Peer Revenue Returns subject to peer review

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)

Wednesday 21 January

Machine Learning

Dimensional Peeking for Low-Variance Gradients in Zeroth-Order Discrete Optimization via Simulation

Gradient-based optimization methods are commonly used to identify local optima in high-dimensional spaces. When derivatives cannot be evaluated directly, stochastic estimators can provide approximate gradients. However, these estimators' perturbation-based sampling of the objective function introduces variance that can lead to slow convergence. In this paper, we present dimensional peeking, a variance reduction method for gradient estimation in discrete optimization via simulation. By lifting the sampling granularity from scalar values to classes of values that follow the same control flow path, we increase the information gathered per simulation evaluation. Our derivation from an established smoothed gradient estimator shows that the method does not introduce any bias. We present an implementation via a custom numerical data type to transparently carry out dimensional peeking over C++ programs. Variance reductions by factors of up to 7.9 are observed for three simulation-based optimization problems with high-dimensional input. The optimization progress compared to three meta-heuristics shows that dimensional peeking increases the competitiveness of zeroth-order optimization for discrete and non-convex simulations.
Read the full abstract

Machine Learning · Cross-listed from math.NA

Large Language Models: A Mathematical Formulation

Large language models (LLMs) process and predict sequences containing text to answer questions, and address tasks including document summarization, providing recommendations, writing software and solving quantitative problems. We provide a mathematical framework for LLMs by describing the encoding of text sequences into sequences of tokens, defining the architecture for next-token prediction models, explaining how these models are learned from data, and demonstrating how they are deployed to address a variety of tasks. The mathematical sophistication required to understand this material is not high, and relies on straightforward ideas from information theory, probability and optimization. Nonetheless, the combination of ideas resting on these different components from the mathematical sciences yields a complex algorithmic structure; and this algorithmic structure has demonstrated remarkable empirical successes. The mathematical framework established here provides a platform from which it is possible to formulate and address questions concerning the accuracy, efficiency and robustness of the algorithms that constitute LLMs. The framework also suggests directions for development of modified and new methodologies.
Read the full abstract

Machine Learning · Cross-listed from cs.CV

Ego4OOD: Rethinking Egocentric Video Domain Generalization via Covariate Shift Scoring

Egocentric video action recognition under domain shifts remains challenging due to large intra-class spatio-temporal variability, long-tailed feature distributions, and strong correlations between actions and environments. Existing benchmarks for egocentric domain generalization often conflate covariate shifts with concept shifts, making it difficult to reliably evaluate a model's ability to generalize across input distributions. To address this limitation, we introduce Ego4OOD, a domain generalization benchmark derived from Ego4D that emphasizes measurable covariate diversity while reducing concept shift through semantically coherent, moment-level action categories. Ego4OOD spans eight geographically distinct domains and is accompanied by a clustering-based covariate shift metric that provides a quantitative proxy for domain difficulty. We further leverage a one-vs-all binary training objective that decomposes multi-class action recognition into independent binary classification tasks. This formulation is particularly well-suited for covariate shift by reducing interference between visually similar classes under feature distribution shift. Using this formulation, we show that a lightweight two-layer fully connected network achieves performance competitive with state-of-the-art egocentric domain generalization methods on both Argo1M and Ego4OOD, despite using fewer parameters and no additional modalities. Our empirical analysis demonstrates a clear relationship between measured covariate shift and recognition performance, highlighting the importance of controlled benchmarks and quantitative domain characterization for studying out-of-distribution generalization in egocentric video.
Read the full abstract

Machine Learning · Cross-listed from cs.CV

A Contrastive Pre-trained Foundation Model for Deciphering Imaging Noisomics across Modalities

Characterizing imaging noise is notoriously data-intensive and device-dependent, as modern sensors entangle physical signals with complex algorithmic artifacts. Current paradigms struggle to disentangle these factors without massive supervised datasets, often reducing noise to mere interference rather than an information resource. Here, we introduce "Noisomics", a framework shifting the focus from suppression to systematic noise decoding via the Contrastive Pre-trained (CoP) Foundation Model. By leveraging the manifold hypothesis and synthetic noise genome, CoP employs contrastive learning to disentangle semantic signals from stochastic perturbations. Crucially, CoP breaks traditional deep learning scaling laws, achieving superior performance with only 100 training samples, outperforming supervised baselines trained on 100,000 samples, thereby reducing data and computational dependency by three orders of magnitude. Extensive benchmarking across 12 diverse out-of-domain datasets confirms its robust zero-shot generalization, demonstrating a 63.8% reduction in estimation error and an 85.1% improvement in the coefficient of determination compared to the conventional training strategy. We demonstrate CoP's utility across scales: from deciphering non-linear hardware-noise interplay in consumer photography to optimizing photon-efficient protocols for deep-tissue microscopy. By decoding noise as a multi-parametric footprint, our work redefines stochastic degradation as a vital information resource, empowering precise imaging diagnostics without prior device calibration.
Read the full abstract

