edits via alpha compositing while releasing a 48K dataset and a 242-sample benchmark.
ViBES introduces a speech-language-behavior model using modality-specific transformer experts that jointly generates dialogue and 3D body actions, showing gains over separate co-speech and text-to-motion baselines on multi-turn metrics.
Text-to-image models show significant limitations in integrating world knowledge, as measured by the new WISE benchmark and WiScore metric across 20 models.
Janus decouples visual encoding into task-specific pathways inside a single autoregressive transformer to unify multimodal understanding and generation while outperforming earlier unified models.
Semantic Generative Tuning uses image segmentation as a generative proxy to align misaligned representation spaces in unified multimodal models and improve both perception and generative layout fidelity.
Lance presents a dual-stream mixture-of-experts model with modality-aware positional encoding and staged multi-task training that outperforms prior open-source unified models on image and video generation while keeping strong understanding performance.
Latent Action Control learns unobserved action trajectories via variational alignment and GRPO to inject reasoning into flow-based image generation, yielding gains on compositional benchmarks.
STARFlow2 presents an autoregressive flow-based architecture for unified multimodal text-image generation by interleaving a VLM stream with a TarFlow stream via residual skips and a unified latent space.
MUSE decouples reconstruction and semantic learning in visual tokenization via topological orthogonality, yielding SOTA generation quality and improved semantic performance over its teacher model.
Tuna-2 shows that direct pixel embeddings can replace vision encoders in unified multimodal models, achieving competitive generation and stronger understanding at scale.
Meta-CoT uses two-level decomposition of editing operations into meta-tasks and a CoT consistency reward to improve granularity and generalization, reporting 15.8% gains across 21 tasks.
CheXmix combines masked autoencoder pretraining with early-fusion generative modeling to outperform prior models on chest X-ray classification by up to 8.6% AUROC, inpainting by 51%, and report generation by 45% on GREEN.
IMU-to-4D uses wearable IMU data and repurposed LLMs to predict coherent 4D human motion plus coarse scene structure, outperforming cascaded state-of-the-art pipelines in temporal stability.
GRN uses hierarchical binary quantization and entropy-guided refinement to set new ImageNet records of 0.56 rFID for reconstruction and 1.81 gFID for class-conditional generation while releasing code and models.
VLMs fail at counting because visual evidence degrades in later language layers, and a lightweight Modality Attention Share intervention can encourage better use of image information during answer generation.
Symbiotic-MoE introduces modality-aware expert disentanglement and progressive training in a multimodal MoE to achieve synergistic generation and understanding without task interference or extra parameters.
CLEAR uses degradation-aware fine-tuning, a latent representation bridge, and interleaved reinforcement learning to connect generative and reasoning capabilities in multimodal models for better degraded image understanding.
LLaMo scales pretrained LLMs for unified motion-language tasks by encoding motion into continuous causal latents and adding a flow-matching head for real-time autoregressive generation and captioning.
citing papers explorer
-
RankE: End-to-End Post-Training for Discrete Text-to-Image Generation with Decoder Co-Evolution
RankE co-evolves AR policy and decoder via alternating ranking optimization, improving both FID and CLIP scores on LlamaGen-XL and Janus-Pro where policy-only RL degrades FID.
-
SaaS-Bench: Can Computer-Use Agents Leverage Real-World SaaS to Solve Professional Workflows?
SaaS-Bench provides 106 realistic professional tasks across 23 deployable SaaS platforms to evaluate LLM-based agents, finding that even the strongest models complete fewer than 4% of tasks end-to-end.
-
Images in Sentences: Scaling Interleaved Instructions for Unified Visual Generation
INSET embeds images as native tokens in interleaved instructions, outperforming prior methods on multi-image consistency and text alignment as complexity grows.
-
Modular Sensory Stream for Integrating Physical Feedback in Vision-Language-Action Models
MoSS augments VLAs with decoupled modality streams for multiple physical signals, achieving synergistic gains in real-world robot tasks via joint attention and auxiliary future-signal prediction.
