Machine Learning · Cross-listed from cs.CV
Scalable Evaluation of the Realism of Synthetic Environmental Augmentations in Images
Damian J. Ruck, Paul Vautravers, Oliver Chalkley et al. (+1 more)
Evaluation of AI systems often requires synthetic test cases, particularly for rare or safety-critical conditions that are difficult to observe in operational data. Generative AI offers a promising approach for producing such data through controllable image editing, but its usefulness depends on whether the resulting images are sufficiently realistic to support meaningful evaluation. We present a scalable framework for assessing the realism of synthetic image-editing methods and apply it to the task of adding environmental conditions-fog, rain, snow, and nighttime-to car-mounted camera images. Using 40 clear-day images, we compare rule-based augmentation libraries with generative AI image-editing models. Realism is evaluated using two complementary automated metrics: a
vision-
language model (VLM) jury for perceptual realism assessment, and
embedding-based distributional analysis to measure similarity to genuine adverse-condition imagery. Generative AI methods substantially outperform rule-based approaches, with the best generative method achieving approximately 3.6 times the acceptance rate of the best rule-based method. Performance varies across conditions: fog proves easiest to simulate, while nighttime transformations remain challenging. Notably, the VLM jury assigns imperfect acceptance even to real adverse-condition imagery, establishing practical ceilings against which synthetic methods can be judged. By this standard, leading generative methods match or exceed real-image performance for most conditions. These results suggest that modern generative image-editing models can enable scalable generation of realistic adverse-condition imagery for evaluation pipelines. Our framework therefore provides a practical approach for scalable realism evaluation, though validation against human studies remains an important direction for future work.
Read the full abstract ▾
All authors Damian J. Ruck, Paul Vautravers, Oliver Chalkley, Jake Thomas
Machine Learning
PTOPOFL: Topology-Guided Personalised Federated Learning with Persistent-Homology Client Descriptors
Kelly L Vomo-Donfack, Adryel Hoszu, Grégory Ginot et al. (+1 more)
Clustered and personalised
federated learning (FL) needs a signal telling the server which clients should share a model. Most methods derive it from losses or model updates that must be recomputed during training. We study pTopoFL, which derives it once, before training, from a compact persistent-homology (PH) descriptor of each client's feature distribution: the server clusters clients on these descriptors, weights them within clusters, and runs blended clustered local gradient descent, returning one personalised model per cluster. For strongly convex, smooth losses we analyse the complete procedure: for any partition, one round is a contraction with factor (1-eta*mu)^tau; the fixed point is characterised by a local-step drift bound, an exact formula for the effective strength of blending (which yields a calibration rule) and a
stochastic floor exposing a bias-variance trade-off of clustering; and personalisation lowers the heterogeneity floor in proportion to a measurable share of the dispersion of client optima. Experiments on synthetic federations, a label-skew
benchmark and a real four-hospital
dataset confirm the theory and delimit the method. When feature geometry and decision rules co-vary, the PH partition recovers the latent client groups, including differences a linear-subspace descriptor misses, and pTopoFL is competitive with the strongest clustered baselines; on the real federation it lowers the test log-loss of FedAvg from 0.463 to 0.438, on par with the best personalised methods. When heterogeneity is invisible in feature geometry, it offers no advantage over FedAvg. pTopoFL transmits model parameters and is no more private than FedAvg; we give a record-level differential-
privacy accounting and show that privatising the descriptor destroys the partition. Code reproduces every number.
Read the full abstract ▾
All authors Kelly L Vomo-Donfack, Adryel Hoszu, Grégory Ginot, Ian Morilla
Machine Learning · Cross-listed from cs.CL
World Properties without World Models: Distributional Associations and the Interpretation of Decoding Results from Language Models
Elan Barenholtz
A growing literature shows that variables can be linearly decoded from the activations of large
language models (LLMs). These range from properties of the world, such as the locations of cities and the lifetimes of historical figures, to
emotions and pain. Such findings are often taken as evidence that
language models go beyond surface text statistics and form internal models of the world. We show that static word
embeddings (fixed, context-insensitive representations learned from corpus statistics) of the same or matched stimuli support much of the same decoding. Across four published cases (place, time, pain and
emotion), static vectors predict coordinates and year of death (R^2 = 0.42-0.59), separate pain from matched control sentences (held-out AUC 0.85-0.88), and classify twelve
emotions in stories written to avoid naming them (AUC 0.84-0.88). Because static
embeddings assign each word a single, context-independent vector, these results are a lower bound on what word associations alone can support. The LLMs retain clear advantages on representational tests, and causal and behavioral findings remain outside the scope of the baseline. On the original authors' entities, where we reproduce their Llama-2 results, the
transformer's advantage lies mostly in placing historical figures in the right century and places in the right country, coarse sorting that richer word associations would be expected to improve; within those groups every representation orders items poorly. Static vectors for disambiguated Wikipedia entities, which carry the associations of a particular place or person rather than of the words in its name, close most of the remaining gap, matching Pythia-2.8B on coordinates and Llama-2-7B on year of death. These results indicate that decodability alone cannot distinguish a representation of a property from information already available in fixed distributional associations.
