Machine Learning
MetaKube: An Experience-Aware LLM Framework for Kubernetes Failure Diagnosis
Wei Sun, Ting Wang, Xinran Tian et al. (+4 more)
Existing LLM-based Kubernetes diagnostic systems cannot learn from operational experience, operating on static knowledge bases without improving from past resolutions. We present MetaKube, an experience-aware LLM framework through three synergistic innovations: (1) an Episodic Pattern
Memory Network (EPMN) that abstracts diagnostic patterns from historical resolutions and provides confidence-calibrated
retrieval for both rapid pattern matching and guided causal exploration, (2) a meta-cognitive controller that dynamically routes between intuitive and analytical pathways based on problem familiarity, optimizing the trade-off between speed and depth, and (3) KubeLLM, a locally-deployable 8B model enhanced through domain-specific post-training on our 7,000-sample Kubernetes Fault Resolution
Dataset. Evaluation on 1,873 real-world scenarios demonstrates MetaKube transforms Qwen3-8B from 50.9 to 90.5 points, approaching GPT-4.1 performance while ensuring complete data
privacy. EPMN contributes 15.3% improvement through experiential learning, with continuous learning experiments showing progressive gains as the system accumulates operational knowledge. The source code and related resources are available at https://github.com/MetaKube-LLM-for-Kubernetes-Diagnosis/MetaKube.
Read the full abstract ▾
All authors Wei Sun, Ting Wang, Xinran Tian, Wanshun Lan, Xuhan Feng, Haoyue Li, Fangxin Wang
Machine Learning
Residual Attention Physics-Informed Neural Networks for Robust Multiphysics Simulation of Steady-State Electrothermal Energy Systems
Yuqing Zhou, Ze Tao and Fujun Liu
Efficient thermal management and precise field prediction are critical for the design of advanced energy systems, including electrohydrodynamic transport, microfluidic energy harvesters, and electrically driven thermal regulators. However, the steady-state simulation of these electrothermal coupled multiphysics systems remains challenging for physics-informed neural computation due to strong nonlinear field coupling, temperature-dependent coefficient variability, and complex interface dynamics. This study proposes a Residual
Attention Physics-Informed Neural Network (RA-PINN) framework for the unified solution of coupled velocity, pressure, electric-potential, and temperature fields. By integrating a unified five-field operator formulation with residual-connected feature propagation and
attention-guided channel modulation, the proposed architecture effectively captures localized coupling structures and steep gradients. We evaluate RA-PINN across four representative energy-relevant
benchmarks: constant-coefficient coupling, indirect pressure-gauge constraints, temperature-dependent transport, and oblique-interface consistency. Comparative analysis against Pure-MLP, LSTM-PINN, and pLSTM-PINN demonstrates that RA-PINN achieves superior accuracy, yielding the lowest MSE, RMSE, and relative $L_2$ errors across all scenarios. Notably, RA-PINN maintains high structural fidelity in interface-dominated and variable-coefficient settings where conventional PINN backbones often fail. These results establish RA-PINN as a robust and accurate computational framework for the high-fidelity modeling and optimization of complex electrothermal multiphysics in sustainable energy applications.
Read the full abstract ▾
Machine Learning
The Geometric Price of Discrete Logic: Context-driven Manifold Dynamics of Number Representations
Long Zhang, Dai-jun Lin and Wei-neng Chen
Large
language models (LLMs) generalize smoothly across continuous semantic spaces, yet strict logical
reasoning demands the formation of discrete decision boundaries. Prevailing theories relying on linear isometric projections fail to resolve this fundamental tension. In this work, we argue that task context operates as a non-isometric dynamical operator that enforces a necessary "topological distortion." By applying Gram-Schmidt decomposition to residual-stream activations , we reveal a dual-modulation mechanism driving this process: a class-agnostic topological preservation that anchors global structure to prevent semantic collapse, and a specific algebraic divergence that directionally tears apart cross-class concepts to forge logical boundaries. We validate this
geometric evolution across a gradient of tasks, from simple mapping to complex primality testing. Crucially, targeted specific vector ablation establishes a strict causal binding between this
topology and model function: algebraically erasing the divergence component collapses parity classification accuracy from 100% to chance levels (38.57%). Furthermore, we uncover a three-phase layer-wise
geometric dynamic and demonstrate that under social pressure
prompts, models fail to generate sufficient divergence. This results in a "
manifold entanglement" that geometrically explains sycophancy and
hallucination. Ultimately, our findings revise the linear-isometric presumption, demonstrating that the emergence of discrete logic in LLMs is purchased at an irreducible cost of topological deformation.
Read the full abstract ▾
Machine Learning · Cross-listed from stat.AP
Wafer-Level Etch Spatial Profiling for Process Monitoring from Time-Series with Time-LLM
Hyunwoo Kim, Munyoung Lee, Seung Hyub Jeon et al. (+1 more)
Understanding wafer-level spatial variations from in-situ process signals is essential for advanced
plasma etching process monitoring. While most data-driven approaches focus on scalar indicators such as average etch rate, actual process quality is determined by complex two-dimensional spatial distributions across the wafer. This paper presents a spatial regression model that predicts wafer-level etch depth distributions directly from multichannel in-situ process time series. We propose a Time-LLM-based spatial regression model that extends LLM reprogramming from conventional time-series
forecasting to wafer-level spatial estimation by redesigning the input
embedding and output projection. Using the BOSCH
plasma-etching
dataset, we demonstrate stable performance under data-limited conditions, supporting the feasibility of LLM-based reprogramming for wafer-level spatial monitoring.
