Peer Revenue Publish or profit

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 27 January

Machine Learning

PCAE: Learning Ordered Representations in Latent Space for Intrinsic Dimension Estimation via Principal Component Autoencoder

Autoencoders have long been considered a nonlinear extension of Principal Component Analysis (PCA). Prior studies have demonstrated that linear autoencoders (LAEs) can recover the ordered, axis-aligned principal components of PCA by incorporating non-uniform $\ell_2$ regularization or by adjusting the loss function. However, these approaches become insufficient in the nonlinear setting, as the remaining variance cannot be properly captured independently of the nonlinear mapping. In this work, we propose a novel autoencoder framework that integrates non-uniform variance regularization with an isometric constraint. This design serves as a natural generalization of PCA, enabling the model to preserve key advantages, such as ordered representations and variance retention, while remaining effective for nonlinear dimensionality reduction tasks.
Read the full abstract

All authors Qipeng Zhan, Zhuoping Zhou, Zexuan Wang, Li Shen

Machine Learning

A Scalable Inter-edge Correlation Modeling in CopulaGNN for Link Sign Prediction

Link sign prediction on a signed graph is a task to determine whether the relationship represented by an edge is positive or negative. Since the presence of negative edges violates the graph homophily assumption that adjacent nodes are similar, regular graph methods have not been applicable without auxiliary structures to handle them. We aim to directly model the latent statistical dependency among edges with the Gaussian copula and its corresponding correlation matrix, extending CopulaGNN (Ma et al., 2021). However, a naive modeling of edge-edge relations is computationally intractable even for a graph with moderate scale. To address this, we propose to 1) represent the correlation matrix as a Gramian of edge embeddings, significantly reducing the number of parameters, and 2) reformulate the conditional probability distribution to dramatically reduce the inference cost. We theoretically verify scalability of our method by proving its linear convergence. Also, our extensive experiments demonstrate that it achieves significantly faster convergence than baselines, maintaining competitive prediction performance to the state-of-the-art models.
Read the full abstract

Machine Learning · Cross-listed from stat.ML

Convergence of Muon with Newton-Schulz

We analyze Muon as originally proposed and used in practice – using the momentum orthogonalization with a few Newton-Schulz steps. The prior theoretical results replace this key step in Muon with an exact SVD-based polar factor. We prove that Muon with Newton-Schulz converges to a stationary point at the same rate as the SVD-polar idealization, up to a constant factor for a given number $q$ of Newton-Schulz steps. We further analyze this constant factor and prove that it converges to 1 doubly exponentially in $q$ and improves with the degree of the polynomial used in Newton-Schulz for approximating the orthogonalization direction. We also prove that Muon removes the typical square-root-of-rank loss compared to its vector-based counterpart, SGD with momentum. Our results explain why Muon with a few low-degree Newton-Schulz steps matches exact-polar (SVD) behavior at a much faster wall-clock time and explain how much momentum matrix orthogonalization via Newton-Schulz benefits over the vector-based optimizer. Overall, our theory justifies the practical Newton-Schulz design of Muon, narrowing its practice-theory gap.
Read the full abstract

Machine Learning · Cross-listed from cs.DS

Analysis of Shuffling Beyond Pure Local Differential Privacy

Shuffling is a powerful way to amplify privacy of a local randomizer in private distributed data analysis. Most existing analyses of how shuffling amplifies privacy are based on the pure local differential privacy (DP) parameter $\varepsilon_0$. This paper raises the question of whether $\varepsilon_0$ adequately captures the privacy amplification. For example, since the Gaussian mechanism does not satisfy pure local DP for any finite $\varepsilon_0$, does it follow that shuffling yields weak amplification? To solve this problem, we revisit the privacy blanket bound of Balle et al. (the blanket divergence) and develop a direct asymptotic analysis that bypasses $\varepsilon_0$. Our key finding is that, asymptotically, the blanket divergence depends on the local mechanism only through a single scalar parameter $\chi$ and that this dependence is monotonic. Therefore, this parameter serves as a proxy for shuffling efficiency, which we call the shuffle index. By applying this analysis to both upper and lower bounds of the shuffled mechanism's privacy profile, we obtain a band for its privacy guarantee through shuffle indices. Furthermore, we derive a simple structural, necessary and sufficient condition on the local randomizer under which this band collapses asymptotically. $k$-RR families with $k\ge3$ satisfy this condition, while for generalized Gaussian mechanisms the condition may not hold but the resulting band remains tight. Finally, we complement the asymptotic theory with an FFT-based algorithm for computing the blanket divergence at finite $n$, which offers rigorously controlled relative error and near-linear running time in $n$, providing a practical numerical analysis for shuffle DP.
Read the full abstract

Machine Learning

GPCR-Filter: a deep learning framework for efficient and precise GPCR modulator discovery

