论文检索

Applications · Computer Vision

Zefeng He, Xiaoye Qu, Yafu Li, Tong Zhu, Qipeng Guo, Muxin Fu, Siyuan Huang, Yu Cheng

While recent Multimodal Large Language Models (MLLMs) have attained significant strides in multimodal reasoning, their reasoning processes remain predominantly text-centric and fail to visualize and track intermediate visual states during the reasoning process, leading to suboptimal performance in complex long-horizon, vision-centric tasks. Moving beyond the constraints of text-centric reasoning, we establish Generative Multimodal Reasoning as a novel paradigm and introduce DiffThinker, a diffusion-based reasoning framework. Conceptually, DiffThinker reformulates multimodal reasoning as a native generative image-to-image task, where the iterative denoising trajectory naturally serves as a visual reasoning path. This enables the model to track the evolution of visual information throughout the reasoning process. We perform a systematic comparison between DiffThinker and MLLMs, providing the first in-depth investigation into the intrinsic characteristics of this paradigm, revealing four core properties: efficiency, controllability, native parallelism, and collaboration. Extensive experiments across seven tasks demonstrate that DiffThinker significantly outperforms leading closed-source models, including GPT-5 (+314.2%) and Gemini-3-Flash (+111.6%), as well as the fine-tuned Qwen3-VL-32B baseline (+39.0%), highlighting Generative Multimodal Reasoning as a promising approach for vision-centric reasoning.

Patrick Pynadath, Jiaxin Shi, Ruqi Zhang

While continuous diffusion has shown remarkable success in continuous domains such as image generation, its direct application to discrete data has underperformed pure discrete formulations. To understand this gap, we introduce *token identifiability*, an analytical framework characterizing how Gaussian noise corrupts discrete data through two mechanisms: *discrete identity corruption* and *continuous rank degradation*. We reveal that these mechanisms scale differently with vocabulary size, creating a *temporal dissonance* that forces a tradeoff between learning continuous geometry and discrete structure. To address this, we propose **CANDI** (**C**ontinuous **AN**d **DI**screte diffusion), a hybrid framework that decouples discrete and continuous corruption, enabling simultaneous learning of both. This unlocks the benefits of continuous diffusion for discrete spaces: on controlled generation, CANDI enables classifier-based guidance with off-the-shelf classifiers through simple gradient addition; on text generation, CANDI outperforms masked diffusion at low NFE, demonstrating the value of learning continuous gradients for discrete spaces.

Deep Learning · Generative Models and Autoencoders

Yangtian Zhang, Zhe Wang, Arthur Gretton, ZHITAO YING, David van Dijk, Michalis Titsias, Jiaxin Shi

Non-monotonic sequence generation methods, such as masked diffusion models, provide a flexible alternative to left-to-right autoregressive modeling by allowing tokens to be generated in non-fixed and prescribed orders. Despite their practical advantages, most existing non-monotonic models are order-agnostic and rely on a fixed-length masked token grid, limiting their ability to support variable-length generation and adaptive insertion order. In this work, we introduce a probabilistic framework for learning insertion order in variable-length insertion models. We formalize a bijective correspondence between insertion trajectories and permutations, which enables an exact reparameterization of the data likelihood as a sum over permutations. Building on this result, we propose the **Insertion Process (IP)**, a stochastic generative model that jointly learns *where* to insert, *what* to insert, and *when* to terminate, trained via permutation-based variational inference. Unlike prior masked or fixed-canvas approaches, IP natively supports variable-length generation and learns data-driven preferences over insertion orders. Experiments on planning benchmarks and molecular SMILES generation demonstrate that learning insertion order improves both modeling quality and generalization in domains without a canonical left-to-right structure.

