论文检索

Jie Shi, Xiaodong Yue, Wei Liu, Yufei Chen, Feifan Dong

Uncertainty Quantification (UQ) is critical for detecting hallucinations in black-box Large Vision-Language Models (LVLMs). However, prevailing methods like Discrete Semantic Entropy (DSE) are unreliable, as their scores are primarily dominated by the number of semantic clusters. This renders them incapable of distinguishing between benign semantic ambiguity (varied but coherent responses) and severe belief conflict (contradictory responses). We address this limitation by proposing a novel framework rooted in Dempster-Shafer theory of evidence, built on the premise that not all inconsistency is equal. Our method decomposes uncertainty into two complementary metrics: Belief Divergence, which quantifies ambiguity by measuring the separation between viewpoints, and Belief Conflict, which captures direct logical contradictions. Extensive experiments demonstrate that our framework provides a more reliable measure of uncertainty.

Chang-Wei Shi, Shi-Shang Wang, Wu-Jun Li

Momentum SGD (MSGD) serves as a foundational optimizer in training deep models due to momentum's key role in accelerating convergence and enhancing generalization. Meanwhile, asynchronous distributed learning is crucial for training large-scale deep models, especially when the computing capabilities of the workers in the cluster are heterogeneous. To reduce communication frequency, local updates are widely adopted in distributed learning. However, how to implement asynchronous distributed MSGD with local updates remains unexplored. To solve this problem, we propose a novel method, called ordered local momentum (OrLoMo), for asynchronous distributed learning. In OrLoMo, each worker runs MSGD locally. Then the local momentum from each worker will be aggregated by the server in order based on its global iteration index. To the best of our knowledge, OrLoMo is the first method to implement asynchronous distributed MSGD with local updates. We prove the convergence of OrLoMo for non-convex problems under arbitrary delays. Experiments validate that OrLoMo can outperform its synchronous counterpart and other asynchronous methods.

Xinyi Sheng, Wei Bao, Hequn Wang, Yuqin Liu, Sen Fu

Federated unlearning (FU) allows a participating client in a federated learning (FL) system to remove its contribution from the trained global model, thereby enforcing the client’s ``right to be forgotten'' (RTBF). However, from the perspective of a client that does not request unlearning, the activation of the FU process may disrupt ongoing FL training and introduce additional computational and time overhead. In such cases, a client opposed to unlearning may be incentivized to retaliate against the unlearning client(s). In this work, we take the first step toward demonstrating the feasibility of such retaliatory behavior by exploiting the information leakage introduced during the FU process. Specifically, we propose a novel unlearning-induced membership inference attack (MIA) model, followed by a coarse-to-fine data generation method that enables an adversarial client to locally reconstruct the unlearned data. Building on this reconstruction, we introduce two targeted retaliatory attacks: (1) Anti-Unlearning Attack (AUA), which hinders the global model from successfully forgetting the data intended for removal, and (2) Discrimination-Unlearning Attack (DUA), which specifically degrades the global model’s performance on the unlearned data. Extensive experiments across a variety of FU methods and settings validate the effectiveness of the proposed retaliatory attack framework.

Qilu Shen, Yingjie Wang, Jinhai Xiang

Understanding the generalization behavior of in-context learning (ICL) in Transformers remains a fundamental challenge, as most existing theoretical analyses are based on the assumption that data are independently and identically distributed (i.i.d.), an assumption that often does not hold in practice. Motivated by the theoretical insight that ICL operates similarly to gradient-based optimization, we leverage the concept of gradient stability to establish generalization error bounds for ICL under a general non-i.i.d. setting. Our analysis shows that two factors play a central role in ICL generalization: the number of demonstrations in the prompt and their distributional alignment with the query. In particular, increasing the number of demonstrations and improving their alignment with the query distribution lead to better generalization, even without any parameter tuning. Under mild conditions, we further prove that the generalization error can achieve the optimal convergence rate of O(N^(-1/2)), where N is the number of demonstrations. Our empirical evaluations validate the effectiveness of our theoretical findings.

Lifeng Shen, Xuyang Li, Lele Long

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.

