论文检索

Computer Vision · Image and Video Generation

Hui Zhang, Dexiang Hong, Maoke Yang, Yutao Cheng, Zhao Zhang, Weidong Chen, Jie Shao, Xinglong Wu, Zuxuan Wu, Yu-Gang Jiang

Graphic design plays a vital role in visual communication across advertising, marketing, and multimedia entertainment. Prior work has explored automated graphic design generation using diffusion models, aiming to streamline creative workflows and democratize design capabilities. However, complex graphic design scenarios require accurately adhering to design intent specified by multiple heterogeneous user-provided elements (\eg images, layouts, and texts), which pose multi-condition control challenges for existing methods. Specifically, previous single-condition control models demonstrate effectiveness only within their specialized domains but fail to generalize to other conditions, while existing multi-condition methods often lack fine-grained control over each sub-condition and compromise overall compositional harmony. To address these limitations, we introduce CreatiDesign, a systematic solution for automated graphic design covering both model architecture and dataset construction. First, we design a unified multi-condition driven architecture that enables flexible and precise integration of heterogeneous design elements with minimal architectural modifications to the base diffusion model. Furthermore, to ensure that each condition precisely controls its designated image region and to avoid interference between conditions, we propose a multimodal attention mask mechanism. Additionally, we develop a fully automated pipeline for constructing graphic design datasets, and introduce a new dataset with 400K samples featuring multi-condition annotations, along with a comprehensive benchmark. Experimental results show that CreatiDesign outperforms existing models by a clear margin in faithfully adhering to user intent.

Reinforcement Learning · Deep RL

Chengyang Ying, Huayu Chen, Xinning Zhou, Zhongkai Hao, Hang Su, Jun Zhu

Unsupervised reinforcement learning (URL) pre-trains agents by exploring diverse states in reward-free environments, aiming to enable efficient adaptation to various downstream tasks. Without extrinsic rewards, prior methods rely on intrinsic objectives, but heterogeneous exploration data demand strong modeling capacity for both intrinsic reward design and policy learning. We introduce the **Ex**ploratory **D**iffusion **M**odel (**ExDM**), which leverages the expressive power of diffusion models to fit diverse replay-buffer distributions, thus providing accurate density estimates and a score-based intrinsic reward that drives exploration into under-visited regions. This mechanism substantially broadens state coverage and yields robust pre-trained policies. Beyond exploration, ExDM offers theoretical guarantees and practical algorithms for fine-tuning diffusion policies under limited interactions, overcoming instability and computational overhead from multi-step sampling. Extensive experiments on Maze2d and URLB show that ExDM achieves superior exploration and faster downstream adaptation, establishing new state-of-the-art results, particularly in environments with complex structure or cross-embodiment settings. The source code is provided at https://github.com/yingchengyang/ExDM.

Deep Learning · Generative Models and Autoencoders

Jiayang Shi, Daniel Pelt, Joost Batenburg

Diffusion models have recently emerged as powerful priors for solving inverse problems. While Computed Tomography (CT) is theoretically a linear inverse problem, it poses many practical challenges. These include correlated noise, artifact structures, reliance on system geometry, and misaligned value ranges, which make the direct application of diffusion models more difficult than in domains like natural image generation. To systematically evaluate how diffusion models perform in this context and compare them with established reconstruction methods, we introduce DM4CT, a comprehensive benchmark for CT reconstruction. DM4CT includes datasets from both medical and industrial domains with sparse-view and noisy configurations. To explore the challenges of deploying diffusion models in practice, we additionally acquire a high-resolution CT dataset at a high-energy synchrotron facility and evaluate all methods under real experimental conditions. We benchmark nine recent diffusion-based methods alongside seven strong baselines, including model-based, unsupervised, and supervised approaches. Our analysis provides detailed insights into the behavior, strengths, and limitations of diffusion models for CT reconstruction. The real-world dataset is publicly available at zenodo.org/records/15420527, and the codebase is open-sourced at github.com/DM4CT/DM4CT.

