Fresh from the feed

arXiv:2511.13078v1 Announce Type: new Abstract: Emergency Medical Technicians (EMTs) operate in high-pressure environments, making rapid, life-critical decisions under heavy cognitive and operational loads. We present EMSGlass, a smart-glasses system powered by EMSNet, the first multimodal multitask model for Emergency Medical Services (EMS), and EMSServe, a low-latency multimodal serving framework tailored to EMS scenarios. EMSNet integrates text, vital signs, and scene images to construct a unified real-time understanding of EMS incidents. Trained on real-world multimodal EMS datasets, EMSNet simultaneously supports up to five critical EMS tasks with superior accuracy compared to state-of-the-art unimodal baselines. Built on top of PyTorch, EMSServe introduces a modality-aware model splitter and a feature caching mechanism, achieving adaptive and efficient inference across heterogeneous hardware while addressing the challenge of asynchronous modality arrival in the field. By optimizing multimodal inference execution in EMS scenarios, EMSServe achieves 1.9x -- 11.7x speedup over direct PyTorch multimodal inference. A user study evaluation with six professional EMTs demonstrates that EMSGlass enhances real-time situational awareness, decision-making speed, and operational efficiency through intuitive on-glass interaction. In addition, qualitative insights from the user study provide actionable directions for extending EMSGlass toward next-generation AI-enabled EMS systems, bridging multimodal intelligence with real-world emergency response workflows.

arXiv:2511.13062v1 Announce Type: new Abstract: Graph Neural Networks (GNNs) have emerged as powerful tools for learning over graph-structured data, yet recent studies have shown that their performance gains are beginning to plateau. In many cases, well-established models such as GCN and GAT, when appropriately tuned, can match or even exceed the performance of more complex, state-of-the-art architectures. This trend highlights a key limitation in the current landscape: the difficulty of selecting the most suitable model for a given graph task or dataset. To address this, we propose Self-Adaptive Graph Mixture of Models (SAGMM), a modular and practical framework that learns to automatically select and combine the most appropriate GNN models from a diverse pool of architectures. Unlike prior mixture-of-experts approaches that rely on variations of a single base model, SAGMM leverages architectural diversity and a topology-aware attention gating mechanism to adaptively assign experts to each node based on the structure of the input graph. To improve efficiency, SAGMM includes a pruning mechanism that reduces the number of active experts during training and inference without compromising performance. We also explore a training-efficient variant in which expert models are pretrained and frozen, and only the gating and task-specific layers are trained. We evaluate SAGMM on 16 benchmark datasets covering node classification, graph classification, regression, and link prediction tasks, and demonstrate that it consistently outperforms or matches leading GNN baselines and prior mixture-based methods, offering a robust and adaptive solution for real-world graph learning.

arXiv:2511.13061v1 Announce Type: new Abstract: Sparse Matrix-Vector Multiplication (SpMV) is a fundamental operation in the inference of sparse Large Language Models (LLMs). Because existing SpMV methods perform poorly under the low and unstructured sparsity (30-90%) commonly observed in pruned LLMs, unstructured pruning provided only limited memory reduction and speedup. We propose MACKO-SpMV, a GPU-optimized format and kernel co-designed to reduce storage overhead while preserving compatibility with the GPU's execution model. This enables efficient SpMV for unstructured sparsity without specialized hardware units (e.g., tensor cores) or format-specific precomputation. Empirical results show that at sparsity 50%, MACKO is the first approach with significant 1.5x memory reduction and 1.2-1.5x speedup over dense representation. Speedups over other SpMV baselines: 2.8-13.0x over cuSPARSE, 1.9-2.6x over Sputnik, and 2.2-2.5x over DASP. Applied to Llama2-7B pruned with Wanda to sparsity 50%, it delivers 1.5x memory reduction and 1.5x faster inference at fp16 precision. Thanks to MACKO, unstructured pruning at 50% sparsity is now justified in real-world LLM workloads.

