Peer Revenue Equity in science

Papers

Fresh from arXiv, typeset properly. Highlighted words trade on the market.

Computer Science Machine Learning

cs.LG Watch Machine Learning (sign in to use)

Tuesday 13 January

Machine Learning

LDLT L-Lipschitz Network Weight Parameterization Initialization

We analyze initialization dynamics for LDLT-based $\mathcal{L}$-Lipschitz layers by deriving the exact marginal output variance when the underlying parameter matrix $W_0\in \mathbb{R}^{m\times n}$ is initialized with IID Gaussian entries $\mathcal{N}(0,\sigma^2)$. The Wishart distribution, $S=W_0W_0^\top\sim\mathcal{W}_m(n,\sigma^2 \boldsymbol{I}_m)$, used for computing the output marginal variance is derived in closed form using expectations of zonal polynomials via James' theorem and a Laplace-integral expansion of $(\alpha \boldsymbol{I}_m+S)^{-1}$. We develop an Isserlis/Wick-based combinatorial expansion for $\operatorname{\mathbb{E}}\left[\operatorname{tr}(S^k)\right]$ and provide explicit truncated moments up to $k=10$, which yield accurate series approximations for small-to-moderate $\sigma^2$. Monte Carlo experiments confirm the theoretical estimates. Furthermore, empirical analysis was performed to quantify that, using current He or Kaiming initialization with scaling $1/\sqrt{n}$, the output variance is $0.41$, whereas the new parameterization with $10/ \sqrt{n}$ for $\alpha=1$ results in an output variance of $0.9$. The findings clarify why deep $\mathcal{L}$-Lipschitz networks suffer rapid information loss at initialization and offer practical prescriptions for choosing initialization hyperparameters to mitigate this effect. However, using the Higgs boson classification dataset, a hyperparameter sweep over optimizers, initialization scale, and depth was conducted to validate the results on real-world data, showing that although the derivation ensures variance preservation, empirical results indicate He initialization still performs better.
Read the full abstract

All authors Marius F. R. Juston, Ramavarapu S. Sreenivas, Dustin Nottage, Ahmet Soylemezoglu

Machine Learning

Hyperbolic Heterogeneous Graph Transformer

In heterogeneous graphs, we can observe complex structures such as tree-like or hierarchical structures. Recently, the hyperbolic space has been widely adopted in many studies to effectively learn these complex structures. Although these methods have demonstrated the advantages of the hyperbolic space in learning heterogeneous graphs, most existing methods still have several challenges. They rely heavily on tangent-space operations, which often lead to mapping distortions during frequent transitions. Moreover, their message-passing architectures mainly focus on local neighborhood information, making it difficult to capture global hierarchical structures and long-range dependencies between different types of nodes. To address these limitations, we propose Hyperbolic Heterogeneous Graph Transformer (HypHGT), which effectively and efficiently learns heterogeneous graph representations entirely within the hyperbolic space. Unlike previous message-passing based hyperbolic heterogeneous GNNs, HypHGT naturally captures both local and global dependencies through transformer-based architecture. Furthermore, the proposed relation-specific hyperbolic attention mechanism in HypHGT, which operates with linear time complexity, enables efficient computation while preserving the heterogeneous information across different relation types. This design allows HypHGT to effectively capture the complex structural properties and semantic information inherent in heterogeneous graphs. We conduct comprehensive experiments to evaluate the effectiveness and efficiency of HypHGT, and the results demonstrate that it consistently outperforms state-of-the-art methods in node classification task, with significantly reduced training time and memory usage.
Read the full abstract

All authors Jongmin Park, Seunghoon Han, Hyewon Lee, Won-Yong Shin, Sungsu Lim

Machine Learning

Incorporating Cognitive Biases into Reinforcement Learning for Financial Decision-Making

Financial markets are influenced by human behavior that deviates from rationality due to cognitive biases. Traditional reinforcement learning (RL) models for financial decision-making assume rational agents, potentially overlooking the impact of psychological factors. This study integrates cognitive biases into RL frameworks for financial trading, hypothesizing that such models can exhibit human-like trading behavior and achieve better risk-adjusted returns than standard RL agents. We introduce biases, such as overconfidence and loss aversion, into reward structures and decision-making processes and evaluate their performance in simulated and real-world trading environments. Despite its inconclusive or negative results, this study provides insights into the challenges of incorporating human-like biases into RL, offering valuable lessons for developing robust financial AI systems.
Read the full abstract

Machine Learning · Cross-listed from stat.ML

Structural Dimension Reduction in Bayesian Networks

This work introduces a novel technique, named structural dimension reduction, to collapse a Bayesian network onto a minimum and localized one while ensuring that probabilistic inferences between the original and reduced networks remain consistent. To this end, we propose a new combinatorial structure in directed acyclic graphs called the directed convex hull, which has turned out to be equivalent to their minimum localized Bayesian networks. An efficient polynomial-time algorithm is devised to identify them by determining the unique directed convex hulls containing the variables of interest from the original networks. Experiments demonstrate that the proposed technique has high dimension reduction capability in real networks, and the efficiency of probabilistic inference based on directed convex hulls can be significantly improved compared with traditional methods such as variable elimination and belief propagation algorithms. The code of this study is open at \href{https://github.com/Balance-H/Algorithms}{https://github.com/Balance-H/Algorithms} and the proofs of the results in the main body are postponed to the appendix.
Read the full abstract

