论文检索

Deep Learning · Generative Models and Autoencoders

Omer Ronen, Ahmed Imtiaz Humayun, Richard Baraniuk, Randall Balestriero, Bin Yu

We develop Latent Exploration Score (LES) to mitigate over-exploration in Latent Space Optimization (LSO), a popular method for solving black-box discrete optimization problems. LSO utilizes continuous optimization within the latent space of a Variational Autoencoder (VAE) and is known to be susceptible to over-exploration, which manifests in unrealistic solutions that reduce its practicality. LES leverages the trained decoder’s approximation of the data distribution, and can be employed with any VAE decoder–including pretrained ones–without additional training, architectural changes or access to the training data. Our evaluation across five LSO benchmark tasks and twenty-two VAE models demonstrates that LES always enhances the quality of the solutions while maintaining high objective values, leading to improvements over existing solutions in most cases. We believe that new avenues to LSO will be opened by LES’ ability to identify out of distribution areas, differentiability, and computational tractability.

Deep Learning · Generative Models and Autoencoders

Reyhane Askari Hemmat, Mohammad Pezeshki, Elvis Dohmatob, Florian Bordes, Pietro Astolfi, Melissa Hall, Jakob Verbeek, Michal Drozdzal, Adriana Romero-Soriano

Inspired by the principle of deliberate practice in human learning, we propose Deliberate Practice for Synthetic Data Generation (DP), a novel framework that improves sample efficiency through dynamic synthetic data generation. Prior work has shown that scaling synthetic data is inherently challenging, as naively adding new data leads to diminishing returns. To address this, pruning has been identified as a key mechanism for improving scaling, enabling models to focus on the most informative synthetic samples. Rather than generating a large dataset and pruning it afterward, DP efficiently approximates the direct generation of informative samples. We theoretically show how training on challenging, informative examples improves scaling laws and empirically validate that DP achieves better scaling performance with significantly fewer training samples and iterations. On ImageNet-100, DP generates 3.4x fewer samples and requires six times fewer iterations, while on ImageNet-1k, it generates 8x fewer samples with a 30% reduction in iterations, all while achieving superior performance compared to prior work.

Deep Learning · Generative Models and Autoencoders

Ruiqi Feng, Chenglei Yu, Wenhao Deng, Peiyan Hu, Tailin Wu

Flow matching has shown state-of-the-art performance in various generative tasks, ranging from image generation to decision-making, where generation under energy guidance (abbreviated as guidance in the following) is pivotal. However, the guidance of flow matching is more general than and thus substantially different from that of its predecessor, diffusion models. Therefore, the challenge in guidance for general flow matching remains largely underexplored. In this paper, we propose the first framework of general guidance for flow matching. From this framework, we derive a family of guidance techniques that can be applied to general flow matching. These include a new training-free asymptotically exact guidance, novel training losses for training-based guidance, and two classes of approximate guidance that cover classical gradient guidance methods as special cases. We theoretically investigate these different methods to give a practical guideline for choosing suitable methods in different scenarios. Experiments on synthetic datasets, image inverse problems, and offline reinforcement learning demonstrate the effectiveness of our proposed guidance methods and verify the correctness of our flow matching guidance framework. Code to reproduce the experiments can be found at https://github.com/AI4Science-WestlakeU/flow_guidance.

Deep Learning · Generative Models and Autoencoders

Ruofeng Yang, Bo Jiang, Cheng Chen, Shuai Li

Consistency models, a new class of one-step generative models, have shown competitive performance with multi-step diffusion models. The most challenging part of consistency models is the training process, which discretizes the continuous diffusion process into $K$ steps and trains a one-step mapping function on these discretized timepoints. Despite the empirical success, only a few works focus on the discretization complexity $K$, and their setting is far from that of empirical works. More specifically, the current theoretical works analyze the variance preserving (VP) diffusion process with a uniform stepsize, while empirical works adopt a variance exploding (VE) process with a decay discretization stepsize. As a result, these works suffer from large discretization complexity and fail to explain the empirical success of consistency models. To close the gap between theory and application, we analyze consistency models with (1) VE process and (2) decay stepsize and prove the state-of-the-art discretization complexity for consistency models. This result is competitive with the results of diffusion models and shows the potential of consistency models. To balance the computation and performance, previous empirical work further proposes a $2$-step consistency algorithm. In this work, we also analyze the role of $2$-step sampling and show that it improves the discretization complexity compared with one-step generation.

