Although lip-to-speech synthesis (L2S) has achieved significant progress in recent years, current state-of-the-art methods typically rely on intermediate representations such as mel-spectrograms or discrete self-supervised learning (SSL) tokens. The potential of latent diffusion models (LDMs) in this task remains largely unexplored. In this paper, we introduce SLD-L2S, a novel L2S framework built upon a hierarchical subspace latent diffusion model. Our method aims to directly map visual lip movements to the continuous latent space of a pre-trained neural audio codec, thereby avoiding the information loss inherent in traditional intermediate representations. The core of our method is a hierarchical architecture that processes visual representations through multiple parallel subspaces, initiated by a subspace decomposition module. To efficiently enhance interactions within and between these subspaces, we design the diffusion convolution block (DiCB) as our network backbone. Furthermore, we employ a reparameterized flow matching technique to directly generate the target latent vectors. This enables a principled inclusion of speech language model (SLM) and semantic losses during training, moving beyond conventional flow matching objectives and improving synthesized speech quality. Our experiments show that SLD-L2S achieves state-of-the-art generation quality on multiple benchmark datasets, surpassing existing methods in both objective and subjective evaluations.
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
DMOSpeech 2: Reinforcement Learning for Duration Prediction in Metric-Optimized Speech Synthesis
PDF ↗Diffusion-based text-to-speech (TTS) systems have made remarkable progress in zero-shot speech synthesis, yet optimizing all components for perceptual metrics remains challenging. Prior work with DMOSpeech demonstrated direct metric optimization for speech generation components, but duration prediction remained unoptimized. This paper presents DMOSpeech 2, which extends metric optimization to the duration predictor through a reinforcement learning approach. The proposed system implements a novel duration policy framework using group relative preference optimization (GRPO) with speaker similarity and word error rate as reward signals. By optimizing this previously unoptimized component, DMOSpeech 2 creates a more complete metric-optimized synthesis pipeline. Additionally, this paper introduces teacher-guided sampling, a hybrid approach leveraging a teacher model for initial denoising steps before transitioning to the student model, significantly improving output diversity while maintaining efficiency. Comprehensive evaluations demonstrate superior performance across all metrics compared to previous systems, while reducing sampling steps by half without quality degradation. These advances represent a significant step toward speech synthesis systems with metric optimization across multiple components.
RAGFort: Dual-Path Defense Against Proprietary Knowledge Base Extraction in Retrieval-Augmented Generation
PDF ↗Retrieval-Augmented Generation (RAG) systems deployed over proprietary knowledge bases face growing threats from reconstruction attacks that aggregate model responses to replicate knowledge bases. Such attacks exploit both intra-class and inter-class paths—progressively extracting fine-grained knowledge within topics and diffusing it across semantically related ones, thereby enabling comprehensive extraction of the original knowledge base. However, existing defenses target only one path, leaving the other unprotected. We conduct a systematic exploration to assess the impact of protecting each path independently and find that joint protection is essential for effective defense. Based on this, we propose RAGFort, a structure-aware dual-module defense combining contrastive reindexing for inter-class isolation and constrained cascade generation for intra-class protection. Experiments across security, performance, and robustness confirm that RAGFort significantly reduces reconstruction success while preserving answer quality, offering the first comprehensive defense against knowledge base extraction attacks.
Retrieval-Augmented Generation (RAG) enhances large language models (LLMs) with external knowledge retrieval, improving factual accuracy and knowledge coverage. However, existing RAG approaches face a fundamental trade-off when handling complex reasoning: while traditional iterative retrieval methods offer flexibility, their local perspective limits their ability to establish global knowledge connections. In contrast, structure-augmented RAG methods capture global relationships but incur significant construction costs. To fill in this gap, we propose MGranRAG, an innovative framework designed to integrate precise local retrieval with structured global reasoning. Our approach circumvents expensive semantic extraction by employing a lightweight contextual hierarchical graph, effectively combining the local adaptability of iterative retrieval with the global consistency of structured knowledge. The framework adopts a novel iterative optimization scheme: at the local level, the LLM identifies multi-granular contextual evidence, such as key sentences and phrases, within retrieved passages to refine retrieval. At the global level, these multi-granularity evidence nodes are then mapped and propagated within the structured hierarchical graph, enabling the diffusion of rich contextual information at different levels to introduce global semantic constraints and reorder retrieval results. This coordination between local and global iterative processes dynamically balances retrieval accuracy and contextual coherence. Experimental results on challenging multi-hop and open-domain question answering datasets show that our proposal achieves new state-of-the-art performance in both retrieval and answer accuracy.
