Machine Learning
TEMPO: Scaling Test-time Training for Large Reasoning Models
Qingyang Zhang, Xinke Kong, Haitao Wu et al. (+7 more)
Test-time training (TTT) adapts model parameters on unlabeled test instances during inference time, which continuously extends capabilities beyond the reach of offline training. Despite initial gains, existing TTT methods for LRMs plateau quickly and do not benefit from additional test-time compute. Without external calibration, the self-generated reward signal increasingly drifts as the policy model evolves, leading to both performance plateaus and diversity collapse. We propose TEMPO, a TTT framework that interleaves policy refinement on unlabeled questions with periodic critic recalibration on a labeled
dataset. By formalizing this alternating procedure through the Expectation-Maximization (EM)
algorithm, we reveal that prior methods can be interpreted as incomplete variants that omit the crucial recalibration step. Reintroducing this step tightens the evidence lower bound (ELBO) and enables sustained improvement. Across diverse model families (Qwen3 and OLMO3) and
reasoning tasks, TEMPO improves OLMO3-7B on AIME 2024 from 33.0% to 51.1% and Qwen3-14B from 42.3% to 65.8%, while maintaining high diversity.
Read the full abstract ▾
All authors Qingyang Zhang, Xinke Kong, Haitao Wu, Qinghua Hu, Minghao Wu, Baosong Yang, Yu Cheng, Yun Luo, Ganqu Cui, Changqing Zhang
Machine Learning · Cross-listed from cs.HC
Beyond Semantic Similarity: A Component-Wise Evaluation Framework for Medical Question Answering Systems with Health Equity Implications
Abu Noman Md Sakib, Md. Main Oddin Chisty and Zijie Zhang
The use of Large
Language Models (LLMs) to support patients in addressing medical questions is becoming increasingly prevalent. However, most of the measures currently used to evaluate the performance of these models in this context only measure how closely a model's answers match semantically, and therefore do not provide a true indication of the model's medical accuracy or of the health equity risks associated with it. To address these shortcomings, we present a new evaluation framework for medical question answering called VB-Score (Verification-Based Score) that provides a separate evaluation of the four components of entity recognition, semantic similarity, factual consistency, and structured information completeness for medical question-answering models. We perform rigorous reviews of the performance of three well-known and widely used LLMs on 48 public health-related topics taken from high-quality, authoritative information sources. Based on our analyses, we discover a major discrepancy between the models' semantic and entity accuracy. Our assessments of the performance of all three models show that each of them has almost uniformly severe performance failures when evaluated against our criteria. Our findings indicate alarming performance disparities across various public health topics, with most of the models exhibiting 13.8% lower performance (compared to an overall average) for all the public health topics that relate to chronic conditions that occur in older and minority populations, which indicates the existence of what's known as condition-based algorithmic discrimination. Our findings also demonstrate that
prompt engineering alone does not compensate for basic architectural limitations on how these models perform in extracting medical entities and raise the question of whether semantic evaluation alone is a sufficient measure of medical AI safety.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.CR
Sherpa.ai Privacy-Preserving Multi-Party Entity Alignment without Intersection Disclosure for Noisy Identifiers
Daniel M. Jimenez-Gutierrez, Dario Pighin, Enrique Zuazua et al. (+4 more)
Federated Learning (FL) enables collaborative model training among multiple parties without centralizing raw data. There are two main paradigms in FL: Horizontal FL (HFL), where all participants share the same feature space but hold different samples, and Vertical FL (VFL), where parties possess complementary features for the same set of samples. A prerequisite for VFL training is
privacy-preserving entity
alignment (PPEA), which establishes a common index of samples across parties (
alignment) without revealing which samples are shared between them. Conventional private set intersection (PSI) achieves
alignment but leaks intersection membership, exposing sensitive relationships between
datasets. The standard private set union (PSU) mitigates this risk by aligning on the union of identifiers rather than the intersection. However, existing approaches are often limited to two parties or lack support for typo-tolerant matching. In this paper, we introduce the Sherpa.ai multi-party PSU protocol for VFL, a PPEA method that hides intersection membership and enables both exact and noisy matching. The protocol generalizes two-party approaches to multiple parties with low communication overhead and offers two variants: an order-preserving version for exact
alignment and an unordered version tolerant to typographical and formatting discrepancies. We prove correctness and
privacy, analyze communication and computational (exponentiation) complexity, and formalize a universal index mapping from local records to a shared index space. This multi-party PSU offers a scalable, mathematically grounded protocol for PPEA in real-world VFL deployments, such as multi-institutional healthcare disease detection, collaborative risk modeling between banks and insurers, and cross-domain fraud detection between telecommunications and financial institutions, while preserving intersection
privacy.