Read the full abstract ▾
All authors Hyunwoo Kim, Munyoung Lee, Seung Hyub Jeon, Kyu Sung Lee
Machine Learning
APreQEL: Adaptive Mixed Precision Quantization For Edge LLMs
Meriem Bouzouad, Yuan-Hao Chang and Jalil Boukhobza
Today, large
language models have demonstrated their strengths in various tasks ranging from
reasoning, code generation, and complex problem solving. However, this advancement comes with a high computational cost and
memory requirements, making it challenging to deploy these models on edge devices to ensure real-time responses and data
privacy. Quantization is one common approach to reducing
memory use, but most methods apply it uniformly across all layers. This does not account for the fact that different layers may respond differently to reduced precision. Importantly,
memory consumption and computational throughput are not necessarily aligned, further complicating deployment decisions. This paper proposes an adaptive mixed precision quantization mechanism that balances
memory, latency, and accuracy in edge deployment under user-defined priorities. This is achieved by analyzing the layer-wise contribution and by inferring how different quantization types behave across the target hardware platform in order to assign the most suitable quantization type to each layer. This integration ensures that layer importance and the overall performance trade-offs are jointly respected in this design. Our work unlocks new configuration designs that uniform quantization cannot achieve, expanding the solution space to efficiently deploy the LLMs on resource-constrained devices.
Read the full abstract ▾
Machine Learning
PoiCGAN: A Targeted Poisoning Based on Feature-Label Joint Perturbation in Federated Learning
Tao Liu, Jiguang Lv, Dapeng Man et al. (+7 more)
Federated Learning (FL), as a popular distributed learning paradigm, has shown outstanding performance in improving computational efficiency and protecting data
privacy, and is widely applied in industrial image classification. However, due to its distributed nature, FL is vulnerable to threats from malicious clients, with poisoning attacks being a common threat. A major limitation of existing poisoning attack methods is their difficulty in bypassing model performance tests and defense mechanisms based on model anomaly detection. This often results in the detection and removal of poisoned models, which undermines their practical utility. To ensure both the performance of industrial image classification and attacks, we propose a targeted poisoning attack, PoiCGAN, based on feature-label collaborative perturbation. Our method modifies the inputs of the discriminator and generator in the Conditional Generative
Adversarial Network (CGAN) to influence the training process, generating an ideal poison generator. This generator not only produces specific poisoned samples but also automatically performs label flipping. Experiments across various
datasets show that our method achieves an attack success rate 83.97% higher than baseline methods, with a less than 8.87% reduction in the main task's accuracy. Moreover, the poisoned samples and malicious models exhibit high stealthiness.
Read the full abstract ▾
All authors Tao Liu, Jiguang Lv, Dapeng Man, Weiye Xi, Yaole Li, Feiyu Zhao, Kuiming Wang, Yingchao Bian, Chen Xu, Wu Yang
Machine Learning
Dual-Criterion Curriculum Learning: Application to Temporal Data
Gaspard Abel, Eloi Campagne, Mohamed Benloughmari et al. (+1 more)
Curriculum Learning (CL) is a meta-learning paradigm that trains a model by feeding the data instances incrementally according to a schedule, which is based on difficulty progression. Defining meaningful difficulty assessment measures is crucial and most usually the main bottleneck for effective learning, while also in many cases the employed heuristics are only application-specific. In this work, we propose the Dual-Criterion Curriculum Learning (DCCL) framework that combines two views of assessing instance-wise difficulty: a loss-based criterion is complemented by a density-based criterion learned in the data representation space. Essentially, DCCL calibrates training-based evidence (loss) under the consideration that data sparseness amplifies the learning difficulty. As a testbed, we choose the time-series
forecasting task. We evaluate our framework on multivariate time-series
benchmarks under standard One-Pass and Baby-Steps training schedules. Empirical results show the interest of density-based and hybrid dual-criterion curricula over loss-only baselines and standard non-CL training in this setting.
Read the full abstract ▾
All authors Gaspard Abel, Eloi Campagne, Mohamed Benloughmari, Argyris Kalogeratos
Machine Learning
StateLinFormer: Stateful Training Enhancing Long-term Memory in Navigation
Zhiyuan Chen, Yuxuan Zhong, Fan Wang et al. (+4 more)
Effective
navigation intelligence relies on long-term
memory to support both immediate generalization and sustained adaptation. However, existing approaches face a dilemma: modular systems rely on explicit mapping but lack flexibility, while
Transformer-based end-to-end models are constrained by fixed context windows, limiting persistent
memory across extended interactions. We introduce StateLinFormer, a linear-
attention navigation model trained with a stateful
memory mechanism that preserves recurrent
memory states across consecutive training segments instead of reinitializing them at each batch boundary. This training paradigm effectively approximates learning on infinitely long sequences, enabling the model to achieve long-horizon
memory retention. Experiments across both MAZE and ProcTHOR environments demonstrate that StateLinFormer significantly outperforms its stateless linear-
attention counterpart and standard
Transformer baselines with fixed context windows. Notably, as interaction length increases, persistent stateful training substantially improves context-dependent adaptation, suggesting an enhancement in the model's In-Context Learning (ICL) capabilities for
navigation tasks.