Applications · Robotics

Siqiao Huang, Jialong Wu, Qixing Zhou, Shangchen Miao, Mingsheng Long

World models, which predict future transitions from past observation and action sequences, have shown great promise for improving data efficiency in sequential decision-making. However, existing world models often require extensive domain-specific training and still produce low-fidelity, coarse predictions, limiting their usefulness in complex environments. In contrast, video diffusion models trained on large-scale internet data have demonstrated impressive capabilities in generating high-quality videos that capture diverse real-world dynamics. In this work, we present _Vid2World_, a general approach for leveraging and transferring pre-trained video diffusion models into interactive world models. To bridge the gap, Vid2World systematically explores _video diffusion causalization_, reshaping both the architecture and training objective of pre-trained models to enable autoregressive generation. Additionally, it incorporates a _causal action guidance_ mechanism to enhance action controllability in the resulting interactive world models. Extensive experiments across multiple domains, including robot manipulation, 3D game simulation, and open-world navigation, demonstrate that our method offers a scalable and effective pathway for repurposing highly capable video diffusion models into interactive world models.

Computer Vision · Image and Video Generation

Zihan Zhou, Shilin Lu, Shuli Leng, Shaocong Zhang, Zhuming Lian, Xinlei Yu, Adams Kong

Drag-based image editing has long suffered from distortions in the target region, largely because the priors of earlier base models, Stable Diffusion, are insufficient to project optimized latents back onto the natural image manifold. With the shift from UNet-based DDPMs to more scalable DiT with flow matching (e.g., SD3.5, FLUX), generative priors have become significantly stronger, enabling advances across diverse editing tasks. However, drag-based editing has yet to benefit from these stronger priors. This work introduces DragFlow, the first framework to effectively harness FLUX’s rich prior via region-based supervision, enabling full use of its finer-grained, spatially precise features for drag-based editing and achieving substantial improvements over existing baselines. We first show that directly applying point-based drag editing to DiTs performs poorly: unlike the highly compressed features of UNets, DiT features are insufficiently structured to provide reliable guidance for point-wise motion supervision. To overcome this limitation, DragFlow introduces a region-based editing paradigm, where affine transformations enable richer and more consistent feature supervision. Additionally, we integrate pretrained open-domain personalization adapters (e.g., IP-Adapter) to enhance subject consistency, while preserving background fidelity through gradient mask-based hard constraints. Multimodal large language models (MLLMs) are further employed to resolve task ambiguities. For evaluation, we curate a novel Region-based Dragging benchmark (ReD Bench) featuring region-level dragging instructions. Extensive experiments on DragBench-DR and ReD Bench show that DragFlow surpasses both point-based and region-based baselines, setting a new state-of-the-art in drag-based image editing. Code and dataset are available at https://github.com/Edennnnnnnnnn/DragFlow.

Computer Vision · Image and Video Generation

Ouxiang Li, Yuan Wang, Xinting Hu, Houcheng Jiang, Jack tao, Yanbin Hao, James Ma, Fuli Feng

Erasing concepts from large-scale text-to-image (T2I) diffusion models has become increasingly crucial due to the growing concerns over copyright infringement, privacy violations, and offensive content. In scalable erasure applications, fine-tuning-based methods are time-consuming to precisely erase multiple target concepts, while real-time editing-based methods often degrade the generation quality of non-target concepts due to conflicting optimization objectives. To address this dilemma, we introduce SPEED, a ***scalable, precise, and efficient*** concept erasure approach that directly edits model parameters. SPEED searches for a null space, a model editing space where parameter updates do not affect non-target concepts, to achieve scalable and precise erasure. To facilitate accurate null space optimization, we incorporate three complementary strategies: Influence-based Prior Filtering (IPF) to selectively retain the most affected non-target concepts, Directed Prior Augmentation (DPA) to enrich the filtered retain set with semantically consistent variations, and Invariant Equality Constraints (IEC) to preserve key invariants during the T2I generation process. Extensive evaluations across multiple concept erasure tasks demonstrate that SPEED consistently outperforms existing methods in non-target preservation while achieving efficient and high-fidelity concept erasure, successfully erasing 100 concepts within only 5 seconds. Our code and models are available at: https://github.com/Ouxiang-Li/SPEED.

