Machine Learning · Cross-listed from math.ST
Minimax Rates for Estimating Powered Sliced Wasserstein Functionals
Binh Thuan Tran
We study the two-sample estimation of the powered Sliced Wasserstein functional under projected $r$-th moment assumptions. Let $N=n\wedge m$, where $n$ and $m$ are two sample sizes. We establish the minimax rates in the noncritical regimes. When $p<r<2p$, the minimax risk is of order $N^{-(r-p)/r}$, while for $r>2p$ it is of order $N^{-1/2}$. In both cases, the natural plug-in
estimator is minimax rate-optimal. At the endpoint $r=p$, the minimax risk is bounded away from zero, so uniformly consistent estimation is impossible. At the critical order $r=2p$, we obtain the exact worst-case rate of the plug-in
estimator and a lower bound for the minimax risk, leaving a logarithmic gap between the lower and upper bounds. The exact minimax rate in this critical case remains open.
Read the full abstract ▾
Machine Learning
KITE: A Knowledge-Injected Temporal Encoder for Time-Series Event Forecasting
Jonas Petersen, Pratik Jawahar, Riccardo Maggioni et al. (+6 more)
Forecasting rare, high-cost events in multivariate time-series systems is hard because their precursors are seldom observed, so a purely data-driven model has little to learn from. The engineers who run these systems, however, hold knowledge that precedes such events, information absent from the scarce labels. We call this a semantic prior and inject it into a self-supervised event forecaster through two switchable mechanisms, a
covariate mechanism and an
attention-bias mechanism, each the identity at its null, so one architecture serves every prior type with no per-
dataset architecture search. A prior helps when it supplies information the observed window does not already contain: in a short context an informative prior beats no prior in-domain (pooled h-AUROC over the no-prior baseline: a periodicity clock +14%, p<0.001; a conservation residual +47% at a 0.25 label fraction), and a working prior transfers out-of-domain (+53%), substituting for feature transfer, while priors the window already recovers stay inert and the
attention-bias mechanism shows no measurable gain. KITE is a switchable, attributable route to contextual conditioning, and a substrate for scaling toward cross-domain, pretrained time-series foundation world models that carry their governing structure explicitly.
Read the full abstract ▾
All authors Jonas Petersen, Pratik Jawahar, Riccardo Maggioni, Gian-Alessandro Lombardi, Matteo Cozzi, Marek Gajewski, Federico Martelli, Camilla Mazzoleni, Philipp Christian Petersen
Machine Learning
Kernelized Parameter Sensitivity Atlases for Amortized Conditional Interpretability
Davide Wiest, Ahanaf Hasan Ariq and Abdul Monaf Chowdhury
Gradient-based attribution provides input-specific information about model parameters, but computing it via backpropagation for many samples is expensive, while static importance scores discard input dependence. We derive KPSA (Kernelized Parameter Sensitivity Atlas) from a block decomposition of the empirical neural tangent kernel. It measures normalized parameter-group sensitivity, embeds those sources in an explicit query space, and uses a lightweight kernel to estimate sensitivities for unseen inputs. We derive bounds that separate finite-source from irreducible representation error and give margin-based top-$k$ recovery. This paper studies two interpretability applications. Firstly, KPSA identifies parameter groups with high susceptibility to perturbations across
vision, forecasting, and
protein-modeling setups. Across a fivefold range of parameter budgets ($0.02$-$0.1\%$), its selected groups attain $39$-$85\%$ of the perturbation susceptibility of a first-order backpropagation oracle. In
vision and forecasting, these parameter groups form sparse sensitivity
circuits that extend across depth and vary systematically with the input. Secondly, we use KPSA on an activation-attribution problem for MLP features in
transformers. It retains $81\%$ of the gap between a backpropagation oracle and a constant-sensitivity baseline on
vision while increasing batched query-time throughput from 551 to 2,041 images/s and reducing peak GPU
memory from 4.55 to 0.44GB. On the
protein-modeling task, it recovers $68\%$ of this gap. An ablation of KPSA's kernel aggregation shows that nearest-neighbor
retrieval in KPSA space can remain competitive. The empirics show that compact kernel atlases can store useful input-dependent parameter sensitivity while amortizing repeated gradient attribution, a step toward scalable conditional interpretability. Code can be found at https://github.com/Axym-Labs/kpsa .