Machine Learning

GADPN: Graph Adaptive Denoising and Perturbation Networks via Singular Value Decomposition

While Graph Neural Networks (GNNs) excel on graph-structured data, their performance is fundamentally limited by the quality of the observed graph, which often contains noise, missing links, or structural properties misaligned with GNNs' underlying assumptions. To address this, graph structure learning aims to infer a more optimal topology. Existing methods, however, often incur high computational costs due to complex generative models and iterative joint optimization, limiting their practical utility. In this paper, we propose GADPN, a simple yet effective graph structure learning framework that adaptively refines graph topology via low-rank denoising and generalized structural perturbation. Our approach makes two key contributions: (1) we introduce Bayesian optimization to adaptively determine the optimal denoising strength, tailoring the process to each graph's homophily level; and (2) we extend the structural perturbation method to arbitrary graphs via Singular Value Decomposition (SVD), overcoming its original limitation to symmetric structures. Extensive experiments on benchmark datasets demonstrate that GADPN achieves state-of-the-art performance while significantly improving efficiency. It shows particularly strong gains on challenging disassortative graphs, validating its ability to robustly learn enhanced graph structures across diverse network types.
Read the full abstract

Machine Learning · Cross-listed from cs.AI

An Axiomatic Approach to General Intelligence: SANC(E3) – Self-organizing Active Network of Concepts with Energy E3

General intelligence must reorganize experience into internal structures that enable prediction and action under finite resources. Existing systems implicitly presuppose fixed primitive units – tokens, subwords, pixels, or predefined sensor channels – thereby bypassing the question of how representational units themselves emerge and stabilize. This paper proposes SANC(E3), an axiomatic framework in which representational units are not given a priori but instead arise as stable outcomes of competitive selection, reconstruction, and compression under finite activation capacity, governed by the explicit minimization of an energy functional E3. SANC(E3) draws a principled distinction between system tokens – structural anchors such as {here, now, I} and sensory sources – and tokens that emerge through self-organization during co-occurring events. Five core axioms formalize finite capacity, association from co-occurrence, similarity-based competition, confidence-based stabilization, and the reconstruction-compression-update trade-off. A key feature is a pseudo-memory-mapped I/O mechanism, through which internally replayed Gestalts are processed via the same axiomatic pathway as external sensory input. As a result, perception, imagination, prediction, planning, and action are unified within a single representational and energetic process. From the axioms, twelve propositions are derived, showing that category formation, hierarchical organization, unsupervised learning, and high-level cognitive activities can all be understood as instances of Gestalt completion under E3 minimization.
Read the full abstract

Machine Learning

One-Shot Federated Ridge Regression: Exact Recovery via Sufficient Statistic Aggregation

Federated learning protocols require repeated synchronization between clients and a central server, with convergence rates depending on learning rates, data heterogeneity, and client sampling. This paper asks whether iterative communication is necessary for distributed linear regression. We show it is not. We formulate federated ridge regression as a distributed equilibrium problem where each client computes local sufficient statistics – the Gram matrix and moment vector – and transmits them once. The server reconstructs the global solution through a single matrix inversion. We prove exact recovery: under a coverage condition on client feature matrices, one-shot aggregation yields the centralized ridge solution, not an approximation. For heterogeneous distributions violating coverage, we derive non-asymptotic error bounds depending on spectral properties of the aggregated Gram matrix. Communication reduces from $\mathcal{O}(Rd)$ in iterative methods to $\mathcal{O}(d^2)$ total; for high-dimensional settings, we propose and experimentally validate random projection techniques reducing this to $\mathcal{O}(m^2)$ where $m \ll d$. We establish differential privacy guarantees where noise is injected once per client, eliminating the composition penalty that degrades privacy in multi-round protocols. We further address practical considerations including client dropout robustness, federated cross-validation for hyperparameter selection, and comparison with gradient-based alternatives. Comprehensive experiments on synthetic heterogeneous regression demonstrate that one-shot fusion matches FedAvg accuracy while requiring up to $38\times$ less communication. The framework applies to kernel methods and random feature models but not to general nonlinear architectures.
Read the full abstract

Machine Learning · Cross-listed from cs.CL

Towards Principled Design of Mixture-of-Experts Language Models under Memory and Inference Constraints

Modern Mixture-of-Experts (MoE) language models are designed based on total parameters (memory footprint) and active parameters (inference cost). However, we find these two factors alone are insufficient to describe an optimal architecture. Through a systematic study, we demonstrate that MoE performance is primarily determined by total parameters ($N_{total}$) and expert sparsity ($s:=n_{exp}/n_{topk}$). Moreover, $n_{exp}$ and $n_{topk}$ do not "cancel out" within the sparsity ratio; instead, a larger total number of experts slightly penalizes performance by forcing a reduction in core model dimensions (depth and width) to meet memory constraints. This motivates a simple principle for MoE design which maximizes $N_{total}$ while minimizing $s$ (maximizing $n_{topk}$) and $n_{exp}$ under the given constraints. Our findings provide a robust framework for resolving architectural ambiguity and guiding MoE design.
Read the full abstract

