Machine Learning
$f$-Divergence Regularized RLHF: Two Tales of Sampling and Unified Analyses
Di Wu, Chengshuai Shi, Jing Yang et al. (+1 more)
Reinforcement Learning from Human Feedback (RLHF) has become a cornerstone technique for post-training large
language models. While most existing approaches rely on the reverse KL-regularization, recent empirical studies have begun exploring alternative divergences (e.g., forward KL, chi-squared) as regularizers in RLHF. However, a unified theoretical understanding of general $f$-divergence regularization remains under-explored. To fill this gap, this work develops a comprehensive theoretical framework for online RLHF with a general $f$-divergence regularized objective. Rather than treating each possible divergence function individually, we adopt a holistic perspective across the entire function class and propose two
algorithms based on distinct sampling principles. The first extends the classical optimism principle with a carefully designed exploration bonus, while the second introduces a new method that exploits the sensitivity of the optimal policy to reward perturbations under $f$-divergence regularization. Theoretical analysis shows that $O(\log T)$ regret and $O(1/T)$ sub-optimality gap are achievable, establishing provable efficiency of both
algorithms and, to the best of our knowledge, the first performance bounds for online RLHF under general $f$-divergence regularization.
Read the full abstract ▾
All authors Di Wu, Chengshuai Shi, Jing Yang, Cong Shen
Machine Learning · Cross-listed from stat.ML
A Differentiable Bayesian Relaxation for Latent Partial-Order Inference
Dongqing Li, Geoff K. Nicholls, Shiyi Sun et al. (+1 more)
Many ranking and
agent trace
datasets are recorded as linear orders even though their latent structure is only partially ordered. This is especially common in
agent and workflow traces, where observed order may reflect arbitrary linearization rather than true prerequisites. We introduce a differentiable relaxation for latent partial-order inference from such traces. Starting from a hard frontier-constrained model of noisy linear extensions, we replace discontinuous product-order precedence and binary frontier feasibility with smooth surrogates, yielding a continuous posterior that preserves closure-level partial-order semantics and supports gradient-based MCMC and variational inference. We prove soft transitivity, sharp-limit frontier recovery, and convergence to the hard likelihood. Experiments on synthetic data, records of social dominance relations, and cloud-
agent traces show close posterior fidelity to hard MCMC on small instances and improved runtime–accuracy trade-offs on larger problems.
Read the full abstract ▾
All authors Dongqing Li, Geoff K. Nicholls, Shiyi Sun, You Luo
Machine Learning · Cross-listed from stat.ML
Locally Near Optimal Piecewise Linear Regression in High Dimensions via Difference of Max-Affine Functions
Haitham Kanj and Kiryung Lee
This paper presents a parametric solution to piecewise linear regression through the Adaptive Block Gradient Descent (ABGD)
algorithm. The heart of the method is the parametrization of piecewise linear functions as the difference of max-affine (DoMA) functions. A non-asymptotic local convergence analysis for ABGD is provided under sub-Gaussian
covariate and noise distributions. To initialize ABGD, we adapt a prior
algorithm originally developed for the simpler setting of max-affine functions. When suitably initialized, ABGD converges linearly to an $\epsilon$-accurate estimate given $\tilde{\mathcal{O}}(d\max(\sigma_z/\epsilon,1)^2)$ observations where $\sigma_z^2$ denotes the noise variance. This implies exact recovery given $\tilde{\mathcal{O}}(d)$ samples in the noiseless case. Also, such a rate is shown to be minimax optimal up to logarithmic factors. Synthetic numerical results corroborate the theoretical guarantees for ABGD. We also observe competitive performance compared to the state-of-the-art methods on real-world
datasets.
Read the full abstract ▾
Machine Learning
Kurtosis-Guided Denoising Score Matching for Tabular Anomaly Detection
Victor Livernoche, Jie Zan and Reihaneh Rabbany
Denoising score matching (DSM) provides a way to learn data distributions by training a neural network to recover the score function, defined as the gradient of the log density, from noise-corrupted samples. Once trained, the score magnitude at a test point reflects how consistent that point is with the learned distribution, making it a natural anomaly signal. The key practical challenge is selecting the perturbation scale: too little noise yields unstable score estimates in sparse regions, while too much erases local structure and weakens anomaly sensitivity. This is compounded by the difficulty of hyperparameter tuning when anomalies are unknown and no validation set is available. We introduce kurtosis-based noise scaling (K-DSM), a per-feature scheme that sets noise levels from the shape of each marginal distribution, improving coverage of low-density regions and precision in high-density regions without extra model complexity. Contrary to prior claims that multi-scale or noise-conditioned training is necessary, we find that a carefully trained single-scale model is already a strong anomaly detector. On standard tabular anomaly detection
benchmarks, K-DSM achieves state-of-the-art performance in the semi-supervised setting. When combined with a lightweight EMA-teacher filtering rule that removes low-density training points before each gradient step, it also achieves strong performance in the fully unsupervised (contaminated) setting, suggesting that simple, data-adaptive noise scaling enables robust anomaly detection while reducing reliance on hyperparameter tuning.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.AI
Multi-Objective Constraint Inference using Inverse reinforcement learning
Syed Ihtesham Hussain Shah, Floris den Hengst, Aneta Lisowska et al. (+1 more)
Constraint inference is widely considered essential to align reinforcement learning
agents with safety boundaries and operational guidelines by observing expert demonstrations. However, existing approaches typically assume homogeneous demonstrations (i.e., generated by a single expert or multiple experts with identical objectives). They also have limited ability to capture individual preferences and often suffer from computational inefficiencies. In this paper, we introduce Multi-Objective Constraint Inference (MOCI), a novel framework designed to jointly extract shared constraints and individual preferences from heterogeneous expert trajectories, where multiple experts pursue different objectives. MOCI effectively models and learns from diverse, and potentially conflicting, behaviors. Empirical evaluations demonstrate that MOCI significantly outperforms existing baselines, achieving improved predictive performance, and maintaining competitive computational efficiency on a standard grid-world
benchmark. These results establish MOCI as an accurate, flexible, and computationally practical approach for real-world constraint inference and preference learning tasks.
