ICML 2025 Papers

We present flow Q-learning (FQL), a simple and performant offline reinforcement learning (RL) method that leverages an expressive flow-matching policy to model arbitrarily complex action distributions in data. Training a flow policy with RL is a tricky problem, due to the iterative nature of the action generation process. We address this challenge by training an expressive one-step policy with RL, rather than directly guiding an iterative flow policy to maximize values. This way, we can completely avoid unstable recursive backpropagation, eliminate costly iterative action generation at test time, yet still mostly maintain expressivity. We experimentally show that FQL leads to strong performance across 73 challenging state- and pixel-based OGBench and D4RL tasks in offline RL and offline-to-online RL.

The design of target-specific molecules such as small molecules, peptides, and antibodies is vital for biological research and drug discovery. Existing generative methods are restricted to single-domain molecules, failing to address versatile therapeutic needs or utilize cross-domain transferability to enhance model performance. In this paper, we introduce **Uni**fied generative **Mo**deling of 3D **Mo**lecules (UniMoMo), the first framework capable of designing binders of multiple molecular domains using a single model. In particular, UniMoMo unifies the representations of different molecules as graphs of blocks, where each block corresponds to either a standard amino acid or a molecular fragment. Based on these unified representations, UniMoMo utilizes a geometric latent diffusion model for 3D molecular generation, featuring an iterative full-atom autoencoder to compress blocks into latent space points, followed by an E(3)-equivariant diffusion process. Extensive benchmarks across peptides, antibodies, and small molecules demonstrate the superiority of our unified framework over existing domain-specific models, highlighting the benefits of multi-domain training.

Graph generative models are essential across diverse scientific domains by capturing complex distributions over relational data. Among them, graph diffusion models achieve superior performance but face inefficient sampling and limited flexibility due to the tight coupling between training and sampling stages. We introduce DeFoG, a novel graph generative framework that disentangles sampling from training, enabling a broader design space for more effective and efficient model optimization. DeFoG employs a discrete flow-matching formulation that respects the inherent symmetries of graphs. We theoretically ground this disentangled formulation by explicitly relating the training loss to the sampling algorithm and showing that DeFoG faithfully replicates the ground truth graph distribution. Building on these foundations, we thoroughly investigate DeFoG's design space and propose novel sampling methods that significantly enhance performance and reduce the required number of refinement steps. Extensive experiments demonstrate state-of-the-art performance across synthetic, molecular, and digital pathology datasets, covering both unconditional and conditional generation settings. It also outperforms most diffusion-based models with just 5–10\% of their sampling steps.

Drug discovery is a complex process that involves multiple stages and tasks. However, existing molecular generative models can only tackle some of these tasks. We present *Generalist Molecular generative model* (GenMol), a versatile framework that uses only a *single* discrete diffusion model to handle diverse drug discovery scenarios. GenMol generates Sequential Attachment-based Fragment Embedding (SAFE) sequences through non-autoregressive bidirectional parallel decoding, thereby allowing the utilization of a molecular context that does not rely on the specific token ordering while having better sampling efficiency. GenMol uses fragments as basic building blocks for molecules and introduces *fragment remasking*, a strategy that optimizes molecules by regenerating masked fragments, enabling effective exploration of chemical space. We further propose *molecular context guidance* (MCG), a guidance method tailored for masked discrete diffusion of GenMol. GenMol significantly outperforms the previous GPT-based model in *de novo* generation and fragment-constrained generation, and achieves state-of-the-art performance in goal-directed hit generation and lead optimization. These results demonstrate that GenMol can tackle a wide range of drug discovery tasks, providing a unified and versatile approach for molecular design.

Fine-tuning pre-trained diffusion models under limited budgets has gained great success. In particular, the recent advances that directly fine-tune the quantized weights using Low-rank Adaptation (LoRA) further reduces training costs. Despite these progress, we point out that existing adaptation recipes are not inference-efficient. Specifically, additional post-training quantization (PTQ) on tuned weights is needed during deployment, which results in noticeable performance drop when the bit-width is low. Based on this observation, we introduce IntLoRA, which adapts quantized diffusion models with integer-type low-rank parameters, to include inference efficiency during tuning. Specifically, IntLoRA enables pre-trained weights to remain quantized during training, facilitating fine-tuning on consumer-level GPUs. During inference, IntLoRA weights can be seamlessly merged into pre-trained weights to directly obtain quantized downstream weights without PTQ. Extensive experiments show our IntLoRA achieves significant speedup on both training and inference without losing performance.