Applications · Computer Vision

Runhui Huang, Jie Wu, Rui Yang, Zhe Liu, Hengshuang Zhao

In this paper, we propose **AlphaGRPO**, a novel framework that applies Group Relative Policy Optimization (GRPO) to AR-Diffusion Unified Multimodal Models (UMMs) to enhance multimodal generation capabilities without relying on external knowledge injection. Our approach unlocks the model's intrinsic potential to perform advanced reasoning tasks: Reasoning Text-to-Image Generation, where the model actively infers implicit user intents, and Self-Reflective Refinement, where it autonomously diagnoses and corrects misalignments in generated outputs. To address the challenge of providing stable supervision for real-world multimodal generation, we introduce the Decompositional Verifiable Reward (**DVReward**). Unlike holistic scalar rewards, DVReward utilizes an LLM to decompose complex user requests into atomic, verifiable semantic and quality questions, which are then evaluated by a general MLLM to provide reliable and interpretable feedback. Extensive experiments demonstrate that AlphaGRPO yields robust improvements across multimodal generation benchmarks, including GenEval, TIIF-Bench, DPG-Bench and WISE, while also achieving significant gains in editing tasks on GEdit without training on editing tasks. These results validate that our self-reflective reinforcement approach effectively leverages inherent understanding to guide high-fidelity generation.

Deep Learning · Foundation Models

Sujung Hong, Chanyong Yoon, Seong Jae Hwang

Large diffusion vision–language models (LDVLMs) have recently demonstrated competitive performance on multimodal tasks, emerging as a promising alternative to autoregressive models. They enable parallel decoding for efficient inference and leverage bidirectional attention to capture global context. Despite these advances, their behavior under long-form generation remains underexplored. In this work, we show that existing LDVLMs suffer from repetitive generation and lead to degraded visual grounding. Through analysis, we identify two underlying causes of these failures. First, repetitive generation originates from a mask token prior. Because generation tokens are initialized as mask tokens, their hidden representations progressively drift toward a shared prior direction over generation steps. Second, a fundamental misalignment exists between the positional attention bias and the iterative unmasking process. This discrepancy suppresses the model's attention toward informative visual tokens, leading to degradation in visual grounding. Based on these insights, we propose a training-free approach that mitigates both issues. Specifically, we introduce Mask Prior Suppression and Monotonic RoPE Scaling, which mitigate mask prior drift and positional attention collapse during decoding. Experiments on general multimodal benchmarks and visual grounding tasks demonstrate improvements over baseline LDVLMs, with robust gains on long-form description benchmarks. Overall, our results show that these failures can be effectively addressed with a lightweight, plug-and-play strategy that requires no additional training and generalizes across diverse LDVLM architectures.

Deep Learning · Generative Models and Autoencoders

Hao Fu, Tianyu Su, Meng Liu, Chenfang Yang, Tian Gan

Diffusion models have shown impressive capabilities in text-to-image synthesis, but multi-concept personalized generation remains challenging, particularly in aligning multiple reference concepts while preserving fidelity. In this work, we propose a novel framework that addresses this challenge with a two-stage Sketch-to-Rendering process, utilizing Dual Optimal Transport (OT) for structural alignment and texture injection. Our approach consists of two key components: Structural Guidance via OT: Ensures shape alignment by using mass-preserving OT for spatial consistency, and Texture Injection via Geometry-Guided OT: Leverages low-frequency structure alignment to inject high-frequency texture details via OT-based residual transfer, preserving texture fidelity without distorting structure. Extensive experiments demonstrate that our method significantly enhances both conceptual fidelity and visual quality in multi-concept generation. Ablation studies further confirm the effectiveness of the proposed optimal transport guidance and the decoupling of structure and texture during the generation process.

Deep Learning · Generative Models and Autoencoders

Tong Yang, Moonkyung Ryu, Chih-wei Hsu, Guy Tennenholtz, Yuejie Chi, Craig Boutilier, Bo Dai