Read the full abstract ▾
All authors Syed Ihtesham Hussain Shah, Floris den Hengst, Aneta Lisowska, Annette ten Teije
Machine Learning
Rollback-Free Stable Brick Structures Generation
Chenhui Xu, Ziyue Bai, Fuxun Yu et al. (+2 more)
While autoregressive models have advanced 3D generation, creating physically stable brick structures remains a challenge due to the strict requirements of
gravity and interconnectivity. Existing approaches rely on external physical simulators during inference to perform rejection sampling and brick-by-brick rollbacks, which severely bottlenecks efficiency. To address this, we propose a reinforcement learning paradigm that shifts physical validity enforcement from test-time correction to training-time policy optimization. By utilizing assembly-level rewards, the model optimizes for collision avoidance, global connectivity, structural interlocking, and shape conformity. This paradigm allows the model to internalize physical priors, enabling the first rollback-free generation of stable brick structures. Experimental results demonstrate that our approach achieves state-of-the-art generation quality while accelerating inference speed by orders of magnitude. Our code and
dataset are available at https://github.com/miniHuiHui/STABLE. Our models are available at https://huggingface.co/miniHui/STABLE.
Read the full abstract ▾
All authors Chenhui Xu, Ziyue Bai, Fuxun Yu, Heng Huang, Jinjun Xiong
Machine Learning
Adaptive Memory Decay for Log-Linear Attention
Yaxita Amin, Helen Zichen Li, Mengfan Zhang et al. (+1 more)
Sequence models face a fundamental tradeoff between
memory capacity and computational efficiency.
Transformers achieve expressive context modeling at quadratic cost, while linear
attention and state-space models run in linear time by compressing context into a fixed-size hidden state, inherently limiting recall. Log-linear
attention navigates this tradeoff by organizing
memory across a Fenwick tree hierarchy, growing its hidden state logarithmically with sequence length at log-linear compute cost. However, its
memory decay parameter {\lambda} is fixed and independent of the input, assigning uniform weights across all hierarchy levels regardless of the content, which introduces unnecessary
rigidity. We propose learning {\lambda} directly from the input via a lightweight two-layer MLP, producing per-
token, per-level decay that adapts to content rather than position. A softplus activation lets each Fenwick tree level scale independently, avoiding the inter-level competition that softmax introduces. This modification preserves log-linear complexity exactly and adds negligible parameter overhead. We evaluate on associative recall, selective copying, and
language modeling, finding that input-dependent decay consistently outperforms the baseline, with the largest gains in long-range
memory settings where baseline {\lambda} degrades or collapses entirely.
Read the full abstract ▾
All authors Yaxita Amin, Helen Zichen Li, Mengfan Zhang, Samet Ayhan
Machine Learning
ProtoSSL: Self-Supervised Pretraining and Downstream Transfer for Projection-Based Prototype Models
Steven Song, Sahil Sethi, Brett Beaulieu-Jones et al. (+1 more)
In domains where both predictive performance and interpretability are essential, deep neural networks achieve strong results but provide limited insight into how their predictions are made. Projection-based prototype networks address this limitation by grounding predictions in similarity to representative training examples, enabling case-based explanations and global prototype inspection. However, existing approaches rely on label supervision, tying prototypes to a specific task and requiring large labeled
datasets. We introduce ProtoSSL, a framework for pretraining a foundational latent prototype bank on unlabeled data and transferring it to downstream tasks to create interpretable, projection-based prototype models. Our key idea is to separate motif discovery from label
alignment. ProtoSSL first learns a transferrable prototype bank using a self-supervised objective applied directly to prototype activations, and then aligns these prototypes to downstream tasks through a novel efficient assignment procedure. Across six electrocardiography (ECG)
datasets, ProtoSSL improves label efficiency, outperforming supervised prototype baselines in low-data regimes with as few as 256 labeled examples; with fine-tuning, ProtoSSL outperforms supervised prototype baselines at full
dataset scale. In a human evaluation study, ProtoSSL produces prototypes and prototype-based explanations that are judged more favorably than those learned with direct label supervision. We further show that the framework extends to audio classification. Thus, ProtoSSL enables both learning foundational prototypes from unlabeled data before the downstream label space is known, and subsequent assignment to new tasks to create interpretable, projection-grounded prototypes.