Read the full abstract ▾
Machine Learning
CRESTomics: Analyzing Carotid Plaques in the CREST-2 Trial with a New Additive Classification Model
Pranav Kulkarni, Brajesh K. Lal, Georges Jreij et al. (+11 more)
Accurate characterization of carotid plaques is critical for stroke prevention in patients with carotid stenosis. We analyze 500 plaques from CREST-2, a multi-center clinical trial, to identify radiomics-based markers from B-mode ultrasound images linked with high-risk. We propose a new kernel-based additive model, combining coherence loss with group-sparse regularization for nonlinear classification. Group-wise additive effects of each feature group are visualized using partial dependence plots. Results indicate our method accurately and interpretably assesses plaques, revealing a strong association between plaque texture and clinical risk.
Read the full abstract ▾
All authors Pranav Kulkarni, Brajesh K. Lal, Georges Jreij, Sai Vallamchetla, Langford Green, Jenifer Voeks, John Huston, Lloyd Edwards, George Howard, Bradley A. Maron, Thomas G. Brott, James F. Meschia, Florence X. Doo, Heng Huang
Machine Learning
Activation Outliers in Transformer Quantization: Reproduction, Statistical Analysis, and Deployment Tradeoffs
Pranav Kumar Kaliaperumal
Post-training quantization (PTQ) of
transformers is known to suffer from severe accuracy degradation due to structured activation outliers, as originally analyzed by Bondarenko et al. (EMNLP 2021) in work associated with Qualcomm AI Research. This paper provides a reproducible empirical reproduction and systems-level extension of that phenomenon in BERT-base fine-tuned on QNLI. When global W8A8 quantization is applied, validation accuracy drops sharply from 89.66% (FP32) to 54.33%, a decrease of 35.33 points. Statistical analysis of FP32 activations shows strongly heavy-tailed behavior that intensifies with model depth: kurtosis reaches 271 in the final layers and approximately 55% of activation energy is concentrated in the top 1% of channels. We evaluate several mitigation strategies. Mixed precision PTQ restores accuracy close to the FP32 baseline (89.42%). Per-
embedding-group (PEG) quantization shows strong sensitivity to grouping structure, improving accuracy from 66.12% with three groups to 86.18% with four groups. In contrast, percentile-based calibration, even at thresholds between 99.0 and 99.99, fails to recover accuracy (about 50.54%), indicating that large activation channels encode structured signal rather than rare noise. Deployment profiling on an RTX 3050 GPU shows minimal differences in latency and
memory usage across methods (median latency about 58-59 ms; VRAM usage about 484-486 MB), highlighting the importance of hardware-aware evaluation. Overall, the results show that PTQ failure in
transformers is primarily driven by structured channel dominance amplified through residual connections. Effective mitigation therefore requires channel-aware precision allocation rather than scalar clipping alone.
Read the full abstract ▾
Machine Learning
LUMINA: Foundation Models for Topology Transferable ACOPF
Yijiang Li, Zeeshan Memon, Hongwei Jin et al. (+7 more)
Foundation models in general promise to accelerate scientific computation by learning reusable representations across problem instances, yet constrained scientific systems, where predictions must satisfy physical laws and safety limits, pose unique challenges that stress conventional training paradigms. We derive design principles for constrained scientific foundation models through systematic investigation of AC optimal power flow (ACOPF), a representative optimization problem in power grid operations where power balance equations and operational constraints are non-negotiable. Through controlled experiments spanning architectures, training objectives, and system diversity, we extract three empirically grounded principles governing scientific foundation model design. These principles characterize three design trade-offs: learning physics-invariant representations while respecting system-specific constraints, optimizing accuracy while ensuring constraint satisfaction, and ensuring reliability in high-impact operating regimes. We present the LUMINA framework, including data processing and training pipelines to support reproducible research on physics-informed, feasibility-aware foundation models across scientific applications.