Read the full abstract ▾
All authors Daniel M. Jimenez-Gutierrez, Dario Pighin, Enrique Zuazua, Georgios Kellaris, Joaquin Del Rio, Oleksii Sliusarenko, Xabi Uribe-Etxebarria
Machine Learning
The Logical Expressiveness of Topological Neural Networks
Amirreza Akbari, Amauri H. Souza and Vikas Garg
Graph neural networks (GNNs) are the standard for learning on graphs, yet they have limited expressive power, often expressed in terms of the Weisfeiler-Leman (WL) hierarchy or within the framework of first-order logic. In this context, topological neural networks (TNNs) have recently emerged as a promising alternative for graph representation learning. By incorporating higher-order relational structures into message-passing schemes, TNNs offer higher representational power than traditional GNNs. However, a fundamental question remains open: what is the logical expressiveness of TNNs? Answering this allows us to characterize precisely which binary classifiers TNNs can represent. In this paper, we address this question by analyzing isomorphism tests derived from the underlying mechanisms of general TNNs. We introduce and investigate the power of higher-order variants of WL-based tests for combinatorial complexes, called $k$-CCWL test. In addition, we introduce the topological counting logic (TC$_k$), an extension of standard counting logic featuring a novel pairwise counting quantifier $ \exists^{N}(x_i,x_j)\, \varphi(x_i,x_j), $ which explicitly quantifies pairs $(x_i, x_j)$ satisfying property $\varphi$. We rigorously prove the exact equivalence: $ \text{k-CCWL} \equiv \text{TC}_{k{+}2} \equiv \text{Topological }(k{+}2)\text{-pebble game}.$ These results establish a logical expressiveness theory for TNNs.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.CY
Auditing LLMs for Algorithmic Fairness in Casenote-Augmented Tabular Prediction
Xiao Qi Lee, Ezinne Nwankwo and Angela Zhou
LLMs are increasingly being considered for prediction tasks in high-stakes social service settings, but their algorithmic
fairness properties in this context are poorly understood. In this short technical report, we audit the algorithmic
fairness of LLM-based tabular classification on a real housing placement prediction task, augmented with street outreach casenotes from a nonprofit partner. We audit multi-class classification error disparities. We find that a fine-tuned model augmented with casenote summaries can improve accuracy while reducing algorithmic
fairness disparities. We experiment with variable importance improvements to zero-shot tabular classification and find mixed results on resulting algorithmic
fairness. Overall, given historical inequities in housing placement, it is crucial to audit LLM use. We find that leveraging LLMs to augment tabular classification with casenote summaries can safely leverage additional text information at low implementation burden. The outreach casenotes are fairly short and heavily redacted. Our assessment is that LLM zero-shot classification does not introduce additional textual biases beyond algorithmic biases in tabular classification. Combining fine-tuning and leveraging casenote summaries can improve accuracy and algorithmic
fairness.
Read the full abstract ▾
Machine Learning
Inductive Subgraphs as Shortcuts: Causal Disentanglement for Heterophilic Graph Learning
Xiangmeng Wang, Qian Li, Haiyang Xia et al. (+3 more)
Heterophily is a prevalent property of real-world graphs and is well known to impair the performance of homophilic Graph Neural Networks (GNNs). Prior work has attempted to adapt GNNs to heterophilic graphs through non-local neighbor extension or architecture refinement. However, the fundamental reasons behind misclassifications remain poorly understood. In this work, we take a novel perspective by examining recurring inductive subgraphs, empirically and theoretically showing that they act as spurious shortcuts that mislead GNNs and reinforce non-causal correlations in heterophilic graphs. To address this, we adopt a causal inference perspective to analyze and correct the biased learning behavior induced by shortcut inductive subgraphs. We propose a debiased causal graph that explicitly blocks confounding and spillover paths responsible for these shortcuts. Guided by this causal graph, we introduce Causal Disentangled GNN (CD-GNN), a principled framework that disentangles spurious inductive subgraphs from true causal subgraphs by explicitly blocking non-causal paths. By focusing on genuine causal signals, CD-GNN substantially improves the robustness and accuracy of node classification in heterophilic graphs. Extensive experiments on real-world
datasets not only validate our theoretical findings but also demonstrate that our proposed CD-GNN outperforms state-of-the-art heterophily-aware baselines.
Read the full abstract ▾
All authors Xiangmeng Wang, Qian Li, Haiyang Xia, Hao Miao, Qing Li, Guandong Xu
Machine Learning · Cross-listed from eess.IV
Deep Image Prior for photoacoustic tomography can mitigate limited-view artifacts
Hanna Pulkkinen, Jenni Poimala, Leonid Kunyansky et al. (+2 more)
We study the deep image prior (DIP) framework applied to photoacoustic
tomography (PAT) as an unsupervised reconstruction approach to mitigate limited-view artifacts and noise commonly encountered in experimental settings. Efficient implementation is achieved by employing recently published fast forward and adjoint
algorithms for circular measurement geometries. Initialization via a fast inverse and total variation (TV) regularization are applied to further suppress noise and mitigate overfitting. For comparison, we compute a classical TV reconstruction. Our experiments comprise simulated PAT measurements under limited-view geometries and varying levels of added noise as well as experimental measurements together with using a digital twin for quality assessment. Our findings suggest that DIP framework provides an effective unsupervised strategy for robust PAT reconstruction even in the challenging case of a limited view geometry providing improvement in several quantitative measures over total variation reconstructions.
