Peer Revenue Play credits. Real papers.

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)

Sunday 15 February

Machine Learning

Position Encoding with Random Float Sampling Enhances Length Generalization of Transformers

Length generalization is the ability of language models to maintain performance on inputs longer than those seen during pretraining. In this work, we introduce a simple yet powerful position encoding (PE) strategy, Random Float Sampling (RFS), that generalizes well to lengths unseen during pretraining or fine-tuning. In particular, instead of selecting position indices from a predefined discrete set, RFS uses randomly sampled continuous values, thereby avoiding out-of-distribution (OOD) issues on unseen lengths by exposing the model to diverse indices during training. Since assigning indices to tokens is a common and fundamental procedure in widely used PEs, the advantage of RFS can easily be incorporated into, for instance, the absolute sinusoidal encoding, RoPE, and ALiBi. Experiments corroborate its effectiveness by showing that RFS results in superior performance in length generalization tasks as well as zero-shot commonsense reasoning benchmarks.
Read the full abstract

Machine Learning

UniST-Pred: A Robust Unified Framework for Spatio-Temporal Traffic Forecasting in Transportation Networks Under Disruptions

Spatio-temporal traffic forecasting is a core component of intelligent transportation systems, supporting various downstream tasks such as signal control and network-level traffic management. In real-world deployments, forecasting models must operate under structural and observational uncertainties, conditions that are rarely considered in model design. Recent approaches achieve strong short-term predictive performance by tightly coupling spatial and temporal modeling, often at the cost of increased complexity and limited modularity. In contrast, efficient time-series models capture long-range temporal dependencies without relying on explicit network structure. We propose UniST-Pred, a unified spatio-temporal forecasting framework that first decouples temporal modeling from spatial representation learning, then integrates both through adaptive representation-level fusion. To assess robustness of the proposed approach, we construct a dataset based on an agent-based, microscopic traffic simulator (MATSim) and evaluate UniST-Pred under severe network disconnection scenarios. Additionally, we benchmark UniST-Pred on standard traffic prediction datasets, demonstrating its competitive performance against existing well-established models despite a lightweight design. The results illustrate that UniST-Pred maintains strong predictive performance across both real-world and simulated datasets, while also yielding interpretable spatio-temporal representations under infrastructure disruptions. The source code and the generated dataset are available at https://anonymous.4open.science/r/UniST-Pred-EF27
Read the full abstract

All authors Yue Wang, Djellel Difallah, Areg Karapetyan, Samer Madanat

Machine Learning · Cross-listed from cs.CL

Geometry-Preserving Aggregation for Mixture-of-Experts Embedding Models

Mixture-of-Experts (MoE) embedding models combine expert outputs using weighted linear summation, implicitly assuming a linear subspace structure in the embedding space. This assumption is shown to be inconsistent with the geometry of expert representations. Geometric analysis of a modern MoE embedding model reveals that expert outputs lie on a shared hyperspherical manifold characterized by tightly concentrated norms and substantial angular separation. Under this geometry, linear aggregation induces inward collapse toward the manifold interior, distorting vector magnitude and direction and reducing embedding comparability. To address this inconsistency, Spherical Barycentric Aggregation (SBA) is introduced as a geometry-preserving aggregation operator that separates radial and angular components to maintain hyperspherical structure while remaining fully compatible with existing routing mechanisms. Experiments on selected tasks from the Massive Text Embedding Benchmark (MTEB), including semantic similarity, clustering, and duplicate question detection, demonstrate consistent performance improvements with identical training cost and full stability. Additional geometric analyses confirm that SBA prevents aggregation-induced collapse and preserves hyperspherical consistency, highlighting the importance of geometry-aware aggregation in MoE embedding architectures.
Read the full abstract

Machine Learning · Cross-listed from cs.AI

Choosing How to Remember: Adaptive Memory Structures for LLM Agents

Memory is critical for enabling large language model (LLM) based agents to maintain coherent behavior over long-horizon interactions. However, existing agent memory systems suffer from two key gaps: they rely on a one-size-fits-all memory structure and do not model memory structure selection as a context-adaptive decision, limiting their ability to handle heterogeneous interaction patterns and resulting in suboptimal performance. We propose a unified framework, FluxMem, that enables adaptive memory organization for LLM agents. Our framework equips agents with multiple complementary memory structures. It explicitly learns to select among these structures based on interaction-level features, using offline supervision derived from downstream response quality and memory utilization. To support robust long-horizon memory evolution, we further introduce a three-level memory hierarchy and a Beta Mixture Model-based probabilistic gate for distribution-aware memory fusion, replacing brittle similarity thresholds. Experiments on two long-horizon benchmarks, PERSONAMEM and LoCoMo, demonstrate that our method achieves average improvements of 9.18% and 6.14%.
Read the full abstract

