Traditional knowledge distillation relies on simple MSE or KL divergence losses that fail to capture the complex distributional relationships between teacher and student model representations. We propose FlowDistill, a novel distillation framework that employs normalizing flows to model and transfer the intricate knowledge distributions from teacher to student models. Our approach introduces three key innovations: (1) Invertible Knowledge Mapping using continuous normalizing flows (CNFs) to learn bijective transformations between teacher and student representation spaces, enabling precise knowledge transfer without information loss, (2) Flow-Guided Progressive Distillation that gradually increases the complexity of knowledge transfer by learning hierarchical flow transformations from simple to complex distributions, and (3) Conditional Flow Networks that adapt knowledge transfer based on input context and task requirements. Unlike previous diffusion-based distillation methods such as DiffKD that suffer from computational overhead due to iterative denoising processes and information loss during noise addition, our flow-based approach provides exact invertible transformations with significantly reduced computational cost. Extensive experiments on ImageNet classification, COCO object detection, and Cityscapes semantic segmentation demonstrate that FlowDistill achieves superior performance with 2.1% accuracy improvement over DiffKD on ResNet-34 to ResNet-18 distillation while reducing inference time by 3.5×. Our method establishes new state-of-the-art results across multiple distillation benchmarks and provides theoretical guarantees for lossless knowledge transfer through invertible flow transformations.
论文检索
输入标题、作者或关键词，从 9,256 篇学术成果中精准定位
Accurate and efficient simulations of physical phenomena governed by partial differential equations (PDEs) are important for scientific and engineering progress. While traditional numerical solvers are powerful, they are often computationally expensive. Recently, data-driven methods have emerged as alternatives, but they frequently suffer from error accumulation and limited physical consistency, especially in multiphysics and complex geometries. To address these challenges, we propose PEGNet, a Physics-Embedded Graph Network that incorporates PDE-guided message passing to redesign the graph neural network architecture. By embedding key PDE dynamics like convection, viscosity, and diffusion into distinct message functions, the model naturally integrates physical constraints into its forward propagation, producing more stable and physically consistent solutions. Additionally, a hierarchical architecture is employed to capture multi-scale features, and physical regularization is integrated into the loss function to further enforce adherence to governing physics. We evaluated PEGNet on benchmarks, including custom datasets for respiratory airflow and drug delivery, showing significant improvements in long-term prediction accuracy and physical consistency over existing methods.
Most state-of-the-art time series imputation methods can leverage textual information to improve imputation quality, but they often struggle because they fail to effectively filter noisy information from large language model (LLM) derived textual information. Some existing solutions only filter over the entire token set, which can introduce erroneous conditional constraints, extreme token frequency effects and increased computational complexity. To address this, we propose CaT-Diff, a novel cascaded text-enhanced diffusion model for probabilistic imputation of multivariate time series under Missing Not At Random (MNAR) scenarios. To suppress irrelevant semantics and focus on context most predictive of missing values, CaT-Diff introduces an innovative Hierarchical Semantic Filter (HSF) that collaborates with a Mixture-of-Experts (MoE) Network. The MoE projects heterogeneous text embeddings into the time series latent space, and the HSF cascade-filters text embeddings from the segment level to the token level, thereby avoiding the pitfalls of direct token-level filtering and reducing overhead. We also incorporate a lightweight Missing Mechanism Estimator, jointly optimized with the denoising network to explicitly capture MNAR missingness patterns. Extensive tests on nine domains show that CaT-Diff outperforms state-of-the-art baselines. Our work presents a new approach for selectively fusing LLM-derived textual information.
Diffusion models have advanced from text-to-image (T2I) to image-to-image (I2I) generation by incorporating structured inputs such as depth maps, enabling fine-grained spatial control. However, existing methods either train separate models for each condition or rely on unified architectures with entangled representations, resulting in poor generalization and high adaptation costs for novel conditions. To this end, we propose DivControl, a decomposable pretraining framework for unified controllable generation and efficient adaptation. DivControl factorizes ControlNet via SVD into basic components—pairs of singular vectors—which are disentangled into condition-agnostic learngenes and condition-specific tailors through knowledge diversion during multi-condition training. Knowledge diversion is implemented via a dynamic gate that performs soft routing over tailors based on the semantics of condition instructions, enabling zero-shot generalization and parameter-efficient adaptation to novel conditions. To further improve condition fidelity and training efficiency, we introduce a representation alignment loss that aligns condition embeddings with early diffusion features. Extensive experiments demonstrate that DivControl achieves state-of-the-art controllability with 36.4× less training cost, while simultaneously improving average performance on basic conditions. It also delivers strong zero-shot and few-shot performance on unseen conditions, demonstrating superior scalability, modularity, and transferability.