Read the full abstract ▾
All authors Zhiyuan Chen, Yuxuan Zhong, Fan Wang, Bo Yu, Pengtao Shao, Shaoshan Liu, Ning Ding
Machine Learning
Causal Reconstruction of Sentiment Signals from Sparse News Data
Stefania Stan, Marzio Lunghi, Vito Vargetto et al. (+4 more)
Sentiment signals derived from sparse news are commonly used in financial analysis and technology monitoring, yet transforming raw article-level observations into reliable temporal series remains a largely unsolved engineering problem. Rather than treating this as a classification challenge, we propose to frame it as a causal signal reconstruction problem: given probabilistic sentiment outputs from a fixed classifier, recover a stable latent sentiment series that is robust to the structural pathologies of news data such as sparsity, redundancy, and classifier uncertainty. We present a modular three-stage pipeline that (i) aggregates article-level scores onto a regular temporal grid with uncertainty-aware and redundancy-aware weights, (ii) fills coverage gaps through strictly causal projection rules, and (iii) applies causal smoothing to reduce residual noise. Because ground-truth longitudinal sentiment labels are typically unavailable, we introduce a label-free evaluation framework based on signal stability diagnostics, information preservation lag proxies, and counterfactual tests for causality compliance and redundancy robustness. As a secondary external check, we evaluate the consistency of reconstructed signals against stock-price data for a multi-firm
dataset of AI-related news titles (November 2024 to February 2026). The key empirical finding is a three-week lead lag pattern between reconstructed sentiment and price that persists across all tested pipeline configurations and aggregation regimes, a structural regularity more informative than any single correlation coefficient. Overall, the results support the view that stable, deployable sentiment indicators require careful reconstruction, not only better classifiers.
Read the full abstract ▾
All authors Stefania Stan, Marzio Lunghi, Vito Vargetto, Claudio Ricci, Rolands Repetto, Brayden Leo, Shao-Hong Gan
Machine Learning
AscendOptimizer: Episodic Agent for Ascend NPU Operator Optimization
Jiehao Wu, Zixiao Huang, Wenhao Li et al. (+3 more)
Optimizing AscendC (Ascend C) operators for Ascend NPUs is difficult for two reasons. First, unlike CUDA, the ecosystem offers few public kernels to learn from. Second, performance depends on a coupled two-part implementation: a host-side tiling program that controls data movement and a kernel program that schedules and pipelines computation. We present AscendOptimizer, an episodic
agent that builds missing optimization knowledge from execution itself. For kernel optimization, AscendOptimizer rewinds strong implementations by removing optimizations in a controlled way, then keeps the changes whose removal measurably hurts performance as reusable experience for later rewriting. For host-side optimization, it runs profiling-in-the-loop evolutionary search to find valid, fast tiling and data-movement configurations directly from hardware feedback. This combination lets the
agent improve kernel structure and host-side scheduling together. On a
benchmark of 101 real AscendC operators, AscendOptimizer achieves a 1.21x
geometric-mean speedup over the open-source baseline, and 53.47% of operators run faster than their references. Given a same budget of evaluations per operator, AscendOptimizer consistently outperforms Best-of-N sampling and OpenEvolve in terms of
geometric mean speedup, fast_p tail speedup ratios, and overall optimization progress across varying budgets.
Read the full abstract ▾
All authors Jiehao Wu, Zixiao Huang, Wenhao Li, Chuyun Shen, Junjie Sheng, Xiangfeng Wang
Machine Learning
Safe Reinforcement Learning with Preference-based Constraint Inference
Chenglin Li, Grant Ruan and Hua Geng
Safe reinforcement learning (RL) is a standard paradigm for safety-critical decision making. However, real-world safety constraints can be complex, subjective, and even hard to explicitly specify. Existing works on constraint inference rely on restrictive assumptions or extensive expert demonstrations, which are not realistic in many real-world applications. How to cheaply and reliably learn these constraints is the major challenge we focus on in this study. While inferring constraints from human preferences offers a data-efficient alternative, we identify popular Bradley-Terry (BT) models fail to capture the asymmetric, heavy-tailed nature of safety costs, resulting in risk underestimation. It is still rare in the literature to understand the impacts of BT models on the downstream policy learning. To address the above knowledge gaps, we propose a novel approach namely Preference-based Constrained Reinforcement Learning (PbCRL). We introduce a novel dead zone mechanism into preference modeling and theoretically prove that it encourages heavy-tailed cost distributions, thereby achieving better constraint
alignment. Additionally, we incorporate a Signal-to-Noise Ratio (SNR) loss to encourage exploration by cost variances, which is found to benefit policy learning. Further, two-stage training strategy is deployed to lower online labeling burdens while adaptively enhancing constraint satisfaction. Empirical results demonstrate that PbCRL achieves superior
alignment with true safety requirements and outperforms state-of-the-art baselines in terms of safety and reward. Our work explores a promising and effective way for constraint inference in Safe RL, with great potential in various safety-critical applications.