Cog-RAG: Cognitive-Inspired Dual-Hypergraph with Theme Alignment Retrieval-Augmented Generation
PDF ↗Retrieval-Augmented Generation (RAG) enhances the response quality and domain-specific performance of large language models (LLMs) by incorporating external knowledge to combat hallucinations. In recent research, graph structures have been integrated into RAG to enhance the capture of semantic relations between entities. However, it primarily focuses on low-order pairwise entity relations, limiting the high-order associations among multiple entities. Hypergraph-enhanced approaches address this limitation by modeling multi-entity interactions via hyperedges, but they are typically constrained to inter-chunk entity-level representations, overlooking the global thematic organization and alignment across chunks. Drawing inspiration from the top-down cognitive process of human reasoning, we propose a theme-aligned dual-hypergraph RAG framework (Cog-RAG) that uses a theme hypergraph to capture inter-chunk thematic structure and an entity hypergraph to model high-order semantic relations. Furthermore, we design a cognitive-inspired two-stage retrieval strategy that first activates query-relevant thematic content from the theme hypergraph, and then guides fine-grained recall and diffusion in the entity hypergraph, achieving semantic alignment and consistent generation from global themes to local details. Our extensive experiments demonstrate that Cog-RAG significantly outperforms existing state-of-the-art baseline approaches.
Zero-shot singing voice conversion (SVC) transforms a source singer's timbre to an unseen target speaker's voice while preserving melodic content without fine-tuning. Existing methods model speaker timbre and vocal content separately, losing essential acoustic information that degrades output quality while requiring significant computational resources. To overcome these limitations, we propose HQ-SVC, an efficient framework for high-quality zero-shot SVC. HQ-SVC first extracts jointly content and speaker features using a decoupled codec. It then enhances fidelity through pitch and volume modeling, preserving critical acoustic information typically lost in separate modeling approaches, and progressively refines outputs via differentiable signal processing and diffusion techniques. Evaluations confirm HQ-SVC significantly outperforms state-of-the-art zero-shot SVC methods in conversion quality and efficiency. Beyond voice conversion, HQ-SVC achieves superior voice naturalness compared to specialized audio super-resolution methods while natively supporting voice super-resolution tasks.
Federated Graph Learning (FGL) has emerged as a compelling paradigm for collaboratively training a global model while preserving the privacy of multi-source graphs. Nonetheless, FGL faces a critical challenge of data heterogeneity, where semantic and structural discrepancies across clients significantly degrade its performance. Although existing methods attempt to calibrate client-specific graph distributions during federated training, they inevitably fall short in aligning the optimization behaviors across clients due to dynamic parameter updates, thereby inducing a bottleneck in generalization improvement. To tackle this challenge, we propose a solution from a new perspective of prior refinement, which seeks to proactively harmonize client graph distributions before the federated training. In particular, we propose a Federated Graph Harmonization (FedGH) framework that exploits the generative strengths of graph diffusion models to perform prior refinement of local graphs. In a nutshell, FedGH designs a conditional diffusion mechanism on each client that synthesizes pseudo-graphs encapsulating both feature and structural priors, thereby facilitating explicit correction of inter-client distributional bias. On the server side, we employ the graph contrastive learning between various client-specific pseudo-graphs to incorporate the global information, subsequently guiding local data reconstruction. Importantly, model-agnostic FedGH can be seamlessly deployed as a plug-and-play module to be easily integrated with existing FGL architectures. Extensive experiments demonstrate that FedGH consistently outperforms state-of-the-art FGL baselines.
