Peer Revenue Equity in science

Papers

Fresh from arXiv, typeset properly. Highlighted words trade on the market.

Computer Science Machine Learning

cs.LG Watch Machine Learning (sign in to use)

Saturday 13 December

Machine Learning · Cross-listed from cs.CV

Journey Before Destination: On the importance of Visual Faithfulness in Slow Thinking

Reasoning-augmented vision language models (VLMs) generate explicit chains of thought that promise greater capability and transparency but also introduce new failure modes: models may reach correct answers via visually unfaithful intermediate steps, or reason faithfully yet fail on the final prediction. Standard evaluations that only measure final-answer accuracy cannot distinguish these behaviors. We introduce the visual faithfulness of reasoning chains as a distinct evaluation dimension, focusing on whether the perception steps of a reasoning chain are grounded in the image. We propose a training- and reference-free framework that decomposes chains into perception versus reasoning steps and uses off-the-shelf VLM judges for step-level faithfulness, additionally verifying this approach through a human meta-evaluation. Building on this metric, we present a lightweight self-reflection procedure that detects and locally regenerates unfaithful perception steps without any training. Across multiple reasoning-trained VLMs and perception-heavy benchmarks, our method reduces Unfaithful Perception Rate while preserving final-answer accuracy, improving the reliability of multimodal reasoning.
Read the full abstract

All authors Rheeya Uppaal, Phu Mon Htut, Min Bai, Nikolaos Pappas, Zheng Qi, Sandesh Swamy

Machine Learning

EEG-DLite: Dataset Distillation for Efficient Large EEG Model Training

Large-scale EEG foundation models have shown strong generalization across a range of downstream tasks, but their training remains resource-intensive due to the volume and variable quality of EEG data. In this work, we introduce EEG-DLite, a data distillation framework that enables more efficient pre-training by selectively removing noisy and redundant samples from large EEG datasets. EEG-DLite begins by encoding EEG segments into compact latent representations using a self-supervised autoencoder, allowing sample selection to be performed efficiently and with reduced sensitivity to noise. Based on these representations, EEG-DLite filters out outliers and minimizes redundancy, resulting in a smaller yet informative subset that retains the diversity essential for effective foundation model training. Through extensive experiments, we demonstrate that training on only 5 percent of a 2,500-hour dataset curated with EEG-DLite yields performance comparable to, and in some cases better than, training on the full dataset across multiple downstream tasks. To our knowledge, this is the first systematic study of pre-training data distillation in the context of EEG foundation models. EEG-DLite provides a scalable and practical path toward more effective and efficient physiological foundation modeling. The code is available at https://github.com/t170815518/EEG-DLite.
Read the full abstract

All authors Yuting Tang, Weibang Jiang, Shanglin Li, Yong Li, Chenyu Liu, Xinliang Zhou, Yi Ding, Cuntai Guan

Machine Learning · Cross-listed from cs.CV

ALERT Open Dataset and Input-Size-Agnostic Vision Transformer for Driver Activity Recognition using IR-UWB

Distracted driving contributes to fatal crashes worldwide. To address this, researchers are using driver activity recognition (DAR) with impulse radio ultra-wideband (IR-UWB) radar, which offers advantages such as interference resistance, low power consumption, and privacy preservation. However, two challenges limit its adoption: the lack of large-scale real-world UWB datasets covering diverse distracted driving behaviors, and the difficulty of adapting fixed-input Vision Transformers (ViTs) to UWB radar data with non-standard dimensions. This work addresses both challenges. We present the ALERT dataset, which contains 10,220 radar samples of seven distracted driving activities collected in real driving conditions. We also propose the input-size-agnostic Vision Transformer (ISA-ViT), a framework designed for radar-based DAR. The proposed method resizes UWB data to meet ViT input requirements while preserving radar-specific information such as Doppler shifts and phase characteristics. By adjusting patch configurations and leveraging pre-trained positional embedding vectors (PEVs), ISA-ViT overcomes the limitations of naive resizing approaches. In addition, a domain fusion strategy combines range- and frequency-domain features to further improve classification performance. Comprehensive experiments demonstrate that ISA-ViT achieves a 22.68% accuracy improvement over an existing ViT-based approach for UWB-based DAR. By publicly releasing the ALERT dataset and detailing our input-size-agnostic strategy, this work facilitates the development of more robust and scalable distracted driving detection systems for real-world deployment.
Read the full abstract

All authors Jeongjun Park, Sunwook Hwang, Hyeonho Noh, Jin Mo Yang, Hyun Jong Yang, Saewoong Bahk

Machine Learning

MolGuidance: Advanced Guidance Strategies for Conditional Molecular Generation with Flow Matching

Key objectives in conditional molecular generation include ensuring chemical validity, aligning generated molecules with target properties, promoting structural diversity, and enabling efficient sampling for discovery. Recent advances in computer vision introduced a range of new guidance strategies for generative models, many of which can be adapted to support these goals. In this work, we integrate state-of-the-art guidance methods – including classifier-free guidance, autoguidance, and model guidance – in a leading molecule generation framework built on an SE(3)-equivariant flow matching process. We propose a hybrid guidance strategy that separately guides continuous and discrete molecular modalities – operating on velocity fields and predicted logits, respectively – while jointly optimizing their guidance scales via Bayesian optimization. Our implementation, benchmarked on the QM9 and QMe14S datasets, achieves new state-of-the-art performance in property alignment for de novo molecular generation. The generated molecules also exhibit high structural validity. Furthermore, we systematically compare the strengths and limitations of various guidance methods, offering insights into their broader applicability.
Read the full abstract