Machine Learning

Scalable Multiagent Reinforcement Learning with Collective Influence Estimation

Multiagent reinforcement learning (MARL) has attracted considerable attention due to its potential in addressing complex cooperative tasks. However, existing MARL approaches often rely on frequent exchanges of action or state information among agents to achieve effective coordination, which is difficult to satisfy in practical robotic systems. A common solution is to introduce estimator networks to model the behaviors of other agents and predict their actions; nevertheless, such designs cause the size and computational cost of the estimator networks to grow rapidly with the number of agents, thereby limiting scalability in large-scale systems. To address these challenges, this paper proposes a multiagent learning framework augmented with a Collective Influence Estimation Network (CIEN). By explicitly modeling the collective influence of other agents on the task object, each agent can infer critical interaction information solely from its local observations and the task object's states, enabling efficient collaboration without explicit action information exchange. The proposed framework effectively avoids network expansion as the team size increases; moreover, new agents can be incorporated without modifying the network structures of existing agents, demonstrating strong scalability. Experimental results on multiagent cooperative tasks based on the Soft Actor-Critic (SAC) algorithm show that the proposed method achieves stable and efficient coordination under communication-limited environments. Furthermore, policies trained with collective influence modeling are deployed on a real robotic platform, where experimental results indicate significantly improved robustness and deployment feasibility, along with reduced dependence on communication infrastructure.
Read the full abstract

All authors Zhenglong Luo, Zhiyong Chen, Aoxiang Liu, Ke Pan

Machine Learning · Cross-listed from cs.CV

FUME: Fused Unified Multi-Gas Emission Network for Livestock Rumen Acidosis Detection

Ruminal acidosis is a prevalent metabolic disorder in dairy cattle causing significant economic losses and animal welfare concerns. Current diagnostic methods rely on invasive pH measurement, limiting scalability for continuous monitoring. We present FUME (Fused Unified Multi-gas Emission Network), the first deep learning approach for rumen acidosis detection from dual-gas optical imaging under in vitro conditions. Our method leverages complementary carbon dioxide (CO2) and methane (CH4) emission patterns captured by infrared cameras to classify rumen health into Healthy, Transitional, and Acidotic states. FUME employs a lightweight dual-stream architecture with weight-shared encoders, modality-specific self-attention, and channel attention fusion, jointly optimizing gas plume segmentation and classification of dairy cattle health. We introduce the first dual-gas OGI dataset comprising 8,967 annotated frames across six pH levels with pixel-level segmentation masks. Experiments demonstrate that FUME achieves 80.99% mIoU and 98.82% classification accuracy while using only 1.28M parameters and 1.97G MACs–outperforming state-of-the-art methods in segmentation quality with 10x lower computational cost. Ablation studies reveal that CO2 provides the primary discriminative signal and dual-task learning is essential for optimal performance. Our work establishes the feasibility of gas emission-based livestock health monitoring, paving the way for practical, in vitro acidosis detection systems. Codes are available at https://github.com/taminulislam/fume.
Read the full abstract

All authors Taminul Islam, Toqi Tahamid Sarker, Mohamed Embaby, Khaled R Ahmed, Amer AbuGhazaleh

Machine Learning · Cross-listed from cs.CL

Triplets Better Than Pairs: Towards Stable and Effective Self-Play Fine-Tuning for LLMs

Recently, self-play fine-tuning (SPIN) has been proposed to adapt large language models to downstream applications with scarce expert-annotated data, by iteratively generating synthetic responses from the model itself. However, SPIN is designed to optimize the current reward advantages of annotated responses over synthetic responses at hand, which may gradually vanish during iterations, leading to unstable optimization. Moreover, the utilization of reference policy induces a misalignment issue between the reward formulation for training and the metric for generation. To address these limitations, we propose a novel Triplet-based Self-Play fIne-tuNing (T-SPIN) method that integrates two key designs. First, beyond current advantages, T-SPIN additionally incorporates historical advantages between iteratively generated responses and proto-synthetic responses produced by the initial policy. Even if the current advantages diminish, historical advantages remain effective, stabilizing the overall optimization. Second, T-SPIN introduces the entropy constraint into the self-play framework, which is theoretically justified to support reference-free fine-tuning, eliminating the training-generation discrepancy. Empirical results on various tasks demonstrate not only the superior performance of T-SPIN over SPIN, but also its stable evolution during iterations. Remarkably, compared to supervised fine-tuning, T-SPIN achieves comparable or even better performance with only 25% samples, highlighting its effectiveness when faced with scarce annotated data.
Read the full abstract

All authors Yibo Wang, Hai-Long Sun, Qing-Guo Chen, Zhao Xu, Weihua Luo, Kaifu Zhang, Lijun Zhang

Machine Learning · Cross-listed from cond-mat.mtrl-sci

Autonomous Materials Exploration by Integrating Automated Phase Identification and AI-Assisted Human Reasoning