All authors Yuanjie Gu, Yiqun Wang, Chaohui Yu, Ang Xuan, Fan Wang, Zhi Lu, Biqin Dong

Machine Learning · Cross-listed from eess.AS

Test-Time Adaptation for Speech Emotion Recognition

The practical utility of Speech Emotion Recognition (SER) systems is undermined by their fragility to domain shifts, such as speaker variability, the distinction between acted and naturalistic emotions, and cross-corpus variations. While domain adaptation and fine-tuning are widely studied, they require either source data or labelled target data, which are often unavailable or raise privacy concerns in SER. Test-time adaptation (TTA) bridges this gap by adapting models at inference using only unlabeled target data. Yet, having been predominantly designed for image classification and speech recognition, the efficacy of TTA for mitigating the unique domain shifts in SER has not been investigated. In this paper, we present the first systematic evaluation and comparison covering 11 TTA methods across three representative SER tasks. The results indicate that backpropagation-free TTA methods are the most promising. Conversely, entropy minimization and pseudo-labeling generally fail, as their core assumption of a single, confident ground-truth label is incompatible with the inherent ambiguity of emotional expression. Further, no single method universally excels, and its effectiveness is highly dependent on the distributional shifts and tasks.
Read the full abstract

Machine Learning · Cross-listed from cs.SE

VibeTensor: System Software for Deep Learning, Fully Generated by AI Agents

VIBETENSOR is an open-source research system software stack for deep learning, generated by LLM-powered coding agents under high-level human guidance. In this paper, "fully generated" refers to code provenance: implementation changes were produced and applied as agent-proposed diffs; validation relied on agent-run builds, tests, and differential checks, without per-change manual diff review. It implements a PyTorch-style eager tensor library with a C++20 core (CPU+CUDA), a torch-like Python overlay via nanobind, and an experimental Node.js/TypeScript interface. Unlike thin bindings, VIBETENSOR includes its own tensor/storage system, schema-lite dispatcher, reverse-mode autograd, CUDA runtime (streams/events/graphs), a stream-ordered caching allocator with diagnostics, and a stable C ABI for dynamically loaded operator plugins. We view this release as a milestone for AI-assisted software engineering: it shows coding agents can generate a coherent deep learning runtime spanning language bindings down to CUDA memory management, validated primarily by builds and tests. We describe the architecture, summarize the workflow used to produce and validate the system, and evaluate the artifact. We report repository scale and test-suite composition, and summarize reproducible microbenchmarks from an accompanying AI-generated kernel suite, including fused attention versus PyTorch SDPA/FlashAttention. We also report end-to-end training sanity checks on 3 small workloads (sequence reversal, ViT, miniGPT) on NVIDIA H100 (Hopper, SM90) and Blackwell-class GPUs; multi-GPU results are Blackwell-only and use an optional CUTLASS-based ring-allreduce plugin gated on CUDA 13+ and sm103a toolchain support. Finally, we discuss failure modes in generated system software, including a "Frankenstein" composition effect where locally correct subsystems interact to yield globally suboptimal performance.
Read the full abstract

All authors Bing Xu, Terry Chen, Fengzhe Zhou, Tianqi Chen, Yangqing Jia, Vinod Grover, Haicheng Wu, Wei Liu, Craig Wittenbrink, Wen-mei Hwu, Roger Bringmann, Ming-Yu Liu, Luis Ceze, Michael Lightstone, Humphrey Shi

Machine Learning

PRISM: Deriving a White-Box Transformer as a Signal-Noise Decomposition Operator via Maximum Coding Rate Reduction

Deep learning models, particularly Transformers, are often criticized as "black boxes" and lack interpretability. We propose Prism, a white-box attention-based architecture derived from the principles of Maximizing Coding Rate Reduction ($\text{MCR}^2$). By modeling the attention mechanism as a gradient ascent process on a distinct signal-noise manifold, we introduce a specific irrational frequency separation ($\pi$-RoPE) to enforce incoherence between signal (semantic) and noise (syntactic) subspaces. We show empirical evidence that these geometric inductive biases can induce unsupervised functional disentanglement alone. Prism spontaneously specializes its attention heads into spectrally distinct regimes: low-frequency heads capturing long-range causal dependencies (signal) and high-frequency heads handling local syntactic constraints and structural artifacts. To provide a theoretical grounding for these spectral phenomena, we draw an analogy between attention mechanism and a Hamiltonian dynamical system and identify that the standard geometric progression of Rotary Positional Embeddings (RoPE) induces dense resonance networks (Arnold Tongues), leading to feature rank collapse. Empirical validation on 124M-parameter models trained on OpenWebText demonstrates that Prism spontaneously isolates the Attention Sink pathology and maintains isentropic information flow across layers. Further, we suggest a physics-informed plug-and-play intervention KAM-RoPE for large language models (LLMs). Our results suggest that interpretability and performance can be unified through principled geometric construction, offering a theoretically grounded alternative to heuristic architectural modifications
Read the full abstract