All authors Jirui Jin, Cheng Zeng, Pawan Prakash, Ellad B. Tadmor, Adrian Roitberg, Richard G. Hennig, Stefano Martiniani, Mingjie Liu

Machine Learning

HydroDiffusion: Diffusion-Based Probabilistic Streamflow Forecasting with a State Space Backbone

Recent advances have introduced diffusion models for probabilistic streamflow forecasting, demonstrating strong early flood-warning skill. However, current implementations rely on recurrent Long Short-Term Memory (LSTM) backbones and single-step training objectives, which limit their ability to capture long-range dependencies and produce coherent forecast trajectories across lead times. To address these limitations, we developed HydroDiffusion, a diffusion-based probabilistic forecasting framework with a decoder-only state space model backbone. The proposed framework jointly denoises full multi-day trajectories in a single pass, ensuring temporal coherence and mitigating error accumulation common in autoregressive prediction. HydroDiffusion is evaluated across 531 watersheds in the contiguous United States (CONUS) in the CAMELS dataset. We benchmark HydroDiffusion against two diffusion baselines with LSTM backbones, as well as the recently proposed Diffusion-based Runoff Model (DRUM). Results show that HydroDiffusion achieves strong nowcast accuracy when driven by observed meteorological forcings, and maintains consistent performance across the full simulation horizon. Moreover, HydroDiffusion delivers stronger deterministic and probabilistic forecast skill than DRUM in operational forecasting. These results establish HydroDiffusion as a robust generative modeling framework for medium-range streamflow forecasting, providing both a new modeling benchmark and a foundation for future research on probabilistic hydrologic prediction at continental scales.
Read the full abstract

All authors Yihan Wang, Annan Yu, Lujun Zhang, Charuleka Varadharajan, N. Benjamin Erichson

Machine Learning · Cross-listed from cs.AI

TA-KAND: Two-stage Attention Triple Enhancement and U-KAN based Diffusion For Few-shot Knowledge Graph Completion

Knowledge Graphs have become fundamental infrastructure for applications such as intelligent question answering and recommender systems due to their expressive representation. Nevertheless, real-world knowledge is heterogeneous, leading to a pronounced long-tailed distribution over relations. Previous studies mainly based on metric matching or meta learning. However, they often overlook the distributional characteristics of positive and negative triple samples. In this paper, we propose a few-shot knowledge graph completion framework that integrates two-stage attention triple enhancer with U-KAN based diffusion model. Extensive experiments on two public datasets show significant advantages of our methods.
Read the full abstract

Machine Learning · Cross-listed from eess.SP

A Sensing Dataset Protocol for Benchmarking and Multi-Task Wireless Sensing

Wireless sensing has become a fundamental enabler for intelligent environments, supporting applications such as human detection, activity recognition, localization, and vital sign monitoring. Despite rapid advances, existing datasets and pipelines remain fragmented across sensing modalities, hindering fair comparison, transfer, and reproducibility. We propose the Sensing Dataset Protocol (SDP), a protocol-level specification and benchmark framework for large-scale wireless sensing. SDP defines how heterogeneous wireless signals are mapped into a unified perception data-block schema through lightweight synchronization, frequency-time alignment, and resampling, while a Canonical Polyadic-Alternating Least Squares (CP-ALS) pooling stage provides a task-agnostic representation that preserves multipath, spectral, and temporal structures. Built upon this protocol, a unified benchmark is established for detection, recognition, and vital-sign estimation with consistent preprocessing, training, and evaluation. Experiments under the cross-user split demonstrate that SDP significantly reduces variance (approximately 88%) across seeds while maintaining competitive accuracy and latency, confirming its value as a reproducible foundation for multi-modal and multitask sensing research.
Read the full abstract

All authors Jiawei Huang, Di Zhang, Yuanhao Cui, Xiaowen Cao, Tony Xiao Han, Xiaojun Jing, Christos Masouros

Machine Learning · Cross-listed from cs.CR

Keep the Lights On, Keep the Lengths in Check: Plug-In Adversarial Detection for Time-Series LLMs in Energy Forecasting

Accurate time-series forecasting is increasingly critical for planning and operations in low-carbon power systems. Emerging time-series large language models (TS-LLMs) now deliver this capability at scale, requiring no task-specific retraining, and are quickly becoming essential components within the Internet-of-Energy (IoE) ecosystem. However, their real-world deployment is complicated by a critical vulnerability: adversarial examples (AEs). Detecting these AEs is challenging because (i) adversarial perturbations are optimized across the entire input sequence and exploit global temporal dependencies, which renders local detection methods ineffective, and (ii) unlike traditional forecasting models with fixed input dimensions, TS-LLMs accept sequences of variable length, increasing variability that complicates detection. To address these challenges, we propose a plug-in detection framework that capitalizes on the TS-LLM's own variable-length input capability. Our method uses sampling-induced divergence as a detection signal. Given an input sequence, we generate multiple shortened variants and detect AEs by measuring the consistency of their forecasts: Benign sequences tend to produce stable predictions under sampling, whereas adversarial sequences show low forecast similarity, because perturbations optimized for a full-length sequence do not transfer reliably to shorter, differently-structured subsamples. We evaluate our approach on three representative TS-LLMs (TimeGPT, TimesFM, and TimeLLM) across three energy datasets: ETTh2 (Electricity Transformer Temperature), NI (Hourly Energy Consumption), and Consumption (Hourly Electricity Consumption and Production). Empirical results confirm strong and robust detection performance across both black-box and white-box attack scenarios, highlighting its practicality as a reliable safeguard for TS-LLM forecasting in real-world energy systems.
Read the full abstract