arXiv:2511.13060v1 Announce Type: new Abstract: Online decision systems routinely operate under delayed feedback and order-sensitive (noncommutative) dynamics: actions affect which observations arrive, and in what sequence. Taking a Bregman divergence $D_\Phi$ as the loss benchmark, we prove that the excess benchmark loss admits a structured lower bound $L \ge L_{\mathrm{ideal}} + g_1(\lambda) + g_2(\varepsilon_\star) + g_{12}(\lambda,\varepsilon_\star) - D_{\mathrm{ncx}}$, where $g_1$ and $g_2$ are calibrated penalties for latency and order-sensitivity, $g_{12}$ captures their geometric interaction, and $D_{\mathrm{ncx}}\ge 0$ is a nonconvexity/approximation penalty that vanishes under convex Legendre assumptions. We extend this inequality to prox-regular and weakly convex settings, obtaining robust guarantees beyond the convex case. We also give an operational recipe for estimating and monitoring the four terms via simple $2\times 2$ randomized experiments and streaming diagnostics (effective sample size, clipping rate, interaction heatmaps). The framework packages heterogeneous latency, noncommutativity, and implementation-gap effects into a single interpretable lower-bound statement that can be stress-tested and tuned in real-world systems.

arXiv:2511.13052v1 Announce Type: new Abstract: Language models (LMs) are often adapted through supervised fine-tuning (SFT) to specialize their capabilities for downstream tasks. However, in typical scenarios where the fine-tuning data is limited, e.g., compared to pre-training, SFT can lead LMs to overfit, causing them to rely on spurious patterns within the target task or to compromise other broadly useful capabilities as a side effect of narrow specialization. In this paper, we propose Learning-from-the-Undesirable (LfU), a simple yet effective regularization scheme for SFT to mitigate overfitting issues when fine-tuning LMs with limited data. Specifically, we aim to regularize the fine-tuning process to favor solutions that are resilient to "undesirable" model updates, e.g., gradient ascent steps that steer the model toward undesirable behaviors. To this end, we propose a novel form of consistency regularization that directly aligns internal representations of the model with those after an undesirable update. By leveraging representation-level data augmentation through undesirable updates, LfU effectively promotes generalization under limited data. Our experiments on diverse LM downstream tasks show that LfU serves as an effective prior that enhances adaptability while preserving pretrained knowledge. For example, our LM from LfU achieves a 16.8% average improvement on math tasks compared to vanilla SFT on the same dataset, where the latter even leads to degraded performance on those tasks. Furthermore, LfU exhibits improved robustness to prompt variations, e.g., yielding a 92.1% lower standard deviation in output performances compared to SFT, highlighting its versatile effects.

arXiv:2511.13044v1 Announce Type: new Abstract: Traditional Machine Learning (ML) methods require large amounts of data to perform well, limiting their applicability in sparse or incomplete scenarios and forcing the usage of additional synthetic data to improve the model training. To overcome this challenge, the research community is looking more and more at Graph Machine Learning (GML) as it offers a powerful alternative by using relationships within data. However, this method also faces limitations, particularly when dealing with Knowledge Graphs (KGs), which can hide huge information due to their semantic nature. This study introduces Bi-View, a novel hybrid approach that increases the informative content of node features in KGs to generate enhanced Graph Embeddings (GEs) that are used to improve GML models without relying on additional synthetic data. The proposed work combines two complementary GE techniques: Node2Vec, which captures structural patterns through unsupervised random walks, and GraphSAGE, which aggregates neighbourhood information in a supervised way. Node2Vec embeddings are first computed to represent the graph topology, and node features are then enriched with centrality-based metrics, which are used as input for the GraphSAGE model. Moreover, a fusion layer combines the original Node2Vec embeddings with the GraphSAGE-influenced representations, resulting in a dual-perspective embedding space. Such a fusion captures both topological and semantic properties of the graph, enabling the model to exploit informative features that may exist in the dataset but that are not explicitly represented. Our approach improves downstream task performance, especially in scenarios with poor initial features, giving the basis for more accurate and precise KG-enanched GML models.

