Machine Learning
A2D2: Fine-Tuning Any-Length Discrete Diffusion for Adaptive Decoding
Sophia Tang, Yuchen Zhu, Molei Tao et al. (+1 more)
Discrete
diffusion models offer a simple and stable likelihood-based framework for sequence generation, recently extended to any-length settings via
token insertion. Principled reward-guided fine-tuning for any-length discrete
diffusion, however, remains largely unexplored. We introduce Fine-Tuning Any-Length Discrete
Diffusion for Adaptive Decoding (A2D2), a unified framework for reward-guided fine-tuning of any-length discrete
diffusion models via joint optimization of the insertion and unmasking policies together with a quality-based inference schedule. We derive the Radon-Nikodym derivative for the joint insertion-unmasking path measures, enabling theoretically guaranteed convergence to the intractable reward-tilted sequence distribution without requiring target samples. Building on this, we establish unmasking and insertion quality as tractable approaches for minimizing decoding error and introduce the Adaptive Joint Decoding (AJD) loss, which provably yields the optimal path measure that generates the reward-tilted distribution. Empirically, A2D2 improves reward optimization while enhancing generation flexibility and accuracy over prior fixed-length fine-tuning and inference-time guidance methods.
Read the full abstract ▾
All authors Sophia Tang, Yuchen Zhu, Molei Tao, Pranam Chatterjee
Machine Learning · Cross-listed from cs.NI
NetCause: Counterfactual Learning for Root Cause Analysis in Large-Scale Networks
Fabien Chraim, Jian Zhang, Dominik Janzing et al. (+3 more)
Can a learned model capture how faults propagate through a large-scale network and use this knowledge to causally attribute customer impact to its underlying root cause? Existing root cause analysis techniques often rely on static rules, correlation heuristics, or
topology-local
reasoning, which struggle to generalize in dynamic environments where faults propagate across complex physical and logical dependencies. We present NetCause, a self-supervised learning-based framework that models network incidents as graph-temporal processes and uses counterfactual simulation to rank candidate root causes. This approach produces an interpretable ranking of root cause hypotheses and integrates naturally with operator-defined mitigation and remediation actions. We train the model on over 1,500 incidents collected over six months from a leading cloud provider's production network and evaluate it on 31 expert-labeled incidents. NetCause consistently improves root cause ranking quality in the regime most relevant to operational decision-making, achieving a 16.1% accuracy improvement over a rule-based heuristic baseline. While training is computationally intensive, inference is lightweight, requiring only seconds of GPU runtime per incident (well below typical telemetry collection latencies).
Read the full abstract ▾
All authors Fabien Chraim, Jian Zhang, Dominik Janzing, Xiang Song, Christos Faloutsos, John Evans
Machine Learning · Cross-listed from cs.NI
Graphical Causal Reasoning for Root Cause Analysis in Cloud Networks
Fabien Chraim, Dominik Janzing and John Evans
Cloud-computing relies on large-scale networks which are inherently complex systems. In this paper, we present a novel approach to root cause analysis (RCA) of cloud network incidents, leveraging graph-based causal discovery techniques. Our method addresses the limitations of rule-based automation by introducing a spatiotemporal grouping strategy and an automation ontology to reduce the dimensionality of the problem. We construct a causal graph from binary time series data using bivariate Granger causality and conditional independence tests. For inference, we introduce a probabilistic method that assigns edge-specific conditional probabilities as a function of time lag, allowing for interpretable, time-aware root cause scoring via causal graph traversal. We evaluated the system using a labeled
dataset of 35 production incidents from a major cloud provider. The model successfully recalled the correct root cause in 85.7% of incidents and produced an exact match in 74.3%. In production, the deployed system has been used in over 800 real-world incidents, with positive qualitative feedback from network engineers. These results highlight the practicality of a data-driven, causal approach to RCA in dynamic and large-scale operational environments.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.HC
Ride, Track, and Recover: Pilot Randomized Trial of a Wearable Digital Self-Management Intervention During a Veteran Endurance-Cycling Program
Alan Ta, Nilsu Salgin, Caleb Armstrong et al. (+2 more)
Post-traumatic stress disorder (PTSD) in veterans is characterized by persistent hyperarousal and comorbid anxiety and depressive symptoms that are difficult to monitor and manage outside clinical settings. Thirteen veterans participating in a Project Hero cycling event in Texas were randomized by computer-generated sequence in a naturalistic setting to two arms: (1) digital intervention plus physical activity, or (2) physical activity only, plus a third at-home monitoring control cohort consisting of 7 veterans selected from the broader Project Hero veteran community. Continuous smartwatch sensing combined heart rate and accelerometer features to detect hyperarousal events, which were confirmed in real time by participants. Weekly self-report measures of anxiety, depression, and PTSD severity were collected. Generalized additive mixed models characterized nonlinear trajectories over time. Baseline-normalized hyperarousal trajectories differed significantly across conditions, with the digital intervention group (n=7) showing structured stabilization compared to late-study escalation in the physical-only group (n=3). Both cycling groups exhibited acute symptom improvements during the endurance event; however, the digital intervention group demonstrated a higher overall maintenance of gains. The at-home control group (n=4) showed gradual symptom declines. Perceived precision of ML detections varied substantially across individuals and was positively associated with symptom severity, with higher-severity participants confirming a greater proportion of detected events. These results suggest that coupling wearable detection with digital self-management tools may support stabilization of hyperarousal and symptom improvement while emphasizing the importance of personalization and human-centered design in wearable mental health systems.