Controllable diffusion generation often relies on various heuristics that are seemingly disconnected without a unified understanding. We bridge this gap with Diffusion Controller (DiffCon), a unified control-theoretic view that casts reverse diffusion sampling as state-only stochastic control within (generalized) linearly-solvable Markov Decision Processes (LS-MDPs). Under this framework, control acts by reweighting the pretrained reverse-time transition kernels, balancing terminal objectives against an $f$-divergence cost. From the resulting optimality conditions, we derive practical reinforcement learning methods for diffusion fine-tuning: (i) $f$-divergence-regularized policy-gradient updates, including a PPO-style rule, and (ii) a regularizer-determined reward-weighted regression objective with a minimizer-preservation guarantee under the Kullback–Leibler (KL) divergence. The LS-MDP framework further implies a principled model form: the optimal score decomposes into a fixed pretrained baseline plus a lightweight control correction, motivating a side-network parameterization conditioned on exposed intermediate denoising outputs, enabling effective \emph{gray-box adaptation} with a frozen backbone. Experiments on Stable Diffusion v1.4 across supervised and reward-driven finetuning show consistent gains in preference-alignment win rates and improved quality–efficiency trade-offs versus gray-box baselines and even the parameter-efficient white-box adapter LoRA.

Deep Learning · Generative Models and Autoencoders

Jaeyeon Kim, Seunggeun Kim, Taekyun Lee, David Pan, Hyeji Kim, Sham Kakade, Sitan Chen

A natural desideratum for generative models is \emph{self-correction}--detecting and revising low-quality tokens at inference. While Masked Diffusion Models (MDMs) have emerged as a promising approach for generative modeling in discrete spaces, their capacity for self-correction remains poorly understood. Prior attempts to incorporate self-correction into MDMs either require overhauling MDM architectures/training or rely on imprecise proxies for token quality, limiting their applicability. Motivated by this, we introduce PRISM--Plug-in Remasking for Inference-time Self-correction of Masked Diffusions--a lightweight, model-agnostic approach that applies to any pretrained MDM. Theoretically, PRISM defines a self-correction loss that provably learns per-token quality scores, without RL or a verifier. These quality scores are computed in the same forward pass with MDM and used to detect low-quality tokens. Empirically, PRISM advances MDM inference across domains and scales: Sudoku; unconditional text (170M); and code with LLaDA (8B).

Reinforcement Learning · Deep RL

Haitong Ma, Ofir Nabati, Aviv Rosenberg, Bo Dai, Oran Lang, Craig Boutilier, Na Li, Shie Mannor, Lior Shani, Guy Tennenholtz

Reinforcement learning (RL) struggles to scale to large, combinatorial action spaces common in many real-world problems. This paper introduces a novel framework for training discrete diffusion models as highly effective policies in these complex settings. Our key innovation is an efficient online training process that ensures stable and effective policy improvement. By leveraging policy mirror descent (PMD) to define an ideal, regularized target policy distribution, we frame the policy update as a distributional matching problem, training the expressive diffusion model to replicate this stable target. This decoupled approach stabilizes learning and significantly enhances training performance. Our method achieves state-of-the-art results and superior sample efficiency across a diverse set of challenging combinatorial benchmarks, including DNA sequence generation, RL with macro-actions, and multi-agent systems. Experiments demonstrate that our diffusion policies attain superior performance compared to other baselines. Crucially, our extensive empirical analysis reveals a key trade-off: FKL demonstrates superior sample efficiency and faster initial convergence, whereas RKL ensures greater training stability and higher asymptotic performance.

Optimization · Non-Convex

Shutong Ding, Yimiao Zhou, Ke Hu, Xi Yao, Junchi Yan, Xiaoying Tang, Ye Shi

Recent advances in diffusion models show promising potential to accelerate nonconvex problem solving by leveraging their multimodality. However, most existing diffusion-based optimization approaches rely on supervised learning and lack a mechanism to enforce constraint satisfaction, which is required in real-world applications. In that case, we investigate and theoretically analyze the inherent problem of supervised diffusion solvers and identify the distributional misalignment problem, i.e., the generated solution distribution often exhibits low probability mass on the feasible region. To resolve this issue, we propose DiOpt, a new diffusion-based learning framework for constrained nonconvex optimization, which effectively learns the mapping from noise to the constraint region. Specifically, this framework operates in two distinct phases: an initial warm-start phase, implemented via supervised learning, followed by a bootstrapping training phase. This dual-phase architecture is designed to iteratively refine solutions, thereby improving the objective function with high constraint satisfaction. Finally, we also employ a solution selection technique in inference for better optimality. Notably, DiOpt is the first successful integration of the diffusion solver in constrained nonconvex optimization. Evaluations on diverse nonconvex tasks demonstrate the superiority of DiOpt in both optimality and constraint satisfaction.