Read the full abstract ▾
Machine Learning · Cross-listed from cs.RO
StereoEngine: Scaling Stereo Bimanual Robot Data without Stereo Cameras
Jason Chen, I-Chun Arthur Liu, Gaurav Sukhatme et al. (+1 more)
Stereo
vision is increasingly used for robotic manipulation, with a growing body of work incorporating it into
Vision-
Language-Action (VLA) models. However, the scarcity of large-scale, real-world stereo
datasets remains a fundamental bottleneck for scaling such policies. Recent generative monocular-to-stereo methods target settings such as VR content and autonomous driving. No prior work produces realistic synthetic stereo data for robotic manipulation, where stereo supervision has come predominantly from simulation. We propose StereoEngine, which introduces two complementary methods to synthesize stereo data for robotic manipulation. In the first, we warp a monocular (left)
video into the right view using estimated depth and inpaint the disoccluded regions with a
video diffusion model, lifting monocular demonstrations into stereo pairs without training on real stereo. In the second, we render a stereo pair in simulation and jointly generate both photorealistic views, producing consistent left-right data without any real
video as input. StereoEngine outperforms existing baselines in generated stereo quality, and using its synthetic data for policy mid-training or task-specific fine-tuning substantially improves downstream bimanual manipulation. Project website: https://stereoengine.github.io
Read the full abstract ▾
All authors Jason Chen, I-Chun Arthur Liu, Gaurav Sukhatme, Daniel Seita
Machine Learning
A Categorical Atlas of Parameter-Efficient Fine-Tuning: Cones, Orbits, and Gauges
Xiaoyu Li, Zhizhou Sha, Chiwun Yang et al. (+1 more)
Parameter-efficient fine-tuning has hundreds of methods, usually compared by parameter count and
benchmark score. We compare them as maps. A pretrained checkpoint is a base point in weight space, and a weight-space method is a smooth map from a small parameter space that starts at that point. These maps form a slice category in which the frozen model is initial and full fine-tuning terminal. Three invariants of the map do most of the work. Its image near the base point governs expressivity, through the first-order image, the dimension, a min-cut bound on rank and whether that point is smooth or an apex. Its fibres, with the optimizer's metric, govern training dynamics. Base change moves the base point and covers splitting initialisations, quantisation, restarts and merging. We prove, for example, that zero-initialised LoRA, and Householder reflection adaptation at its default start under stated rank and parity conditions, begin at the apex of a cone; that no exact initialisation lets LoRA reach an update of rank above twice its own; that exactly orthogonal methods never change a weight's singular values in exact arithmetic, however often they are merged; that under Adam with no epsilon, weight decay or clipping and one shared schedule, LoRA+ from the standard zero initialisation follows exactly the trajectory of plain LoRA with its scale multiplied by the learning-rate ratio; that Adam with shared hyperparameters respects only the signed permutations inside LoRA's continuous
symmetry group of full-rank factors; and that the activation function decides when a scaling adapter folds into preceding weights. We classify 382 methods from 138 papers by seven coordinates read off their formulas, with 403 simulation arrows and 485 obstructions. Every numbered result is proved in full, and results due to others are credited where we re-derive them.
Read the full abstract ▾
All authors Xiaoyu Li, Zhizhou Sha, Chiwun Yang, Dai Shi
Machine Learning · Cross-listed from cs.CV
Zebra3D: Efficient Hybrid Foundation Models For Scalable 3D Reconstruction
Utkarsh Saxena, Ruijing Yang, Mehdi Rezagholizadeh et al. (+3 more)
Feed-forward 3D foundation models reconstruct scenes from unposed images, but the quadratic cost of global
attention limits their scalability to large view sets. We present Zebra3D, a layerwise sparse-linear hybrid
attention framework that improves the efficiency of pretrained 3D foundation models without training from scratch. Across VGGT, HunyuanWorld-Mirror, and $\pi^3$, we observe a broadly consistent depth-wise pattern: early stages are relatively tolerant to linear replacement, while sensitive middle-to-late stages tend to exhibit more concentrated
attention. Zebra3D exploits this structure by assigning linear-centered
attention to tolerant stages and tile-sparse
attention to sensitive stages, using landmark summaries to preserve unselected context. Closed-form affine fitting enables training-free conversion, while optional post-conversion training combines task supervision with output and relational feature
distillation. Across all three backbones, Zebra3D achieves strong reconstruction and camera-pose accuracy at high
attention sparsity, with training-free variants remaining close to their dense counterparts. End-to-end speedups increase with input view count, reaching up to $7.1\times$ at 1,024 views. After post-conversion training, Zebra3D-VGGT reaches 80.5% RealEstate10K AUC@30 at 94% mean
attention sparsity, within 1.1 percentage points of dense VGGT fine-tuned on the same data and schedule.
Read the full abstract ▾
All authors Utkarsh Saxena, Ruijing Yang, Mehdi Rezagholizadeh, Akash Haridas, Vikram Appia, Emad Barsoum
Machine Learning
Spatial Context or Memory? Sizing the Inputs of Neural Surrogates for Partially Observed Fields
Ruige Kong
Neural surrogates that forecast a physical field from sparse, noisy sensors read a window of nearby sensors and a history of past snapshots. Practitioners choose both by comparing fitted models with each other. Such comparisons cannot tell a model's shortfall from missing information. We measure the trade-off between window and history against the Bayes-optimal error of the same readings. An exact Gaussian analysis shows that noisy or sparse observation of a field with local dynamics makes the optimal forecast read distant sensors only through spatial correlation. On a forced linear field with a known optimum, trained models that read only the window come within 1% of it. We then train such models on viscous Burgers flow and the chaotic Kuramoto-Sivashinsky (KS) equation, with every deciding comparison fixed before any test evaluation. In every field except KS, eight snapshots remove a smaller fraction of the one-snapshot error as the lead time, the number of steps to the forecast target, grows. In KS, for windows up to one correlation length, they remove a larger fraction. This lead-time inversion persists across sensor densities, three architectures and a two-dimensional domain. It shrinks as damping lowers the Lyapunov exponent. Damping also removes the linear instability of KS. We therefore tie the inversion to instability and leave chaos and linear amplification unseparated. For surrogate design the results give two rules. Size the window in correlation lengths of the field. Split a fixed input budget between window and history for the lead time the model will serve, because the best split moves toward wider windows as the lead time grows. In Burgers flow the split chosen at lead time one ends with 13.5 times the best error at lead time eight.
Read the full abstract ▾
Machine Learning · Cross-listed from q-fin.RM
A Distributional Framework for Behavioral Characterization and Risk Management of Large Language Models
David García-Lorite and Raul Merino
Large
language models are
stochastic by nature. Repeated executions under the same experimental conditions may produce different responses. We propose a framework that can be applied across the model lifecycle, from task design to residual behavior and continuous monitoring. The method consists of building an empirical response distribution estimated through Monte Carlo simulation. Semantic interventions are introduced to study how these distributions change. We illustrate the framework with two different tasks, borrower classification and music album recommendation, and quantify the resulting distributional changes. The framework is linked to model risk management and governance by measuring robustness and control effectiveness, and characterizing residual behavior. Since it relies only on observed responses, it can also be applied to black-box models accessed through commercial APIs.