Read the full abstract ▾
All authors Alan Ta, Nilsu Salgin, Caleb Armstrong, Kala Phillips Reindel, Farzan Sasangohar
Machine Learning · Cross-listed from cs.CV
MaskWAM: Unifying Mask Prompting and Prediction for World-Action Models
Hanyang Yu, Haitao Lin, Jingbo Zhang et al. (+4 more)
World Action Models (WAMs) present a promising paradigm for robotic control via
video prediction. However, current WAMs suffer from fundamental spatial bottlenecks: standard text inputs introduce referential ambiguity in cluttered scenes, while unstructured RGB predictions lack semantic grounding and remain biased by task-irrelevant backgrounds. To overcome these limitations, we introduce MaskWAM, an object-centric world-action model. By jointly integrating masks as both explicit inputs and predictions via a unified Mixture of
Transformers (MoT), MaskWAM unlocks robust policy generalization. This design provides two key benefits: (1) predicting future masks yields object-centric semantic supervision that suppresses visual noise, significantly enhancing even standard text-conditioned WAMs; and (2) coupling this predictive supervision with first-frame visual
prompts, such as target object masks, establishes a precise spatial anchor that substantially reduces
language ambiguity. Crucially, as WAMs are inherently
vision-driven architectures, direct mask conditioning yields substantially stronger guidance than text alone, establishing a precise and robust paradigm for manipulating unseen objects. Evaluations on LIBERO, RoboTwin, and real-world tasks demonstrate that MaskWAM significantly outperforms baselines in both
language-clear and
language-ambiguous tasks.
Read the full abstract ▾
All authors Hanyang Yu, Haitao Lin, Jingbo Zhang, Wenyao Zhang, Chenghao Gu, Heng Li, Ping Tan
Machine Learning · Cross-listed from cs.DC
GF-DiT: Scheduling Parallelism for Diffusion Transformer Serving
Xinwei Qiang, Yifan Hu, Shixuan Sun et al. (+6 more)
Diffusion Transformers (DiTs) have become the dominant architecture for image and
video generation, creating growing demand for efficient DiT serving. Existing systems assign each request a fixed parallel configuration throughout its lifetime. However, DiT workloads exhibit substantial heterogeneity across requests, execution stages, and system conditions, making static parallelism inefficient and often leading to poor GPU utilization and degraded service quality. This paper argues that DiT serving should treat GPU parallelism as a first-class schedulable resource. We present GF-DiT, a policy-programmable runtime for elastic DiT serving that dynamically adapts the parallelism of running requests according to workload demands and service objectives. GF-DiT introduces an asynchronous execution abstraction that decomposes requests into independently schedulable trajectory tasks and enables online GPU reallocation. To make elastic parallelism practical, GF-DiT further proposes group-free collectives, a lightweight communication abstraction that supports low-overhead online formation and reconfiguration of arbitrary execution groups. We implement GF-DiT in vLLM-Omni and evaluate it on representative image and
video diffusion workloads. Compared with fixed-pipeline execution with static parallelism, GF-DiT improves throughput by up to 6.01$\times$, reduces mean latency by up to 95%, lowers SLO violation rates by up to 90%, and reduces communication-group setup overhead from 778 ms to approximately 60 $\mu$s. Our code is available at https://github.com/SJTU-
Liquid/GF-DiT.