arXiv:2511.13035v1 Announce Type: new Abstract: We introduce a one-step generative policy for offline reinforcement learning that maps noise directly to actions via a residual reformulation of MeanFlow, making it compatible with Q-learning. While one-step Gaussian policies enable fast inference, they struggle to capture complex, multimodal action distributions. Existing flow-based methods improve expressivity but typically rely on distillation and two-stage training when trained with Q-learning. To overcome these limitations, we propose to reformulate MeanFlow to enable direct noise-to-action generation by integrating the velocity field and noise-to-action transformation into a single policy network-eliminating the need for separate velocity estimation. We explore several reformulation variants and identify an effective residual formulation that supports expressive and stable policy learning. Our method offers three key advantages: 1) efficient one-step noise-to-action generation, 2) expressive modelling of multimodal action distributions, and 3) efficient and stable policy learning via Q-learning in a single-stage training setup. Extensive experiments on 73 tasks across the OGBench and D4RL benchmarks demonstrate that our method achieves strong performance in both offline and offline-to-online reinforcement learning settings. Code is available at https://github.com/HiccupRL/MeanFlowQL.

arXiv:2511.13023v1 Announce Type: new Abstract: Despite the growing interest in Small Language Models (SLMs) as resource-efficient alternatives to Large Language Models (LLMs), their deployment on edge devices remains challenging due to unresolved efficiency gaps in model compression. While quantization has proven effective for LLMs, its applicability to SLMs is significantly underexplored, with critical questions about differing quantization bottlenecks and efficiency profiles. This paper introduces SLMQuant, the first systematic benchmark for evaluating LLM compression techniques when applied to SLMs. Through comprehensive multi-track evaluations across diverse architectures and tasks, we analyze how state-of-the-art quantization methods perform on SLMs. Our findings reveal fundamental disparities between SLMs and LLMs in quantization sensitivity, demonstrating that direct transfer of LLM-optimized techniques leads to suboptimal results due to SLMs' unique architectural characteristics and training dynamics. We identify key factors governing effective SLM quantization and propose actionable design principles for SLM-tailored compression. SLMQuant establishes a foundational framework for advancing efficient SLM deployment on low-end devices in edge applications, and provides critical insights for deploying lightweight language models in resource-constrained scenarios.

arXiv:2511.13022v1 Announce Type: new Abstract: General-purpose foundation models for neural time series can help accelerate neuroscientific discoveries and enable applications such as brain computer interfaces (BCIs). A key component in scaling these models is population-level representation learning, which leverages information across channels to capture spatial as well as temporal structure. Population-level approaches have recently shown that such representations can be both efficient to learn on top of pretrained temporal encoders and produce useful representations for decoding a variety of downstream tasks. However, these models remain sensitive to mismatches in preprocessing, particularly on time-scales, between pretraining and downstream settings. We systematically examine how time-scale mismatches affects generalization and find that existing representations lack invariance. To address this, we introduce Time-scale Augmented Pretraining (TSAP), which consistently improves robustness to different time-scales across decoding tasks and builds invariance in the representation space. These results highlight handling preprocessing diversity as a key step toward building generalizable neural foundation models.

arXiv:2511.13018v1 Announce Type: new Abstract: The R-Learner is a powerful, theoretically-grounded framework for estimating heterogeneous treatment effects, prized for its robustness to nuisance model errors. However, its application to network data, where causal heterogeneity is often graph-dependent, presents a critical challenge to its core assumption of a well-specified final-stage model. In this paper, we conduct a large-scale empirical study to systematically dissect the R-Learner framework on graphs. We provide the first rigorous evidence that the primary driver of performance is the inductive bias of the final-stage CATE estimator, an effect that dominates the choice of nuisance models. Our central finding is the quantification of a catastrophic "representation bottleneck": we prove with overwhelming statistical significance (p 4.0), even when paired with powerful GNN nuisance models. Conversely, our proposed end-to-end Graph R-Learner succeeds and significantly outperforms a strong, non-DML GNN T-Learner baseline. Furthermore, we identify and provide a mechanistic explanation for a subtle, topology-dependent "nuisance bottleneck," linking it to GNN over-squashing via a targeted "Hub-Periphery Trade-off" analysis. Our findings are validated across diverse synthetic and semi-synthetic benchmarks. We release our code as a reproducible benchmark to facilitate future research on this critical "final-stage bottleneck."

