Machine Learning · Cross-listed from cs.CV
Toxicity Assessment in Preclinical Histopathology via Class-Aware Mahalanobis Distance for Known and Novel Anomalies
Olga Graf, Dhrupal Patel, Peter Groß et al. (+3 more)
Drug-induced toxicity is a leading cause of preclinical and early-clinical failure, making early detection critical. Histopathology is the gold standard for toxicity assessment but relies on expert pathologists, creating a bottleneck for large-scale screening. We introduce an AI-based anomaly detection framework for whole-slide images (WSIs) of rodent liver that identifies healthy tissue and known pathologies (anomalies) and flags samples without training data as out-of-distribution (OOD). We evaluate OOD detection on two held-out categories: apoptosis (single-
cell, near-OOD) and staining/processing artifacts (heterogeneous, far-OOD). We build a novel pixelwise-annotated
dataset and fine-tune a pre-trained
Vision Transformer (DINOv2) via Low-Rank Adaptation (LoRA) for
segmentation, then use the Mahalanobis distance for OOD detection with class-specific thresholds. Optimizing the false positive rate subject to a predefined constraint on the false negative rate yields only 0.16% of pathological tissue classified as healthy and 0.35% of healthy tissue classified as pathological. Our false negative rate does not penalise cross-type errors, reflecting the safety-first objective of never overlooking a lesion; under the stricter correct-class criterion our method assigns 93.93% of ID and 89.38% of OOD findings to their own class. The study demonstrates technical feasibility of pixel-level anomaly detection for mouse liver histopathology, indicating possible applications in improving preclinical workflows and drug development efficiency.
Read the full abstract ▾
All authors Olga Graf, Dhrupal Patel, Peter Groß, Charlotte Lempp, Matthias Hein, Fabian Heinemann
Machine Learning
The Maximum von Neumann Entropy Principle: Theory and Applications in Machine Learning
Youqi Wu and Farzan Farnia
Von Neumann
entropy (VNE) is a fundamental quantity in
quantum information theory and has recently been adopted in machine learning as a spectral measure of diversity for kernel
matrices and kernel covariance operators. While maximizing VNE under constraints is well known in
quantum settings, a principled analogue of the classical maximum
entropy framework, particularly its decision theoretic and game theoretic interpretation, has not been explicitly developed for VNE in data driven contexts. In this paper, we extend the minimax formulation of the maximum
entropy principle due to Grünwald and Dawid to the setting of von Neumann
entropy, providing a game-theoretic justification for VNE maximization over density
matrices and trace-normalized positive semidefinite operators. This perspective yields a robust interpretation of maximum VNE solutions under partial information and clarifies their role as least committed inferences in spectral domains. We then illustrate how the resulting Maximum VNE principle applies to modern machine learning problems by considering two representative applications, selecting a kernel representation from multiple normalized
embeddings via kernel-based VNE maximization, and completing kernel
matrices from partially observed entries. These examples demonstrate how the proposed framework offers a unifying information-theoretic foundation for VNE-based methods in kernel learning.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.CV
Enhancing Diffusion-Based Quantitatively Controllable Image Generation via Matrix-Form EDM and Adaptive Vicinal Training
Xin Ding, Yun Chen, Sen Zhang et al. (+5 more)
Continuous Conditional
Diffusion Model (CCDM) is a
diffusion-based framework designed to generate high-quality images conditioned on continuous regression labels. Although CCDM has demonstrated clear advantages over prior approaches across a range of
datasets, it still exhibits notable limitations and has recently been surpassed by a GAN-based method, namely CcGAN-AVAR. These limitations mainly arise from its reliance on an outdated
diffusion framework and its low sampling efficiency due to long sampling trajectories. To address these issues, we propose an improved CCDM framework, termed iCCDM, which incorporates the more advanced Elucidated
Diffusion Model (EDM) framework with substantial modifications to improve both generation quality and sampling efficiency. Specifically, iCCDM introduces a novel
matrix-form EDM formulation together with an adaptive vicinal training strategy. Extensive experiments on four
benchmark datasets, spanning image resolutions from $64\times64$ to $256\times256$, demonstrate that iCCDM consistently outperforms existing methods, including state-of-the-art large-scale text-to-image
diffusion models (e.g., Stable
Diffusion 3, FLUX.1, and Qwen-Image), achieving higher generation quality while significantly reducing sampling cost.