Read the full abstract ▾
Machine Learning
Byzantine-Resilient Federated Large Language Model via Hypergraph Message Passing
Kai Li, Hanlin Cai, Zihao Liu et al. (+5 more)
Federated Large
Language Models (FedLLMs) are promising to deliver
privacy-preserving, collaborative intelligence. The decentralized training process is vulnerable to Byzantine attacks that corrupt semantic consistency and factual resilience through malicious model updates. This paper presents a new resilience strategy that prevents semantically corrupted knowledge from propagating during
federated aggregation. A defense problem is formulated to jointly maximize global accuracy and suppress manipulated model updates, enabling trustworthy knowledge aggregation without accessing private local data. To strengthen the resilience of FedLLMs, we develop a novel Hypergraph Message Passing Graph Autoencoder (HMP-GAE) framework, where low-rank model updates are represented as nodes in a hypergraph and high-order semantic relationships among multiple
agents are exploited through iterative message passing. By leveraging historical checkpoints and cross-
agent relational
reasoning, HMP-GAE identifies and suppresses semantically inconsistent updates while preserving knowledge
alignment among
agents throughout
federated training. HMP-GAE is implemented using Qwen-2.5 and Llama-3.2 as pretrained FedLLM backbones and evaluated on AG News and Yahoo! Answers
datasets. Compared to existing defenses, HMP-GAE improves global accuracy by $1.21$%, reduces final-model classification semantic
entropy by $44.08$%, and lowers perplexity by $13.34$%. HMP-GAE outperforms the GAE-based defense by improving the accuracy $1.39$%, reducing the semantic
entropy by $54.5$%, and lowering perplexity by $35.5$%.
Read the full abstract ▾
All authors Kai Li, Hanlin Cai, Zihao Liu, Yichen Li, Jose Alcaraz Calero, Wei Ni, Falko Dressler, Özgür B. Akan
Machine Learning · Cross-listed from cs.CR
PVBRF-ID: Private, Verifiable and Byzantine-Robust Federated Intrusion Detection for Oilfield Enterprise Networks
Mustafa S. Aljumaily, Ali Ataeemh Allami, Mustafa N. Mnati et al. (+2 more)
Federated learning allows dispersed oilfield sites to train a shared intrusion detector without pooling network traffic, yet its aggregation step forces a choice between
privacy and robustness. Byzantine-robust rules must read each update in the clear, whereas secure aggregation hides updates from the checks that detect poisoning. We present PVBRF-ID, a two-server protocol in which sites secret-share their updates and the servers jointly test each update's norm and its cosine similarity to a reference computed on a small clean root set, revealing one accept bit per site. Commitments, Merkle roots and a homomorphic audit make the inclusion of accepted updates publicly verifiable. On a 15-class Edge-IIoTset task with ten sites holding differently distributed data and ten random seeds, PVBRF-ID matched FedAvg on clean data (macro-F1 0.708 vs. 0.706) and withstood sign-flip attacks (0.696 vs. 0.091). Against an adaptive attacker controlling 30% of sites, PVBRF-ID with secure clipping reached 0.641, whereas FedAvg fell to 0.046; plaintext multi-Krum remained higher by 0.052. An update-inference attacker recovered each site's class mix from plaintext updates (Spearman correlation 0.81) but not from one server's view. Backdoors passed the filter, and noise-based mitigation gave only heuristic protection. The implementation uses Python 3.13, NumPy 2.3, 30 rounds and 10 seeds.
Read the full abstract ▾
All authors Mustafa S. Aljumaily, Ali Ataeemh Allami, Mustafa N. Mnati, Nawar S. Alseelawi, Shahab Abdulla
Machine Learning · Cross-listed from cs.CV
Bridging Human and Model Attention: Explainability Analysis of CNN, Mamba, and ViT Architectures with Gaze-Based Validation
Marco Stefani, Edoardo Parpaiola, Matteo Bino et al. (+5 more)
High-risk applications of deep learning require precise characterization of model decision-making. We conduct a systematic explainability evaluation across Convolutional Neural Networks (CNNs),
Vision Transformers (ViTs), and
Vision Mamba (ViM). Unlike predominantly qualitative studies, we quantify the
alignment between model
attention and human visual perception using eye-tracking ground truth. We formalize this comparison via a standardized normalization pipeline mapping post-hoc attribution maps and gaze heatmaps onto spatial probability distributions.
Alignment is evaluated across fine-grained classification, medical imaging, and emotion recognition using architecture-specific XAI methods. We measure fidelity using Jensen-Shannon similarity, Chi-square similarity, and Pearson correlation, three complementary
estimators capturing support overlap, mass discrepancy, and structural co-variation. Our results reveal distinct
attention dynamics: CNNs tend to exhibit a more global focus, with spatially more diffuse saliency maps that correlate well with human perception in general contexts, while ViTs demonstrate fine-grained, patch-level
attention, often focused on discriminative microfeatures. The Mamba architecture shows biased behavior: it achieves strong explainability in medical tasks but exhibits divergent intensity distributions in natural images; our analytical characterization of the metrics makes this dissociation explicit, since near-unit support overlap is attained simultaneously with a vanishing linear correlation. We further analyze the effect of backbone freezing and ensemble strategies on model interpretability. The results highlight how architectural and training choices influence the
alignment between model saliency and human visual
attention.