All authors Hua Ma, Ruoxi Sun, Minhui Xue, Xingliang Yuan, Carsten Rudolph, Surya Nepal, Ling Liu

Machine Learning · Cross-listed from cs.CV

MeltwaterBench: Deep learning for spatiotemporal downscaling of surface meltwater

The Greenland ice sheet is melting at an accelerated rate due to processes that are not fully understood and hard to measure. The distribution of surface meltwater can help understand these processes and is observable through remote sensing, but current maps of meltwater face a trade-off: They are either high-resolution in time or space, but not both. We develop a deep learning model that creates gridded surface meltwater maps at daily 100m resolution by fusing data streams from remote sensing observations and physics-based models. In particular, we spatiotemporally downscale regional climate model (RCM) outputs using synthetic aperture radar (SAR), passive microwave (PMW), and a digital elevation model (DEM) over the Helheim Glacier in Eastern Greenland from 2017-2023. Using SAR-derived meltwater as "ground truth", we show that a deep learning-based method that fuses all data streams is over 10 percentage points more accurate over our study area than existing non deep learning-based approaches that only rely on a regional climate model (83% vs. 95% Acc.) or passive microwave observations (72% vs. 95% Acc.). Alternatively, creating a gridded product through a running window calculation with SAR data underestimates extreme melt events, but also achieves notable accuracy (90%) and does not rely on deep learning. We evaluate standard deep learning methods (UNet and DeepLabv3+), and publish our spatiotemporally aligned dataset as a benchmark, MeltwaterBench, for intercomparisons with more complex data-driven downscaling methods. The code and data are available at github.com/blutjens/hrmelt.
Read the full abstract

All authors Björn Lütjens, Patrick Alexander, Raf Antwerpen, Til Widmann, Guido Cervone, Marco Tedesco

Machine Learning

BaRISTA: Brain Scale Informed Spatiotemporal Representation of Human Intracranial Neural Activity

Intracranial recordings have opened a unique opportunity to simultaneously measure activity across multiregional networks in the human brain. Recent works have focused on developing transformer-based neurofoundation models of such recordings that can generalize across subjects and datasets. However, these recordings exhibit highly complex spatiotemporal interactions across diverse spatial scales, from the single-channel scale to the scale of brain regions. As such, there remain critical open questions regarding how best to encode spatial information and how to design self-supervision tasks that enable the learning of brain network patterns and enhance downstream decoding performance using such high-dimensional, multiregional recordings. To allow for exploring these questions, we propose a new spatiotemporal transformer model of multiregional neural activity and a corresponding self-supervised masked latent reconstruction task, designed to enable flexibility in the spatial scale used for token encoding and masking. Applying this model on publicly available multiregional intracranial electrophysiology (iEEG) data, we demonstrate that adjusting the spatial scale for both token encoding and masked reconstruction significantly impacts downstream decoding. Further, we find that spatial encoding at larger scales than channel-level encoding, which is commonly used in existing iEEG transformer models, improves downstream decoding performance. Finally, we demonstrate that our method allows for region-level token encoding while also maintaining accurate channel-level neural reconstruction. Taken together, our modeling framework enables exploration of the spatial scales used for token encoding and masking, reveals their importance towards self-supervised pretraining of neurofoundation models of multiregional human brain activity, and enhances downstream decoding performance.
Read the full abstract

Machine Learning · Cross-listed from q-bio.BM

Modeling Dabrafenib Response Using Multi-Omics Modality Fusion and Protein Network Embeddings Based on Graph Convolutional Networks

Cancer cell response to targeted therapy arises from complex molecular interactions, making single omics insufficient for accurate prediction. This study develops a model to predict Dabrafenib sensitivity by integrating multiple omics layers (genomics, transcriptomics, proteomics, epigenomics, and metabolomics) with protein network embeddings generated using Graph Convolutional Networks (GCN). Each modality is encoded into low dimensional representations through neural network preprocessing. Protein interaction information from STRING is incorporated using GCN to capture biological topology. An attention based fusion mechanism assigns adaptive weights to each modality according to its relevance. Using GDSC cancer cell line data, the model shows that selective integration of two modalities, especially proteomics and transcriptomics, achieves the best test performance (R2 around 0.96), outperforming all single omics and full multimodal settings. Genomic and epigenomic data were less informative, while proteomic and transcriptomic layers provided stronger phenotypic signals related to MAPK inhibitor activity. These results show that attention guided multi omics fusion combined with GCN improves drug response prediction and reveals complementary molecular determinants of Dabrafenib sensitivity. The approach offers a promising computational framework for precision oncology and predictive modeling of targeted therapies.
Read the full abstract