Machine Learning · Cross-listed from eess.IV

A Machine Vision Approach to Preliminary Skin Lesion Assessments

Early detection of malignant skin lesions is critical for improving patient outcomes in aggressive, metastatic skin cancers. This study evaluates a comprehensive system for preliminary skin lesion assessment that combines the clinically established ABCD rule of dermoscopy (analyzing Asymmetry, Borders, Color, and Dermoscopic Structures) with machine learning classification. Using a 1,000-image subset of the HAM10000 dataset, the system implements an automated, rule-based pipeline to compute a Total Dermoscopy Score (TDS) for each lesion. This handcrafted approach is compared against various machine learning solutions, including traditional classifiers (Logistic Regression, Random Forest, and SVM) and deep learning models. While the rule-based system provides high clinical interpretability, results indicate a performance bottleneck when reducing complex morphology to five numerical features. Experimental findings show that transfer learning with EfficientNet-B0 failed significantly due to domain shift between natural and medical images. In contrast, a custom three-layer Convolutional Neural Network (CNN) trained from scratch achieved 78.5% accuracy and 86.5% recall on median-filtered images, representing a 19-point accuracy improvement over traditional methods. The results demonstrate that direct pixel-level learning captures diagnostic patterns beyond handcrafted features and that purpose-built lightweight architectures can outperform large pretrained models for small, domain-specific medical datasets.
Read the full abstract

Machine Learning

QUAIL: Quantization Aware Unlearning for Mitigating Misinformation in LLMs

Machine unlearning aims to remove specific knowledge (e.g., copyrighted or private data) from a trained model without full retraining. In practice, models are often quantized (e.g., 4-bit) for deployment, but we find that quantization can catastrophically restore forgotten information [1]. In this paper, we (1) analyze why low-bit quantization undermines unlearning, and (2) propose a quantization-aware unlearning method to mitigate this. We first compute weight-change statistics and bucket overlaps in quantization to show that typical unlearning updates are too small to cross quantization thresholds. Building on this insight, we introduce a logits space hinge loss: for each forget example, we force the output logits of the unlearned model to differ from the original model by at least a margin (half the quantization step). This ensures forgotten examples remain distinguishable even after quantization. We evaluate on language and classification tasks (including a Twitter misinformation dataset) and show our method preserves forgetting under 4-bit quantization, whereas existing methods almost entirely recover the forgotten knowledge.
Read the full abstract

Machine Learning

Machine learning-enhanced non-amnestic Alzheimer's disease diagnosis from MRI and clinical features

Alzheimer's disease (AD), defined as an abnormal buildup of amyloid plaques and tau tangles in the brain can be diagnosed with high accuracy based on protein biomarkers via PET or CSF analysis. However, due to the invasive nature of biomarker collection, most AD diagnoses are made in memory clinics using cognitive tests and evaluation of hippocampal atrophy based on MRI. While clinical assessment and hippocampal volume show high diagnostic accuracy for amnestic or typical AD (tAD), a substantial subgroup of AD patients with atypical presentation (atAD) are routinely misdiagnosed. To improve diagnosis of atAD patients, we propose a machine learning approach to distinguish between atAD and non-AD cognitive impairment using clinical testing battery and MRI data collected as standard-of-care. We develop and evaluate our approach using 1410 subjects across four groups (273 tAD, 184 atAD, 235 non-AD, and 685 cognitively normal) collected from one private data set and two public data sets from the National Alzheimer's Coordinating Center (NACC) and the Alzheimer's Disease Neuroimaging Initiative (ADNI). We perform multiple atAD vs. non-AD classification experiments using clinical features and hippocampal volume as well as a comprehensive set of MRI features from across the brain. The best performance is achieved by incorporating additional important MRI features, which outperforms using hippocampal volume alone. Furthermore, we use the Boruta statistical approach to identify and visualize significant brain regions distinguishing between diagnostic groups. Our ML approach improves the percentage of correctly diagnosed atAD cases (the recall) from 52% to 69% for NACC and from 34% to 77% for ADNI, while achieving high precision. The proposed approach has important implications for improving diagnostic accuracy for non-amnestic atAD in clinical settings using only clinical testing battery and MRI.
Read the full abstract

All authors Megan A. Witherow, Michael L. Evans, Ahmed Temtam, Hamid R. Okhravi, Khan M. Iftekharuddin

Machine Learning · Cross-listed from cs.IR

DS@GT at TREC TOT 2025: Bridging Vague Recollection with Fusion Retrieval and Learned Reranking