Read the full abstract ▾
All authors Xinwei Qiang, Yifan Hu, Shixuan Sun, Jing Yang, Han Zhao, Chen Chen, Yu Feng, Jingwen Leng, Minyi Guo
Machine Learning
CRAFTIIF: Cross-Resolution Analytic Four-Type Interpretable Isolation Forest for Multivariate Time Series Anomaly Detection
William Smits
Anomaly detection in multivariate time series is challenged by four structurally distinct anomaly types – point (isolated spikes), distributional (level shifts), temporal (rhythm changes), and collective (inter-sensor correlation breakdowns) – each requiring different feature representations. Most unsupervised methods target only one or two types and provide limited interpretability. We present CRAFTIIF (Cross-Resolution Analytic Four-Type Interpretable Isolation Forest), a fully unsupervised framework targeting all four types without
dataset-specific tuning. CRAFTIIF generates K=500 random analytic wavelet feature draws across four families (Morlet, DOG, Haar, Coiflet), each targeting a specific anomaly type, feeding five structured Isolation Forests – one per type plus a meta-IF for compound anomalies. An adaptive Otsu/MAD threshold calibrates detection automatically across anomaly rates from 0.1% to 69.2%. Because each IF is trained exclusively on type-specific features, branch firing provides direct anomaly-type attribution by construction, without post-hoc explanation. Evaluated on all 19
datasets of the mTSBench
benchmark (Zhou et al., TMLR 2026), CRAFTIIF achieves mean F1=0.228 (all 19
datasets) and F1=0.322 (13 detectable
datasets), ranking first among all 25 evaluated methods on VUS-PR (0.463 vs. previous best 0.329, +40.7%). A diagnostic framework – oracle F1, detectability limits, and branch separation ratios – identifies 6 of 19
datasets as fundamentally undetectable by any unsupervised method. Ablation over 11 conditions confirms adaptive thresholding (+38% F1), four-branch structure (+20%), and meta-IF (+23%) are each essential. Code: https://github.com/smitswil/craftiif
Read the full abstract ▾
Machine Learning
SupraBench: A Benchmark for Supramolecular Chemistry
Tianyi Ma, Yijun Ma, Zehong Wang et al. (+6 more)
Supramolecular chemistry, which includes the study of non-covalent host-guest assemblies, has advanced various applications. However, designing host-guest systems remains time-consuming, requiring days of dry-lab verification per candidate pair. Although LLMs have emerged as a fast alternative with strong performance on molecular binding tasks, no
benchmark currently systematically evaluates LLMs for host-guest
reasoning across fundamental supramolecular chemistry tasks, e.g., binding affinity prediction. To this end, we collaborate with domain experts to release the first Supramolecular
Benchmark, called SupraBench, to evaluate LLMs in chemistry
reasoning. Specifically, we design four fundamental tasks, i.e., binding affinity prediction, top-binder selection, solvent identification, and host-guest description, plus an auxiliary
vision-based task for molecular identification. We also release SupraPMC, a curated 16M-
token corpus of Supramolecular chemistry articles distilled from Europe PMC, to support the adaptation to the supramolecular domain. We
benchmark a broad range of open and proprietary LLMs and find that LLMs leave substantial headroom across all tasks. Domain adaptation pretraining over SupraPMC transfers cleanly to in-distribution regression but trades off against strict letter-format output. Moreover, the difficulty profile differs sharply across task families, revealing distinct failure modes that indicate specific gaps in current supramolecular chemistry
reasoning. Our source codes and
benchmark datasets are available at https://github.com/Tianyi-Billy-Ma/SupraBench.
Read the full abstract ▾
All authors Tianyi Ma, Yijun Ma, Zehong Wang, Weixiang Sun, Ziming Li, Connor R. Schmidt, Chuxu Zhang, Matthew J. Webber, Yanfang Ye
Machine Learning
MaxProof: Scaling Mathematical Proof with Generative-Verifier RL and Population-Level Test-Time Scaling
Jiacheng Chen, Xinyu Zhang, Shunkai Zhang et al. (+20 more)
We present MaxProof, a population-level test-time scaling framework for competition-level mathematical proof in the MiniMax-M3 series. M3 first trains three proof-oriented capabilities – proof generation, proof verification, and critique-conditioned proof repair – using a defense-in-depth generative verifier engineered for low false-positive rate. These capabilities are merged into a single released M3 model. At test time, MaxProof treats the model as a generator, verifier, refiner, and ranker, searches over a population of candidate proofs, and returns one final proof through tournament selection. With MaxProof test-time scaling, the M3 model reaches 35/42 on IMO 2025 and 36/42 on USAMO 2026, exceeding the human gold-medal threshold on both.
Read the full abstract ▾
All authors Jiacheng Chen, Xinyu Zhang, Shunkai Zhang, Yanmohan Wang, Lin Li, Tiancheng Qin, Qin Wang, Zhengmao Zhu, Tianle Li, Jingyang Li, Zehan Li, Binyang Jiang, Jin Zhu, Han Ding, Fei Yu, Chenyu Du, Zijian Song, Jiayuan Song, Zhi Zhang, Yunan Huang, Weiyu Cheng, Pengyu Zhao, Yu Cheng
Machine Learning
Reinforcement Learning for Neural Model Editing
Shaivi Malik
Editing pretrained neural networks requires specialized
algorithms tailored to specific objectives. Designing such
algorithms is often time-consuming and demands significant effort. We present an exploratory framework that formulates neural model editing as a reinforcement learning problem, where
agents modify models using reward feedback. We introduce two environments: MaskWorld, where
agents scale weights multiplicatively, and ShiftWorld, where
agents apply additive weight updates. The reward function combines a utility-preservation objective with a task-specific editing objective, enabling
agents to learn targeted modifications while maintaining overall model performance. We evaluate the framework on bias mitigation in text classification and machine unlearning in image classification, both of which traditionally rely on specialized
algorithms. Our results show that the learned policies reduce forget set accuracy to nearly 0% while preserving over 90% retain set accuracy on the unlearning task. In the bias mitigation setting, the learned policies improve bias-related performance by more than 5% while maintaining general classification utility. Our findings show that neural model editing can be cast as a reinforcement learning problem, allowing editing policies to be learned from reward feedback rather than manually engineered for each task.