Read the full abstract ▾
Machine Learning
Synthetic Mixed Training: Scaling Parametric Knowledge Acquisition Beyond RAG
Seungju Han, Konwoo Kim, Chanwoo Park et al. (+5 more)
Synthetic data augmentation helps
language models learn new knowledge in data-constrained domains. However, naively scaling existing synthetic data methods by training on more synthetic
tokens or using stronger generators yields diminishing returns below the performance of RAG. To break the RAG ceiling, we introduce Synthetic Mixed Training, which combines synthetic QAs and synthetic documents. This leverages their complementary training signals, and enables log-linear improvements as both synthetic data volume and generator strength increase. This allows the model to outperform RAG by a 2.6% relative gain on QuaLITY, a long-document reading comprehension
benchmark. In addition, we introduce Focal Rewriting, a simple technique for synthetic document generation that explicitly conditions document generation on specific questions, improving the diversity of synthetic documents and yielding a steeper log-linear scaling curve. On QuaLITY, our final recipe trains a Llama 8B model that outperforms RAG by 4.4% relatively. Across models and
benchmarks (QuaLITY, LongHealth, FinanceBench), our training enables models to beat RAG in five of six settings, outperforms by 2.6%, and achieves a 9.1% gain when combined with RAG.
Read the full abstract ▾
All authors Seungju Han, Konwoo Kim, Chanwoo Park, Benjamin Newman, Suhas Kotha, Jaehun Jung, James Zou, Yejin Choi
Machine Learning · Cross-listed from cs.IT
The No-Clash Teaching Dimension is Bounded by VC Dimension
Jiahua Liu and Benchong Li
In the realm of machine learning theory, to prevent unnatural coding schemes between teacher and learner, No-Clash Teaching Dimension was introduced as provably optimal complexity measure for collusion-free teaching. However, whether No-Clash Teaching Dimension is upper-bounded by Vapnik-Chervonenkis dimension remains unknown. In this paper, for any finite concept class, we construct fragments of size equals to its Vapnik-Chervonenkis dimension which identify concepts through an ordered compression scheme. Naturally, these fragments are used as teaching sets, one can easily see that they satisfy the non-clashing condition, i.e., this open question is resolved for finite concept classes.
Read the full abstract ▾
Machine Learning
Estimating Flow Velocity and Vehicle Angle-of-Attack from Non-invasive Piezoelectric Structural Measurements Using Deep Learning
Chandler B. Smith, S. Hales Swift, Andrew Steyer et al. (+1 more)
Accurate estimation of aerodynamic state variables such as freestream velocity and angle of attack (AoA) is important for aerodynamic load prediction, flight control, and model validation. This work presents a non-intrusive method for estimating vehicle velocity and AoA from structural vibration measurements rather than direct flow instrumentation such as pitot tubes. A dense array of piezoelectric sensors mounted on the interior skin of an aeroshell capture vibrations induced by turbulent boundary layer pressure fluctuations, and a convolutional neural network (CNN) is trained to invert these structural responses to recover velocity and AoA. Proof-of-concept is demonstrated through controlled experiments in Sandia's hypersonic wind tunnel spanning zero and nonzero AoA configurations, Mach~5 and Mach~8 conditions, and both constant and continuously varying tunnel operations. The CNN is trained and evaluated using data from 16 wind tunnel runs, with a temporally centered held-out interval within each run used to form training, validation, and test
datasets and assess intra-run temporal generalization. Raw CNN predictions exhibit increased variance during continuously varying conditions; a short-window moving-median post-processing step suppresses this variance and improves robustness. After post-processing, the method achieves a mean velocity error relative to the low-pass filtered reference velocity below 2.27~m/s (0.21%) and a mean AoA error of $0.44^{\circ} (8.25\%)$ on held-out test data from the same experimental campaign, demonstrating feasibility of vibration-based velocity and AoA estimation in a controlled laboratory environment.
Read the full abstract ▾
All authors Chandler B. Smith, S. Hales Swift, Andrew Steyer, Ihab El-Kady
Machine Learning · Cross-listed from cs.CV
VISion On Request: Enhanced VLLM efficiency with sparse, dynamically selected, vision-language interactions
Adrian Bulat, Alberto Baldrati, Ioannis Maniadis Metaxas et al. (+2 more)
Existing approaches for improving the efficiency of Large
Vision-
Language Models (LVLMs) are largely based on the concept of visual
token reduction. This approach, however, creates an information bottleneck that impairs performance, especially on challenging tasks that require fine-grained understanding and
reasoning. In this work, we challenge this paradigm by introducing
VISion On Request (VISOR), a method that reduces inference cost without discarding visual information. Instead of compressing the image, VISOR improves efficiency by sparsifying the interaction between image and text
tokens. Specifically, the
language model attends to the full set of high-resolution visual
tokens through a small, strategically placed set of
attention layers: general visual context is provided by efficient cross-
attention between text-image, while a few well-placed and dynamically selected self-
attention layers refine the visual representations themselves, enabling complex, high-resolution
reasoning when needed. Based on this principle, we first train a single universal network on a range of computational budgets by varying the number of self-
attention layers, and then introduce a lightweight policy mechanism that dynamically allocates visual computation based on per-sample complexity. Extensive experiments show that VISOR drastically reduces computational cost while matching or exceeding state-of-the-art results across a diverse suite of
benchmarks, and excels in challenging tasks that require detailed visual understanding.