OT-ALD: Aligning Latent Distributions with Optimal Transport for Accelerated Image-to-Image Translation
PDF ↗The Dual Diffusion Implicit Bridge (DDIB) is an emerging image-to-image (I2I) translation method that preserves cycle consistency while achieving strong flexibility. It links two independently trained diffusion models (DMs) in the source and target domains by first adding noise to a source image to obtain a latent code, then denoising it in the target domain to generate the translated image. However, this method faces two key challenges: (1) low translation efficiency, and (2) translation trajectory deviations caused by mismatched latent distributions. To address these issues, we propose a novel I2I translation framework, OT-ALD, grounded in optimal transport (OT) theory, which retains the strengths of DDIB-based approach. Specifically, we compute an OT map from the latent distribution of the source domain to that of the target domain, and use the mapped distribution as the starting point for the reverse diffusion process in the target domain. Our error analysis confirms that OT-ALD eliminates latent distribution mismatches. Moreover, OT-ALD effectively balances faster image translation with improved image quality. Experiments on four translation tasks across three high-resolution datasets show that OT-ALD improves sampling efficiency by 20.29% and reduces the FID score by 2.6 on average compared to the top-performing baseline models.
Open-Set Domain Generalization (OSDG) aims to generalize over unseen target domains containing open classes, and the core challenge lies in identifying unknown samples never encountered during training. Recently, CLIP has exhibited impressive performance in OSDG, while it still falls into the dilemma between structural risk of known classes and open space risk from unknown classes, and easily suffers from over-confidence, especially when distinguishing known-like unknown samples. To this end, we propose a Semantic-enhanced CLIP (SeeCLIP) framework that leverages fine-grained semantics to boost unknown detection, so as to accommodate both risks and enable precise discrimination among categories. In SeeCLIP, we propose a semantic-aware prompt enhancement module to extract fine-grained key semantic features, and establish a fine-grained vision-language alignment. Duplex contrastive learning is proposed for prompt learning, which jointly optimizes duplex losses such that the unknown prompt is similar to known prompts, yet exhibits key semantic differences. We also design a semantic-guided diffusion module to enable nuanced capture in generation. By injecting perturbed key semantics into a diffusion model as control conditions, it generates the closest unknowns or pseudo-open samples with high similarity yet low belongingness to known classes. We formulate a generalization bound for OSDG, and show that SeeCLIP can achieve a lower generalization risk. Extensive experiments on benchmark datasets validate the superiority of SeeCLIP, it outperforms the SOTA methods by nearly 3% on accuracy and 5% on H-index, respectively.
Driving world models are used to simulate futures by video generation based on the condition of the current state and actions. However, current models often suffer serious error accumulations when predicting the long-term future, which limits practical applications. Recent studies utilize the Diffusion Transformer (DiT) as the backbone of driving world models to improve learning flexibility. However, these models are always trained on short video clips, and multiple roll-out generations struggle to produce consistent and reasonable long videos due to the training-inference gap. To this end, we propose several solutions to build a simple yet effective long-term driving world model. First, we hierarchically decouple world model learning into large motion learning and bidirectional continuous motion learning. Then, considering the continuity of driving scenes, we propose a simple distillation method where fine-grained video flows are self-supervised signals for coarse-grained flows. The distillation is designed to improve the coherence of infinite video generation. The coarse-grained and fine-grained modules are coordinated to generate long-term and temporally coherent videos. On NuScenes, compared with the state-of-the-art front-view models, our model improves FVD by 27% and reduces inference time by 85% for the video task of generating 110+ frames.
Generating co-speech gestures in real time requires both temporal coherence and efficient sampling. We introduce a novel framework for streaming gesture generation that extends Rolling Diffusion models with structured progressive noise scheduling, enabling seamless long-sequence motion synthesis while preserving realism and diversity. Our framework is universally compatible with existing diffusion-based gesture generation model, transforming them into streaming methods capable of continuous generation without requiring post-processing. We evaluate our framework on ZEGGS and BEAT, strong benchmarks for real-world applicability. Applied to state-of-the-art baselines on both datasets, it consistently outperforms them, demonstrating its effectiveness as a generalizable and efficient solution for real-time co-speech gesture synthesis. We further propose Rolling Diffusion Ladder Acceleration (RDLA), a new approach that employs a ladder-based noise scheduling strategy to simultaneously denoise multiple frames. This significantly improves sampling efficiency while maintaining motion consistency, achieving up to a 4× speedup with high visual fidelity and temporal coherence in our experiments. Comprehensive user studies further validate our framework’s ability to generate realistic, diverse gestures closely synchronized with the audio input.