All authors La Ode Aman, A Mu'thi Andy Suryadi, Dizky Ramadani Putri Papeo, Hamsidar Hasan, Ariani H Hutuba, Netty Ino Ischak, Yuszda K. Salimi

Machine Learning

Approximation with SiLU Networks: Constant Depth and Exponential Rates for Basic Operations

We present SiLU network constructions whose approximation efficiency depends critically on proper hyperparameter tuning. For the square function $x^2$, with optimally chosen shift $a$ and scale $\beta$, we achieve approximation error $\varepsilon$ using a two-layer network of constant width, where weights scale as $\beta^{\pm k}$ with $k = \mathcal{O}(\ln(1/\varepsilon))$. We then extend this approach through functional composition to Sobolev spaces, we obtain networks with depth $\mathcal{O}(1)$ and $\mathcal{O}(\varepsilon^{-d/n})$ parameters under optimal hyperparameters settings. Our work highlights the trade-off between architectural depth and activation parameter optimization in neural network approximation theory.
Read the full abstract

Machine Learning

BOOST: BOttleneck-Optimized Scalable Training Framework for Low-Rank Large Language Models

The scale of transformer model pre-training is constrained by the increasing computation and communication cost. Low-rank bottleneck architectures offer a promising solution to significantly reduce the training time and memory footprint with minimum impact on accuracy. Despite algorithmic efficiency, bottleneck architectures scale poorly under standard tensor parallelism. Simply applying 3D parallelism designed for full-rank methods leads to excessive communication and poor GPU utilization. To address this limitation, we propose BOOST, an efficient training framework tailored for large-scale low-rank bottleneck architectures. BOOST introduces a novel Bottleneck-aware Tensor Parallelism, and combines optimizations such as online-RMSNorm, linear layer grouping, and low-rank activation checkpointing to achieve end-to-end training speedup. Evaluations on different low-rank bottleneck architectures demonstrate that BOOST achieves 1.46-1.91$\times$ speedup over full-rank model baselines and 1.87-2.27$\times$ speedup over low-rank model with naively integrated 3D parallelism, with improved GPU utilization and reduced communication overhead.
Read the full abstract

All authors Zhengyang Wang, Ziyue Liu, Ruijie Zhang, Avinash Maurya, Paul Hovland, Bogdan Nicolae, Franck Cappello, Zheng Zhang

Machine Learning

High-Dimensional Tensor Discriminant Analysis: Low-Rank Discriminant Structure, Representation Synergy, and Theoretical Guarantees

High-dimensional tensor-valued predictors arise in modern applications, increasingly as learned representations from neural networks. Existing tensor classification methods rely on sparsity or Tucker structures and often lack theoretical guarantees. Motivated by empirical evidence that discriminative signals concentrate along a few multilinear components, we introduce CP low-rank structure for the discriminant tensor, a modeling perspective not previously explored. Under a Tensor Gaussian Mixture Model, we propose high-dimensional CP low-rank Tensor Discriminant Analysis (CP-TDA) with Randomized Composite PCA (rc-PCA) initialization, that is essential for handling dependent and anisotropic noise under weaker signal strength and incoherence conditions, followed by iterative refinement algorithm. We establish global convergence and minimax-optimal misclassification rates. To handle tensor data deviating from tensor normality, we develop the first semiparametric tensor discriminant model, in which learned tensor representations are mapped via deep generative models into a latent space tailored for CP-TDA. Misclassification risk decomposes into representation, approximation, and estimation errors. Numerical studies and real data analysis on graph classification demonstrate substantial gains over existing tensor classifiers and state-of-the-art graph neural networks, particularly in high-dimensional, small-sample regimes.
Read the full abstract

Machine Learning

MixtureKit: A General Framework for Composing, Training, and Visualizing Mixture-of-Experts Models

We introduce MixtureKit, a modular open-source framework for constructing, training, and analyzing Mixture-of-Experts (MoE) models from arbitrary pre-trained or fine-tuned models. MixtureKit currently supports three complementary methods: (i) Traditional MoE, which uses a single router per transformer block to select experts, (ii) BTX (Branch-Train-Mix), which introduces separate routers for each specified sub-layer enabling fine-grained token routing, and (iii) BTS (Branch-Train-Stitch), which keeps experts fully intact and introduces trainable stitch layers for controlled information exchange between hub and experts. MixtureKit automatically modifies the model configuration, patches decoder and causal LM classes, and saves a unified checkpoint ready for inference or fine-tuning. We further provide a visualization interface to inspect per-token routing decisions, expert weight distributions, and layer-wise contributions. Experiments with multilingual code-switched data (e.g. Arabic-Latin) show that a BTX-based model trained using MixtureKit can outperform baseline dense models on multiple benchmarks. We release MixtureKit as a practical foundation for research and development of MoE-based systems across diverse domains.
Read the full abstract

Machine Learning · Cross-listed from cs.SE

Citation-Grounded Code Comprehension: Preventing LLM Hallucination Through Hybrid Retrieval and Graph-Augmented Context