Read the full abstract ▾
All authors Marco Stefani, Edoardo Parpaiola, Matteo Bino, Gianluca Caregnato, Francesco Roncolato, Daniel Fusaro, Loris Nanni, Alberto Pretto
Machine Learning · Cross-listed from stat.ME
Product Monte Carlo: Expectation Under a Product of Densities
Pietro Carlotti, Sifan Liu and Yuling Yao
Aggregating independently computed sub-sample inferences is a well-known challenge in large-scale
Bayesian computation,
federated learning, and opinion pooling. The core problem is to approximate a distribution whose density is proportional to a product of individual densities. We propose Product Monte Carlo (PMC), an
algorithm for computing arbitrary expectations under a product of densities using only Monte Carlo draws from individual densities. We turn the intractable product expectation into a regression problem by expressing it through a family of computable conditional expectations. Besides the point estimate, our fully
Bayesian regression formulation provides coherent uncertainty quantification and principled diagnostics. We establish theoretical guarantees on consistency and characterize convergence rates for the PMC
estimator. Across simulated and real-data experiments varying the number, dimensionality, and heterogeneity of the component distributions, PMC achieves higher estimation accuracy, better-calibrated uncertainty coverage, and improved scalability at a lower computational cost than existing methods. In addition, PMC requires no density evaluation, making it applicable to simulation-based inference, as we demonstrate in an application with
protein images.
Read the full abstract ▾
Machine Learning
Primal-Dual Flow Matching for Sample-Wise Constrained Generation
Zhengyan Huan, Peter Y. Lu and Shuchin Aeron
We consider the problem of learning to generate data while satisfying a prescribed sample-wise constraint with a user-specified probability of constraint satisfaction. Starting with a population-level constrained negative log-likelihood minimization and using a flow-matching (FM) parameterization, under regularity assumptions and sufficient expressivity of the velocity field family, we derive guarantees on the probability of constraint satisfaction for the corresponding primal-dual optimization
algorithm. We provide a practical implementation of this approach, called Primal-Dual Flow Matching (PDFM), which has direct control over constraint satisfaction rate and requires only binary membership oracle feedback for constraint satisfaction, avoiding the need for differentiable distances, projections, or special structure of the constraint set, such as convexity. We show that PDFM improves constraint satisfaction over vanilla FM and achieves competitive performance against constraint-aware baselines while maintaining distributional fidelity. Our code is available at https://github.com/ZhengyanHuan/PDFM.
Read the full abstract ▾
Machine Learning · Cross-listed from math.OC
Toward Maximizing Algebraic Connectivity via Density-Dependent Backbone Construction and Reinforcement Learning Completion
Zeru Zhu, Marco Gamarra and Ji Liu
This paper studies an open network design problem of constructing graph
topologies with maximum algebraic connectivity under fixed numbers of vertices and edges. A density-dependent approach is proposed that decomposes the design task into two stages: a high-quality, low-cost structural backbone construction and a reinforcement learning completion stage. The method selects the backbone based on density, using complete multipartite graphs in dense regimes and Cayley graphs in low-to-intermediate regimes, and then refines the remaining edges through a learning-based procedure. Numerical results show that the proposed method achieves high algebraic connectivity with favorable runtime scalability, outperforming existing methods. These results support a structural-family-first strategy for scalable network design.
Read the full abstract ▾
Machine Learning
Critical Mass: Structure-Disjoint Splits Drift With the Libraries They Are Built On
Tomo Oga, Devesh Shah, Cailum M. K. Stienstra et al. (+4 more)
Molecular machine learning evaluates out-of-distribution performance with structure disjoint splits, a construction rule fixed once at the scale its library happened to have: threshold a pairwise distance, then assign whole connected components to folds. For predicting structures from mass spectra, the field has converged on single-linkage clustering under the myopic Maximum Common Edge Subgraph (MCES) distance at a threshold of 10. This convention was set on 29,000 molecules but public libraries now hold 227,690 molecules. MCES is NP-hard per pair over a quadratically growing set, and so the criterion has never been evaluated at that scale. We propose an optimized version of this criterion, allowing for computationally feasible application on the public libraries: Admissible bounds and a union-find skip reduce $2.6 \times 10^{10}$ molecular pairs to only $1.15 \times 10^{7}$ integer programs, a $2{,}259\times$ saving, while provably producing the lossless partition. We find that at this scale the graph percolates. A single component holds $95.5\%$ of the library, capping any test set at $4.5\%$. What remains is not merely smaller, but systematically different: a held-out compound outweighs a training compound 88.1% of the time, because a fixed absolute budget is a tighter relative tolerance on a larger molecule. Large library
benchmarks using this splitting rule naively therefore conflate structural novelty with extrapolation to larger, more complex chemistry.
Read the full abstract ▾
All authors Tomo Oga, Devesh Shah, Cailum M. K. Stienstra, Gabriel Asher, Antonio H. de O. Fonseca, Niall O'Connor, Michael Widrich
Machine Learning
Expert-level detection of low-voltage intervals in EEG as a robust biomarker of neonatal encephalopathy
John M. O'Toole, Sean R. Mathieson, Aurel Luca et al. (+4 more)
Background: Discontinuity in neonatal
EEG is a critical marker of
brain dysfunction but can be difficult to quantify visually. Inter-burst intervals (IBIs) are a key characteristic of discontinuity, yet their definition does not easily translate to AI detection. Objectives: To introduce low-voltage intervals (LVIs), defined exclusively by amplitude and duration, as a context-independent alternative to IBIs, develop an AI detection method for LVIs, and assess their clinical utility as a marker of
brain injury. Methods: We developed a ConvNeXt model to detect LVIs and compared its performance with existing methods. We then tested the clinical relevance of detected LVIs across four applications: 1) grading background
EEG abnormalities on an open
benchmark dataset, 2) classifying clinical hypoxic-ischaemic encephalopathy (HIE) grades and comparing with a normal
EEG dataset, 3) seizure prediction, and 4) association with seizure burden. Results: For training and validation, 654 hours of per-channel
EEG from 123 neonates were reviewed and 51,162 LVIs were annotated. On held-out validation, ConvNeXt had an AUC of 0.996 and a Matthews correlation coefficient of 0.926. Model-reader agreement exceeded inter-reader agreement ($\Delta \kappa = 0.025$, 95% CI: 0.007 to 0.045, $p<0.001$), attaining expert-level equivalence. On a combined
dataset of 444 neonates, percentage LVI showed a strong association with
EEG grades (Spearman's $\rho=0.801$), a moderate association with HIE grades ($\rho=0.384$), a weaker association with seizure burden ($\rho=0.244$), and a strong seizure prediction capacity (AUC $=0.872$). Conclusion: AI detection of LVIs achieves expert-level equivalence, whereas quantitative features do not. Automated LVI quantification provides a robust clinical biomarker of neonatal encephalopathy associated with background
EEG activity, HIE severity, and seizure risk.