Lifeng Shen, Liang Peng, Ruiwen Liu, Shuyin Xia, Yi Liu

Modeling normal behavior in dynamic, nonlinear time series data is challenging for effective anomaly detection. Traditional methods, such as nearest neighbor and clustering approaches, often depend on rigid assumptions, such as a predefined number of reliable neighbors or clusters, which frequently break down in complex temporal scenarios. To address these limitations, we introduce the Granular-ball One-Class Network (GBOC), a novel approach based on a data-adaptive representation called Granular-ball Vector Data Description (GVDD). GVDD partitions the latent space into compact, high-density regions represented by granular-balls, which are generated through a density-guided hierarchical splitting process and refined by removing noisy structures. Each granular-ball serves as a prototype for local normal behavior, naturally positioning itself between individual instances and clusters while preserving the local topological structure of the sample set. During training, GBOC improves the compactness of representations by aligning samples with their nearest granular-ball centers. During inference, anomaly scores are computed based on the distance to the nearest granular-ball. By focusing on dense, high-quality regions and significantly reducing the number of prototypes, GBOC delivers both robustness and efficiency in anomaly detection. Extensive experiments validate the effectiveness and superiority of the proposed method, highlighting its ability to handle the challenges of time series anomaly detection.

Bowen Shen, Yuyue Chen, Peng Yang, Bin Zhang, Xi Zhang, Zoe L. Jiang

Privacy-preserving Transformer inference has gained attention due to the potential leakage of private information. Despite recent progress, existing frameworks still fall short of practical model scales, with gaps up to a hundredfold. A possible way to close this gap is the Mixture of Experts (MoE) architecture, which has emerged as a promising technique to scale up model capacity with minimal overhead. However, given that the current secure two-party (2-PC) protocols allow the server to homomorphically compute the FFN layer with its plaintext model weight, under the MoE setting, this could reveal which expert is activated to the server, exposing token-level privacy about the client's input. While naively evaluating all the experts before selection could protect privacy, it nullifies MoE sparsity and incurs the heavy computational overhead that sparse MoE seeks to avoid. To address the privacy and efficiency limitations above, we propose a 2-PC privacy-preserving inference framework, SecMoE. Unifying per-entry circuits in both the MoE layer and piecewise polynomial functions, SecMoE obliviously selects the extracted parameters from circuits and only computes one encrypted entry, which we refer to as Select-Then-Compute. This makes the model for private inference scale to 63× larger while only having a 15.2× increase in end-to-end runtime. Extensive experiments show that, under 5 expert settings, SecMoE lowers the end-to-end private inference communication by 1.8~7.1× and achieves 1.3~3.8× speedup compared to the state-of-the-art (SOTA) protocols.

Zishan Shao, Yixiao Wang, Qinsi Wang, Ting Jiang, Zhixu Du, Hancheng Ye, Danyang Zhuo, Yiran Chen, Hai ¨Helen¨ Li

Singular Value Decomposition (SVD) has recently gained traction as an effective compression technique for large language models (LLMs), with many studies reporting 20-80% parameter reduction at minimal accuracy cost. However, despite reducing weight memory, existing SVD-based approaches still rely on standard dense CUDA kernels during inference, which incur substantial-and ultimately unnecessary-activation memory overhead. Our analysis reveals that this kernel-induced cost, which grows with sequence length and hidden size, in worst case prevents any real reduction in peak inference memory, limiting the practical impact of SVD compression for on-device deployment. To address this bottleneck, we propose FlashSVD, an end-to-end, rank-aware streaming inference framework for SVD-compressed LLMs. FlashSVD integrates seamlessly with any SVD-based model and directly fuses low-rank projection kernels into self-attention and feed-forward pipelines. This design avoids materializing large activation buffers by streaming small tiles of truncated factors through on-chip SRAM, performing on-the-fly multiplication and reduction, and immediately evicting results–thus preserving high GPU occupancy without introducing latency. On standard benchmarks (e.g., BERT-Base), FlashSVD reduces peak activation memory by up to 70.2% and transient memory by 75%, with zero accuracy loss against low-rank baselines, enabling truly memory-efficient deployment of low-rank LLMs.