Read the full abstract ▾
Machine Learning · Cross-listed from physics.optics
Optical Implementation of Equilibrium Propagation Using Spatial Photonic Ising Machines
Dimitri Vanden Abeele, Daniele Veraldi, Davide Pierangeli et al. (+2 more)
Equilibrium Propagation offers a compelling alternative to traditional machine learning for training energy-based networks. Here we demonstrate a hybrid optical-digital implementation of EP using a Spatial Photonic Ising Machine (SPIM). The SPIM exploits the gauge transformation method to optically encode both continuous
neuron states and rank-1 binary trainable patterns as phase modulations via a spatial light modulator, with inference realized using a finite difference scheme. The experimental system is evaluated on the Wine classification
dataset. The potential of this approach, including the use of continuous couplings and structured coupling
matrices, is evaluated numerically on the more complex MNIST
dataset. Our work provides a concrete pathway toward energy-efficient physical implementations of
Equilibrium Propagation.
Read the full abstract ▾
All authors Dimitri Vanden Abeele, Daniele Veraldi, Davide Pierangeli, Claudio Conti, Serge Massar
Machine Learning
Uncertainty Estimation for Molecular Diffusion Models
Paul Seij, Christian A. Naesseth, Stephan Mandt et al. (+1 more)
Diffusion models have seen wide adoption for 3D molecular generation, yet they offer no principled signal of when a generated molecule is likely to be of low quality. We propose a post-hoc method for estimating per-sample uncertainty in pretrained molecular
diffusion models. Building on a Laplace approximation of the denoising network, we measure the variability of the noise prediction across the generation trajectory. Empirically, we show that the resulting uncertainty score is informative of sample quality, exhibiting a negative correlation with established sample-level quality metrics. We further study how the proposed uncertainty score can be used to filter generated samples, improving model performance via test-time scaling.
Read the full abstract ▾
All authors Paul Seij, Christian A. Naesseth, Stephan Mandt, Metod Jazbec
Machine Learning
Clustering Node Attributed Networks with Graph Neural Networks and Self Learning
Rodrigo de Sapienza Luna and Daniel Ratton Figueiredo
Graph clustering - partitioning the node set of a graph into disjoint subsets that reflect some latent information - is a fundamental problem as it finds applications in a myriad of different scenarios. While this classic problem has been tackled for decades by different communities, a recent variation of the problem driven by real data considers the scenario where nodes have attributes that are also informative. This has triggered novel methods that simultaneously leverage network information (edges) and node information (attributed) in the design of novel clustering
algorithms. This work proposes a novel framework that builds on prior works that have applied graph neural networks (GNN) to graph clustering. The proposed framework operates in rounds of self learning in a fully unsupervised setting. In each round, a GNN generates representations for nodes that are used to cluster the nodes. This clustering influences the graph used to generate the node representation in the next round. Moreover, a context graph built in each round using the original graph is used to generate the node representations. Empirical results show that the proposed methodology extracts information from both network edges and node attributes in synthetic data, outperforming
algorithms focused solely on the network or attributes when neither are very informative. Multiple rounds of learning also improve the performance and always outperforms a long single round of training (i.e., classic GNN graph clustering). When considering real
datasets, empirical results indicate that the proposed methodology is competitive to state-of-the-art methods when cluster sizes are balanced.
Read the full abstract ▾
Machine Learning
How Much Memory Do We Need? Adaptive Memory Gate for Neural Operators
Jihyeon Hur, Yongseok Kwon, Min-Gi Jo et al. (+2 more)
Neural operators have emerged as a powerful data-driven approach for solving time-dependent PDEs. Among recent advances,
memory-augmented neural operators explicitly incorporate past states and have achieved remarkable performance under low-resolution observation settings. However, existing approaches apply a fixed
memory weight regardless of observation conditions, such as resolution or physical parameters, limiting their adaptability. Our preliminary experiments reveal that optimal
memory weight varies with resolution and viscosity, implying that a fixed
memory weight cannot simultaneously optimize performance across diverse settings. We propose AMGFNO, which dynamically modulates
memory weight through a learnable gate. On the Kuramoto-Sivashinsky and Burgers' equations, AMGFNO achieves 55-79% nRMSE reduction over at low resolution, with the learned gate value automatically decreasing from $\bar{g} \approx 0.7$ to near-zero as resolution increases.
Read the full abstract ▾
All authors Jihyeon Hur, Yongseok Kwon, Min-Gi Jo, Jeongwhan Choi, Noseong Park
Machine Learning · Cross-listed from cs.CL
S-GBT: Smooth Growth Bound Tensor for Certified Robustness Against Word Substitution Attacks in NLP
Mohammed Bouri, Mohammed Erradi and Adnane Saoud
Despite recent progress in Natural
Language Processing (NLP), models remain vulnerable to word substitution attacks. Most existing defenses focus on first order sensitivity and measure how much the output changes when the input is slightly perturbed. However, they ignore how this sensitivity evolves, which is described by
curvature. When gradients vary sharply, models can still fail. This paper introduces the Smooth Growth Bound Tensor (S-GBT), a second order method that bounds the Hessian element-wise, for which we provide formal theoretical proofs on the resulting robustness bounds. A regularization term is added during training to minimize these bounds. This yields tighter certified robustness against word substitution attacks. The change in the output under word substitution is bounded by both a linear term and a quadratic term. S-GBT is derived for two architectures: Long Short-Term
Memory (LSTM) and Convolutional Neural Networks (CNN). The method is integrated directly into the training objective. Its effectiveness is evaluated on multiple
benchmark datasets. The results show that combining first and second order regularization improves certified robust accuracy by up to 23.4% compared to prior methods, while clean accuracy remains competitive. These findings indicate that controlling both the gradient and its variation is a promising direction for building more robust models.