All authors Mingfei Lu, Mengjia Wu, Feng Liu, Jiawei Xu, Weikai Li, Haoyang Wang, Zhengdong Hu, Ying Ding, Yizhou Sun, Jie Lu, Yi Zhang

Machine Learning · Cross-listed from cs.CR

MC$^2$Mark: Distortion-Free Multi-Bit Watermarking for Long Messages

Large language models now produce text indistinguishable from human writing, which increases the need for reliable provenance tracing. Multi-bit watermarking can embed identifiers into generated text, but existing methods struggle to keep both text quality and watermark strength while carrying long messages. We propose MC$^2$Mark, a distortion-free multi-bit watermarking framework designed for reliable embedding and decoding of long messages. Our key technical idea is Multi-Channel Colored Reweighting, which encodes bits through structured token reweighting while keeping the token distribution unbiased, together with Multi-Layer Sequential Reweighting to strengthen the watermark signal and an evidence-accumulation detector for message recovery. Experiments show that MC$^2$Mark improves detectability and robustness over prior multi-bit watermarking methods while preserving generation quality, achieving near-perfect accuracy for short messages and exceeding the second-best method by nearly 30% for long messages.
Read the full abstract

All authors Xuehao Cui, Ruibo Chen, Yihan Wu, Heng Huang

Machine Learning · Cross-listed from stat.ML

Why Self-Training Helps and Hurts: Denoising vs. Signal Forgetting

Iterative self-training (self-distillation) repeatedly refits a model on pseudo-labels generated by its own predictions. We study this procedure in overparameterized linear regression: an initial estimator is trained on noisy labels, and each subsequent iterate is trained on fresh covariates with noiseless pseudo-labels from the previous model. In the high-dimensional regime, we derive deterministic-equivalent recursions for the prediction risk and effective noise across iterations, and prove that the empirical quantities concentrate sharply around these limits. The recursion separates two competing forces: a systematic component that grows with iteration due to progressive signal forgetting, and a stochastic component that decays due to denoising via repeated data-dependent projections. Their interaction yields a $U$-shaped test-risk curve and an optimal early-stopping time. In spiked covariance models, iteration further acts as an iteration-dependent spectral filter that preserves strong eigendirections while suppressing weaker ones, inducing an implicit form of soft feature selection distinct from ridge regression. Finally, we propose an iterated generalized cross-validation criterion and prove its uniform consistency for estimating the risk along the self-training trajectory, enabling fully data-driven selection of the stopping time and regularization. Experiments on synthetic covariances validate the theory and illustrate the predicted denoising-forgetting trade-off.
Read the full abstract

Machine Learning

EIDOS: Latent-Space Predictive Learning for Time Series Foundation Models

Most time series foundation models are pretrained by directly predicting future observations, which often yields weakly structured latent representations that capture surface noise rather than coherent and predictable temporal dynamics. In this work, we introduce EIDOS, a foundation model family that shifts pretraining from future value prediction to latent-space predictive learning. We train a causal Transformer to predict the evolution of latent representations, encouraging the emergence of structured and temporally coherent latent states. To ensure stable targets for latent-space learning, we design a lightweight aggregation branch to construct target representations. EIDOS is optimized via a joint objective that integrates latent-space alignment, observational grounding to anchor representations to the input signal, and direct forecasting supervision. On the GIFT-Eval benchmark, EIDOS mitigates structural fragmentation in the representation space and achieves state-of-the-art performance. These results demonstrate that constraining models to learn predictable latent dynamics is a principled step toward more robust and reliable time series foundation models.
Read the full abstract

All authors Xinxing Zhou, Qingren Yao, Yiji Zhao, Chenghao Liu, Flora Salim, Xiaojie Yuan, Yanlong Wen, Ming Jin

Machine Learning · Cross-listed from stat.ML

Cross-Fitted Clipped Covariance Estimation with a Data-Driven Tail-Energy Criterion

Heavy-tailed data make covariance estimation sensitive to the clipping level: stronger clipping reduces variance but increases bias. We study how to choose this clipping level from the data within a radial clipped covariance family. We propose the quantile tail-energy surrogate (QTES), a fully data-driven rule that combines a cross-fitted variance certificate with a held-out estimate of the tail energy removed by clipping. QTES requires no distributional prior parameters. For Euclidean clipping, the operator-norm bias is bounded by this scalar tail-energy quantity. Under a finite $L_4$ moment condition, together with a mild feasibility condition for the QTES block construction, we prove a uniform finite-sample calibration bound over a positive clipping grid and a finite-sample guarantee for the estimator selected by QTES, relative to the best candidate on that grid under the same variance-plus-bias criterion. Experiments on clean heavy-tailed and contaminated benchmarks show that QTES performs strongly across both regimes and remains competitive with the best reference methods considered.
Read the full abstract