Yi Shan, Liyang Gao, Yuena Lin, Zhen Yang, Gengyu Lyu, Honggui Han

In multi-view multi-label (MVML) classification, each sample is represented by multiple heterogeneous views and annotated with multiple labels. Existing methods typically exploit pairwise semantic relationships to mine intra-view correlations and align inter-view features for generating structural representations. However, these methods ignore the direct expression of high-order semantic similarities and alignments from a group perspective, which necessitates multi-step aggregation for subsequent feature fusion, leading to the inefficient and incomplete integration of key semantic information. To overcome this limitation, we propose a novel hypergraph-based MVML method with Adaptive High-Order Semantic Fusion (HyperAHSF), which leverages hypergraphs to adaptively model group-level semantic similarities within each view and group-level semantic alignments across different views, enabling more effective feature fusion. Specifically, we first construct view-specific hyperedges by selecting multiple groups of node representations exhibiting high semantic similarity, which captures the group-level semantic similarities within each view, forming view-specific hypergraphs. Furthermore, we establish cross-view hyperedges to connect the multi-view node representations of each sample, which characterizes the group-level semantic alignments across different views, accordingly forming a unified multi-view hypergraph. Afterwards, we employ hypergraph neural networks to efficiently aggregate view-specific information and consensus information from their corresponding hypergraphs via group-level message passing. During the passing process, we impose a label-driven contrastive loss on the consensus information to encourage these representations to cluster toward their corresponding class prototypes, enhancing their discriminability. Finally, the consensus information together with the view-specific information is jointly integrated for multi-label classification. Extensive experiments demonstrate that HyperAHSF outperforms other state-of-the-art methods.

Lianze Shan, Jitao Zhao, Dongxiao He, Yongqi Huang, Zhiyong Feng, Weixiong Zhang

Universal graph pre-training has emerged as a key paradigm in graph representation learning, offering a promising way to train encoders to learn transferable representations from unlabeled graphs and to effectively generalize across a wide range of downstream tasks. However, recent explorations in universal graph pre-training primarily focus on homogeneous graphs and it remains unexplored for heterogeneous graphs, which exhibit greater structural and semantic complexity. This heterogeneity makes it highly challenging to train a universal encoder for diverse heterogeneous graphs: (i) the diverse types with dataset-specific semantics hinder the construction of a unified representation space; (ii) the number and semantics of meta-paths vary across datasets, making encoding and aggregation patterns learned from one dataset difficult to apply to others. To address these challenges, we propose a novel Meta-path-aware Universal heterogeneous Graph pre-training (MUG) approach. Specifically, for challenge (i), MUG introduces a input unification module that integrates information from multiple node and relation types within each heterogeneous graph into a unified representation. This representation is then projected into a shared space by a dimension-aware encoder, enabling alignment across graphs with diverse schemas. Furthermore, for challenge (ii), MUG trains a shared encoder to capture consistent structural patterns across diverse meta-path views rather than relying on dataset-specific aggregation strategies, while a global objective encourages discriminability and reduces dataset-specific biases. Extensive experiments demonstrate the effectiveness of MUG on some real datasets.

Hazem Hesham Yousef Shalby, Fabrizio Pittorino, Francesca Palermo, Diana Trojaniello, Manuel Roveri

The deployment of deep neural networks on resource-constrained devices relies on quantization. While static, uniform quantization applies a fixed bit-width to all inputs, it fails to adapt to their varying complexity. Dynamic, instance-based mixed-precision quantization promises a superior accuracy-efficiency trade-off by allocating higher precision only when needed. However, a critical bottleneck remains: existing methods require a costly dequantize-to-float and requantize-to-integer cycle to change precision, breaking the integer-only hardware paradigm and compromising performance gains. This paper introduces Dynamic Quantization Training (DQT), a novel framework that removes this bottleneck. At the core of DQT is a nested integer representation where lower-precision values are bit-wise embedded within higher-precision ones. This design, coupled with custom integer-only arithmetic, allows for on-the-fly bit-width switching through a near-zero-cost bit-shift operation. This makes DQT the first quantization framework to enable both dequantization-free static mixed-precision of the backbone network, and truly efficient dynamic, instance-based quantization through a lightweight controller that decides at runtime how to quantize each layer. We demonstrate DQT state-of-the-art performance on ResNet18 on CIFAR-10 and ResNet50 on ImageNet. On ImageNet, our 4-bit dynamic ResNet50 achieves 77.00% top-1 accuracy, an improvement over leading static (LSQ, 76.70%) and dynamic (DQNET, 76.94%) methods at a comparable BitOPs budget. Crucially, DQT achieves this with a bit-width transition cost of only 28.3M simple bit-shift operations, a drastic improvement over the 56.6M costly Multiply-Accumulate (MAC) floating-point operations required by previous dynamic approaches - unlocking a new frontier in efficient, adaptive AI.