Task decomposition has shown promise in complex cooperative multi-agent reinforcement learning (MARL) tasks, which enables efficient hierarchical learning for long-horizon tasks in dynamic and uncertain environments. However, learning dynamic task decomposition from scratch generally requires a large number of training samples, especially exploring the large joint action space under partial observability. In this paper, we present the Conditional Diffusion Model for Dynamic Task Decomposition (CD3T), a novel two-level hierarchical MARL framework designed to automatically infer subtask and coordination patterns. The high-level policy learns subtask representation to generate a subtask selection strategy based on subtask effects. To capture the effects of subtasks on the environment, CD3T predicts the next observation and reward using a conditional diffusion model. At the low level, agents collaboratively learn and share specialized skills within their assigned subtasks. Moreover, the learned subtask representation is also used as additional semantic information in a multi-head attention mixing network to enhance value decomposition and provide an efficient reasoning bridge between individual and joint value functions. Experimental results on various benchmarks demonstrate that CD3T achieves better performance than existing baselines.
Schrödinger Bridge-based diffusion models have demonstrated promising performance in signal denoising. However, since ground truth signals are unavailable during the sampling process, neural networks must be employed to learn the mapping, which breaks the theoretical coupling between diffusion and sampling processes. This paper reveals a critical inconsistency between the theoretical diffusion path and the learned sampling trajectory across different frequency bands. This diffusion-sampling inconsistency directly undermines denoising effectiveness. To address this limitation, we propose the Frequency-Dependent Scheduled Schrödinger Bridge (FDSSB), which leverages power spectral density to adaptively schedule diffusion processes across frequencies. This mechanism assigns asynchronous diffusion schedules to different frequency components, correcting the diffusion schedule to better match the sampling process. As a result, FDSSB effectively mitigates the mismatch and enhances the consistency between diffusion and sampling processes. Extensive experiments demonstrate that FDSSB achieves state-of-the-art performance, with an average scale-invariant signal-to-noise ratio improvement of 7.9066 dB over competitive approaches.
DeNC++: Efficient Diffusion-Enhanced Neural Codec for End-to-end Semantic Streaming at the Edge
PDF ↗The neural-enhanced video streaming (NeVS) has been an emerging technique to integrate neural models into video codecs for higher streaming efficiency. The state-of-the-art methods, e.g., DeNC and Gemino, typically compress videos in RGB space and restore video quality via a neural enhancement model hosted on the external media server. However, these methods are not always accessible in resource-constrained edge environments due to their heavy reliance on the media server's computation, which undermines end-to-end performance and restricts NeVS's usage boundary. This limitation raises an interesting question: is it possible to make NeVS lightweight so that all neural codec operations can be handled directly by clients' edge devices? In this paper, we present the answer yes and develop a new plug-and-play module called DeNC++, which significantly improves the compression-restoration-overhead trade-off over existing methods. Our core design philosophy is to wrap all the codec operations within a latent semantic space, in which the original high-dimensional visual signals are efficiently embedded into low-dimensional semantic representations. With this fundamental transformation, DeNC++'s neural encoder introduces the triple semantic-bitwidth-resolution compression to effectively lower the streaming traffic. Meanwhile, we make DeNC++'s neural decoder aware of the perceptual loss caused by its encoder and design tiny generative models to guarantee high restoration quality. We also strictly restrict the runtime computational overhead and accelerate the neural enhancement process, making DeNC++ compatible with commodity edge devices. Real-world evaluations reveal that DeNC++ consistently provides higher restoration quality while achieving 24-55 times higher compression ratio and 5-7 times end-to-end speedup over the latest NeVS solutions.