Read the full abstract ▾
All authors Steven Song, Sahil Sethi, Brett Beaulieu-Jones, Robert L. Grossman
Machine Learning
Constrained Triple-Head Price Optimization (C3PO) Network for Discrete-Choice Models
Shivaram Subramanian, Zhengliang Xue, Markus Ettl et al. (+2 more)
We propose a Constrained Triple-Head Price Optimization (C3PO) network for real-time bi-level decision making in discrete-choice environments. In these settings, a seller selects product or service offerings to achieve business objectives, while heterogeneous users make personalized acceptance or rejection decisions based on their preferences, ultimately determining seller outcomes. Existing approaches that fine-tune pre-trained tabular foundation models on synthetic data are limited by their imitation-learning paradigm and inability to enforce common pricing rules, including cross-product and global constraints. C3PO addresses these limitations through a novel
transformer-based architecture that jointly integrates price imitation learning, multi-task revenue prediction, and in-context elasticity learning to generate robust pricing recommendations across domains without retraining. A lightweight differentiable constraint layer enables generated prices to satisfy business constraints while optimizing the revenue objective. We demonstrate strong out-of-distribution performance on simulated, synthetic, and real-world
datasets. Across simulated
benchmarks where the calibrated MNL model is misspecified relative to the ground-truth choice model, C3PO improves expected revenue by 1.4 to 7.9 percentage points over a calibrated MNL baseline. The constraint layer reduces average absolute constraint violations by more than 50%. We further deploy the model in real-world applications, including healthcare tender pricing and airline ancillary pricing, where C3PO improves directional pricing effectiveness, measured by price-increase and price-decrease recall, by 18–34 percentage points depending on the baselines considered, including calibrated MNL, classical optimization, and off-the-shelf tabular foundation-models.
Read the full abstract ▾
All authors Shivaram Subramanian, Zhengliang Xue, Markus Ettl, Yingdong Lu, Jayant Kalagnanam
Machine Learning · Cross-listed from cs.CL
MultiSoc-4D: A Benchmark for Diagnosing Instruction-Induced Label Collapse in Closed-Set LLM Annotation of Bengali Social Media
Souvik Pramanik, S.M. Riaz Rahman Antu, Shak Mohammad Abyad et al. (+2 more)
Annotation automation via Large
Language Models (LLMs) is the core approach for scaling NLP
datasets; however, LLM behavior with respect to closed-set instructions in low-resource
languages has not been well studied. We present MultiSoc-4D, a Bengali social media
dataset benchmark, which contains 58K+ social media comments from six sources annotated along four dimensions: category, sentiment, hate
speech, and sarcasm. By employing a structured pipeline where ChatGPT, Gemini, Claude, and Grok individually annotate separate partitions, while sharing a common validation set of 20%, we diagnose LLM behavior systematically. We discover a prevalent phenomenon called "instruction-induced label collapse", wherein LLMs show a systematic preference towards fallback labels (Other, Neutral, No), leading to high agreement rates but under-detection of minority categories. For example, we find that LLMs failed to detect 79% and 75% of instances with hateful and sarcastic content compared to a human-calibrated reference. Furthermore, we prove that it represents a "label agreement illusion", statistically validated via almost null Fleiss' Kappa ($\kappa \approx -0.001$) on sarcasm detection. Across 40+ LLMs, we
benchmark this annotation bias propagation within the training pipeline, regardless of architectural differences. We release MultiSoc-4D as a diagnostic
benchmark for annotation biases in Bengali NLP.
Read the full abstract ▾
All authors Souvik Pramanik, S.M. Riaz Rahman Antu, Shak Mohammad Abyad, Md. Ibrahim Khalil, Md. Shahriar Hussain
Machine Learning
Bias and Uncertainty in LLM-as-a-Judge Estimation
James Fiedler
LLM-as-a-Judge evaluation has become a standard tool for assessing base model performance. However, characterizing performance via the naive
estimator, i.e., raw judge outputs, is systematically biased. Recent work has proposed
estimators to correct this bias, but their reliability depends critically on judge quality and, for model comparisons, on calibration stability. Sharing calibration across compared models is practically attractive but can introduce severe bias, including cases where the comparison estimate points in the wrong direction with high apparent confidence. We study these failure modes through analytical results, simulations over judge quality ($J$) and cross-model calibration instability ($\Delta J$), and a real-data MMLU-Pro case study with sign reversal. We propose $J$ and $\Delta J$ as diagnostics for when corrected estimates, especially shared-calibration comparisons, are likely unreliable, and provide reporting guidance for LaaJ evaluation.
