Machine Learning
Just on Time: Token-Level Early Stopping for Diffusion Language Models
Zakhar Kohut, Severyn Shykula, Mykola Vysotskyi et al. (+7 more)
Diffusion language models generate text through iterative refinement, a process that is often computationally inefficient because many
tokens reach stability long before the final denoising step. We introduce a training-free,
token-level early stopping approach that identifies convergence independently at each position. Our method leverages lightweight signals derived from the model's predictions and local context to dynamically determine when individual
tokens can be finalized. This yields adaptive per-
token freezing without task-specific fine-tuning, substantially reducing the total number of
diffusion steps required. Across diverse
benchmarks, spanning mathematical
reasoning, general question answering, and scientific understanding, our approach achieves substantial efficiency gains while preserving generation quality.
Read the full abstract ▾
All authors Zakhar Kohut, Severyn Shykula, Mykola Vysotskyi, Serhii Dmytryshyn, Dmytro Khamula, Michal Zakrzewski, Damian Rynczak, Jacek Małecki, Taras Rumezhak, Volodymyr Karpiv
Machine Learning
Meltdown: Circuits and Bifurcations in Point-Cloud-Conditioned 3D Diffusion Transformers
Maximilian Plattner, Fabian Paischer, Johannes Brandstetter et al. (+1 more)
Sparse point clouds are a common input modality for 3D surface reconstruction, including in safety-critical settings such as
surgical navigation and autonomous perception. Recent point-cloud-conditioned 3D
diffusion transformers achieve state-of-the-art results in this regime by leveraging learned priors. We show that these models can fail catastrophically under realistic input variation, and present a mechanistic case study of why. We identify a failure mode we call Meltdown: tiny on-surface perturbations to a sparse input point cloud can fracture the reconstructed output into hundreds of disconnected pieces.
Adversarial search recovers Meltdown in 89.9-100% of shapes across the two open-weight state-of-the-art architectures we study (WaLa, Make-a-Shape) on real-world
datasets (GSO, SimJEB) and under both DDPM and DDIM sampling. We trace Meltdown along the forward pass: it is governed by how uniformly the points are distributed on the surface, faithfully transduced through the point-cloud encoder, and committed by a single early-denoising cross-
attention write in the
diffusion backbone.
Diffusion-trajectory ensembles exhibit
symmetry-breaking near this commit step, consistent with a bifurcation of the reverse process. Through a suite of matched-magnitude controls, we show that the variable on which the model commits is directional, concentrated in a low-rank subspace of the write's perturbation drift. Motivated by this finding, we introduce PowerRemap, a test-time control that reshapes the singular spectrum of the localized write to suppress this drift, with rescue rates of 98.3% on WaLa and 84.6% on Make-a-Shape. Together, these results link a
circuit-level cross-
attention mechanism to a trajectory-level account of the failure, demonstrating how mechanistic analysis can explain and guide behavior in conditional
diffusion transformers.
Read the full abstract ▾
All authors Maximilian Plattner, Fabian Paischer, Johannes Brandstetter, Arturs Berzins
Machine Learning
Asymmetric Prompt Weighting for Reinforcement Learning with Verifiable Rewards
Reinhard Heckel, Mahdi Soltanolkotabi and Christos Thramboulidis
Reinforcement learning with verifiable rewards has driven recent advances in LLM post-training, in particular for
reasoning. Policy optimization
algorithms generate a number of responses for a given
prompt and then effectively weight the corresponding gradients depending on the rewards. The most popular
algorithms including GRPO, DAPO, and RLOO focus on ambiguous
prompts, i.e.,
prompts with intermediate success probability, while downgrading gradients with very easy and very hard
prompts. In this paper, we consider asymmetric
prompt weightings that assign higher weights to
prompts with low, or even zero, empirical success probability. We find that asymmetric weighting particularly benefits from-scratch RL (as in R1-Zero), where training traverses a wide accuracy range, and less so in post-SFT RL where the model already starts at high accuracy. We also provide theory that characterizes
prompt weights which minimize the time needed to raise success probability from an initial level to a target accuracy under a fixed update budget. In low-success regimes, where informative responses are rare and response cost dominates, these optimal weights become asymmetric, upweighting low success probabilities and thereby accelerating effective-time convergence.
Read the full abstract ▾
Machine Learning
The Offline-Frontier Shift: Diagnosing Distributional Limits in Generative Multi-Objective Optimization
Stephanie Holly, Alexandru-Ciprian Zăvoianu, Siegfried Silber et al. (+2 more)
Offline multi-objective optimization (MOO) aims to recover Pareto-optimal designs given a finite, static
dataset. Recent generative approaches, including
diffusion models, show strong performance under hypervolume, yet their behavior under other established MOO metrics is less understood. We show that generative methods systematically underperform evolutionary alternatives with respect to other metrics, such as generational distance. We relate this failure mode to the offline-frontier shift, i.e., the displacement of the offline
dataset from the Pareto front, which acts as a fundamental limitation in offline MOO. We argue that overcoming this limitation requires out-of-distribution sampling in objective space (via an integral probability metric) and empirically observe that generative methods remain conservatively close to the offline objective distribution. Our results position offline MOO as a distribution-shift–limited problem and provide a diagnostic lens for understanding when and why generative optimization methods fail.