Read the full abstract ▾
All authors Xin Ding, Yun Chen, Sen Zhang, Kao Zhang, Nenglun Chen, Peibei Cao, Yongwei Wang, Fei Wu
Machine Learning · Cross-listed from stat.ML
Training-free score-based diffusion for parameter-dependent stochastic dynamical systems
Minglei Yang and Sicheng He
Simulating parameter-dependent
stochastic differential equations (SDEs) presents significant computational challenges, as separate high-fidelity simulations are typically required for each parameter value of interest. Despite the success of machine learning methods in learning SDE dynamics, existing approaches either require expensive neural network training for score function estimation or lack the ability to handle continuous parameter dependence. We present a training-free conditional
diffusion model framework for learning
stochastic flow maps of parameter-dependent SDEs, where both drift and
diffusion coefficients depend on physical parameters. The key technical innovation is a joint kernel-weighted Monte Carlo
estimator that approximates the conditional score function using trajectory data sampled at discrete parameter values, enabling interpolation across both state space and the continuous parameter domain. Once trained, the resulting generative model produces sample trajectories for any parameter value within the training range without retraining, significantly accelerating parameter studies, uncertainty quantification, and real-time filtering applications. The performance of the proposed approach is demonstrated via three numerical examples of increasing complexity, showing accurate approximation of conditional distributions across varying parameter values.
Read the full abstract ▾
Machine Learning
Unifying Masked Diffusion Models with Various Generation Orders and Beyond
Chunsan Hong, Sanghyun Lee and Jong Chul Ye
Masked
diffusion models (MDMs) are a potential alternative to autoregressive models (ARMs) for
language generation, but generation quality depends critically on the generation order. Prior work either hard-codes an ordering (e.g., blockwise left-to-right) or learns an ordering policy for a pretrained MDM, which incurs extra cost and can yield suboptimal solutions due to the two-stage optimization. Motivated by this, we propose order-expressive masked
diffusion model (OeMDM) for a broad class of
diffusion generative processes with various generation orders, enabling the interpretation of MDM, ARM, and block
diffusion in a single framework. Furthermore, building on OeMDM, we introduce learnable-order masked
diffusion model (LoMDM), which jointly learns the generation ordering and
diffusion backbone through a single objective from scratch, enabling the
diffusion model to generate text in context-dependent ordering. Empirically, we confirm that LoMDM outperforms various discrete
diffusion models across multiple
language modeling
benchmarks.
Read the full abstract ▾
Machine Learning
An Empirical Study of World Model Quantization
Zhongqian Fu, Tianyi Zhao, Kai Han et al. (+3 more)
World models learn an internal representation of environment dynamics, enabling
agents to simulate and reason about future states within a compact latent space for tasks such as planning, prediction, and inference. However, running world models rely on hevay computational cost and
memory footprint, making model quantization essential for efficient deployment. To date, the effects of post-training quantization (PTQ) on world models remain largely unexamined. In this work, we present a systematic empirical study of world model quantization using DINO-WM as a representative case, evaluating diverse PTQ methods under both weight-only and joint weight-activation settings. We conduct extensive experiments on different visual planning tasks across a wide range of bit-widths, quantization granularities, and planning horizons up to 50 iterations. Our results show that quantization effects in world models extend beyond standard accuracy and bit-width trade-offs: group-wise weight quantization can stabilize low-bit rollouts, activation quantization granularity yields inconsistent benefits, and quantization sensitivity is highly asymmetric between encoder and predictor modules. Moreover, aggressive low-bit quantization significantly degrades the
alignment between the planning objective and task success, leading to failures that cannot be remedied by additional optimization. These findings reveal distinct quantization-induced failure modes in world model-based planning and provide practical guidance for deploying quantized world models under strict computational constraints. The code will be available at https://github.com/huawei-noah/noah-research/tree/master/QuantWM.
Read the full abstract ▾
All authors Zhongqian Fu, Tianyi Zhao, Kai Han, Hang Zhou, Xinghao Chen, Yunhe Wang
Machine Learning
How Far Ahead Do LLMs Plan? Uncovering the Latent Horizon in Chain-of-Thought Reasoning
Liyan Xu, Mo Yu, Fandong Meng et al. (+1 more)
Chain-of-thought (CoT)
reasoning has become a central mechanism for eliciting multi-step
reasoning in Large
Language Models (LLMs). Yet recent evidence presents a tension: hidden states appear to already encode future
reasoning before CoT fully unfolds, while explicit steps still remain crucial for tasks requiring compositional computation. To deepen the understanding between LLM's internal states and its verbalized
reasoning trajectories, we investigate the latent planning strength of LLMs, through our probing method, Tele-Lens, applying to hidden states across diverse task domains. Our empirical results indicate that LLMs exhibit a myopic horizon, primarily conducting incremental transitions without precise global planning. Leveraging this characteristic, we propose a hypothesis on enhancing uncertainty estimation of CoT, which we validate that a sparse set of pivot positions can effectively represent the uncertainty of the entire path. We further underscore the significance of exploiting CoT dynamics, and demonstrate that automatic recognition of CoT bypass can be achieved without performance degradation. Our code, data and models are released at https://github.com/lxucs/tele-lens.