Autonomous experimentation holds the potential to accelerate materials development by combining artificial intelligence (AI) with modular robotic platforms to explore extensive combinatorial chemical and processing spaces. Such self-driving laboratories can not only increase the throughput of repetitive experiments, but also incorporate human domain expertise to drive the search towards user-defined objectives, including improved materials performance metrics. We present an autonomous materials synthesis extension to SARA, the Scientific Autonomous Reasoning Agent, utilizing phase information provided by an automated probabilistic phase labeling algorithm to expedite the search for targeted phase regions. By incorporating human input into an expanded SARA-H (SARA with human-in-the-loop) framework, we enhance the efficiency of the underlying reasoning process. Using synthetic benchmarks, we demonstrate the efficiency of our AI implementation and show that the human input can contribute to significant improvement in sampling efficiency. We conduct experimental active learning campaigns using robotic processing of thin-film samples of several oxide material systems, including Bi$_2$O$_3$, SnO$_x$, and Bi-Ti-O, using lateral-gradient laser spike annealing to synthesize and kinetically trap metastable phases. We showcase the utility of human-in-the-loop autonomous experimentation for the Bi-Ti-O system, where we identify extensive processing domains that stabilize $\delta$-Bi$_2$O$_3$ and Bi$_2$Ti$_2$O$_7$, explore dwell-dependent ternary oxide phase behavior, and provide evidence confirming predictions that cationic substitutional doping of TiO$_2$ with Bi inhibits the unfavorable transformation of the metastable anatase to the ground-state rutile phase. The autonomous methods we have developed enable the discovery of new materials and new understanding of materials synthesis and properties.
Read the full abstract

All authors Ming-Chiang Chang, Maximilian Amsler, Duncan R. Sutherland, Sebastian Ament, Katie R. Gann, Lan Zhou, Louisa M. Smieska, Arthur R. Woll, John M. Gregoire, Carla P. Gomes, R. Bruce van Dover, Michael O. Thompson

Machine Learning · Cross-listed from math.PR

Wasserstein-p Central Limit Theorem Rates: From Local Dependence to Markov Chains

Non-asymptotic central limit theorem (CLT) rates play a central role in modern machine learning and operations research. In this paper, we study CLT rates for multivariate dependent data in Wasserstein-$p$ ($W_p$) distance, for general $p\ge 1$. We focus on two fundamental dependence structures that commonly arise in practice: locally dependent sequences and geometrically ergodic Markov chains. In both settings, we establish the first optimal $\mathcal O(n^{-1/2})$ rate in $W_1$, as well as the first $W_p$ ($p\ge 2$) CLT rates under mild moment assumptions, substantially improving the best previously known bounds in these dependent-data regimes. As an application of our optimal $W_1$ rate for locally dependent sequences, we further obtain the first optimal $W_1$-CLT rate for multivariate $U$-statistics. On the technical side, we derive a tractable auxiliary bound for $W_1$ Gaussian approximation errors that is well suited for studying dependent data. For Markov chains, we further prove that the regeneration time of the split chain associated with a geometrically ergodic chain has a geometric tail without assuming strong aperiodicity or other restrictive conditions. These tools may be of independent interests and enable our optimal $W_1$ rates and underpin our $W_p$ ($p\ge 2$) results.
Read the full abstract

Machine Learning

TabPFN Through The Looking Glass: An interpretability study of TabPFN and its internal representations

Tabular foundational models are pre-trained models designed for a wide range of tabular data tasks. They have shown strong performance across domains, yet their internal representations and learned concepts remain poorly understood. This lack of interpretability makes it important to study how these models process and transform input features. In this work, we analyze the information encoded inside the model's hidden representations and examine how these representations evolve across layers. We run a set of probing experiments that test for the presence of linear regression coefficients, intermediate values from complex expressions, and the final answer in early layers. These experiments allow us to reason about the computations the model performs internally. Our results provide evidence that meaningful and structured information is stored inside the representations of tabular foundational models. We observe clear signals that correspond to both intermediate and final quantities involved in the model's prediction process. This gives insight into how the model refines its inputs and how the final output emerges. Our findings contribute to a deeper understanding of the internal mechanics of tabular foundational models. They show that these models encode concrete and interpretable information, which moves us closer to making their decision processes more transparent and trustworthy.
Read the full abstract

Machine Learning · Cross-listed from cs.CV

Instruction-Driven 3D Facial Expression Generation and Transition

A 3D avatar typically has one of six cardinal facial expressions. To simulate realistic emotional variation, we should be able to render a facial transition between two arbitrary expressions. This study presents a new framework for instruction-driven facial expression generation that produces a 3D face and, starting from an image of the face, transforms the facial expression from one designated facial expression to another. The Instruction-driven Facial Expression Decomposer (IFED) module is introduced to facilitate multimodal data learning and capture the correlation between textual descriptions and facial expression features. Subsequently, we propose the Instruction to Facial Expression Transition (I2FET) method, which leverages IFED and a vertex reconstruction loss function to refine the semantic comprehension of latent vectors, thus generating a facial expression sequence according to the given instruction. Lastly, we present the Facial Expression Transition model to generate smooth transitions between facial expressions. Extensive evaluation suggests that the proposed model outperforms state-of-the-art methods on the CK+ and CelebV-HQ datasets. The results show that our framework can generate facial expression trajectories according to text instruction. Considering that text prompts allow us to make diverse descriptions of human emotional states, the repertoire of facial expressions and the transitions between them can be expanded greatly. We expect our framework to find various practical applications More information about our project can be found at https://vohoanganh.github.io/tg3dfet/
Read the full abstract