Applications · Robotics

Kangye Ji, Yuan Meng, Hanyun Cui, Ye Li, Jianbo Zhou, Shengjia Hua, Lei Chen, Zhi Wang

Diffusion Policy has demonstrated strong visuomotor modeling capabilities, but its high computational cost renders it impractical for real-time robotic control. Despite huge redundancy across repetitive denoising steps, existing diffusion acceleration techniques fail to generalize to Diffusion Policy due to fundamental architectural and data divergences. In this paper, we propose **B**lock-wise **A**daptive **C**aching (**BAC**), a method to accelerate Diffusion Policy by caching intermediate action features. BAC achieves lossless action generation acceleration by adaptively updating and reusing cached features at the block level, based on a key observation that feature similarities exhibit non-uniform temporal dynamics and distinct block-specific patterns. To operationalize this insight, we first design an Adaptive Caching Scheduler to identify optimal update timesteps by maximizing the global feature similarities between cached and skipped features. However, applying this scheduler for each block leads to significant error surges due to the inter-block propagation of caching errors, particularly within Feed-Forward Network (FFN) blocks. To mitigate this issue, we develop the Bubbling Union Algorithm, which truncates these errors by updating the upstream blocks with significant caching errors before downstream FFNs. As a training-free plugin, BAC is readily integrable with existing transformer-based Diffusion Policy and vision-language-action models. Extensive experiments on multiple robotic benchmarks demonstrate that BAC achieves up to 3x inference speedup for free. Project page: https://block-wise-adaptive-caching.github.io.

Optimization · Sampling and Optimization

Nishant Jain, Tong Zhang

Diffusion-based generative models have emerged as highly effective methods for synthesizing high-quality samples. Recent works have focused on analyzing the convergence of their generation process with minimal assumptions, either through reverse SDEs or probability flow ODEs. The best known guarantees, without any smoothness assumptions, for the KL divergence so far achieve a linear dependence on the data dimension $d$ and an inverse quadratic dependence on accuracy level $\varepsilon$. In this work, we present a refined analysis for the standard Exponential Integrator discretization that improves the dependence on $\varepsilon$, at the same time maintaining the linear dependence on $d$. Following recent works on higher order/randomized midpoint discretizations, we model the generation process as a composition of two steps: a reverse ODE step followed by a smaller noising step, which leads to better dependence on step size. We then provide a novel analysis which achieves linear dependence on $d$ for the ODE discretization error without any smoothness assumptions. Specifically, we introduce a general ODE-based counterpart of the stochastic localization argument from Benton et al and develop new proof techniques to bound second-order spatial derivatives of the score function -- terms that do not arise in previous diffusion analyses and cannot be handled by existing techniques. Leveraging this framework, we prove that $\tilde{O}\left(\tfrac{d \log^{3/2}(1/\delta)}{\varepsilon}\right)$ steps suffice to approximate the target distribution—corrupted by Gaussian noise of variance $\delta$—to within $O(\varepsilon^2)$ in KL divergence, improving upon the previous best result requiring $\tilde{O}\left(\tfrac{d \log^2(1/\delta)}{\varepsilon^2}\right)$ steps.