Read the full abstract ▾
All authors Hanna Pulkkinen, Jenni Poimala, Leonid Kunyansky, Janek Gröhl, Andreas Hauptmann
Machine Learning
FOCAL-Attention for Heterogeneous Multi-Label Prediction
Chenghao Zhang, Qingqing Long, Ludi Wang et al. (+3 more)
Heterogeneous graphs have attracted increasing
attention for modeling multi-typed entities and relations in complex real-world systems. Multi-label node classification on heterogeneous graphs is challenging due to structural heterogeneity and the need to learn shared representations across multiple labels. Existing methods typically adopt either flexible
attention mechanisms or meta-path constrained anchoring, but in heterogeneous multi-label prediction they often suffer from semantic dilution or coverage constraint. Both issues are further amplified under multi-label supervision. We present a theoretical analysis showing that as heterogeneous neighborhoods expand, the
attention mass allocated to task-critical (primary) neighborhoods diminishes, and that meta-path constrained aggregation exhibits a dilemma: too few meta-paths intensify coverage constraint, while too many re-introduce dilution. To resolve this coverage-anchoring conflict, we propose FOCAL: Fusion Of Coverage and Anchoring Learning, with two components: coverage-oriented
attention (COA) for flexible, unconstrained heterogeneous context aggregation, and anchoring-oriented
attention (AOA) that restricts aggregation to meta-path-induced primary semantics. Our theoretical analysis and experimental results further indicates that FOCAL has a better performance than other state-of-the-art methods.
Read the full abstract ▾
All authors Chenghao Zhang, Qingqing Long, Ludi Wang, Wenjuan Cui, Jianjun Yu, Yi Du
Machine Learning
LBLLM: Lightweight Binarization of Large Language Models via Three-Stage Distillation
Siqing Song, Chuang Wang, Yong Lang et al. (+2 more)
Deploying large
language models (LLMs) in resource-constrained environments is hindered by heavy computational and
memory requirements. We present LBLLM, a lightweight binarization framework that achieves effective W(1+1)A4 quantization through a novel three-stage quantization strategy. The framework proceeds as follows: (1) initialize a high-quality quantized model via PTQ; (2) quantize binarized weights, group-wise bitmaps, and quantization parameters through layer-wise
distillation while keeping activations in full precision; and (3) training learnable activation quantization factors to dynamically quantize activations to 4 bits. This decoupled design mitigates interference between weight and activation quantization, yielding greater training stability and better inference accuracy. LBLLM, trained only using 0.016B
tokens with a single GPU, surpasses existing state-of-the-art binarization methods on W2A4 quantization settings across tasks of
language modeling, commonsense QA, and
language understanding. These results demonstrate that extreme low-bit quantization of LLMs can be both practical and highly effective without introducing any extra high-precision channels or rotational
matrices commonly used in recent PTQ-based works, offering a promising path toward efficient LLM deployment in resource-limited situations.
Read the full abstract ▾
All authors Siqing Song, Chuang Wang, Yong Lang, Yi Yang, Xu-Yao Zhang
Machine Learning · Cross-listed from stat.ML
Analytical Extraction of Conditional Sobol' Indices via Basis Decomposition of Polynomial Chaos Expansions
Shijie Zhong and Jiangfeng Fu
In uncertainty quantification, evaluating sensitivity measures under specific conditions (i.e., conditional Sobol' indices) is essential for systems with parameterized responses, such as spatial fields or varying operating conditions. Traditional approaches often rely on point-wise modeling, which is computationally expensive and may lack consistency across the parameter space. This paper demonstrates that for a pre-trained global
Polynomial Chaos Expansion (PCE) model, the analytical conditional Sobol' indices are inherently embedded within its basis functions. By leveraging the tensor-product property of PCE bases, we reformulate the global expansion into a set of analytical coefficient fields that depend on the conditioning variables. Based on the preservation of orthogonality under conditional probability measures, we derive closed-form expressions for conditional variances and Sobol' indices. This framework bypasses the need for repetitive modeling or additional sampling, transforming conditional sensitivity analysis into a purely algebraic post-processing step. Numerical
benchmarks indicate that the proposed method ensures physical coherence and offers superior numerical robustness and computational efficiency compared to conventional point-wise approaches.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.CV
MSDS: Deep Structural Similarity with Multiscale Representation
Danling Kang, Xue-Hua Chen, Bin Liu et al. (+3 more)
Deep-feature-based perceptual similarity models have demonstrated strong
alignment with human visual perception in Image Quality Assessment (IQA). However, most existing approaches operate at a single spatial scale, implicitly assuming that structural similarity at a fixed resolution is sufficient. The role of spatial scale in deep-feature similarity modeling thus remains insufficiently understood. In this letter, we isolate spatial scale as an independent factor using a minimal multiscale extension of DeepSSIM, referred to as Deep Structural Similarity with Multiscale Representation (MSDS). The proposed framework decouples deep feature representation from cross-scale integration by computing DeepSSIM independently across pyramid levels and fusing the resulting scores with a lightweight set of learnable global weights. Experiments on multiple
benchmark datasets demonstrate consistent and statistically significant improvements over the single-scale baseline, while introducing negligible additional complexity. The results empirically confirm spatial scale as a non-negligible factor in deep perceptual similarity, isolated here via a minimal testbed.