Read the full abstract ▾
All authors John M. O'Toole, Sean R. Mathieson, Aurel Luca, Soraia Ventura, Sean Griffin, Geraldine B. Boylan, Robert Hogan
Machine Learning
Amortised Inference through One-Step Implicit Sampling
Vincent Pauline, Kirill Tamogashev, Arran Carter et al. (+3 more)
Efficient sampling from
Bayesian posterior distributions in high dimensions remains a hard problem, despite advances in theory and
algorithms. Multiple steps are usually required to draw unbiased samples, for example, iterations of an MCMC
algorithm or integration steps in a
diffusion-based amortised sampler. However, scalable one-step amortised inference remains a challenging open problem. In this work, we build upon recent progress in data-driven generative modelling to offer a possible solution for one-step amortised sampling. Our one-step implicit sampler (OSIS) uses short-time MCMC dynamics to define a local target for the
evolution of an implicitly modelled distribution. In the asymptotic limit, the modelled distribution is a fixed point of the MCMC kernel and thus samples from the target. We analyse the convergence properties of OSIS and show connections with other generative modelling and sampling
algorithms. We study various design choices and show that OSIS performs well compared to multi-step amortised samplers and non-amortised MCMC baselines while being far more efficient at sampling time.
Read the full abstract ▾
All authors Vincent Pauline, Kirill Tamogashev, Arran Carter, Sanghyeok Choi, Stefan Bauer, Esmeralda S. Whitammer
Machine Learning
Recurrent Harness for Agentic Continual Learning
Yuxin Xiao, Zhiyun Lu, Jianyu Wang et al. (+4 more)
Language model
agents increasingly operate over long interaction streams, requiring online adaptation to distribution shifts through continual learning. However, existing
agent harnesses typically either evolve their states only through forward information flow or rely on additional replay or validation data for harness optimization. To address this, we propose ReHarness, a recurrent harness framework for agentic continual learning that complements forward read and write with backward revision under a strictly online streaming protocol. We ask what information could have been captured differently in the harness state to better inform the current instance in the stream. Specifically, after each instance, we leverage the resulting trajectory as feedback to revise the reflections retrieved for that instance, thereby propagating feedback backward through the textual harness state. Across three continual learning
benchmarks and three
language model backbones, ReHarness consistently outperforms strong raw-context baselines,
memory- and reflection-based methods, and
prompt optimization approaches. Further analysis shows that ReHarness produces source-grounded and meaningful revisions, corrects overgeneralized or outdated experience under distribution shifts, and improves both stability and plasticity during continual learning.
Read the full abstract ▾
All authors Yuxin Xiao, Zhiyun Lu, Jianyu Wang, Yangtian Zhang, Yang Song, Qifan Wang, Bailin Wang
Machine Learning · Cross-listed from cs.AI
MagicBeanStalk: Escaping the RLVR Zero Advantage Trap with Recursive Data Synthesis
Ximing Lu, Aviral Kumar, Jan Kautz et al. (+2 more)
Data-centric scaling of RLVR has focused on collecting or generating verifiable training problems. However, corpus size alone does not determine whether the
dataset provides a useful learning signal for a target policy. To guide the synthesis of effective RLVR data, we experimentally characterize
dataset effectiveness as a function of its problems, the target policy, and the training rollout budget. Under this characterization, we show that a large open-source math corpus pooled from widely used RLVR
datasets falls almost entirely into a zero-advantage trap: for a fixed target policy and rollout budget, roughly 88% of its problems are solved in every rollout or failed in every rollout. Filtering concentrates what remains, but it can only select, discarding the hard problems. Effective synthetic problems should therefore require the
reasoning operations and compositions required to solve those hard problems. Yet their difficulty must be calibrated, so that some rollouts succeed, some fail, and at least one correct solution fits within the training budget. Prompting a teacher to vary hard problems directly does not achieve this. Guided by these empirical principles, we introduce MagicBeanStalk, a top-down decomposition and bottom-up recursive data-synthesis
algorithm that grows seed problems into families of substantively new, policy- and budget-calibrated training problems while preserving the seeds'
reasoning blueprints. Across 8 math
benchmarks, continual RLVR on MagicBeanStalk problems improves gpt-oss-120b from 61.2 to 69.8 (+8.6) and DeepSeek v4Flash from 72.4 to 77.9 (+5.4) on a 16K-
token budget. Training on the full 78K source corpus improves by only +1.1 and its best filtered real data subset by +5.8. In finance, we synthesize over 14K verifiable problems from only 340 solutions and improve over base by 6.9 and 2.4 points on SecQue and FinanceBench, respectively.