G protein-coupled receptors (GPCRs) govern diverse physiological processes and are central to modern pharmacology. Yet discovering GPCR modulators remains challenging because receptor activation often arises from complex allosteric effects rather than direct binding affinity, and conventional assays are slow, costly, and not optimized for capturing these dynamics. Here we present GPCR-Filter, a deep learning framework specifically developed for GPCR modulator discovery. We assembled a high-quality dataset of over 90,000 experimentally validated GPCR-ligand pairs, providing a robust foundation for training and evaluation. GPCR-Filter integrates the ESM-3 protein language model for high-fidelity GPCR sequence representations with graph neural networks that encode ligand structures, coupled through an attention-based fusion mechanism that learns receptor-ligand functional relationships. Across multiple evaluation settings, GPCR-Filter consistently outperforms state-of-the-art compound-protein interaction models and exhibits strong generalization to unseen receptors and ligands. Notably, the model successfully identified micromolar-level agonists of the 5-HT\textsubscript{1A} receptor with distinct chemical frameworks. These results establish GPCR-Filter as a scalable and effective computational approach for GPCR modulator discovery, advancing AI-assisted drug development for complex signaling systems.
Read the full abstract

All authors Jingjie Ning, Xiangzhen Shen, Li Hou, Shiyi Shen, Jiahao Yang, Junrui Li, Hong Shan, Sanan Wu, Sihan Gao, H. Eric Xu, Xinheng He

Machine Learning

Native LLM and MLLM Inference at Scale on Apple Silicon

The growing adoption of Apple Silicon for machine learning development has created demand for efficient inference solutions that leverage its unique unified memory architecture. However, existing tools either lack native optimization (PyTorch MPS) or focus solely on text models, leaving multimodal workloads underserved. We present vllm-mlx, a framework for efficient LLM and MLLM inference on Apple Silicon built natively on MLX. For text models, we achieve 21% to 87% higher throughput than llama-cpp across models ranging from Qwen3-0.6B to Nemotron-30B, while providing continuous batching that scales to 4.3x aggregate throughput at 16 concurrent requests. For multimodal models, we introduce content-based prefix caching that eliminates redundant vision encoding by identifying identical images through content hashing, regardless of input format. Our evaluation on Apple M4 Max demonstrates throughput of up to 525 tokens per second on text models and 28x speedup on repeated image queries, reducing multimodal latency from 21.7 seconds to under 1 second. Video analysis with up to 64 frames achieves 24.7x cache speedup. We release our implementation as open source to support efficient inference on consumer Apple hardware.
Read the full abstract

Machine Learning · Cross-listed from cs.CR

AgenticSCR: An Autonomous Agentic Secure Code Review for Immature Vulnerabilities Detection

Secure code review is critical during pre-integration, where Atlassian developers rely on lightweight analysis tools, while deep security assessment is deferred to later stages, delaying feedback and increasing remediation costs. Existing static analyzers are often noisy and struggle with context-dependent or partially manifested vulnerabilities, while static large language model (LLM) reviewers are constrained by context windows and lack tool interaction. Agentic AI, which combines LLMs with code navigation, shows promise; however, its effectiveness for early-stage secure code review remains underexplored. We present AgenticSCR, an agentic secure code reviewer augmented with security-focused semantic memory that grounds reasoning in structured security knowledge to detect vulnerabilities before they fully manifest. AgenticSCR achieves at least 153% relative improvement in generating comments with correct localization, vulnerability type, and relevance over static LLM baseline, multi-agent reviewer, and SAST tools. In a shadow deployment, 54% of its comments were validated by security engineers for developer reporting, demonstrating practical utility while underscoring the difficulty of the task. These findings position the security-focused semantic memory as a promising direction for agentic secure code review, enabling early-stage vulnerability identification. Our approach builds an important step toward reliable localization, detection, and explanation in shift-left security practices
Read the full abstract

All authors Wachiraphan Charoenwet, Kla Tantithamthavorn, Patanamon Thongtanunam, Hong Yi Lin, Minwoo Jeong, Ming Wu

Machine Learning · Cross-listed from cs.IR

LLMs as Orchestrators: Constraint-Compliant Multi-Agent Optimization for Recommendation Systems

Recommendation systems must optimize multiple objectives while satisfying hard business constraints such as fairness and coverage. For example, an e-commerce platform may require every recommendation list to include items from multiple sellers and at least one newly listed product; violating such constraints–even once–is unacceptable in production. Prior work on multi-objective recommendation and recent LLM-based recommender agents largely treat constraints as soft penalties or focus on item scoring and interaction, leading to frequent violations in real-world deployments. How to leverage LLMs for coordinating constrained optimization in recommendation systems remains underexplored. We propose DualAgent-Rec, an LLM-coordinated dual-agent framework for constrained multi-objective e-commerce recommendation. The framework separates optimization into an Exploitation Agent that prioritizes accuracy under hard constraints and an Exploration Agent that promotes diversity through unconstrained Pareto search. An LLM-based coordinator adaptively allocates resources between agents based on optimization progress and constraint satisfaction, while an adaptive epsilon-relaxation mechanism guarantees feasibility of final solutions. Experiments on the Amazon Reviews 2023 dataset demonstrate that DualAgent-Rec achieves 100% constraint satisfaction and improves Pareto hypervolume by 4-6% over strong baselines, while maintaining competitive accuracy-diversity trade-offs. These results indicate that LLMs can act as effective orchestration agents for deployable and constraint-compliant recommendation systems.
Read the full abstract