Computer Vision · Image and Video Generation

Ruibin Li, Tao Yang, Yangming Shi, Weiguo Feng, Shilei Wen, BINGYUE PENG, Lei Zhang

Diffusion models have shown impressive performance in many visual generation and manipulation tasks. Many existing methods focus on training a model for a specific task, especially, text-to-video (T2V) generation, while many other works focus on finetuning the pretrained T2V model for image-to-video (I2V), video-to-video (V2V), image and video manipulation tasks, \etc. However, training a strong T2V foundation model requires a large amount of high-quality annotations, which is very costly. In addition, many existing models can perform only one or several tasks. In this work, we introduce a unified framework, namely \textit{many-for-many}, which leverages the available training data from many different visual generation and manipulation tasks to train a single model for those different tasks. Specifically, we design a lightweight adapter to unify the different conditions in different tasks, then employ a joint image-video learning strategy to progressively train the model from scratch. Our joint learning not only leads to a unified generation and manipulation model but also benefits the performance of different tasks. In addition, we introduce depth maps as a condition to help our model better perceive the 3D space in visual generation. Two versions of our model are trained with different model sizes (8B and 2B), each of which can perform more than 10 different tasks. In particular, our 8B model demonstrates highly competitive performance in different generation and manipulation tasks compared to open-source and even commercial engines. Our models and source codes will be made publicly available.

Deep Learning · Generative Models and Autoencoders

Paribesh Regmi, Sandesh Ghimire, Rui Li

Although iterative denoising (i.e., diffusion/flow) methods offer strong generative performance, they suffer from low generation efficiency, requiring hundreds of steps of network forward passes to simulate a single sample. Mitigating this requires taking larger step-sizes during simulation, thereby allowing one- or few-step generation. Recently proposed shortcut model learns larger step-sizes by enforcing alignment between its direction and the path defined by a base many-step flow-matching model through a self-consistency loss. However, its generation quality is significantly lower than the base model. In this paper, we formulate few-step generation as a controlled base generative process, and show that self-consistency loss can be understood through the lens of optimal control. This perspective naturally motivates its generalization to the proposed cumulative self-consistency loss that cumulatively penalizes misalignment along the entire trajectory. This encourages larger step-sizes that not only align with the base model at the current time step but also support alignment in the subsequent steps, facilitating high-quality generation. Furthermore, we draw a connection between our approach and reinforcement learning, potentially opening the door to a new set of approaches for few-step generation. Experiments show that we significantly improve one- and few-step generation quality under the same training budget. Implementation is available at: [https://github.com/paribeshregmi/Shortcut-CSL](https://github.com/paribeshregmi/Shortcut-CSL)

Computer Vision · Image and Video Generation

Jiayi Lyu, Leigang Qu, Wenjing Zhang, Hanyu Jiang, Kai Liu, Zhenglin Zhou, Xiaobo Xia, Jian Xue, Tat-Seng Chua

Realistic talking-head video generation is critical for virtual avatars, film production, and interactive systems. Current methods struggle with nuanced emotional expressions due to the lack of fine-grained emotion control. To address this issue, we introduce a novel two-stage method (AUHead) to disentangle fine-grained emotion control, i.e. , Action Units (AUs), from audio and achieve controllable generation. In the first stage, we explore the AU generation abilities of large audio-language models (ALMs), by spatial-temporal AU tokenization and an "emotion-then-AU" chain-of-thought mechanism. It aims to disentangle AUs from raw speech, effectively capturing subtle emotional cues. In the second stage, we propose an AU-driven controllable diffusion model that synthesizes realistic talking-head videos conditioned on AU sequences. Specifically, we first map the AU sequences into the structured 2D facial representation to enhance spatial fidelity, and then model the AU-vision interaction within cross-attention modules. To achieve flexible AU-quality trade-off control, we introduce an AU disentanglement guidance strategy during inference, further refining the emotional expressiveness and identity consistency of the generated videos. Results on benchmark datasets demonstrate that our approach achieves competitive performance in emotional realism, accurate lip synchronization, and visual coherence, significantly surpassing existing techniques. Our implementation is available at https://github.com/laura990501/AUHead_ICLR