Read the full abstract ▾
All authors Ximing Lu, Aviral Kumar, Jan Kautz, Yejin Choi, David Acuna
Machine Learning
Data-driven Optimal Sensor Placement for Aerosol Monitoring in the UK
Talha Ansar, Waqar Muhammad Ashraf, Alejandro Coca-Castro et al. (+3 more)
We develop a data-driven sensor-placement framework and apply it to aerosol monitoring in the United Kingdom (UK). A trained convolutional Gaussian neural process is embedded within the DeepSensor optimisation framework. Genetic optimisation with lazy evaluation and caching reduces mean computational time by 60% (10$\pm$3 versus 25$\pm$7 minutes) while producing sequential placement performance comparable to the greedy solver. Using the CAMS reference field to construct a retrospective oracle
benchmark, Joint NLL improves by about 22% for Joint-MI-driven genetic placement after five locations for aerosol stations are identified. Seasonal and wind-regime analyses show that agreement between model-based criteria and oracle
benchmarks varies with meteorological transport conditions. These results show a computationally efficient approach for data-informed expansion of environmental observing systems.
Read the full abstract ▾
All authors Talha Ansar, Waqar Muhammad Ashraf, Alejandro Coca-Castro, Manvendra Janmaijaya, Ramit Debnath, J. Scott Hosking
Machine Learning
Kronecker Product Attention: Memory-Efficient KV Compression via Structured Factorization
Bahareh Nikpour, Hossein Rajabzadeh, Maryam Dialameh et al. (+2 more)
Efficient autoregressive generation is increasingly limited by the
memory footprint of the key-value (KV) cache, which grows linearly with sequence length, batch size, and model depth. Existing approaches such as Multi-Query
Attention (MQA), Grouped-Query
Attention (GQA), Multi-Head Latent
Attention (MLA), and Tensor Product
Attention (TPA) reduce this cost through different trade-offs, but often sacrifice expressivity, require additional positional-encoding machinery, or impose restrictive low-rank structure. We propose Kronecker Product
Attention (KPA), which represents key and value activations as sums of Kronecker products of compact,
token-dependent
matrix factors. KPA strictly generalizes TPA: rank-one vector-outer-product factorization arises as a degenerate Kronecker split, while non-degenerate
matrix factors can represent richer block-structured patterns. We further show that a structured rotary
embedding operator matched to the Kronecker representation preserves the relative-position property of RoPE while rotating only the compact factors, removing the need for a decoupled RoPE branch as in MLA. Empirically, KPA matches or exceeds TPA, MHA, MQA, GQA, and MLA across four model scales and nine downstream
benchmarks under identical training conditions, while achieving up to 10x KV cache compression. The Kronecker head split is a tuneable hyperparameter that allows practitioners to navigate the compression-accuracy trade-off at design time without architectural changes.
Read the full abstract ▾
All authors Bahareh Nikpour, Hossein Rajabzadeh, Maryam Dialameh, Vahid Partovi Nia, Parsa Omidi
Machine Learning
SynAct: Synergistic Active Feedback Learning for LLM Agents
Ning Liu, Ian Li and Kristina Klinkner
LLM
agents executing multi-step workflows fail in two fundamentally different ways: recoverable slips, which further attempts can repair, and knowledge gaps, which retrying cannot resolve. Expert feedback can address the latter, but expert
attention is scarce. The key challenge is therefore not whether to ask for feedback, but where feedback can change the outcome. Existing approaches either avoid expert feedback, allowing
agents to reinforce their own errors, or allocate feedback at the task level without identifying consequential decisions. We present SynAct, an active learning framework that treats expert
attention as the binding constraint and allocates feedback at the level of individual decisions. SynAct ranks decisions by the mutual information between the selected action and the terminal outcome across repeated rollouts, queries an expert at the highest-value decisions, and distills the resulting corrections into transferable rules that the
agent can reuse without expert access at deployment. We theoretically characterize what this signal identifies under finite repeated sampling: with k rollouts and at least m observations per action, outcome-constant decisions have zero mutual information, while outcome-separating decisions have mutual information at least H2(m/k) bits, yielding exact separation for any threshold t in (0,H2(m/k)). This also explains why success-based acquisition can be blind when all rollouts fail: success is constant even when failed runs reach different outcomes. Across four
agent benchmarks and four models spanning three families, SynAct improves held-out accuracy in all 16 evaluated settings, by +11.7pp on average. The same signal transfers to inference-time routing, where SynAct outperforms budget-matched cascade, uncertainty, and expert-judge routers in 15 of 16 settings, while a single targeted correction outperforms seven additional unaimed retries.
Read the full abstract ▾
Machine Learning
Machine Learning and Time-Series Foundation Models for Day-Ahead Electricity Forecasting in a University Building
Amey Vasulkar, Samuel Kernan Freire, Arie-Willem de Leeuw et al. (+1 more)
Day-ahead electricity forecasts can help building operators schedule heating, ventilation, and other services around anticipated demand. Choosing a forecasting model also requires balancing accuracy with its forecast-time inputs, local training, and computational requirements. We
benchmark statistical, machine-learning, recurrent neural-network, and pretrained TimesFM models for a university building. We use chronological validation and evaluate all configurations on the same 57 test days, comparing accuracy across workdays, weekends, and holidays alongside local fitting and forecasting time. Weather
covariates use retrospective observations. TimesFM 3.0 with
covariates achieves the lowest overall errors, reducing mean absolute error by approximately 43% relative to weekly seasonal-naive forecasting. XGBoost remains competitive, although paired daily comparisons do not establish a clear mean-absolute-error advantage for TimesFM. TimesFM also performs strongly using only past electricity consumption. Adding
covariates improves its holiday forecasts but slightly worsens workday and weekend forecasts, leaving overall mean absolute error almost unchanged. TimesFM requires no building-specific weight training, while XGBoost offers rapid local fitting and inference. The evaluated LSTM takes longer to fit without outperforming either approach. An exploratory historical evaluation reveals seasonal variation, while a separate weather-source comparison produces only small changes in the selected TimesFM configuration's accuracy. These results support pretrained TimesFM as a strong initial forecasting baseline for this building, with XGBoost as a competitive locally fitted alternative.