Read the full abstract ▾
All authors Liyan Xu, Mo Yu, Fandong Meng, Jie Zhou
Machine Learning · Cross-listed from cs.CL
Think Dense, Not Long: Dynamic Decoupled Conditional Advantage for Efficient Reasoning
Keqin Peng, Yuanxin Ouyang, Xuebo Liu et al. (+4 more)
Reinforcement Learning with Verifiable Rewards (RLVR) can elicit strong multi-step
reasoning, yet it often encourages overly verbose traces. Moreover, naive length penalties in group-relative optimization can severely hurt accuracy. We attribute this failure to two structural issues: (i) Dilution of Length Baseline, where incorrect responses (with zero length reward) depress the group baseline and over-penalize correct solutions; and (ii) Difficulty-Penalty Mismatch, where a static penalty cannot adapt to problem difficulty, suppressing necessary
reasoning on hard instances while leaving redundancy on easy ones. We propose Dynamic Decoupled Conditional Advantage (DDCA) to decouple efficiency optimization from correctness. DDCA computes length advantages conditionally within the correct-response cluster to eliminate baseline dilution, and dynamically scales the penalty strength using the group pass rate as a proxy for difficulty. Experiments on GSM8K, MATH500, AMC23, and AIME25 show that DDCA consistently improves the efficiency–accuracy trade-off relative to adaptive baselines, reducing generated
tokens by approximately 60% on simpler tasks (e.g., GSM8K) versus over 20% on harder
benchmarks (e.g., AIME25), thereby maintaining or improving accuracy. Code is available at https://github.com/alphadl/DDCA.
Read the full abstract ▾
All authors Keqin Peng, Yuanxin Ouyang, Xuebo Liu, Zhiliang Tian, Ruijian Han, Yancheng Yuan, Liang Ding
Machine Learning
Probabilistic Performance Guarantees for Multi-Task Reinforcement Learning
Yannik Schnitzer, Mathias Jackermeier, Alessandro Abate et al. (+1 more)
Multi-task reinforcement learning trains generalist policies that can execute multiple tasks. While recent years have seen significant progress, existing approaches rarely provide formal performance guarantees, which are indispensable when deploying policies in safety-critical settings. We present an approach for computing high-confidence guarantees on the performance of a multi-task policy on tasks not seen during training. Concretely, we introduce a new generalisation bound that composes (i) per-task lower confidence bounds from finitely many rollouts with (ii) task-level generalisation from finitely many sampled tasks, yielding a high-confidence guarantee for new tasks drawn from the same arbitrary and unknown distribution. Across state-of-the-art multi-task RL methods, we show that the guarantees are theoretically sound and informative at realistic sample sizes.
Read the full abstract ▾
All authors Yannik Schnitzer, Mathias Jackermeier, Alessandro Abate, David Parker
Machine Learning
Efficient Swap Regret Minimization in Combinatorial Bandits
Andreas Kontogiannis, Vasilis Pollatos, Panayotis Mertikopoulos et al. (+1 more)
This paper addresses the problem of designing efficient no-swap regret
algorithms for combinatorial bandits, where the number of actions $N$ is exponentially large in the dimensionality of the problem. In this setting, designing efficient no-swap regret translates to sublinear – in horizon $T$ – swap regret with polylogarithmic dependence on $N$. In contrast to the weaker notion of external regret minimization - a problem which is fairly well understood in the literature - achieving no-swap regret with a polylogarithmic dependence on $N$ has remained elusive in combinatorial bandits. Our paper resolves this challenge, by introducing a no-swap-regret learning
algorithm with regret that scales polylogarithmically in $N$ and is tight for the class of combinatorial bandits. To ground our results, we also demonstrate how to implement the proposed
algorithm efficiently – that is, with a per-iteration complexity that also scales polylogarithmically in $N$ – across a wide range of well-studied applications.
Read the full abstract ▾
All authors Andreas Kontogiannis, Vasilis Pollatos, Panayotis Mertikopoulos, Ioannis Panageas
Machine Learning
Active learning from positive and unlabeled examples
Farnam Mansouri, Sandra Zilles and Shai Ben-David
Learning from positive and unlabeled data (PU learning) is a weakly supervised variant of binary classification in which the learner receives labels only for (some) positively labeled instances, while all other examples remain unlabeled. Motivated by applications such as advertising and anomaly detection, we study an active PU learning setting where the learner can adaptively query instances from an unlabeled pool, but a queried label is revealed only when the instance is positive and an independent coin flip succeeds; otherwise the learner receives no information. In this paper, we provide the first theoretical analysis of the label complexity of active PU learning.
Read the full abstract ▾
Machine Learning
Learning Half-Spaces from Perturbed Contrastive Examples
Aryan Alavi Razavi Ravari, Farnam Mansouri, Yuxin Chen et al. (+3 more)
We study learning under a two-step contrastive example oracle, as introduced by Mansouri et. al. (2025), where each queried (or sampled) labeled example is paired with an additional contrastive example of opposite label. While Mansouri et al. assume an idealized setting, where the contrastive example is at minimum distance of the originally queried/sampled point, we introduce and analyze a mechanism, parameterized by a non-decreasing noise function $f$, under which this ideal contrastive example is perturbed. The amount of perturbation is controlled by $f(d)$, where $d$ is the distance of the queried/sampled point to the decision boundary. Intuitively, this results in higher-quality contrastive examples for points closer to the decision boundary. We study this model in two settings: (i) when the maximum perturbation magnitude is fixed, and (ii) when it is
stochastic. For one-dimensional thresholds and for half-spaces under the uniform distribution on a bounded domain, we characterize active and passive contrastive sample complexity in dependence on the function $f$. We show that, under certain conditions on $f$, the presence of contrastive examples speeds up learning in terms of asymptotic query complexity and asymptotic expected query complexity.