Bidirectional Noise Injection: Enhancing Diffusion Models via Coordinated Input-Output Perturbation
PDF ↗Diffusion models have demonstrated remarkable success in image generation, yet a persistent challenge remains: the bias between model predictions and the target distribution. In this paper, we propose a Bidirectional Noise Injection framework for enhancing diffusion models, implemented via Coordinated Input-Output Perturbation (CIOP). Our approach mitigates this bias by randomly applying synchronized noise injection to both the model inputs and the prediction targets during the training stage. This stochastic, synchronized noise injected acts as a smoothing mechanism that effectively reduces the 2-Wasserstein distance between the predicted and target distributions, as substantiated by our theoretical analysis based on optimal transport theory. Extensive experiments on multiple benchmark datasets and various generative tasks demonstrate that our method improves generation quality and training efficiency without incurring additional computational cost. Furthermore, the design of CIOP enables seamless integration with existing diffusion model improvements and advanced frameworks, thereby broadening its applicability. These results highlight the potential of Bidirectional Noise Injection via CIOP to alleviate bias in diffusion-based generative models across a wide range of settings.
Graph VQ-Transformer (GVT): Fast and Accurate Molecular Generation via High-Fidelity Discrete Latents
PDF ↗The de novo generation of molecules with desirable properties is a critical challenge, where diffusion models are computationally intensive and autoregressive models struggle with error propagation. In this work, we introduce the Graph VQ-Transformer (GVT), a two-stage generative framework that achieves both high accuracy and efficiency. The core of our approach is a novel Graph Vector Quantized Variational Autoencoder (VQ-VAE) that compresses molecular graphs into high-fidelity discrete latent sequences. By synergistically combining a Graph Transformer with canonical Reverse Cuthill-McKee (RCM) node ordering and Rotary Positional Embeddings (RoPE), our VQ-VAE achieves near-perfect reconstruction rates. An autoregressive Transformer is then trained on these discrete latents, effectively converting graph generation into a well-structured sequence modeling problem. Crucially, this mapping of complex graphs to high-fidelity discrete sequences bridges molecular design with the powerful paradigm of large-scale sequence modeling, unlocking potential synergies with Large Language Models (LLMs). Extensive experiments show that GVT achieves state-of-the-art or highly competitive performance across major benchmarks like ZINC250k, MOSES, and GuacaMol, and notably outperforms leading diffusion models on key distribution similarity metrics such as FCD and KL Divergence. With its superior performance, efficiency, and architectural novelty, GVT not only presents a compelling alternative to diffusion models but also establishes a strong new baseline for the field, paving the way for future research in discrete latent-space molecular generation.
Enabling neural networks to learn complex logical constraints and fulfill symbolic reasoning is a critical challenge. Bridging this gap often requires guiding the neural network’s output distribution to move closer to the symbolic constraints. While diffusion models have shown remarkable generative capability across various domains, we employ the powerful architecture to perform neuro-symbolic learning and solve logical puzzles. Our diffusion-based pipeline adopts a two-stage training strategy: the first stage focuses on cultivating basic reasoning abilities, while the second emphasizes systematic learning of logical constraints. To impose hard constraints on neural outputs in the second stage, we formulate the diffusion reasoner as a Markov decision process and innovatively fine-tune it with an improved proximal policy optimization algorithm. We utilize a rule-based reward signal derived from the logical consistency of neural outputs and adopt a flexible strategy to optimize the diffusion reasoner's policy. We evaluate our methodology on some classical symbolic reasoning benchmarks, including Sudoku, Maze, pathfinding and preference learning. Experimental results demonstrate that our approach achieves outstanding accuracy and logical consistency among neural networks.