Reinforcement Learning · Online

Shutong Ding, Zejia Zhong, Zhongyi Wang, Ke Hu, Bikang Pan, Jingya Wang, Ye Shi

Recent advances in reinforcement learning (RL) have achieved great successes by leveraging the multimodality and exploration capability of diffusion policies. Among these approaches, one representative branch focuses on the weighted-based policy optimization. This design enables better exploration capability of diffusion model, particularly at the beginning of training, but suffer from the low exploitation in Q-value information, resulting in a slow policy convergence. Another branch pay attention to gradient-based policy optimization, which sufficiently exploit the gradient of Q function yet tend to collapse into a unimodal policy with low diversity. To address this issue, we propose CGPO, \textbf{C}ritic-\textbf{G}uided diffusion \textbf{P}olicy \textbf{O}ptimization, which effectively balances exploration and exploitation with the training-free guidance technique integrated into the denoising process of diffusion policy. Concretely, CGPO steers action generation toward high-value regions defined by the critic network and uses the guided actions as regression objectives. In this manner, CGPO reduces the time required to obtain high-quality actions and improves final performance with better balance between exploration-exploitation tradeoff. We validate the effectiveness of CGPO on 5 MuJoCo locomotion tasks, and CGPO achieves state-of-the-art performance compared with existing diffusion-based RL methods. Notably, CGPO is the first success to incorporate diffusion policy into real-world RL, with its superior performance on Franka robot arm grasping tasks.

Applications · Chemistry, Physics, and Earth Sciences

Ruikun Li, Huandong Wang, Jingtao Ding, Yuan Yuan, Qingmin Liao, Yong Li

Data-driven dynamics prediction often fails under environmental shifts, while traditional fine-tuning remains computationally prohibitive for hardware-constrained or data-scarce applications. We propose DynaDiff, a generative meta-learning framework that transitions the paradigm from gradient-based tuning or modulation to direct weight-space generation. Specifically, we first abstract expert weights as novel weight graphs, utilizing multi-head attention to explicitly capture topological coupling within weights. Subsequently, we design a functional loss to ensure that the generated models achieve consistency with expert models in physical behavior. Finally, we develop a dynamics-informed prompter that extracts cross-domain physical and spectral features from observation sequences to condition the diffusion model. Experiments demonstrate that DynaDiff boosts average prediction accuracy by 10.78\% over competitive baselines. Furthermore, by pre-constructing a model zoo of expert predictors, we amortize the fine-tuning overhead into a one-time offline cost, significantly boosting deployment efficiency in new environments.

Social Aspects · Safety

Nicola Novello, Federico Fontana, Luigi Cinque, Deniz Gunduz, Andrea Tonello

Most current methods for unlearning concepts in text-to-image diffusion models rely on mean squared error-based loss functions to align target distributions with anchors. In this paper, we generalize this idea into a unified $f$-divergence-based framework that recovers the standard mean squared error loss as a specific instance. By generalizing the loss function, we theoretically analyze and numerically validate how different $f$-divergences impact the gradient magnitude and the convergence properties of the algorithm, affecting the quality of unlearning. The proposed unified framework offers a flexible paradigm for selecting the optimal divergence based on the application and user goal, allowing for finer control over the trade-off between unlearning efficacy and generative fidelity.

Deep Learning · Generative Models and Autoencoders

Yuanbang Liang, Zhengwen Chen, Yu-Kun Lai

Latent Diffusion Models (LDMs) achieve high-fidelity synthesis but suffer from latent space brittleness, causing discontinuous semantic jumps during editing. We introduce a Riemannian framework to diagnose this instability by analyzing the generative Jacobian, decomposing geometry into *Local Scaling* (capacity) and *Local Complexity* (curvature). Our study uncovers a **``Geometric Decoupling"**: while curvature in normal generation functionally encodes image detail, OOD generation exhibits a functional decoupling where extreme curvature is wasted on unstable semantic boundaries rather than perceptible details. This geometric misallocation identifies ``Geometric Hotspots" as the structural root of instability, providing a robust intrinsic metric for diagnosing generative reliability.