-
LangFlow: Continuous Diffusion Rivals Discrete in Language Modeling
LangFlow is the first continuous diffusion language model to rival discrete diffusion on perplexity and generative perplexity while exceeding autoregressive baselines on several zero-shot tasks.
-
Think in Strokes, Not Pixels: Process-Driven Image Generation via Interleaved Reasoning
Process-driven image generation decomposes text-to-image synthesis into interleaved cycles of textual planning, visual drafting, textual reflection, and visual refinement with dense consistency supervision.
-
A Unified and Controllable Framework for Layered Image Generation with Visual Effects
LASAGNA produces layered images with integrated visual effects in a single pass, enabling drift-free edits via alpha compositing while releasing a 48K dataset and a 242-sample benchmark.
-
ViBES: A Conversational Agent with Behaviorally-Intelligent 3D Virtual Body
ViBES introduces a speech-language-behavior model using modality-specific transformer experts that jointly generates dialogue and 3D body actions, showing gains over separate co-speech and text-to-motion baselines on multi-turn metrics.
-
WISE: A World Knowledge-Informed Semantic Evaluation for Text-to-Image Generation
Text-to-image models show significant limitations in integrating world knowledge, as measured by the new WISE benchmark and WiScore metric across 20 models.
-
Janus: Decoupling Visual Encoding for Unified Multimodal Understanding and Generation
Janus decouples visual encoding into task-specific pathways inside a single autoregressive transformer to unify multimodal understanding and generation while outperforming earlier unified models.
-
Semantic Generative Tuning for Unified Multimodal Models
Semantic Generative Tuning uses image segmentation as a generative proxy to align misaligned representation spaces in unified multimodal models and improve both perception and generative layout fidelity.
-
Lance: Unified Multimodal Modeling by Multi-Task Synergy
Lance presents a dual-stream mixture-of-experts model with modality-aware positional encoding and staged multi-task training that outperforms prior open-source unified models on image and video generation while keeping strong understanding performance.
-
Latent Action Control for Reasoning-Guided Unified Image Generation
Latent Action Control learns unobserved action trajectories via variational alignment and GRPO to inject reasoning into flow-based image generation, yielding gains on compositional benchmarks.
-
STARFlow2: Bridging Language Models and Normalizing Flows for Unified Multimodal Generation
STARFlow2 presents an autoregressive flow-based architecture for unified multimodal text-image generation by interleaving a VLM stream with a TarFlow stream via residual skips and a unified latent space.
-
MUSE: Resolving Manifold Misalignment in Visual Tokenization via Topological Orthogonality
MUSE decouples reconstruction and semantic learning in visual tokenization via topological orthogonality, yielding SOTA generation quality and improved semantic performance over its teacher model.
-
Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generation
Tuna-2 shows that direct pixel embeddings can replace vision encoders in unified multimodal models, achieving competitive generation and stronger understanding at scale.
-
Meta-CoT: Enhancing Granularity and Generalization in Image Editing
Meta-CoT uses two-level decomposition of editing operations into meta-tasks and a CoT consistency reward to improve granularity and generalization, reporting 15.8% gains across 21 tasks.
-
CheXmix: Unified Generative Pretraining for Vision Language Models in Medical Imaging
CheXmix combines masked autoencoder pretraining with early-fusion generative modeling to outperform prior models on chest X-ray classification by up to 8.6% AUROC, inpainting by 51%, and report generation by 45% on GREEN.
-
Seeing Without Eyes: 4D Human-Scene Understanding from Wearable IMUs
IMU-to-4D uses wearable IMU data and repurposed LLMs to predict coherent 4D human motion plus coarse scene structure, outperforming cascaded state-of-the-art pipelines in temporal stability.