Flow matching casts sample generation as learning a continuous-time velocity field that transports noise to data. Existing flow matching networks typically predict each point's velocity independently, considering only its location and time along its flow trajectory, and ignoring neighboring points. However, this pointwise approach may overlook correlations between points along the generation trajectory that could enhance velocity predictions, thereby improving downstream generation quality. To address this, we propose Graph Flow Matching (GFM), a lightweight enhancement that decomposes the learned velocity into a reaction term -- any standard flow matching network -- and a diffusion term that aggregates neighbor information via a graph neural module. This reaction-diffusion formulation retains the scalability of deep flow models while enriching velocity predictions with local context, all at minimal additional computational cost. Operating in the latent space of a pretrained variational autoencoder, GFM consistently improves Fréchet Inception Distance (FID) and recall across five image generation benchmarks (LSUN Church, LSUN Bedroom, FFHQ, AFHQ-Cat, and CelebA-HQ at 256 × 256), demonstrating its effectiveness as a modular enhancement to existing flow matching architectures.
Single-channel audio separation aims to separate individual sources from a single-channel mixture. Most existing methods rely on supervised learning with synthetically generated paired data. However, obtaining high-quality paired data in real-world scenarios is often difficult. This data scarcity can degrade model performance under unseen conditions and limit generalization ability. To this end, in this work, we approach this problem from an unsupervised perspective, framing it as a probabilistic inverse problem. Our method requires only diffusion priors trained on individual sources. Separation is then achieved by iteratively guiding an initial state toward the solution through reconstruction guidance. Importantly, we introduce an advanced inverse problem solver specifically designed for separation, which mitigates gradient conflicts caused by interference between the diffusion prior and reconstruction guidance during inverse denoising. This design ensures high-quality and balanced separation performance across individual sources. Additionally, we find that initializing the denoising process with an augmented mixture instead of pure Gaussian noise provides an informative starting point that significantly improves the final performance. To further enhance audio prior modeling, we design a novel time–frequency attention-based network architecture that demonstrates strong audio modeling capability. Collectively, these improvements lead to significant performance gains, as validated across speech–sound event, sound event, and speech separation tasks.
Diffusion models have shown great promise in data generation, yet generating time series data remains challenging due to the need to capture complex temporal dependencies and structural patterns. In this paper, we present TSGDiff, a novel framework that rethinks time series generation from a graph-based perspective. Specifically, we represent time series as dynamic graphs, where edges are constructed based on Fourier spectrum characteristics and temporal dependencies. A graph neural network-based encoder-decoder architecture is employed to construct a latent space, enabling the diffusion process to model the structural representation distribution of time series effectively. Furthermore, we propose the Topological Structure Fidelity (Topo-FID) score, a graph-aware metric for assessing the structural similarity of time series graph representations. Topo-FID integrates two sub-metrics: Graph Edit Similarity, which quantifies differences in adjacency matrices, and Structural Entropy Similarity, which evaluates the entropy of node degree distributions. This comprehensive metric provides a more accurate assessment of structural fidelity in generated time series. Experiments on real-world datasets demonstrate that TSGDiff generates high-quality synthetic time series data generation, faithfully preserving temporal dependencies and structural integrity, thereby advancing the field of synthetic time series generation.
Diffusion and flow matching models have recently emerged as promising approaches for peptide binder design. Despite their progress, these models still face two major challenges. First, categorical sampling of discrete residue types collapses their continuous parameters into one-hot assignments, while continuous variables (e.g., atom positions) evolve smoothly throughout the generation process. This mismatch disrupts the update dynamics and results in suboptimal performance. Second, current models assume unimodal distributions for side-chain torsion angles, which conflicts with the inherently multimodal nature of side-chain rotameric states and limits prediction accuracy. To address these limitations, we introduce PepBFN, the first Bayesian flow network for full-atom peptide design that directly models parameter distributions in fully continuous space. Specifically, PepBFN models discrete residue types by learning their continuous parameter distributions, enabling joint and smooth Bayesian updates with other continuous structural parameters. It further employs a novel Gaussian mixture-based Bayesian flow to capture the multimodal side-chain rotameric states and a Matrix Fisher-based Riemannian flow to directly model residue orientations on the SO(3) manifold. Together, these parameter distributions are progressively refined via Bayesian updates, yielding smooth and coherent peptide generation. Experiments on side-chain packing, reverse folding, and binder design tasks demonstrate the strong potential of PepBFN in computational peptide design.