Read the full abstract ▾
All authors Stephanie Holly, Alexandru-Ciprian Zăvoianu, Siegfried Silber, Sepp Hochreiter, Werner Zellinger
Machine Learning
From Natural Language to Materials Discovery:The Materials Knowledge Navigation Agent
Genmao Zhuang and Amir Barati Farimani
Accelerating the discovery of high-performance materials remains a central challenge across energy, electronics, and aerospace technologies, where traditional workflows depend heavily on expert intuition and computationally expensive simulations. Here we introduce the Materials Knowledge
Navigation Agent (MKNA), a
language-driven system that translates natural-
language scientific intent into executable actions for database
retrieval, property prediction, structure generation, and stability evaluation. Beyond automating tool invocation, MKNA autonomously extracts quantitative thresholds and chemically meaningful design motifs from literature and database evidence, enabling data-grounded hypothesis formation. Applied to the search for high-Debye-temperature ceramics, the
agent identifies a literature-supported screening criterion (Theta_D > 800 K), rediscovers canonical ultra-stiff materials such as diamond, SiC, SiN, and BeO, and proposes thermodynamically stable, previously unreported Be-C-rich compounds that populate the sparsely explored 1500-1700 K regime. These results demonstrate that MKNA not only finds stable candidates but also reconstructs interpretable design heuristics, establishing a generalizable platform for autonomous,
language-guided materials exploration.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.MA
Learning to Compose for Cross-domain Agentic Workflow Generation
Jialiang Wang, Shengxiang Xu, Hanmo Liu et al. (+5 more)
Automatically generating agentic workflows – executable operator graphs or codes that orchestrate
reasoning, verification, and repair – has become a practical way to solve complex tasks beyond what single-pass LLM generation can reliably handle. Yet what constitutes a good workflow depends heavily on the task distribution and the available operators. Under domain shift, current systems typically rely on iterative workflow refinement to discover a feasible workflow from a large workflow space, incurring high iteration costs and yielding unstable, domain-specific behavior. In response, we internalize a decompose-recompose-decide mechanism into an open-source LLM for cross-domain workflow generation. To decompose, we learn a compact set of reusable workflow capabilities across diverse domains. To recompose, we map each input task to a sparse composition over these bases to generate a task-specific workflow in a single pass. To decide, we attribute the success or failure of workflow generation to counterfactual contributions from learned capabilities, thereby capturing which capabilities actually drive success by their marginal effects. Across stringent multi-domain, cross-domain, and unseen-domain evaluations, our 1-pass generator surpasses SOTA refinement baselines that consume 20 iterations, while substantially reducing generation latency and cost.
Read the full abstract ▾
All authors Jialiang Wang, Shengxiang Xu, Hanmo Liu, Jiachuan Wang, Yuyu Luo, Shimin Di, Min-Ling Zhang, Lei Chen
Machine Learning · Cross-listed from stat.ME
Renet: Principled and Efficient Relaxation for the Elastic Net via Dynamic Objective Selection
Albert Dorador
We introduce Renet, a principled generalization of the Relaxed Lasso to the Elastic Net family of
estimators. While, on the one hand, $\ell_1$-regularization is a standard tool for variable selection in high-dimensional regimes and, on the other hand, the $\ell_2$ penalty provides stability and solution uniqueness through strict convexity, the standard Elastic Net nevertheless suffers from shrinkage bias that frequently yields suboptimal prediction accuracy. We propose to address this limitation through a framework called relaxation. Existing relaxation implementations rely on naive linear interpolations of penalized and unpenalized solutions, which ignore the non-linear geometry that characterizes the entire regularization path and risk violating the Karush-Kuhn-Tucker conditions. Renet addresses these limitations by enforcing sign consistency through an adaptive relaxation procedure that dynamically dispatches between convex blending and efficient sub-path refitting. Furthermore, we identify and formalize a unique synergy between relaxation and the “One-Standard-Error” rule: relaxation serves as a robust debiasing mechanism, allowing practitioners to leverage the parsimony of the 1-SE rule without the traditional loss in predictive fidelity. Our theoretical framework incorporates automated stability safeguards for ultra-high dimensional regimes and is supported by a comprehensive benchmarking suite across 20 synthetic and real-world
datasets, demonstrating that Renet consistently outperforms the standard Elastic Net and provides a more robust alternative to the Adaptive Elastic Net in high-dimensional, low signal-to-noise ratio and high-multicollinearity regimes. By leveraging an adaptive solver backend, Renet delivers these statistical gains while offering a computational profile that remains competitive with state-of-the-art coordinate descent implementations.