arXiv:2511.13016v1 Announce Type: new Abstract: Reward design is central to reinforcement learning from human feedback (RLHF) and alignment research. In this work, we propose a unified framework to study hard, continuous, and hybrid reward structures for fine-tuning large language models (LLMs) on mathematical reasoning tasks. Using Qwen3-4B with LoRA fine-tuning on the GSM8K dataset, we formalize and empirically evaluate reward formulations that incorporate correctness, perplexity, reasoning quality, and consistency. We introduce an adaptive hybrid reward scheduler that transitions between discrete and continuous signals, balancing exploration and stability. Our results show that hybrid reward structures improve convergence speed and training stability over purely hard or continuous approaches, offering insights for alignment via adaptive reward modeling.

arXiv:2511.13010v1 Announce Type: new Abstract: Graph Neural Networks (GNNs) have emerged as powerful tools for learning on graph-structured data, but often struggle to balance local and global information. While graph Transformers aim to address this by enabling long-range interactions, they often overlook the inherent locality and efficiency of Message Passing Neural Networks (MPNNs). We propose a new concept called fractal nodes, inspired by the fractal structure observed in real-world networks. Our approach is based on the intuition that graph partitioning naturally induces fractal structure, where subgraphs often reflect the connectivity patterns of the full graph. Fractal nodes are designed to coexist with the original nodes and adaptively aggregate subgraph-level feature representations, thereby enforcing feature similarity within each subgraph. We show that fractal nodes alleviate the over-squashing problem by providing direct shortcut connections that enable long-range propagation of subgraph-level representations. Experiment results show that our method improves the expressive power of MPNNs and achieves comparable or better performance to graph Transformers while maintaining the computational efficiency of MPNN by improving the long-range dependencies of MPNN.

arXiv:2511.12986v1 Announce Type: new Abstract: Branch-and-Bound (B\&B) is the dominant exact solution method for Mixed Integer Linear Programs (MILP), yet its exponential time complexity poses significant challenges for large-scale instances. The growing capabilities of machine learning have spurred efforts to improve B\&B by learning data-driven branching policies. However, most existing approaches rely on Imitation Learning (IL), which tends to overfit to expert demonstrations and struggles to generalize to structurally diverse or unseen instances. In this work, we propose Tree-Gate Proximal Policy Optimization (TGPPO), a novel framework that employs Proximal Policy Optimization (PPO), a Reinforcement Learning (RL) algorithm, to train a branching policy aimed at improving generalization across heterogeneous MILP instances. Our approach builds on a parameterized state space representation that dynamically captures the evolving context of the search tree. Empirical evaluations show that TGPPO often outperforms existing learning-based policies in terms of reducing the number of nodes explored and improving p-Primal-Dual Integrals (PDI), particularly in out-of-distribution instances. These results highlight the potential of RL to develop robust and adaptable branching strategies for MILP solvers.

arXiv:2511.12979v1 Announce Type: new Abstract: Retrieval-Augmented Generation (RAG) is a critical paradigm for building reliable, knowledge-intensive Large Language Model (LLM) applications. However, the multi-stage pipeline (retrieve, generate) and unique workload characteristics (e.g., knowledge dependency) of RAG systems pose significant challenges for serving performance optimization. Existing generic LLM inference traces fail to capture these RAG-specific dynamics, creating a significant performance gap between academic research and real-world deployment. To bridge this gap, this paper introduces RAGPulse, an open-source RAG workload trace dataset. This dataset was collected from an university-wide Q&A system serving that has served more than 40,000 students and faculties since April 2024. We detail RAGPulse's system architecture, its privacy-preserving hash-based data format, and provide an in-depth statistical analysis. Our analysis reveals that real-world RAG workloads exhibit significant temporal locality and a highly skewed hot document access pattern. RAGPulse provides a high-fidelity foundation for researchers to develop and validate novel optimization strategies for RAG systems, such as content-aware batching and retrieval caching, ultimately enhancing the efficiency and reliability of RAG services. The code is available at https://github.com/flashserve/RAGPulse.