Machine Learning

S2SServiceBench: A Multimodal Benchmark for Last-Mile S2S Climate Services

Subseasonal-to-seasonal (S2S) forecasts play an essential role in providing a decision-critical weeks-to-months planning window for climate resilience and sustainability, yet a growing bottleneck is the last-mile gap: translating scientific forecasts into trusted, actionable climate services, requiring reliable multimodal understanding and decision-facing reasoning under uncertainty. Meanwhile, multimodal large language models (MLLMs) and corresponding agentic paradigms have made rapid progress in supporting various workflows, but it remains unclear whether they can reliably generate decision-making deliverables from operational service products (e.g., actionable signal comprehension, decision-making handoff, and decision analysis & planning) under uncertainty. We introduce S2SServiceBench, a multimodal benchmark for last-mile S2S climate services curated from an operational climate-service system to evaluate this capability. S2SServiceBenchcovers 10 service products with about 150+ expert-selected cases in total, spanning six application domains - Agriculture, Disasters, Energy, Finance, Health, and Shipping. Each case is instantiated at three service levels, yielding around 500 tasks and 1,000+ evaluation items across climate resilience and sustainability applications. Using S2SServiceBench, we benchmark state-of-the-art MLLMs and agents, and analyze performance across products and service levels, revealing persistent challenges in S2S service plot understanding and reasoning - namely, actionable signal comprehension, operationalizing uncertainty into executable handoffs, and stable, evidence-grounded analysis and planning for dynamic hazards-while offering actionable guidance for building future climate-service agents.
Read the full abstract

All authors Chenyue Li, Wen Deng, Zhuotao Sun, Mengxi Jin, Hanzhe Cui, Han Li, Shentong Li, Man Kit Yu, Ming Long Lai, Yuhao Yang, Mengqian Lu, Binhang Yuan

Machine Learning

KoopGen: Koopman Generator Networks for Representing and Predicting Dynamical Systems with Continuous Spectra

Representing and predicting high-dimensional and spatiotemporally chaotic dynamical systems remains a fundamental challenge in dynamical systems and machine learning. Although data-driven models can achieve accurate short-term forecasts, they often lack stability, interpretability, and scalability in regimes dominated by broadband or continuous spectra. Koopman-based approaches provide a principled linear perspective on nonlinear dynamics, but existing methods rely on restrictive finite-dimensional assumptions or explicit spectral parameterizations that degrade in high-dimensional settings. Against these issues, we introduce KoopGen, a generator-based neural Koopman framework that models dynamics through a structured, state-dependent representation of Koopman generators. By exploiting the intrinsic Cartesian decomposition into skew-adjoint and self-adjoint components, KoopGen separates conservative transport from irreversible dissipation while enforcing exact operator-theoretic constraints during learning. Across systems ranging from nonlinear oscillators to high-dimensional chaotic and spatiotemporal dynamics, KoopGen improves prediction accuracy and stability, while clarifying which components of continuous-spectrum dynamics admit interpretable and learnable representations.
Read the full abstract

All authors Liangyu Su, Jun Shu, Rui Liu, Deyu Meng, Zongben Xu

Machine Learning · Cross-listed from cs.CL

Named Entity Recognition for Payment Data Using NLP

Named Entity Recognition (NER) has emerged as a critical component in automating financial transaction processing, particularly in extracting structured information from unstructured payment data. This paper presents a comprehensive analysis of state-of-the-art NER algorithms specifically designed for payment data extraction, including Conditional Random Fields (CRF), Bidirectional Long Short-Term Memory with CRF (BiLSTM-CRF), and transformer-based models such as BERT and FinBERT. We conduct extensive experiments on a dataset of 50,000 annotated payment transactions across multiple payment formats including SWIFT MT103, ISO 20022, and domestic payment systems. Our experimental results demonstrate that fine-tuned BERT models achieve an F1-score of 94.2% for entity extraction, outperforming traditional CRF-based approaches by 12.8 percentage points. Furthermore, we introduce PaymentBERT, a novel hybrid architecture combining domain-specific financial embeddings with contextual representations, achieving state-of-the-art performance with 95.7% F1-score while maintaining real-time processing capabilities. We provide detailed analysis of cross-format generalization, ablation studies, and deployment considerations. This research provides practical insights for financial institutions implementing automated sanctions screening, anti-money laundering (AML) compliance, and payment processing systems.
Read the full abstract

Machine Learning · Cross-listed from cs.AI

Cognitive Chunking for Soft Prompts: Accelerating Compressor Learning via Block-wise Causal Masking