Large language models have become essential tools for code comprehension, enabling developers to query unfamiliar codebases through natural language interfaces. However, LLM hallucination, generating plausible but factually incorrect citations to source code, remains a critical barrier to reliable developer assistance. This paper addresses the challenges of achieving verifiable, citation grounded code comprehension through hybrid retrieval and lightweight structural reasoning. Our work is grounded in systematic evaluation across 30 Python repositories with 180 developer queries, comparing retrieval modalities, graph expansion strategies, and citation verification mechanisms. We find that challenges of citation accuracy arise from the interplay between sparse lexical matching, dense semantic similarity, and cross file architectural dependencies. Among these, cross file evidence discovery is the largest contributor to citation completeness, but it is largely overlooked because existing systems rely on pure textual similarity without leveraging code structure. We advocate for citation grounded generation as an architectural principle for code comprehension systems and demonstrate this need by achieving 92 percent citation accuracy with zero hallucinations. Specifically, we develop a hybrid retrieval system combining BM25 sparse matching, BGE dense embeddings, and Neo4j graph expansion via import relationships, which outperforms single mode baselines by 14 to 18 percentage points while discovering cross file evidence missed by pure text similarity in 62 percent of architectural queries.
Read the full abstract

Machine Learning

Neural CDEs as Correctors for Learned Time Series Models

Learned time-series models, whether continuous or discrete, are widely used for forecasting the states of dynamical systems but suffer from error accumulation in multi-step forecasts. To address this issue, we propose a Predictor-Corrector framework in which the Predictor is a learned time-series model that generates multi-step forecasts and the Corrector is a neural controlled differential equation that corrects the forecast errors. The Corrector works with irregularly sampled time series and is compatible with both continuous- and discrete-time Predictors. We further introduce two regularization strategies that improve the Corrector's extrapolation performance and accelerate its training. We also provide theoretical guarantees on the stability and convergence of the proposed framework. Experiments on synthetic, physics-based, and real-world datasets show that the proposed framework consistently improves forecasting performance across diverse Predictors, including neural ordinary differential equations, ContiFormer, and DLinear, demonstrating its predictor-agnostic nature.
Read the full abstract

All authors Muhammad Bilal Shahid, Zhanhong Jiang, Prajwal Koirala, Soumik Sarkar, Cody Fleming

Machine Learning · Cross-listed from cs.CV

A Novel Patch-Based TDA Approach for Computed Tomography Imaging

The development of machine learning models based on computed tomography (CT) imaging has been a major focus due to the promise that imaging holds for diagnosis, staging, and prognostication. These models often rely on the extraction of hand-crafted features where incorporating robust feature engineering improves the performance of these models. Topological data analysis (TDA), based on the mathematical field of algebraic topology, focuses on data from a topological perspective, extracting deeper insight and higher dimensional structures. Persistent homology (PH), a fundamental tool in TDA, extracts topological features such as connected components, cycles, and voids. A popular approach to construct PH from 3D CT images is to utilize 3D cubical complex filtration, a method adapted for grid-structured data. However, this approach is subject to poor performance and high computational cost with higher resolution images. This study introduces a novel patch-based PH construction approach designed for volumetric CT imaging data that improves performance and reduces computational time. This study conducts a series of experiments to comprehensively analyze the performance of the proposed method and benchmarks against the cubical complex algorithm and radiomic features. Our results highlight the dominance of the patch-based TDA approach in terms of both classification performance and computational time. The proposed approach outperformed the cubical complex method and radiomic features, achieving average improvement of 7.2%, 3.6%, 2.7%, 8.0%, and 7.2% in accuracy, AUC, sensitivity, specificity, and F1 score, respectively, across all datasets. Finally, we provide a convenient Python package, Patch-TDA, to facilitate the utilization of the proposed approach.
Read the full abstract

All authors Dashti A. Ali, Aras T. Asaad, Jacob J. Peoples, Ahmad Bashir Barekzai, Camila Vilela, Hala Khasawneh, Jayasree Chakraborty, João Miranda, Mohammad Hamghalam, Natalie Gangai, Natally Horvat, Richard K. G. Do, Alice C. Wei, Amber L. Simpson

Machine Learning · Cross-listed from cs.CV

AI-Augmented Pollen Recognition in Optical and Holographic Microscopy for Veterinary Imaging

We present a comprehensive study on fully automated pollen recognition across both conventional optical and digital in-line holographic microscopy (DIHM) images of sample slides. Visually recognizing pollen in unreconstructed holographic images remains challenging due to speckle noise, twin-image artifacts and substantial divergence from bright-field appearances. We establish the performance baseline by training YOLOv8s for object detection and MobileNetV3L for classification on a dual-modality dataset of automatically annotated optical and affinely aligned DIHM images. On optical data, detection mAP50 reaches 91.3% and classification accuracy reaches 97%, whereas on DIHM data, we achieve only 8.15% for detection mAP50 and 50% for classification accuracy. Expanding the bounding boxes of pollens in DIHM images over those acquired in aligned optical images achieves 13.3% for detection mAP50 and 54% for classification accuracy. To improve object detection in DIHM images, we employ a Wasserstein GAN with spectral normalization (WGAN-SN) to create synthetic DIHM images, yielding an FID score of 58.246. Mixing real-world and synthetic data at the 1.0 : 1.5 ratio for DIHM images improves object detection up to 15.4%. These results demonstrate that GAN-based augmentation can reduce the performance divide, bringing fully automated DIHM workflows for veterinary imaging a small but important step closer to practice.
Read the full abstract