Read the full abstract ▾
Machine Learning
Statistical Learning Analysis of Physics-Informed Neural Networks
David A. Barajas-Solano
We study the training and performance of physics-informed learning for initial and boundary value problems (IBVP) with physics-informed neural networks (PINNs) from a statistical learning perspective. Specifically, we restrict ourselves to parameterizations with hard initial and boundary condition constraints and reformulate the problem of estimating PINN parameters as a statistical learning problem. From this perspective, the physics penalty on the IBVP residuals can be better understood not as a regularizing term bus as an infinite source of indirect data, and the learning process as fitting the PINN distribution of residuals $p(y \mid x, t, w) q(x, t) $ to the true data-generating distribution $\delta(0) q(x, t)$ by minimizing the Kullback-Leibler divergence between the true and PINN distributions. Furthermore, this analysis show that physics-informed learning with PINNs is a singular learning problem, and we employ singular learning theory tools, namely the so-called Local Learning Coefficient (Lau et al., 2025) to analyze the estimates of PINN parameters obtained via
stochastic optimization for a heat equation IBVP. Finally, we discuss implications of this analysis on the quantification of predictive uncertainty of PINNs and the extrapolation capacity of PINNs.
Read the full abstract ▾
Machine Learning
MerLin: A Discovery Engine for Photonic and Hybrid Quantum Machine Learning
Cassandre Notton, Benjamin Stott, Philippe Schoeb et al. (+7 more)
Identifying where
quantum models may offer practical benefits in near term
quantum machine learning (QML) requires moving beyond isolated algorithmic proposals toward systematic and empirical exploration across models,
datasets, and hardware constraints. We introduce MerLin, an open-source framework designed as a discovery engine for photonic and hybrid
quantum machine learning. MerLin integrates optimized strong simulation of linear optical
circuits into standard PyTorch and scikit learn workflows, enabling end-to-end differentiable training of
quantum layers. MerLin is designed around systematic benchmarking and reproducibility. As an initial contribution, we reproduce eighteen state-of-the-art photonic and hybrid QML works spanning kernel methods, reservoir computing, convolutional and recurrent architectures, generative models, and modern training paradigms. These reproductions are released as reusable, modular experiments that can be directly extended and adapted, establishing a shared experimental baseline consistent with empirical benchmarking methodologies widely adopted in modern artificial intelligence. By
embedding photonic
quantum models within established machine learning ecosystems, MerLin allows practitioners to leverage existing tooling for ablation studies, cross-modality comparisons, and hybrid classical-
quantum workflows. The framework already implements hardware-aware features, allowing tests on available
quantum hardware while enabling exploration beyond its current capabilities, positioning MerLin as a forward-looking co-design tool linking
algorithms,
benchmarks, and hardware.
Read the full abstract ▾
All authors Cassandre Notton, Benjamin Stott, Philippe Schoeb, Anthony Walsh, Grégoire Leboucher, Vincent Espitalier, Vassilis Apostolou, Louis-Félix Vigneux, Alexia Salavrakos, Jean Senellart
Machine Learning
Direct Learning of Calibration-Aware Uncertainty for Neural PDE Surrogates
Carlos Stein Brito
Neural PDE surrogates are often deployed in data-limited or partially observed regimes where downstream decisions depend on calibrated uncertainty in addition to low prediction error. Existing approaches obtain uncertainty through ensemble replication, fixed
stochastic noise such as dropout, or post hoc calibration. Cross-regularized uncertainty learns uncertainty parameters during training using gradients routed through a held-out regularization split. The predictor is optimized on the training split for fit, while low-dimensional uncertainty controls are optimized on the regularization split to reduce train-test mismatch, yielding regime-adaptive uncertainty without per-regime noise tuning. The framework can learn continuous noise levels at the output head, within hidden features, or within operator-specific components such as spectral modes. We instantiate the approach in
Fourier Neural Operators and evaluate on APEBench sweeps over observed fraction and training-set size. Across these sweeps, the learned predictive distributions are better calibrated on held-out splits and the resulting uncertainty fields concentrate in high-error regions in one-step spatial diagnostics.
Read the full abstract ▾
Machine Learning
General Flexible $f$-divergence for Challenging Offline RL Datasets with Low Stochasticity and Diverse Behavior Policies
Jianxun Wang, Grant C. Forbes, Leonardo Villalobos-Arias et al. (+1 more)
Offline RL
algorithms aim to improve upon the behavior policy that produces the collected data while constraining the learned policy to be within the support of the
dataset. However, practical offline
datasets often contain examples with little diversity or limited exploration of the environment, and from multiple behavior policies with diverse expertise levels. Limited exploration can impair the offline RL
algorithm's ability to estimate Q or V values, while constraining towards diverse behavior policies can be overly conservative. Such
datasets call for a balance between the RL objective and behavior policy constraints. We first identify the connection between $f$-divergence and optimization constraint on the Bellman residual through a more general Linear Programming form for RL and the convex conjugate. Following this, we introduce the general flexible function formulation for the $f$-divergence to incorporate an adaptive constraint on
algorithms' learning objectives based on the offline training
dataset. Results from experiments on the MuJoCo, Fetch, and AdroitHand environments show the correctness of the proposed LP form and the potential of the flexible $f$-divergence in improving performance for learning from a challenging
dataset when applied to a compatible constrained optimization
algorithm.