Reinforcement Learning · Batch/Offline

Tieru Wang, Kunbao Wu, Guoshun Nan

Recent advances in offline reinforcement learning (RL) have led to the development of high-performing algorithms that achieve impressive results across standard benchmarks. However, many of these methods depend on increasingly complex planning architectures, which hinder their deployment in real-world settings due to high inference costs. To overcome this limitation, recent research has explored data augmentation techniques that offload computation from online decision-making to offline data preparation. Among these, diffusion-based generative models have shown potential in synthesizing diverse trajectories but incur significant overhead in training and data generation. In this work, we propose Trajectory Generation with Conservative Value Guidance (TGCVG), a novel trajectory-level data augmentation framework that integrates a high-performing offline policy with a learned dynamics model. To ensure that the synthesized trajectories are both high-quality and close to the original dataset distribution, we introduce a value-guided regularization during the training of the offline policy. This regularization encourages conservative action selection, effectively mitigating distributional shift during trajectory synthesis. Empirical results on standard benchmarks demonstrate that TGCVG not only improves the performance of state-of-the-art offline RL algorithms but also significantly reduces training and trajectory synthesis time. These findings highlight the effectiveness of value-aware data generation in improving both efficiency and policy performance.

Computer Vision · Image and Video Generation

Qingyang Mao, Qi Cai, Yehao Li, Yingwei Pan, Mingyue Cheng, Ting Yao, Qi Liu, Tao Mei

Recent advances in diffusion models have brought remarkable visual fidelity to instruction-guided image editing. However, their global denoising process inherently entangles the edited region with the entire image context, leading to unintended spurious modifications and compromised adherence to editing instructions. In contrast, autoregressive models offer a distinct paradigm by formulating image synthesis as a sequential process over discrete visual tokens. Their causal and compositional mechanism naturally circumvents the adherence challenges of diffusion-based methods. In this paper, we present VAREdit, a visual autoregressive (VAR) framework that reframes image editing as a next-scale prediction problem. Conditioned on source image features and text instructions, VAREdit generates multi-scale target features to achieve precise edits. A core challenge in this paradigm is how to effectively condition the source image tokens. We observe that finest-scale source features cannot effectively guide the prediction of coarser target features. To bridge this gap, we introduce a Scale-Aligned Reference (SAR) module, which injects scale-matched conditioning information into the first self-attention layer. VAREdit demonstrates significant advancements in both editing adherence and efficiency. On EMU-Edit and PIE-Bench benchmarks, VAREdit outperforms leading diffusion-based methods by a substantial margin in terms of both CLIP and GPT scores. Moreover, VAREdit completes a 512$\times$512 editing in 1.2 seconds, making it 2.2$\times$ faster than the similarly sized UltraEdit. Code is available at: https://github.com/HiDream-ai/VAREdit.

Computer Vision · Image and Video Generation

Hanzhuo Huang, Qingyang Bao, Zekai Gu, Zhongshuo Du, Cheng Lin, Yuan Liu, Sibei Yang

In this paper, we propose a 3D asset-referenced diffusion model for image generation, exploring how to integrate 3D assets into image diffusion models. Existing reference-based image generation methods leverage large-scale pretrained diffusion models and demonstrate strong capability in generating diverse images conditioned on a single reference image. However, these methods are limited to single-image references and cannot leverage 3D assets, constraining their practical versatility. To address this gap, we present a cross-domain diffusion model with dual-branch perception that leverages multi-view RGB images and point maps of 3D assets to jointly model their colors and canonical-space coordinates, achieving precise consistency between generated images and the 3D references. Our spatially aligned dual-branch generation architecture and domain-decoupled generation mechanism ensure the simultaneous generation of two spatially aligned but content-disentangled outputs, RGB images and point maps, linking 2D image attributes with 3D asset attributes. Experiments show that our approach effectively uses 3D assets as references to produce images consistent with the given assets, opening new possibilities for combining diffusion models with 3D content creation.

