✨EVTAR: End-to-End Try on with Additional Unpaired Visual Reference

📝 Summary:
EVTAR is an end-to-end virtual try-on model that enhances accuracy and garment detail preservation using additional reference images. It simplifies the process by requiring only source and target garment inputs, producing high-quality, realistic try-on results.

🔹 Publication Date: Published on Nov 2

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2511.00956
• PDF: https://arxiv.org/pdf/2511.00956
• Github: https://github.com/360CVGroup/EVTAR

🔹 Models citing this paper:
• https://huggingface.co/qihoo360/EVTAR

==================================

For more data science resources:
✓ https://xn--r1a.website/DataScienceT

#VirtualTryOn #ComputerVision #DeepLearning #AIFashion #ImageSynthesis

✨MMaDA-Parallel: Multimodal Large Diffusion Language Models for Thinking-Aware Editing and Generation

📝 Summary:
A parallel multimodal diffusion framework, MMaDA-Parallel, enhances cross-modal alignment and semantic consistency in thinking-aware image synthesis by addressing error propagation issues in sequentia...

🔹 Publication Date: Published on Nov 12

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2511.09611
• PDF: https://arxiv.org/pdf/2511.09611
• Project Page: https://tyfeld.github.io/mmadaparellel.github.io/
• Github: https://github.com/tyfeld/MMaDA-Parallel

🔹 Models citing this paper:
• https://huggingface.co/tyfeld/MMaDA-Parallel-A
• https://huggingface.co/tyfeld/MMaDA-Parallel-M

==================================

For more data science resources:
✓ https://xn--r1a.website/DataScienceT

#MultimodalAI #DiffusionModels #ImageSynthesis #LLM #AIResearch

✨InstructMix2Mix: Consistent Sparse-View Editing Through Multi-View Model Personalization

📝 Summary:
InstructMix2Mix I-Mix2Mix improves multi-view image editing from sparse inputs, which often lack consistency. It distills a 2D diffusion model into a multi-view diffusion model, leveraging its 3D prior for cross-view coherence. This framework significantly enhances multi-view consistency and per-...

🔹 Publication Date: Published on Nov 18

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2511.14899
• PDF: https://arxiv.org/pdf/2511.14899
• Project Page: https://danielgilo.github.io/instruct-mix2mix/
• Github: https://danielgilo.github.io/instruct-mix2mix/

==================================

For more data science resources:
✓ https://xn--r1a.website/DataScienceT

#MultiViewEditing #DiffusionModels #ComputerVision #3DVision #ImageSynthesis

✨Adversarial Flow Models

📝 Summary:
Adversarial flow models unify adversarial and flow-based generative models for stable training and efficient one-step generation. They learn a deterministic noise-to-data mapping, achieving record FIDs of 1.94 on ImageNet-256px with a single pass, outperforming consistency models.

🔹 Publication Date: Published on Nov 27

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2511.22475
• PDF: https://arxiv.org/pdf/2511.22475

==================================

For more data science resources:
✓ https://xn--r1a.website/DataScienceT

#GenerativeAI #DeepLearning #AdversarialModels #FlowModels #ImageSynthesis

✨Distribution Matching Variational AutoEncoder

📝 Summary:
DMVAE explicitly aligns VAE latent distributions with arbitrary reference distributions, generalizing beyond fixed priors. This improves modeling efficiency and image synthesis fidelity, with SSL-derived distributions showing excellent balance.

🔹 Publication Date: Published on Dec 8

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2512.07778
• PDF: https://arxiv.org/pdf/2512.07778
• Github: https://github.com/sen-ye/dmvae%7D

==================================

For more data science resources:
✓ https://xn--r1a.website/DataScienceT

#VAE #DeepLearning #GenerativeAI #ImageSynthesis #ArtificialIntelligence

✨StereoSpace: Depth-Free Synthesis of Stereo Geometry via End-to-End Diffusion in a Canonical Space

📝 Summary:
StereoSpace generates stereo images from monocular input using viewpoint-conditioned diffusion, avoiding explicit depth or warping. It leverages a canonical rectified space for sharp parallax and robust results on complex scenes. This establishes a scalable, depth-free stereo synthesis solution.