-
Generative Refinement Networks for Visual Synthesis
GRN uses hierarchical binary quantization and entropy-guided refinement to set new ImageNet records of 0.56 rFID for reconstruction and 1.81 gFID for class-conditional generation while releasing code and models.
-
Counting to Four is still a Chore for VLMs
VLMs fail at counting because visual evidence degrades in later language layers, and a lightweight Modality Attention Share intervention can encourage better use of image information during answer generation.
-
Symbiotic-MoE: Unlocking the Synergy between Generation and Understanding
Symbiotic-MoE introduces modality-aware expert disentanglement and progressive training in a multimodal MoE to achieve synergistic generation and understanding without task interference or extra parameters.
-
CLEAR: Unlocking Generative Potential for Degraded Image Understanding in Unified Multimodal Models
CLEAR uses degradation-aware fine-tuning, a latent representation bridge, and interleaved reinforcement learning to connect generative and reasoning capabilities in multimodal models for better degraded image understanding.
-
LLaMo: Scaling Pretrained Language Models for Unified Motion Understanding and Generation with Continuous Autoregressive Tokens
LLaMo scales pretrained LLMs for unified motion-language tasks by encoding motion into continuous causal latents and adding a flow-matching head for real-time autoregressive generation and captioning.
-
HunyuanImage 3.0 Technical Report
HunyuanImage 3.0 delivers an 80B-parameter MoE model unifying multimodal understanding and generation that matches prior state-of-the-art results while being fully open-sourced.
-
EditVerse: Unifying Image and Video Editing and Generation with In-Context Learning
EditVerse unifies image and video editing and generation in one transformer model via unified token sequences and in-context learning, trained jointly on curated video editing data plus image/video corpora and evaluated on a new instruction-based benchmark.
-
Muddit: Liberating Generation Beyond Text-to-Image with a Unified Discrete Diffusion Model
Muddit is a unified discrete diffusion transformer that integrates strong visual priors from a pretrained text-to-image model with a lightweight text decoder to enable fast parallel generation across text and image modalities.
-
LLaDA-V: Large Language Diffusion Models with Visual Instruction Tuning
LLaDA-V is a diffusion-based multimodal large language model that reaches competitive or state-of-the-art results on visual instruction tasks while using a non-autoregressive architecture.
-
MMaDA: Multimodal Large Diffusion Language Models
MMaDA is a unified multimodal diffusion model using mixed chain-of-thought fine-tuning and a new UniGRPO reinforcement learning algorithm that outperforms specialized models in reasoning, understanding, and text-to-image tasks.
-
Mogao: An Omni Foundation Model for Interleaved Multi-Modal Generation
Mogao presents a causal unified model with deep fusion, dual encoders, and interleaved position embeddings that achieves strong performance on multi-modal understanding, text-to-image generation, and coherent interleaved outputs including zero-shot editing.
-
Unified World Models: Coupling Video and Action Diffusion for Pretraining on Large Robotic Datasets
Unified World Models couple video and action diffusion inside one transformer with independent timesteps, enabling pretraining on heterogeneous robot datasets that include action-free video and producing more generalizable policies than imitation learning alone.
-
Long-Context Autoregressive Video Modeling with Next-Frame Prediction
FAR baseline plus asymmetric kernels for long short-term context modeling achieves SOTA short and long video generation in autoregressive setups.
-
HybridVLA: Collaborative Diffusion and Autoregression in a Unified Vision-Language-Action Model
HybridVLA unifies diffusion and autoregression in a single VLA model via collaborative training and ensemble to raise robot manipulation success rates by 14% in simulation and 19% in real-world tasks.
-
LMM-R1: Empowering 3B LMMs with Strong Reasoning Abilities Through Two-Stage Rule-Based RL
A two-stage RL framework first boosts text reasoning in 3B LMMs then adapts it to multimodal inputs, producing modest benchmark gains of 4.5-4.8%.