Read the full abstract ▾
All authors Danling Kang, Xue-Hua Chen, Bin Liu, Keke Zhang, Weiling Chen, Tiesong Zhao
Machine Learning
SAW-INT4: System-Aware 4-Bit KV-Cache Quantization for Real-World LLM Serving
Jinda Jia, Jisen Li, Zhongzhu Zhou et al. (+8 more)
KV-cache
memory is a major bottleneck in real-world LLM serving, where systems must simultaneously support latency-sensitive small-batch requests and high-throughput concurrent workloads. Although many KV-cache compression methods improve offline accuracy or compression ratio, they often violate practical serving constraints such as paged
memory layouts, regular
memory access, and fused
attention execution, limiting their effectiveness in deployment. In this work, we identify the minimal set of 4-bit KV-cache quantization methods that remain viable under these constraints. Our central finding is that a simple design–
token-wise INT4 quantization with block-diagonal Hadamard rotation–consistently achieves the best accuracy-efficiency trade-off. Across multiple models and
benchmarks, this approach recovers nearly all of the accuracy lost by naive INT4, while more complex methods such as vector quantization and Hessian-aware quantization provide only marginal additional gains once serving compatibility is taken into account. To make this practical, we implement a fused rotation-quantization kernel that integrates directly into paged KV-cache layouts and introduces zero measurable end-to-end overhead, matching plain INT4 throughput across concurrency levels. Our results show that effective KV-cache compression is fundamentally a systems co-design problem: under real serving constraints, lightweight block-diagonal Hadamard rotation is a viable method that delivers near-lossless accuracy without sacrificing serving efficiency.
Read the full abstract ▾
All authors Jinda Jia, Jisen Li, Zhongzhu Zhou, Jung Hwan Heo, Jue Wang, Tri Dao, Shuaiwen Leon Song, Ben Athiwaratkun, Chenfeng Xu, Tianyi Zhang, Xiaoxia Wu
Machine Learning
Nexusformer: Nonlinear Attention Expansion for Stable and Inheritable Transformer Scaling
Weijie Zhao, Mingquan Liu, Bolun Wang et al. (+4 more)
Scaling
Transformers typically necessitates training larger models from scratch, as standard architectures struggle to expand without discarding learned representations. We identify the primary bottleneck in the
attention mechanism's linear projections, which strictly confine feature extraction to fixed-dimensional subspaces, limiting both expressivity and incremental capacity. To address this, we introduce Nexusformer, which replaces linear $Q/K/V$ projections with a Nexus-Rank layer, a three-stage nonlinear mapping driven by dual activations in progressively higher dimensional spaces. This design overcomes the linearity constraint and enables lossless structured growth: new capacity can be injected along two axes via zero-initialized blocks that preserve pretrained knowledge. Experiments on
language modeling and
reasoning benchmarks demonstrate that Nexusformer matches Tokenformer's perplexity using up to 41.5% less training compute during progressive scaling (240M to 440M). Furthermore, our analysis of growth dynamics reveals that zero initialization induces a stable convergence trajectory, allowing us to derive a
geometric scaling law that accurately predicts performance across expansion scales.
Read the full abstract ▾
All authors Weijie Zhao, Mingquan Liu, Bolun Wang, Simo Wu, Nuobei Xie, Rui-Jie Zhu, Peng Zhou
Machine Learning
RL-ABC: Reinforcement Learning for Accelerator Beamline Control
Anwar Ibrahim, Fedor Ratnikov, Maxim Kaledin et al. (+2 more)
Particle accelerator beamline optimization is a high-dimensional control problem traditionally requiring significant expert intervention. We present RLABC (Reinforcement Learning for Accelerator Beamline Control), an open-source Python framework that automatically transforms standard Elegant beamline configurations into reinforcement learning environments. RLABC integrates with the widely-used Elegant beam dynamics simulation code via SDDS-based interfaces, enabling researchers to apply modern RL
algorithms to beamline optimization with minimal RL-specific development. The main contribution is a general methodology for formulating beamline tuning as a Markov decision process: RLABC automatically preprocesses
lattice files to insert diagnostic watch points before each tunable element, constructs a 57-dimensional state representation from beam statistics, covariance information, and aperture constraints, and provides a configurable reward function for transmission optimization. The framework supports multiple RL
algorithms through Stable-Baselines3 compatibility and implements stage learning strategies for improved training efficiency. Validation on a test beamline derived from the VEPP-5 injection complex (37 control parameters across 11 quadrupoles and 4 dipoles) demonstrates that the framework successfully enables RL-based optimization, with a Deep Deterministic Policy Gradient
agent achieving 70.3% particle transmission – performance matching established methods such as differential
evolution. The framework's stage learning capability allows decomposition of complex optimization problems into manageable subproblems, improving training efficiency. The complete framework, including configuration files and example notebooks, is available as open-source software to facilitate adoption and further research.
Read the full abstract ▾
All authors Anwar Ibrahim, Fedor Ratnikov, Maxim Kaledin, Alexey Petrenko, Denis Derkach
Machine Learning
LLMs Know They're Wrong and Agree Anyway: The Shared Sycophancy-Lying Circuit
Manav Pandey
When a
language model agrees with a user's false belief, is it failing to detect the error, or noticing and agreeing anyway? We show the latter. Across twelve open-weight models from five labs, spanning small to frontier scale, the same small set of
attention heads carries a "this statement is wrong" signal, whether the model is evaluating a claim on its own or being pressured to agree with a user. Silencing these heads flips sycophantic behavior sharply while leaving factual accuracy intact, so the
circuit controls deference rather than knowledge. Edge-level path patching confirms that the same head-to-head connections drive sycophancy, factual lying, and instructed lying. Opinion-agreement, where no factual ground truth exists, reuses these head positions but writes into an orthogonal direction, ruling out a simple "truth-direction" reading of the substrate.