We develop a two-stage retrieval system that combines multiple complementary retrieval methods with a learned reranker and LLM-based reranking, to address the TREC Tip-of-the-Tongue (ToT) task. In the first stage, we employ hybrid retrieval that merges LLM-based retrieval, sparse (BM25), and dense (BGE-M3) retrieval methods. We also introduce topic-aware multi-index dense retrieval that partitions the Wikipedia corpus into 24 topical domains. In the second stage, we evaluate both a trained LambdaMART reranker and LLM-based reranking. To support model training, we generate 5000 synthetic ToT queries using LLMs. Our best system achieves recall of 0.66 and NDCG@1000 of 0.41 on the test set by combining hybrid retrieval with Gemini-2.5-flash reranking, demonstrating the effectiveness of fusion retrieval.
Read the full abstract

Machine Learning · Cross-listed from cs.CV

DeltaDorsal: Enhancing Hand Pose Estimation with Dorsal Features in Egocentric Views

The proliferation of XR devices has made egocentric hand pose estimation a vital task, yet this perspective is inherently challenged by frequent finger occlusions. To address this, we propose a novel approach that leverages the rich information in dorsal hand skin deformation, unlocked by recent advances in dense visual featurizers. We introduce a dual-stream delta encoder that learns pose by contrasting features from a dynamic hand with a baseline relaxed position. Our evaluation demonstrates that, using only cropped dorsal images, our method reduces the Mean Per Joint Angle Error (MPJAE) by 18% in self-occluded scenarios (fingers >= 50% occluded) compared to state-of-the-art techniques that depend on the whole hand's geometry and large model backbones. Consequently, our method not only enhances the reliability of downstream tasks like index finger pinch and tap estimation in occluded scenarios but also unlocks new interaction paradigms, such as detecting isometric force for a surface "click" without visible movement while minimizing model size.
Read the full abstract

All authors William Huang, Siyou Pei, Leyi Zou, Eric J. Gonzalez, Ishan Chatterjee, Yang Zhang

Machine Learning · Cross-listed from cs.CL

ViT Registers and Fractal ViT

Drawing inspiration from recent findings including surprisingly decent performance of transformers without positional encoding (NoPE) in the domain of language models and how registers (additional throwaway tokens not tied to input) may improve the performance of large vision transformers (ViTs), we invent and test a variant of ViT called fractal ViT that breaks permutation invariance among the tokens by applying an attention mask between the regular tokens and “summary tokens” similar to registers, in isolation or in combination with various positional encodings. These models do not improve upon ViT with registers, highlighting the fact that these findings may be scale, domain, or application-specific.
Read the full abstract

Machine Learning

SAGE-FM: A lightweight and interpretable spatial transcriptomics foundation model

Spatial transcriptomics enables spatial gene expression profiling, motivating computational models that capture spatially conditioned regulatory relationships. We introduce SAGE-FM, a lightweight spatial transcriptomics foundation model based on graph convolutional networks (GCNs) trained with a masked central spot prediction objective. Trained on 416 human Visium samples spanning 15 organs, SAGE-FM learns spatially coherent embeddings that robustly recover masked genes, with 91% of masked genes showing significant correlations (p < 0.05). The embeddings generated by SAGE-FM outperform MOFA and existing spatial transcriptomics methods in unsupervised clustering and preservation of biological heterogeneity. SAGE-FM generalizes to downstream tasks, enabling 81% accuracy in pathologist-defined spot annotation in oropharyngeal squamous cell carcinoma and improving glioblastoma subtype prediction relative to MOFA. In silico perturbation experiments further demonstrate that the model captures directional ligand-receptor and upstream-downstream regulatory effects consistent with ground truth. These results demonstrate that simple, parameter-efficient GCNs can serve as biologically interpretable and spatially aware foundation models for large-scale spatial transcriptomics.
Read the full abstract

All authors Xianghao Zhan, Jingyu Xu, Yuanning Zheng, Zinaida Good, Olivier Gevaert

Machine Learning

Data-driven Lake Water Quality Forecasting for Time Series with Missing Data using Machine Learning

Volunteer-led lake monitoring yields irregular, seasonal time series with many gaps arising from ice cover, weather-related access constraints, and occasional human errors, complicating forecasting and early warning of harmful algal blooms. We study Secchi Disk Depth (SDD) forecasting on a 30-lake, data-rich subset drawn from three decades of in-situ records collected across Maine lakes. Missingness is handled via Multiple Imputation by Chained Equations (MICE), and we evaluate performance with a normalized Mean Absolute Error (nMAE) metric for cross-lake comparability. Among six candidates, ridge regression provides the best mean test performance. Using ridge regression, we then quantify the minimal sample size, showing that under a backward, recent-history protocol, the model reaches within 5% of full-history accuracy with approximately 176 training samples per lake on average. We also identify a minimal feature set, where a compact four-feature subset matches the thirteen-feature baseline within the same 5% tolerance. Bringing these results together, we introduce a joint feasibility function that identifies the minimal training history and fewest predictors sufficient to achieve the target of staying within 5% of the complete-history, full-feature baseline. In our study, meeting the 5% accuracy target required about 64 recent samples and just one predictor per lake, highlighting the practicality of targeted monitoring. Hence, our joint feasibility strategy unifies recent-history length and feature choice under a fixed accuracy target, yielding a simple, efficient rule for setting sampling effort and measurement priorities for lake researchers.
Read the full abstract