Ashkan Shahbazi, Kyvia Pereira, Jon S. Heiselman, Elaheh Akbari, Annie C. Benson, Sepehr Seifi, Xinyuan Liu, Garrison Lawrence Horswill Johnston, Jie Ying Wu, Nabil Simaan 等

Accurate and efficient modeling of soft-tissue interactions is fundamental for advancing surgical simulation, surgical robotics, and model-based surgical automation. To achieve real-time latency, classical Finite Element Method (FEM) solvers are often replaced with neural approximations; however, naively training such models in a fully data-driven manner without incorporating physical priors frequently leads to poor generalization and physically implausible predictions. We present a novel physics-informed neural simulation framework that enables real-time prediction of soft-tissue deformations under complex single- and multi-grasper interactions. Our approach integrates Kelvinlet-based analytical priors with large-scale FEM data, capturing both linear and nonlinear tissue responses. This hybrid design improves predictive accuracy and physical plausibility across diverse neural architectures while maintaining the low-latency performance required for interactive applications. We validate our method on challenging surgical manipulation tasks involving standard laparoscopic grasping tools, demonstrating substantial improvements in deformation fidelity and temporal stability over existing baselines. These results establish Kelvinlet-augmented learning as a principled and computationally efficient paradigm for real-time, physics-aware soft-tissue simulation in surgical AI.

Hyunseok Seung, Jaewoo Lee, Hyunsuk Ko

We introduce LOREN, a curvature-aware zeroth-order (ZO) optimization method for fine-tuning large language models (LLMs). Existing ZO methods, which estimate gradients via finite differences using random perturbations, often suffer from high variance and suboptimal search directions. Our approach addresses these challenges by: (i) reformulating the problem of gradient preconditioning as that of adaptively estimating an anisotropic perturbation distribution for gradient estimation, (ii) capturing curvature through a low-rank block diagonal preconditioner using the framework of natural evolution strategies, and (iii) applying a REINFORCE leave-one-out (RLOO) gradient estimator to reduce variance. Experiments on standard LLM benchmarks show that our method outperforms state-of-the-art ZO methods by achieving higher accuracy and faster convergence, while cutting peak memory usage by up to 27.3% compared with MeZO-Adam.

Timo Pierre Schrader, Lukas Lange, Tobias Kaminski, Simon Razniewski, Annemarie Friedrich

The rise of large language models (LLMs) has sparked interest in coding assistants. While general-purpose programming languages are well supported, generating code for domain-specific languages remains a challenging problem for LLMs. In this paper, we focus on the LLM-based generation of code for Answer Set Programming (ASP), a particularly effective approach for finding solutions to combinatorial search problems. The effectiveness of LLMs in ASP code generation is currently hindered by the limited number of examples seen during their initial pre-training phase. In this paper, we introduce a novel ASP-solver-in-the-loop approach for solver-guided instruction-tuning of LLMs to addressing the highly complex semantic parsing task inherent in ASP code generation. Our method only requires problem specifications in natural language and their solutions. Specifically, we sample ASP statements for program continuations from LLMs for unriddling logic puzzles. Leveraging the special property of declarative ASP programming that partial encodings increasingly narrow down the solution space, we categorize them into chosen and rejected instances based on solver feedback. We then apply supervised fine-tuning to train LLMs on the curated data and further improve robustness using a solver-guided search that includes best-of-N sampling. Our experiments demonstrate consistent improvements in two distinct prompting settings on two datasets.

Moritz Schönherr, Carsten Lutz

We study the expressive power of graph neural networks (GNNs) with mean as the aggregation function, with the following results. In the non-uniform setting, such GNNs have exactly the same expressive power as ratio modal logic, which has modal operators expressing that at least a certain ratio of the successors of a vertex satisfies a specified property. In the uniform setting, the expressive power relative to MSO is exactly that of modal logic, and thus identical to the (absolute) expressive power of GNNs with max aggregation. The proof, however, depends on constructions that are not satisfactory from a practical perspective. This leads us to making the natural assumptions that combination functions are continuous and classification functions are thresholds. The resulting class of GNNs with mean aggregation turns out to be much less expressive: relative to MSO and in the uniform setting, it has the same expressive power as alternation-free modal logic. This is in contrast to the expressive power of GNNs with max and sum aggregation, which is not affected by these assumptions.

Davide Scassola, Sebastiano Saccani, Luca Bortolussi

Data synthesis is gaining momentum as a privacy-enhancing technology. While single-table tabular data generation has seen considerable progress, current methods for multi-table data often lack the flexibility and expressiveness needed to capture complex relational structures. In particular, they struggle with long-range dependencies and complex foreign-key relationships, such as tables with multiple parent tables or multiple types of links between the same pair of tables. We propose a generative model for relational data that generates the content of a relational dataset given the graph formed by the foreign-key relationships. We do this by learning a deep generative model of the content of the whole relational database by flow matching, where the neural network trained to denoise records leverages a graph neural network to obtain information from connected records. Our method is flexible, as it can support relational datasets with complex structures, and expressive, as the generation of each record can be influenced by any other record within the same connected component. We evaluate our method on several benchmark datasets and show that it achieves state-of-the-art performance in terms of synthetic data fidelity.

