72 articles tagged #machine-learning
arXiv:2604.19753v1 Announce Type: cross Abstract: We propose a feature-free approach to algorithm selection that replaces hand-crafted instance features with pretrained text embeddings. Our method, ZeroFolio, proceeds in three steps: it reads the raw instance file as plain text, embeds it with a pre
arXiv:2604.20822v1 Announce Type: cross Abstract: The offshore wind energy sector is expanding rapidly, increasing the need for independent, high-temporal-resolution monitoring of infrastructure deployment and operation at global scale. While Earth Observation based offshore wind infrastructure mapp
arXiv:2604.16565v2 Announce Type: replace-cross Abstract: While Diffusion Large Language Models (dLLMs) offer structural advantages for global planning, efficiently verifying that they arrive at correct answers via valid reasoning traces remains a critical challenge. In this work, we propose a geome
arXiv:2604.20313v1 Announce Type: new Abstract: This technical note provides a first-order formalisation of the logit shift and fact-margin change induced by Low-Rank Adaptation (LoRA). Using a first-order Fr\'echet approximation around the base model trajectory, we show that the multi-layer LoRA ef
arXiv:2407.11933v4 Announce Type: replace Abstract: Target-group detection is the task of detecting which group(s) a piece of content is ``directed at or about''. Applications include targeted marketing, content recommendation, and group-specific content assessment. Key challenges include: 1) that a
arXiv:2604.01577v2 Announce Type: replace Abstract: We extend the recent latent recurrent modeling to sequential input streams. By interleaving fast, recurrent latent updates with self-organizational ability between slow observation updates, our method facilitates the learning of stable internal str
arXiv:2604.19526v1 Announce Type: cross Abstract: Cross-site scripting (XSS) remains a persistent web security vulnerability, especially because obfuscation can change the surface form of a malicious payload while preserving its behavior. These transformations make it difficult for traditional and m
arXiv:2510.10959v3 Announce Type: replace-cross Abstract: Reasoning ability has become a defining capability of Large Language Models (LLMs), with Reinforcement Learning with Verifiable Rewards (RLVR) emerging as a key paradigm to enhance it. However, RLVR training often suffers from policy entropy
arXiv:2604.15617v1 Announce Type: cross Abstract: Hyperbolic conservation laws govern a wide range of transport-driven dynamics featuring shocks, contact discontinuities, and complex wave interactions, posing distinct challenges for deep-learning-based surrogate modeling. While classical numerical m
arXiv:2604.15609v1 Announce Type: new Abstract: Test-Time Adaptation (TTA) for black-box models accessible only via APIs remains a largely unexplored challenge. Existing approaches such as post-hoc output refinement offer limited adaptive capacity, while Zeroth-Order Optimization (ZOO) enables input
arXiv:2604.14460v2 Announce Type: replace-cross Abstract: Neuromotor decoding from upper-limb electromyography (sEMG) can enhance human-machine interfaces and offer a more natural means of controlling prosthetic limbs, virtual reality, and household electronics. Unfortunately, current sEMG technolog
arXiv:2604.14345v1 Announce Type: new Abstract: As search depth increases in autonomous reasoning and embodied planning, the candidate action space expands exponentially, heavily taxing computational budgets. While heuristic pruning is a common countermeasure, it operates without formal safety guara
arXiv:2410.01540v4 Announce Type: replace-cross Abstract: Classical diffusion models typically rely on isotropic Gaussian noise, treating all regions uniformly and overlooking structural information important for high-quality generation. We introduce an edge-preserving diffusion process that general
arXiv:2604.15216v1 Announce Type: cross Abstract: Mobility in urban and interurban areas, mainly by cars, is a day-to-day activity of many people. However, some of its main drawbacks are traffic jams and accidents. Newly made vehicles have pre-installed driving evaluation systems, which can prevent
arXiv:2604.07941v2 Announce Type: replace-cross Abstract: Post-training has become central to turning pretrained large language models (LLMs) into aligned, capable, and deployable systems. Recent progress spans supervised fine-tuning (SFT), preference optimization, reinforcement learning (RL), proce
arXiv:2604.14246v1 Announce Type: new Abstract: Sparse Mixture-of-Experts (MoE) models have achieved remarkable scalability, yet they remain vulnerable to hallucinations, particularly when processing long-tail knowledge. We identify that this fragility stems from static Top-$k$ routing: routers tend
arXiv:2604.14251v1 Announce Type: new Abstract: Monitoring LLM safety at scale requires balancing cost and accuracy: a cheap latent-space probe can screen every input, but hard cases should be escalated to a more expensive expert. Existing cascades delegate based on probe uncertainty, but uncertaint
arXiv:2604.14583v1 Announce Type: new Abstract: Decentralized Finance (DeFi) lending protocols like Aave v3 rely on over-collateralization to secure loans, yet users frequently face liquidation due to volatile market conditions. Existing risk management tools utilize static health-factor thresholds,
arXiv:2604.15285v1 Announce Type: cross Abstract: We study post-training interpretability for Support Vector Machines (SVMs) built from truncated orthogonal polynomial kernels. Since the associated reproducing kernel Hilbert space is finite-dimensional and admits an explicit tensor-product orthonorm