Tabular data generation has attracted significant research interest in recent years, with the tabular diffusion models greatly improving the quality of synthetic data. However, while memorization—where models inadvertently replicate exact or near-identical training data—has been thoroughly investigated in image and text generation, its effects on tabular data remain largely unexplored. In this paper, we conduct the first comprehensive investigation of memorization phenomena in diffusion models for tabular data. Our empirical analysis reveals that memorization appears in tabular diffusion models and increases with larger training epochs. We further examine the influence of factors such as dataset sizes, feature dimensions, and different diffusion models on memorization. Additionally, we provide a theoretical explanation for why memorization occurs in tabular diffusion models. To address this issue, we propose TabCutMix, a simple yet effective data augmentation technique that exchanges randomly selected feature segments between random same-class training sample pairs. Building upon this, we introduce TabCutMixPlus, an enhanced method that clusters features based on feature correlations and ensures that features within the same cluster are exchanged together during augmentation. This clustering mechanism mitigates out-of-distribution (OOD) generation issues by maintaining feature coherence. Experimental results across various datasets and diffusion models demonstrate that TabCutMix effectively mitigates memorization while maintaining high-quality data generation. Our code is available at https://github.com/fangzy96/TabCutMix.

In this work, we focus on the alignment problem of diffusion models with a continuous reward function, which represents specific objectives for downstream tasks, such as increasing darkness or improving the aesthetics of images. The central goal of the alignment problem is to adjust the distribution learned by diffusion models such that the generated samples maximize the target reward function. We propose a novel alignment approach, named Direct Noise Optimization (DNO), that optimizes the injected noise during the sampling process of diffusion models. By design, DNO operates at inference-time, and thus is tuning-free and prompt-agnostic, with the alignment occurring in an online fashion during generation. We rigorously study the theoretical properties of DNO and also propose variants to deal with non-differentiable reward functions. Furthermore, we identify that naive implementation of DNO occasionally suffers from the out-of-distribution reward hacking problem, where optimized samples have high rewards but are no longer in the support of the pretrained distribution. To remedy this issue, we leverage classical high-dimensional statistics theory to an effective probability regularization technique. We conduct extensive experiments on several important reward functions and demonstrate that the proposed DNO approach can achieve state-of-the-art reward scores within a reasonable time budget for generation.

Diffusion models have demonstrated remarkable performance in generative modeling, but generating samples with specific desiderata remains challenging. Existing solutions --- such as fine-tuning, best-of-n sampling, and gradient-based guidance --- are expensive, inefficient, or limited in applicability. In this work, we propose FK steering, a framework for inference-time steering diffusion models with reward functions. In this work, we introduce FK steering, which applies Feynman-Kac interacting particle systems to the inference-time steering of diffusion models with arbitrary reward functions. FK steering works by generating multiple trajectories, called particles, and resampling particles at intermediate steps based on scores computed using functions called potentials. Potentials are defined using rewards for intermediate states and are chosen such that a high score indicates the particle will yield a high-reward sample. We explore various choices of potentials, rewards, and samplers. Steering text-to-image models with a human preference reward, we find that FK steering outperforms fine-tuned models with just 2 particles. Moreover, FK steering a 0.8B parameter model outperforms a 2.6B model, achieving state-of-the-art performance on prompt fidelity. We also steer text diffusion models with rewards for text quality and rare attributes such as toxicity, and find that FK steering generates lower perplexity text and enables gradient-free control. Overall, inference-time scaling and steering of diffusion models, even training-free, provides significant quality and controllability benefits. Code available [here](https://github.com/zacharyhorvitz/FK-Diffusion-Steering).

Generative models have demonstrated remarkable abilities in generating high-fidelity visual content. In this work, we explore how generative models can further be used not only to synthesize visual content but also to understand the properties of a scene given a natural image. We formulate scene understanding as an inverse generative modeling problem, where we seek to find conditional parameters of a visual generative model to best fit a given natural image. To enable this procedure to infer scene structure from images substantially different than those seen during training, we further propose to build this visual generative model compositionally from smaller models over pieces of a scene. We illustrate how this procedure enables us to infer the set of objects in a scene, enabling robust generalization to new test scenes with an increased number of objects of new shapes. We further illustrate how this enables us to infer global scene factors, likewise enabling robust generalization to new scenes. Finally, we illustrate how this approach can be directly applied to existing pretrained text-to-image generative models for zero-shot multi-object perception. Code and visualizations are at https://energy-based-model.github.io/compositional-inference.