Deep Learning · Generative Models and Autoencoders

Pengxiang Li, Yefan Zhou, Dilxat Muhtar, Lu Yin, Shilin Yan, Li Shen, Yi Liang, Soroush Vosoughi, Shiwei Liu

Diffusion language models (DLMs) have recently emerged as an alternative to autoregressive approaches, offering parallel sequence generation and flexible token orders. However, their inference remains slower than that of autoregressive models, primarily due to the cost of bidirectional attention and the large number of refinement steps required for high-quality outputs. In this work, we highlight and leverage an overlooked property of DLMs—**early answer convergence**: in many cases, the correct answer can be internally identified by half steps before the final decoding step, under both semi-autoregressive and random remasking schedules. For example, on GSM8K and MMLU, up to 97\% and 99\% of instances, respectively, can be decoded correctly using only half of the refinement steps. Building on this observation, we introduce **Prophet**, a training-free fast decoding paradigm that enables **early commit decoding**. Specifically, Prophet dynamically decides whether to continue refinement or to go "all-in" (i.e. decode all remaining tokens in one step), using the confidence gap between the top-2 prediction candidates as the criterion. It integrates seamlessly into existing DLM implementations, incurs negligible overhead, and requires no additional training. Empirical evaluations on LLaDA-8B and Dream-7B across multiple tasks show that Prophet reduces the number of decoding steps by up to 3.4$\times$ while preserving high generation quality, and yields additional speedups when combined with existing acceleration methods. These results recast DLM decoding as a problem of *when to stop sampling*, and demonstrate that early answer convergence provides a simple yet powerful mechanism for accelerating DLMs on reasoning, code, and planning tasks with identifiable answer regions. Our code is available at \url{https://github.com/pixeli99/Prophet}.

Social Aspects · Trustworthy Machine Learning

Zhuo Cai, Shoujin Wang, Jin Li, Peilin Zhou, Victor W. Chu, Fang Chen, Tianqing Zhu, Charu Aggarwal

In recent years, diffusion models (DMs) have achieved remarkable success in recommender systems (RSs), owing to their strong capacity to model the complex distributions of item content and user behaviors. Despite their effectiveness, existing methods pose the danger of generating uncredible content recommendations (e.g., fake news, misinformation) that may significantly harm social well-being, as they primarily emphasize recommendation accuracy while neglecting the credibility of the recommended content. To address this issue, in this paper, we propose Disco, a novel method to steer diffusion models towards credible content recommendation. Specifically, we design a novel disentangled diffusion model to mitigate the harmful influence of uncredible content on the generation process while preserving high recommendation accuracy. This is achieved by reformulating the diffusion objective to encourage generation conditioned on preference-related signals while discouraging generation conditioned on uncredible content-related signals. In addition, to further improve the recommendation credibility, we design a progressively enhanced credible subspace projection that suppresses uncredible content by projecting diffusion targets into the null space of uncredible content. Extensive experiments on real-world datasets demonstrate the effectiveness of Disco in terms of both accurate and credible content recommendations.

Zigeng Chen, Gongfan Fang, Xinyin Ma, Ruonan Yu, Xinchao Wang

Diffusion large language models (dLLMs) have recently drawn considerable attention within the research community as a promising alternative to autoregressive generation, offering parallel token prediction and lower inference latency. Yet, their parallel decoding potential remains largely underexplored, as existing open-source models still require nearly token-length decoding steps to ensure performance. To address this, we introduce dParallel, a simple and effective method that unlocks the inherent parallelism of dLLMs for fast sampling. We identify that the key bottleneck to parallel decoding arises from the sequential certainty convergence for masked tokens. Building on this insight, we introduce the core of our approach: certainty-forcing distillation, a novel training strategy that distills the model to follow its original sampling trajectories while enforcing it to achieve high certainty on masked tokens more rapidly and in parallel. Extensive experiments demonstrate that our method can dramatically reduce the number of decoding steps while maintaining performance. When applied to the LLaDA-8B-Instruct model, dParallel reduces decoding steps from 256 to 30 on GSM8K, achieving an 8.5× speedup without performance degradation. On the MBPP benchmark, it cuts decoding steps from 256 to 24, resulting in a 10.5× speedup while maintaining accuracy.