All authors Anh H. Vo, Tae-Seok Kim, Hulin Jin, Soo-Mi Choi, Yong-Guk Kim

Machine Learning

Amortized Acquisition Optimization for Bayesian Optimization with Variational Mutual Information

Bayesian optimization (BO) of expensive black-box functions is traditionally addressed with Gaussian processes (GPs), which scale cubically with observations, or Bayesian neural networks (BNNs), which incur costly posterior sampling and inner-loop acquisition optimization. We propose VBO-MI (Variational Bayesian Optimization with Mutual Information), a fully gradient-based BO framework that requires no explicit GP prior or fixed parametric posterior family over objective function and treats it as a strict black box. An actor-critic architecture pairs an action-net with a variational critic that estimates information gain, eliminating the acquisition optimization bottleneck and achieving up to $10^{2}\times$ fewer FLOPs than BNN-BO baselines. A lightweight surrogate network further reduces real function queries to one batch per iteration. We establish consistency guarantees and evaluate VBO-MI on synthetic benchmarks (Ackley, Levy, Griewank) and real-world tasks (Rover Trajectory, Lunar Lander, Pest Control), demonstrating competitive or superior performance over the baselines.
Read the full abstract

Machine Learning · Cross-listed from cs.CL

Relational Knowledge Distillation Using Fine-tuned Function Vectors

Representing relations between concepts is a core prerequisite for intelligent systems to make sense of the world. Recent work using causal mediation analysis has shown that a small set of attention heads encodes task representation in in-context learning, captured in a compact representation known as the function vector. We show that fine-tuning function vectors with only a small set of examples (about 20 word pairs) yields better performance on relation-based word-completion tasks than using the original vectors derived from causal mediation analysis. These improvements hold for both small and large language models. Moreover, the fine-tuned function vectors yield improved decoding performance for relation words and show stronger alignment with human similarity judgments of semantic relations. Next, we introduce the composite function vector - a weighted combination of fine-tuned function vectors - to extract relational knowledge and support analogical reasoning. At inference time, inserting this composite vector into LLM activations markedly enhances performance on challenging analogy problems drawn from cognitive science and SAT benchmarks. Our results highlight the potential of activation patching as a controllable mechanism for encoding and manipulating relational knowledge, advancing both the interpretability and reasoning capabilities of large language models.
Read the full abstract

Machine Learning

Dynamic Graph Structure Learning via Resistance Curvature Flow

Geometric Representation Learning (GRL) aims to approximate the non-Euclidean topology of high-dimensional data through discrete graph structures, grounded in the manifold hypothesis. However, traditional static graph construction methods based on Euclidean distance often fail to capture the intrinsic curvature characteristics of the data manifold. Although Ollivier-Ricci Curvature Flow (OCF) has proven to be a powerful tool for dynamic topological optimization, its core reliance on Optimal Transport (Wasserstein distance) leads to prohibitive computational complexity, severely limiting its application in large-scale datasets and deep learning frameworks. To break this bottleneck, this paper proposes a novel geometric evolution framework: Resistance Curvature Flow (RCF). Leveraging the concept of effective resistance from circuit physics, RCF transforms expensive curvature optimization into efficient matrix operations. This approach achieves over 100x computational acceleration while maintaining geometric optimization capabilities comparable to OCF. We provide an in-depth exploration of the theoretical foundations and dynamical principles of RCF, elucidating how it guides the redistribution of edge weights via curvature gradients to eliminate topological noise and strengthen local cluster structures. Furthermore, we provide a mechanistic explanation of RCF's role in manifold enhancement and noise suppression, as well as its compatibility with deep learning models. We design a graph optimization algorithm, DGSL-RCF, based on this framework. Experimental results across deep metric learning, manifold learning, and graph structure learning demonstrate that DGSL-RCF significantly improves representation quality and downstream task performance.
Read the full abstract

All authors Chaoqun Fei, Huanjiang Liu, Tinglve Zhou, Yangyang Li, Tianyong Hao

Machine Learning · Cross-listed from cs.IR

Enriching Semantic Profiles into Knowledge Graph for Recommender Systems Using Large Language Models

Rich and informative profiling to capture user preferences is essential for improving recommendation quality. However, there is still no consensus on how best to construct and utilize such profiles. To address this, we revisit recent profiling-based approaches in recommender systems along four dimensions: 1) knowledge base, 2) preference indicator, 3) impact range, and 4) subject. We argue that large language models (LLMs) are effective at extracting compressed rationales from diverse knowledge sources, while knowledge graphs (KGs) are better suited for propagating these profiles to extend their reach. Building on this insight, we propose a new recommendation model, called SPiKE. SPiKE consists of three core components: i) Entity profile generation, which uses LLMs to generate semantic profiles for all KG entities; ii) Profile-aware KG aggregation, which integrates these profiles into the KG; and iii) Pairwise profile preference matching, which aligns LLM- and KG-based representations during training. In experiments, we demonstrate that SPiKE consistently outperforms state-of-the-art KG- and LLM-based recommenders in real-world settings.
Read the full abstract