Read the full abstract ▾
All authors Adrian Bulat, Alberto Baldrati, Ioannis Maniadis Metaxas, Yassine Ouali, Georgios Tzimiropoulos
Machine Learning · Cross-listed from cs.RO
VTAM: Efficient Visuo-Tactile World-Action Models for Contact-Rich Manipulation without Tactile Pretraining
Haoran Yuan, Weigang Yi, Zhenyu Zhang et al. (+11 more)
Tactile
vision-
language-action models (VLAs) and tactile world-action models (WAMs) are a promising new paradigm for contact-rich manipulation, but existing models either underutilize touch, rely on large-scale tactile pretraining, or incur high inference latency due to iterative
video generation. We present VTAM, an efficient visuo-tactile world-action model for contact-rich manipulation that requires no tactile or action pretraining. RGB and tactile observations share a frozen
video VAE and the pretrained
video transformer weights. VTAM first adapts the
video backbone to jointly predict future visual and tactile latents, then fine-tunes it end-to-end with a randomly initialized action expert that predicts actions, proprioceptive states, and a light flow-force proxy computed from tactile optical flow. Trained only on task demonstrations, VTAM outperforms all baselines on four real-
robot tasks across two platforms with different tactile sensors, outperforms all baselines without tactile pretraining in average success on eight UniVTAC simulation tasks, and is comparable to tactile VLAs and WAMs pretrained on over 30K hours of largely visuo-tactile
robot data (83.4% vs. 84.5% for N0-TWAM). Without full
video denoising at inference, VTAM is approximately 6x and 16x faster than N0-TWAM and LingBot-VA without compilation, with compiled latency comparable to Fast-WAM. Ablations show that feeding frozen-VAE tactile features directly to the action expert, bypassing tactile world modeling, fails on every tested task, that Stage I visuo-tactile world-model fine-tuning improves UniVTAC success on most tasks, and that flow-force proxy keeps the policy from fully ignoring touch. The tactile encoder transfers zero-shot across GelSight Mini and Xense
Photon sensors.
Read the full abstract ▾
All authors Haoran Yuan, Weigang Yi, Zhenyu Zhang, Wendi Chen, Yuchen Mo, Jiashi Yin, Xinzhuo Li, Yue Luo, Jialin Li, Xiangyu Zeng, Chuan Wen, Cewu Lu, Katherine Driggs-Campbell, Ismini Lourentzou
Machine Learning
Byzantine-Robust and Differentially Private Federated Optimization under Weaker Assumptions
Rustem Islamov, Grigory Malinovsky, Alexander Gaponov et al. (+3 more)
Federated Learning (FL) enables heterogeneous clients to collaboratively train a shared model without centralizing their raw data, offering an inherent level of
privacy. However, gradients and model updates can still leak sensitive information, while malicious servers may mount
adversarial attacks such as Byzantine manipulation. These vulnerabilities highlight the need to address differential
privacy (DP) and Byzantine robustness within a unified framework. Existing approaches, however, often rely on unrealistic assumptions such as bounded gradients, require auxiliary server-side
datasets, or fail to provide convergence guarantees. We address these limitations by proposing Byz-Clip21-SGD2M, a new
algorithm that integrates robust aggregation with double momentum and carefully designed clipping. We prove high-probability convergence guarantees under standard $L$-smoothness and $\sigma$-sub-Gaussian gradient noise assumptions, thereby relaxing conditions that dominate prior work. Our analysis recovers state-of-the-art convergence rates in the absence of adversaries and improves utility guarantees under Byzantine and DP settings. Empirical evaluations on CNN and MLP models trained on MNIST further validate the effectiveness of our approach.
Read the full abstract ▾
All authors Rustem Islamov, Grigory Malinovsky, Alexander Gaponov, Aurelien Lucchi, Peter Richtárik, Eduard Gorbunov
Machine Learning
End-to-End Efficient RL for Linear Bellman Complete MDPs with Deterministic Transitions
Zakaria Mhammedi, Alexander Rakhlin and Nneka Okolo
We study reinforcement learning (RL) with linear function approximation in Markov Decision Processes (MDPs) satisfying linear Bellman completeness – a fundamental setting where the Bellman backup of any linear value function remains linear. While statistically tractable, prior computationally efficient
algorithms are either limited to small action spaces or require strong oracle assumptions over the feature space. We provide a computationally efficient
algorithm for linear Bellman complete MDPs with deterministic transitions,
stochastic initial states, and
stochastic rewards. For finite action spaces, our
algorithm is end-to-end efficient; for large or infinite action spaces, we require only a standard argmax oracle over actions. Our
algorithm learns an $\varepsilon$-optimal policy with sample and computational complexity
polynomial in the horizon, feature dimension, and $1/\varepsilon$.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.CR
CSTS: A Canonical Security Telemetry Substrate for AI-Native Cyber Detection
Abdul Rahman
Cybersecurity data remains fragmented across vendors, formats, schemas, and deployment environments, forcing AI and analytics programs to spend disproportionate effort on ingestion, normalization, and brittle source-specific engineering. This paper introduces the Canonical Security Telemetry Substrate (CSTS), a canonical, AI-ready telemetry foundation designed to harmonize heterogeneous cyber data into a common representation over persistent entities, typed relations, events, temporal state, and provenance. CSTS is intended to move cybersecurity analytics beyond ad hoc record normalization toward a reusable substrate that supports anomaly detection, graph learning,
forecasting, behavior-based modeling, and agentic cyber AI. We formalize the core design principles of CSTS, define its representational components, and explain how it preserves source-specific nuance through explicit mappings and extensible metadata while still enabling portable downstream inference. We further position CSTS as a cloud-agnostic and deployment-agnostic substrate suitable for on-prem, hybrid, and multi-cloud environments. The result is a unifying telemetry model that reduces the blue-collar burden of cyber data engineering and creates a clearer path to scalable, interoperable, and model-agnostic cyber AI.