CHDP: Cooperative Hybrid Diffusion Policies for Reinforcement Learning in Parameterized Action Space
PDF ↗Hybrid action space, which combines discrete choices and continuous parameters, is prevalent in domains such as robot control and game AI. However, efficiently modeling and optimizing hybrid discrete-continuous action space remains a fundamental challenge, mainly due to limited policy expressiveness and poor scalability in high-dimensional settings. To address this challenge, we view the hybrid action space problem as a fully cooperative game and propose a Cooperative Hybrid Diffusion Policies (CHDP) framework to solve it. CHDP employs two cooperative agents that leverage a discrete and a continuous diffusion policy, respectively. The continuous policy is conditioned on the discrete action's representation, explicitly modeling the dependency between them. This cooperative design allows the diffusion policies to leverage their expressiveness to capture complex distributions in their respective action spaces. To mitigate the update conflicts arising from simultaneous policy updates in this cooperative setting, we employ a sequential update scheme that fosters co-adaptation. Moreover, to improve scalability when learning in high-dimensional discrete action space, we construct a codebook that embeds the action space into a low-dimensional latent space. This mapping enables the discrete policy to learn in a compact, structured space. Finally, we design a Q-function-based guidance mechanism to align the codebook's embeddings with the discrete policy's representation during training. On challenging hybrid action benchmarks, CHDP outperforms state-of-the-art method by up to 19.3% in success rate.
We propose BRIC, a novel test-time adaptation (TTA) framework that enables long-term human motion generation by resolving execution discrepancies between diffusion-based kinematic motion planners and reinforcement learning-based physics controllers. While diffusion models can generate diverse and expressive motions conditioned on text and scene context, they often produce physically implausible outputs, leading to execution drift during simulation. To address this, BRIC dynamically adapts the physics controller to noisy motion plans at test time, while preserving pre-trained skills via a loss function that mitigates catastrophic forgetting. In addition, BRIC introduces a lightweight test-time guidance mechanism that steers the diffusion model in the signal space without updating its parameters. By combining both adaptation strategies, BRIC ensures consistent and physically plausible long-term executions across diverse environments in an effective and efficient manner. We validate the effectiveness of BRIC on a variety of long-term tasks, including motion composition, obstacle avoidance, and human-scene interaction, achieving state-of-the-art performance across all tasks.
Multimedia technologies leverage multi-source to alleviate real-world data incompleteness, providing a versatile platform for multi-view learning. Among existing research, graph-based multi-view learning has achieved notable success. However, prior studies always immerse in comprehensive collaboration across all views and nodes to pursue consistency and complementary, which ignore the negative contribution of nodes from low-quality views. To overcome the above limitation, we explore node behavior selection in multi-view dynamic modeling and propose a knowledge-aware multi-view state space model. Specifically, nodes autonomously select either activation sequences or static sequences according to their current knowledge. In the former, we design the mask-based attention mechanism to capture the dynamics of node behaviors. In the latter, we construct a history pool and simulate synaptic signals to regulate the behavioral distribution of nodes. Moreover, the proposed model provides a directional inter-view diffusion equation that selectively propagates information to alleviate interference from low-quality nodes across views. Extensive experiments demonstrate that the proposed model outperforms baselines on multiple benchmarks and achieves significant performance improvement.
Multi-Robot Motion Planning (MRMP) involves generating collision-free trajectories for multiple robots operating in a shared continuous workspace. While discrete multi-agent path finding (MAPF) methods are broadly adopted due to their scalability, their coarse discretization severely limits trajectory quality. In contrast, continuous optimization-based planners offer higher-quality paths but suffer from the curse of dimensionality, resulting in poor scalability with respect to the number of robots. This paper tackles the limitations of these two approaches by introducing a novel framework that integrates discrete MAPF solvers with constrained generative diffusion models. The resulting framework, called Discrete-Guided Diffusion (DGD), has three key characteristics: (1) it decomposes the original nonconvex MRMP problem into tractable subproblems with convex configuration spaces, (2) it combines discrete MAPF solutions with constrained optimization techniques to guide diffusion models capture complex spatiotemporal dependencies among robots, and (3) it incorporates a lightweight constraint repair mechanism to ensure trajectory feasibility. The proposed method sets a new state-of-the-art performance in large-scale, complex environments, scaling to 100 robots while achieving planning efficiency and high success rates.