Computer Vision · Image and Video Generation

Ziqi Ye, Shuran Ma, Jie Yang, Xiaoyi Yang, Yi Yang, Ziyang Gong, Xue Yang, Haipeng Wang

High-precision controllable remote sensing image generation is both meaningful and challenging. Existing diffusion models often produce low-fidelity objects due to their inability to adequately capture morphological details, which may affect the robustness and reliability of object detection models. To enhance the accuracy and fidelity of generated objects in remote sensing, this paper proposes Object Fidelity Diffusion (OF-Diff), which effectively improves the fidelity of generated objects. Specifically, we are the first to extract the prior shapes of objects based on the layout for diffusion models in remote sensing. Then, we introduce a self-distillation diffusion model with consistency distillation loss, which can generate high-fidelity remote sensing images without providing real images during the sampling phase. Furthermore, we introduce DDPO to fine-tune the diffusion process, making the generated remote sensing images more diverse and semantically consistent. Comprehensive experiments demonstrate that OF-Diff outperforms state-of-the-art methods in the remote sensing across key quality metrics. Notably, the performance of several polymorphic and small object classes shows significant improvement. For instance, the mAP increases by 8.3%, 7.7%, and 4.0% for airplanes, ships, and vehicles, respectively.

Deep Learning · Generative Models and Autoencoders

Andrew Campbell, Valentin De Bortoli, Jiaxin Shi, Arnaud Doucet

We present self-speculative masked diffusions, a new class of masked diffusion generative models for discrete data that require significantly fewer function evaluations to generate samples. Standard masked diffusion models predict factorized logits over currently masked positions. A number of masked positions are then sampled, however, the factorization approximation means that sampling too many positions in one go leads to poor sample quality. As a result, many simulation steps and therefore neural network function evaluations are required to generate high-quality data. We reduce the computational burden by generating \emph{non-factorized} predictions over masked positions. This is achieved by modifying the final transformer attention mask from non-causal to causal, enabling draft token generation and parallel validation via a novel, model-integrated speculative sampling mechanism. This results in a non-factorized predictive distribution over masked positions in a single forward pass. We apply our method to GPT2 scale text modelling and protein sequence generation, finding that we can achieve a ~2x reduction in the required number of network forward passes relative to standard masked diffusion models.

Deep Learning · Generative Models and Autoencoders

sina alemohammad, Zhangyang Wang, Richard Baraniuk

Scaling generative AI models is bottlenecked by the scarcity of high-quality training data. The ease of synthesizing from a generative model suggests using (unverified) synthetic data to augment a limited corpus of real data for the purpose of fine-tuning in the hope of improving performance. Unfortunately, however, the resulting positive feedback loop leads to model autophagy disorder (MAD, aka model collapse) that results in a rapid degradation in sample quality and/or diversity. In this paper, we introduce Neon (for Negative Extrapolation frOm self-traiNing), a new learning method that turns the degradation from self-training into a powerful signal for self-improvement. Given a base model, Neon first fine-tunes it on its own self-synthesized data but then, counterintuitively, reverses its gradient updates to extrapolate away from the degraded weights. We prove that Neon works because typical inference samplers that favor high-probability regions create a predictable anti-alignment between the synthetic and real data population gradients, which negative extrapolation corrects to better align the model with the true data distribution. Neon is remarkably easy to implement via a simple post-hoc merge that requires no new real data, works effectively with as few as 1k synthetic samples, and typically uses less than 1\% additional training compute. We demonstrate Neon’s universality across a range of architectures (diffusion, flow matching, autoregressive, and inductive moment matching models) and datasets (ImageNet, CIFAR-10, and FFHQ). In particular, on ImageNet 256x256, Neon elevates the xAR-L model to a new state-of-the-art FID of 1.02 with only 0.36\% additional training compute.