arXiv:2511.12955v1 Announce Type: new Abstract: Multivariate time series classification is increasingly investigated in space weather research as a means to predict intense solar flare events, which can cause widespread disruptions across modern technological systems. Magnetic field measurements of solar active regions are converted into structured multivariate time series, enabling predictive modeling across segmented observation windows. However, the inherently imbalanced nature of solar flare occurrences, where intense flares are rare compared to minor flare events, presents a significant barrier to effective learning. To address this challenge, we propose a novel Global Cross-Time Attention Fusion (GCTAF) architecture, a transformer-based model to enhance long-range temporal modeling. Unlike traditional self-attention mechanisms that rely solely on local interactions within time series, GCTAF injects a set of learnable cross-attentive global tokens that summarize salient temporal patterns across the entire sequence. These tokens are refined through cross-attention with the input sequence and fused back into the temporal representation, enabling the model to identify globally significant, non-contiguous time points that are critical for flare prediction. This mechanism functions as a dynamic attention-driven temporal summarizer that augments the model's capacity to capture discriminative flare-related dynamics. We evaluate our approach on the benchmark solar flare dataset and show that GCTAF effectively detects intense flares and improves predictive performance, demonstrating that refining transformer-based architectures presents a high-potential alternative for solar flare prediction tasks.

arXiv:2511.12951v1 Announce Type: new Abstract: Financial markets are inherently volatile and prone to sudden disruptions such as market crashes, flash collapses, and liquidity crises. Accurate anomaly detection and early risk forecasting in financial time series are therefore crucial for preventing systemic instability and supporting informed investment decisions. Traditional deep learning models, such as LSTM and GRU, often fail to capture long-term dependencies and complex periodic patterns in highly nonstationary financial data. To address this limitation, this study proposes a FEDformer-Based Hybrid Framework for Anomaly Detection and Risk Forecasting in Financial Time Series, which integrates the Frequency Enhanced Decomposed Transformer (FEDformer) with a residual-based anomaly detector and a risk forecasting head. The FEDformer module models temporal dynamics in both time and frequency domains, decomposing signals into trend and seasonal components for improved interpretability. The residual-based detector identifies abnormal fluctuations by analyzing prediction errors, while the risk head predicts potential financial distress using learned latent embeddings. Experiments conducted on the S&P 500, NASDAQ Composite, and Brent Crude Oil datasets (2000-2024) demonstrate the superiority of the proposed model over benchmark methods, achieving a 15.7 percent reduction in RMSE and an 11.5 percent improvement in F1-score for anomaly detection. These results confirm the effectiveness of the model in capturing financial volatility, enabling reliable early-warning systems for market crash prediction and risk management.

arXiv:2511.12945v1 Announce Type: new Abstract: Time series forecasting under distribution shift remains challenging, as existing deep learning models often rely on local statistical normalization (e.g., mean and variance) that fails to capture global distribution shift. Methods like RevIN and its variants attempt to decouple distribution and pattern but still struggle with missing values, noisy observations, and invalid channel-wise affine transformation. To address these limitations, we propose Affine Prototype Timestamp (APT), a lightweight and flexible plug-in module that injects global distribution features into the normalization-forecasting pipeline. By leveraging timestamp conditioned prototype learning, APT dynamically generates affine parameters that modulate both input and output series, enabling the backbone to learn from self-supervised, distribution-aware clustered instances. APT is compatible with arbitrary forecasting backbones and normalization strategies while introducing minimal computational overhead. Extensive experiments across six benchmark datasets and multiple backbone-normalization combinations demonstrate that APT significantly improves forecasting performance under distribution shift.