Machine Learning · Cross-listed from stat.ML

Low-Dimensional Adaptation of Rectified Flow: A Diffusion and Stochastic Localization Perspective

In recent years, Rectified flow (RF) has gained considerable popularity largely due to its generation efficiency and state-of-the-art performance. In this paper, we investigate how well RF automatically adapts to the intrinsic low dimensionality of the support of the target distribution to accelerate sampling. We show that, using a carefully designed \blue{end-point adapted} time-discretization scheme and with sufficiently accurate drift estimates, the RF sampler enjoys an iteration complexity of order $O(k/\varepsilon)$ (up to log factors), where $\varepsilon$ is the precision in total variation distance and $k$ is the intrinsic dimension of the target distribution. In addition, we show that the denoising diffusion probabilistic model (DDPM) procedure is equivalent to a stochastic version of RF by establishing a novel connection between these processes and stochastic localization. Building on this connection, we further design a stochastic RF sampler that also adapts to the low-dimensionality of the target distribution under mild requirements on the accuracy of the drift estimates, and also with a specific time schedule. We illustrate the efficacy of newly designed time-discretization schedules with simulations on the synthetic data and text-to-image (T2I) data experiments.
Read the full abstract

Machine Learning

MARS: Unleashing the Power of Speculative Decoding via Margin-Aware Verification

Speculative Decoding (SD) accelerates autoregressive large language model (LLM) inference by decoupling generation and verification. While recent methods improve draft quality by tightly coupling the drafter with the target model, the verification mechanism itself remains largely unchanged, relying on strict token-level rejection sampling. In practice, modern LLMs frequently operate in low-margin regimes where the target model exhibits weak preference among top candidates. In such cases, rejecting plausible runner-up tokens yields negligible information gain while incurring substantial rollback cost, leading to a fundamental inefficiency in verification. We propose Margin-Aware Speculative Verification, a training-free and domain-agnostic verification strategy that adapts to the target model's local decisiveness. Our method conditions verification on decision stability measured directly from the target logits and relaxes rejection only when strict verification provides minimal benefit. Importantly, the approach modifies only the verification rule and is fully compatible with existing target-coupled speculative decoding frameworks. Extensive experiments across model scales ranging from 8B to 235B demonstrate that our method delivers consistent and significant inference speedups over state-of-the-art baselines while preserving generation quality across diverse benchmarks. The code is available at https://github.com/5SSjw/MARS.
Read the full abstract

All authors Jingwei Song, Xinyu Wang, Hanbin Wang, Xiaoxuan Lei, Bill Shi, Shixin Han, Eric Yang, Xiao-Wen Chang, Lynn Ai

Machine Learning

Martingale Foresight Sampling: A Principled Approach to Inference-Time LLM Decoding

Standard autoregressive decoding in large language models (LLMs) is inherently short-sighted, often failing to find globally optimal reasoning paths due to its token-by-token generation process. While inference-time strategies like foresight sampling attempt to mitigate this by simulating future steps, they typically rely on ad-hoc heuristics for valuing paths and pruning the search space. This paper introduces Martingale Foresight Sampling (MFS), a principled framework that reformulates LLM decoding as a problem of identifying an optimal stochastic process. By modeling the quality of a reasoning path as a stochastic process, we leverage Martingale theory to design a theoretically-grounded algorithm. Our approach replaces heuristic mechanisms with principles from probability theory: step valuation is derived from the Doob Decomposition Theorem to measure a path's predictable advantage, path selection uses Optional Stopping Theory for principled pruning of suboptimal candidates, and an adaptive stopping rule based on the Martingale Convergence Theorem terminates exploration once a path's quality has provably converged. Experiments on six reasoning benchmarks demonstrate that MFS surpasses state-of-the-art methods in accuracy while significantly improving computational efficiency. Code will be released at https://github.com/miraclehetech/EACL2026-Martingale-Foresight-Sampling.
Read the full abstract

All authors Huayu Li, ZhengXiao He, Siyuan Tian, Jinghao Wen, Ao Li

Machine Learning

Early predicting of hospital admission using machine learning algorithms: Priority queues approach