Read the full abstract ▾
All authors Yijiang Li, Zeeshan Memon, Hongwei Jin, Stefano Fenu, Keunju Song, Sunash B Sharma, Parfait Gasana, Hongseok Kim, Liang Zhao, Kibaek Kim
Machine Learning · Cross-listed from cs.SD
LabelBuddy: An Open Source Music and Audio Language Annotation Tagging Tool Using AI Assistance
Ioannis Prokopiou, Ioannis Sina, Agisilaos Kounelis et al. (+2 more)
The advancement of Machine learning (ML), Large Audio
Language Models (LALMs), and autonomous AI
agents in Music Information
Retrieval (MIR) necessitates a shift from static tagging to rich, human-aligned representation learning. However, the scarcity of open-source infrastructure capable of capturing the subjective nuances of audio annotation remains a critical bottleneck. This paper introduces LabelBuddy, an open-source collaborative auto-tagging audio annotation tool designed to bridge the gap between human intent and machine understanding. Unlike static tools, it decouples the interface from inference via containerized backends, allowing users to plug in custom models for AI-assisted pre-annotation. We describe the system architecture, which supports multi-user consensus, containerized model isolation, and a roadmap for extending
agents and LALMs. Code available at https://github.com/GiannisProkopiou/gsoc2022-Label-buddy.
Read the full abstract ▾
All authors Ioannis Prokopiou, Ioannis Sina, Agisilaos Kounelis, Pantelis Vikatos, Themos Stafylakis
Machine Learning
IPD: Boosting Sequential Policy with Imaginary Planning Distillation in Offline Reinforcement Learning
Yihao Qin, Yuanfei Wang, Hang Zhou et al. (+3 more)
Decision
transformer based sequential policies have emerged as a powerful paradigm in offline reinforcement learning (RL), yet their efficacy remains constrained by the quality of static
datasets and inherent architectural limitations. Specifically, these models often struggle to effectively integrate suboptimal experiences and fail to explicitly plan for an optimal policy. To bridge this gap, we propose Imaginary Planning
Distillation (IPD), a novel framework that seamlessly incorporates offline planning into data generation, supervised training, and online inference. Our framework first learns a world model equipped with uncertainty measures and a quasi-optimal value function from the offline data. These components are utilized to identify suboptimal trajectories and augment them with reliable, imagined optimal rollouts generated via Model Predictive Control (MPC). A
Transformer-based sequential policy is then trained on this enriched
dataset, complemented by a value-guided objective that promotes the
distillation of the optimal policy. By replacing the conventional, manually-tuned return-to-go with the learned quasi-optimal value function, IPD improves both decision-making stability and performance during inference. Empirical evaluations on the D4RL
benchmark demonstrate that IPD significantly outperforms several state-of-the-art value-based and
transformer-based offline RL methods across diverse tasks.
Read the full abstract ▾
All authors Yihao Qin, Yuanfei Wang, Hang Zhou, Peiran Liu, Hao Dong, Yiding Ji
Machine Learning
Causality Elicitation from Large Language Models
Takashi Kameyama, Masahiro Kato, Yasuko Hio et al. (+2 more)
Large
language models (LLMs) are trained on enormous amounts of data and encode knowledge in their parameters. We propose a pipeline to elicit causal relationships from LLMs. Specifically, (i) we sample many documents from LLMs on a given topic, (ii) we extract an event list from from each document, (iii) we group events that appear across documents into canonical events, (iv) we construct a binary indicator vector for each document over canonical events, and (v) we estimate candidate causal graphs using causal discovery methods. Our approach does not guarantee real-world causality. Rather, it provides a framework for presenting the set of causal hypotheses that LLMs can plausibly assume, as an inspectable set of variables and candidate graphs.
Read the full abstract ▾
All authors Takashi Kameyama, Masahiro Kato, Yasuko Hio, Yasushi Takano, Naoto Minakawa
Machine Learning · Cross-listed from cs.CL
Memex(RL): Scaling Long-Horizon LLM Agents via Indexed Experience Memory
Zhenting Wang, Huancheng Chen, Jiayun Wang et al. (+1 more)
Large
language model (LLM)
agents are fundamentally bottlenecked by finite context windows on long-horizon tasks. As trajectories grow, retaining tool outputs and intermediate
reasoning in-context quickly becomes infeasible: the working context becomes prohibitively long, eventually exceeds the context budget, and makes distant evidence harder to use even when it is still present. Existing solutions typically shorten context through truncation or running summaries, but these methods are fundamentally lossy because they compress or discard past evidence itself. We introduce Memex, an indexed experience
memory mechanism that instead compresses context without discarding evidence. Memex maintains a compact working context consisting of concise structured summaries and stable indices, while storing full-fidelity underlying interactions in an external experience database under those indices. The
agent can then decide when to dereference an index and recover the exact past evidence needed for the current subgoal. We optimize both write and read behaviors with our reinforcement learning framework MemexRL, using reward shaping tailored to indexed
memory usage under a context budget, so the
agent learns what to summarize, what to archive, how to index it, and when to retrieve it. This yields a substantially less lossy form of long-horizon
memory than summary-only approaches. We further provide a theoretical analysis showing the potential of the Memex loop to preserve decision quality with bounded dereferencing while keeping effective in-context computation bounded as history grows. Empirically, on challenging long-horizon tasks, Memex
agent trained with MemexRL improves task success while using a significantly smaller working context.