Deep Learning · Generative Models and Autoencoders

Shaobin Zhuang, Yiwei Guo, Yanbo Ding, Kunchang Li, Xinyuan Chen, Yaohui Wang, Fangyikang Wang, Ying Zhang, Chen Li, Yali Wang

Diffusion models have driven the advancement of vision generation over the past years. However, it is often difficult to apply these large models in downstream tasks, due to massive fine-tuning cost. Recently, Low-Rank Adaptation (LoRA) has been applied for efficient tuning of diffusion models. Unfortunately, the capabilities of LoRA-tuned diffusion models are limited, since the same LoRA is used for different timesteps of the diffusion process. To tackle this problem, we introduce a general and concise TimeStep Master (TSM) paradigm with two key fine-tuning stages. In the fostering stage (1-stage), we apply different LoRAs to fine-tune the diffusion model at different timestep intervals. This results in different TimeStep LoRA experts that can effectively capture different noise levels. In the assembling stage (2-stage), we design a novel asymmetrical mixture of TimeStep LoRA experts, via core-context collaboration of experts at multi-scale intervals. For each timestep, we leverage TimeStep LoRA expert within the smallest interval as the core expert without gating, and use experts within the bigger intervals as the context experts with time-dependent gating. Consequently, our TSM can effectively model the noise level via the expert in the finest interval, and adaptively integrate contexts from the experts of other scales, boosting the versatility of diffusion models. To show the effectiveness of our TSM paradigm, we conduct extensive experiments on three typical and popular LoRA-related tasks of diffusion models, including domain adaptation, post-pretraining, and model distillation. Our TSM achieves the state-of-the-art results on all these tasks, throughout various model structures (UNet, DiT and MM-DiT) and visual data modalities (Image, Video), showing its remarkable generalization capacity.

Deep Learning · Generative Models and Autoencoders

Ivan Skorokhodov, Sharath Girish, Benran Hu, Willi Menapace, Yanyu Li, Rameen Abdal, Sergey Tulyakov, Aliaksandr Siarohin

Latent diffusion models have emerged as the leading approach for generating high-quality images and videos, utilizing compressed latent representations to reduce the computational burden of the diffusion process. While recent advancements have primarily focused on scaling diffusion backbones and improving autoencoder reconstruction quality, the interaction between these components has received comparatively less attention. In this work, we perform a spectral analysis of modern autoencoders and identify inordinate high-frequency components in their latent spaces, which are especially pronounced in the autoencoders with a large bottleneck channel size. We hypothesize that this high-frequency component interferes with the coarse-to-fine nature of the diffusion synthesis process and hinders the generation quality. To mitigate the issue, we propose scale equivariance: a simple regularization strategy that aligns latent and RGB spaces across frequencies by enforcing scale equivariance in the decoder. It requires minimal code changes and only up to $20$K autoencoder fine-tuning steps, yet significantly improves generation quality, reducing FID by 19% for image generation on ImageNet-1K 256x256 and FVD by at least 44% for video generation on Kinetics-700 17x256x256. The source code is available at https://github.com/snap-research/diffusability.