Applications · Computer Vision

Fuyun Wang, Yuanzhi Wang, Xu Guo, Sujia Huang, Tong Zhang, Dan Wang, Xin Liu, Hui Yan, Zhen Cui

Synthesizing realistic and diverse anomalous samples from limited data is vital for robust model generalization. However, existing methods struggle to reconcile fidelity and diversity, often hampered by distribution misalignment and overfitting, respectively. To mitigate this, we introduce Anomaly Preference Optimization (APO), a novel paradigm that reformulates anomaly generation as a preference learning problem. Central to our approach is an implicit preference alignment mechanism that leverages real anomalies as positive references, deriving optimization signals directly from denoising trajectory deviations without requiring costly human annotation. Furthermore, we propose a Time-Aware Capacity Allocation module that dynamically distributes model capacity along the diffusion timeline— prioritizing structural diversity during highnoise phases while enhancing fine-grained fidelity in low-noise stages. During inference, a hierarchical sampling strategy modulates the coherencealignment trade-off, enabling precise control over generation. Extensive experiments demonstrate that significantly outperforms existing baselines, achieving state-of-the-art performance in both realism and diversity.

Reinforcement Learning · Deep RL

Huy Le, Onur Celik, Denis Blessing, Tai Hoang, Claas Voelcker, Axel Brunnbauer, Felix Richter, Michael Volpp, Gerhard Neumann

Reinforcement learning with massively parallel simulations has become an emerging trend; however, most existing approaches still rely on simple Gaussian policy parameterizations. Diffusion models provide a more expressive policy class and have shown strong performance on challenging control problems, yet most diffusion-based RL methods are designed for offline or off-policy training. In this work, we ask whether diffusion policies can be trained effectively in the massively parallel, on-policy regime. To this end, we introduce Trust-region Diffusion Policies (TruDi), which enables diffusion policies for on-policy RL with massively parallel simulations. This setting is particularly challenging because the data distribution changes quickly across updates, making stable training with complex policies difficult. TruDi addresses this by integrating a trust-region optimization rule to enforce a KL-divergence constraint over the entire diffusion trajectory, rather than only at the final denoising step. Empirically, we evaluate TruDi on a diverse set of 4 massively parallel RL benchmarks comprising a total of 73 tasks. Across these tasks, TruDi consistently outperforms or is on-par with strong baselines on standard tasks and achieves clear gains on more challenging humanoid control tasks, establishing a strong new baseline for massively parallel on-policy RL.

Deep Learning · Graph Neural Networks

Wei Huang, Hanchen Wang, Dong Wen, Wenjie Zhang, Ying Zhang, Xuemin Lin

Graph Edit Distance (GED), which aims to find an edit path with minimum number of edit operations to transform one graph into another, is a fundamental NP-hard problem and a widely used graph similarity measure. Recent matching-based hybrid approaches have demonstrated better scalability than A* search-based hybrids by reformulating GED as a graph matching problem. In these methods, a neural network predicts a single deterministic node matching matrix, from which top-$k$ node mappings are extracted iteratively to derive candidate edit paths. However, these methods often suffer from highly correlated candidates that easily lead to suboptimal solutions, while the iterative extraction becomes inefficient for large $k$. In this paper, we propose DiffGED, the first generative approach for GED computation. Specifically, we formulate the graph matching problem as a generative task, and employ a diffusion-based model to generate multiple diverse node matching matrices simultaneously, from which diverse node mappings can be efficiently extracted. The generative diversity introduced by the diffusion process enables DiffGED to avoid suboptimal solutions and achieve superior solution quality close to the exact solution. Experiments on real-world datasets show that DiffGED generates multiple diverse edit paths with accuracy comparable to exact solutions, while running faster than existing hybrid approaches.