Designing molecules with desired properties, aka the oRiented molEcule Design (RED), is a fundamental task in chemistry and materials science. While graph diffusion models (GDMs) and reinforcement learning techniques (RL) show promise in molecule structure generation and property optimization stages individually, their integration in the unified RED task often suffers from poor compatibility. The large variance among candidate molecular structures generated by GDMs can be amplified in the iterative optimization process of RL, leading to slow and unstable convergence. In this work, motivated by the adaptive and divide-and-conquer characteristics of Mixture of Experts (MoE) architecture, we propose a novel framework called MoE-Guided Graph Diffusion Model (MEGD) that incorporates the MoE architecture to guide the orchestration of GDM and RL, promoting faster and more stable convergence in the design process. MEGD is evaluated on benchmark datasets optimizing the physical and chemical properties of AI-generated molecular structures. On all three datasets, our method outperforms the best of 9 alternative models by 7.73% on the target structural properties, while not penalizing other important application-level quality metrics of the generated molecules. A real-world case study on an emerging class of material, i.e., metal-organic framework, is also conducted, which further demonstrates the effectiveness of our method in accomplishing the RED task.
Learning Curve Extrapolation (LCE) is a critical technique for accelerating automated machine learning by terminating unpromising training runs early. Recent state-of-the-art methods have improved predictive accuracy by incorporating contextual information, such as neural network architecture. However, these approaches, whether context-agnostic or architecture-aware, still operate under the implicit assumption of a uniform task landscape. They overlook a pivotal, complementary factor: the intrinsic difficulty of the learning task itself. This oversight leads to significant performance degradation, especially for tasks whose learning dynamics diverge from the model's priors. In this work, we argue that task difficulty is a crucial yet neglected dimension for robust LCE. We introduce Difficulty-Aware Learning Curve Extrapolation (DA-LCE), which explicitly conditions its predictions on task complexity. Our core contributions are threefold: (1) We propose a transparent, rule-based method to quantify task difficulty from early learning curve dynamics, eliminating the need for external meta-features. (2) We design a novel data generation pipeline using conditional diffusion models to create high-fidelity, difficulty-conditioned synthetic training data. (3) We introduce a Transformer-based predictor that leverages difficulty information to achieve superior accuracy across diverse benchmarks. Extensive experiments demonstrate that our approach significantly outperforms both difficulty-agnostic and architecture-aware baselines, with task difficulty emerging as a powerful conditioning signal whose impact matches or exceeds that of model architecture.
Negative sampling (NS) strategies play a crucial role in knowledge graph representation. In order to overcome the limitations of existing negative sampling strategies, such as vulnerability to false negatives, limited generalization, and lack of control over sample hardness, we propose DANS-KGC (Diffusion-based Adaptive Negative Sampling for Knowledge Graph Completion). DANS-KGC comprises three key components: the Difficulty Assessment Module (DAM), the Adaptive Negative Sampling Module (ANS), and the Dynamic Training Mechanism (DTM). DAM evaluates the learning difficulty of entities by integrating semantic and structural features. Based on this assessment, ANS employs a conditional diffusion model with difficulty-aware noise scheduling, leveraging semantic and neighborhood information during the denoising phase to generate negative samples of diverse hardness. DTM further enhances learning by dynamically adjusting the hardness distribution of negative samples throughout training, enabling a curriculum-style progression from easy to hard examples. Extensive experiments on six benchmark datasets demonstrate the effectiveness and generalization ability of DANS-KGC, with the method achieving state-of-the-art results on all three evaluation metrics for the UMLS and YAGO3-10 datasets.
Adversarial Perturbation Shield: Preventing Concept Bleed-through in Continual Learning of Personalized Generative Models
PDF ↗Personalized text-to-image diffusion models have gained increasing attention because they can generate images that contain unique concepts based on limited training data. However, in continual learning scenarios, these models suffer from concept bleed-through, where newly introduced concepts frequently overwrite or interfere with the previously learned concepts. Previous studies have attempted to mitigate this issue at the model adaptation level; however, they failed to fully preserve the distinct semantic representations in the latent space. Thus, this paper proposes an adversarial perturbation-based training strategy to address concept bleed-through in continual learning for personalized diffusion models. The proposed method introduces adversarial perturbations into the training images, which strategically shifts their semantic representations in the latent space to ensure that the newly learned concepts remain distinct and do not interfere with the previously acquired knowledge. Unlike structural modifications to the model, the proposed method operates at the data level, which makes it broadly applicable to existing continual personalization frameworks without increasing model complexity. Experimental results demonstrate that the proposed method significantly improves concept separation while maintaining high image fidelity, offering a solution to enhance the reliability of continual learning in personalized generative models.