Read the full abstract ▾
All authors Zhenting Wang, Huancheng Chen, Jiayun Wang, Wei Wei
Machine Learning
Online Learning for Multi-Layer Hierarchical Inference under Partial and Policy-Dependent Feedback
Haoran Zhang, Seohyeon Cha, Hasan Burhan Beytur et al. (+3 more)
Hierarchical inference systems route tasks across multiple computational layers, where each node may either finalize a prediction locally or offload the task to a node in the next layer for further processing. Learning optimal routing policies in such systems is challenging: inference loss is defined recursively across layers, while feedback on prediction error is revealed only at a terminal oracle layer. This induces a partial, policy-dependent feedback structure in which observability probabilities decay with depth, causing importance-weighted
estimators to suffer from amplified variance. We study online routing for multi-layer hierarchical inference under long-term resource constraints and terminal-only feedback. We formalize the recursive loss structure and show that naive importance-weighted contextual bandit methods become unstable as feedback probability decays along the hierarchy. To address this, we develop a variance-reduced EXP4-based
algorithm integrated with Lyapunov optimization, yielding unbiased loss estimation and stable learning under sparse and policy-dependent feedback. We provide regret guarantees relative to the best fixed routing policy in hindsight and establish near-optimality under
stochastic arrivals and resource constraints. Experiments on large-scale multi-task workloads demonstrate improved stability and performance compared to standard importance-weighted approaches.
Read the full abstract ▾
All authors Haoran Zhang, Seohyeon Cha, Hasan Burhan Beytur, Kevin S Chan, Gustavo de Veciana, Haris Vikalo
Machine Learning · Cross-listed from cs.AI
Agentics 2.0: Logical Transduction Algebra for Agentic Data Workflows
Alfio Massimiliano Gliozzo, Junkyu Lee and Nahuel Defosse
Agentic AI is rapidly transitioning from research prototypes to enterprise deployments, where requirements extend to meet the software quality attributes of reliability, scalability, and observability beyond plausible text generation. We present Agentics 2.0, a lightweight, Python-native framework for building high-quality, structured, explainable, and type-safe agentic data workflows. At the core of Agentics 2.0, the logical transduction
algebra formalizes a large
language model inference call as a typed semantic transformation, which we call a transducible function that enforces schema validity and the locality of evidence. The transducible functions compose into larger programs via algebraically grounded operators and execute as stateless asynchronous calls in parallel in asynchronous Map-Reduce programs. The proposed framework provides semantic reliability through strong typing, semantic observability through evidence tracing between slots of the input and output types, and scalability through stateless parallel execution. We instantiate reusable design patterns and evaluate the programs in Agentics 2.0 on challenging
benchmarks, including DiscoveryBench for data-driven discovery and Archer for NL-to-SQL semantic parsing, demonstrating state-of-the-art performance.
Read the full abstract ▾
Machine Learning
Nearest-Neighbor Density Estimation for Dependency Suppression
Kathleen Anderson and Thomas Martinetz
The ability to remove unwanted dependencies from data is crucial in various domains, including
fairness, robust learning, and
privacy protection. In this work, we propose an encoder-based approach that learns a representation independent of a sensitive variable but otherwise preserving essential data characteristics. Unlike existing methods that rely on decorrelation or
adversarial learning, our approach explicitly estimates and modifies the data distribution to neutralize statistical dependencies. To achieve this, we combine a specialized variational autoencoder with a novel loss function driven by non-parametric nearest-neighbor density estimation, enabling direct optimization of independence. We evaluate our approach on multiple
datasets, demonstrating that it can outperform existing unsupervised techniques and even rival supervised methods in balancing information removal and utility.
Read the full abstract ▾
Machine Learning · Cross-listed from stat.ML
Semi-Supervised Generative Learning via Latent Space Distribution Matching
Kwong Yu Chong and Long Feng
We introduce Latent Space Distribution Matching (LSDM), a novel framework for semi-supervised generative modeling of conditional distributions. LSDM operates in two stages: (i) learning a low-dimensional latent space from both paired and unpaired data, and (ii) performing joint distribution matching in this space via the 1-Wasserstein distance, using only paired data. This two-step approach minimizes an upper bound on the 1-Wasserstein distance between joint distributions, reducing reliance on scarce paired samples while enabling fast one-step generation. Theoretically, we establish non-asymptotic error bounds and demonstrate a key benefit of unpaired data: enhanced
geometric fidelity in generated outputs. Furthermore, by extending the scope of its two core steps, LSDM provides a coherent statistical perspective that connects to a broad class of latent-space approaches. Notably, Latent
Diffusion Models (LDMs) can be viewed as a variant of LSDM, in which joint distribution matching is achieved indirectly via score matching. Consequently, our results also provide theoretical insights into the consistency of LDMs. Empirical evaluations on real-world image tasks, including class-conditional generation and image super-resolution, demonstrate the effectiveness of LSDM in leveraging unpaired data to enhance generation quality.