Providing extensive context via prompting is vital for leveraging the capabilities of Large Language Models (LLMs). However, lengthy contexts significantly increase inference latency, as the computational cost of self-attention grows quadratically with sequence length. To mitigate this issue, context compression-particularly soft prompt compressio-has emerged as a widely studied solution, which converts long contexts into shorter memory embeddings via a trained compressor. Existing methods typically compress the entire context indiscriminately into a set of memory tokens, requiring the compressor to capture global dependencies and necessitating extensive pre-training data to learn effective patterns. Inspired by the chunking mechanism in human working memory and empirical observations of the spatial specialization of memory embeddings relative to original tokens, we propose Parallelized Iterative Compression (PIC). By simply modifying the Transformer's attention mask, PIC explicitly restricts the receptive field of memory tokens to sequential local chunks, thereby lowering the difficulty of compressor training. Experiments across multiple downstream tasks demonstrate that PIC consistently outperforms competitive baselines, with superiority being particularly pronounced in high compression scenarios (e.g., achieving relative improvements of 29.8% in F1 score and 40.7% in EM score on QA tasks at the $64\times$ compression ratio). Furthermore, PIC significantly expedites the training process. Specifically, when training the 16$\times$ compressor, it surpasses the peak performance of the competitive baseline while effectively reducing the training time by approximately 40%.
Read the full abstract

All authors Guojie Liu, Yiqi Wang, Yanfeng Yang, Wenqi Fan, Songlei Jian, Jianfeng Zhang, Jie Yu

Machine Learning

Constant-Stepsize Stochastic Approximation: Finite-Time Convergence, Gaussian Approximation, and Tail Bounds

Constant-stepsize stochastic approximation (SA) is widely used in learning for computational efficiency, yet the distribution of the iterates is typically intractable. Classical asymptotics results give $X_k^{(\alpha)} \approx X^{(\alpha)} \approx x^\star+\sqrt{\alpha}Y$, where $X^{(\alpha)}$ is the steady state and $Y$ is an appropriate Gaussian limit, by progressively taking the time $k\uparrow\infty$ and stepsize $\alpha\downarrow0$. Such limit results, however, do not quantify finite-time, finite-stepsize errors. We develop an explicit pre-limit characterization for SA with i.i.d.\ and Markovian noise. We establish existence and uniqueness of the stationary law, a geometric Wasserstein convergence to stationarity, and almost-sure and $L^3$ convergence of the steady state to the root $x^\star$, identifying the scale $\sqrt{\alpha}$ as first-order fluctuation. At this scale, we derive a higher-order quantitative Gaussian approximation with a Wasserstein error, using Stein's method and Poisson equation techniques. We further obtain non-uniform Berry–Esseen-type tail bounds, incorporating both steady-state approximation and finite-time convergence errors. We instantiate the theory for strongly convex smooth SGD, linear SA, and nonlinear contractive SA. Beyond strong convexity, for general convex SGD, we identify a Gibbs limiting law and prove a pre-limit Wasserstein approximation error under stability and Stein-equation hypothesis, which are validated numerically.
Read the full abstract

All authors Zedong Wang, Yuyang Wang, Ijay Narang, Felix Wang, Yuzhou Wang, Siva Theja Maguluri

Machine Learning

Chemical Language Models for Natural Products: A State-Space Model Approach

Language models are widely used in chemistry for molecular property prediction and small-molecule generation, yet Natural Products (NPs) remain underexplored despite their importance in drug discovery. To address this gap, we develop NP-specific chemical language models (NPCLMs) by pre-training state-space models (Mamba and Mamba-2) and comparing them with transformer baselines (GPT). Using a dataset of about 1M NPs, we present the first systematic comparison of selective state-space models and transformers for NP-focused tasks, together with eight tokenization strategies including character-level, Atom-in-SMILES (AIS), byte-pair encoding (BPE), and NP-specific BPE. We evaluate molecule generation (validity, uniqueness, novelty) and property prediction (membrane permeability, taste, anti-cancer activity) using MCC and AUC-ROC. Mamba generates 1-2 percent more valid and unique molecules than Mamba-2 and GPT, with fewer long-range dependency errors, while GPT yields slightly more novel structures. For property prediction, Mamba variants outperform GPT by 0.02-0.04 MCC under random splits, while scaffold splits show comparable performance. Results demonstrate that domain-specific pre-training on about 1M NPs can match models trained on datasets over 100 times larger.
Read the full abstract

All authors Ho-Hsuan Wang, Afnan Sultan, Andrea Volkamer, Dietrich Klakow

Machine Learning

QuRL: Efficient Reinforcement Learning with Quantized Rollout

Reinforcement learning with verifiable rewards (RLVR) has become a trending paradigm for training reasoning large language models (LLMs). However, due to the autoregressive decoding nature of LLMs, the rollout process becomes the efficiency bottleneck of RL training, consisting of up to 70% of the total training time. In this work, we propose Quantized Reinforcement Learning (QuRL) that uses a quantized actor for accelerating the rollout. We address two challenges in QuRL. First, we propose Adaptive Clipping Range (ACR) that dynamically adjusts the clipping ratio based on the policy ratio between the full-precision actor and the quantized actor, which is essential for mitigating long-term training collapse. Second, we identify the weight update problem, where weight changes between RL steps are extremely small, making it difficult for the quantization operation to capture them effectively. We mitigate this problem through the invariant scaling technique that reduces quantization noise and increases weight update. We evaluate our method with INT8 and FP8 quantization experiments on DeepScaleR and DAPO, and achieve 20% to 80% faster rollout during training.
Read the full abstract