All authors Swarn S. Warshaneyan, Maksims Ivanovs, Blaž Cugmas, Inese Bērziņa, Laura Goldberga, Mindaugas Tamosiunas, Roberts Kadiķis

Friday 12 December

Machine Learning · Cross-listed from cs.AR

CHIME: Chiplet-based Heterogeneous Near-Memory Acceleration for Edge Multimodal LLM Inference

The proliferation of large language models (LLMs) is accelerating the integration of multimodal assistants into edge devices, where inference is executed under stringent latency and energy constraints, often exacerbated by intermittent connectivity. These challenges become particularly acute in the context of multimodal LLMs (MLLMs), as high-dimensional visual inputs are transformed into extensive token sequences, thereby inflating the key-value (KV) cache and imposing substantial data movement overheads to the LLM backbone. To address these issues, we present CHIME, a chiplet-based heterogeneous near-memory acceleration for edge MLLMs inference. CHIME leverages the complementary strengths of integrated monolithic 3D (M3D) DRAM and RRAM chiplets: DRAM supplies low-latency bandwidth for attention, while RRAM offers dense, non-volatile storage for weights. This heterogeneous hardware is orchestrated by a co-designed mapping framework that executes fused kernels near data, minimizing cross-chiplet traffic to maximize effective bandwidth. On FastVLM (0.6B/1.7B) and MobileVLM (1.7B/3B), CHIME achieves up to 54x speedup and up to 246x better energy efficiency per inference as compared to the edge GPU NVIDIA Jetson Orin NX. It sustains 116.5-266.5 token/J compared to Jetson's 0.7-1.1 token/J. Furthermore, it delivers up to 69.2x higher throughput than the state-of-the-art PIM accelerator FACIL. Compared to the M3D DRAM-only design, CHIME's heterogeneous memory further improves energy efficiency by 7% and performance by 2.4x.
Read the full abstract

All authors Yanru Chen, Runyang Tian, Yue Pan, Zheyu Li, Weihong Xu, Tajana Rosing

Machine Learning

Forecasting N-Body Dynamics: A Comparative Study of Neural Ordinary Differential Equations and Universal Differential Equations

The n body problem, fundamental to astrophysics, simulates the motion of n bodies acting under the effect of their own mutual gravitational interactions. Traditional machine learning models that are used for predicting and forecasting trajectories are often data intensive black box models, which ignore the physical laws, thereby lacking interpretability. Whereas Scientific Machine Learning ( Scientific ML ) directly embeds the known physical laws into the machine learning framework. Through robust modelling in the Julia programming language, our method uses the Scientific ML frameworks: Neural ordinary differential equations (NODEs) and Universal differential equations (UDEs) to predict and forecast the system dynamics. In addition, an essential component of our analysis involves determining the forecasting breakdown point, which is the smallest possible amount of training data our models need to predict future, unseen data accurately. We employ synthetically created noisy data to simulate real-world observational limitations. Our findings indicate that the UDE model is much more data efficient, needing only 20% of data for a correct forecast, whereas the Neural ODE requires 90%.
Read the full abstract

All authors Suriya R S, Prathamesh Dinesh Joshi, Rajat Dandekar, Raj Dandekar, Sreedath Panat

Machine Learning · Cross-listed from cs.CR

Data-Chain Backdoor: Do You Trust Diffusion Models as Generative Data Supplier?

The increasing use of generative models such as diffusion models for synthetic data augmentation has greatly reduced the cost of data collection and labeling in downstream perception tasks. However, this new data source paradigm may introduce important security concerns. Publicly available generative models are often reused without verification, raising a fundamental question of their safety and trustworthiness. This work investigates backdoor propagation in such emerging generative data supply chain, namely, Data-Chain Backdoor (DCB). Specifically, we find that open-source diffusion models can become hidden carriers of backdoors. Their strong distribution-fitting ability causes them to memorize and reproduce backdoor triggers in generation, which are subsequently inherited by downstream models, resulting in severe security risks. This threat is particularly concerning under clean-label attack scenarios, as it remains effective while having negligible impact on the utility of the synthetic data. We study two attacker choices to obtain a backdoor-carried generator, training from scratch and fine-tuning. While naive fine-tuning leads to weak inheritance of the backdoor, we find that novel designs in the loss objectives and trigger processing can substantially improve the generator's ability to preserve trigger patterns, making fine-tuning a low-cost attack path. We evaluate the effectiveness of DCB under the standard augmentation protocol and further assess data-scarce settings. Across multiple trigger types, we observe that the trigger pattern can be consistently retained in the synthetic data with attack efficacy comparable to the conventional backdoor attack.
Read the full abstract

All authors Junchi Lu, Xinke Li, Yuheng Liu, Qi Alfred Chen

Machine Learning · Cross-listed from cs.CR

PHANTOM: Progressive High-fidelity Adversarial Network for Threat Object Modeling

The scarcity of cyberattack data hinders the development of robust intrusion detection systems. This paper introduces PHANTOM, a novel adversarial variational framework for generating high-fidelity synthetic attack data. Its innovations include progressive training, a dual-path VAE-GAN architecture, and domain-specific feature matching to preserve the semantics of attacks. Evaluated on 100,000 network traffic samples, models trained on PHANTOM data achieve 98% weighted accuracy on real attacks. Statistical analyses confirm that the synthetic data preserves authentic distributions and diversity. Limitations in generating rare attack types are noted, highlighting challenges with severe class imbalance. This work advances the generation of synthetic data for training robust, privacy-preserving detection systems.
Read the full abstract