Read the full abstract ▾
Machine Learning
Beyond Edge Deletion: A Comprehensive Approach to Counterfactual Explanation in Graph Neural Networks
Matteo De Sanctis, Riccardo De Sanctis, Stefano Faralli et al. (+2 more)
Graph Neural Networks (GNNs) are increasingly adopted across domains such as molecular biology and social network analysis, yet their black-box nature hinders interpretability and trust. This is especially problematic in high-stakes applications, such as predicting molecule toxicity, drug discovery, or guiding financial fraud detections, where transparent explanations are essential. Counterfactual explanations - minimal changes that flip a model's prediction - offer a transparent lens into GNNs' behavior. In this work, we introduce XPlore, a novel technique that significantly broadens the counterfactual search space. It consists of gradient-guided perturbations to adjacency and node feature
matrices. Unlike most prior methods, which focus solely on edge deletions, our approach belongs to the growing class of techniques that optimize edge insertions and node-feature perturbations, here jointly performed under a unified gradient-based framework, enabling a richer and more nuanced exploration of counterfactuals. To quantify both structural and semantic fidelity, we introduce a cosine similarity metric for learned graph
embeddings that addresses a key limitation of traditional distance-based metrics, and demonstrate that XPlore produces more coherent and minimal counterfactuals. Empirical results on 13 real-world and 5 synthetic
benchmarks show up to +56.3% improvement in validity and +52.8% in fidelity over state-of-the-art baselines, while retaining competitive runtime.
Read the full abstract ▾
All authors Matteo De Sanctis, Riccardo De Sanctis, Stefano Faralli, Paola Velardi, Bardh Prenkaj
Machine Learning · Cross-listed from stat.ML
Beyond Mixtures and Products for Ensemble Aggregation: A Likelihood Perspective on Generalized Means
Raphaël Razafindralambo, Rémy Sun, Frédéric Precioso et al. (+2 more)
Density aggregation is a central problem in machine learning, for instance when combining predictions from a Deep Ensemble. The choice of aggregation remains an open question with two commonly proposed approaches being linear pooling (probability averaging) and
geometric pooling (logit averaging). In this work, we address this question by studying the normalized generalized mean of order $r \in \mathbb{R} \cup \{-\infty,+\infty\}$ through the lens of log-likelihood, the standard evaluation criterion in machine learning. This provides a unifying aggregation formalism and shows different optimal configurations for different situations. We show that the regime $r \in [0,1]$ is the only range ensuring systematic improvements relative to individual distributions, thereby providing a principled justification for the reliability and widespread practical use of linear ($r=1$) and
geometric ($r=0$) pooling. In contrast, we show that aggregation rules with $r \notin [0,1]$ may fail to provide consistent gains with explicit counterexamples. Finally, we corroborate our theoretical findings with empirical evaluations using Deep Ensembles on image and text classification
benchmarks.
Read the full abstract ▾
All authors Raphaël Razafindralambo, Rémy Sun, Frédéric Precioso, Damien Garreau, Pierre-Alexandre Mattei
Machine Learning · Cross-listed from math.ST
Cameron Bell, Timothy Johnston, Antoine Luciano et al. (+1 more)
Theoretical and applied research into
privacy encompasses an incredibly broad swathe of differing approaches, emphases and aims. This work introduces a novel quantitative notion of
privacy that is both contextual and specific. Building on and extending ideas from statistical disclosure control and differential
privacy, our aim is to model the implications of a disclosure decision in an
adversarial setting. Our definition relies on concepts inherent to standard
Bayesian decision theory, while departing from them in several important respects. In particular, (i) inference about the data itself becomes meaningful and (ii) the party controlling the release of sensitive information should make disclosure decisions from the prior viewpoint, rather than conditional on the data, which is a feature shared with
Bayesian design. Illuminating toy examples are exploited towards highlighting the specificities of the method.