Read the full abstract ▾
All authors Aryan Alavi Razavi Ravari, Farnam Mansouri, Yuxin Chen, Valentio Iverson, Adish Singla, Sandra Zilles
Machine Learning
AICD Bench: A Challenging Benchmark for AI-Generated Code Detection
Daniil Orel, Dilshod Azizov, Indraneil Paul et al. (+3 more)
Large
language models (LLMs) are increasingly capable of generating functional source code, raising concerns about authorship, accountability, and security. While detecting AI-generated code is critical, existing
datasets and
benchmarks are narrow, typically limited to binary human-machine classification under in-distribution settings. To bridge this gap, we introduce $\emph{AICD Bench}$, the most comprehensive
benchmark for AI-generated code detection. It spans $\emph{2M examples}$, $\emph{77 models}$ across $\emph{11 families}$, and $\emph{9 programming languages}$, including recent
reasoning models. Beyond scale, AICD Bench introduces three realistic detection tasks: ($\emph{i}$)~$\emph{Robust Binary Classification}$ under distribution shifts in
language and domain, ($\emph{ii}$)~$\emph{Model Family Attribution}$, grouping generators by architectural lineage, and ($\emph{iii}$)~$\emph{Fine-Grained Human-Machine Classification}$ across human, machine, hybrid, and
adversarial code. Extensive evaluation on neural and classical detectors shows that performance remains far below practical usability, particularly under distribution shift and for hybrid or
adversarial code. We release AICD Bench as a $\emph{unified, challenging evaluation suite}$ to drive the next generation of robust approaches for AI-generated code detection. The data and the code are available at https://huggingface.co/AICD-bench}.
Read the full abstract ▾
All authors Daniil Orel, Dilshod Azizov, Indraneil Paul, Yuxia Wang, Iryna Gurevych, Preslav Nakov
Machine Learning
Calibrating Adaptive Smoothing Methods for Freeway Traffic Reconstruction
Junyi Ji, Derek Gloudemans, Gergely Zachár et al. (+3 more)
The adaptive smoothing method (ASM) is a widely used approach for traffic state reconstruction. This article presents a Python implementation of ASM, featuring end-to-end calibration using real-world ground truth data. The calibration is formulated as a parameterized kernel optimization problem. The model is calibrated using data from a full-state observation testbed, with input from a sparse radar sensor network. The implementation is developed in PyTorch, enabling integration with various deep learning methods. We evaluate the results in terms of speed distribution, spatio-temporal error distribution, and spatial error to provide
benchmark metrics for the traffic reconstruction problem. We further demonstrate the usability of the calibrated method across multiple freeways. Finally, we discuss the challenges of reproducibility in general traffic model calibration and the limitations of ASM. This article is reproducible and can serve as a
benchmark for various freeway operation tasks.
Read the full abstract ▾
All authors Junyi Ji, Derek Gloudemans, Gergely Zachár, Matthew Nice, William Barbour, Daniel B. Work
Machine Learning
BAPS: A Fine-Grained Low-Precision Scheme for Softmax in Attention via Block-Aware Precision reScaling
Zisheng Ye, Xiaoyu He, Maoyuan Song et al. (+10 more)
As the performance gains from accelerating quantized
matrix multiplication plateau, the softmax operation becomes the critical bottleneck in
Transformer inference. This bottleneck stems from two hardware limitations: (1) limited data bandwidth between
matrix and vector compute cores, and (2) the significant area cost of high-precision (FP32/16) exponentiation units (EXP2). To address these issues, we introduce a novel low-precision workflow that employs a specific 8-bit floating-point format (HiF8) and block-aware precision rescaling for softmax. Crucially, our algorithmic innovations make low-precision softmax feasible without the significant model accuracy loss that hampers direct low-precision approaches. Specifically, our design (i) halves the required data movement bandwidth by enabling
matrix multiplication outputs constrained to 8-bit, and (ii) substantially reduces the EXP2 unit area by computing exponentiations in low (8-bit) precision. Extensive evaluation on
language models and multi-modal models confirms the validity of our method. By alleviating the vector computation bottleneck, our work paves the way for doubling end-to-end inference throughput without increasing chip area, and offers a concrete co-design path for future low-precision hardware and software.