Read the full abstract ▾
Machine Learning
Accelerating Speculative Diffusions via Block Verification
Alexander Soen, Hisham Husain, Valentin De Bortoli et al. (+1 more)
Speculative decoding speeds up LLM inference by using a draft model to generate
tokens, with an acceptance-rejection scheme that ensures that the output matches the target distribution. Adapting this to continuous
diffusions is difficult because speculative sampling requires drawing from a residual distribution. While straightforward in discrete spaces, efficiently sampling this residual in continuous space is non-trivial. Consequently, existing
diffusion adaptations either use computationally inefficient sampling techniques or rely on an alternative scheme. In this work, we introduce a novel scheme that efficiently implements the original speculative sampling mechanism for
diffusion models. Our approach offers a critical advantage over current methods: it enables us to adapt block verification from LLMs to
diffusions – which provably improves the acceptance rate of drafts. Furthermore, we formalize and analyze the Free Drafter, a heuristic self-speculative drafter for
diffusions that requires no training. By enabling block verification, our Free Drafter yields up to a 6.3% speedup over existing speculative methods with no additional training and negligible overhead beyond the existing parallel verification pass.
Read the full abstract ▾
All authors Alexander Soen, Hisham Husain, Valentin De Bortoli, Arnaud Doucet
Machine Learning · Cross-listed from quant-ph
Quantum Statistical Memory Advantage Reveals Predictive Structure in Chaotic Invariant Measures
Maida Wang, Xiao Xue, Minh Chung et al. (+1 more)
Long-horizon prediction of a chaotic system is governed by fidelity to its invariant measure, and which parts of that measure a learned predictor needs is a physical question not known in advance. We establish a
quantum statistical
memory advantage for interrogating it. A
quantum statistical prior (Q-Prior), trained once on classical data, stores an efficiently preparable $k$-point marginal in polynomially many
circuit parameters against exponentially many for explicit tabulation. Collective Bell measurements on two copies then estimate any post hoc Pauli-expectation magnitude at a copy cost independent of register size, with a worst-case exponential separation from single-copy protocols. A single Bell
dataset supports an entire family of candidate observables at a cost growing only logarithmically in the family size, so an exponentially large candidate space stays open for later analysis. We implement the protocol on IQM superconducting processors with two-copy registers of up to 54 physical-
qubit chips. We apply this to turbulent channel flow and ERA5
forecasting, resolving invariant structure by statistical sector and order. Turbulent phase correlations persist through eighth order, while most predictive gains arise from low-order constraints; in ERA5, planetary-wave phase coherence complements covariance regularisation, identifying distinct low-order sectors with predictive value.
Quantum statistical
memory is therefore both a near-term computational resource and an instrument for identifying which invariant structures matter for prediction.
Read the full abstract ▾
All authors Maida Wang, Xiao Xue, Minh Chung, Peter V. Coveney
Machine Learning
PolyFlow: Safe and Efficient Polytope-Constrained Flow Matching with Constraint Embedding and Projection-free Update
Jianming Ma, Qiyue Yang, Yang Zhang et al. (+4 more)
While flow-based generative models have demonstrated strong performance across a wide range of domains, deploying them in safety-critical physical systems remains challenging due to strict constraint requirements. Existing approaches typically enforce safety through post-hoc corrections, which incur substantial computational overhead and may distort the learned distribution. We propose PolyFlow, a polytope-constrained flow matching framework that embeds constraints directly into the model and flow dynamics. PolyFlow introduces a discrete-time flow formulation and a projection-free architecture, which eliminate the discretization error and guarantee strict satisfaction of arbitrary polyhedral constraints, without the need for expensive iterative solvers. Experimental results show that PolyFlow achieves zero constraint violation while maintaining high distributional fidelity across a range of planning and control tasks. Compared to state-of-the-art constrained generation baselines, PolyFlow significantly reduces inference latency and demonstrates a favorable trade-off between safety, efficiency, and generative quality. Code is available on https://github.com/MJianM/PolyFlow.