Read the full abstract ▾
All authors Cameron Bell, Timothy Johnston, Antoine Luciano, Christian P Robert
Machine Learning · Cross-listed from stat.ML
Stable and Steerable Sparse Autoencoders with Weight Regularization
Piotr Jedryszek and Oliver M. Crook
Sparse autoencoders (SAEs) are widely used to extract human-interpretable features from neural network activations, but their learned features can vary substantially across random seeds and training choices. To improve stability, we studied weight regularization by adding L1 or L2 penalties on encoder and decoder weights, and evaluate how regularization interacts with common SAE training defaults. On MNIST, we observe that L2 weight regularization produces a core of highly aligned features and, when combined with tied initialization and unit-norm decoder constraints, it dramatically increases cross-seed feature consistency. For TopK SAEs trained on
language model activations (Pythia-70M-deduped), adding a small L2 weight penalty increased the fraction of features shared across three random seeds and roughly doubles steering success rates, while leaving the mean of automated interpretability scores essentially unchanged. Finally, in the regularized setting, activation steering success becomes better predicted by auto-interpretability scores, suggesting that regularization can align text-based feature explanations with functional controllability.
Read the full abstract ▾
Machine Learning
Noise-aware Client Selection for carbon-efficient Federated Learning via Gradient Norm Thresholding
Patrick Wilhelm, Inese Yilmaz and Odej Kao
Training large-scale Neural Networks requires substantial computational power and energy.
Federated Learning enables distributed model training across geospatially distributed data centers, leveraging renewable energy sources to reduce the carbon footprint of AI training. Various client selection strategies have been developed to align the
volatility of renewable energy with stable and fair model training in a
federated system. However, due to the
privacy-preserving nature of
Federated Learning, the quality of data on client devices remains unknown, posing challenges for effective model training. In this paper, we introduce a modular approach on top to state-of-the-art client selection strategies for carbon-efficient
Federated Learning. Our method enhances robustness by incorporating a noisy client data filtering, improving both model performance and sustainability in scenarios with unknown data quality. Additionally, we explore the impact of carbon budgets on model convergence, balancing efficiency and sustainability. Through extensive evaluations, we demonstrate that modern client selection strategies based on local client loss tend to select clients with noisy data, ultimately degrading model performance. To address this, we propose a gradient norm thresholding mechanism using probing rounds for more effective client selection and noise detection, contributing to the practical deployment of carbon-efficient
Federated Learning.
Read the full abstract ▾
Machine Learning
REDNET-ML: A Multi-Sensor Machine Learning Pipeline for Harmful Algal Bloom Risk Detection Along the Omani Coast
Ameer Alhashemi
Harmful algal blooms (HABs) can threaten coastal infrastructure, fisheries, and desalination dependent water supplies. This project (REDNET-ML) develops a reproducible machine learning pipeline for HAB risk detection along the Omani coastline using multi sensor satellite data and non leaky evaluation. The system fuses (i) Sentinel-2 optical chips (high spatial resolution) processed into spectral indices and texture signals, (ii) MODIS Level-3 ocean color and thermal indicators, and (iii) learned image evidence from object detectors trained to highlight bloom like patterns. A compact decision fusion model (CatBoost) integrates these signals into a calibrated probability of HAB risk, which is then consumed by an end to end inference workflow and a risk field viewer that supports operational exploration by site (plant) and time. The report documents the motivation, related work, methodological choices (including label mining and strict split strategies), implementation details, and a critical evaluation using AUROC/AUPRC, confusion
matrices, calibration curves, and drift analyses that quantify distribution shift in recent years.
Read the full abstract ▾
Machine Learning
Architectural Proprioception in State Space Models: Thermodynamic Training Induces Anticipatory Halt Detection
Jay Noon
We introduce the Probability
Navigation Architecture (PNA) framework, which treats neural computation as
navigation through a probability
manifold governed by thermodynamic principles. We train State Space Models (SSMs) and
Transformers with a novel thermodynamic loss function that penalizes computational waste alongside standard cross-
entropy. Across 19 experimental phases, we discover that thermodynamically-trained SSMs develop architectural proprioception: a strong anticipatory coupling between recurrent state
entropy and halt confidence (r = -0.836, p < 0.001) in which the halt signal leads state
entropy collapse by exactly two
tokens (tau = -2.0). This Universal Stopping Signature (USS) reproduces to four decimal places across random seeds and generalizes to a structurally distinct sorting task. Critically,
Transformers trained identically show no such coupling (r = -0.07), demonstrating that the phenomenon is architecture-dependent. Cross-task transfer experiments confirm that SSM halt detection reflects genuine meta-cognition (zero-shot transfer F1: SSMs 64.2% vs.
Transformers 69.3%; post-adaptation: SSMs 94.5% vs.