Deep Learning · Generative Models and Autoencoders

Soobin Um, Beomsu Kim, Jong Chul YE

Minority samples are underrepresented instances located in low-density regions of a data manifold, and are valuable in many generative AI applications, such as data augmentation, creative content generation, etc. Unfortunately, existing diffusion-based minority generators often rely on computationally expensive guidance dedicated for minority generation. To address this, here we present a simple yet powerful guidance-free approach called *Boost-and-Skip* for generating minority samples using diffusion models. The key advantage of our framework requires only two minimal changes to standard generative processes: (i) variance-boosted initialization and (ii) timestep skipping. We highlight that these seemingly-trivial modifications are supported by solid theoretical and empirical evidence, thereby effectively promoting emergence of underrepresented minority features. Our comprehensive experiments demonstrate that Boost-and-Skip greatly enhances the capability of generating minority samples, even rivaling guidance-based state-of-the-art approaches while requiring significantly fewer computations. Code is available at https://github.com/soobin-um/BnS.

Deep Learning · Generative Models and Autoencoders

Fang-Duo Tsai, Shih-Lun Wu, Weijaw Lee, Sheng-Ping Yang, Bo-Rui Chen, Hao-Chung Cheng, Yi-Hsuan Yang

We propose MuseControlLite, a lightweight mechanism designed to fine-tune text-to-music generation models for precise conditioning using various time-varying musical attributes and reference audio signals. The key finding is that positional embeddings, which have been seldom used by text-to-music generation models in the conditioner for text conditions, are critical when the condition of interest is a function of time. Using melody control as an example, our experiments show that simply adding rotary positional embeddings to the decoupled cross-attention layers increases control accuracy from 56.6% to 61.1%, while requiring 6.75 times fewer trainable parameters than state-of-the-art fine-tuning mechanisms, using the same pre-trained diffusion Transformer model of Stable Audio Open. We evaluate various forms of musical attribute control, audio inpainting, and audio outpainting, demonstrating improved controllability over MusicGen-Large and Stable Audio Open ControlNet at a significantly lower fine-tuning cost, with only 85M trainable parameters. Source code, model checkpoints, and demo examples are available at: https://MuseControlLite.github.io/web/

Deep Learning · Generative Models and Autoencoders

Fangyikang Wang, Hubery Yin, Shaobin Zhuang, Huminhao Zhu, Yinan Li, Lei Qian, Chao Zhang, Hanbin Zhao, Hui Qian, Chen Li

Recent Diffusion models (DMs) advancements have explored incorporating the second-order diffusion Fisher information (DF), defined as the negative Hessian of log density, into various downstream tasks and theoretical analysis.However, current practices typically approximate the diffusion Fisher by applying auto-differentiation to the learned score network. This black-box method, though straightforward, lacks any accuracy guarantee and is time-consuming.In this paper, we show that the diffusion Fisher actually resides within a space spanned by the outer products of score and initial data.Based on the outer-product structure, we develop two efficient approximation algorithms to access the trace and matrix-vector multiplication of DF, respectively.These algorithms bypass the auto-differentiation operations with time-efficient vector-product calculations. Furthermore, we establish the approximation error bounds for the proposed algorithms.Experiments in likelihood evaluation and adjoint optimization demonstrate the superior accuracy and reduced computational cost of our proposed algorithms.Additionally, based on the novel outer-product formulation of DF, we design the first numerical verification experiment for the optimal transport property of the general PF-ODE deduced map.

Applications

Chao, Shisong Tang, Fan Li, Jiechao Gao, Hechang Chen

Accurately predicting user watch-time is crucial for enhancing user stickiness and retention in video recommendation systems. Existing watch-time prediction approaches typically involve transformations of watch-time labels for prediction and subsequent reversal, ignoring both the natural distribution properties of label and the \textit{instance representation confusion} that results in inaccurate predictions. In this paper, we propose ProWTP, a two-stage method combining prototype learning and optimal transport for watch-time regression prediction, suitable for any deep recommendation model. Specifically, we observe that the watch-ratio (the ratio of watch-time to video duration) within the same duration bucket exhibits a multimodal distribution. To facilitate incorporation into models, we use a hierarchical vector quantised variational autoencoder (HVQ-VAE) to convert the continuous label distribution into a high-dimensional discrete distribution, serving as credible prototypes for calibrations. Based on this, ProWTP views the alignment between prototypes and instance representations as a Semi-relaxed Unbalanced Optimal Transport (SUOT) problem, where the marginal constraints of prototypes are relaxed. And the corresponding optimization problem is reformulated as a weighted Lasso problem for solution. Moreover, ProWTP introduces the assignment and compactness losses to encourage instances to cluster closely around their respective prototypes, thereby enhancing the prototype-level distinguishability. Finally, we conducted extensive offline experiments on two industrial datasets, demonstrating our consistent superiority in real-world application.