Applications · Computer Vision

Yunhong Lu, Qichao Wang, Hengyuan Cao, Xiaoyin Xu, Min Zhang

Existing preference datasets for text-to-image (T2I) models typically store only the final winner/loser images. This representation is insufficient for rectified flow (RF) models, whose generation is naturally indexed by a specific prior noise sample and follows a nearly straight denoising trajectory. In contrast, prior DPO-style alignment for diffusion models commonly estimates trajectories using an independent forward noising process, which can be mismatched to the true reverse dynamics and introduces unnecessary variance. We propose Prior Noise-Aware Preference Optimization (PNAPO), an off-policy alignment framework specialized for rectified flow. PNAPO augments preference data by retaining the paired prior noises used to generate each winner/loser image, turning the standard (prompt, winner, loser) triplet into a sextuple. Leveraging the straight-line property of RF, we estimate intermediate states via noise–image interpolation, which constrains the trajectory estimation space and yields a tighter surrogate objective for preference optimization. In addition, we introduce a dynamic regularization strategy that adapts the DPO temperature/regularization based on (i) the reward gap between winner and loser and (ii) training progress, improving stability and sample efficiency. Experiments on state-of-the-art RF T2I backbones (FLUX.1-dev and SD3-Medium) show that PNAPO consistently improves preference metrics while substantially reducing training compute compared to Diffusion-DPO.

Deep Learning · Generative Models and Autoencoders

Daniil Selikhanovych, David Li, Aleksei Leonov, Nikita Gushchin, Sergei Kushneriuk, Alexander Filippov, Evgeny Burnaev, Iaroslav Koshelev, Aleksandr Korotin

Diffusion models for super-resolution (SR) produce high-quality visual results but require expensive computational costs. Despite the development of several methods to accelerate diffusion-based SR models, some (e.g., SinSR) fail to produce realistic perceptual details, while others (e.g., OSEDiff) may hallucinate non-existent structures. To overcome these issues, we present **RSD**, a new distillation method for ResShift. Our method is based on training the student network to produce images such that a new fake ResShift model trained on them will coincide with the teacher model. RSD achieves single-step restoration and outperforms the teacher by a noticeable margin in various perceptual metrics (LPIPS, CLIPIQA, MUSIQ). We show that our distillation method can surpass SinSR, the other distillation-based method for ResShift, making it on par with state-of-the-art diffusion SR distillation methods with limited computational costs in terms of perceptual quality. Compared to SR methods based on pre-trained text-to-image models, RSD produces competitive perceptual quality and requires fewer parameters, GPU memory, and training cost. We provide experimental results on various real-world and synthetic datasets, including RealSR, RealSet65, DRealSR, ImageNet, and DIV2K.

Deep Learning · Graph Neural Networks

Zhizhi Yu, Jiachen Liu, Qingyu Li, Dongxiao He, Di Jin

Representation learning on text-attributed graphs (TAGs) is crucial for real-world applications, as it enables effective modeling of both rich node semantics and complex graph structure. Nevertheless, this task is intrinsically challenging due to structural–semantic mismatch stemming from divergent modality distributions, as well as dual-source noise inherent in node textual content and graph structure. Existing approaches often enforce a rigid fusion of distinct modalities while overlooking their inherent noise, which inevitably results in persistent distribution gaps and amplifies mixed interference during information propagation. To address these issues, we propose UDPD, an Uncertainty-modulated Dual-Path Diffusion model for robust text-attributed graph learning. Specifically, we first employ a dual-perspective node encoding strategy to separately learn semantic and structural embeddings. We then introduce a cooperative diffusion paradigm with parallel semantic and structural branches, where mutual guidance enables progressive alignment of different distributions while effectively suppressing modality inherent noise. Crucially, the reverse process is guided by node uncertainty, which is used to adaptively modulate cross-branch interaction strength, ensuring robust coupling and maximizing denoising effectiveness. Extensive experiments on five public benchmarks demonstrate the effectiveness and superiority of our UDPD over state-of-the-art baselines.