Read the full abstract ▾
Machine Learning
A Nonlinear Singular Value Theory for Neural Networks
Brian Charles Brown, Mauricio Munoz, Robert Bridges et al. (+2 more)
Recently Brown et al. [2025] established a singular value decomposition (SVD) for maps (especially nonlinear) satisfying certain norm conditions. We prove that most modern neural architectures admit this nonlinear SVD (NLSVD) representation—with no change in input–output behavior—and enumerate the classes covered. In this factorization the network is a left-invertible nonlinear map followed by a final linear layer. Moreover, the left-invertible factor is norm-preserving, so distances in the
embedding (activations before the final linear layer) calibrate directly to distances in input space. We introduce a flexible architecture that yields an explicit decomposition at training time, a data-driven
algorithm for estimating the representation from trained models, and the mathematical foundations for nonlinear analogues of row and null spaces in neural networks. Empirical case studies illustrate uses of the theory for latent-space pullback (visualization and data generation), bias detection, and membership-inference robustness under training. Altogether, these foundations support new approaches to core problems in neural-network analysis.
Read the full abstract ▾
All authors Brian Charles Brown, Mauricio Munoz, Robert Bridges, David Grimsman, Sean Warnick
Machine Learning
A Reproducible Optimisation Protocol for Calibrating Prompt-Based Large Language Model Workflows in Evidence Synthesis
Teo Susnjak
This methods article presents a reproducible calibration workflow for
prompt-based large
language models (LLMs) in structured evidence-synthesis tasks. The method separates the rules that define the scientific task from the mutable
prompt harness that frames and applies them. It optimises that harness against labelled or reference examples and an explicit task metric, then preserves the calibrated workflow as an inspectable artefact with its specification, metric, settings, and evaluation traces. The example code instantiates the protocol with DSPy and GEPA tools, but the underlying logic can transfer to other
prompt-optimisation frameworks that support structured task definitions, metric-guided search, and artefact reuse. Title and abstract screening is the worked validation case because it provides labelled
benchmark data and clear evaluation metrics. The demonstrated workflow uses a smaller student LLM for performing the scientific task execution and a larger reflection LLM to steer the
prompt optimisation process during calibration. This work shows compilation, artefact round-tripping, and how optimisation budget affects a smaller student model.
Read the full abstract ▾
Machine Learning
Learned Lyapunov Shielding for Adaptive Control
Giansalvo Cirrincione and Adriano Fagiolini
We augment the Slotine–Li adaptive controller for Euler–Lagrange systems with three learned components: a structured-quadratic Lyapunov function \(V_\psi\) whose positive-definiteness follows from a Cholesky parameterization, a residual Soft Actor–Critic policy that adds bounded torque corrections to the analytic baseline, and a physics-informed neural network that estimates unmodeled dynamics. A closed-form safety filter, derived from the single affine constraint \(\dot V_\psi + \alpha V_\psi \le 0\), projects every policy output onto the safe set without requiring an online QP solver. We prove: global feasibility of the filter under a drift-decay condition on the control-degeneracy set; exponential stability under exact shielding, with a robust extension whose margin depends on the PINN approximation error; almost-sure convergence of the three-timescale policy–certificate–multiplier updates to a KKT point; and a PAC generalization bound for the certificate over compacts. On a 2-DOF manipulator with nonlinear friction and variable payload, the learned certificate accounts for most of the empirical gain: tracking error drops by 41% on nominal friction and 24% on aggressive friction at the centroid of the training distribution. A 7-DOF scalability study on a Franka Emika Panda confirms clean convergence of the full pipeline at industrial scale, identifies the conditions under which gains over exact model-based baselines should and should not be expected, and documents a warm-start pathology of the learned certificate that has practical implications for deployment.
Read the full abstract ▾
Machine Learning
MAGIQ: A Post-Quantum Multi-Agentic AI Governance System with Provable Security
Sepideh Avizheh, Tushin Mallick, Alina Oprea et al. (+2 more)
Our computing ecosystem is being transformed by two emerging paradigms: the increased deployment of agentic AI systems and advancements in
quantum computing. With respect to agentic AI systems, one of the most critical problems is creating secure governing architectures that ensure
agents follow their owners' communication and interaction policies and can be held accountable for the messages they exchange with other
agents. With respect to
quantum computing, existing systems must be retrofitted and new cryptographic mechanisms must be designed to ensure long-term security and
quantum resistance. In fact, NIST recommends that standard public-key cryptographic
algorithms, including RSA, Diffie-Hellman (DH), and
elliptic-curve constructions (ECC), be deprecated starting in 2030 and disallowed after 2035. In this paper, we present MAGIQ, a framework for policy definition and enforcement in multi-
agent AI systems using novel, highly efficient,
quantum-resistant cryptographic protocols with proven security guarantees. MAGIQ (i) allows users to define rich communication and access-control policy budgets for
agent-to-
agent sessions and tasks, including global budgets for one-to-many
agent sessions; (ii) enforces such policies using post-
quantum cryptographic primitives; (iii) supports session-based enforcement of policies for
agent-to-
agent and one-to-many
agent sessions; and (iv) provides accountability of
agents to their users through message attribution. We formally model and prove the correctness and security of the system using the Universal Composability (UC) framework. We evaluate the computation and communication overhead of our framework and compare it with the state-of-the-art agentic AI framework SAGA. MAGIQ is a first step toward post-
quantum-secure solutions for agentic AI systems.