arXiv:2604.14424v1 Announce Type: new Abstract: Most practical engineering design problems involve nonlinear spatio-temporal dynamical systems. Multi-physics simulations are often performed to capture the fine spatio-temporal scales which govern the evolution of these systems. However, these simulat
arXiv:2604.14614v1 Announce Type: cross Abstract: We give an algorithm for PAC learning intersections of $k$ halfspaces with a $\rho$ margin to within error $\varepsilon$ that runs in time $\textsf{poly}(k, \varepsilon^{-1}, \rho^{-1}) \cdot \exp \left(O(\sqrt{n \log(1/\rho) \log k})\right)$. Notabl
arXiv:2604.14267v1 Announce Type: new Abstract: Search agents extend Large Language Models (LLMs) beyond static parametric knowledge by enabling access to up-to-date and long-tail information unavailable during pretraining. While reinforcement learning has been widely adopted for training such agent
arXiv:2604.13354v1 Announce Type: cross Abstract: The discovery of inorganic crystal structures with targeted properties is a significant challenge in materials science. Generative models, especially state-of-the-art diffusion models, offer the promise of modeling complex data distributions and prop
arXiv:2604.13070v1 Announce Type: cross Abstract: Palaeohispanic languages are those spoken in the Iberian Peninsula before the arrival of the Romans in the 3rd Century B.C. Their study was really put on motion after G\'omez Moreno deciphered the Iberian Levantine script, one of the several semi-sil
arXiv:2507.09503v4 Announce Type: replace-cross Abstract: This paper proposes a neural stochastic optimization method for efficiently solving the two-stage stochastic unit commitment (2S-SUC) problem under high-dimensional uncertainty scenarios. The proposed method approximates the second-stage reco
arXiv:2604.13313v1 Announce Type: new Abstract: Vision-Language Models demonstrate remarkable capabilities but often struggle with compositional reasoning, exhibiting vulnerabilities regarding word order and attribute binding. This limitation arises from a scarcity of informative samples needed to d
arXiv:2505.23737v2 Announce Type: replace-cross Abstract: The majority of parameters in neural networks are naturally represented as matrices. However, most commonly used optimizers treat these matrix parameters as flattened vectors during optimization, potentially overlooking their inherent structu
arXiv:2604.12513v1 Announce Type: new Abstract: We study whether a variational language model can support a minimal and measurable form of agentic control grounded in its own internal evidence. Our model combines local variational hidden computation (EVE), a homeostatic latent regulator, structurall
arXiv:2604.09673v1 Announce Type: cross Abstract: The mirror self-recognition test evaluates whether a subject touches a mark on its own body that is visible only in a mirror, and is widely used as an indicator of self-awareness. In this study, we present a computational model in which this behavior
arXiv:2511.20577v3 Announce Type: replace Abstract: Real-world time series often exhibit strong non-stationarity, complex nonlinear dynamics, and behavior expressed across multiple temporal scales, from rapid local fluctuations to slow-evolving long-range trends. However, many contemporary architect
arXiv:2604.10248v1 Announce Type: new Abstract: Complex systems such as aircraft engines, turbines, and industrial machinery often operate under dynamically changing conditions. These varying operating conditions can substantially influence degradation behavior and make prognostic modeling more chal
arXiv:2604.09563v1 Announce Type: new Abstract: AI systems produce large volumes of logs as they interact with tools and users. Analysing these logs can help understand model capabilities, propensities, and behaviours, or assess whether an evaluation worked as intended. Researchers have started deve
arXiv:2604.08708v1 Announce Type: cross Abstract: While Large Language Model-based Multi-Agent Systems (MAS) consistently outperform single-agent systems on complex tasks, their intricate interactions introduce critical reliability challenges arising from communication dynamics and role dependencies
arXiv:2511.17687v2 Announce Type: replace Abstract: The brain's Path Integration (PI) mechanism offers substantial guidance and inspiration for Brain-Inspired Navigation (BIN). However, the PI capability constructed by the Continuous Attractor Neural Networks (CANNs) in most existing BIN studies exh
arXiv:2604.08584v1 Announce Type: cross Abstract: Long-context LLMs increasingly rely on extended, reusable prefill prompts for agents and domain Q&A, pushing attention and KV-cache to become the dominant decode-time bottlenecks. While sparse attention reduces computation and transfer costs, it ofte
arXiv:2604.09519v1 Announce Type: new Abstract: World models have emerged as a unifying paradigm for learning latent dynamics, simulating counterfactual futures, and supporting planning under uncertainty. In this paper, we argue that computational epidemiology is a natural and underdeveloped setting
arXiv:2604.09181v1 Announce Type: cross Abstract: Diffusion models and their variations, such as rectified flows, generate diverse and high-quality images, but they are still hindered by slow iterative sampling caused by the highly curved generative paths they learn. An important cause of high curva
arXiv:2601.22285v4 Announce Type: replace Abstract: Model merging combines knowledge from separately fine-tuned models, yet success factors remain poorly understood. While recent work treats mergeability as an intrinsic property, we show with an architecture-agnostic framework that it fundamentally
arXiv:2604.08588v1 Announce Type: cross Abstract: Effective automation hinges on deciding when to act and when to escalate. We model this as a decision under uncertainty: an LLM forms a prediction, estimates its probability of being correct, and compares the expected costs of acting and escalating.