Read the full abstract ▾
Machine Learning
Similarity-Aware Mixture-of-Experts for Data-Efficient Continual Learning
Connor Mclaughlin, Nigel Lee and Lili Su
Machine learning models often need to adapt to new data after deployment due to structured or unstructured real-world dynamics. The Continual Learning (CL) framework enables continuous model adaptation, but most existing approaches either assume each task contains sufficiently many data samples or that the learning tasks are non-overlapping. In this paper, we address the more general setting where each task may have a limited
dataset, and tasks may overlap in an arbitrary manner without a priori knowledge. This general setting is substantially more challenging for two reasons. On the one hand, data scarcity necessitates effective contextualization of general knowledge and efficient knowledge transfer across tasks. On the other hand, unstructured task overlapping can easily result in negative knowledge transfer. To address the above challenges, we propose an adaptive mixture-of-experts (MoE) framework over pre-trained models that progressively establishes similarity awareness among tasks. Our design contains two innovative algorithmic components: incremental global pooling and instance-wise
prompt masking. The former mitigates
prompt association noise through gradual
prompt introduction over time. The latter decomposes incoming task samples into those aligning with current
prompts (in-distribution) and those requiring new
prompts (out-of-distribution). Together, our design strategically leverages potential task overlaps while actively preventing negative mutual interference in the presence of per-task data scarcity. Experiments across varying data volumes and inter-task similarity show that our method enhances sample efficiency and is broadly applicable.
Read the full abstract ▾
Machine Learning
SortedRL: Accelerating RL Training for LLMs through Online Length-Aware Scheduling
Yiqi Zhang, Huiqiang Jiang, Xufang Luo et al. (+7 more)
Scaling reinforcement learning (RL) has shown strong promise for enhancing the
reasoning abilities of large
language models (LLMs), particularly in tasks requiring long chain-of-thought generation. However, RL training efficiency is often bottlenecked by the rollout phase, which can account for up to 70% of total training time when generating long trajectories (e.g., 16k
tokens), due to slow autoregressive generation and synchronization overhead between rollout and policy updates. We propose SortedRL, an online length-aware scheduling strategy designed to address this bottleneck by improving rollout efficiency and maintaining training stability. SortedRL reorders rollout samples based on output lengths, prioritizing short samples forming groups for early updates. This enables large rollout batches, flexible update batches, and near on-policy micro-curriculum construction simultaneously. To further accelerate the pipeline, SortedRL incorporates a mechanism to control the degree of off-policy training through a cache-based mechanism, and is supported by a dedicated RL infrastructure that manages rollout and update via a stateful controller and rollout buffer. Experiments using LLaMA-3.1-8B and Qwen-2.5-32B on diverse tasks, including logical puzzles, and math challenges like AIME 24, Math 500, and Minerval, show that SortedRL reduces RL training bubble ratios by over 50%, while attaining 3.9% to 18.4% superior performance over baseline given same amount of data.
Read the full abstract ▾
All authors Yiqi Zhang, Huiqiang Jiang, Xufang Luo, Zhihe Yang, Chengruidong Zhang, Yifei Shen, Dongsheng Li, Yuqing Yang, Lili Qiu, Yang You
Machine Learning
Graph Energy Matching: Transport-Aligned Energy-Based Modeling for Graph Generation
Michal Balcerak, Suprosanna Shit, Chinmay Prabhakar et al. (+4 more)
Generative modeling of discrete data, such as graphs, underpins many scientific and industrial applications, including molecular discovery and materials design. In these domains, probabilistic inference is particularly valuable, as it enables composable generation and principled incorporation of desired constraints, such as structural or functional properties. Energy-based models naturally support this goal by capturing relative likelihoods and enabling composable inference by directly enforcing constraints during inference. However, discrete energy-based models typically struggle with efficient and high-quality sampling, as off-support regions often contain spurious local minima, trapping samplers and causing training instabilities, resulting in a fidelity gap compared to discrete
diffusion models. To address this gap, we introduce Graph Energy Matching (GEM), a discrete generative framework inspired by the Jordan-Kinderlehrer-Otto (JKO) transport-map optimization perspective. GEM learns a permutation-invariant potential energy that simultaneously guides discrete transport from noise toward high-likelihood graph regions and refines samples within these regions. We further introduce a sampling protocol leveraging an energy-based switching strategy, seamlessly bridging rapid, gradient-guided transport and a local mixing regime for effective exploration. On molecular graph
benchmarks, GEM matches or surpasses strong discrete
diffusion baselines on most reported metrics. Beyond improving generation quality, GEM's relative likelihood modeling enables targeted exploration, facilitating compositional generation, property-constrained sampling, and interpolation between graphs. Project page: https://michalbalcerak.ai/graph-energy-matching/.
Read the full abstract ▾
All authors Michal Balcerak, Suprosanna Shit, Chinmay Prabhakar, Sebastian Kaltenbach, Michael S. Albergo, Yilun Du, Bjoern Menze
Machine Learning
Central Dogma Transformer III: Interpretable AI Across DNA, RNA, and Protein
Nobuyuki Ota
Biological AI models increasingly predict complex cellular responses, yet their learned representations remain disconnected from the molecular processes they aim to capture. We present CDT-III, which extends mechanism-oriented AI across the full central dogma: DNA, RNA, and
protein. Its two-stage Virtual
Cell Embedder architecture mirrors the spatial compartmentalization of the
cell: VCE-N models transcription in the
nucleus and VCE-C models translation in the cytosol. On five held-out genes, CDT-III achieves per-gene RNA r=0.843 and
protein r=0.969. Adding
protein prediction improves RNA performance (r=0.804 to 0.843), demonstrating that downstream tasks regularize upstream representations.