Read the full abstract ▾
All authors Sepideh Avizheh, Tushin Mallick, Alina Oprea, Cristina Nita-Rotaru, Reihaneh Safavi-Naini
Machine Learning
Target-Aware Data Augmentation for SAT Prediction
Eshed Gal, Uri Ascher and Eldad Haber
Learning-based approaches to NP-hard problems have shown increasing promise, but their progress is fundamentally constrained by the high cost of generating labeled training data. In domains such as Boolean satisfiability (SAT), standard pipelines rely on solver-in-the-loop labeling, which scales poorly with problem size and limits the amount of usable supervision. This bottleneck hinders the broader goal of leveraging machine learning to capture structure in hard combinatorial problems. In this work, we propose a target-aware, solver-free data generation framework for SAT that produces correctly labeled SAT and UNSAT instances by construction, eliminating the need for expensive solver calls. Our method aligns generated instances with the structural properties of a target
benchmark, making synthetic data effective for downstream learning. We further develop a linear-programming-aware graph neural network (LPGNN) architecture that incorporates constraint-violation residuals into message passing, enabling the model to exploit underlying optimization structure. Together, these contributions support a data-centric paradigm for learning on NP-hard problems, where scalable, task-aligned data generation is as critical as model design. Our approach yields orders-of-magnitude speedups in data generation, demonstrating that
benchmark-aligned synthetic data can effectively augment solver-labeled
datasets for GNN-based SAT prediction.
Read the full abstract ▾
Machine Learning · Cross-listed from physics.optics
Physics-Based Flow Matching for Full-Field Prediction of Silicon Photonic Devices
Joseph Quaratiello and Anthony Rizzo
Designing photonic integrated
circuits requires accurate electromagnetic field simulations, which remain computationally expensive even for simple device geometries. We present PIC-Flow, a generative neural surrogate that predicts electromagnetic field distributions for photonic devices given their geometry and operating wavelength as an alternative to costly finite-difference time-domain (FDTD) simulations. Our approach combines three key ideas: (i) conditional flow matching as the generative framework, learning a velocity field that transports Gaussian noise to physically valid field solutions; (ii) a real-valued U-Net operating on split real and imaginary field channels; and (iii) physics-constrained training through a Helmholtz residual loss enforcing $\nabla^2 E_z + k_0^2 \varepsilon E_z = 0$. We introduce an interface-aware masking scheme for the Helmholtz residual that excludes dielectric boundary pixels where finite-difference stencil errors dominate, yielding a physically meaningful compliance metric. The data set consists of 22,500 ground-truth FDTD simulations split evenly between multimode interferometers, Y-branches, and directional couplers at $\lambda=1.55\,\mu$m in an 80/10/10 split between training, validation, and test sets. We evaluate ablations on the network against the held out test devices and also show that the model generalizes to held out device classes such as S-bends, tapers, and cascaded Y-branches. Rather than a drop-in replacement for FDTD, this work establishes a foundation that, with broader data coverage, more compute, and further training optimization, could scale toward broadband, device-agnostic field prediction with dramatically improved runtime for rapid design-space exploration of complex photonic devices and
circuits.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.GT
In-Context Credit Assignment via the Core
Keegan Harris, Siddharth Prasad and Asher Trockman
We propose incentive-aligned mechanisms for in-context credit assignment: the task of assigning credit for AI-generated content among creators whose intellectual property appears in the context window. Our approach is based on the least core solution concept from cooperative game theory, which distributes value in a way that is as stable as possible by ensuring that no subset of creators is significantly under-compensated relative to the value they could generate on their own. We develop
algorithms for approximating the least core, which leverage novel routines for constraint seeding and constraint separation. On a web
retrieval credit assignment task, we find that our approaches approximate the least core using an order of magnitude fewer LLM calls compared to alternative methods.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.MA
Generalising Travel Time Prediction To Varying Route Choices In Urban Networks
Łukasz Gorczyca, Kacper Drozd, Michał Bujak et al. (+1 more)
Previous methods that predict system-wide travel time, predominantly grounded in graph neural networks, remain limited to typical and recurring demand patterns. While they successfully predict future congestion following daily commute, they inherently approximate a single demand realisation and fail to capture varying route choices. In this work, we propose a Generalised Travel Time Predictor (GenTTP) that successfully differentiates route choices and offers accurate flow and travel time predictions. Our framework learns to uncover complex spatiotemporal traffic patterns and microscopic relationships between route choices and the resulting travel times. This addresses a critical gap: the lack of travel time prediction models that generalise across varying route assignments, where the same demand can produce substantially different network-wide outcomes depending on how travellers are distributed over available paths.