Autoregressive (AR) modeling has achieved remarkable success in natural language processing by enabling models to generate text with coherence and contextual understanding through next token prediction. Recently, in image generation, VAR proposes scale-wise autoregressive modeling, which extends the next token prediction to the next scale prediction, preserving the 2D structure of images. However, VAR encounters two primary challenges: (1) its complex and rigid scale design limits generalization in next scale prediction, and (2) the generator’s dependence on a discrete tokenizer with the same complex scale structure restricts modularity and flexibility in updating the tokenizer. To address these limitations, we introduce FlowAR, a general next scale prediction method featuring a streamlined scale design, where each subsequent scale is simply double the previous one. This eliminates the need for VAR’s intricate multi-scale residual tokenizer and enables the use of any off-the-shelf Variational AutoEncoder (VAE). Our simplified design enhances generalization in next scale prediction and facilitates the integration of Flow Matching for high-quality image synthesis. We validate the effectiveness of FlowAR on the challenging ImageNet-256 benchmark, demonstrating superior generation performance compared to previous methods. Codes is available at \href{https://github.com/OliverRensu/FlowAR}{https://github.com/OliverRensu/FlowAR}.

Panoramic image outpainting acts as a pivotal role in immersive content generation, allowing for seamless restoration and completion of panoramic content. Given the fact that the majority of generative outpainting solutions operates on planar images, existing methods for panoramic images address the sphere nature by soft regularisation during the end-to-end learning, which still fails to fully exploit the spherical content. In this paper, we set out the first attempt to impose the sphere nature in the design of diffusion model, such that the panoramic format is intrinsically ensured during the learning procedure, named as spherical-nested diffusion (SpND) model. This is achieved by employing spherical noise in the diffusion process to address the structural prior, together with a newly proposed spherical deformable convolution (SDC) module to intrinsically learn the panoramic knowledge. Upon this, the proposed method is effectively integrated into a pre-trained diffusion model, outperforming existing state-of-the-art methods for panoramic image outpainting. In particular, our SpND method reduces the FID values by more than 50\% against the state-of-the-art PanoDiffusion method. Codes are publicly available at \url{https://github.com/chronos123/SpND}.

Real-world visual perception requires invariance to diverse transformations, yet current methods rely heavily on specialized architectures or training on predefined augmentations, limiting generalization. We propose FoCal, a test-time, data-driven framework that achieves robust perception by leveraging internet-scale visual priors from foundation models. By generating and optimizing candidate transformations toward visually typical, "canonical" views, FoCal enhances robustness without retraining or architectural changes. Experiments demonstrate improved robustness of CLIP and SAM across challenging transformations, including 2D/3D rotations, illumination shifts (contrast and color), and day-night variations. We also highlight potential applications in active vision. Our approach challenges the assumption that transform-specific training is necessary, instead offering a scalable path to invariance. Our code is available at: https://github.com/sutkarsh/focal.

Diffusion models have transformed generative modeling but suffer from scalability limitations due to computational overhead and inflexible architectures that process all generative stages and tokens uniformly. In this work, we introduce Diff-MoE, a novel framework that combines Diffusion Transformers with Mixture-of-Experts to exploit both temporarily adaptability and spatial flexibility. Our design incorporates expert-specific timestep conditioning, allowing each expert to process different spatial tokens while adapting to the generative stage, to dynamically allocate resources based on both the temporal and spatial characteristics of the generative task. Additionally, we propose a globally-aware feature recalibration mechanism that amplifies the representational capacity of expert modules by dynamically adjusting feature contributions based on input relevance. Extensive experiments on image generation benchmarks demonstrate that Diff-MoE significantly outperforms state-of-the-art methods. Our work demonstrates the potential of integrating diffusion models with expert-based designs, offering a scalable and effective framework for advanced generative modeling.