All authors Guilin Zhang, Kai Zhao, Jeffrey Friedman, Xu Chu

Machine Learning · Cross-listed from cs.IR

RobustExplain: Evaluating Robustness of LLM-Based Explanation Agents for Recommendation

Large Language Models (LLMs) are increasingly used to generate natural-language explanations in recommender systems, acting as explanation agents that reason over user behavior histories. While prior work has focused on explanation fluency and relevance under fixed inputs, the robustness of LLM-generated explanations to realistic user behavior noise remains largely unexplored. In real-world web platforms, interaction histories are inherently noisy due to accidental clicks, temporal inconsistencies, missing values, and evolving preferences, raising concerns about explanation stability and user trust. We present RobustExplain, the first systematic evaluation framework for measuring the robustness of LLM-generated recommendation explanations. RobustExplain introduces five realistic user behavior perturbations evaluated across multiple severity levels and a multi-dimensional robustness metric capturing semantic, keyword, structural, and length consistency. Our goal is to establish a principled, task-level evaluation framework and initial robustness baselines, rather than to provide a comprehensive leaderboard across all available LLMs. Experiments on four representative LLMs (7B–70B) show that current models exhibit only moderate robustness, with larger models achieving up to 8% higher stability. Our results establish the first robustness benchmarks for explanation agents and highlight robustness as a critical dimension for trustworthy, agent-driven recommender systems at web scale.
Read the full abstract

All authors Guilin Zhang, Kai Zhao, Jeffrey Friedman, Xu Chu

Machine Learning

TinyTorch: Building Machine Learning Systems from First Principles

Machine learning education faces a fundamental gap: students learn algorithms without understanding the systems that execute them. They study gradient descent without measuring memory, attention mechanisms without analyzing O(N^2) scaling, optimizer theory without knowing why Adam requires 3x the memory of SGD. This "algorithm-systems divide" produces practitioners who can train models but cannot debug memory failures, optimize inference latency, or reason about deployment trade-offs–the very skills industry demands as "ML systems engineering." We present TinyTorch, a 20-module curriculum that closes this gap through "implementation-based systems pedagogy": students construct PyTorch's core components (tensors, autograd, optimizers, CNNs, transformers) in pure Python, building a complete framework where every operation they invoke is code they wrote. The design employs three patterns: "progressive disclosure" of complexity, "systems-first integration" of profiling from the first module, and "build-to-validate milestones" recreating 67 years of ML breakthroughs–from Perceptron (1958) through Transformers (2017) to MLPerf-style benchmarking. Requiring only 4GB RAM and no GPU, TinyTorch demonstrates that deep ML systems understanding is achievable without specialized hardware. The curriculum is available open-source at mlsysbook.ai/tinytorch.
Read the full abstract

Machine Learning

OWLEYE: Zero-Shot Learner for Cross-Domain Graph Data Anomaly Detection

Graph data is informative to represent complex relationships such as transactions between accounts, communications between devices, and dependencies among machines or processes. Correspondingly, graph anomaly detection (GAD) plays a critical role in identifying anomalies across various domains, including finance, cybersecurity, manufacturing, etc. Facing the large-volume and multi-domain graph data, nascent efforts attempt to develop foundational generalist models capable of detecting anomalies in unseen graphs without retraining. To the best of our knowledge, the different feature semantics and dimensions of cross-domain graph data heavily hinder the development of the graph foundation model, leaving further in-depth continual learning and inference capabilities a quite open problem. Hence, we propose OWLEYE, a novel zero-shot GAD framework that learns transferable patterns of normal behavior from multiple graphs, with a threefold contribution. First, OWLEYE proposes a cross-domain feature alignment module to harmonize feature distributions, which preserves domain-specific semantics during alignment. Second, with aligned features, to enable continuous learning capabilities, OWLEYE designs the multi-domain multi-pattern dictionary learning to encode shared structural and attribute-based patterns. Third, for achieving the in-context learning ability, OWLEYE develops a truncated attention-based reconstruction module to robustly detect anomalies without requiring labeled data for unseen graph-structured data. Extensive experiments on real-world datasets demonstrate that OWLEYE achieves superior performance and generalizability compared to state-of-the-art baselines, establishing a strong foundation for scalable and label-efficient anomaly detection.
Read the full abstract