Read the full abstract ▾
All authors Jianxun Wang, Grant C. Forbes, Leonardo Villalobos-Arias, David L. Roberts
Machine Learning · Cross-listed from cs.CV
First International StepUP Competition for Biometric Footstep Recognition: Methods, Results and Remaining Challenges
Robyn Larracy, Eve MacDonald, Angkoon Phinyomark et al. (+5 more)
Biometric footstep recognition, based on a person's unique pressure patterns under their feet during walking, is an emerging field with growing applications in security and safety. However, progress in this area has been limited by the lack of large, diverse
datasets necessary to address critical challenges such as generalization to new users and robustness to shifts in factors like footwear or walking speed. The recent release of the UNB StepUP-P150
dataset, the largest and most comprehensive collection of high-resolution footstep pressure recordings to date, opens new opportunities for addressing these challenges through deep learning. To mark this milestone, the First International StepUP Competition for Biometric Footstep Recognition was launched. Competitors were tasked with developing robust recognition models using the StepUP-P150
dataset that were then evaluated on a separate, dedicated test set designed to assess verification performance under challenging variations, given limited and relatively homogeneous reference data. The competition attracted global participation, with 23 registered teams from academia and industry. The top-performing team, Saeid_UCC, achieved the best equal error rate (EER) of 10.77% using a generative reward machine (GRM) optimization strategy. Overall, the competition showcased strong solutions, but persistent challenges in generalizing to unfamiliar footwear highlight a critical area for future work.
Read the full abstract ▾
All authors Robyn Larracy, Eve MacDonald, Angkoon Phinyomark, Saeid Rezaei, Mahdi Laghaei, Ali Hajighasem, Aaron Tabor, Erik Scheme
Machine Learning
GRASP: group-Shapley feature selection for patients
Yuheng Luo, Shuyan Li and Zhong Cao
Feature selection remains a major challenge in medical prediction, where existing approaches such as LASSO often lack robustness and interpretability. We introduce GRASP, a novel framework that couples Shapley value driven attribution with group $L_{21}$ regularization to extract compact and non-redundant feature sets. GRASP first distills group level importance scores from a pretrained tree model via SHAP, then enforces structured sparsity through group $L_{21}$ regularized logistic regression, yielding stable and interpretable selections. Extensive comparisons with LASSO, SHAP, and deep learning based methods show that GRASP consistently delivers comparable or superior predictive accuracy, while identifying fewer, less redundant, and more stable features.
Read the full abstract ▾
Machine Learning
Token-Efficient Change Detection in LLM APIs
Timothée Chauvin, Clément Lalanne, Erwan Le Merrer et al. (+3 more)
Remote change detection in LLMs is a difficult problem. Existing methods are either too expensive for deployment at scale, or require initial white-box access to model weights or grey-box access to log probabilities. We aim to achieve both low cost and strict black-box operation, observing only output
tokens. Our approach hinges on specific inputs we call Border Inputs, for which there exists more than one output top
token. From a statistical perspective, optimal change detection depends on the model's Jacobian and the Fisher information of the output distribution. Analyzing these quantities in low-temperature regimes shows that border inputs enable powerful change detection tests. Building on this insight, we propose the Black-Box Border Input Tracking (B3IT) scheme. Extensive in-vivo and in-vitro experiments show that border inputs are easily found for non-
reasoning tested endpoints, and achieve performance on par with the best available grey-box approaches. B3IT reduces costs by $30\times$ compared to existing methods, while operating in a strict black-box setting.
Read the full abstract ▾
All authors Timothée Chauvin, Clément Lalanne, Erwan Le Merrer, Jean-Michel Loubes, François Taïani, Gilles Tredan
Machine Learning · Cross-listed from cs.CL
SteuerLLM: Local specialized large language model for German tax law analysis
Sebastian Wind, Jeta Sopa, Laurin Schmid et al. (+8 more)
Large
language models (LLMs) demonstrate strong general
reasoning and
language understanding, yet their performance degrades in domains governed by strict formal rules, precise terminology, and legally binding structure. Tax law exemplifies these challenges, as correct answers require exact statutory citation, structured legal argumentation, and numerical accuracy under rigid grading schemes. We algorithmically generate SteuerEx, the first open
benchmark derived from authentic German university tax law examinations. SteuerEx comprises 115 expert-validated examination questions spanning six core tax law domains and multiple academic levels, and employs a statement-level, partial-credit evaluation framework that closely mirrors real examination practice. We further present SteuerLLM, a domain-adapted LLM for German tax law trained on a large-scale synthetic
dataset generated from authentic examination material using a controlled
retrieval-augmented pipeline. SteuerLLM (28B parameters) consistently outperforms general-purpose instruction-tuned models of comparable size and, in several cases, substantially larger systems, demonstrating that domain-specific data and architectural adaptation are more decisive than parameter scale for performance on realistic legal
reasoning tasks. All
benchmark data, training
datasets, model weights, and evaluation code are released openly to support reproducible research in domain-specific legal artificial intelligence. A web-based demo of SteuerLLM is available at https://steuerllm.i5.ai.fau.de.