Read the full abstract ▾
All authors Łukasz Gorczyca, Kacper Drozd, Michał Bujak, Rafał Kucharski
Machine Learning
Tyche: One Step Flow for Efficient Probabilistic Weather Forecasting
Fan Xu, Yuan Gao, Kun Wang et al. (+4 more)
Probabilistic weather
forecasting requires not only accurate trajectories, but calibrated distributions over plausible atmospheric futures. Recent data-driven systems have achieved remarkable deterministic skill, and
diffusion-based ensemble forecasters have substantially improved sample realism and uncertainty quantification. However, their inference cost scales with forecast horizon, ensemble size, and the number of denoising steps required for each transition, making large operational ensembles expensive. To address this, we present Tyche, a one-step conditional flow model for efficient probabilistic weather
forecasting. Tyche models the conditional forecast distribution with a destination-aware average-velocity flow that maps Gaussian noise directly to future weather states in a single function evaluation (1-NFE). To make this one-step transport learnable in high-dimensional geophysical fields, we derive a JVP-regularized rectification objective that enforces temporal self-consistency across source and destination flow timesteps without explicitly forming Jacobians. The transport field is parameterized by an isotropic Swin-style
transformer that preserves fine-scale spatial structure while remaining scalable on global grids. To improve ensemble reliability under autoregressive
forecasting, we further introduce a rollout-based finetuning stage with curriculum CRPS calibration supervision. Experiments on ERA5 at 1.5$^\circ$ and 6-hour resolution show that our Tyche, using merely a single NFE, matches or exceeds the forecast skill and calibration of state-of-the-art multi-step generative baselines and the operational ECMWF IFS ensemble.
Read the full abstract ▾
All authors Fan Xu, Yuan Gao, Kun Wang, Rui Su, Fenghua Ling, Hao Wu, Wanli Ouyang
Machine Learning
LLMs are not (consistently) Bayesian: Quantifying internal (in)consistencies of LLMs' probabilistic beliefs
Chacha Chen, Matthew Jörke, Adam Goliński et al. (+4 more)
Modern AI systems are being deployed in complex domains such as medicine, science, and law, where it is important that they not only produce correct answers, but also represent and update uncertain beliefs about the world as new evidence arrives. We introduce the novel technique of studying LLMs as information processing rules and utilize the information processing gap to study the internal (in)consistencies of how LLMs update their probabilistic beliefs from evidence. Our extensive experiments evaluate multiple approaches in which LLMs can incorporate evidence into their beliefs. Some of these approaches produce (nearly)
Bayesian updates; others seem to use a learned heuristic. Surprisingly, the non-
Bayesian heuristic updates often outperform exact
Bayesian computation in terms of downstream task performance – indicating the LLMs' probabilistic models of the world are misspecified. Lastly, we show how our measure can provide diagnostics to identify issues with LLM-powered inferential systems.
Read the full abstract ▾
All authors Chacha Chen, Matthew Jörke, Adam Goliński, Masha Fedzechkina, Guillermo Sapiro, Sinead Williamson, Nicholas Foti
Machine Learning · Cross-listed from astro-ph.EP
You Only Stack Once (YOSO): A Motion-Filtered, Deep-Learning Framework for Detecting Faint Moving Sources
Nitya Pandey, César Fuentes, Pedro Bernardinelli et al. (+15 more)
We present You Only Stack Once (YOSO), an automated pipeline designed to detect faint, slow-moving
Solar System objects in wide-field astronomical surveys. The pipeline integrates a novel Gaussian Motion Filter (GMoF) that operates at the pixel level to enhance signal-to-noise for objects exhibiting a range of apparent rates of motion. Unlike conventional shift-and-stack methods, which rely on discrete velocity trials, GMoF amplifies trails while suppressing random noise and static background features. Applied to a subset of DEEP observations from the Dark Energy Camera, YOSO recovered 45 out of 73 previously detected objects, as well as 11 new TNOs. It also discovered 216 objects in the near
Solar System. Although alternative shift-and-stack methods are sensitive to objects about 0.88 magnitudes fainter, YOSO's false positive rate is extremely low, since it detects only sources that exhibit a trail and are consistent with a point source when shifted at the right rate. We show how this method can be deployed on large surveys like LSST, and adapted for other domains that require motion-based signal enhancement, including
exoplanet imaging through Angular Differential Imaging (ADI), and near-Earth object (NEO) detection for missions like NEO Surveyor. YOSO thus provides a versatile, scalable approach for extracting faint, motion-dependent signals in the era of data-intensive astronomy.
Read the full abstract ▾
All authors Nitya Pandey, César Fuentes, Pedro Bernardinelli, Valeria Frías, Colin Orion Chandler, David E. Trilling, Matthew J. Holman, Steven Stetzler, Dallin Spencer, Hsing Wen Lin, Luis E. Salazar Manzano, Darin Ragozzine, Ryder Strauss, Mario Jurić, Andrew J. Connolly, Hayden Smotherman, Scott S. Sheppard, Kevin Napier
Machine Learning
Dual-Scale Temporal Fusion Reveals Structured Predictability in Subseasonal-to-Seasonal Temperature Prediction
Elnaz Bashir, Jiali Wang and Lin Yan
Subseasonal-to-seasonal (S2S) temperature forecasts, spanning several weeks to a few months, are critically needed in agriculture practice, energy planning, and extreme-weather induced risk management, yet their reliability varies substantially across seasons and regions. Forecast skill is often attributed primarily to lead time, but this perspective does not fully explain the spatiotemporal patterns of predictability. Here we show that S2S predictability is organized across interacting temporal components, spatial heterogeneity, and large-scale pattern coherence, and that this structure can be explicitly characterized and exploited. We develop a dual-scale learning framework that separates calendar-aligned historical
climate context from lead-time matched recent weather
evolution, combining them through spatially adaptive fusion to enable stable temperature forecasts across the 30 to 90-day window. The learned fusion weights reveal that the balance between these two temporal scales shifts systematically with season and geography: during winter, interannual context dominates over high latitudes and complex terrain where forecast is the most difficult, while summer predictions reflect a more balanced temporal contribution across the domain. This spatially explicit reorganization of predictability, rather than simple lead-time decay, emerges as the primary determinant of forecast skill within the subseasonal window.