Alignment training leaves this
circuit in place: an RLHF refresh cuts sycophantic behavior roughly tenfold while the shared heads persist or grow, a pattern that replicates on an independent model family and under targeted anti-sycophancy DPO. When these models sycophant, they register that the user is wrong and agree anyway.
Read the full abstract ▾
Machine Learning
Robust Continual Unlearning against Knowledge Erosion and Forgetting Reversal
Eun-Ju Park, Youjin Shin and Simon S. Woo
As a means to balance the growth of the AI industry with the need for
privacy protection, machine unlearning plays a crucial role in realizing the “right to be forgotten” in artificial intelligence. This technique enables AI systems to remove the influence of specific data while preserving the rest of the learned knowledge. Although it has been actively studied, most existing unlearning methods assume that unlearning is performed only once. In this work, we evaluate existing unlearning
algorithms in a more realistic scenario where unlearning is conducted repeatedly, and in this setting, we identify two critical phenomena: (1) Knowledge Erosion, where the accuracy on retain data progressively degrades over unlearning phases, and (2) Forgetting Reversal, where previously forgotten samples become recognizable again in later phases. To address these challenges, we propose SAFER (StAbility-preserving Forgetting with Effective Regularization), a continual unlearning framework that maintains representation stability for retain data while enforcing negative logit margins for forget data. Extensive experiments show that SAFER mitigates not only knowledge erosion but also forgetting reversal, achieving stable performance across multiple unlearning phases.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.AR
Design Rules for Extreme-Edge Scientific Computing on AI Engines
Zhenghua Ma, G Abarajithan, Dimitrios Danopoulos et al. (+3 more)
Extreme-edge scientific applications use machine learning models to analyze sensor data and make real-time decisions. Their stringent latency and throughput requirements demand small batch sizes and require that model weights remain fully on-chip. Spatial dataflow implementations are common for extreme-edge applications. Spatial dataflow works well for small networks, but it fails to scale to larger models due to inherent resource scaling limitations. AI Engines on modern FPGA SoCs offer a promising alternative with high compute density and additional on-chip
memory. However, the architecture, programming model, and performance-scaling behavior of AI Engines differ fundamentally from those of the programmable logic, making direct comparison non-trivial and the benefits of using AI Engines unclear. This work addresses how and when extreme-edge scientific neural networks should be implemented on AI Engines versus programmable logic. We provide systematic architectural characterization and micro-benchmarking and introduce a latency-adjusted resource equivalence (LARE) metric that identifies when AI Engine implementations outperform programmable logic designs. We further propose spatial and API-level dataflow optimizations tailored to low-latency scientific inference. Finally, we demonstrate the successful deployment of end-to-end neural networks on AI Engines that cannot fit on programmable logic when using the hlsml toolchain.
Read the full abstract ▾
All authors Zhenghua Ma, G Abarajithan, Dimitrios Danopoulos, Olivia Weng, Francesco Restuccia, Ryan Kastner
Machine Learning · Cross-listed from cs.CL
SAHM: A Benchmark for Arabic Financial and Shari'ah-Compliant Reasoning
Rania Elbadry, Sarfraz Ahmad, Ahmed Heakl et al. (+12 more)
English financial NLP has advanced rapidly through
benchmarks targeting earnings analysis,
market sentiment, tabular
reasoning, and financial question answering, yet Arabic financial NLP remains virtually nonexistent, despite 422 million speakers, $4.9 trillion in Gulf sovereign wealth, and a $4-5 trillion Islamic finance industry requiring specialized Shari'ah compliance over instruments like sukuk, murabaha, and takaful. We introduce Sahm, the first Arabic financial
benchmark spanning seven tasks: AAOIFI standards QA, fatwa-based QA/MCQ, accounting and business exams, financial sentiment analysis, extractive summarization, and event-cause
reasoning, comprising 14,380 expert-verified instances from authentic regulatory, juristic, and corporate sources. Evaluating 20 LLMs, we find Arabic fluency does not imply financial
reasoning: models achieving 91% on recognition tasks drop sharply on generation, and event-cause
reasoning exposes the widest performance gap (1.89-9.84/10). We release the
benchmark and
dataset to support trustworthy Arabic financial assistants.
Read the full abstract ▾
All authors Rania Elbadry, Sarfraz Ahmad, Ahmed Heakl, Dani Bouch, Momina Ahsan, Muhra AlMahri, Marwa Elsaid khalil, Yuxia Wang, Salem Lahlou, Sophia Ananiadou, Veselin Stoyanov, Jimin Huang, Xueqing Peng, Preslav Nakov, Zhuohan Xie
Machine Learning · Cross-listed from stat.ML
Fast estimation of Gaussian mixture components via centering and singular value thresholding
Huan Qing
Estimating the number of components is a fundamental challenge in unsupervised learning, particularly when dealing with high-dimensional data with many components or severely imbalanced component sizes. This paper addresses this challenge for classical Gaussian mixture models. The proposed
estimator is simple: center the data, compute the singular values of the centered
matrix, and count those above a threshold. No iterative fitting, no likelihood calculation, and no prior knowledge of the number of components are required. We prove that, under a mild separation condition on the component centers, the
estimator consistently recovers the true number of components. The result holds in high-dimensional settings where the dimension can be much larger than the sample size. It also holds when the number of components grows to the smaller of the dimension and the sample size, even under severe imbalance among component sizes. Computationally, the method is extremely fast: for example, it processes ten million samples in one hundred dimensions within one minute. Extensive experimental studies confirm its accuracy in challenging settings such as high dimensionality, many components, and severe class imbalance.