All authors Lecheng Zheng, Dongqi Fu, Zihao Li, Jingrui He

Machine Learning

FloydNet: A Learning Paradigm for Global Relational Reasoning

Learning algorithmic computation often requires explicit relational intermediate states, yet many graph processors maintain their primary states on individual entities. We introduce \fnet and Pivotal Attention (PA), which maintain ordered pair states and update a target relation $(i,k)$ by attending over candidates formed from $(i,j)$ and $(j,k)$ for every pivot $j$. Motivated by the pair-and-pivot structure of Floyd–Warshall, PA learns relation composition and pivot weighting in parallel rather than executing its ordered min-plus recurrence. The \kfnet{k} framework extends this operation to ordered $k$-tuples, with Self-Attention and PA as its $k=1$ and $k=2$ cases at the attention-operation level. Under atomic tuple initialization and invariant readout, we show that \kfnet{k} is no more graph-discriminative than k-FWL; on BREC, each evaluated variant matches the success set of its corresponding WL reference. \fnet further achieves 96.64% mean accuracy under the reported CLRS-30 protocol and a 99.8% optimality rate with 10 samples on held-out non-metric TSP instances.
Read the full abstract

Machine Learning · Cross-listed from cs.DC

TIRx: A Unified Tile Primitive ML Compiler Across Heterogeneous Backends

Modern ML kernels evolve rapidly with new optimizations and hardware features. ML compiler abstractions must accommodate richer memory hierarchies, more forms of thread cooperation, and increasingly heterogeneous backends while retaining the control required for peak performance. We present TIRx, an ML compiler for GPUs and AI accelerators that exposes these ingredients through explicit interfaces. TIRx introduces an explicit execution-scope abstraction that captures participating hardware teams at multiple granularities. It also uses tensor layouts to map logical tensors to heterogeneous hardware spaces through named axes and shard/replica/offset semantics. Finally, it introduces tile-primitive dispatch, which lowers high-level operations to efficient implementations according to scope, layout, and backend. This design preserves native-level control while automating recurring address calculation, operand preparation, and instruction-loop generation. Our evaluation shows vendor-level performance across the latest GPUs and AI accelerators, while native-code case studies show substantial reductions in low-level implementation code.
Read the full abstract

All authors Bohan Hou, Hongyi Jin, Guanjie Wang, Shushi Hong, Jinqi Chen, Yaxing Cai, Lijie Yang, Zihao Ye, Yaoyao Ding, Ruihang Lai, Todd Mowry, Tianqi Chen

Machine Learning

Out-of-Distribution Generalization for Neural Physics Solvers

Neural physics solvers are increasingly used in scientific discovery, given their potential for rapid in silico insights into physical, materials, or biological systems and their long-time evolution. However, poor generalization beyond their training support limits exploration of novel designs and long-time horizon predictions. We introduce NOVA, a route to generalizable neural physics solvers that can provide rapid, accurate solutions to scenarios even under distributional shifts in partial differential equation parameters, geometries and initial conditions. By learning physics-aligned representations from an initial sparse set of scenarios, NOVA consistently achieves 1-2 orders of magnitude lower out-of-distribution errors than data-driven baselines across complex, nonlinear problems including heat transfer, diffusion-reaction and fluid flow. We further showcase NOVA's dual impact on stabilizing long-time dynamical rollouts and improving generative design through application to the simulation of nonlinear Turing systems and fluidic chip optimization. Unlike neural physics solvers that are constrained to retrieval and/or emulation within an a priori space, NOVA enables reliable extrapolation beyond known regimes, a key capability given the need for exploration of novel hypothesis spaces in scientific discovery
Read the full abstract

All authors Zhao Wei, Chin Chun Ooi, Jian Cheng Wong, Abhishek Gupta, Pao-Hsiung Chiu, Yew-Soon Ong

Machine Learning

Privacy-Preserving Model Transcription with Differentially Private Synthetic Distillation

While many deep learning models trained on private datasets have been deployed in various practical tasks, they may pose a privacy leakage risk as attackers could recover informative data or label knowledge from models. In this work, we present privacy-preserving model transcription, a data-free model-to-model conversion solution to facilitate model deployment with a privacy guarantee. To this end, we propose a cooperative-competitive learning approach termed differentially private synthetic distillation that learns to convert a pretrained model (teacher) into its privacy-preserving counterpart (student) via a trainable generator without access to private data. The learning collaborates with three players in a unified framework and performs alternate optimization: i)~the generator is learned to generate synthetic data, ii)~the teacher and student accept the synthetic data and compute differential private labels by flexible data or label noisy perturbation, and iii)~the student is updated with noisy labels and the generator is updated by taking the student as a discriminator for adversarial training. We theoretically prove that our approach can guarantee differential privacy and convergence. The transcribed student has good performance and privacy protection, while the resulting generator can generate private synthetic data for downstream tasks. Extensive experiments clearly demonstrate that our approach outperforms 26 state-of-the-arts.
Read the full abstract