Read the full abstract ▾
All authors Zisheng Ye, Xiaoyu He, Maoyuan Song, Guoliang Qiu, Chao Liao, Chen Wu, Yonggang Sun, Zhichun Li, Xiaoru Xie, Yuanyong Luo, Hu Liu, Pinyan Lu, Heng Liao
Machine Learning
Learning to Route and Schedule LLMs from User Retrials via Contextual Queueing Bandits
Seoungbin Bae, Junyoung Son and Dabeen Lee
Explosive demands for LLMs often cause user queries to accumulate in server queues, requiring efficient routing (query-LLM matching) and scheduling (query prioritization) mechanisms. Several online
algorithms are being deployed, but they overlook the following two key challenges inherent to conversational LLM services: (1) unsatisfied users may retry queries, increasing the server backlog, and (2) requests for “explicit" feedback, such as ratings, degrade user experiences. In this paper, we develop a joint routing and scheduling
algorithm that leverages “implicit" feedback inferred from user retrial behaviors. The key idea is to propose and study the framework of contextual queueing bandits with multinomial logit feedback (CQB-MNL). CQB-MNL models query retrials, as well as context-based learning for user preferences over LLMs. Our
algorithm, anytime CQB (ACQB), achieves efficient learning while maintaining queue stability by combining Thompson sampling with forced exploration at a decaying rate. We show that ACQB simultaneously achieves a cumulative regret of $\widetilde{\mathcal{O}}(\sqrt{t})$ for routing and a queue length regret of $\widetilde{\mathcal{O}}(t^{-1/4})$ for any large $t$. For experiments, we refine query
embeddings via contrastive learning while adopting a disjoint parameter model to learn LLM-specific parameters. Experiments on synthetic data, offline routing
datasets (SPROUT, EmbedLLM, and RouterBench), and real user conversation logs (WildChat-1M) confirm that our methods improve routing, scheduling, and queue stability against strong online and offline-trained baselines.
Read the full abstract ▾
Machine Learning
FiLoRA: Focus-and-Ignore LoRA for Controllable Feature Reliance
Hyunsuk Chung, Soyeon Caren Han, Seungyeon Ji et al. (+3 more)
Multimodal foundation models integrate heterogeneous signals across modalities, yet it remains unclear whether their predictions can be controlled by explicitly modulating reliance on different internal feature pathways. Existing approaches to shortcut and spurious behavior primarily rely on post hoc analysis or data-level interventions, offering limited ability to directly intervene on how models use information. We introduce FiLoRA (Focus-and-Ignore LoRA), an instruction-conditioned, parameter-efficient adaptation framework that enables controllable modulation of feature reliance while keeping the task and predictive objective fixed. FiLoRA decomposes adaptation into feature-aligned low-rank modules and applies instruction-conditioned gating, allowing natural
language instructions to act as computation-level control signals over internal representations. We evaluate FiLoRA across both controlled classification settings and generative
multimodal tasks, and under a range of instruction types, including natural and compositional instructions. Results show that FiLoRA induces consistent and interpretable shifts in feature reliance, selectively amplifying or suppressing different feature groups in accordance with the instruction, without altering task semantics. Our findings suggest that instruction-conditioned parameter adaptation can serve as a practical mechanism for intervening on internal model behavior, providing a new perspective on controllability and analysis of
multimodal systems beyond output-level prompting or post hoc interpretation.
Read the full abstract ▾
All authors Hyunsuk Chung, Soyeon Caren Han, Seungyeon Ji, Jinwoo Kim, Eun-Jung Holden, Kyungreem Han
Machine Learning · Cross-listed from cs.AR
Ultrafast On-Chip Online Learning via Spline Locality in Kolmogorov-Arnold Networks
Duc Hoang, Aarush Gupta and Philip Harris
Ultrafast online learning is essential for high-frequency systems, such as controls for
quantum computing and
nuclear fusion, where adaptation must occur on sub-microsecond timescales. Meeting these requirements demands low-latency, fixed-precision computation under strict
memory constraints, a regime in which conventional Multi-Layer Perceptrons (MLPs) are both inefficient and numerically unstable. We identify key properties of Kolmogorov-Arnold Networks (KANs) that align with these constraints. Specifically, we show that: (i) KAN updates exploiting B-spline locality are sparse, enabling superior on-chip resource scaling, and (ii) KANs are inherently robust to fixed-point quantization. By implementing fixed-point online training on Field-Programmable Gate Arrays (FPGAs), a representative platform for on-chip computation, we demonstrate that KAN-based online learners are significantly more efficient and expressive than MLPs across a range of low-latency and resource-constrained tasks. To our knowledge, this work is the first to demonstrate model-free online learning at sub-microsecond latencies.