arXiv:2604.09303v1 Announce Type: cross Abstract: This paper presents an online intention prediction framework for estimating the goal state of autonomous systems in real time, even when intention is time-varying, and system dynamics or objectives include unknown parameters. The problem is formulate
arXiv:2510.24561v2 Announce Type: replace-cross Abstract: LoRA has become a widely adopted method for PEFT, and its initialization methods have attracted increasing attention. However, existing methods have notable limitations: many methods do not incorporate target-domain data, while gradient-based
arXiv:2512.00170v2 Announce Type: replace Abstract: Existing high-dimensional Bayesian optimization (BO) methods aim to overcome the curse of dimensionality by carefully encoding structural assumptions, from locality to sparsity to smoothness, into the optimization procedure. Surprisingly, we demons
arXiv:2603.28281v2 Announce Type: replace Abstract: We consider robustness against data corruption in offline multi-agent reinforcement learning from human feedback (MARLHF) under a strong-contamination model: given a dataset $D$ of trajectory-preference tuples (each preference being an $n$-dimensio
arXiv:2604.07762v1 Announce Type: cross Abstract: Controlling the evolution of a many-body stochastic system from a disordered reference state to a structured target ensemble, characterized empirically through samples, arises naturally in non-equilibrium statistical mechanics and stochastic control.
arXiv:2604.07108v1 Announce Type: cross Abstract: Catastrophic forgetting is not an engineering failure. It is a mathematical consequence of storing knowledge as global parameter superposition. Existing methods, such as regularization, replay, and frozen subnetworks, add external mechanisms to a sha
arXiv:2407.19426v2 Announce Type: replace Abstract: The presence of unobserved common causes and measurement error poses two major obstacles to causal structure learning, since ignoring either source of complexity can induce spurious causal relations among variables of interest. We study causal stru
arXiv:2601.08950v3 Announce Type: replace Abstract: Despite their growing adoption in education, LLMs remain misaligned with the core principle of effective tutoring: the dialogic construction of knowledge. We introduce CONVOLEARN1, a dataset of 2,134 semi-synthetic tutor-student dialogues operation
arXiv:2604.08204v1 Announce Type: new Abstract: For applications on the extreme edge, minimal networks of only a few dozen artificial neurons for event detection and classification in discrete time signals would be highly desirable. Feed-forward networks, RNNs, and CNNs evolved through evolutionary
arXiv:2409.09298v2 Announce Type: replace-cross Abstract: The Matrix Profile (MP), a versatile tool for time series data mining, has been shown effective in time series anomaly detection (TSAD). This paper delves into the problem of anomaly detection in multidimensional time series, a common occurre
arXiv:2604.06440v1 Announce Type: cross Abstract: Visual prompting (VP) has emerged as a popular method to repurpose pretrained vision models for adaptation to downstream tasks. Unlike conventional model fine-tuning techniques, VP introduces a universal perturbation directly into the input data to f
arXiv:2604.07254v1 Announce Type: cross Abstract: Deep neural networks can predict human judgments, but this does not imply that they rely on human-like information or reveal the cues underlying those judgments. Prior work has addressed this issue using attribution heatmaps, but their explanatory va
arXiv:2512.19253v3 Announce Type: replace-cross Abstract: We present the first empirical study of machine unlearning (MU) in hybrid quantum-classical neural networks. While MU has been extensively explored in classical deep learning, its behavior within variational quantum circuits (VQCs) and quantu
arXiv:2510.20200v2 Announce Type: replace Abstract: Replicability, introduced by (Impagliazzo et al. STOC '22), is the notion that algorithms should remain stable under a resampling of their inputs (given access to shared randomness). While a strong and interesting notion of stability, the cost of r
arXiv:2306.02781v3 Announce Type: replace-cross Abstract: Generative artificial intelligence, and large language models in particular, have emerged as one of the most transformative paradigms in modern computer science. This automated survey provides an accessible treatment of the field as of early
arXiv:2604.00799v2 Announce Type: replace-cross Abstract: Spatial consistency is a fundamental property of the visual world and a key requirement for models that aim to understand physical reality. Despite recent advances, multimodal large language models (MLLMs) often struggle to reason about 3D ge