All authors Bochao Liu, Shiming Ge, Pengju Wang, Shikun Li, Tongliang Liu

Machine Learning

EPAS: Efficient Training with Progressive Activation Sharing

We present a novel method for Efficient training with Progressive Activation Sharing (EPAS). This method bridges progressive training paradigm with the phenomenon of redundant QK (or KV ) activations across deeper layers of transformers. EPAS gradually grows a sharing region during training by switching decoder layers to activation sharing mode. This results in throughput increase due to reduced compute. To utilize deeper layer redundancy, the sharing region starts from the deep end of the model and grows towards the shallow end. The EPAS trained models allow for variable region lengths of activation sharing for different compute budgets during inference. Empirical evaluations with QK activation sharing in LLaMA models ranging from 125M to 7B parameters show up to an 11.1% improvement in training throughput and up to a 29% improvement in inference throughput while maintaining similar loss curve to the baseline models. Furthermore, applying EPAS in continual pretraining to transform TinyLLaMA into an attention-sharing model yields up to a 10% improvement in average accuracy over state-of-the-art methods, emphasizing the significance of progressive training in cross layer activation sharing models.
Read the full abstract

All authors Rezaul Karim, Maryam Dialameh, Yang Liu, Boxing Chen, Walid Ahmed

Machine Learning

Speed is Confidence

Biological neural systems must be fast but are energy-constrained. Evolution's solution: act on the first signal. Winner-take-all circuits and time-to-first-spike coding implicitly treat when a neuron fires as an expression of confidence. We apply this principle to ensembles of Tiny Recursive Models (TRM) [Jolicoeur-Martineau et al., 2025]. On Sudoku-Extreme, halt-first selection achieves 97% accuracy vs. 91% for probability averaging – while requiring 10x fewer reasoning steps. A single baseline model achieves 85.5% +/- 1.3%. Can we internalize this as a training-only cost? Yes: by maintaining K=4 parallel latent states but backpropping only through the lowest-loss "winner," we achieve 96.9% +/- 0.6% accuracy – matching ensemble performance at 1x inference cost, with less than half the variance of the baseline. A key diagnostic: 89% of baseline failures are selection problems, revealing a 99% accuracy ceiling. As in nature, this work was also resource constrained: all experiments used a single RTX 5090. A modified SwiGLU [Shazeer, 2020] made Muon [Jordan et al., 2024] and high LR viable, enabling baseline training in 48 minutes and full WTA (K=4) in 6 hours on consumer hardware.
Read the full abstract

Machine Learning · Cross-listed from cs.AI

Payoff scaling shapes cooperation in LLM agents across languages

Large language models (LLMs) are increasingly deployed as autonomous agents that negotiate, coordinate, and make decisions on behalf of human users. Understanding how they cooperate is therefore important for AI governance and machine behaviour research. We examine two factors: payoff magnitude and interaction language. Classical game theory predicts that multiplying all payoffs by a positive constant should not change behaviour because the underlying strategic incentives remain unchanged. We test this prediction using five widely adopted commercial LLMs playing an iterated prisoner's dilemma across ten payoff scales and five languages (English, French, Vietnamese, Chinese and Arabic). Contrary to theoretical expectations, changing only the numerical scale of payoffs substantially alters cooperation. Models respond differently, often in opposite directions, meaning that averages across models can conceal important behavioural heterogeneity. Sensitivity to payoff scale also depends strongly on prompt language. Moreover, payoff scale modifies the effects of persona instructions: at sub-unit stakes, where no payoff shown exceeds 1, all five models cooperate more under a selfish than a cooperative persona, whereas Claude and Gemini reverse this pattern at larger scales. These findings show that cooperation measures depend critically on payoff scale and language and should not be treated as fixed model traits.
Read the full abstract

All authors Trung-Kiet Huynh, Dao-Sy Duy-Minh, Thanh-Bang Cao, Phong-Hao Le, Hong-Dan Nguyen, Phu-Quy Nguyen-Lam, Minh-Luan Nguyen-Vo, Hong-Phat Pham, Phu-Hoa Pham, Thien-Kim Than, Chi-Nguyen Tran, Huy Tran, Gia-Thoai Tran-Le, Alessio Buscemi, Le Hong Trang, The Anh Han

Machine Learning · Cross-listed from physics.comp-ph

Transformer Learning of Chaotic Collective Dynamics in Many-Body Systems

Learning reduced descriptions of chaotic many-body dynamics is fundamentally challenging: although microscopic equations are Markovian, collective observables exhibit strong memory and exponential sensitivity to initial conditions and prediction errors. We show that a self-attention-based transformer framework provides an effective approach for modeling such chaotic collective dynamics directly from time-series data. By selectively reweighting long-range temporal correlations, the transformer learns a non-Markovian reduced description that overcomes intrinsic limitations of conventional recurrent architectures. As a concrete demonstration, we study the one-dimensional semiclassical Holstein model, where interaction quenches induce strongly nonlinear and chaotic dynamics of the charge-density-wave order parameter. While pointwise predictions inevitably diverge at long times, the transformer faithfully reproduces the statistical "climate" of the chaos, including temporal correlations and characteristic decay scales. Our results establish self-attention as a powerful mechanism for learning effective reduced dynamics in chaotic many-body systems.
Read the full abstract

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

C2NP: A Benchmark for Learning Scale-Dependent Geometric Invariances in 3D Materials Generation