Read the full abstract ▾
All authors Jianming Ma, Qiyue Yang, Yang Zhang, Liyun Yan, Zhanxiang Cao, Yazhou Zhang, Yue Gao
Machine Learning
Hölder++: Improving the Quality-Coherence Trade-off in Multimodal VAEs
Huyen Vo, María Martínez-García and Isabel Valera
Existing approaches for
multimodal variational autoencoders (VAEs) face a trade-off between generative quality and coherence-i.e., they struggle to generate realistic and diverse samples that, at the same time, are semantically consistent across modalities. A recent work shows that using a simple approximation to Hölder pooling as an aggregation method improves coherence over the SOTA MMVAE+, despite assuming a single shared representation across all modalities. Yet, it slightly compromises sample diversity. Inspired by this insight, we propose Hölder++, a novel
multimodal VAE that improves the generative quality-coherence trade-off through: (i) the first implementation of Hölder pooling without any approximation for
multimodal VAEs; (ii) an extended architecture that models distinct shared and private (i.e., modality-specific) representations (Hölder+); and (iii) hierarchical inference that further enhances the disentanglement between the shared and private representations (Hölder++). Our experiments corroborate that Hölder++ consistently improves the generative quality-coherence trade-off, yields more structured latent spaces, and learns shared representations that are informative for downstream tasks.
Read the full abstract ▾
Machine Learning
Positional Encoding in the Context of Memristor-Based Analog Computation for Automatic Speech Recognition
Benedikt Hilmes, Nick Rossenbach and Ralf Schlüter
Memristors provide a new chance for resource-efficient computation of neural models for natural
language processing by enabling analog execution of vector-
matrix-multiplication. Yet, computations on these devices are currently subject to larger distortion, both in weight programming and execution. In this work, we identify large output values of transformed positional encodings to cause major degradation within analog-to-digital conversion (ADC) as part of memristor-based computation. By adjusting the proportion of weight and precision bits of the ADC of specific memristor layers, we reduce the degradation of the execution by ~50% relative, while keeping the estimated energy consumption stable. Additionally, we investigate scenarios where the ADC cannot be modified. In that case the degradation can be reduced by ~30% relative after removing encoding-related linear transformations.
Read the full abstract ▾
Machine Learning
VideoMDM: Towards 3D Human Motion Generation From 2D Supervision
Amir Mann, Gal Michael Harari, Merav Keidar et al. (+1 more)
We introduce VideoMDM, a
diffusion-based framework that trains 3D human motion priors directly from accurate 2D poses extracted from
monocular videos, without any 3D ground truth. A pretrained 2D-to-3D lifter provides approximate 3D pose sequences that serve as a noisy teacher: these are diffused, denoised by the model in 3D, and supervised in 2D by reprojecting the prediction and comparing against accurate keypoints. We show that, under mild assumptions, a depth-weighted 2D reprojection loss is equivalent in expectation to direct 3D supervision, and we adapt standard 3D motion regularizers - velocity consistency and over-parameterized representation
alignment - to this 2D setting. Unlike methods that lift 2D to 3D only at inference, VideoMDM learns a coherent 3D motion
manifold during training. On HumanML3D it nearly closes the gap to fully 3D-supervised MDM (FID 0.88 vs 0.54); On real
video datasets Fit3D and NBA the method learns to generate motions consistently preferred by humans, with strong quantitative results.
Read the full abstract ▾
All authors Amir Mann, Gal Michael Harari, Merav Keidar, Or Litany
Machine Learning
Enhanced Low-Density Region Exploration in Classifier-Guided Diffusion Models Through Modified Reverse Diffusion Sampling
Jagriti Singh, Shekhar Verma and Muneendra Ojha
Diffusion models have emerged as state-of-the-art generative models for high-fidelity image synthesis, particularly in their classifier-free guided and classifier-guided forms. However, standard classifier guidance concentrates probability mass around high-density class mean, leading to poor coverage of rare samples in the tails of the class-conditional distributions. Recent work on
diffusion-based tail sampling mitigates this by training an additional low-density-seeking classifier with a synthetic-vs-real discriminator, at the cost of additional networks and training. In parallel, a number of samplers and
distillation techniques accelerate or refine
diffusion sampling, but do not explicitly address long-tail coverage. We propose a purely sampling-time, density-aware extension of classifier-guided conditional
diffusion model that targets low-density regions without any additional training. We have applied guidance at noisy images not on predicted noise like most
diffusion models. Starting from a pretrained conditional
diffusion model and classifier on ImageNet, we modify the guided reverse dynamics by steering trajectories toward low-confidence regions via the modified classifier gradient, and at each time step, we also guide the sampling process toward the predicted real image. 1st guidance helps explore low-probability samples, and 2nd guidance helps to generate samples to be close to the real data
manifold. The proposed sampler consistently improves ADM model recall at 64x64 resolution while maintaining a comparable FID, and with a 256x256 ADM model, we showed the results visually with different combinations of both guidance. We also showed that standard ADM classifier guidance, combined with predicted real image guidance, helps generate high perceptual quality samples with a 256x256 ADM model on ImageNet.
Read the full abstract ▾
Machine Learning
Navigating the Safety-Fidelity Trade-off: Massive-Variate Time Series Forecasting for Power Systems via Probabilistic Scenarios
Kaijie Xu, Anqi Wang and Xilin Dai
Probabilistic
forecasting models are increasingly deployed on multivariate systems with distinct channel physics and operational constraints, but existing
benchmarks evaluate neither property at scale. Public canonical multivariate
benchmarks cap out at 2,000 channels, while power-system
benchmarks either lack temporal structure or probabilistic evaluation. We introduce PowerPhase, a probabilistic
forecasting benchmark built on six transmission grids ranging from 2,000 to 36,964 jointly forecasted channels, more than an order of magnitude beyond popular canonical multivariate
benchmarks. Each target trajectory is the output of an AC power-flow solve, and PowerPhase ships with constraint-aware metrics, including Safety_mBrier, NECV, and CVaR-alpha, that complement CRPS and Distortion. Across eight baselines and three seeds, distributional accuracy and constraint satisfaction rank models differently, a trade-off we term safety-fidelity. We further propose PowerForge, a scenario-based
quantile forecaster with type-specific decoding heads and a causal bridge between variable groups, which achieves the best average rank on every grid.