Unifying Channel Independence and Mixing: Multi-Scale Patch Recursion for Global–Local Representation Synergy in Multivariate Time Series Forecasting
PDF ↗Multivariate time series forecasting underpins applications in finance, meteorology, and industrial operations. Yet two persistent hurdles remain: (i) models typically choose between Channel–Independent (CI) and Channel–Mixed (CM) formulations—each with distinct strengths—leading to large performance variance across datasets; and (ii) short-term dynamics and long-term trends are hard to model jointly, making it difficult to capture both transient bursts and periodic patterns. We propose FusionTimePatch (FTP), a purely MLP-driven, lightweight framework composed of three modules: (1) Dual-View Global–Local Fusion (Dual-GLF), which runs CI and CM views in parallel and employs multi-scale patch recursion to adaptively adjust the look-back window, thereby coupling global tendencies with local details; (2) Channel Enhancement (CE), which adaptively identifies and amplifies salient channel signals and diffuses them to others, improving sensitivity to abrupt events and latent drivers; and (3) a Linear Fusion layer, which unifies Dual-GLF and CE outputs to strengthen cross-view interactions and enhance robustness. Extensive experiments on multiple public benchmarks show FTP consistently surpasses state-of-the-art counterparts in both accuracy and efficiency, offering a scalable new paradigm for multichannel forecasting. Code and datasets are publicly available at https://github.com/Zhveh7/FTP.
Molecular assembly (MA) has long been a fundamental task in chemistry and biology, with the potential to create new materials and enable novel functions beyond the molecular scale. However, its vast conformational search space poses substantial challenges, and current generative models remain limited in capturing molecular flexibility and preventing non-physical poses. In this paper, we propose AssemUDB, a diffusion bridge–based framework that learns transport mappings between two distinct flexible domains for molecular assembly generation. We reformulate the marginal matching constraint of diffusion bridges as a coupling distribution governed by unbalanced transport rather than imposing strict conservation. Subsequently, we employ a progressive process from structural relaxation in Euclidean space to assembly on the SE(3) manifold. This relaxation of marginal conservation grants the generative model greater flexibility and leads to more physically plausible atom placements. Comprehensive experiments demonstrate the superior performance of AssemUDB. Notably, we find that the method demonstrates performance comparable to, or even better than, mature tools such as PackMol for packing tasks.
Recent unified models have demonstrated that the reasoning capacity of Multimodal Large Language Models (MLLMs) can be leveraged to facilitate diffusion-based image generation with impressive flexibility and performance. However, approaches that rely heavily on MLLMs for high-level semantic encoding often struggle with fine-grained visual tasks like image editing and virtual try-on. To address this gap, we propose FUSE, a unified framework excelling at both high-level vision–language understanding and fine-grained generation. First, we introduce a Semantic-to-Detail Connector that pre-aligns fine-grained visual features with the MLLM's semantic space. This design counteracts the low-level information loss inherent in MLLM encodings, creating a unified representation that steers the diffusion process with both global semantics and rich local details. Second, to further enhance semantic awareness and detail preservation, we introduce Adaptive-GRPO, a post-training objective that dynamically balances semantic coherence against pixel-level fidelity. The integration of these two innovations allows FUSE to generate images that are both semantically faithful and visually fine-grained. Comprehensive experiments on text-to-image and instruction-guided editing benchmarks show that FUSE significantly outperforms existing unified baselines, achieving 0.89 on Geneval, 0.65 on WISE, and 3.88 on ImageEdit.
Diffusion models show promise for 3D molecular generation, but face a fundamental trade-off between sampling efficiency and conformational accuracy. While flow-based models are fast, they often produce geometrically inaccurate structures, as they have difficulty capturing the multimodal distributions of molecular conformations. In contrast, denoising diffusion models are more accurate but suffer from slow sampling, a limitation attributed to sub-optimal integration between diffusion dynamics and SE(3)‑equivariant architectures. To address this, we propose VEDA, a unified SE(3)-equivariant framework that combines variance-exploding diffusion with annealing to efficiently generate conformationally accurate 3D molecular structures. Specifically, our key technical contributions include: (1) a VE schedule that enables noise injection functionally analogous to simulated annealing, improving 3D accuracy and reducing relaxation energy; (2) a novel preconditioning scheme that reconciles the coordinate-predicting nature of SE(3)-equivariant networks with a residual-based diffusion objective, and (3) a new arcsin-based scheduler that concentrates sampling in critical intervals of the logarithmic signal-to-noise ratio. On the QM9 and GEOM-DRUGS datasets, VEDA matches the sampling efficiency of flow-based models, achieving state-of-the-art valency stability and validity with only 100 sampling steps. More importantly, VEDA's generated structures are remarkably stable, as measured by their relaxation energy (Delta E_relax) during GFN2-xTB optimization. The median energy change is only 1.72kcal/mol, significantly lower than the 32.3kcal/mol from its architectural baseline, SemlaFlow. Our framework demonstrates that principled integration of VE diffusion with SE(3)-equivariant architectures can achieve both high chemical accuracy and computational efficiency.