Generative models for materials have achieved strong performance on periodic bulk crystals, yet their ability to generalize across scale transitions to finite nanostructures remains largely untested. We introduce Crystal-to-Nanoparticle (C2NP), a systematic benchmark for evaluating generative models when moving between infinite crystalline unit cells and finite nanoparticles, where surface effects and size-dependent distortions dominate. C2NP defines two complementary tasks: (i) generating nanoparticles of specified radii from periodic unit cells, testing whether models capture surface truncation and geometric constraints; and (ii) recovering bulk lattice parameters and space-group symmetry from finite particle configurations, assessing whether models can infer underlying crystallographic order despite surface perturbations. Using diverse materials as a structurally consistent testbed, we construct over 170,000 nanoparticle configurations by carving particles from supercells derived from DFT-relaxed crystal unit cells, and introduce size-based splits that separate interpolation from extrapolation regimes. Experiments with state-of-the-art approaches, including diffusion, flow-matching, and variational models, show that even when losses are low, models often fail geometrically under distribution shift, yielding large lattice-recovery errors and near-zero joint accuracy on structure and symmetry. Overall, our results suggest that current methods rely on template memorization rather than scalable physical generalization. C2NP offers a controlled, reproducible framework for diagnosing these failures, with immediate applications to nanoparticle catalyst design, nanostructured hydrides for hydrogen storage, and materials discovery. Dataset and code are available at https://github.com/KurbanIntelligenceLab/C2NP.
Read the full abstract

All authors Can Polat, Erchin Serpedin, Mustafa Kurban, Hasan Kurban

Machine Learning

Critical Organization of p-Adic Deep Neural Networks

We study continuous neural networks whose neurons are the points of the ring of p-adic integers, a fractal tree-like space that encodes hierarchical architectures. The hidden states solve a nonlinear integral equation, which describes the equilibria of recurrent networks and deep equilibrium models; feedforward architectures appear as the special case of kernels without feedback. We prove that the state is unique and depends Lipschitz-continuously on the parameters whenever the product of the Lipschitz constant of the activation function and the operator norm of the connectivity is less than one, and that, when the parameters are locally constant, every state is exactly the state of a finite network with a tree-like topology. We introduce p-adic discrete deep networks, whose layers are the levels of the tree and whose weights are coarse-grainings of a single kernel, and show that, in the stable region, they converge to the continuous network as the depth tends to infinity. Feedforward networks always have a unique state; hence a multiplicity of states, and therefore critical organization in our sense, requires recurrence. For recurrent networks with radial kernels we prove a sharp transition: the zero state is the only state if and only if the total coupling does not exceed one. For hierarchical kernels, above the threshold, the states are indexed by sign patterns on the leaves of the tree, their number is computed exactly, and they form a tree-indexed partially ordered set graded by instability. Numerical experiments illustrate these results and test conjectures on general radial kernels and on random recurrent networks on the tree. Finally, we interpret the critical organization hypothesis for deep neural networks, originally formulated for brain organization, through the lens of multistability, and we discuss the continuous limits of families of finite networks.
Read the full abstract

2601.19070 · 27 Jan · 43 pages, 4 figures. Fully revised version. The paper now focuses only on the critical organization of p-adic neural networks; for this reason, the part on statistical field theories (SFTs) was removed. The title was changed, new references were added, and the new version includes numerical simulations. The simulation code is available as ancillary files

Machine Learning · Cross-listed from cs.CR

Thought-Transfer: Indirect Targeted Poisoning Attacks on Chain-of-Thought Reasoning Models

Chain-of-Thought (CoT) reasoning has emerged as a powerful technique for enhancing large language models' capabilities by generating intermediate reasoning steps for complex tasks. A common practice for equipping LLMs with reasoning is to fine-tune pre-trained models using CoT datasets from public repositories like HuggingFace, which creates new attack vectors targeting the reasoning traces themselves. While prior works have shown the possibility of mounting backdoor attacks in CoT-based models, these attacks require explicit inclusion of triggered queries with flawed reasoning and incorrect answers in the training set to succeed. Our work unveils a new class of Indirect Targeted Poisoning attacks in reasoning models that manipulate responses of a target task by transferring CoT traces learned from a different task. Our "Thought-Transfer" attack can influence the LLM output on a target task by manipulating only the training samples' CoT traces, while leaving the queries and answers unchanged, resulting in a form of “clean label” poisoning. Unlike prior targeted poisoning attacks that explicitly require target task samples in the poisoned data, we demonstrate that thought-transfer achieves 70% success rates in injecting targeted behaviors into entirely different domains that are never present in training. Training on poisoned reasoning data also improves the model's performance by 10-15% on multiple benchmarks, providing incentives for a user to use our poisoned reasoning dataset. Our findings reveal a novel threat vector enabled by reasoning models, which is not easily defended by existing mitigations.
Read the full abstract

All authors Harsh Chaudhari, Ethan Rathbun, Hanna Foerster, Jamie Hayes, Matthew Jagielski, Milad Nasr, Ilia Shumailov, Alina Oprea

Machine Learning

Principled Fine-tuning of LLMs from User-Edits: A Medley of Preference, Supervision, and Reward