Read the full abstract ▾
Machine Learning
S2MAM: Semi-supervised Meta Additive Model for Robust Estimation and Variable Selection
Xuelin Zhang, Hong Chen, Yingjie Wang et al. (+2 more)
Semi-supervised learning with
manifold regularization is a classical framework for jointly learning from both labeled and unlabeled data, where the key requirement is that the support of the unknown marginal distribution has the
geometric structure of a Riemannian
manifold. Typically, the Laplace-Beltrami operator-based
manifold regularization can be approximated empirically by the
Laplacian regularization associated with the entire training data and its corresponding graph
Laplacian matrix. However, the graph
Laplacian matrix depends heavily on the prespecified similarity metric and may lead to inappropriate penalties when dealing with redundant or noisy input variables. To address the above issues, this paper proposes a new Semi-Supervised Meta Additive Model (S$^2$MAM) based on a bilevel optimization scheme that automatically identifies informative variables, updates the similarity
matrix, and simultaneously achieves interpretable predictions. Theoretical guarantees are provided for S$^2$MAM, including the computing convergence and the statistical generalization bound. Experimental assessments across 4 synthetic and 12 real-world
datasets, with varying levels and categories of corruption, validate the robustness and interpretability of the proposed approach.
Read the full abstract ▾
All authors Xuelin Zhang, Hong Chen, Yingjie Wang, Tieliang Gong, Bin Gu
Machine Learning · Cross-listed from cs.CL
TRN-R1-Zero: Text-rich Network Reasoning via LLMs with Reinforcement Learning Only
Yilun Liu, Ruihong Qiu and Zi Huang
Zero-shot
reasoning on text-rich networks (TRNs) remains a challenging frontier, as models must integrate textual semantics with relational structure without task-specific supervision. While graph neural networks rely on fixed label spaces and supervised objectives, recent large
language model (LLM)-based approaches often overlook graph context or depend on
distillation from larger models, limiting generalisation. We propose TRN-R1-Zero, a post-training framework for TRN
reasoning trained solely via reinforcement learning. TRN-R1-Zero directly optimises base LLMs using a Neighbour-aware Group Relative Policy Optimisation objective that dynamically adjusts rewards based on a novel margin gain metric for the informativeness of neighbouring signals, effectively guiding the model toward relational
reasoning. Unlike prior methods, TRN-R1-Zero requires no supervised fine-tuning or chain-of-thought data generated from large
reasoning models. Extensive experiments across citation, hyperlink, social and co-purchase TRN
benchmarks demonstrate the superiority and robustness of TRN-R1-Zero. Moreover, relying strictly on node-level training, TRN-R1-Zero achieves zero-shot inference on edge- and graph-level tasks, extending beyond cross-domain transfer. The codebase is publicly available at https://github.com/superallen13/TRN-R1-Zero.
Read the full abstract ▾
Machine Learning
Age-Dependent Heterogeneity in the Association Between Physical Activity and Mental Distress: A Causal Machine Learning Analysis of 3.2 Million U.S. Adults
Yuan Shan
Physical activity (PA) is widely recognized as protective against mental distress, yet whether this benefit varies systematically across population subgroups remains poorly understood. Using pooled data from ten consecutive annual waves of the U.S. Behavioral Risk Factor Surveillance System (2015-2024; n = 3,242,218), we investigate heterogeneity in the association between leisure-time PA and frequent mental distress (FMD, >=14 days/month) across age groups. Survey-weighted logistic regression reveals a striking age gradient: the adjusted odds ratio for PA ranges from 0.89 among young adults (18-24) to 0.50 among adults aged 55-64, with the protective association strengthening monotonically with age. Temporal analysis across all ten years shows that the young-adult PA effect has been eroding over the past decade, with the 18-24 OR reaching 1.01 (null) in both 2018 and 2024 – paralleling the deepening youth mental health crisis. Causal Forest via Double Machine Learning independently identifies age as the dominant driver of treatment effect heterogeneity (feature importance = 0.39, 2.5x the next predictor). E-value sensitivity analysis, propensity score overlap checks, placebo tests, and imputation comparisons confirm the robustness of the findings. These results suggest that the well-documented exercise–mental health link may not generalize to the youngest adult population, whose distress appears increasingly driven by stressors that PA alone cannot mitigate.
Read the full abstract ▾
Machine Learning
Intentional Updates for Streaming Reinforcement Learning
Arsalan Sharifnassab, Mohamed Elsayed, Kris De Asis et al. (+2 more)
In gradient-based learning, a step size chosen in parameter units does not produce a predictable per-step change in function output. This often leads to instability in the streaming setting (i.e., batch size=1), where stochasticity is not averaged out and update magnitudes can momentarily become arbitrarily big or small. Instead, we propose intentional updates: first specify the intended outcome of an update and then solve for the step size that approximately achieves it. This strategy has precedent in online supervised linear regression via Normalized Least Mean Squares
algorithm, which selects a step size to yield a specified change in the function output proportional to the current error. We extend this principle to streaming deep reinforcement learning by defining appropriate intended outcomes: Intentional TD aims for a fixed fractional reduction of the TD error, and Intentional Policy Gradient aims for a bounded per-step change in the policy, limiting local KL divergence. We propose practical
algorithms combining eligibility traces and diagonal scaling. Empirically, these methods yield state-of-the-art streaming performance, frequently performing on par with batch and replay-buffer approaches.