All authors Yuhang Li, Reena Elangovan, Xin Dong, Priyadarshini Panda, Brucek Khailany

Machine Learning

Experiential Reinforcement Learning

Reinforcement learning has become the central approach for language models (LMs) to learn from environmental reward or feedback. In practice, the environmental feedback is usually sparse and delayed. Learning from such signals is challenging, as LMs must implicitly infer how observed failures should translate into behavioral changes for future iterations. We introduce Experiential Reinforcement Learning (ERL), a training paradigm that embeds an explicit experience-reflection-consolidation loop into the reinforcement learning process. Given a task, the model generates an initial attempt, receives environmental feedback, and produces a reflection that guides a refined second attempt, whose success is reinforced and internalized into the base policy. This process converts feedback into structured behavioral revision, improving exploration and stabilizing optimization while preserving gains at deployment without additional inference cost. Across sparse-reward control environments and agentic reasoning benchmarks, ERL consistently improves learning efficiency and final performance over strong reinforcement learning baselines, achieving gains of up to +81% in complex multi-step environments and up to +11% in tool-using reasoning tasks. These results suggest that integrating explicit self-reflection into policy training provides a practical mechanism for transforming feedback into durable behavioral improvement.
Read the full abstract

All authors Taiwei Shi, Sihao Chen, Bowen Jiang, Linxin Song, Longqi Yang, Jieyu Zhao

Machine Learning · Cross-listed from stat.ML

A Theoretical Framework for LLM Fine-tuning Using Early Stopping for Non-random Initialization

In the era of large language models (LLMs), fine-tuning pretrained models has become ubiquitous. Yet the theoretical underpinning remains an open question. A central question is why only a few epochs of fine-tuning are typically sufficient to achieve strong performance on many different tasks. In this work, we approach this question by developing a statistical framework, combining rigorous early stopping theory with the attention-based Neural Tangent Kernel (NTK) for LLMs, offering new theoretical insights on fine-tuning practices. Specifically, we formally extend classical NTK theory [Jacot et al., 2018] to non-random (i.e., pretrained) initializations and provide a convergence guarantee for attention-based fine-tuning. One key insight provided by the theory is that the convergence rate with respect to sample size is closely linked to the eigenvalue decay rate of the empirical kernel matrix induced by the NTK. We also demonstrate how the framework can be used to explain task vectors for multiple tasks in LLMs. Finally, experiments with modern language models on real-world datasets provide empirical evidence supporting our theoretical insights.
Read the full abstract

Machine Learning

You Can Learn Tokenization End-to-End with Reinforcement Learning

Tokenization is a hardcoded compression step which remains in the training pipeline of Large Language Models (LLMs), despite a general trend towards architectures becoming increasingly end-to-end. Prior work has shown promising results at scale in bringing this compression step inside the LLMs' architecture with heuristics to draw token boundaries, and also attempts to learn these token boundaries with straight-through estimates, which treat the problem of drawing discrete token boundaries as a continuous one. We show that these token boundaries can instead be learned using score function estimates, which have tighter theoretical guarantees due to directly optimizing the problem of drawing discrete token boundaries to minimize loss. We observe that techniques from reinforcement learning, such as time discounting, are necessary to reduce the variance of this score function sufficiently to make it practicable. We demonstrate that the resultant method outperforms prior proposed straight-through estimates, both qualitatively and quantitatively at the $100$ million parameter scale.
Read the full abstract

Machine Learning

Adaptive Automatic Model Selection for Demand Forecasting under Heterogeneous Demand Patterns

Demand forecasting is critical for inventory planning, procurement, replenishment, production, and capacity decisions in heterogeneous supply chains. However, selecting the most appropriate model for each demand series remains challenging because performance varies across datasets, demand structures, horizons, and evaluation metrics. This study proposes the Adaptive Hybrid Selector (AHS), an automatic model-selection rule that combines observed predictive performance with structural demand information. AHS uses demand frequency and series variability to activate a hierarchical logic based on RMSSE, MAE, sMAPE, and BIAS. The proposed selector is compared with Overall Weighted Average (OWA), a benchmark-relative criterion based on sMAPE and MASE, and Equilibrium Ranking Aggregation (ERA), a comparator based on MAE, RMSE, and R^2 rankings. The empirical evaluation uses the Walmart, M3, M4, and M5 datasets, three training-testing partitions, 22 forecasting models, and horizons of up to 12 cycles. Selector performance is assessed ex post using Global Relative Accuracy (GRA), interpreted as an indicator of volumetric coherence between accumulated forecasted demand and observed demand. Results show that AHS provides the most robust overall behavior, especially in M5, while OWA remains competitive in more regular datasets. ERA shows lower volumetric coherence in most configurations. These findings suggest that automatic model selection should account for demand structure and be evaluated using ex post indicators of volumetric coherence.
Read the full abstract