Read the full abstract ▾
Machine Learning
FORLER: Federated Offline Reinforcement Learning with Q-Ensemble and Actor Rectification
Nan Qiao and Sheng Yue
In Internet-of-Things systems,
federated learning has advanced online reinforcement learning (RL) by enabling parallel policy training without sharing raw data. However, interacting with real environments online can be risky and costly, motivating offline
federated RL (FRL), where local devices learn from fixed
datasets. Despite its promise, offline FRL may break down under low-quality, heterogeneous data. Offline RL tends to get stuck in local optima, and in FRL, one device's suboptimal policy can degrade the aggregated model, i.e., policy pollution. We present FORLER, combining Q-ensemble aggregation on the server with actor rectification on devices. The server robustly merges device Q-functions to curb policy pollution and shift heavy computation off resource-constrained hardware without compromising
privacy. Locally, actor rectification enriches policy gradients via a zeroth-order search for high-Q actions plus a bespoke regularizer that nudges the policy toward them. A $\delta$-periodic strategy further reduces local computation. We theoretically provide safe policy improvement performance guarantees. Extensive experiments show FORLER consistently outperforms strong baselines under varying data quality and heterogeneity.
Read the full abstract ▾
Machine Learning
Dissecting Outlier Dynamics in LLM NVFP4 Pretraining
Peijie Dong, Ruibo Fan, Yuechen Tao et al. (+11 more)
Training large
language models using 4-bit arithmetic enhances throughput and
memory efficiency. Yet, the limited dynamic range of FP4 increases sensitivity to outliers. While NVFP4 mitigates quantization error via hierarchical microscaling, a persistent loss gap remains compared to BF16. This study conducts a longitudinal analysis of outlier dynamics across architecture during NVFP4 pretraining, focusing on where they localize, why they occur, and how they evolve temporally. We find that, compared with Softmax
Attention (SA), Linear
Attention (LA) reduces per-tensor heavy tails but still exhibits persistent block-level spikes under block quantization. Our analysis attributes outliers to specific architectural components: Softmax in SA, gating in LA, and SwiGLU in FFN, with "post-QK" operations exhibiting higher sensitivity to quantization. Notably, outliers evolve from transient spikes early in training to a small set of persistent hot channels (i.e., channels with persistently large magnitudes) in later stages. Based on these findings, we introduce Hot-Channel Patch (HCP), an online compensation mechanism that identifies hot channels and reinjects residuals using hardware-efficient kernels. We then develop CHON, an NVFP4 training recipe integrating HCP with post-QK operation protection. On GLA-1.3B model trained for 60B
tokens, CHON reduces the loss gap to BF16 from 0.94% to 0.58% while maintaining downstream accuracy.
Read the full abstract ▾
All authors Peijie Dong, Ruibo Fan, Yuechen Tao, Di Mou, Wenhu Hu, Zhenheng Tang, Yinghao Yu, Jiamang Wang, Wenbo Su, Guodong Yang, Liping Zhang, Xiaowen Chu, Baochun Li, Bo Li
Machine Learning
Outlier-robust Diffusion Posterior Sampling for Bayesian Inverse Problems
Yiming Yang, Xiaoyuan Cheng, Yi He et al. (+3 more)
Diffusion models have emerged as powerful learned priors for
Bayesian inverse problems (BIPs).
Diffusion-based solvers rely on a presumed likelihood for the observations in BIPs to guide the generation process. Likelihood misspecification is common in practical BIPs and is known to degrade recovery performance, particularly under outlier contamination. We investigate this problem by first characterizing the induced posterior deviation and proving the stability of
diffusion-based solvers for linear BIPs. Our stability analysis further reveals potential robustness deficiencies of existing
diffusion-based solvers under outlier-contaminated measurements. To address this issue, we propose a simple yet effective solution: robust
diffusion posterior sampling, which is provably outlier-robust for linear BIPs and compatible with existing gradient-based posterior samplers. Empirical results from scientific inverse problems and natural image tasks demonstrate the effectiveness and robustness of our method, with consistent performance gains in challenging scenarios involving outlier contamination for both linear and nonlinear tasks.
Read the full abstract ▾
All authors Yiming Yang, Xiaoyuan Cheng, Yi He, Kaiyu Li, Wenxuan Yuan, Zhuo Sun
Machine Learning · Cross-listed from cs.SI
Twinning Complex Networked Systems: Data-Driven Calibration of the mABCD Synthetic Graph Generator
Piotr Bródka, Michał Czuba, Bogumił Kamiński et al. (+4 more)
The increasing availability of relational data has contributed to a growing reliance on network-based representations of complex systems. Over time, these models have evolved to capture more nuanced properties, such as the heterogeneity of relationships, leading to the concept of multilayer networks. However, the analysis and evaluation of methods for these structures is often hindered by the limited availability of large-scale empirical data. As a result, graph generators are commonly used as a workaround, albeit at the cost of introducing systematic biases. In this paper, we address the inverse-generator problem by inferring the configuration parameters of a multilayer network generator, \mABCD, from a real-world system. Our goal is to identify parameter settings that enable the generator to produce synthetic networks that act as digital twins of the original structure. We propose a method for estimating matching configurations and for quantifying the associated error. Our results demonstrate that this task is non-trivial, as strong interdependencies between configuration parameters weaken independent estimation and instead favour a joint-prediction approach.