Emergency Department overcrowding is a critical issue that compromises patient safety and operational efficiency, necessitating accurate demand forecasting for effective resource allocation. This study evaluates and compares three distinct predictive models: Seasonal AutoRegressive Integrated Moving Average with eXogenous regressors (SARIMAX), EXtreme Gradient Boosting (XGBoost) and Long Short-Term Memory (LSTM) networks for forecasting daily ED arrivals over a seven-day horizon. Utilizing data from an Australian tertiary referral hospital spanning January 2017 to December 2021, this research distinguishes itself by decomposing demand into eight specific ward categories and stratifying patients by clinical complexity. To address data distortions caused by the COVID-19 pandemic, the study employs the Prophet model to generate synthetic counterfactual values for the anomalous period. Experimental results demonstrate that all three proposed models consistently outperform a seasonal naive baseline. XGBoost demonstrated the highest accuracy for predicting total daily admissions with a Mean Absolute Error of 6.63, while the statistical SARIMAX model proved marginally superior for forecasting major complexity cases with an MAE of 3.77. The study concludes that while these techniques successfully reproduce regular day-to-day patterns, they share a common limitation in underestimating sudden, infrequent surges in patient volume.
Read the full abstract

All authors Jakub Antczak, James Montgomery, Małgorzata O'Reilly, Zbigniew Palmowski, Richard Turner

Machine Learning

BadImplant: Injection-based Multi-Targeted Graph Backdoor Attack

Graph neural network (GNN) have demonstrated exceptional performance in solving critical problems across diverse domains yet remain susceptible to backdoor attacks. Existing studies on backdoor attack for graph classification are limited to single target attack using subgraph replacement based mechanism where the attacker implants only one trigger into the GNN model. In this paper, we introduce the first multi-targeted backdoor attack for graph classification task, where multiple triggers simultaneously redirect predictions to different target labels. Instead of subgraph replacement, we propose subgraph injection which preserves the structure of the original graphs while poisoning the clean graphs. Extensive experiments demonstrate the efficacy of our approach, where our attack achieves high attack success rates for all target labels with minimal impact on the clean accuracy. Experimental results on five dataset demonstrate the superior performance of our attack framework compared to the conventional subgraph replacement-based attack. Our analysis on four GNN models confirms the generalization capability of our attack which is effective regardless of the GNN model architectures and training parameters settings. We further investigate the impact of the attack design parameters including injection methods, number of connections, trigger sizes, trigger edge density and poisoning ratios. Additionally, our evaluation against state-of-the-art defenses (randomized smoothing and fine-pruning) demonstrates the robustness of our proposed multi-target attacks. This work highlights the GNN vulnerability against multi-targeted backdoor attack in graph classification task. Our source codes will be available at https://github.com/SiSL-URI/Multi-Targeted-Graph-Backdoor-Attack.
Read the full abstract

Machine Learning

Panther: Faster and Cheaper Computations with Randomized Numerical Linear Algebra

Training modern deep learning models is increasingly constrained by GPU memory and compute limits. While Randomized Numerical Linear Algebra (RandNLA) offers proven techniques to compress these models, the lack of a unified, production-grade library prevents widely adopting these methods. We present Panther, a PyTorch-compatible library that consolidates established RandNLA algorithms into a single high-performance framework. Panther engineers efficient, drop-in replacements for standard components including sketched linear layers, 2D convolution, multi-head attention, and randomized matrix decompositions (such as pivoted CholeskyQR). By implementing a custom C++/CUDA backend (pawX), Panther provides an optimized implementation that can run on both CPUs and GPUs. We demonstrate the effectiveness of RandNLA techniques and Panther's ease of adoption. By replacing standard PyTorch linear layers with Panther layers (requiring only a few lines of code) we achieve significant memory savings (up to 75%) on BERT while maintaining comparable loss. Source code is available (MIT License) at https://github.com/FahdSeddik/panther, along with demonstration video at https://youtu.be/7M3RQb4KWxs.
Read the full abstract

All authors Fahd Seddik, Abdulrahman Elbedewy, Gaser Sami, Mohamed Abdelmoniem, Yahia Zakaria

Machine Learning

Learning from Synthetic Data: Limitations of ERM

The prevalence and low cost of LLMs have led to a rise of synthetic content. From review sites to court documents, "natural" content has been contaminated by data points that appear similar to natural data, but are in fact LLM-generated. In this work we revisit fundamental learning theory questions in this, now ubiquitous, setting. We model this scenario as a sequence of learning tasks where the input is a mix of natural and synthetic data, and the learning algorithms are oblivious to the origin of any individual example. We study the possibilities and limitations of ERM in this setting. For the problem of estimating the mean of an arbitrary $d$-dimensional distribution, we find that while ERM converges to the true mean, it is outperformed by an algorithm that assigns non-uniform weights to examples from different generations of data. For the PAC learning setting, the disparity is even more stark. We find that ERM does not always converge to the true concept, echoing the model collapse literature. However, we show there are algorithms capable of learning the correct hypothesis for arbitrary VC classes and arbitrary amounts of contamination.
Read the full abstract