Machine Learning

iML: Executable, Problem-Grounded, and Broadly Exploratory Code-Driven AutoML

Automated Machine Learning (AutoML) has improved access to machine learning, yet existing techniques often remain limited in flexibility, transparency, and execution reliability. Code-driven AutoML offers a promising direction by synthesizing executable code for preprocessing, model training, and evaluation. However, current LLM-based approaches frequently generate code that is plausible in text yet brittle in execution, insufficiently grounded in the actual dataset, or restricted to narrow solution paths. In this paper, we introduce iML, a multi-agent code-driven AutoML framework designed around three requirements: executability, problem grounding, and broad exploration of valid solutions. iML first analyzes the task and profiles the data, then synthesizes a structured blueprint that guides modular code generation across multiple implementation tracks, including traditional ML,pretrained adaptation, and custom neural architectures. To improve reliability, iML enforces interface checking, dynamic execution, and iterative debugging during integration. We evaluate iML on MLE-BENCH and the newly introduced iML-BENCH, covering diverse Kaggle-style tasks. On MLE-BENCH, iML attains a 90% valid submission rate and a 45% medal rate, and an APS of 0.82, improving the average standardized performance score (APS) over the LLM-based baselines by 52%-273%. On iML-BENCH, it achieves the highest APS and demonstrates robust performance even when task descriptions are substantially stripped. These results establish iML as a reliable and competitive framework for code-driven AutoML.
Read the full abstract

All authors Dat Le, Duc-Cuong Le, Anh-Son Nguyen, Tuan-Dung Bui, Thu-Trang Nguyen, Son Nguyen, Hieu Dinh Vo

Machine Learning · Cross-listed from cs.AI

Statistical Early Stopping for Reasoning Models

While LLMs have seen substantial improvement in reasoning capabilities, they also sometimes overthink, generating unnecessary reasoning steps, particularly under uncertainty, given ill-posed or ambiguous queries. We introduce statistically principled early stopping methods that monitor uncertainty signals during generation to mitigate this issue. Our first approach is parametric: it models inter-arrival times of uncertainty keywords as a renewal process and applies sequential testing for stopping. Our second approach is nonparametric and provides finite-sample guarantees on the probability of halting too early on well-posed queries. We conduct empirical evaluations on reasoning tasks across several domains and models. Our results indicate that uncertainty-aware early stopping can improve both efficiency and reliability in LLM reasoning, and we observe especially significant gains for math reasoning.
Read the full abstract

All authors Yangxinyu Xie, Tao Wang, Soham Mallick, Yan Sun, Georgy Noarov, Mengxin Yu, Tanwi Mallick, Edgar Dobriban

Machine Learning

Why Code, Why Now: An Information-Theoretic Perspective on the Limits of Machine Learning

This paper offers a new perspective on the limits of machine learning: the ceiling on progress is set not by model size or algorithm choice but by the information structure of the task itself. Code generation has progressed more reliably than reinforcement learning, largely because code provides dense, local, verifiable feedback at every token, whereas most reinforcement learning problems do not. This difference in feedback quality is not binary but graded. We propose a five-level hierarchy of learnability based on information structure and argue that diagnosing a task's position in this hierarchy is more predictive of scaling outcomes than any property of the model. The hierarchy rests on a formal distinction among three properties of computational problems (expressibility, computability, and learnability). We establish their pairwise relationships, including where implications hold and where they fail, and present a unified template that makes the structural differences explicit. The analysis suggests why supervised learning on code scales predictably while reinforcement learning does not, and why the common assumption that scaling alone will solve remaining ML challenges warrants scrutiny.
Read the full abstract

Saturday 14 February

Machine Learning · Cross-listed from cs.CL

TAMUSA-Chat: A Domain-Adapted Large Language Model Conversational System for Research and Responsible Deployment