arXiv:2604.02765v1 Announce Type: new Abstract: Class-incremental learning (CIL) is typically evaluated under predefined schedules with equal-sized tasks, leaving more realistic and complex cases unexplored. However, a practical CIL system should learns immediately when any number of new classes arr
arXiv:2602.16967v3 Announce Type: replace Abstract: Grokking -- the abrupt transition from memorization to generalization after prolonged training -- has been linked to confinement on low-dimensional execution manifolds in modular arithmetic. Whether this mechanism extends beyond arithmetic remains
arXiv:2602.16746v3 Announce Type: replace Abstract: Grokking -- the delayed transition from memorization to generalization in small algorithmic tasks -- remains poorly understood. We present a geometric analysis of optimization dynamics in transformers trained on modular arithmetic. PCA of attention
arXiv:2604.02558v1 Announce Type: new Abstract: We address nonconvex learning problems over undirected networks. In particular, we focus on the challenge of designing an algorithm that is both communication-efficient and that guarantees the privacy of the agents' data. The first goal is achieved thr
arXiv:2405.03083v5 Announce Type: replace-cross Abstract: Causal effects are often characterized with population summaries. These might provide an incomplete picture when there are heterogeneous treatment effects across subgroups. Since the subgroup structure is typically unknown, it is more challen
arXiv:2510.09908v3 Announce Type: replace-cross Abstract: The rise of large-scale pretrained models has made it feasible to generate predictive or synthetic features at low cost, raising the question of how to incorporate such surrogate predictions into downstream decision-making. We study this prob
arXiv:2604.00319v1 Announce Type: new Abstract: We develop algorithms for collaborative control of AI agents and critics in a multi-actor, multi-critic federated multi-agent system. Each AI agent and critic has access to classical machine learning or generative AI foundation models. The AI agents an
arXiv:2604.01949v1 Announce Type: new Abstract: The scale of biological datasets now routinely exceeds system memory, making data access rather than model computation the primary bottleneck in training machine-learning models. This bottleneck is particularly acute in biology, where widely used commu
arXiv:2604.02244v1 Announce Type: cross Abstract: This is an extended version of our publication Learning state machines from data streams: A generic strategy and an improved heuristic, International Conference on Grammatical Inference (ICGI) 2023, Rabat, Morocco. It has been extended with a formal
arXiv:2603.10202v2 Announce Type: replace-cross Abstract: Generating synthetic financial time series that preserve the statistical properties of real market data is essential for stress testing, risk model validation, and scenario design. Existing approaches struggle to simultaneously reproduce heav
arXiv:2604.02255v1 Announce Type: cross Abstract: In this paper, we consider a multi-armed bandit (MAB) instance and study how to identify the best arm when arm commands are conveyed from a central learner to a distributed agent over a discrete memoryless channel (DMC). Depending on the agent capabi
arXiv:2603.22455v4 Announce Type: replace Abstract: Reusable skills let LLM agents package task-specific procedures, tool affordances, and execution guidance into modular building blocks. As skill ecosystems grow to tens of thousands of entries, exposing every skill at inference time becomes infeasi
arXiv:2603.08426v2 Announce Type: replace Abstract: Class Incremental Learning (CIL) poses a fundamental challenge: maintaining a balance between the plasticity required to learn new tasks and the stability needed to prevent catastrophic forgetting. While expansion-based methods effectively mitigate
arXiv:2604.00260v1 Announce Type: new Abstract: Shuffling strategies for stochastic gradient descent (SGD), including incremental gradient, shuffle-once, and random reshuffling, are supported by rigorous convergence analyses for arbitrary within-epoch permutations. In particular, random reshuffling
arXiv:2601.12604v2 Announce Type: replace Abstract: Policy gradient methods are known to be highly sensitive to the choice of policy parameterization. In particular, the widely used softmax parameterization can induce ill-conditioned optimization landscapes and lead to exponentially slow convergence
arXiv:2604.01117v1 Announce Type: new Abstract: Dependency networks (Heckerman et al., 2000) provide a flexible framework for modeling complex systems with many variables by combining independently learned local conditional distributions through pseudo-Gibbs sampling. Despite their computational adv
arXiv:2603.29999v1 Announce Type: cross Abstract: Aggregate programming is a field-based coordination paradigm with over a decade of exploration and successful applications across domains including sensor networks, robotics, and IoT, with implementations in various programming languages, such as Pro