Read the full abstract ▾
All authors Piotr Bródka, Michał Czuba, Bogumił Kamiński, Łukasz Kraiński, Katarzyna Musial, Paweł Prałat, Mateusz Stolarski
Machine Learning · Cross-listed from cs.AI
Hunt Instead of Wait: Evaluating Deep Data Research on Large Language Models
Wei Liu, Peijie Yu, Michele Orini et al. (+2 more)
The agency expected of Agentic Large
Language Models goes beyond answering correctly, requiring autonomy to set goals and decide what to explore. We term this investigatory intelligence, distinguishing it from executional intelligence, which merely completes assigned tasks. Data Science provides a natural testbed, as real-world analysis starts from raw data rather than explicit queries, yet few
benchmarks focus on it. To address this, we introduce Deep Data Research (DDR), an open-ended task where LLMs autonomously extract key insights from databases, and DDR-Bench, a large-scale, checklist-based
benchmark that enables verifiable evaluation. Results show that while frontier models display emerging agency, long-horizon exploration remains challenging. Our analysis highlights that effective investigatory intelligence depends not only on
agent scaffolding or merely scaling, but also on intrinsic strategies of agentic models.
Read the full abstract ▾
All authors Wei Liu, Peijie Yu, Michele Orini, Yali Du, Yulan He
Machine Learning · Cross-listed from cs.RO
Bandwidth-Efficient Multi-Agent Communication through Information Bottleneck and Vector Quantization
Ahmad Farooq and Kamran Iqbal
Multi-
agent reinforcement learning systems deployed in real-world robotics applications face severe communication constraints that significantly impact coordination effectiveness. We present a framework that combines information bottleneck theory with vector quantization to enable selective, bandwidth-efficient communication in multi-
agent environments. Our approach learns to compress and discretize communication messages while preserving task-critical information through principled information-theoretic optimization. We introduce a gated communication mechanism that dynamically determines when communication is necessary based on environmental context and
agent states. Experimental evaluation on challenging coordination tasks demonstrates that our method achieves 181.8% performance improvement over no-communication baselines while reducing bandwidth usage by 71.4%. Pareto frontier analysis shows dominance across the entire success-bandwidth spectrum, with an area under the curve of 0.198 vs 0.142 for next-best methods. Our approach significantly outperforms existing communication strategies and establishes a theoretically grounded framework for deploying multi-
agent systems in bandwidth-constrained environments such as robotic swarms, autonomous vehicle fleets, and distributed sensor networks.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.AI
Light Alignment Improves LLM Safety via Model Self-Reflection with a Single Neuron
Sicheng Shen, Mingyang Lv, Han Shen et al. (+7 more)
The safety of large
language models (LLMs) has increasingly emerged as a fundamental aspect of their development. Existing safety
alignment for LLMs is predominantly achieved through post-training methods, which are computationally expensive and often fail to generalize well across different models. A small number of lightweight
alignment approaches either rely heavily on prior-computed safety injections or depend excessively on the model's own capabilities, resulting in limited generalization and degraded efficiency and usability during generation. In this work, we propose a safety-aware decoding method that requires only low-cost training of an expert model and employs a single
neuron as a gating mechanism. By effectively balancing the model's intrinsic capabilities with external guidance, our approach simultaneously preserves utility and enhances output safety. It demonstrates clear advantages in training overhead and generalization across model scales, offering a new perspective on lightweight
alignment for the safe and practical deployment of large
language models. Code: https://github.com/Beijing-AISI/NGSD.
Read the full abstract ▾
All authors Sicheng Shen, Mingyang Lv, Han Shen, Jialin Wu, Binghao Wang, Zhou Yang, Guobin Shen, Dongcheng Zhao, Feifei Zhao, Yi Zeng
Machine Learning · Cross-listed from cs.DB
Hippasus: Accurate and Cost-Efficient Feature Augmentation over Relational Tables
Serafeim Papadias, Kostas Patroumpas and Dimitrios Skoutas
ML models critically depend on feature quality, yet in real-world settings, useful features are often distributed across multiple relational tables rather than a single
dataset. Feature augmentation addresses this problem by automatically discovering and joining additional tables to enrich a base table with predictive features. However, scaling feature augmentation to complex schemas with many tables and multi-hop relationships is challenging. It requires exploring a large space of join paths, executing costly joins, and selecting useful features from noisy results. Existing approaches suffer from either limited effectiveness or efficiency. Restricting exploration to simple joins limits predictive performance, while more expressive methods rely on expensive training data, lack scalability, or fail to fully exploit schema-level semantics. We present Hippasus, a cost-aware, LLM-guided feature augmentation framework over relational schemas, that addresses these challenges. Hippasus ranks candidate join paths before executing any join, by combining lightweight statistical signals with adaptive semantic analysis, invoking an LLM only when necessary. It further introduces efficient multi-way join execution with cross-path feature consolidation, and a hybrid feature selection strategy that integrates statistical relevance with semantic refinement. Experiments on 13 real-world
datasets show that Hippasus improves predictive performance by up to 15.7% on average over state-of-the-art methods, while running on par with the fastest of them and keeping its LLM
token cost low.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.IR
Adaptive Quality-Diversity Trade-offs for Large-Scale Batch Recommendation
Clémence Réda, Tomas Rigaux, Hiba Bederina et al. (+3 more)
A core research question in recommender systems is to propose batches of highly relevant and diverse items, that is, items personalized to the user's preferences, but which also might get the user out of their comfort zone. This diversity might induce properties of serendipidity and novelty which might increase user engagement or revenue. However, many real-life problems arise in that case: e.g., avoiding to recommend distinct but too similar items to reduce the churn risk, and computational cost for large item libraries, up to millions of items. First, we consider the case when the user feedback model is perfectly observed and known in advance, and introduce an efficient
algorithm called B-DivRec combining determinantal point processes and a fuzzy denuding procedure to adjust the degree of item diversity. This helps enforcing a quality-diversity trade-off throughout the user history. Second, we propose an approach to adaptively tailor the quality-diversity trade-off to the user, so that diversity in recommendations can be enhanced if it leads to positive feedback, and vice-versa. Finally, we illustrate the performance and versatility of B-DivRec in the two settings on synthetic and real-life data sets on movie recommendation and drug repurposing.