Machine Learning

Bridging Data and Physics: A Graph Neural Network-Based Hybrid Twin Framework

Simulating complex unsteady physical phenomena relies on detailed mathematical models, simulated for instance by using the Finite Element Method (FEM). However, these models often exhibit discrepancies from the reality due to unmodeled effects or simplifying assumptions. We refer to this gap as the ignorance model. While purely data-driven approaches attempt to learn full system behavior, they require large amounts of high-quality data across the entire spatial and temporal domain. In real-world scenarios, such information is unavailable, making full data-driven modeling unreliable. To overcome this limitation, we model of the ignorance component using a hybrid twin approach, instead of simulating phenomena from scratch. Since physics-based models approximate the overall behavior of the phenomena, the remaining ignorance is typically lower in complexity than the full physical response, therefore, it can be learned with significantly fewer data. A key difficulty, however, is that spatial measurements are sparse, also obtaining data measuring the same phenomenon for different spatial configurations is challenging in practice. Our contribution is to overcome this limitation by using Graph Neural Networks (GNNs) to represent the ignorance model. GNNs learn the spatial pattern of the missing physics even when the number of measurement locations is limited. This allows us to enrich the physics-based model with data-driven corrections without requiring dense spatial, temporal and parametric data. To showcase the performance of the proposed method, we evaluate this GNN-based hybrid twin on nonlinear heat transfer problems across different meshes, geometries, and load positions. Results show that the GNN successfully captures the ignorance and generalizes corrections across spatial configurations, improving simulation accuracy and interpretability, while minimizing data requirements.
Read the full abstract

All authors M. Gorpinich, B. Moya, S. Rodriguez, F. Meraghni, Y. Jaafra, A. Briot, M. Henner, R. Leon, F. Chinesta

Machine Learning

Shapley-based Data Valuation for LLM Alignment via Sequential Preference Optimization

Data valuation is a natural framework for understanding which data sources matter most when aligning a Large Language Model (LLM) from multiple sources. The standard game-theoretic approach treats each source, or equivalently each preference dataset, as a player in a cooperative game and assigns it a contribution score through the Shapley value. In practice, however, Shapley-based valuation is computationally prohibitive because it requires aligning a separate model for every possible coalition of sources, i.e., an exponential number of alignments. We address this challenge for Direct Alignment Algorithms (DAAs), including IPO, which learn through log-policy ratios with respect to a reference policy. We show that, when a model is aligned sequentially source by source, exact optimization makes each stage contribute additively to the log-probability of a full response, up to a prompt-dependent normalization constant. This allows the log-probability assigned by any coalition to a fixed response to be reconstructed from the base policy and the policies trained on each source individually. This reduces the alignment cost of Shapley-based valuation from exponential to linear, since only one model per source needs to be trained to evaluate coalition scores. We test whether this theoretical property remains approximately valid under finite training across several base models and real-world data sources. We finally compute the Shapley values of these sources under multiple reward models, showing how their estimated contributions vary across evaluation criteria.
Read the full abstract

All authors Mélissa Tamine, Otmane Sakhi, Benjamin Heymann, Maxime Vono, Patrick Loiseau

Machine Learning

AdaGradSelect: An adaptive gradient-guided layer selection method for efficient fine-tuning of SLMs

Large Language Models (LLMs) can perform many NLP tasks well, but fully fine-tuning them is expensive and requires a lot of memory. Parameter-Efficient Fine-Tuning (PEFT) methods such as LoRA reduce this cost by adding small low-rank updates to frozen model weights. However, these methods restrict the training to a limited subspace, which can sometimes reduce performance. For Small Language Models (SLMs), where efficiency gains matter even more, we introduce AdaGradSelect, an adaptive method that selects which transformer blocks to update based on gradients. Early observations showed that updating only the transformer blocks with the highest gradient norms can achieve performance close to full fine-tuning. Building on this insight, AdaGradSelect adaptively chooses which blocks to train. It uses a combination of Dirichlet-based sampling, which depends on how frequently blocks were updated in the past, and an epsilon-greedy exploration strategy. This lets the method explore different blocks in early training and gradually focus on the most important ones in later epochs. Experiments show that AdaGradSelect trains about 12 percent faster and uses 35 percent less GPU memory while delivering performance very close to full fine-tuning. On the GSM8K dataset, it outperforms LoRA (rank 256) by about 3 percent on average across models such as Qwen2.5-0.5B, LLaMA3.2-1B, and Phi4-mini-3.8B. It also achieves similar accuracy on the MATH dataset. Overall, AdaGradSelect provides a more effective and resource-efficient alternative to traditional fine-tuning methods.
Read the full abstract

Machine Learning

Cross-Sample Augmented Test-Time Adaptation for Personalized Intraoperative Hypotension Prediction