Protein supervision sharpens DNA-level interpretability, increasing CTCF enrichment by 30%. Analysis of experimentally measured mRNA and
protein responses reveals that the majority of genes with observable mRNA changes show opposite
protein-level changes (66.7% at |log2FC|>0.01, rising to 87.5% at |log2FC|>0.02), exposing a fundamental limitation of RNA-only perturbation models. Despite this pervasive direction discordance, CDT-III correctly predicts both mRNA and
protein responses. Applied to in silico CD52 knockdown approximating Alemtuzumab, the model predicts 29/29
protein changes correctly and rediscovers 5 of 7 known clinical side effects without clinical data. Gradient-based side effect profiling requires only unperturbed baseline data (r=0.939), enabling screening of all 2,361 genes without new experiments.
Read the full abstract ▾
Machine Learning · Cross-listed from hep-ex
Contrastive Metric Learning for Point Cloud Segmentation in Highly Granular Detectors
Max Marriott-Clarke, Lazar Novakovic, Elizabeth Ratzer et al. (+3 more)
We propose a novel clustering approach for point-cloud
segmentation based on supervised contrastive metric learning (CML). Rather than predicting cluster assignments or object-centric variables, the method learns a latent representation in which points belonging to the same object are embedded nearby while unrelated points are separated. Clusters are then reconstructed using a density-based readout in the learned metric space, decoupling representation learning from cluster formation and enabling flexible inference. The approach is evaluated on simulated data from a highly granular calorimeter, where the task is to separate highly overlapping particle showers represented as sets of calorimeter hits. A direct comparison with object condensation (OC) is performed using identical graph neural network backbones and equal latent dimensionality, isolating the effect of the learning objective. The CML method produces a more stable and separable
embedding geometry for both electromagnetic and hadronic particle showers, leading to improved local neighbourhood consistency, a more reliable separation of overlapping showers, and better generalization when extrapolating to unseen multiplicities and energies. This translates directly into higher reconstruction efficiency and purity, particularly in high-multiplicity regimes, as well as improved energy resolution. In mixed-particle environments, CML maintains strong performance, suggesting robust learning of the shower
topology, while OC exhibits significant degradation. These results demonstrate that similarity-based representation learning combined with density-based aggregation is a promising alternative to object-centric approaches for point cloud
segmentation in highly granular detectors.
Read the full abstract ▾
All authors Max Marriott-Clarke, Lazar Novakovic, Elizabeth Ratzer, Robert J. Bainbridge, Loukas Gouskos, Benedikt Maier
Machine Learning
Off-Policy Value-Based Reinforcement Learning for Large Language Models
Peng-Yuan Wang, Ziniu Li, Tian Xu et al. (+8 more)
Improving data utilization efficiency is critical for scaling reinforcement learning (RL) for long-horizon tasks where generating trajectories is expensive. However, the dominant RL methods for LLMs are largely on-policy: they update each batch of data only once, discard it, and then collect fresh samples, resulting in poor sample efficiency. In this work, we explore an alternative value-based RL framework for LLMs that naturally enables off-policy learning. We propose ReVal, a Bellman-update-based method that combines stepwise signals capturing internal consistency with trajectory-level signals derived from outcome verification. ReVal naturally supports replay-buffer-based training, allowing efficient reuse of past trajectories. Experiments on standard mathematical
reasoning benchmarks show that ReVal not only converges faster but also outperforms GRPO in final performance. On DeepSeek-R1-Distill-1.5B, ReVal improves training efficiency and achieves improvement of 2.7% in AIME24 and 4.5% in out-of-domain
benchmark GPQA over GRPO. These results suggest that value-based RL is a practical alternative to policy-based methods for LLM training.
Read the full abstract ▾
All authors Peng-Yuan Wang, Ziniu Li, Tian Xu, Bohan Yang, Tian-Shuo Liu, ChenYang Wang, Xiong-Hui Chen, Yi-Chen Li, Tianyun Yang, Congliang Chen, Yang Yu
Machine Learning
Robustness Quantification for Discriminative Models: a New Robustness Metric and its Application to Dynamic Classifier Selection
Rodrigo F. L. Lassance and Jasper De Bock
Among the different possible strategies for evaluating the reliability of individual predictions of classifiers, robustness quantification stands out as a method that evaluates how much uncertainty a classifier could cope with before changing its prediction. However, its applicability is more limited than some of its alternatives, since it requires the use of generative models and restricts the analyses either to specific model architectures or discrete features. In this work, we propose a new robustness metric applicable to any probabilistic discriminative classifier and any type of features. We demonstrate that this new metric is capable of distinguishing between reliable and unreliable predictions, and use this observation to develop new strategies for dynamic classifier selection.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.CV
ARGENT: Adaptive Hierarchical Image-Text Representations
Chuong Huynh, Hossein Souri, Abhinav Kumar et al. (+3 more)
Large-scale
Vision-
Language Models (VLMs) such as CLIP learn powerful semantic representations but operate in Euclidean space, which fails to capture the inherent hierarchical structure of visual and linguistic concepts.