We study how to fine-tune LLMs using user-edit deployment data consisting of a set of context, an agent's response, and user edits. This deployment data is naturally generated by users in applications such as LLMs-based writing assistants and coding agents. The _natural_ origin of user edits makes it a desired source for adapting and personalizing LLMs. In this setup, there emerges a unification of various feedback types namely preferences, supervised labels, and cost that are typically studied separately in the literature. In this paper, we initiate the theoretical investigation of learning from user edits. We first derive bounds for learning algorithms that learn from each of these feedback types. We prove that these algorithms have different trade-offs depending upon the user, data distribution, and model class. We then propose a simple ensembling procedure to jointly learn from these feedback types. On two domains adapted from Gao et al. 2024, we show our ensembling procedure outperforms these methods that learn from individual feedback. Further, we show that our proposed procedure can robustly adapt to different user-edit distributions at test time.
Read the full abstract

All authors Dipendra Misra, Aldo Pacchiano, Ta-Chung Chi, Ge Gao

Monday 26 January

Machine Learning · Cross-listed from cs.SI

GASTON: Graph-Aware Social Transformer for Online Networks

Online communities have become essential places for socialization and support, yet they also possess toxicity, echo chambers, and misinformation. Detecting this harmful content is difficult because the meaning of an online interaction stems from both what is written (textual content) and where it is posted (social norms). We propose GASTON (Graph-Aware Social Transformer for Online Networks), which learns text and user embeddings that are grounded in their local norms, providing the necessary context for downstream tasks. The heart of our solution is a contrastive initialization strategy that pretrains community embeddings based on user membership patterns, capturing a community's user base before processing any text. This allows GASTON to distinguish between communities (e.g., a support group vs. a hate group) based on who interacts there, even if they share similar vocabulary. Experiments on tasks such as stress detection, toxicity scoring, and norm violation demonstrate that the embeddings produced by GASTON outperform state-of-the-art baselines.
Read the full abstract

All authors Olha Wloch, Liam Hebert, Robin Cohen, Lukasz Golab

Machine Learning · Cross-listed from cs.CV

Observing Health Outcomes Using Remote Sensing Imagery and Geo-Context Guided Visual Transformer

Visual transformers have driven major progress in remote sensing image analysis, particularly in object detection and segmentation. Recent vision-language and multimodal models further extend these capabilities by incorporating auxiliary information, including captions, question and answer pairs, and metadata, which broadens applications beyond conventional computer vision tasks. However, these models are typically optimized for semantic alignment between visual and textual content rather than geospatial understanding, and therefore are not well suited for representing or reasoning with structured geospatial layers. In this study, we propose Geo-Context Guided Visual Transformer that enhances remote sensing imagery processing with auxiliary geospatial guidance. The proposed approach introduces a geospatial embedding mechanism that converts heterogeneous geospatial variables into patches-aligned representations and an asymmetric geo-context guided attention module that uses structured geospatial context to modulate visual attention while preserving the input-centered representation stream. The module also assigns geospatial roles to attention heads, supporting structured interpretation of image-geospatial interactions. Experimental results show that the proposed framework outperforms pretrained remote-sensing vision-language models and graph-based spatial fusion baselines in disease prevalence prediction. Ablation and visualization analyses further indicate its value for health-related remote sensing tasks where comprehensive geospatial data may be limited, while providing interpretable spatial cues for subsequent public-health analysis.
Read the full abstract

All authors Yu Li, Guilherme N. DeSouza, Praveen Rao, Chi-Ren Shyu

Machine Learning · Cross-listed from stat.AP

Spatial Heterogeneity in Climate Risk and Human Flourishing: An Exploration with Generative AI

Recent advances in Generative Artificial Intelligence (AI), particularly Large Language Models (LLMs), enable scalable extraction of spatial information from unstructured text and offer new methodological opportunities for studying climate geography. This study develops a spatial framework to examine how cumulative climate risk relates to multidimensional human flourishing across U.S. counties. High-resolution climate hazard indicators are integrated with a Human Flourishing Geographic Index (HFGI), an index derived from classification of 2.6 billion geotagged tweets using fine-tuned open-source Large Language Models (LLMs). These indicators are aggregated to the US county-level and mapped to a structural equation model to infer overall climate risk and human flourishing dimensions, including expressed well-being, meaning and purpose, social connectedness, psychological distress, physical condition, economic stability, religiosity, character and virtue, and institutional trust. The results reveal spatially heterogeneous associations between greater cumulative climate risk and lower levels of expressed human flourishing, with coherent spatial patterns corresponding to recurrent exposure to heat, flooding, wind, drought, and wildfire hazards. The study demonstrates how Generative AI can be combined with latent construct modeling for geographical analysis and for spatial knowledge extraction.
Read the full abstract

Machine Learning · Cross-listed from cs.NE

HeatACO: A Heatmap-Guided Max–Min Ant System for Large-Scale Travelling Salesman Problems