Deep Learning · Generative Models and Autoencoders

Kushagra Pandey, Farrin Marouf Sofian, Felix Draxler, Theofanis Karaletsos, Stephan Mandt

Diffusion models exhibit excellent sample quality, but existing guidance methods often require additional model training or are limited to specific tasks. We revisit guidance in diffusion models from the perspective of variational inference and control, introducing \emph{Diffusion Trajectory Matching (DTM)} that enables guiding pretrained diffusion trajectories to satisfy a terminal cost. DTM unifies a broad class of guidance methods and enables novel instantiations. We introduce a new method within this framework that achieves state-of-the-art results on several linear, non-linear, and blind inverse problems without requiring additional model training or specificity to pixel or latent space diffusion models. Our code will be available at https://github.com/czi-ai/oc-guidance.

Probabilistic Methods · Gaussian Processes

Xinxing Shi, Xiaoyu Jiang, Mauricio Álvarez

Gaussian Process (GP) Variational Autoencoders (VAEs) extend standard VAEs by replacing the fully factorised Gaussian prior with a GP prior, thereby capturing richer correlations among latent variables. However, performing exact GP inference in large-scale GPVAEs is computationally prohibitive, often forcing existing approaches to rely on restrictive kernel assumptions or large sets of inducing points. In this work, we propose a neighbour-driven approximation strategy that exploits local adjacencies in the latent space to achieve scalable GPVAE inference. By confining computations to the nearest neighbours of each data point, our method preserves essential latent dependencies, allowing more flexible kernel choices and mitigating the need for numerous inducing points. Through extensive experiments on tasks including representation learning, data imputation, and conditional generation, we demonstrate that our approach outperforms other GPVAE variants in both predictive performance and computational efficiency.

Deep Learning · Generative Models and Autoencoders

Rajat Rasal, Avinash Kori, Fabio De Sousa Ribeiro, Tian Xia, Ben Glocker

Counterfactual image generation presents significant challenges, including preserving identity, maintaining perceptual quality, and ensuring faithfulness to an underlying causal model. While existing auto-encoding frameworks admit semantic latent spaces which can be manipulated for causal control, they struggle with scalability and fidelity. Advancements in diffusion models present opportunities for improving counterfactual image editing, having demonstrated state-of-the-art visual quality, human-aligned perception and representation learning capabilities. Here, we present a suite of diffusion-based causal mechanisms, introducing the notions of spatial, semantic and dynamic abduction. We propose a general framework that integrates semantic representations into diffusion models through the lens of Pearlian causality to edit images via a counterfactual reasoning process. To the best of our knowledge, ours is the first work to consider high-level semantic identity preservation for diffusion counterfactuals and to demonstrate how semantic control enables principled trade-offs between faithful causal control and identity preservation.

Social Aspects · Accountability, Transparency, and Interpretability

Harrish Thasarathan, Julian Forsyth, Thomas Fel, Matthew Kowal, Konstantinos Derpanis

We present Universal Sparse Autoencoders (USAEs), a framework for uncovering and aligning interpretable concepts spanning multiple pretrained deep neural networks. Unlike existing concept-based interpretability methods, which focus on a single model, USAEs jointly learn a universal concept space that can reconstruct and interpret the internal activations of multiple models at once. Our core insight is to train a single, overcomplete sparse autoencoder (SAE) that ingests activations from any model and decodes them to approximate the activations of any other model under consideration. By optimizing a shared objective, the learned dictionary captures common factors of variation—concepts—across different tasks, architectures, and datasets. We show that USAEs discover semantically coherent and important universal concepts across vision models; ranging from low-level features (e.g., colors and textures) to higher-level structures (e.g., parts and objects). Overall, USAEs provide a powerful new method for interpretable cross-model analysis and offers novel applications—such as coordinated activation maximization—that open avenues for deeper insights in multi-model AI systems.