Intraoperative hypotension (IOH) poses significant surgical risks, but accurate prediction remains challenging due to patient-specific variability. While test-time adaptation (TTA) offers a promising approach for personalized prediction, the rarity of IOH events often leads to unreliable test-time training. To address this, we propose CSA-TTA, a novel Cross-Sample Augmented Test-Time Adaptation framework that enhances training by incorporating hypotension events from other individuals. Specifically, we first construct a cross-sample bank by segmenting historical data into hypotensive and non-hypotensive samples. Then, we introduce a coarse-to-fine retrieval strategy for building test-time training data: we initially apply K-Shape clustering to identify representative cluster centers and subsequently retrieve the top-K semantically similar samples based on the current patient signal. Additionally, we integrate both self-supervised masked reconstruction and retrospective sequence forecasting signals during training to enhance model adaptability to rapid and subtle intraoperative dynamics. We evaluate the proposed CSA-TTA on both the VitalDB dataset and a real-world in-hospital dataset by integrating it with state-of-the-art time series forecasting models, including TimesFM and UniTS. CSA-TTA consistently enhances performance across settings-for instance, on VitalDB, it improves Recall and F1 scores by +1.33% and +1.13%, respectively, under fine-tuning, and by +7.46% and +5.07% in zero-shot scenarios-demonstrating strong robustness and generalization.
Read the full abstract

All authors Kanxue Li, Yibing Zhan, Hua Jin, Chongchong Qi, Xu Lin, Baosheng Yu

Machine Learning

Machine Learning Framework for Thrombosis Risk Prediction in Rotary Blood Pumps

Thrombosis in rotary blood pumps arises from complex flow conditions that remain difficult to translate into reliable and interpretable risk predictions using existing computational models. This limitation reflects an incomplete understanding of how specific flow features contribute to thrombus initiation and growth. This study introduces an interpretable machine learning framework for spatial thrombosis assessment based directly on computational fluid dynamics-derived flow features. A logistic regression (LR) model combined with a structured feature-selection pipeline is used to derive a compact and physically interpretable feature set, including nonlinear feature combinations. The framework is trained using spatial risk patterns from a validated, macro-scale thrombosis model for two representative scenarios. The model reproduces the labeled risk distributions and identifies distinct sets of flow features associated with increased thrombosis risk. When applied to a centrifugal pump, despite training on a single axial pump operating point, the model predicts plausible thrombosis-prone regions. These results show that interpretable machine learning can link local flow features to thrombosis risk while remaining computationally efficient and mechanistically transparent. The low computational cost enables rapid thrombogenicity screening without repeated or costly simulations. The proposed framework complements physics-based thrombosis modeling and provides a methodological basis for integrating interpretable machine learning into CFD-driven thrombosis analysis and device design workflows.
Read the full abstract

Machine Learning

A Tutorial on Dimensionless Learning: Geometric Interpretation and the Effect of Noise

Dimensionless learning is a data-driven framework for discovering dimensionless numbers and scaling laws from experimental measurements. This tutorial introduces the method, explaining how it transforms experimental data into compact physical laws that reveal compact dimensional invariance between variables. The approach combines classical dimensional analysis with modern machine learning techniques. Starting from measurements of physical quantities, the method identifies the fundamental ways to combine variables into dimensionless groups, then uses neural networks to discover which combinations best predict the experimental output. A key innovation is a regularization technique that encourages the learned coefficients to take simple, interpretable values like integers or half-integers, making the discovered laws both accurate and physically meaningful. We systematically investigate how measurement noise and discrete sampling affect the discovery process, demonstrating that the regularization approach provides robustness to experimental uncertainties. The method successfully handles cases with single or multiple dimensionless numbers, revealing how different but equivalent representations can capture the same underlying physics. Despite recent progress, key challenges remain, including managing the computational cost of identifying multiple dimensionless groups, understanding the influence of data characteristics, automating the selection of relevant input variables, and developing user-friendly tools for experimentalists. This tutorial serves as both an educational resource and a practical guide for researchers seeking to apply dimensionless learning to their experimental data.
Read the full abstract

Machine Learning

Semantic-Constrained Federated Aggregation: Convergence Theory and Privacy-Utility Bounds for Knowledge-Enhanced Distributed Learning

Federated learning enables collaborative model training across distributed data sources but suffers from slow convergence under non-IID data conditions. Existing solutions employ algorithmic modifications treating all client updates identically, ignoring semantic validity. We introduce Semantic-Constrained Federated Aggregation (SCFA), a theoretically-grounded framework incorporating domain knowledge constraints into distributed optimization. We prove SCFA achieves convergence rate O(1/sqrt(T) + rho) where rho represents constraint violation rate, establishing the first convergence theory for constraint-based federated learning. Our analysis shows constraints reduce effective data heterogeneity by 41% and improve privacy-utility tradeoffs through hypothesis space reduction by factor theta=0.37. Under (epsilon,delta)-differential privacy with epsilon=10, constraint regularization maintains utility within 3.7% of non-private baseline versus 12.1% degradation for standard federated learning, representing 2.7x improvement. We validate our framework on manufacturing predictive maintenance using Bosch production data with 1.18 million samples and 968 sensor features, constructing knowledge graphs encoding 3,000 constraints from ISA-95 and MASON ontologies. Experiments demonstrate 22% faster convergence, 41.3% model divergence reduction, and constraint violation thresholds where rho<0.05 maintains 90% optimal performance while rho>0.18 causes catastrophic failure. Our theoretical predictions match empirical observations with R^2>0.90 across convergence, privacy, and violation-performance relationships.
Read the full abstract