Read the full abstract ▾
Machine Learning
Rarity-Gated Context Conditioning for Offline Imitation Learning-Based Maritime Anomaly Detection
Yongmin Kim, ByeongHoon Jeon and Sungil Kim
Contextual anomaly detection aims to identify abnormal behavior conditional on context variables, but practical deployments often face highly imbalanced context distributions where rare regimes can be critical information. Under such frequency bias, context-conditioned models can produce unstable decisions and excessive false alarms in rare contexts. We propose Rarity-Gated Feature-wise Linear Modulation (RGFiLM), a rarity-aware conditioning module that combines feature-wise modulation (i.e., context-conditioned scaling and shifting of hidden features) with a gate controlled by a data-driven rarity score. The rarity score is estimated from the empirical distribution of context variables and regulates how strongly context modulates intermediate representations: the gate becomes more decisive under rare contexts while remaining conservative under frequent contexts. We evaluate RGFiLM on maritime trajectory anomaly detection using AIS motion sequences with ERA5 environmental context in an environment-sensitive detour scenario. When instantiated in a sequential anomaly scoring pipeline, RGFiLM achieves the best mean F1–False Positive Rate (FPR) trade-off among the compared context-agnostic and context-conditioned methods. These results suggest that explicitly accounting for context rarity is an effective approach for reducing false alarms in context-sensitive anomaly detection.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.AI
Physics-Guided Spatiotemporal Learning for Coastal Wave Peak Period Estimation from Video
Abubakar Hamisu Kamagata, Dharm Singh Jat, Attlee Munyaradzi Gamundani et al. (+2 more)
Direct estimation of physically interpretable periodic signals from raw
video constitutes a spatiotemporally grounded learning problem that proves to be difficult especially when facing label sparsity, lack of physical grounding and standardization
benchmarks. The wave monitoring at coastal sites is one such real-world example where current deep learning approaches for estimating wave parameters using
video as input suffer from physical interpretability and require some kind of intermediate data processing. In this study we propose a framework for wave peak period estimation using only
video as input through three components: automated region-of-interest detection using temporal pixel variance, multi-stage Sim-to-Real transfer learning process, and physics-guided regularization of the output predictions. Various spatiotemporal architectures, including
Transformer and recurrent-convolutional were compared during the stages of synthetic pretraining, silver label adaptation, and expert fine-tuning. It has been found out that LtViViT achieves the highest accuracy in its estimates, while TinyWaveNet shows superior temporal stability and oceanographic skill. Additionally, ablation studies have demonstrated that physics-guided regularization helps to follow the trends in predictions more consistently and prevent physically meaningless predictions. Moreover, Grad-CAM-based explainability analysis of the physics-guided TinyWaveNet showed that its spatial focus aligns with hydrodynamically active surf-zone regions. Overall, the findings support physics-guided,
video-based deep learning as a cost-effective and operationally viable approach for long-term coastal wave monitoring, and demonstrate a transferable strategy for physically-constrained spatiotemporal regression from
video under data-scarce conditions.
Read the full abstract ▾
All authors Abubakar Hamisu Kamagata, Dharm Singh Jat, Attlee Munyaradzi Gamundani, Abhishek Srivastava, Paramasivam Saravanakumar
Machine Learning
Quantizing Time-Series Models As Dynamical Systems: Trajectory-Based Quantization Sensitivity Score
Mariya Pavlova, Harrison Bo Hua Zhu, Lidia Vitanova et al. (+2 more)
We introduce the Trajectory-based Quantization Sensitivity Score (TQS), a metric that reframes post-training quantization (PTQ) through the lens of dynamical-systems stability. By modeling the network's rollout as a discrete-time dynamical system, TQS characterizes how quantization-induced errors propagate and amplify over the rollout horizon. Unlike conventional PTQ methods, where sensitivity analysis is often coupled to the quantization procedure, TQS enables a priori sensitivity estimation decoupled from quantizer selection and bit-width assignment. This separation allows for quantization budget planning even for black-box or compiled networks with fused operators. Building on this, we present TQS-PTQ, a flexible mixed-precision framework that requires no calibration data or costly second-order approximations. Our experiments show that a dynamical-systems perspective provides a robust, high-performing pathway for low-precision deployment in resource-constrained settings.