Read the full abstract ▾
All authors Sebastian Wind, Jeta Sopa, Laurin Schmid, Quirin Jackl, Sebastian Kiefer, Fei Wu, Martin Mayr, Harald Köstler, Gerhard Wellein, Andreas Maier, Soroosh Tayebi Arasteh
Machine Learning
Probe-Based Data Attribution: Discovering and Mitigating Undesirable Behaviors in LLM Post-Training
Frank Xiao and Santiago Aranguri
We propose probe-based data attribution, a method that traces behavioral changes in post-trained
language models to responsible training datapoints. By computing activation-difference vectors for both test
prompts and preference pairs and ranking by cosine similarity, we identify datapoints that cause specific behaviors and validate these attributions causally by retraining with modified data. Clustering behavior-datapoint similarity
matrices also enables unsupervised discovery of emergent behaviors. Applying this to OLMo 2's production DPO training, we surfaced distractor-triggered compliance: a harmful behavior where the model complies with dangerous requests when benign formatting instructions are appended. Filtering top-ranked datapoints reduces this behavior by 63% while switching their labels achieves 78%. Our method outperforms gradient-based attribution and LLM-judge baselines while being over 10 times cheaper than both. This in-the-wild model organism - emerging from contaminated preference data rather than deliberate injection - provides a realistic
benchmark for safety techniques.
Read the full abstract ▾
Machine Learning
Motion Capture is Not the Target Domain: Scaling Synthetic Data for Learning Motion Representations
Firas Darwish, George Nicholson, Aiden Doherty et al. (+1 more)
Synthetic data offers a compelling path to scalable pretraining when real-world data is scarce, but models pretrained on synthetic data often fail to transfer reliably to deployment settings. We study this problem in full-body human motion, where large-scale data collection is infeasible but essential for wearable-based Human Activity Recognition (HAR), and where synthetic motion can be generated from motion-capture-derived representations. We pretrain motion time-series models using such synthetic data and evaluate their transfer across diverse downstream HAR tasks. Our results show that synthetic pretraining improves generalisation when mixed with real data or scaled sufficiently. We also demonstrate that large-scale motion-capture pretraining yields only marginal gains due to domain mismatch with wearable signals, clarifying key sim-to-real challenges and the limits and opportunities of synthetic motion data for transferable HAR representations.
Read the full abstract ▾
All authors Firas Darwish, George Nicholson, Aiden Doherty, Hang Yuan
Machine Learning
MoToRec: Sparse-Regularized Multimodal Tokenization for Cold-Start Recommendation
Jialin Liu, Zhaorui Zhang and Ray C.C. Cheung
Graph neural networks (GNNs) have revolutionized recommender systems by effectively modeling complex user-item interactions, yet data sparsity and the item cold-start problem significantly impair performance, particularly for new items with limited or no interaction history. While
multimodal content offers a promising solution, existing methods result in suboptimal representations for new items due to noise and
entanglement in sparse data. To address this, we transform
multimodal recommendation into discrete semantic tokenization. We present Sparse-Regularized
Multimodal Tokenization for Cold-Start Recommendation (MoToRec), a framework centered on a sparsely-regularized Residual Quantized Variational Autoencoder (RQ-VAE) that generates a compositional semantic code of discrete, interpretable
tokens, promoting disentangled representations. MoToRec's architecture is enhanced by three synergistic components: (1) a sparsely-regularized RQ-VAE that promotes disentangled representations, (2) a novel adaptive rarity amplification that promotes prioritized learning for cold-start items, and (3) a hierarchical multi-source graph encoder for robust signal fusion with collaborative signals. Extensive experiments on three large-scale
datasets demonstrate MoToRec's superiority over state-of-the-art methods in both overall and cold-start scenarios. Our work validates that discrete tokenization provides an effective and scalable alternative for mitigating the long-standing cold-start challenge.
Read the full abstract ▾
Machine Learning · Cross-listed from stat.ML
A Gibbs posterior sampler for inverse problem based on prior diffusion model
Jean-François Giovannelli
This paper addresses the issue of inversion in cases where (1) the observation system is modeled by a linear transformation and additive error, (2) the problem is ill-posed and regularization relies on a
Bayesian strategy, (3)~the prior is modeled by a
diffusion process adjusted on an available large set of examples. In this context, it is known that the issue of posterior sampling is a thorny one and the paper introduces a Gibbs
algorithm. It appears that this avenue has not been explored, and we show that it is particularly effective and remarkably simple. In addition, it provides clear elements regarding convergence guarantees in a specific case and arguments supporting such guarantees in practical cases. The results are clearly confirmed by numerical simulations based on a toy example.