Andrey Savchenko, Oleg Kachan

Accurate forecasting of multivariate time series data remains a formidable challenge, particularly due to the growing complexity of temporal dependencies in real-world scenarios. While neural network-based models have achieved notable success in this domain, complex channel-dependent models often suffer from performance degradation compared to channel-independent models that do not consider the relationship between components but provide high robustness due to small capacity. In this work, we propose HN-MVTS, a novel architecture that integrates the hypernetwork-based generative prior with an arbitrary neural network forecasting model. The input of this hypernetwork is a learnable embedding matrix of time series components. To restrict the number of new parameters, the hypernetwork learns to generate the weights of the last layer of the target forecasting networks, serving as a data-adaptive regularizer that improves generalization and long-range predictive accuracy. The hypernetwork is only used during training, so it does not increase the inference time compared to the base forecasting model. Extensive experiments on eight benchmark datasets demonstrate that application of HN-MVTS to the state-of-the-art models (DLinear, PatchTST, TSMixer, etc.) typically improves their performance. Our findings suggest that hypernetwork-driven parameterization offers a promising direction for enhancing existing forecasting techniques in complex scenarios.

Dhruv Sarkar, Nishant Pandey, Sayak Ray Chowdhury

Multi-armed bandit algorithms are fundamental tools for sequential decision-making under uncertainty, with widespread applications across domains such as clinical trials and personalized decision-making. As bandit algorithms are increasingly deployed in these socially sensitive settings, it becomes critical to protect user data privacy and ensure fair treatment across decision rounds. While prior work has independently addressed privacy and fairness in bandit settings, the question of whether both objectives can be achieved simultaneously has remained largely open. Existing privacy-preserving bandit algorithms typically optimize average regret, a utilitarian measure, whereas fairness-aware approaches focus on minimizing Nash regret, which penalizes inequitable reward distributions, but often disregard privacy concerns. To bridge this gap, we introduce Differentially Private Nash Confidence Bound (DP-NCB)—a novel and unified algorithmic framework that simultaneously ensures ϵ-differential privacy and achieves order-optimal Nash regret, matching known lower bounds up to logarithmic factors. The framework is sufficiently general to operate under both global and local differential privacy models, and is anytime, requiring no prior knowledge of the time horizon. We support our theoretical guarantees with simulations on synthetic bandit instances, showing that DP-NCB incurs substantially lower Nash regret than state-of-the-art baselines. Our results offer a principled foundation for designing bandit algorithms that are both privacy-preserving and fair, making them suitable for high-stakes, socially impactful applications.

Ricardo G. Sanfelice

For a class of hybrid dynamical systems, we show that a recurrent neural network with hybrid dynamics, which we refer to as a hybrid dynamic recurrent neural network (HyRNN), can be constructed to approximate solutions to hybrid systems over bounded (hybrid) time horizons. Specifically, given a desired precision level, we show that a hybrid system with dynamics resembling those of recurrent neural networks for continuous-time and discrete-time systems can be designed so that, for each bounded hybrid time horizon, its solutions are close to the solutions to the given hybrid system. Through the use of universal approximation theorems, we show that the approximation result holds for traditional smooth activation functions, such as sigmoid and arctan, and that extensions to ReLU functions are possible, and characterize the complexity of the proposed HyRNN.

Pablo Ruiz-Morales, Dries Vanoost, Davy Pissoort, Mathias Verbeke

Joint-Embedding Predictive Architectures (JEPAs), a powerful class of self-supervised models, exhibit an unexplained ability to cluster time-series data by their underlying dynamical regimes. We propose a novel theoretical explanation for this phenomenon, hypothesizing that JEPA's predictive objective implicitly drives it to learn the invariant subspace of the system's Koopman operator. We prove that an idealized JEPA loss is minimized when the encoder represents the system's regime indicator functions, which are Koopman eigenfunctions. This theory was validated on synthetic data with known dynamics, demonstrating that constraining the JEPA's linear predictor to be a near-identity operator is the key inductive bias that forces the encoder to learn these invariants. We further discuss that this constraint is critical for selecting this interpretable solution from a class of mathematically equivalent but entangled optima, revealing the predictor's role in representation disentanglement. This work demystifies a key behavior of JEPAs, provides a principled connection between modern self-supervised learning and dynamical systems theory, and informs the design of more robust and interpretable time-series models.