This paper presents TAMUSA-Chat, a research-oriented framework for building domain-adapted large language model conversational systems. The work addresses critical challenges in adapting general-purpose foundation models to institutional contexts through supervised fine-tuning, retrieval-augmented generation, and systematic evaluation methodologies. We describe the complete architecture encompassing data acquisition from institutional sources, preprocessing pipelines, embedding construction, model training workflows, and deployment strategies. The system integrates modular components enabling reproducible experimentation with training configurations, hyper-parameters, and evaluation protocols. Our implementation demonstrates how academic institutions can develop contextually grounded conversational agents while maintaining transparency, governance compliance, and responsible AI practices. Through empirical analysis of fine-tuning behavior across model sizes and training iterations, we provide insights into domain adaptation efficiency, computational resource requirements, and quality-cost trade-offs. The publicly available codebase at https://github.com/alsmadi/TAMUSA_LLM_Based_Chat_app supports continued research into institutional LLM deployment, evaluation methodologies, and ethical considerations for educational AI systems.
Read the full abstract

Machine Learning

Machine Learning for Complex Systems Dynamics: Detecting Bifurcations in Dynamical Systems with Deep Neural Networks

Critical transitions are the abrupt shifts between qualitatively different states of a system, and they are crucial to understanding tipping points in complex dynamical systems across ecology, climate science, and biology. Detecting these shifts typically involves extensive forward simulations or bifurcation analyses, which are often computationally intensive and limited by parameter sampling. In this study, we propose a novel machine learning approach based on deep neural networks (DNNs) called equilibrium-informed neural networks (EINNs) to identify critical thresholds associated with catastrophic regime shifts. Rather than fixing parameters and searching for solutions, the EINN method reverses this process by using candidate equilibrium states as inputs and training a DNN to infer the corresponding system parameters that satisfy the equilibrium condition. By analyzing the learned parameter landscape and observing abrupt changes in the feasibility or continuity of equilibrium mappings, critical thresholds can be effectively detected. We demonstrate this capability on nonlinear systems exhibiting saddle-node bifurcations and multi-stability, showing that EINNs can recover the parameter regions associated with impending transitions. This method provides a flexible alternative to traditional techniques, offering new insights into the early detection and structure of critical shifts in high-dimensional and nonlinear systems.
Read the full abstract

Machine Learning · Cross-listed from cs.CL

Context-Dependent Affordance Reports in Vision-Language Models

Vision-language models produce different object and use descriptions under different persona prompts, but low overlap alone does not identify an affordance effect. We audit an earlier seven-prompt study and add matched-question controls. In the historical Qwen pilot, 363 of 3,213 parsed responses contain empty object lists. These affect 2,037 of 9,244 comparisons, with the implementation assigning zero lexical overlap to every affected pair. Conditioning on nonempty reports raises pooled word Jaccard from 0.095 to 0.121 and sentence cosine from 0.415 to 0.511. A previously named chef-specific Tucker factor loses its concentrated loading under missing-cell and complete-nonempty analyses. We withdraw the functional-manifold interpretation and the conversion of similarity scores into percentages of meaning. A new experiment uses 48 images absent from the original pilot, four personas, a shared three-object task, two wordings, and two requested seeds in each of two model configurations. Qwen3.5-9B's persona-minus-wording cosine-distance contrast is 0.0146 (95% CI [-0.0003, 0.0295]; 37 complete images). Ollama llava:13b's persona-minus-wording cosine-distance contrast is -0.0266 (95% CI [-0.0412, -0.0121]; 32 complete images). Persona-associated variation does not uniformly exceed wording or sampling variation. The study provides a reproducible analysis of context-conditioned reports while separating response availability, content similarity, and the limits of inference from linguistic outputs.
Read the full abstract

Machine Learning · Cross-listed from cs.CR

An Adaptive Multichain Blockchain: A Multiobjective Optimization Approach

Blockchains are widely used for secure transaction processing, but their scalability remains limited, and existing multichain designs are typically static even as demand and capacity shift. We cast blockchain configuration as a multiagent resource-allocation problem: applications and operators declare demand, capacity, and price bounds; an optimizer groups them into ephemeral chains each epoch and sets a chain-level clearing price. The objective maximizes a governance-weighted combination of normalized utilities for applications, operators, and the system. The model is modular – accommodating capability compatibility, application-type diversity, and epoch-to-epoch stability – and can be solved off-chain with outcomes verifiable on-chain. We analyze fairness and incentive issues and present simulations that highlight trade-offs among throughput, decentralization, operator yield, and service stability.
Read the full abstract

Machine Learning · Cross-listed from cs.DB

RDBLearn: Simple In-Context Prediction Over Relational Databases

Recent advances in tabular in-context learning (ICL) show that a single pretrained model can adapt to new prediction tasks from a small set of labeled examples, avoiding per-task training and heavy tuning. However, many real-world tasks live in relational databases, where predictive signal is spread across multiple linked tables rather than a single flat table. We show that tabular ICL can be extended to relational prediction with a simple recipe: automatically featurize each target row using relational aggregations over its linked records, materialize the resulting augmented table, and run an off-the-shelf tabular foundation model on it. We package this approach in RDBLearn (https://github.com/HKUSHXLab/rdblearn), an easy-to-use toolkit with a scikit-learn-style estimator interface that makes it straightforward to swap different tabular ICL backends; a complementary agent-specific interface is provided as well. Across a broad collection of RelBench and 4DBInfer datasets, RDBLearn is the best-performing foundation model approach we evaluate, at times even outperforming strong supervised baselines trained or fine-tuned on each dataset.
Read the full abstract