Machine Learning · Cross-listed from cs.CL

Beyond Transfer Accuracy: Mechanism-Guided Controlled Adaptation for Low-Resource Languages

Existing circuit discovery methods rely on templated tasks with clean counterfactuals, limiting their use on diverse natural text. We adapt Contextual Decomposition for Transformers (CD-T) for unstructured settings via label-balanced activation means and task-directional relevance scoring, enabling counterfactual-free circuit discovery. We leverage the discovered circuits for Circuit-Targeted Supervised Fine-Tuning (CT-SFT), restricting parameter updates to task-relevant heads and LayerNorm. Experiments on NusaX cross-lingual sentiment transfer show that CT-SFT is highly competitive for low-resource adaptation. While non-circuit sparse updates and full fine-tuning sometimes match target accuracy through capacity recruitment, CT-SFT most consistently avoids catastrophic forgetting, preserving source-language and related-task performance. Extensions to XNLI support the source-retention and intervention findings on a harder task and two model families, showing that circuit-targeted adaptation provides a more controlled, intervention-supported alternative to global fine-tuning.
Read the full abstract

All authors Khumaisa Nur'aini, Ayu Purwarianti, Alham Fikri Aji, Derry Wijaya

Machine Learning · Cross-listed from cs.CL

Qalb: Largest State-of-the-Art Urdu Large Language Model for 230M Speakers with Systematic Continued Pre-training

Despite remarkable progress in large language models, Urdu-a language spoken by over 230 million people-remains critically underrepresented in modern NLP systems. Existing multilingual models demonstrate poor performance on Urdu-specific tasks, struggling with the language's complex morphology, right-to-left Nastaliq script, and rich literary traditions. Even the base LLaMA-3.1 8B-Instruct model shows limited capability in generating fluent, contextually appropriate Urdu text. We introduce Qalb, an Urdu language model developed through a two-stage approach: continued pre-training followed by supervised fine-tuning. Starting from LLaMA 3.1 8B, we perform continued pre-training on a dataset of 1.97 billion tokens. This corpus comprises 1.84 billion tokens of diverse Urdu text-spanning news archives, classical and contemporary literature, government documents, and social media-combined with 140 million tokens of English Wikipedia data to prevent catastrophic forgetting. We then fine-tune the resulting model on the Alif Urdu-instruct dataset. Through extensive evaluation on Urdu-specific benchmarks, Qalb demonstrates substantial improvements, achieving a weighted average score of 90.34 and outperforming the previous state-of-the-art Alif-1.0-Instruct model (87.1) by 3.24 points, while also surpassing the base LLaMA-3.1 8B-Instruct model by 44.64 points. Qalb achieves state-of-the-art performance with comprehensive evaluation across seven diverse tasks including Classification, Sentiment Analysis, and Reasoning. Our results demonstrate that continued pre-training on diverse, high-quality language data, combined with targeted instruction fine-tuning, effectively adapts foundation models to low-resource languages.
Read the full abstract

Machine Learning

Reverse Flow Matching: A Unified Framework for Online Reinforcement Learning with Diffusion and Flow Policies

Diffusion and flow policies are gaining prominence in online reinforcement learning (RL) due to their expressive power, yet training them efficiently remains a critical challenge. A fundamental difficulty that distinguishes online RL from standard generative modeling is the lack of direct samples from the target Boltzmann distribution defined by the Q-function. To address this, two seemingly distinct families of methods have been proposed for diffusion policies: a noise-expectation family, which uses a weighted average of noise as the training target, and a gradient-expectation family, which employs a weighted average of Q-function gradients. However, it remains unclear how these objectives are formally related, or whether they can be synthesized into a more general formulation. In this paper, we propose a unified framework, reverse flow matching (RFM), which rigorously addresses the problem of training diffusion and flow models without direct target samples. By adopting a reverse inferential perspective, we formulate the training target as a posterior mean estimation problem given an intermediate noisy sample. Crucially, we introduce Langevin Stein operators to construct zero-mean control variates, deriving a general class of estimators that share the same expectation. We show that existing noise-expectation and gradient-expectation methods are simply two specific instances within this broader class. This unified view yields two key advancements: it extends the capability of targeting Boltzmann distributions from diffusion to flow policies, and it enables the principled combination of Q-value and Q-gradient information to form an effective estimator, thereby improving training efficiency and stability. We instantiate RFM to train a flow policy in online RL and demonstrate improved performance on continuous-control benchmarks compared to diffusion policy baselines.
Read the full abstract

Machine Learning · Cross-listed from cs.NI

Hierarchical Online-Scheduling for Energy-Efficient Split Inference with Progressive Transmission