Covariates are particularly useful when improved holiday forecasts justify the additional input preparation.
Read the full abstract ▾
All authors Amey Vasulkar, Samuel Kernan Freire, Arie-Willem de Leeuw, Tadeo-Baldiri Salcedo-Rahola
Machine Learning
STAPLE: Static Sparse Upcycling of Pretrained Checkpoints via Embedding Modules
Ranajoy Sadhukhan, Euijin Hong, Sheng Cao et al. (+9 more)
Sparse computation can scale the parametric capacity of LLMs without proportionally increasing active computation, but pretraining sparse architectures remains expensive and data-hungry. Existing sparse upcycling methods mainly target Mixture-of-Experts models, where expert homogeneity, sample inefficiency, and system overheads can limit practical scalability. Static sparse
memory offers predictable access and
token-specific updates that can help address these challenges, but naively integrating it into pretrained computation yields poor returns. In this work, we introduce STAPLE, a recipe built upon STEM for integrating static sparse
memory into pretrained models. Whereas STEM replaces FFN up-projections with
token-indexed
embeddings, STAPLE retains them and adds the
embeddings as a residual pathway, preserving pretrained computation while learning complementary
token-specific information in a scalable manner. On OLMo-2 1B, STAPLE improves over continued dense training by 4.27 points on HumanEval, 2.80 on MBPP, 2.27 on GSM8K, and 1.65 on DROP. Average performance increases with static capacity, and improvements persist on the larger OLMo-2 7B backbone. STAPLE also outperforms static sparse baselines such as STEM and an Engram-style model, and achieves a higher average score than an MoE upcycling baseline while decoding 2x faster with less than half its GPU model
memory and measured GPU energy per
token in our throughput-oriented decoding evaluation. Importantly, despite introducing billions of parameters late in training, our host-offloaded implementation keeps generation throughput within 1.5% and training throughput within 3% of the dense baseline, while caching only the ~5% most frequent
embeddings on GPU. These results show that static sparse
memory can provide a sample-efficient, scalable, and sustainable path for expanding pretrained models without sparse pretraining from scratch.
Read the full abstract ▾
All authors Ranajoy Sadhukhan, Euijin Hong, Sheng Cao, Zechun Liu, Shuowei Jin, Sha Li, Changlong Yu, Xin Liu, Qin Lu, Zhenyu Shi, Priyanka Nigam, Beidi Chen
Machine Learning · Cross-listed from cs.AI
SpireBench: Evaluating Long-Horizon Strategic Play of Agentic Models with Slay the Spire
Scott C. Lowe and Sander W. Keemink
Agentic large
language models now tackle complex tasks, yet strategic
reasoning over long horizons is under-studied: most agentic
benchmarks are short and episodic, and performance on long tasks is hard to dissect into stored knowledge,
reasoning and luck. We introduce SpireBench, in which models play the complete commercial deck-builder Slay the Spire (StS), where early decisions decide long-term success. Across 20 large
language models (LLMs) at the game's highest difficulty, frontier models beat heuristic baselines and match the average human player but remain far behind experts. This gap widens as the run lengthens: the strongest models win the first act as often as experts, then fall behind. What separates strong models from weak is how well they play each fight; all of them misjudge risk over a run, preserving health rather than spending it to grow stronger. A comprehensive, self-consistent renaming of every game term shows that part of their performance rests on prior knowledge of the game, and models do not improve from the
memories they write across runs, which are often wrong and overly cautious. Our harness is the first to give a model the complete original game, and we compare it with existing harnesses. Overall, SpireBench offers an unsaturated long-horizon
benchmark with tools to locate where and why
agents fail.
Read the full abstract ▾
Machine Learning
Realism VS Accuracy: Event Sequence Forecasting from a Generative Modeling Perspective
Dmitry Osin, Egor Surkov, Petr Mokrov et al. (+5 more)
Event sequences are chains of random events, each described by heterogeneous (numerical and categorical) features. The problem of event sequence forecasting occurs in finance, healthcare, business process intelligence, and other fields. In this work, we study multi-horizon forecasting of event sequences as a conditional generative modeling problem. We evaluate forecasts not only for prediction accuracy, but also for distributional realism. To this end, we present a
benchmark comprising metrics for both quality aspects, strong statistical baselines, recent models adapted from adjacent fields, and curated real-world
datasets. Careful evaluation reveals that no method excels at both accuracy and realism, highlighting a fundamental trade-off between the two. Finally, we introduce Wasserstein BaryBooster, an
algorithm that aggregates samples from a realism-strong
diffusion model into a state-of-the-art predictor, demonstrating that distributional realism can be converted into prediction accuracy. Code is available at https://github.com/xaosina/event-sequence-forecasting.