All authors Kareem Amin, Alex Bie, Weiwei Kong, Umar Syed, Sergei Vassilvitskii

Machine Learning · Cross-listed from cs.AI

A tensor network formalism for neuro-symbolic AI

The unification of neural and symbolic approaches to artificial intelligence remains a central open challenge. In this work, we introduce a tensor network formalism, which captures sparsity principles originating in the different approaches in tensor decompositions. In particular, we describe a basis encoding scheme for functions and model neural decompositions as tensor decompositions. The proposed formalism can be applied to represent logical formulas and probability distributions as structured tensor decompositions. This unified treatment identifies tensor network contractions as a fundamental inference class and formulates efficiently scaling reasoning algorithms, originating from probability theory and propositional logic, as contraction message passing schemes. The framework enables the definition and training of hybrid logical and probabilistic models, which we call Hybrid Logic Network. The theoretical concepts are accompanied by the python library tnreason, which enables the implementation and practical use of the proposed architectures.
Read the full abstract

All authors Alex Goessmann, Janina Schütte, Maximilian Fröhlich, Martin Eigel

Machine Learning

CASL: Concept-Aligned Sparse Latents for Interpreting Diffusion Models

Internal activations of diffusion models encode rich semantic information, but interpreting such representations remains challenging. While Sparse Autoencoders (SAEs) have shown promise in disentangling latent representations, existing SAE-based methods for diffusion model understanding rely on unsupervised approaches that fail to align sparse features with human-understandable concepts. This limits their ability to provide reliable semantic control over generated images. We introduce CASL (Concept-Aligned Sparse Latents), a supervised framework that aligns sparse latent dimensions of diffusion models with semantic concepts. CASL first trains an SAE on frozen U-Net activations to obtain disentangled latent representations, and then learns a lightweight linear mapping that associates each concept with a small set of relevant latent dimensions. To validate the semantic meaning of these aligned directions, we propose CASL-Steer, a controlled latent intervention that shifts activations along the learned concept axis. Unlike editing methods, CASL-Steer is used solely as a causal probe to reveal how concept-aligned latents influence generated content. We further introduce the Editing Precision Ratio (EPR), a metric that jointly measures concept specificity and the preservation of unrelated attributes. Experiments show that our method achieves superior editing precision and interpretability compared to existing approaches. To the best of our knowledge, this is the first work to achieve supervised alignment between latent representations and semantic concepts in diffusion models.
Read the full abstract

All authors Zhenghao He, Guangzhi Xiong, Boyang Wang, Sanchit Sinha, Aidong Zhang

Machine Learning

Lattice: A Confidence-Gated Hybrid System for Uncertainty-Aware Sequential Prediction with Behavioral Archetypes

We introduce Lattice, a hybrid sequential prediction system that conditionally activates learned behavioral structure using binary confidence gating. The system summarizes behavior windows as behavioral archetypes and activates archetype-based scoring only when an in-support confidence signal exceeds a validation-calibrated threshold, falling back to backbone predictions when uncertain. Our primary estimand is the controlled effect of adding Lattice to a fixed backbone on identical test rows. On MovieLens (30 paired seeds, full-catalog ranking), LSTM+Lattice improves HR@10 by +31.7% (gated) versus the LSTM backbone alone (p much less than 10^-20); ungated fusion reaches +58.7% on the same protocol. We do not claim gating maximizes pooled accuracy. With backbone-native archetypes (fit in each backbone's embedding space), gated lifts of +13.3% (transformer) and +17.0% (SASRec) hold under the same evaluation design. A prior approximately 0% transformer row in version 1 reflected an invalid cross-backbone transfer, not evidence that composition cannot help stronger encoders. Amazon Electronics provides supporting cross-domain evidence (+124.0% gated, 15 seeds, high variance). Controlled shift checks (appendix) illustrate gate refusal under distribution shift. Standalone SASRec and BERT4Rec scores are contextual references, not the target estimand. We report what composition achieves and when it activates; production calibration and implementation details remain proprietary pending patent prosecution.
Read the full abstract

Machine Learning

Ambient Dataloops: Generative Models for Dataset Refinement

We propose Ambient Dataloops, an iterative framework for refining datasets that makes it easier for diffusion models to learn the underlying data distribution. Modern datasets contain samples of highly varying quality, and training directly on such heterogeneous data often yields suboptimal models. We propose a dataset-model co-evolution process; at each iteration of our method, the dataset becomes progressively higher quality, and the model improves accordingly. To avoid destructive self-consuming loops, at each generation, we treat the synthetically improved samples as noisy, but at a slightly lower noisy level than the previous iteration, and we use Ambient Diffusion techniques for learning under corruption. Empirically, Ambient Dataloops achieve state-of-the-art performance in unconditional and text-conditional image generation and de novo protein design. We further provide a theoretical justification for the proposed framework that captures the benefits of the data looping procedure.
Read the full abstract

All authors Adrián Rodríguez-Muñoz, William Daspit, Adam Klivans, Antonio Torralba, Constantinos Daskalakis, Giannis Daras