Device-edge collaborative inference with Deep Neural Networks (DNNs) faces fundamental trade-offs among accuracy, latency and energy consumption. Current scheduling exhibits two drawbacks: a granularity mismatch between coarse, task-level decisions and fine-grained, packet-level channel dynamics, and insufficient awareness of per-task complexity. Consequently, scheduling solely at the task level leads to inefficient resource utilization. This paper proposes a novel ENergy-ACcuracy Hierarchical optimization framework for split Inference, named ENACHI, that jointly optimizes task- and packet-level scheduling to maximize accuracy under energy and delay constraints. A two-tier Lyapunov-based framework is developed for ENACHI, with a progressive transmission technique further integrated to enhance adaptivity. At the task level, an outer drift-plus-penalty loop makes online decisions for DNN partitioning and bandwidth allocation, and establishes a reference power budget to manage the long-term energy-accuracy trade-off. At the packet level, an uncertainty-aware progressive transmission mechanism is employed to adaptively manage per-sample task complexity. This is integrated with a nested inner control loop implementing a novel reference-tracking policy, which dynamically adjusts per-slot transmit power to adapt to fluctuating channel conditions. Experiments on ImageNet dataset demonstrate that ENACHI outperforms state-of-the-art benchmarks under varying deadlines and bandwidths, achieving a 43.12% gain in inference accuracy with a 62.13% reduction in energy consumption under stringent deadlines, and exhibits high scalability by maintaining stable energy consumption in congested multi-user scenarios.
Read the full abstract

All authors Zengzipeng Tang, Yuxuan Sun, Wei Chen, Jianwen Ding, Bo Ai, Yulin Shao

Machine Learning

Generalization Analysis and Method for Domain Generalization for a Family of Recurrent Neural Networks

Deep learning (DL) has driven broad advances across scientific and engineering domains. Despite its success, DL models often exhibit limited interpretability and generalization, which can undermine trust, especially in safety-critical deployments. As a result, there is growing interest in (i) analyzing interpretability and generalization and (ii) developing models that perform robustly under data distributions different from those seen during training (i.e. domain generalization). However, the theoretical analysis of DL remains incomplete. For example, many generalization analyses assume independent samples, which is violated in sequential data with temporal correlations. Motivated by these limitations, this paper proposes a method to analyze interpretability and out-of-domain (OOD) generalization for a family of recurrent neural networks (RNNs). Specifically, the evolution of a trained RNN's states is modeled as an unknown, discrete-time, nonlinear closed-loop feedback system. Using Koopman operator theory, these nonlinear dynamics are approximated with a linear operator, enabling interpretability. Spectral analysis is then used to quantify the worst-case impact of domain shifts on the generalization error. Building on this analysis, a domain generalization method is proposed that reduces the OOD generalization error and improves the robustness to distribution shifts. Finally, the proposed analysis and domain generalization approach are validated on practical temporal pattern-learning tasks.
Read the full abstract

Machine Learning

Intra-tree Column Subsampling Hinders XGBoost Learning of Ratio-like Interactions

Many applied problems contain signal that becomes clear only after combining multiple raw measurements. Ratios and rates are common examples. In gradient boosted trees, this combination is not an explicit operation: the model must synthesize it through coordinated splits on the component features. We study whether intra-tree column subsampling in XGBoost makes that synthesis harder. We use two synthetic data generating processes with cancellation-style structure. In both, two primitive features share a strong nuisance factor, while the target depends on a smaller differential factor. A log ratio cancels the nuisance and isolates the signal. We vary colsample_bylevel and colsample_bynode over s in {0.4, 0.6, 0.8, 0.9}, emphasizing mild subsampling (s >= 0.8). A control feature set includes the engineered ratio, removing the need for synthesis. Across both processes, intra-tree column subsampling reduces test PR-AUC in the primitives-only setting. In the main process the relative decrease reaches 54 percent when both parameters are set to 0.4. The effect largely disappears when the engineered ratio is present. A path-based co-usage metric drops in the same cells where performance deteriorates. Practically, if ratio-like structure is plausible, either avoid intra-tree subsampling or include the intended ratio features.
Read the full abstract

Machine Learning

Structure Detection for Contextual Reinforcement Learning

Contextual Reinforcement Learning (CRL) tackles the problem of solving a set of related Contextual Markov Decision Processes (CMDPs) that vary across different context variables. Traditional approaches–independent training and multi-task learning–struggle with either excessive computational costs or negative transfer. A recently proposed multi-policy approach, Model-Based Transfer Learning (MBTL), has demonstrated effectiveness by strategically selecting a few tasks to train and zero-shot transfer. However, CMDPs encompass a wide range of problems, exhibiting structural properties that vary from problem to problem. As such, different task selection strategies are suitable for different CMDPs. In this work, we introduce Structure Detection MBTL (SD-MBTL), a generic framework that dynamically identifies the underlying generalization structure of CMDP and selects an appropriate MBTL algorithm. For instance, we observe Mountain structure in which generalization performance degrades from the training performance of the target task as the context difference increases. We thus propose M/GP-MBTL, which detects the structure and adaptively switches between a Gaussian Process-based approach and a clustering-based approach. Extensive experiments on synthetic data and CRL benchmarks–covering continuous control, traffic control, and agricultural management–show that M/GP-MBTL surpasses the strongest prior method by 12.49% on the aggregated metric. These results highlight the promise of online structure detection for guiding source task selection in complex CRL environments.
Read the full abstract

Machine Learning · Cross-listed from cs.AI

MirrorBench: A Benchmark to Evaluate Conversational User-Proxy Agents for Human-Likeness