🔹 Publication Date: Published on Dec 11

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2512.10959
• PDF: https://arxiv.org/pdf/2512.10959
• Project Page: https://huggingface.co/spaces/prs-eth/stereospace_web
• Github: https://github.com/prs-eth/stereospace

🔹 Models citing this paper:
• https://huggingface.co/prs-eth/stereospace-v1-0

✨ Spaces citing this paper:
• https://huggingface.co/spaces/prs-eth/stereospace_web

==================================

For more data science resources:
✓ https://xn--r1a.website/DataScienceT

#StereoVision #DiffusionModels #ComputerVision #DeepLearning #ImageSynthesis

✨WaDi: Weight Direction-aware Distillation for One-step Image Synthesis

📝 Summary:
Diffusion model inference is slow. WaDi focuses on weight direction changes during distillation to accelerate models into efficient one-step generators. This achieves state-of-the-art quality with significantly fewer parameters and broad versatility.

🔹 Publication Date: Published on Mar 9

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2603.08258
• PDF: https://arxiv.org/pdf/2603.08258
• Github: https://github.com/gudaochangsheng/WaDi

==================================

For more data science resources:
✓ https://xn--r1a.website/DataScienceT

#DiffusionModels #ImageSynthesis #ModelAcceleration #DeepLearning #AIResearch

🔥 i1: A Simple and Fully Open Recipe for Strong Text-to-Image Models

💡 The paper presents a comprehensive study of text-to-image diffusion models, aiming to identify key design choices and training insights that lead to strong model performance. The problem addressed is the lack of fully open models that match the performance of state-of-the-art models, which hinders further research in the field. To tackle this, the authors conducted over 300 controlled experiments, totaling 700K TPU v6e hours, to investigate modeling and data design choices in text-to-image diffusion training and inference.

The method used involved a systematic investigation of various design decisions, such as dataset mixing and text encoder adapters, to identify simple yet effective approaches to training strong models. The authors found several empirical findings, including the use of equal weighting for mixing curated datasets and the benefits of larger text encoder adapters.

The results of the study led to the development of i1, a 3B-parameter text-to-image diffusion model trained using only publicly available datasets. The i1 model is competitive with leading models on five representative benchmarks and outperforms the best existing fully open model by 29.5 absolute percentage points on average. The authors provide the i1 checkpoints, training and inference code, and the data processing pipeline, making it a fully open model that can serve as a foundation for future research in text-to-image diffusion models.

Overall, the paper contributes to the field by providing a practical foundation for open research in text-to-image diffusion models, highlighting the importance of transparency and reproducibility in AI research. The release of the i1 model and its associated code and data processing pipeline enables the research community to build upon and improve the model, driving further progress in the field.

📅 Published on Jun 9

🔗 Links:
• GitHub: https://github.com/huggingface
• arXiv: https://arxiv.org/abs/2606.11289
• PDF: https://arxiv.org/pdf/2606.11289
• Project Page: https://zlab-princeton.github.io/i1/

🤖 Models citing this paper:
• https://huggingface.co/zlab-princeton/i1-3B

📊 Datasets citing this paper:
• https://huggingface.co/datasets/zlab-princeton/i1-captions
• https://huggingface.co/datasets/zlab-princeton/i1-gptedit-tfrecord

🚀 Spaces citing this paper:
• https://huggingface.co/spaces/multimodalart/i1-3B

━━━━━━━━━━━━━━━━━━━━━━━━
📢 By: https://xn--r1a.website/PaperNexus

#TextToImageModels #DiffusionModels #TextEncoderAdapters #ImageSynthesis #DeepLearningModels

🔥 GEAR: Guided End-to-End AutoRegression for Image Synthesis

💡 The paper introduces GEAR, a method for training a vector-quantized tokenizer and an autoregressive generator jointly and end-to-end for image synthesis. Typically, these models are trained in two stages, where the tokenizer is first trained and then frozen, and then the generator is trained on its output. However, this approach has a limitation, as the tokenizer is not aware of what the generator finds easy to model.