Machine Learning · Cross-listed from cs.CV

CURE: Curriculum-guided Multi-task Training for Reliable Anatomy Grounded Report Generation

Medical vision-language models can automate the generation of radiology reports but struggle with accurate visual grounding and factual consistency. Existing models often misalign textual findings with visual evidence, leading to unreliable or weakly grounded predictions. We present CURE, an error-aware curriculum learning framework that improves grounding and report quality without any additional data. CURE fine-tunes a multimodal instructional model on phrase grounding, grounded report generation, and anatomy-grounded report generation using public datasets. The method dynamically adjusts sampling based on model performance, emphasizing harder samples to improve spatial and textual alignment. CURE improves grounding accuracy by +0.35 IoU, boosts report quality by +0.192 CXRFEScore, and reduces hallucinations by 18.6%. CURE is a data-efficient framework that enhances both grounding accuracy and report reliability. Code is available at https://github.com/PabloMessina/CURE and model weights at https://huggingface.co/pamessina/medgemma-4b-it-cure
Read the full abstract

All authors Pablo Messina, Andrés Villa, Juan León Alcázar, Karen Sánchez, Carlos Hinojosa, Denis Parra, Álvaro Soto, Bernard Ghanem

Machine Learning

Attention-Informed Surrogates for Navigating Power-Performance Trade-offs in HPC

High-Performance Computing (HPC) schedulers must balance user performance with facility-wide resource constraints. The task boils down to selecting the optimal number of nodes for a given job. We present a surrogate-assisted multi-objective Bayesian optimization (MOBO) framework to automate this complex decision. Our core hypothesis is that surrogate models informed by attention-based embeddings of job telemetry can capture performance dynamics more effectively than standard regression techniques. We pair this with an intelligent sample acquisition strategy to ensure the approach is data-efficient. On two production HPC datasets, our embedding-informed method consistently identified higher-quality Pareto fronts of runtime-power trade-offs compared to baselines. Furthermore, our intelligent data sampling strategy drastically reduced training costs while improving the stability of the results. To our knowledge, this is the first work to successfully apply embedding-informed surrogates in a MOBO framework to the HPC scheduling problem, jointly optimizing for performance and power on production workloads.
Read the full abstract

All authors Ashna Nawar Ahmed, Banooqa Banday, Terry Jones, Tanzima Z. Islam

Machine Learning · Cross-listed from cs.AI

GeMM-GAN: A Multimodal Generative Model Conditioned on Histopathology Images and Clinical Descriptions for Gene Expression Profile Generation

Biomedical research increasingly relies on integrating diverse data modalities, including gene expression profiles, medical images, and clinical metadata. While medical images and clinical metadata are routinely collected in clinical practice, gene expression data presents unique challenges for widespread research use, mainly due to stringent privacy regulations and costly laboratory experiments. To address these limitations, we present GeMM-GAN, a novel Generative Adversarial Network conditioned on histopathology tissue slides and clinical metadata, designed to synthesize realistic gene expression profiles. GeMM-GAN combines a Transformer Encoder for image patches with a final Cross Attention mechanism between patches and text tokens, producing a conditioning vector to guide a generative model in generating biologically coherent gene expression profiles. We evaluate our approach on the TCGA dataset and demonstrate that our framework outperforms standard generative models and generates more realistic and functionally meaningful gene expression profiles, improving by more than 11% the accuracy on downstream disease type prediction compared to current state-of-the-art generative models. Code will be available at: https://github.com/francescapia/GeMM-GAN
Read the full abstract

Machine Learning

FedUMM: A General Framework for Federated Learning with Unified Multimodal Models

Unified multimodal models (UMMs) are emerging as strong foundation models that can do both generation and understanding tasks in a single architecture. However, they are typically trained in centralized settings where all training and downstream datasets are gathered in a central server, limiting the deployment in privacy-sensitive and geographically distributed scenarios. In this paper, we present FedUMM, a general federated learning framework for UMMs under non-IID multimodal data with low communication cost. Built on NVIDIA FLARE, FedUMM instantiates federation for a BLIP3o backbone via parameter-efficient fine-tuning: clients train lightweight LoRA adapters while freezing the foundation models, and the server aggregates only adapter updates. We evaluate on VQA v2 and the GenEval compositional generation benchmarks under Dirichlet-controlled heterogeneity with up to 16 clients. Results show slight degradation as client count and heterogeneity increase, while remaining competitive with centralized training. We further analyze computation–communication trade-offs and demonstrate that adapter-only federation reduces per-round communication by over an order of magnitude compared to full fine-tuning, enabling practical federated UMM training. This work provides empirical experience for future research on privacy-preserving federated unified multimodal models.
Read the full abstract

All authors Zhaolong Su, Leheng Zhao, Xiaoying Wu, Ziyue Xu, Jindong Wang