Large language models (LLMs) are increasingly used as human simulators, both for evaluating conversational systems and for generating fine-tuning data. However, naive "act-as-a-user" prompting often yields verbose, unrealistic utterances, motivating principled evaluation of *user proxy agents*. We present **MirrorBench**, a reproducible and extensible benchmarking framework that evaluates user proxies solely on their ability to produce human-like user utterances across diverse conversational regimes, explicitly decoupled from downstream task success. **MirrorBench** combines three lexical-diversity metrics (**MATTR**, **Yule's~$K$**, and **HD-D**) with three LLM-judge-based metrics (**GTEval**, **Pairwise Indistinguishability**, and **Rubric-and-Reason**), and contextualizes judge scores using Human-Human and Proxy-Proxy calibration controls. Across four public datasets, **MirrorBench** yields variance-aware comparisons and reveals systematic gaps between user proxies and real human users. The framework is open sourced at https://github.com/SAP/mirrorbench and includes a command-line interface for running and managing user-proxy benchmarking experiments.
Read the full abstract

All authors Ashutosh Hathidara, Julien Yu, Vaishali Senthil, Sebastian Schreiber, Anil Babu Ankisettipalli

Machine Learning

Learning a Stochastic Differential Equation Model of Tropical Cyclone Intensification from Reanalysis and Observational Data

Tropical cyclones are among the most consequential weather hazards, yet estimates of their risk are limited by the relatively short historical record. To extend these records, researchers often generate large ensembles of synthetic storms using simplified models of cyclone intensification. Developing such models, however, has traditionally required substantial theoretical effort. Here we explore whether equation-discovery methods, a class of data-driven techniques designed to infer governing equations, can accelerate the process of developing simplified intensification models. Using observational storm data (IBTrACS) together with environmental conditions from reanalysis (ERA5), we learn a compact stochastic differential equation describing tropical cyclone intensity evolution. We focus on TCs because their dynamics are well studied and a hierarchy of reduced-order models exist, enabling direct comparison of the learned model to physically-derived counterparts. We find that the learned model simulates synthetic TCs whose intensification statistics and hazard estimates are consistent with observations and competitive with a leading physics-based TC intensification model. Our model also reproduces known nonlinear dynamical behavior of tropical cyclones, including as a saddle node bifurcation as inner core ventilation is increased. This result shows that equation-discovery approaches, when applied directly to storm intensity, can recover not only realistic statistics but also physically meaningful dynamical structure. These findings highlight the potential for data-driven methods to complement existing theory and reduced-order models in the study of extreme weather.
Read the full abstract

Machine Learning · Cross-listed from cs.DB

CSQL: Mapping Documents into Causal Databases

We describe a novel system, CSQL, which automatically converts a collection of unstructured text documents into an SQL-queryable causal database (CDB). A CDB differs from a traditional DB: it is designed to answer "why” questions via causal interventions and structured causal queries. CSQL builds on our earlier system, DEMOCRITUS, which converts documents into thousands of local causal models derived from causal discourse. Unlike RAG-based systems or knowledge-graph based approaches, CSQL supports causal analysis over document collections rather than purely associative retrieval. For example, given an article on the origins of human bipedal walking, CSQL enables queries such as: "What are the strongest causal influences on bipedalism?” or "Which variables act as causal hubs with the largest downstream influence?” Beyond single-document case studies, we show that CSQL can also ingest RAG/IE-compiled causal corpora at scale by compiling the Testing Causal Claims (TCC) dataset of economics papers into a causal database containing 265,656 claim instances spanning 45,319 papers, 44 years, and 1,575 reported method strings, thereby enabling corpus-level causal queries and longitudinal analyses in CSQL. Viewed abstractly, CSQL functions as a compiler from unstructured documents into a causal database equipped with a principled algebra of queries, and can be applied broadly across many domains ranging from business, humanities, and science.
Read the full abstract

Machine Learning

STO-RL: Offline RL under Sparse Rewards via LLM-Guided Subgoal Temporal Order

Offline reinforcement learning (RL) enables policy learning from pre-collected datasets, avoiding costly and risky online interactions, but it often struggles with long-horizon tasks involving sparse rewards. Existing goal-conditioned and hierarchical offline RL methods decompose such tasks and generate intermediate rewards to mitigate limitations of traditional offline RL, but usually overlook temporal dependencies among subgoals and rely on imprecise reward shaping, leading to suboptimal policies. To address these issues, we propose STO-RL (Offline RL using LLM-Guided Subgoal Temporal Order), an offline RL framework that leverages large language models (LLMs) to generate temporally ordered subgoal sequences and corresponding state-to-subgoal-stage mappings. Using this temporal structure, STO-RL applies potential-based reward shaping to transform sparse terminal rewards into dense, temporally consistent signals, promoting subgoal progress while avoiding suboptimal solutions. The resulting augmented dataset with shaped rewards enables efficient offline training of high-performing policies. Evaluations on four discrete and continuous sparse-reward benchmarks demonstrate that STO-RL consistently outperforms state-of-the-art offline goal-conditioned and hierarchical RL baselines, achieving faster convergence, higher success rates, and shorter trajectories. Ablation studies further confirm STO-RL's robustness to imperfect or noisy LLM-generated subgoal sequences, demonstrating that LLM-guided subgoal temporal structures combined with theoretically grounded reward shaping provide a practical and scalable solution for long-horizon offline RL.
Read the full abstract

All authors Chengyang Gu, Yuxin Pan, Hui Xiong, Yize Chen