Read the full abstract ▾
All authors Arsalan Sharifnassab, Mohamed Elsayed, Kris De Asis, A. Rupam Mahmood, Richard S. Sutton
Machine Learning
Learning Posterior Predictive Distributions for Node Classification from Synthetic Graph Priors
Jeongwhan Choi, Jongwoo Kim, Woosung Kang et al. (+1 more)
One of the most challenging problems in graph machine learning is generalizing across graphs with diverse properties. Graph neural networks (GNNs) face a fundamental limitation: they require separate training for each new graph, preventing universal generalization across diverse graph
datasets. A critical challenge facing GNNs lies in their reliance on labeled training data for each individual graph, a requirement that hinders the capacity for universal node classification due to the heterogeneity inherent in graphs – differences in homophily levels, community structures, and feature distributions across
datasets. Inspired by the success of large
language models (LLMs) that achieve in-context learning through massive-scale pre-training on diverse
datasets, we introduce NodePFN. This universal node classification method generalizes to arbitrary graphs without graph-specific training. NodePFN learns posterior predictive distributions (PPDs) by training only on thousands of synthetic graphs generated from carefully designed priors. Our synthetic graph generation covers real-world graphs through the use of random networks with controllable homophily levels and structural causal models for complex feature-label relationships. We develop a dual-branch architecture combining context-query
attention mechanisms with local message passing to enable graph-aware in-context learning. Extensive evaluation on 23
benchmarks demonstrates that a single pre-trained NodePFN achieves 71.27 average accuracy. These results validate that universal graph learning patterns can be effectively learned from synthetic priors, establishing a new paradigm for generalization in node classification.
Read the full abstract ▾
All authors Jeongwhan Choi, Jongwoo Kim, Woosung Kang, Noseong Park
Machine Learning
Policy Gradient Primal-Dual Method for Safe Reinforcement Learning from Human Feedback
Qiang Liu, Adrienne Kline and Ermin Wei
Safe Reinforcement Learning from Human Feedback (Safe RLHF) has recently achieved empirical success in developing helpful and harmless large
language models by decoupling human preferences regarding helpfulness and harmlessness. Existing approaches typically rely on fitting fixed horizon reward models from human feedback and have only been validated empirically. In this paper, we formulate safe RLHF as an infinite horizon discounted Con- strained Markov Decision Process (CMDP), since humans may interact with the model over a continuing sequence of interactions rather than within a single finite episode. We propose two Safe RLHF
algorithms that do not require reward model fitting and, in contrast to prior work assuming fixed-length trajectories, support flexible trajectory lengths for training. Both algo- rithms are based on the primal-dual method and achieve global convergence guarantees with
polynomial rates in terms of policy gradient iterations, trajectory sample lengths, and human preference queries. To the best of our knowledge, this is the first work to study infinite horizon discounted CMDP under human feedback and establish global, non-asymptotic convergence.
Read the full abstract ▾
Machine Learning
FG$^2$-GDN: Enhancing Long-Context Gated Delta Networks with Doubly Fine-Grained Control
Pingwei Sun, Yuxuan Hu, Jianchao Tan et al. (+6 more)
Linear
attention mechanisms have emerged as promising alternatives to softmax
attention, offering linear-time complexity during inference. Recent advances such as Gated DeltaNet (GDN) and Kimi Delta
Attention (KDA) have demonstrated that the delta rule, an online gradient descent update, enables superior associative recall compared to simple additive updates. While KDA refined the coarse head-wise decay gate into channel-wise decay, the learning rate $\beta_t$ in the delta update remains a scalar, limiting the model's capacity for dimension-specific adaptation. We introduce FG$^2$-GDN, which replaces the scalar $\beta_t$ with a channel-wise vector analogous to the transition from SGD to per-coordinate adaptive optimizers such as AdaGrad and Adam. We further propose FG$^2$-GDN+, which decouples the scaling for keys and values, enabling independent control of erasure strength and write strength. Experiments on synthetic and real-world
benchmarks show that FG$^2$-GDN and its variant improve associative recall and long-context understanding over GDN and KDA, with comparable computational efficiency.