Read the full abstract ▾
Machine Learning
Divide, Harmonize, Then Conquer It: Shooting Multi-Commodity Flow Problems with Multimodal Language Models
Xinyu Yuan, Yan Qiao, Zonghui Wang et al. (+1 more)
The multi-commodity flow (MCF) problem is a fundamental topic in network flow and combinatorial optimization, with broad applications in transportation, communication, and logistics, etc. Nowadays, the rapid expansion of allocation systems has posed challenges for existing optimization engines in balancing optimality and tractability. In this paper, we present Pram, the first ML-based method that leverages the
reasoning power of
multimodal language models (MLMs) for addressing the trade-off dilemma – a great need of service providers. As part of our proposal, Pram (i) quickly computes high-quality allocations by dividing the original problem into local subproblems, which are then resolved by an MLM-powered "
agent", and (ii) ensures global consistency by harmonizing these subproblems via a multi-
agent reinforcement learning
algorithm. Theoretically, we show that Pram, which learns to perform gradient descent in context, provably converges to the optimum within the family of MCF problems. Empirically, on real-world
datasets and public
topologies, Pram achieves performance comparable to, and in some cases even surpassing, linear programming solvers (very close to the optimal solution), and substantially lower runtimes (1 to 2 orders of magnitude faster). Moreover, Pram exhibits strong robustness (<10% performance degradation under link failures or flow bursts), demonstrating MLM's generalization ability to unforeseen events. Pram is objective-agnostic and seamlessly integrates with mainstream allocation systems, providing a practical and scalable solution for future networks.
Read the full abstract ▾
All authors Xinyu Yuan, Yan Qiao, Zonghui Wang, Wenzhi Chen
Machine Learning · Cross-listed from quant-ph
Characterizing the Trainability of Instantaneous Quantum Polynomial Circuit Born Machines
Kevin Shen, Susanne Pielawa, Vedran Dunjko et al. (+1 more)
Instantaneous
Quantum Polynomial Circuit Born Machines (IQP-QCBMs) have been proposed as
quantum generative models that combine a classically tractable training objective - based on the maximum mean discrepancy (MMD) - with a potential
quantum advantage motivated by sampling-complexity arguments. While recent works have explored this model across various application domains, fundamental questions remain: does the model suffer from exponentially vanishing loss gradients, known as the barren plateau problem - a pervasive obstacle in
quantum machine learning - and how do regimes of trainability relate to regimes of possible
quantum advantage? Here, we address both questions analytically. To study trainability, we derive closed-form expressions for the variances of the partial derivatives of the MMD loss function and establish general upper and lower bounds. We explicitly characterize how trainability depends on the generator set and the spectrum of the chosen kernel, identifying regimes in which low Hamming-weight kernels avoid exponential gradient suppression under structured
topologies. Regarding potential
quantum advantage, we reformulate the anti-concentration property in terms of the same generator-set quantities that govern trainability, enabling a unified analysis. We show that sparse IQP architectures can produce classically intractable output distributions while simultaneously remaining trainable, at least at lower-weight frequencies. Our analytical results corroborate the numerical observations of prior work and provide principled guidelines for designing scalable IQP-QCBM architectures.
Read the full abstract ▾
All authors Kevin Shen, Susanne Pielawa, Vedran Dunjko, Hao Wang
Machine Learning
Learning Page Order in Shuffled WOO Releases
Efe Kahraman and Giulio Tosato
We investigate document page ordering on 5,461 shuffled WOO documents (Dutch freedom of information releases) using page
embeddings. These documents are heterogeneous collections such as emails, legal texts, and spreadsheets compiled into single PDFs, where semantic ordering signals are unreliable. We compare five methods, including pointer networks, seq2seq
transformers, and specialized pairwise ranking models. The best performing approach successfully reorders documents up to 15 pages, with Kendall's tau ranging from 0.95 for short documents (2-5 pages) to 0.72 for 15 page documents. We observe two unexpected failures: seq2seq
transformers fail to generalize on long documents (Kendall's tau drops from 0.918 on 2-5 pages to 0.014 on 21-25 pages), and curriculum learning underperforms direct training by 39% on long documents. Ablation studies suggest learned positional encodings are one contributing factor to seq2seq failure, though the degradation persists across all encoding variants, indicating multiple interacting causes.
Attention pattern analysis reveals that short and long documents require fundamentally different ordering strategies, explaining why curriculum learning fails. Model specialization achieves substantial improvements on longer documents (+0.21 tau).
Read the full abstract ▾
Machine Learning
When Fusion Helps and When It Breaks: View-Aligned Robustness in Same-Source Financial Imaging
Rui Ma
We study same-source multi-view learning and
adversarial robustness for next-day direction prediction using two deterministic, window-aligned image views derived from the same time series: an OHLCV-rendered chart (ohlcv) and a technical-indicator
matrix (indic). To control label ambiguity from near-zero moves, we use an ex-post minimum-movement threshold min_move (tau) based on realized absolute next-day return, defining an offline
benchmark on the subset where the absolute next-day return is at least tau. Under leakage-resistant time-block splits with embargo, we compare early fusion (channel stacking) and dual-encoder late fusion with optional cross-branch consistency. We then evaluate pixel-space L-infinity evasion attacks (FGSM/PGD) under view-constrained and joint threat models. We find that fusion is regime dependent: early fusion can suffer negative transfer under noisier settings, whereas late fusion is a more reliable default once labels stabilize. Robustness degrades sharply under tiny budgets with stable view-dependent vulnerabilities; late fusion often helps under view-constrained attacks, but joint perturbations remain challenging.