GEAR overcomes this limitation by training the tokenizer and generator jointly, guided by representation alignment. The key challenge is that the output of the tokenizer is non-differentiable, making it difficult to train the tokenizer and generator jointly. To address this, GEAR uses a dual read-out approach, where the tokenizer output is used in two different ways. A hard, one-hot branch is used to train the autoregressive generator, while a differentiable soft branch is used to carry a representation-alignment loss that guides the tokenizer.

This approach allows the autoregressive generator to steer the tokenizer towards an index distribution that it can predict more easily. As a result, the tokenizer's features become less complex, while the autoregressive generator's features become more complex and semantic. The paper demonstrates that GEAR speeds up convergence by up to 10 times relative to a strong baseline, and learns better patch-level and spatially-coherent features. Additionally, GEAR generalizes across different quantizers and can be applied to text-to-image generation. Overall, GEAR provides a new approach for training visual generative models, and achieves state-of-the-art results in image synthesis.

📅 Published on Jun 30

🔗 Links:
• GitHub: https://github.com/huggingface
• arXiv: https://arxiv.org/abs/2606.32039
• PDF: https://arxiv.org/pdf/2606.32039
• Project Page: https://linb203.github.io/gear

🤖 Models citing this paper:
• https://huggingface.co/BinLin203/Warmup-LFQ
• https://huggingface.co/BinLin203/Warmup-IBQ
• https://huggingface.co/BinLin203/GEAR-VQ

━━━━━━━━━━━━━━━━━━━━━━━━
📢 By: https://xn--r1a.website/PaperNexus

#ImageSynthesis #AutoRegression #VectorQuantization #EndToEndLearning #AutoregressiveGenerators

🔥 Representation Distribution Matching for One-Step Visual Generation

💡 The paper introduces Representation Distribution Matching, a method for one-step visual generation that matches feature distributions under pretrained encoders. The goal is to generate high-quality images by comparing the distributions of generated and reference features. The authors identify two key design axes: how the distributions are compared and the representations they are compared in. They conduct controlled studies and find three main results.

First, they show that the Maximum Mean Discrepancy, a classical method that was previously ineffective, becomes a strong and scalable objective when estimated correctly. Second, they find that the batch size of the generated images has a significant impact on performance, with an optimum batch size above 2048, which is much larger than typical batch sizes. Third, they demonstrate that using a single representation can be gamed, resulting in low scores despite visibly fake images, and instead propose using a balanced set of encoders and evaluating with a Sliced-Wasserstein distance over 14 encoders.

The authors combine these findings to develop an improved Representation Distribution Matching method, which they call iRDM. They evaluate iRDM on the ImageNet dataset and achieve state-of-the-art results, with a Sliced-Wasserstein distance of 1.30. Additionally, they use a human-preference proxy, called PickScore, which shows that iRDM is preferred over the previous best one-step generator on 71.2% of matched samples. They also apply the same method to post-train a four-step generator, called FLUX.2, and achieve better results than the original four-step version, with improved performance on GenEval and PickScore, and requiring only 90 GPU-hours. Overall, the paper presents a new method for one-step visual generation that achieves state-of-the-art results and can be used to improve existing generators.

📅 Published on Jul 2

🔗 Links:
• GitHub: https://github.com/huggingface
• arXiv: https://arxiv.org/abs/2607.02375
• PDF: https://arxiv.org/pdf/2607.02375
• Project Page: https://alan-lanfeng.github.io/rdm/

🤖 Models citing this paper:
• https://huggingface.co/epfl-vita/flux2-klein-1step-rdm

🚀 Spaces citing this paper:
• https://huggingface.co/spaces/epfl-vita/flux2-klein-1step-demo

━━━━━━━━━━━━━━━━━━━━━━━━
📢 By: https://xn--r1a.website/PaperNexus

#VisualGeneration #RepresentationLearning #DistributionMatching #ImageSynthesis #DeepLearning