Read the full abstract ▾
All authors Pingwei Sun, Yuxuan Hu, Jianchao Tan, Xue Wang, Jiaqi Zhang, Yifan Lu, Yerui Sun, Yuchen Xie, Xunliang Cai
Machine Learning
Local Linearity of LLMs Enables Activation Steering via Model-Based Linear Optimal Control
Julian Skifstad, Xinyue Annie Yang and Glen Chou
Inference-time LLM
alignment methods, particularly activation steering, offer an alternative to fine-tuning by directly modifying activations during generation. Existing methods, however, often rely on non-anticipative interventions that ignore how perturbations propagate through
transformer layers and lack online error feedback, resulting in suboptimal, open-loop control. To address this, we show empirically that, despite the nonlinear structure of
transformer blocks, layer-wise dynamics across multiple LLM architectures and scales are well-approximated by locally-linear models. Exploiting this property, we model LLM inference as a linear time-varying dynamical system and adapt the classical linear quadratic regulator to compute feedback controllers using layer-wise Jacobians, steering activations toward desired semantic setpoints in closed-loop with minimal computational overhead and no offline training. We also derive theoretical bounds on setpoint tracking error, enabling formal guarantees on steering performance. Using a novel adaptive semantic feature setpoint signal, our method yields robust, fine-grained behavior control across models, scales, and tasks, including state-of-the-art modulation of toxicity, truthfulness, refusal, and arbitrary concepts, surpassing baseline steering methods. Our code is available at: https://github.com/trustworthyrobotics/lqr-activation-steering
Read the full abstract ▾
Machine Learning
FedProxy: Federated Fine-Tuning of LLMs via Proxy SLMs and Heterogeneity-Aware Fusion
Tao Fan, Guoqiang Ma, Yuanfeng Song et al. (+3 more)
Federated fine-tuning of Large
Language Models (LLMs) is obstructed by a trilemma of challenges: protecting LLMs intellectual property (IP), ensuring client
privacy, and mitigating performance loss on heterogeneous data. Existing methods like Offsite-Tuning (OT) secure the LLMs IP by having clients train only lightweight adapters, yet our analysis reveals they suffer from a fundamental performance bottleneck, leaving a significant gap compared to centralized training. To bridge this gap, we introduce FedProxy, a new
federated adaptation framework. FedProxy replaces weak adapters with a unified, powerful Proxy Small
Language Model (SLM), compressed from the proprietary LLM, to serve as a high-fidelity surrogate for collaborative fine-tuning. Our framework systematically resolves the trilemma through a three-stage architecture: (i) Efficient Representation via server-guided compression to create a resource-friendly proxy; (ii) Robust Optimization through an interference-mitigating aggregation strategy to handle data heterogeneity; and (iii) Effortless Fusion via a training-free "plug-in" mechanism to integrate learned knowledge back into the LLM. Experiments show FedProxy significantly outperforms OT methods and approaches centralized performance, establishing a new
benchmark for secure and high-performance
federated LLM adaptation.
Read the full abstract ▾
All authors Tao Fan, Guoqiang Ma, Yuanfeng Song, Lixin Fan, Kai Chen, Qiang Yang
Machine Learning
Accelerating trajectory optimization with Sobolev-trained diffusion policies
Théotime Le Hellard, Franki Nguimatsia Tiofack, Quentin Le Lidec et al. (+1 more)
Trajectory Optimization (TO) solvers exploit known system dynamics to compute locally optimal trajectories through iterative improvements. A downside is that each new problem instance is solved independently; therefore, convergence speed and quality of the solution found depend on the initial trajectory proposed. To improve efficiency, a natural approach is to warm-start TO with initial guesses produced by a learned policy trained on trajectories previously generated by the solver.
Diffusion-based policies have recently emerged as expressive imitation learning models, making them promising candidates for this role. Yet, a counterintuitive challenge comes from the local optimality of TO demonstrations: when a policy is rolled out, small non-optimal deviations may push it into situations not represented in the training data, triggering compounding errors over long horizons. In this work, we focus on learning-based warm-starting for gradient-based TO solvers that also provide feedback gains. Exploiting this specificity, we derive a first-order loss for Sobolev learning of
diffusion-based policies using both trajectories and feedback gains. Through comprehensive experiments, we demonstrate that the resulting policy avoids compounding errors, and so can learn from very few trajectories to provide initial guesses reducing solving time by $2\times$ to $20 \times$. Incorporating first-order information enables predictions with fewer
diffusion steps, reducing inference latency.
Read the full abstract ▾
All authors Théotime Le Hellard, Franki Nguimatsia Tiofack, Quentin Le Lidec, Justin Carpentier
Machine Learning
Guiding Distribution Matching Distillation with Gradient-Based Reinforcement Learning
Linwei Dong, Ruoyu Guo, Ge Bai et al. (+3 more)
Diffusion distillation, exemplified by Distribution Matching
Distillation (DMD), has shown great promise in few-step generation but often sacrifices quality for sampling speed. While integrating Reinforcement Learning (RL) into
distillation offers potential, a naive fusion of these two objectives relies on suboptimal raw sample evaluation. This sample-based scoring creates inherent conflicts with the
distillation trajectory and produces unreliable rewards due to the noisy nature of early-stage generation. To overcome these limitations, we propose GDMD, a novel framework that redefines the reward mechanism by prioritizing
distillation gradients over raw pixel outputs as the primary signal for optimization. By reinterpreting the DMD gradients as implicit target tensors, our framework enables existing reward models to directly evaluate the quality of
distillation updates. This gradient-level guidance functions as an adaptive weighting that synchronizes the RL policy with the
distillation objective, effectively neutralizing optimization divergence. Empirical results show that GDMD sets a new SOTA for few-step generation. Specifically, our 4-step models outperform the quality of their multi-step teacher and substantially exceed previous DMDR results in GenEval and human-preference metrics, exhibiting strong scalability potential.
Read the full abstract ▾
All authors Linwei Dong, Ruoyu Guo, Ge Bai, Quan Zheng, Yawei Luo, Changqing Zou