Topology-aware structural constraints further improve spatial coherence of predicted temperature fields, stabilizing large-scale pattern organization particularly over complex terrain. These results reframe S2S predictability as a structured, multi-scale phenomenon, providing a more interpretable foundation for improving forecast systems and informing their use in practice.
Read the full abstract ▾
Machine Learning
Same Signal, Opposite Meaning: Direction-Informed Adaptive Learning for LLM Agents
Ziming Li, Jiatan Huang, Xiaoguang Guo et al. (+2 more)
Adaptive test-time compute for LLM
agents aims to invoke extra computation only when it improves performance. Existing methods typically use confidence-, uncertainty-, or difficulty-based gates, assuming a fixed direction from the gating signal through compute need to the value of computation. This makes gating a utility-calibration problem: gating signals should align with whether extra computation improves the final outcome over the base policy. We show that this
alignment is unstable: the same signal predicts rollout benefit in one setting and rollout harm in another, with reversals across environments and backbones even when the task is fixed. Wrong-direction gates can therefore worsen performance by precisely selecting harmful states. This reversal reflects a deeper distinction between compute need and compute suitability: a high uncertainty signal may indicate decision-difficult states where rollouts help compare alternatives, or intervention-unsuitable states where the current context does not support useful rollout-based improvement. Under this two-source model, fixed-direction gates are unreliable across heterogeneous settings. To address this, we propose DIAL (Direction-Informed Adaptive Learning), a sparse gate trained from signal-agnostic counterfactual exploration to learn the utility direction of state features per (environment, backbone). Across six environments and three backbones, DIAL yields a stronger overall success-cost trade-off than fixed-direction baselines. Our code is open-sourced at https://github.com/zmli6/DIAL.
Read the full abstract ▾
All authors Ziming Li, Jiatan Huang, Xiaoguang Guo, Guiling Wang, Chuxu Zhang
Machine Learning
TraXion: Rethinking Pre-training Frameworks for Mobility and Beyond
Shang-Ling Hsu, Mark Tenzer, Cyrus Shahabi et al. (+1 more)
Human mobility differs from text and from generic time series in three structural ways: visits are tuple-valued events whose meaning depends on the joint distribution over location, time, and activity; users carry persistent signatures across trajectories; and visits are not independent across users, since co-location at shared places is a primary signal. Existing pre-training recipes for mobility import objectives from
language modeling, treating trajectories as sentences and visits as
tokens, an analogy that fails against each of the three properties above. These properties define a broader class, multi-entity spatiotemporal event streams (MESES), spanning enterprise authentication logs, electronic health records, and other event-stream domains where entities share infrastructure, schedules, or contexts. We make the properties precise as three axioms that any pre-training framework for MESES should satisfy, and introduce TraXion, whose objectives and architecture are jointly designed to meet them. A single TraXion checkpoint per
dataset beats task-specific baselines on every task across six public mobility
datasets covering anomaly detection, next-POI recommendation, next-visit prediction, and social-link prediction. The same recipe, applied unchanged to enterprise authentication logs and ICU mortality prediction, matches or exceeds prior work on both, showing that event streams from domains as different as mobility, security, and healthcare can be modeled under a single framework.
Read the full abstract ▾
All authors Shang-Ling Hsu, Mark Tenzer, Cyrus Shahabi, Khurram Shafique
Machine Learning
Conservative Flows: A New Paradigm of Generative Models
Eshed Gal, Md Shahriar Rahim Siddiqui, Moshe Eliasof et al. (+1 more)
Modern generative modeling is dominated by transport from a noise prior to data. We propose an alternative paradigm in which generation is performed by a discrete
stochastic dynamics that leaves the data distribution invariant, initialized from data-supported states rather than from noise. The framework can utilize any pretrained flow model. We develop two probability-preserving sampling mechanisms, a corrected Langevin dynamics with a Metropolis adjustment and a predictor-corrector flow, that operate directly on existing checkpoints. We validate the framework on a synthetic Swiss-roll target, ImageNet-256 and Oxford Flowers-102, where our samplers consistently improve over the original generation procedures.