Deep Learning · Generative Models and Autoencoders

Peiyuan Zhang, Yongqi Chen, Runlong Su, Hangliang Ding, Ion Stoica, Zhengzhong Liu, Hao Zhang

Diffusion Transformers (DiTs) with 3D full attention power state-of-the-art video generation, but suffer from prohibitive compute cost -- when generating just a 5-second 720P video, attention alone takes 800 out of 950 seconds of total inference time. This paper introduces sliding tile attention (STA) to address this challenge. STA leverages the observation that attention scores in pretrained video diffusion models predominantly concentrate within localized 3D windows. By sliding and attending over local spatial-temporal region, STA eliminates redundancy from full attention. Unlike traditional token-wise sliding window attention (SWA), STA operates tile-by-tile with a novel hardware-aware sliding window design, preserving expressiveness while being \emph{hardware-efficient}. With careful kernel-level optimizations, STA offers the first efficient 2D/3D sliding-window-like attention implementation, achieving 58.79\% MFU -- 7.17× faster than prior art methods. On the leading video DiT model, Hunyuan, it accelerates attention by 1.6–10x over FlashAttention-3, yielding a 1.36–3.53× end-to-end speedup with no or minimum quality loss.

Deep Learning · Generative Models and Autoencoders

Payman Behnam, Yaosheng Fu, Ritchie Zhao, Po-An Tsai, Zhiding Yu, Alexey Tumanov

Transformer-based Large Language Models rely critically on the KV cache to efficiently handle extended contexts during the decode phase. Yet, the size of the KV cache grows proportionally with the input length, burdening both memory bandwidth and capacity as decoding progresses. To address this challenge, we present RocketKV, a training-free KV cache compression strategy containing two consecutive stages. In the first stage, it performs coarse-grain permanent KV cache eviction on the input sequence tokens. In the second stage, it adopts a hybrid sparse attention method to conduct fine-grain top-k sparse attention, approximating the attention scores by leveraging both head and sequence dimensionality reductions. We show that RocketKV provides a compression ratio of up to 400×, end-to-end speedup of up to 3.7× as well as peak memory reduction of up to 32.6% in the decode phase on an NVIDIA A100 GPU compared to the full KV cache baseline, while achieving negligible accuracy loss on a variety of long-context tasks. We also propose a variant of RocketKV for multi-turn scenarios, which consistently outperforms other existing methods and achieves accuracy nearly on par with an oracle top-k attention scheme.

Deep Learning · Generative Models and Autoencoders

Alec Helbling, Tuna Han Salih Meral, Benjamin Hoover, Pinar Yanardag, Polo Chau

Do the rich representations of multi-modal diffusion transformers (DiTs) exhibit unique properties that enhance their interpretability? We introduce ConceptAttention, a novel method that leverages the expressive power of DiT attention layers to generate high-quality saliency maps that precisely locate textual concepts within images. Without requiring additional training, ConceptAttention repurposes the parameters of DiT attention layers to produce highly contextualized *concept embeddings*, contributing the major discovery that performing linear projections in the output space of DiT attention layers yields significantly sharper saliency maps compared to commonly used cross-attention maps. ConceptAttention even achieves state-of-the-art performance on zero-shot image segmentation benchmarks, outperforming 15 other zero-shot interpretability methods on the ImageNet-Segmentation dataset. ConceptAttention works for popular image models and even seamlessly generalizes to video generation. Our work contributes the first evidence that the representations of multi-modal DiTs are highly transferable to vision tasks like segmentation.