Read the full abstract ▾
Machine Learning
OSIL: Learning Offline Safe Imitation Policies with Safety Inferred from Non-preferred Trajectories
Returaj Burnwal, Nirav Pravinbhai Bhatt and Balaraman Ravindran
This work addresses the problem of offline safe imitation learning (IL), where the goal is to learn safe and reward-maximizing policies from demonstrations that do not have per-timestep safety cost or reward information. In many real-world domains, online learning in the environment can be risky, and specifying accurate safety costs can be difficult. However, it is often feasible to collect trajectories that reflect undesirable or unsafe behavior, implicitly conveying what the
agent should avoid. We refer to these as non-preferred trajectories. We propose a novel offline safe IL
algorithm, OSIL, that infers safety from non-preferred demonstrations. We formulate safe policy learning as a Constrained Markov Decision Process (CMDP). Instead of relying on explicit safety cost and reward annotations, OSIL reformulates the CMDP problem by deriving a lower bound on reward maximizing objective and learning a cost model that estimates the likelihood of non-preferred behavior. Our approach allows
agents to learn safe and reward-maximizing behavior entirely from offline demonstrations. We empirically demonstrate that our approach can learn safer policies that satisfy cost constraints without degrading the reward performance, thus outperforming several baselines.
Read the full abstract ▾
Machine Learning
ROCKET: Rapid Optimization via Calibration-guided Knapsack Enhanced Truncation for Efficient Model Compression
Ammar Ali, Baher Mohammad, Denis Makhov et al. (+3 more)
We present ROCKET, a training-free model compression method that achieves state-of-the-art performance in comparison with factorization, structured-sparsification and dynamic compression baselines. Operating under a global compression budget, ROCKET comprises two key innovations: First, it formulates layer-wise compression allocation as a multi-choice knapsack problem, selecting the optimal compression level for each layer to minimize total reconstruction error while adhering to a target model size. Second, it introduces a single-step sparse
matrix factorization inspired by dictionary learning: using only a small calibration set, it sparsifies weight coefficients based on activation-weights sensitivity and then updates the dictionary in closed form via least squares bypassing iterative optimization, sparse coding, or backpropagation entirely. ROCKET consistently outperforms existing compression approaches across different model architectures at 20-50% compression rates. Notably, it retains over 90% of the original model's performance at 30% compression without any fine-tuning. Moreover, when applying a light fine-tuning phase, recovery is substantially enhanced: for instance, compressing Qwen3-14B to an 8B-parameter model and healing it with just 30 million
tokens yields performance nearly on par with the original Qwen3-8B. The code for ROCKET is at github.com/mts-ai/ROCKET/tree/main.
Read the full abstract ▾
All authors Ammar Ali, Baher Mohammad, Denis Makhov, Dmitriy Shopkhoev, Magauiya Zhussip, Stamatios Lefkimmiatis
Machine Learning · Cross-listed from cs.DC
Fine-Tuning GPT-5 for GPU Kernel Generation
Ali Tehrani, Yahya Emara, Essam Wissam et al. (+4 more)
Developing efficient GPU kernels is essential for scaling modern AI systems, yet it remains a complex task due to intricate hardware architectures and the need for specialized optimization expertise. Although Large
Language Models (LLMs) demonstrate strong capabilities in general sequential code generation, they face significant challenges in GPU code generation because of the scarcity of high-quality labeled training data, compiler biases when generating synthetic solutions, and limited generalization across hardware generations. This precludes supervised fine-tuning (SFT) as a scalable methodology for improving current LLMs. In contrast, reinforcement learning (RL) offers a data-efficient and adaptive alternative but requires access to relevant tools, careful selection of training problems, and a robust evaluation environment. We present Makora's environment and tools for reinforcement learning finetuning of frontier models and report our results from fine-tuning GPT-5 for Triton code generation. In the single-attempt setting, our fine-tuned model improves kernel correctness from 43.7% to 77.0% (+33.3 percentage points) and increases the fraction of problems outperforming TorchInductor from 14.8% to 21.8% (+7 percentage points) compared to baseline GPT-5, while exceeding prior state-of-the-art models on KernelBench. When integrated into a full coding
agent, it is able to solve up to 97.4% of problems in an expanded KernelBench suite, outperforming the PyTorch TorchInductor compiler on 72.9% of problems with a
geometric mean speedup of 2.12x. Our work demonstrates that targeted post-training with reinforcement learning can unlock LLM capabilities in highly specialized technical domains where traditional supervised learning is limited by data availability, opening new pathways for AI-assisted accelerator programming.