Read the full abstract ▾
All authors Mariya Pavlova, Harrison Bo Hua Zhu, Lidia Vitanova, Elizaveta Semenova, Yingzhen Li
Machine Learning · Cross-listed from stat.ML
Simultaneous Latent Budget Trees for Stratified Classification
Cristian Buoncompagni, Stefano Pellegrino, Giulia Vannucci et al. (+2 more)
In the era of Explainable Artificial Intelligence, there is a renewed focus on single trees for their ease of interpretation. This paper introduces Simultaneous Latent Budget Trees, a probabilistic machine learning framework for classification trees in the presence of a stratification factor such as a temporal, spatial, or demographic variable, acting as a control variable or potential confounder. Standard tree growth procedures are not designed to optimize a conditional split rule. A model-based split rule is proposed in which child nodes are interpreted as latent components of a simultaneous mixture model, such as the Simultaneous Latent Budget Model and its constrained versions, fitted to the parent node. Mixing parameters drive the observations, differently for each group, to the child nodes whereas latent budgets parameters update the response classes profile of each level of the control variable. Parameters are estimated by least squares considering a neural network perspective of the model. An informative tree structure can be interactively visualized with interpretation aids on the node and the paths, including visual
pruning and decision tree selection procedure. Suitable measures are proposed to handle an unbalanced response class distribution. The proposed methodology is applied to investigate gender-related differences in disease progression of Amyotrophic Lateral Sclerosis. The SLBT library with the various tree-based
algorithms is available in the linked GitHub repository.
Read the full abstract ▾
All authors Cristian Buoncompagni, Stefano Pellegrino, Giulia Vannucci, Raffaele Dubbioso, Roberta Siciliano
Machine Learning
Clipping Makes Distributed and Federated Asynchronous SGD Robust to Stragglers
Samuel Erickson and Mikael Johansson
In modern machine learning, parallelization of training is an important strategy for increasing scale. Asynchronous
stochastic gradient descent (ASGD), which maximizes the utilization of available hardware by avoiding waiting for slow workers. However, with constant step sizes, the convergence of ASGD is nonetheless affected negatively by slow workers due to large delays in updates. At the same time, it has been empirically observed in asynchronous training of deep learning models that gradient clipping "stabilizes" training. In this work, we provide a theoretical justification for this behavior, as we show that clipping removes the dependence of the maximum delay in the oracle complexity. We employ a sub-Weibull model of gradient noise which generalizes sub-Gaussian and sub-exponential distributions to more heavy-tailed distributions, motivated by empirical observations in deep learning. We show convergence in expectation, and the first time in asynchronous optimization, convergence with high probability.
Read the full abstract ▾
Machine Learning
Once-for-All: Scalable Simultaneous Forecasting via Equilibrium State Estimation
Beinan Xu, Andy Song, Jiti Gao et al. (+1 more)
We introduce
Equilibrium State Estimation (ESE), a novel paradigm for simultaneous prediction, where multiple interacting systems require separate yet coordinated forecasts. Such scenarios often arise in real-world settings such as economics and healthcare modeling. Unlike existing approaches that predict one system at a time, ESE forecasts all systems in a single pass. It first estimates the
equilibrium state across systems, then generates holistic forecasts based on the difference between the current state and the estimated
equilibrium. Extensive experiments on synthetic and real-world
datasets, including currency exchange and COVID-19 spread modeling, demonstrate that ESE is at least as accurate as state-of-the-art (SOTA) methods while being significantly faster. In addition, ESE integrates seamlessly with conventional predictors, combining their accuracy with its exceptional efficiency and delivering a 10-70x speedup. With linear-time complexity, ESE scales far better than SOTA methods as the number of systems increases. Moreover, it remains accurate under diverse perturbations, establishing ESE as a fast, generalizable, robust, and scalable multi-prediction method.
Read the full abstract ▾
All authors Beinan Xu, Andy Song, Jiti Gao, Feng Liu
Machine Learning · Cross-listed from stat.ML
ProtoX-AD: Self-Explainable Time Series Anomaly Detection and Characterization
Aitor Sánchez-Ferrera, Elisabeth Wetzer, Kristoffer Wickstrøm et al. (+2 more)
Recent advances in time series anomaly detection (TSAD) have highlighted the effectiveness of self-supervised classification-based approaches. These methods apply transformations to normal training samples, training a classifier to recognize transformation-specific patterns that help identify anomalies through increased classification errors. Despite their strong performance, a significant challenge is their lack of explainability, as they provide limited insight into the characteristics of flagged anomalies. To address this limitation, we propose ProtoX-AD, a prototype-based self-explainable framework for self-supervised TSAD. ProtoX-AD learns transformation-aware latent representations alongside interpretable prototypes, enabling both accurate anomaly detection and the identification of distinct anomalous profiles through prototype-based explanations. Additionally, it allows for systematic analysis of how transformation design impacts detection performance and explainability. Experimental results on synthetic and real-world
datasets demonstrate that ProtoX-AD achieves detection performance comparable to its black-box counterparts while offering more consistent and semantically meaningful explanations than existing explainable baselines. Our code is publicly available at https://github.com/Aitorzan3/ProtoX-AD.
Read the full abstract ▾
All authors Aitor Sánchez-Ferrera, Elisabeth Wetzer, Kristoffer Wickstrøm, Michael Kampffmeyer, Robert Jenssen