Peptide-based drug design targeting “undruggable” proteins remains one of the most critical challenges in modern drug discovery. Conventional peptide-discovery pipelines rely on low-throughput experimental screening, which is both time-consuming and prohibitively expensive. Moreover, existing computational approaches for designing peptides against target proteins typically depend on the availability of high-quality structural information. Although recent structure-prediction tools such as AlphaFold3 have achieved breakthroughs in protein modeling, their accuracy for functional interfaces remains limited. The acquisition of high-resolution structures is often expensive, time-intensive, and particularly challenging for targets with dynamic conformations, further restricting the efficient development of peptide therapeutics. Additionally, current sequence-based generative methods follow a paradigm that relies on known templates, which limits the exploration of sequence space and results in generated peptides lacking diversity and novelty. To address these limitations, we propose a contrastive conditioned diffusion framework for target-specific peptide generation, referred to as PepCCD. It employs a contrastive learning strategy between proteins and peptides to extract sequence-based conditioning representations of target proteins, which serve as precise conditions to guide a pre-trained diffusion model to generate peptide sequences with the desired target specificity. Extensive experiments on multiple benchmark target proteins demonstrate that the peptides designed by PepCCD exhibit strong binding affinity and outperform state-of-the-art methods in terms of diversity and generation efficiency.
Although neural networks achieve promising performance in many tasks, they may still fail when encountering some examples and bring about risks to applications. To discover risky samples, previous literature attempts to search for patterns of risky samples within existing datasets or inject perturbation into them. Yet in this way the diversity of risky samples is limited by the coverage of existing datasets. To overcome this limitation, recent works adopt diffusion models to produce new risky samples beyond the coverage of existing datasets. However, these methods struggle in the conformity between generated samples and expected categories, which could introduce label noise and severely limit their effectiveness in applications. To address this issue, we propose RiskyDiff that incorporates the embeddings of both texts and images as implicit constraints of category conformity. We also design a conformity score to further explicitly strengthen the category conformity, as well as introduce the mechanisms of embedding screening and risky gradient guidance to boost the risk of generated samples. Extensive experiments reveal that RiskyDiff greatly outperforms existing methods in terms of the degree of risk, generation quality, and conformity with conditioned categories. We also empirically show the generalization ability of the models can be enhanced by augmenting training data with generated samples of high conformity.
Continual Test-Time Domain Adaptation (CTTA) aims to adapt a pre-trained source model to a dynamically evolving target domain without requiring additional data collection or labeling efforts. A key challenge in this setting is to achieve rapid performance improvement in the current domain using unlabeled data, while avoiding impairing generalization to future domains in complex scenarios. To enhance the discriminative capability of the inference models, we propose a novel framework that integrates an external auxiliary generative model with a test-time adaptive method, leveraging cross-validation to identify reliable supervisory signals. Specifically, for each test instance, we utilize a diffusion module to generate a calibrated instance under the textual description of its predicted category. Based on the generated one, we design a learning strategy with the following components: (1) the calibrated instance and its category are used to form a supervisory signal; (2) the predicted category of the calibrated instance is compared with the test instance for selecting reliable signals. For these generated and selected instances, adaptive weighting is applied during optimization to stabilize the category distribution and preserve prediction diversity. Finally, based on the inverse process of diffusion, we construct the negative instance of the generated instance and introduce a robust contrastive learning to further calibrate model optimization. Extensive experiments demonstrate that our method achieves state-of-the-art performance across multiple benchmarks. Ablation studies further validate the effectiveness of each proposed component.