-
Imagine while Reasoning in Space: Multimodal Visualization-of-Thought
MVoT lets multimodal models create coherent images during chain-of-thought reasoning via a token discrepancy loss, yielding competitive or better results than text-only CoT on dynamic spatial tasks.
-
MetaMorph: Multimodal Understanding and Generation via Instruction Tuning
VPiT enables pretrained LLMs to perform both visual understanding and generation by predicting discrete text tokens and continuous visual tokens, with understanding data proving more effective than generation-specific data.
-
Mixture-of-Transformers: A Sparse and Scalable Architecture for Multi-Modal Foundation Models
MoT decouples non-embedding parameters by modality in transformers to match dense multi-modal performance with roughly one-third to one-half the FLOPs.
-
$\pi_0$: A Vision-Language-Action Flow Model for General Robot Control
π₀ is a vision-language-action flow model trained on diverse multi-platform robot data that supports zero-shot task performance, language instruction following, and efficient fine-tuning for dexterous tasks.
-
Emu3: Next-Token Prediction is All You Need
Emu3 shows that next-token prediction on a unified discrete token space for text, images, and video lets a single transformer outperform task-specific models such as SDXL and LLaVA-1.6 in multimodal generation and perception.
-
SenseNova-U1: Unifying Multimodal Understanding and Generation with NEO-unify Architecture
SenseNova-U1 presents native unified multimodal models that match top understanding VLMs while delivering strong performance in image generation, infographics, and interleaved tasks via the NEO-unify architecture.
-
CG-MLLM: Captioning and Generating 3D content via Multi-modal Large Language Models
CG-MLLM is a multimodal LLM using a Mixture-of-Transformer architecture with separate TokenAR and BlockAR components integrated with a pre-trained vision-language backbone and 3D VAE to enable 3D captioning and high-fidelity generation.
-
WorldVLA: Towards Autoregressive Action World Model
WorldVLA unifies VLA and world models in one autoregressive system, shows they boost each other, and adds an attention mask to stop error buildup when generating action chunks.
-
OmniGen2: Towards Instruction-Aligned Multimodal Generation
OmniGen2 introduces a unified generative model with two distinct decoding pathways and a decoupled image tokenizer that achieves competitive results on text-to-image and editing benchmarks plus state-of-the-art consistency among open-source models on the new OmniContext benchmark.
-
Emerging Properties in Unified Multimodal Pretraining
BAGEL is a unified decoder-only model that develops emerging complex multimodal reasoning abilities after pretraining on large-scale interleaved data and outperforms prior open-source unified models.
-
BLIP3-o: A Family of Fully Open Unified Multimodal Models-Architecture, Training and Dataset
BLIP3-o uses a diffusion transformer to generate CLIP image features and a sequential pretraining strategy to build open models that perform strongly on both image understanding and generation benchmarks.
-
Hallucination of Multimodal Large Language Models: A Survey
The survey organizes causes of hallucinations in MLLMs, reviews evaluation benchmarks and metrics, and outlines mitigation approaches plus open questions.
-
MMCORE: MultiModal COnnection with Representation Aligned Latent Embeddings
MMCORE transfers VLM reasoning into diffusion-based image generation and editing via aligned latent embeddings from learnable queries, outperforming baselines on text-to-image and editing tasks.
-
Janus-Pro: Unified Multimodal Understanding and Generation with Data and Model Scaling
Scaling data, model size, and training optimization on the Janus architecture yields better multimodal understanding and more stable, instruction-following text-to-image generation.
-
Cosmos World Foundation Model Platform for Physical AI
The Cosmos platform supplies open-source pre-trained world models and supporting tools for building fine-tunable digital world simulations to train Physical AI.
-
Redefining End-of-Life: Intelligent Automation for Electronics Remanufacturing Systems
A literature review of intelligent automation approaches using robotics, AI, and control for disassembly, inspection, sorting, and reprocessing of end-of-life electronics.