Transformers 86.4%), while
Transformer halt detection relies on syntactic pattern matching. A 2D hyperparameter sweep over energy penalty (alpha) and halt supervision (beta) reveals that the anticipatory coupling is continuously controllable through training, with thermodynamic pressure serving as the primary induction mechanism and explicit halt supervision as an amplifier. Our results establish that SSMs are thermodynamically native architectures whose fixed-size recurrent states naturally support the Markovian compression that enables computational self-awareness, with implications for cost-aware inference, dynamic
token budgets, and confidence-based routing in production systems.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.SE
CodeTaste: Can LLMs Generate Human-Level Code Refactorings?
Alex Thillen, Niels Mündler, Veselin Raychev et al. (+1 more)
LLM coding
agents can generate working code, but their solutions often accumulate complexity, duplication, and architectural debt. Human developers address such issues through refactoring: behavior-preserving program transformations that improve structure and maintainability. We investigate whether
agents (i) can execute refactorings reliably and (ii) identify the refactorings that human developers actually chose in real codebases. To this end, we construct CodeTaste, a
benchmark mined from large multi-file open-source refactorings. To score solutions, we combine repository test suites that measure functional correctness with tailored static checks that verify removal of undesired and introduction of desired code patterns using dataflow
reasoning. Our results show a clear gap:
agents perform well at implementing refactorings that are specified in detail, but often fail to discover the human refactoring choices when given a focus area for changes. A propose-then-implement decomposition improves
alignment, and selecting the best-aligned proposal before implementation can yield further gains. CodeTaste provides an evaluation target and a potential preference signal for aligning coding
agents with human refactoring decisions in realistic codebases. We release the
benchmark, leaderboard, and code.
Read the full abstract ▾
All authors Alex Thillen, Niels Mündler, Veselin Raychev, Martin Vechev
Machine Learning · Cross-listed from cs.RO
Learning Hip Exoskeleton Control Policy via Predictive Neuromusculoskeletal Simulation
Ilseung Park, Changseob Song and Inseung Kang
Developing exoskeleton controllers that generalize across diverse locomotor conditions typically requires extensive motion-capture data and biomechanical labeling, limiting scalability beyond instrumented laboratory settings. Here, we present a physics-based neuromusculoskeletal learning framework that trains a hip-exoskeleton control policy entirely in simulation, without motion-capture demonstrations, and deploys it on hardware via policy
distillation. A reinforcement learning teacher policy is trained using a muscle-synergy action prior over a wide range of walking speeds and slopes through a two-stage curriculum, enabling direct comparison between assisted and no-exoskeleton conditions. In simulation, exoskeleton assistance reduces mean muscle activation by up to 3.4% and mean positive joint power by up to 7.0% on level ground and ramp ascent, with benefits increasing systematically with walking speed. On hardware, the assistance profiles learned in simulation are preserved across matched speed-slope conditions (r: 0.82, RMSE: 0.03 Nm/kg), providing quantitative evidence of sim-to-real transfer without additional hardware tuning. These results demonstrate that physics-based neuromusculoskeletal simulation can serve as a practical and scalable foundation for exoskeleton controller development, substantially reducing experimental burden during the design phase.
Read the full abstract ▾
Machine Learning
A Multi-Agent Framework for Interpreting Multivariate Physiological Time Series
Davide Gabrielli, Paola Velardi, Stefano Faralli et al. (+1 more)
Continuous physiological monitoring is central to emergency care, yet deploying trustworthy AI is challenging. While LLMs can translate complex physiological signals into clinical narratives, it is unclear how agentic systems perform relative to zero-shot inference. To address these questions, we present Vivaldi, a role-structured multi-
agent system that explains multivariate physiological time series. Due to regulatory constraints that preclude live deployment, we instantiate Vivaldi in a controlled, clinical pilot to a small, highly qualified cohort of emergency medicine experts, whose evaluations reveal a context-dependent picture that contrasts with prevailing assumptions that agentic
reasoning uniformly improves performance. Our experiments show that agentic pipelines substantially benefit non-thinking and medically fine-tuned models, improving expert-rated explanation justification and relevance by +6.9 and +9.7 points, respectively. Contrarily, for thinking models, agentic orchestration often degrades explanation quality, including a 14-point drop in relevance, while improving diagnostic precision (ESI F1 +3.6). We also find that explicit tool-based computation is decisive for codifiable clinical metrics, whereas subjective targets, such as pain scores and length of stay, show limited or inconsistent changes. Expert evaluation further indicates that gains in clinical utility depend on visualization conventions, with medically specialized models achieving the most favorable trade-offs between utility and clarity. Together, these findings show that the value of agentic AI lies in the selective externalization of computation and structure rather than in maximal
reasoning complexity, and highlight concrete design trade-offs and learned lessons, broadly applicable to explainable AI in safety-critical healthcare settings.