Deep Learning · Generative Models and Autoencoders

Zheng Fang, Lichuan Xiang, Xu Cai, Kaicheng Zhou, Hongkai Wen

Spatial conditioning control offers a powerful way to guide diffusion‐based generative models. Yet, most implementations (e.g., ControlNet) rely on ad-hoc heuristics to choose which network blocks to control — an approach that varies unpredictably with different tasks. To address this gap, we propose FlexControl, a novel framework that equips all diffusion blocks with control signals during training and employs a trainable gating mechanism to dynamically select which control signal to activate at each denoising step. By introducing a computation-aware loss, we can encourage the control signal to activate only when it benefits the generation quality. By eliminating manual control unit selection, FlexControl enhances adaptability across diverse tasks and streamlines the design pipeline with computation-aware training loss in an end-to-end training manner. Through comprehensive experiments on both UNet and DiT architectures on different control methods, we show that our method can upgrade existing controllable generative models in certain key aspects of interest. As evidenced by both quantitative and qualitative evaluations, FlexControl preserves or enhances image fidelity while also reducing computational overhead by selectively activating the most relevant blocks to control. These results underscore the potential of a flexible, data‐driven approach for controlled diffusion and open new avenues for efficient generative model design. The code will soon be available at https://github.com/Daryu-Fan/FlexControl.

Deep Learning · Generative Models and Autoencoders

Kaiwen Zheng, Yongxin Chen, Huayu Chen, Guande He, Ming-Yu Liu, Jun Zhu, Qinsheng Zhang

While likelihood-based generative models, particularly diffusion and autoregressive models, have achieved remarkable fidelity in visual generation, the maximum likelihood estimation (MLE) objective, which minimizes the forward KL divergence, inherently suffers from a mode-covering tendency that limits the generation quality under limited model capacity. In this work, we propose Direct Discriminative Optimization (DDO) as a unified framework that integrates likelihood-based generative training and GAN-type discrimination to bypass this fundamental constraint by exploiting reverse KL and self-generated negative signals. Our key insight is to parameterize a discriminator implicitly using the likelihood ratio between a learnable target model and a fixed reference model, drawing parallels with the philosophy of Direct Preference Optimization (DPO). Unlike GANs, this parameterization eliminates the need for joint training of generator and discriminator networks, allowing for direct, efficient, and effective finetuning of a well-trained model to its full potential beyond the limits of MLE. DDO can be performed iteratively in a self-play manner for progressive model refinement, with each round requiring less than 1\% of pretraining epochs. Our experiments demonstrate the effectiveness of DDO by significantly advancing the previous SOTA diffusion model EDM, reducing FID scores from 1.79/1.58/1.96 to new records of 1.30/0.97/1.26 on CIFAR-10/ImageNet-64/ImageNet 512$\times$512 datasets without any guidance mechanisms, and by consistently improving both guidance-free and CFG-enhanced FIDs of visual autoregressive models on ImageNet 256$\times$256.

Deep Learning · Generative Models and Autoencoders

Ching-Hua Lee, Chouchang Yang, Jaejin Cho, Yashas Malur Saidutta, Rakshith Sharma Srinivasa, Yilin Shen, Hongxia Jin

Denoising diffusion probabilistic models (DDPMs) can be utilized to recover a clean signal from its degraded observation(s) by conditioning the model on the degraded signal. The degraded signals are themselves contaminated versions of the clean signals; due to this correlation, they may encompass certain useful information about the target clean data distribution. However, existing adoption of the standard Gaussian as the prior distribution in turn discards such information when shaping the prior, resulting in sub-optimal performance. In this paper, we propose to improve conditional DDPMs for signal restoration by leveraging a more informative prior that is jointly learned with the diffusion model. The proposed framework, called RestoreGrad, seamlessly integrates DDPMs into the variational autoencoder (VAE) framework, taking advantage of the correlation between the degraded and clean signals to encode a better diffusion prior. On speech and image restoration tasks, we show that RestoreGrad demonstrates faster convergence (5-10 times fewer training steps) to achieve better quality of restored signals over existing DDPM baselines and improved robustness to using fewer sampling steps in inference time (2-2.5 times fewer), advocating the advantages of leveraging jointly learned prior for efficiency improvements in the diffusion process.