Hyperbolic geometry, with its exponential volume growth, offers a principled alternative for
embedding such hierarchies with low distortion. However, existing
hyperbolic VLMs use entailment losses that are unstable: as parent
embeddings contract toward the origin, their entailment cones widen toward a half-space, causing catastrophic cone collapse that destroys the intended hierarchy. Additionally, hierarchical evaluation of these models remains unreliable, being largely
retrieval-based and correlation-based metrics and prone to taxonomy dependence and ambiguous negatives. To address these limitations, we propose an adaptive entailment loss paired with a norm regularizer that prevents cone collapse without heuristic aperture clipping. We further introduce an angle-based probabilistic entailment protocol (PEP) for evaluating hierarchical understanding, scored with AUC-ROC and Average Precision. This paper introduces a stronger
hyperbolic VLM baseline ARGENT, Adaptive hieRarchical imaGe-tExt represeNTation. ARGENT improves the SOTA
hyperbolic VLM by 0.7, 1.1, and 0.8 absolute points on image classification, text-to-image
retrieval, and proposed hierarchical metrics, respectively.
Read the full abstract ▾
All authors Chuong Huynh, Hossein Souri, Abhinav Kumar, Vitali Petsiuk, Deen Dayal Mohan, Suren Kumar
Machine Learning · Cross-listed from stat.ML
Sharp Statistical Thresholds for Attributed Gaussian Graph Matching
Mohammad Hassan Ahmad Yarandi and Luca Ganassali
We investigate the problem of matching networks where both edge weights and node features are correlated following a specific node correspondence. While prior work has established sharp thresholds for matching either graphs or features individually, the joint setting has been significantly less explored. In this study, we derive precise information-theoretic thresholds for exact recovery, almost-exact recovery, and partial recovery of the underlying
alignment. These are expressed in terms of graph and feature correlation strengths, the number of nodes, and the dimension of the features. Interestingly, whereas an all-or-nothing phase transition is observed in the standard graph-matching scenario, the inclusion of contextual information at the node level introduces a richer structure: the exact-recovery threshold separates from the shared threshold for almost-exact and partial recovery. Closing gaps left by prior works, we provide a sharp characterization of the thresholds governing how structural and contextual information interact in graph matching, and thereby establish a
benchmark for designing efficient
algorithms in the high-dimensional setting.
Read the full abstract ▾
Machine Learning
A Comparative Study of Machine Learning Models for Hourly Forecasting of Air Temperature and Relative Humidity
Jiaqi Dong
Accurate short-term
forecasting of air temperature and relative humidity is critical for urban management, especially in topographically complex cities such as Chongqing, China. This study compares seven machine learning models: eXtreme Gradient Boosting (XGBoost), Random Forest, Support Vector Regression (SVR), Multi-Layer Perceptron (MLP), Decision Tree, Long Short-Term
Memory (LSTM) networks, and Convolutional Neural Network (CNN)-LSTM (CNN-LSTM), for hourly prediction using real-world open data. Based on a unified framework of data preprocessing, lag-feature construction, rolling statistical features, and time-series validation, the models are systematically evaluated in terms of predictive accuracy and robustness. The results show that XGBoost achieves the best overall performance, with a test mean absolute error (MAE) of 0.302 {\deg}C for air temperature and 1.271% for relative humidity, together with an average R2 of 0.989 across the two
forecasting tasks. These findings demonstrate the strong effectiveness of tree-based ensemble learning for structured meteorological time-series
forecasting and provide practical guidance for intelligent meteorological
forecasting in mountainous cities.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.CR
Not All Tokens Are Created Equal: Query-Efficient Jailbreak Fuzzing for LLMs
Wenyu Chen, Xiangtao Meng, Chuanchao Zang et al. (+6 more)
Large
Language Models(LLMs) are widely deployed, yet are vulnerable to jailbreak
prompts that elicit policy-violating outputs. Although prior studies have uncovered these risks, they typically treat all
tokens as equally important during
prompt mutation, overlooking the varying contributions of individual
tokens to triggering model refusals. Consequently, these attacks introduce substantial redundant searching under query-constrained scenarios, reducing attack efficiency and hindering comprehensive vulnerability assessment. In this work, we conduct a
token-level analysis of refusal behavior and observe that
token contributions are highly skewed rather than uniform. Moreover, we find strong cross-model consistency in refusal tendencies, enabling the use of a surrogate model to estimate
token-level contributions to the target model's refusals. Motivated by these findings, we propose TriageFuzz, a
token-aware jailbreak fuzzing framework that adapts the fuzz testing approach with a series of customized designs. TriageFuzz leverages a surrogate model to estimate the contribution of individual
tokens to refusal behaviors, enabling the identification of sensitive regions within the
prompt. Furthermore, it incorporates a refusal-guided evolutionary strategy that adaptively weights candidate
prompts with a lightweight scorer to steer the
evolution toward bypassing safety constraints. Extensive experiments on six open-source LLMs and three commercial APIs demonstrate that TriageFuzz achieves comparable attack success rates (ASR) with significantly reduced query costs. Notably, it attains a 90% ASR with over 70% fewer queries compared to baselines. Even under an extremely restrictive budget of 25 queries, TriageFuzz outperforms existing methods, improving ASR by 20-40%.
Read the full abstract ▾
All authors Wenyu Chen, Xiangtao Meng, Chuanchao Zang, Li Wang, Xinyu Gao, Jianing Wang, Peng Zhan, Zheng Li, Shanqing Guo