arXiv:2511.12934v1 Announce Type: new Abstract: In industrial recommendation systems, pre-ranking models based on deep neural networks (DNNs) commonly adopt a sequential execution framework: feature fetching and model forward computation are triggered only after receiving candidates from the upstream retrieval stage. This design introduces inherent bottlenecks, including redundant computations of identical users/items and increased latency due to strictly sequential operations, which jointly constrain the model's capacity and system efficiency. To address these limitations, we propose the Asynchronous Inference Framework (AIF), a cost-effective computational architecture that decouples interaction-independent components, those operating within a single user or item, from real-time prediction. AIF reorganizes the model inference process by performing user-side computations in parallel with the retrieval stage and conducting item-side computations in a nearline manner. This means that interaction-independent components are calculated just once and completed before the real-time prediction phase of the pre-ranking stage. As a result, AIF enhances computational efficiency and reduces latency, freeing up resources to significantly improve the feature set and model architecture of interaction-independent components. Moreover, we delve into model design within the AIF framework, employing approximated methods for interaction-dependent components in online real-time predictions. By co-designing both the framework and the model, our solution achieves notable performance gains without significantly increasing computational and latency costs. This has enabled the successful deployment of AIF in the Taobao display advertising system.

arXiv:2511.12903v1 Announce Type: new Abstract: This paper studies the interpretability of neural network features from a Bayesian Gaussian view, where optimizing a cost is reaching a probabilistic bound; learning a model approximates a density that makes the bound tight and the cost optimal, often with a Gaussian mixture density. The two examples are Mixture Density Networks (MDNs) using the bound for the marginal and autoencoders using the conditional bound. It is a known result, not only for autoencoders, that minimizing the error between inputs and outputs maximizes the dependence between inputs and the middle. We use Hilbert space and decomposition to address cases where a multiple-output network produces multiple centers defining a Gaussian mixture. Our first finding is that an autoencoder's objective is equivalent to maximizing the trace of a Gaussian operator, the sum of eigenvalues under bases orthonormal w.r.t. the data and model distributions. This suggests that, when a one-to-one correspondence as needed in autoencoders is unnecessary, we can instead maximize the nuclear norm of this operator, the sum of singular values, to maximize overall rank rather than trace. Thus the trace of a Gaussian operator can be used to train autoencoders, and its nuclear norm can be used as divergence to train MDNs. Our second test uses inner products and norms in a Hilbert space to define bounds and costs. Such bounds often have an extra norm compared to KL-based bounds, which increases sample diversity and prevents the trivial solution where a multiple-output network produces the same constant, at the cost of requiring a sample batch to estimate and optimize. We propose an encoder-mixture-decoder architecture whose decoder is multiple-output, producing multiple centers per sample, potentially tightening the bound. Assuming the data are small-variance Gaussian mixtures, this upper bound can be tracked and analyzed quantitatively.

arXiv:2511.12890v1 Announce Type: new Abstract: Training neural operators to approximate mappings between infinite-dimensional function spaces often requires extensive datasets generated by either demanding experimental setups or computationally expensive numerical solvers. This dependence on solver-based data limits scalability and constrains exploration across physical systems. Here we introduce the Method of Manufactured Learning (MML), a solver-independent framework for training neural operators using analytically constructed, physics-consistent datasets. Inspired by the classical method of manufactured solutions, MML replaces numerical data generation with functional synthesis, i.e., smooth candidate solutions are sampled from controlled analytical spaces, and the corresponding forcing fields are derived by direct application of the governing differential operators. During inference, setting these forcing terms to zero restores the original governing equations, allowing the trained neural operator to emulate the true solution operator of the system. The framework is agnostic to network architecture and can be integrated with any operator learning paradigm. In this paper, we employ Fourier neural operator as a representative example. Across canonical benchmarks including heat, advection, Burgers, and diffusion-reaction equations. MML achieves high spectral accuracy, low residual errors, and strong generalization to unseen conditions. By reframing data generation as a process of analytical synthesis, MML offers a scalable, solver-agnostic pathway toward constructing physically grounded neural operators that retain fidelity to governing laws without reliance on expensive numerical simulations or costly experimental data for training.