Read the full abstract ▾
All authors Dmitry Osin, Egor Surkov, Petr Mokrov, Igor Udovichenko, Ivan Karpukhin, Evgeny Burnaev, Egor Shvetsov, Alexander Korotin
Machine Learning
DiffusionART: Efficient, Stable and Scalable Reinforcement of Diffusion Models
Zhenglin Wan, Jiayu Chen, Zhengfeiyang Zhang et al. (+6 more)
Online reinforcement learning (RL) fine-tunes
diffusion models with black-box rewards, but reverse-process methods such as Flow-GRPO are limited in efficiency by poor credit assignment, while forward-process methods such as DiffusionNFT are efficient yet unstable without carefully tuned exponential-moving-average (EMA) off-policy training. We show that NFT-style objectives contain a hidden forward–reverse consistency force that joint positive–negative training cancels only partially, and that EMA stabilizes training through restoration rather than off-policy rollouts. We introduce DiffusionART (
Diffusion Reinforcement with Aggregation-First Reward Tilting), which aggregates each
prompt's rewards into a shared reward-improving direction for reverse-process states, removing the consistency force by construction, and adds a trust-region-masked second update for drift-adaptive restoration without EMA tuning. It requires no differentiable reward model, remains effective with fewer samples per
prompt, and supports pairwise reward models (DiffusionART-Pairwise). Across image and
video generation, DiffusionART trains efficiently and stably without per-task tuning. In particular, on HunyuanVideo-13B with equally weighted visual and motion quality rewards, DiffusionART reaches the late-stage mean reward levels of DiffusionNFT and Flow-GRPO-Fast with 12.02 and 11.72 times fewer GPU hours, respectively, while achieving 28.8% and 53.0% higher mean training rewards.
Read the full abstract ▾
All authors Zhenglin Wan, Jiayu Chen, Zhengfeiyang Zhang, Pengfei Zhou, Wangbo Zhao, Fangyuan Kong, Pengfei Wan, Kun Gai, Yang You
Machine Learning
An all-transistor physical-learning transformer can be trained to perform in-context learning
Michael C. Abbott and Benjamin B. Machta
Most systems trained by
equilibrium propagation or coupled learning are in the same class as multi-layer perceptrons: while they may be universal function approximators, they struggle to learn associative tasks which are easy for
transformers.
Equilibrium propagation relies on a bidirectional flow of information through the physical system between input and output. The reverse flow is broken by more complex nonlinear systems, such as those performing multiplication which is needed to express dot-product
attention. Here we explicitly restore this bidirectional flow by introducing extra
circuit elements for this purpose into a double or dyadic
circuit. We then use these ideas to construct an
attention mechanism exploiting the exponential current law of sub-threshold MOSFET devices. We show that in simulations this
circuit can be trained to perform a simple in-context learning task, despite using realistic reverse components which transmit only an approximate gradient. For this training to succeed we need cross-
entropy loss (not mean squared error). We generate nudges appropriate for this loss using a novel floating
circuit element, based on the same MOSFET sub-
circuit used for softmax. We train the resistors in this
circuit using the Lion optimiser, which can be implemented using one capacitor per parameter to store local
memory of past gradient estimates.
Read the full abstract ▾
Machine Learning
Sample-Adaptive Zeroth-Order Post-Training
Haiyuan Wan, Yanyi Li, Weicheng Lin et al. (+1 more)
Zeroth-order (ZO) optimization offers a
memory-efficient alternative to backpropagation for fine-tuning large
language models. However, existing ZO methods typically sample training examples uniformly, overlooking their evolving importance and leaving avoidable estimation variance. To address this limitation, we propose Sample-Adaptive Zeroth-Order Optimization (SAZO), which learns sample importance online and adaptively allocates queries to accelerate convergence. SAZO extracts gradient-norm information from existing directional differences to estimate sample importance without access to true gradients. Furthermore, to track evolving importance from sparse minibatch feedback, SAZO maintains per-example exponential moving averages that aggregate observations across updates. The method requires no additional model evaluations and only $O(N)$ additional scalar state compared with MeZO. We prove that SAZO asymptotically matches the leading convergence term of the minimum-variance sampling oracle, and achieves a strictly faster convergence rate than standard methods. Extensive experiments across four model families demonstrate improved average downstream performance and up to $6\times$ faster convergence to the same training loss in terms of query count.
Read the full abstract ▾
All authors Haiyuan Wan, Yanyi Li, Weicheng Lin, Cong Fang
Machine Learning · Cross-listed from cs.RO
Fly-by-Code: Embodied Coding Agents for Aerial Manipulation with Active Visual and Physical Feedback
Jaewoo Lee, Jeongyeon Seo, Sihyun Cho et al. (+10 more)
Embodied coding
agents construct
robot policies from natural-
language instructions by generating executable programs and refining them from execution feedback. This refinement assumes that execution feedback reveals whether the task succeeded and, after a failure, provides sufficient evidence to guide program revision. Aerial manipulation violates this assumption in two ways. Payload constraints restrict onboard camera coverage and leave task-critical outcomes outside the
robot's view (partial observability), while strong dynamic coupling and limited control margins make physical interactions fragile (limited interaction robustness) and leave failure causes unresolved. Re-examining the same feedback cannot recover observations that were never collected or separate failure causes that the available evidence does not distinguish. To acquire this missing evidence, we introduce Active Feedback (AF), an active "View and Probe" framework. When execution feedback leaves unresolved questions, the
agent synthesizes a separate diagnostic program that runs in simulation to inspect unseen outcomes from informative viewpoints (View) or test hypotheses about failure causes through targeted physical interactions (Probe). Across six simulated aerial manipulation tasks with 60 trials per condition, AF reduces false completion declarations from 25 to 5 and raises final task success from 31.7% to 75% compared with terminal feedback under the same coding-
agent configuration and task-execution limit. Using shared
robot APIs, task programs refined with AF in simulation run on a physical aerial manipulator without task-program source-code modification and complete multi-stage manipulation tasks in the real world. These results show that executable diagnosis fills gaps in execution feedback for embodied coding
agents, improving both completion assessment and program refinement in aerial manipulation.
Read the full abstract ▾
All authors Jaewoo Lee, Jeongyeon Seo, Sihyun Cho, Gyeongrak Choe, Yutong Wang, Bavin Saravanan, Jia-Bin Huang, Furong Huang, Sebastian Scherer, Guanya Shi, H. Jin Kim, Seungjae Lee, Dongjae Lee