Read the full abstract ▾
All authors Eshed Gal, Md Shahriar Rahim Siddiqui, Moshe Eliasof, Eldad Haber
Machine Learning
Streaming Adversarial Robustness in Fuzzy ARTMAP: Mechanism-Aligned Evaluation, Progressive Training, and Interpretable Diagnostics
Shane Cairns, Leonardo Enzo Brito da Silva, Sasha Petrenko et al. (+2 more)
Adversarial robustness has been studied extensively for offline deep networks, but less is known about strict single-pass streaming neural learners. This paper studies
adversarial robustness in Fuzzy ARTMAP, an Adaptive Resonance Theory architecture based on category competition, complement coding, match tracking, and replay-free prototype updates. We introduce WB-Softmax, a differentiable white-box attack surrogate aligned with ARTMAP's category-competition and map-field prediction mechanism, and formalize a streaming evaluation principle requiring robustness to be assessed on the final deployed model. Across four image
benchmarks, WB-Softmax achieves 89-100% attack success on vanilla Fuzzy ARTMAP models. We show that defense rankings can reverse across protocols: offline
adversarial training may appear strong under transfer attacks yet collapse under adaptive white-box evaluation, whereas progressive two-stage selective training provides the strongest overall replay-free robustness. We further show that ART's explicit category geometry enables interpretable diagnosis of separation collapse and match-score inversion. These results provide a mechanism-aligned, protocol-aware framework for
adversarial robustness in streaming prototype-based learners.
Read the full abstract ▾
All authors Shane Cairns, Leonardo Enzo Brito da Silva, Sasha Petrenko, Donald C. Wunsch II, Jian Liu
Machine Learning · Cross-listed from cs.DS
Accelerated Relax-and-Round for Concave Coverage Problems
Matthew Fahrbach, Mehraneh Liaee and Morteza Zadimoghaddam
We present an accelerated relax-and-round
algorithm for concave coverage problems, which generalize the classic maximum coverage problem. Building on the relax-and-round framework of Barman et al. [STACS 2021], we propose two significant improvements. First, we replace the linear programming (LP) relaxation step with a projected accelerated gradient method applied to a smooth surrogate objective to achieve a $\widetilde{O}(mn \varepsilon^{-1})$ running time. Second, we use a specialized rounding scheme for the hypersimplex that combines the Carathéodory decomposition
algorithm in Karalias et al. [NeurIPS 2025] with randomized swap rounding of Chekuri et al. [FOCS 2010]. We prove tight approximation ratios for new reward functions, including a $0.827$-approximation for the logarithmic reward $\varphi(x) = \log(1 + x)$. Finally, we conduct maximum multi-coverage experiments on synthetic and real-world graphs, demonstrating that our
algorithm outperforms approaches that use state-of-the-art LP solvers.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.CR
McNdroid: A Longitudinal Multimodal Benchmark for Robust Drift Detection in Android Malware
Md Mahmuduzzaman Kamol, Jesus Lopez, Saeefa Rubaiyet Nowmi et al. (+5 more)
Machine learning (ML) in real-world systems must contend with concept drift,
adversarial actors, and a spectrum of potential features with varying costs and benefits. Malware naturally exhibits all of these complexities, but for the same reason, it is challenging to curate and organize data to study these factors. We present McNdroid, to our knowledge the largest longitudinal
multimodal Android malware
benchmark for malware detection and drift analysis. McNdroid spans 2013–2025, excluding 2015, and represents each application with three aligned modalities–static features from manifests and smali code, dynamic behavioral features from sandbox execution, and graph-based features from function-call graphs. Using temporally separated splits, we evaluate standard ML and deep-learning detectors across increasing train–test time gaps. Results show clear temporal degradation, while
multimodal fusion outperforms the best single modality across long-term temporal gaps. Cross-modal agreement also declines over time, suggesting that drift affects both individual feature spaces and the consistency among modalities. We further analyze modality-specific drift, malware-family
evolution, and temporal changes in model explanations. We publicly release McNdroid,
benchmark splits, and code to support reproducible research on temporal generalization and robust
multimodal learning in security-critical, non-stationary settings.
Read the full abstract ▾
All authors Md Mahmuduzzaman Kamol, Jesus Lopez, Saeefa Rubaiyet Nowmi, Emilia Rivas, Md Ahsanul Haque, Edward Raff, Aritran Piplai, Mohammad Saidur Rahman
Machine Learning · Cross-listed from cs.CV
Towards Fairness under Label Bias in Image Segmentation: Impact, Measurement and Mitigation
Aditya Parikh, Stella Frank, Sneha Das et al. (+1 more)
Biases in annotation pipelines may introduce label bias: when annotation quality or style varies systematically across demographic subgroups, causing disparities in performance and auditability. Label bias in image
segmentation remains underexplored, as even detecting it typically requires clean, unbiased annotations, which are not readily available. We present a Confident Learning framework adapted to
segmentation for
auditing label bias directly in the training data without a clean, unbiased ground truth. By comparing the provided training labels to the model's confident predictions, we measure the prevalence and direction of suspected label errors; where standard overlap metrics like Dice fail. We further show that label bias influences subgroup separability in the encoder's feature space, an artifact we leverage for bias mitigation rather than suppressing it. We evaluate three
datasets spanning from synthetic to real-life bias and across experimental conditions, showing how our framework produces proxy audit signals without clean labels and mitigates disparities with a correctly identified cleaner reference group.
Read the full abstract ▾
All authors Aditya Parikh, Stella Frank, Sneha Das, Aasa Feragen