Read the full abstract ▾
All authors Clémence Réda, Tomas Rigaux, Hiba Bederina, Koh Takeuchi, Hisashi Kashima, Jill-Jênn Vie
Machine Learning · Cross-listed from cs.NE
Scale-covariant spiking wavelets
Jens Egholm Pedersen, Tony Lindeberg and Peter Gerstoft
We establish a theoretical connection between wavelet transforms and spiking neural networks through scale-space theory. We rely on the scale-covariant guarantees in the leaky integrate-and-fire
neurons to implement discrete mother wavelets that approximate continuous wavelets. A reconstruction experiment demonstrates the feasibility of the approach and warrants further analysis to mitigate current approximation errors. Our work suggests a novel spiking signal representation that could enable more energy-efficient signal processing
algorithms.
Read the full abstract ▾
Machine Learning
DASH: Faster Shampoo via Batched Block Preconditioning and Efficient Inverse-Root Solvers
Ionut-Vlad Modoranu, Philip Zmushko, Erik Schultheis et al. (+2 more)
Shampoo is one of the leading approximate second-order optimizers: a variant of it has won the MLCommons AlgoPerf competition, and it has been shown to produce models with lower activation outliers that are easier to compress. Yet, applying Shampoo currently comes at the cost of significant computational slowdown, due to its expensive internal operations. In this paper, we take a significant step to address this shortcoming by proposing \method (for Distributed Accelerated SHampoo), a faster implementation of Distributed Shampoo based on two main new techniques: First, we show that preconditioner blocks can be stacked into 3D tensors to significantly improve GPU utilization; second, we introduce the Newton-DB iteration and the Chebyshev
polynomial approximations as novel and faster approaches for computing the inverse
matrix roots required by Shampoo. Along with these algorithmic contributions, we provide a first in-depth analysis of how
matrix scaling critically affects Shampoo convergence. On the practical side, our GPU-aware implementation achieves up to $5.6\times$ faster optimizer steps compared to the well-optimized Distributed Shampoo, while Newton-DB attains the lowest validation perplexity per iteration among all tested methods. Our code is available at https://github.com/IST-DASLab/DASH.
Read the full abstract ▾
All authors Ionut-Vlad Modoranu, Philip Zmushko, Erik Schultheis, Mher Safaryan, Dan Alistarh
Machine Learning
Robust Domain Generalization under Divergent Marginal and Conditional Distributions
Jewon Yeom, Kyubyung Chae, Hyunggyu Lim et al. (+3 more)
Domain generalization (DG) aims to learn predictive models that can generalize to unseen domains. Most existing DG approaches focus on learning domain-invariant representations under the assumption of conditional distribution shift (i.e., primarily addressing changes in $P(X\mid Y)$ while assuming $P(Y)$ remains stable). However, real-world scenarios with multiple domains often involve compound distribution shifts where both the marginal label distribution $P(Y)$ and the conditional distribution $P(X\mid Y)$ vary simultaneously. To address this, we propose a unified framework for robust domain generalization under divergent marginal and conditional distributions. We derive a novel risk bound for unseen domains by explicitly decomposing the joint distribution into marginal and conditional components and characterizing risk gaps arising from both sources of divergence. To operationalize this bound, we design a meta-learning procedure that minimizes and validates the proposed risk bound across seen domains, ensuring strong generalization to unseen ones. Empirical evaluations demonstrate that our method achieves state-of-the-art performance not only on conventional DG
benchmarks but also in challenging multi-domain long-tailed recognition settings where both marginal and conditional shifts are pronounced.
Read the full abstract ▾
All authors Jewon Yeom, Kyubyung Chae, Hyunggyu Lim, Yoonna Oh, Dongyoon Yang, Taesup Kim