Recent advances in diffusion models have significantly enhanced the quality of image synthesis, yet they have also introduced serious safety concerns, particularly the generation of Not Safe for Work (NSFW) content. Previous research has demonstrated that adversarial prompts can be used to generate NSFW content. However, such adversarial text prompts are often easily detectable by text-based filters, limiting their efficacy. In this paper, we expose a previously overlooked vulnerability: adversarial image attacks targeting Image-to-Image (I2I) diffusion models. We propose AdvI2I, a novel framework that manipulates input images to induce diffusion models to generate NSFW content. By optimizing a generator to craft adversarial images, AdvI2I circumvents existing defense mechanisms, such as Safe Latent Diffusion (SLD), without altering the text prompts. Furthermore, we introduce AdvI2I-Adaptive, an enhanced version that adapts to potential countermeasures and minimizes the resemblance between adversarial images and NSFW concept embeddings, making the attack more resilient against defenses. Through extensive experiments, we demonstrate that both AdvI2I and AdvI2I-Adaptive can effectively bypass current safeguards, highlighting the urgent need for stronger security measures to address the misuse of I2I diffusion models.

The rise of generative APIs has fueled interest in privacy-preserving synthetic data generation. While the Private Evolution (PE) algorithm generates Differential Privacy (DP) synthetic images using diffusion model APIs, it struggles with few-shot private data due to the limitations of its DP-protected similarity voting approach. In practice, the few-shot private data challenge is particularly prevalent in specialized domains like healthcare and industry. To address this challenge, we propose a novel API-assisted algorithm, Private Contrastive Evolution (PCEvolve), which iteratively mines inherent inter-class contrastive relationships in few-shot private data beyond individual data points and seamlessly integrates them into an adapted Exponential Mechanism (EM) to optimize DP’s utility in an evolution loop. We conduct extensive experiments on four specialized datasets, demonstrating that PCEvolve outperforms PE and other API-assisted baselines. These results highlight the potential of leveraging API access with private data for quality evaluation, enabling the generation of high-quality DP synthetic images and paving the way for more accessible and effective privacy-preserving generative API applications. Our code is available at https://github.com/TsingZ0/PCEvolve.

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.

Antibodies are widely used as therapeutics, but their development requires costly affinity maturation, involving iterative mutations to enhance binding affinity. This paper explores a sequence-only scenario for affinity maturation, using solely antibody and antigen sequences. Recently AlphaFlow wraps AlphaFold within flow matching to generate diverse protein structures, enabling a sequence-conditioned generative model of structure. Building on this, we propose an \textit{alternating optimization} framework that (1) fixes the sequence to guide structure generation toward high binding affinity using a structure-based predictor, then (2) applies inverse folding to create sequence mutations, refined by a sequence-based predictor. A key challenge is the lack of labeled data for training both predictors. To address this, we develop a \textit{co-teaching} module that incorporates valuable information from noisy biophysical energies into predictor refinement. The sequence-based predictor selects consensus samples to teach the structure-based predictor, and vice versa. Our method, \textit{AffinityFlow}, achieves state-of-the-art performance in proof-of-concept affinity maturation experiments.

We explore the potential of \emph{AI-enhanced combinatorial optimization theory}, taking online bipartite matching (OBM) as a case study. In the theoretical study of OBM, the \emph{hardness} corresponds to a performance \emph{upper bound} of a specific online algorithm or any possible online algorithms. Typically, these upper bounds derive from challenging instances meticulously designed by theoretical computer scientists. Zhang et al. (ICML 2024) recently provide an example demonstrating how reinforcement learning techniques enhance the hardness result of a specific OBM model. Their attempt is inspiring but preliminary. It is unclear whether their methods can be applied to other OBM problems with similar breakthroughs. This paper takes a further step by introducing DiMa, a unified and novel framework that aims at understanding the hardness of OBM problems based on denoising diffusion probabilistic models (DDPMs). DiMa models the process of generating hard instances as denoising steps, and optimizes them by a novel reinforcement learning algorithm, named \emph{shortcut policy gradient} (SPG). We first examine DiMa on the classic OBM problem by reproducing its known hardest input instance in literature. Further, we apply DiMa to two well-known variants of OBM, for which the exact hardness remains an open problem, and we successfully improve their theoretical state-of-the-art upper bounds.

We propose a simple, training-free mechanism which explains the generalization behaviour of diffusion models. By comparing pre-trained diffusion models to their theoretically optimal empirical counterparts, we identify a shared local inductive bias across a variety of network architectures. From this observation, we hypothesize that network denoisers generalize through localized denoising operations, as these operations approximate the training objective well over much of the training distribution. To validate our hypothesis, we introduce novel denoising algorithms which aggregate local empirical denoisers to replicate network behaviour. Comparing these algorithms to network denoisers across forward and reverse diffusion processes, our approach exhibits consistent visual similarity to neural network outputs, with lower mean squared error than previously proposed methods.