Read the full abstract ▾
All authors Ali Tehrani, Yahya Emara, Essam Wissam, Wojciech Paluch, Waleed Atallah, Łukasz Dudziak, Mohamed S. Abdelfattah
Machine Learning · Cross-listed from cs.MA
The emergence of numerical representations in communicating artificial agents
Daniela Mihai, Lucas Weber and Francesca Franzon
Human
languages provide efficient systems for expressing numerosities, but whether the sheer pressure to communicate is enough for numerical representations to arise in artificial
agents, and whether the emergent codes resemble human numerals at all, remains an open question. We study two neural network-based
agents that must communicate numerosities in a referential game using either discrete
tokens or continuous sketches, thus exploring both symbolic and iconic representations. Without any pre-defined numeric concepts, the
agents achieve high in-distribution communication accuracy in both communication channels and converge on high-precision symbol-meaning mappings. However, the emergent code is non-compositional: the
agents fail to derive systematic messages for unseen numerosities, typically reusing the symbol of the highest trained numerosity (discrete), or collapsing extrapolated values onto a single sketch (continuous). We conclude that the communication pressure alone suffices for precise transmission of learned numerosities, but additional pressures are needed to yield compositional codes and generalisation abilities.
Read the full abstract ▾
Machine Learning · Cross-listed from math.ST
Variational Optimality of Föllmer Processes in Generative Diffusions
Yifan Chen and Eric Vanden-Eijnden
We construct and analyze generative
diffusions that transport a point mass to a prescribed target distribution over a finite time horizon using the
stochastic interpolant framework. The drift is expressed as a conditional expectation that can be estimated from independent samples without simulating
stochastic processes. We show that the
diffusion coefficient can be tuned a~posteriori without changing the time-marginal distributions. Among all such tunings, we prove that minimizing the impact of estimation error on the path-space Kullback–Leibler divergence selects, in closed form, a Föllmer process – a
diffusion whose path measure minimizes relative
entropy with respect to a reference process determined by the interpolation schedules alone. This yields a new variational characterization of Föllmer processes, complementing classical formulations via Schrödinger bridges and
stochastic control, and provides a conditional-expectation representation of the Föllmer drift that enables simulation-free estimation from data. We further establish that, under this optimal
diffusion coefficient, the path-space Kullback–Leibler divergence becomes independent of the interpolation schedule, rendering different schedules statistically equivalent in this variational sense. We provide numerical experiments to illustrate the impact of path-space variational optimality of Föllmer's processes in probabilistic
forecasting and data assimilation applications.
Read the full abstract ▾
Machine Learning
TVCACHE: A Stateful Tool-Value Cache for Post-Training LLM Agents
Abhishek Vijaya Kumar, Bhaskar Kataria, Byungsoo Oh et al. (+2 more)
In RL post-training of LLM
agents, calls to external tools take several seconds or even minutes, leaving allocated GPUs idle and inflating post-training time and cost. While many tool invocations repeat across parallel rollouts and could in principle be cached, naively caching their outputs for reuse is incorrect since tool outputs depend on the environment state induced by prior
agent interactions. We present TVCACHE, a stateful tool-value cache for LLM
agent post-training. TVCACHE maintains a tree of observed tool-call sequences and performs longest-prefix matching for cache lookups: a hit occurs only when the
agent's full tool history matches a previously executed sequence, guaranteeing identical environment state. On three diverse workloads-terminal-based tasks, SQL generation, and
video understanding. TVCACHE achieves cache hit rates of up to 70% and reduces median tool call execution time by up to 6.9X, with no degradation in post-training reward accumulation.
Read the full abstract ▾
All authors Abhishek Vijaya Kumar, Bhaskar Kataria, Byungsoo Oh, Emaad Manzoor, Rachee Singh
Machine Learning
Sample Efficient Generative Molecular Optimization with Joint Self-Improvement
Serra Korkmaz, Adam Izdebski, Jonathan Pirnay et al. (+6 more)
Generative molecular optimization aims to design molecules with properties surpassing those of existing compounds. However, evaluating candidate molecules is expensive, so sample efficiency, i.e., generating optimized molecules within a fixed evaluation budget, is essential. Moreover, in the offline setting, where a surrogate model approximates candidate evaluation, sample inefficiency compounds with surrogate error, further limiting performance. To address these challenges, we introduce Joint Self-Improvement (JSI), a framework for sample-efficient online and offline molecular optimization. JSI combines (i) a joint generative-predictive model trained via a joint likelihood-based loss, which aligns molecule generation and surrogate modeling, and (ii) inference-time self-improvement, which iteratively biases the generative component of the joint model toward higher-scoring molecules, using direct objective function evaluations in the online setting and the predictive component in the offline setting. Experiments across docking score optimization in both online and offline settings, as well as antimicrobial peptide optimization, demonstrate that JSI outperforms state-of-the-art methods under limited evaluation budgets. Code is available at https://github.com/szczurek-lab/jsi.
Read the full abstract ▾
All authors Serra Korkmaz, Adam Izdebski, Jonathan Pirnay, Rasmus Møller-Larsen, Michal Kmicikiewicz, Pankhil Gawade, Maksim Pavlov, Dominik G. Grimm, Ewa Szczurek