All authors Yanlin Zhang, Linjie Xu, Quan Gan, David Wipf, Minjie Wang

Machine Learning · Cross-listed from cs.AI

On the Dynamics of Observation and Semantics

A dominant paradigm in visual intelligence treats semantics as a static property of latent representations, assuming that meaning can be discovered through geometric proximity in high dimensional embedding spaces. In this work, we argue that this view is physically incomplete. We propose that intelligence is not a passive mirror of reality but a property of a physically realizable agent, a system bounded by finite memory, finite compute, and finite energy interacting with a high entropy environment. We formalize this interaction through the kinematic structure of an Observation Semantics Fiber Bundle, where raw sensory observation data (the fiber) is projected onto a low entropy causal semantic manifold (the base). We prove that for any bounded agent, the thermodynamic cost of information processing (Landauer's Principle) imposes a strict limit on the complexity of internal state transitions. We term this limit the Semantic Constant B. From these physical constraints, we derive the necessity of symbolic structure. We show that to model a combinatorial world within the bound B, the semantic manifold must undergo a phase transition, it must crystallize into a discrete, compositional, and factorized form. Thus, language and logic are not cultural artifacts but ontological necessities the solid state of information required to prevent thermal collapse. We conclude that understanding is not the recovery of a hidden latent variable, but the construction of a causal quotient that renders the world algorithmically compressible and causally predictable.
Read the full abstract

Machine Learning · Cross-listed from cs.CV

MamaDino: A Hybrid Vision Model for Breast Cancer 3-Year Risk Prediction

Breast cancer screening programmes increasingly seek to move from one-size-fits-all intervals to risk-adapted and personalized strategies. Deep learning (DL) has enabled image-based risk models with stronger 1- to 5-year prediction than clinical models, but leading systems (e.g., Mirai) typically use convolutional backbones, high-resolution inputs (>1M pixels) and simple multi-view fusion, with limited explicit modelling of contralateral asymmetry. We hypothesised that combining complementary inductive biases (convolutional and transformer-based) with explicit contralateral asymmetry modelling would allow us to match state-of-the-art 3-year risk prediction performance on lower-resolution mammograms, suggesting that using less detail in a more structured way can recover state-of-the-art accuracy. We present MamaDino, a mammography-aware multi-view attentional DINO model. MamaDino fuses frozen self-supervised DINOv3 ViT-S features with a trainable CNN encoder at 512x512 resolution and aggregates bilateral breast information via a BilateralMixer to output a 3-year breast cancer risk score. We train on 53,883 women from OPTIMAM (UK) and evaluate on matched 3-year case-control cohorts: an in-distribution test set from four screening sites and an external out-of-distribution cohort from an unseen site. At breast level, MamaDino achieves discrimination comparable to Mirai on internal and external tests while using ~13x fewer input pixels. Adding the BilateralMixer improves patient-level discrimination to AUC 0.736 (vs Mirai 0.713) in-distribution and 0.677 (vs Mirai 0.676) out-of-distribution, with overlapping confidence intervals. Performance was evaluated across age, ethnicity, scanner manufacturer, tumour type and grade. These findings suggest that complementary inductive biases and explicit contralateral modelling can achieve Mirai-comparable discrimination at lower resolution.
Read the full abstract

Machine Learning · Cross-listed from cs.SD

voice2mode: Phonation Mode Classification in Singing using Self-Supervised Speech Models

We present voice2mode, a method for classification of four singing phonation modes (breathy, neutral (modal), flow, and pressed) using embeddings extracted from large self-supervised speech models. Prior work on singing phonation has relied on handcrafted signal features or task-specific neural nets; this work evaluates the transferability of speech foundation models to singing phonation classification. voice2mode extracts layer-wise representations from HuBERT and two wav2vec2 variants, applies global temporal pooling, and classifies the pooled embeddings with lightweight classifiers (SVM, XGBoost). Experiments on a publicly available soprano dataset (763 sustained vowel recordings, four labels) show that foundation-model features substantially outperform conventional spectral baselines (spectrogram, mel-spectrogram, MFCC). HuBERT embeddings obtained from early layers yield the best result (~95.7% accuracy with SVM), an absolute improvement of ~12-15% over the best traditional baseline. We also show layer-wise behaviour: lower layers, which retain acoustic/phonetic detail, are more effective than top layers specialized for Automatic Speech Recognition (ASR).
Read the full abstract

All authors Aju Ani Justus, Ruchit Agrawal, Sudarsana Reddy Kadiri, Shrikanth Narayanan