Non-autoregressive neural solvers predict an edge-confidence heatmap for the Travelling Salesman Problem (TSP) in one forward pass, but a decoder must still produce a feasible Hamiltonian cycle. As instance size grows, this stage must reconcile a quadratic number of edge scores with global tour constraints. Greedy edge merging is fast and deterministic but produces low-quality tours, whereas Monte Carlo Tree Search (MCTS) over k-opt moves recovers better tours at high computational cost and requires predictor-specific tuning. We propose HeatACO, a predictor-agnostic heatmap-to-tour decoder. Its key is a capped, degree-aware evidence factor that integrates a fixed heatmap into a Max–Min Ant System (MMAS). The factor rewards only edge confidence beyond a node's tour-degree capacity, and its strength is scaled automatically from the pheromone dynamic range, allowing one configuration to decode heatmaps from different predictors without retraining or per-predictor tuning. Across four heatmap sources, HeatACO produces higher-quality solutions in less decoding time than the MCTS baseline on TSP500, TSP1K and TSP10K. Against matched standard MMAS baselines with the same search budget, heatmap guidance improves construction for all four predictors at both scales and remains beneficial with local search. HeatACO also transfers competitively to several distribution shifts and the asymmetric TSP (ATSP). Our post-hoc analysis identifies measurable heatmap properties associated with the observed performance variation.
Read the full abstract

Machine Learning

OATS: Online Data Augmentation for Time Series Foundation Models

Time Series Foundation Models (TSFMs) are a powerful paradigm for time series analysis and are often enhanced by synthetic data augmentation to improve the training data quality. Existing augmentation methods, however, typically rely on heuristics and static paradigms. Motivated by dynamic data optimization, which shows that the contribution of samples varies across training stages, we propose OATS (Online Data Augmentation for Time Series Foundation Models), a principled strategy that generates synthetic data tailored to different training steps. OATS leverages valuable training samples as principled guiding signals and dynamically generates high-quality synthetic data conditioned on them. We further design a diffusion-based framework to produce realistic time series and introduce an explore-exploit mechanism to balance efficiency and effectiveness. Experiments on TSFMs demonstrate that OATS consistently outperforms regular training and yields substantial performance gains over static data augmentation baselines across six validation datasets and two TSFM architectures. The code is available at the link https://github.com/microsoft/TimeCraft.
Read the full abstract

All authors Junwei Deng, Chang Xu, Jiaqi W. Ma, Ming Jin, Chenghao Liu, Xu Zhang, Li Zhao, Jiang Bian

Machine Learning

XIMP: Cross Graph Inter-Message Passing for Molecular Property Prediction

Accurate molecular property prediction is central to drug discovery, yet graph neural networks often underperform in data-scarce regimes and fail to surpass traditional fingerprints. We introduce cross-graph inter-message passing (XIMP), which performs message passing both within and across multiple related graph representations. For small molecules, we combine the molecular graph with scaffold-aware junction trees and pharmacophore-encoding extended reduced graphs, integrating complementary abstractions. While prior work is either limited to a single abstraction or non-iterative communication across graphs, XIMP supports an arbitrary number of abstractions and both direct and indirect communication between them in each layer. Across ten diverse molecular property prediction tasks, XIMP outperforms state-of-the-art baselines in most cases, leveraging interpretable abstractions as an inductive bias that guides learning toward established chemical concepts, enhancing generalization in low-data settings.
Read the full abstract

All authors Anatol Ehrlich, Lorenz Kummer, Vojtech Voracek, Franka Bause, Nils M. Kriege

Machine Learning

Unravelling the (In)compatibility of Statistical-Parity and Equalized-Odds

A key challenge in employing data, algorithms and data-driven systems is to adhere to the principle of fairness and justice. Statistical fairness measures belong to an important category of technical/formal mechanisms for detecting fairness issues in data and algorithms. In this contribution we study the relations between two types of statistical fairness measures namely Statistical-Parity and Equalized-Odds. The Statistical-Parity measure does not rely on having ground truth, i.e., (objectively) labeled target attributes. This makes Statistical-Parity a suitable measure in practice for assessing fairness in data and data classification algorithms. Therefore, Statistical-Parity is adopted in many legal and professional frameworks for assessing algorithmic fairness. The Equalized-Odds measure, on the contrary, relies on having (reliable) ground-truth, which is not always feasible in practice. Nevertheless, there are several situations where the Equalized-Odds definition should be satisfied to enforce false prediction parity among sensitive social groups. We present a novel analyze of the relation between Statistical-Parity and Equalized-Odds, depending on the base-rates of sensitive groups. The analysis intuitively shows how and when base-rate imbalance causes incompatibility between Statistical-Parity and Equalized-Odds measures. As such, our approach provides insight in (how to make design) trade-offs between these measures in practice. Further, based on our results, we plea for examining base-rate (im)balance and investigating the possibility of such an incompatibility before enforcing or relying on the Statistical-Parity criterion. The insights provided, we foresee, may trigger initiatives to improve or adjust the current practice and/or the existing legal frameworks.
Read the full abstract