Read the full abstract ▾
All authors Davide Gabrielli, Paola Velardi, Stefano Faralli, Bardh Prenkaj
Machine Learning
Unbiased Dynamic Pruning for Efficient Group-Based Policy Optimization
Haodong Zhu, Yangyang Ren, Yanjing Li et al. (+6 more)
Group Relative Policy Optimization (GRPO) effectively scales LLM
reasoning but incurs prohibitive computational costs due to its extensive group-based sampling requirement. While recent selective data utilization methods can mitigate this overhead, they could induce estimation bias by altering the underlying sampling distribution, compromising theoretical rigor and convergence behavior. To address this limitation, we propose Dynamic
Pruning Policy Optimization (DPPO), a framework that enables dynamic
pruning while preserving unbiased gradient estimation through importance sampling-based correction. By incorporating mathematically derived rescaling factors, DPPO significantly accelerates GRPO training without altering the optimization objective of the full-batch baseline. Furthermore, to mitigate the data sparsity induced by
pruning, we introduce Dense
Prompt Packing, a window-based greedy strategy that maximizes valid
token density and hardware utilization. Extensive experiments demonstrate that DPPO consistently accelerates training across diverse models and
benchmarks. For instance, on Qwen3-4B trained on MATH, DPPO achieves 2.37$\times$ training speedup and outperforms GRPO by 3.36% in average accuracy across six mathematical
reasoning benchmarks.
Read the full abstract ▾
All authors Haodong Zhu, Yangyang Ren, Yanjing Li, Mingbao Lin, Linlin Yang, Xuhui Liu, Xiantong Zhen, Haiguang Liu, Baochang Zhang
Machine Learning
InstMeter: An Instruction-Level Method to Predict Energy and Latency of DL Model Inference on MCUs
Hao Liu, Qing Wang and Marco Zuniga
Deep learning (DL) models can now run on microcontrollers (MCUs). Through neural architecture search (NAS), we can search DL models that meet the constraints of MCUs. Among various constraints, energy and latency costs of the model inference are critical metrics. To predict them, existing research relies on coarse proxies such as multiply-accumulations (MACs) and model's input parameters, often resulting in inaccurate predictions or requiring extensive data collection. In this paper, we propose InstMeter, a predictor leveraging MCUs' clock cycles to accurately estimate the energy and latency of DL models. Clock cycles are fundamental metrics reflecting MCU operations, directly determining energy and latency costs. Furthermore, a unique property of our predictor is its strong linearity, allowing it to be simple and accurate. We thoroughly evaluate InstMeter under different scenarios, MCUs, and software settings. Compared with state-of-the-art studies, InstMeter can reduce the energy and latency prediction errors by $3\times$ and $6.5\times$, respectively, while requiring $100\times$ and $10\times$ less training data. In the NAS scenario, InstMeter can fully exploit the energy budget, identifying optimal DL models with higher inference accuracy. We also evaluate InstMeter's generalization performance through various experiments on three ARM MCUs (Cortex-M4, M7, M33) and one RISC-V-based MCU (ESP32-C3), different compilation options (-Os, -O2), GCC versions (v7.3, v10.3), application scenarios (keyword spotting, image recognition), dynamic voltage and frequency scaling, temperatures (21{\deg}C, 43{\deg}C), and software settings (TFLMv2.4, TFLMvCI). We will open our source codes and the MCU-specific
benchmark datasets.
Read the full abstract ▾
Machine Learning · Cross-listed from stat.ML
Exploiting Subgradient Sparsity in Max-Plus Neural Networks
Ikhlas Enaieh and Olivier Fercoq
Deep Neural Networks are powerful tools for solving machine learning problems, but their training often involves dense and costly parameter updates. In this work, we use a novel Max-Plus neural architecture in which classical addition and multiplication are replaced with maximum and summation operations respectively. This is a promising architecture in terms of interpretability, but its training is challenging. A particular feature is that this algebraic structure naturally induces sparsity in the subgradients, as only
neurons that contribute to the maximum affect the loss. However, standard backpropagation fails to exploit this sparsity, leading to unnecessary computations. In this work, we focus on the minimization of the worst sample loss which transfers this sparsity to the optimization loss. To address this, we propose a sparse subgradient
algorithm that explicitly exploits the algebraic sparsity. By tailoring the optimization procedure to the non-smooth nature of Max-Plus models, our method achieves more efficient updates while retaining theoretical guarantees. This highlights a principled path toward bridging algebraic structure and scalable learning.
Read the full abstract ▾
Machine Learning
Two-Stage Photovoltaic Forecasting: Separating Weather Prediction from Plant-Characteristics
Philipp Danner and Hermann de Meer
Several energy management applications rely on accurate photovoltaic generation forecasts. Common metrics like mean absolute error or root-mean-square error, omit error-distribution details needed for
stochastic optimization. In addition, several approaches use weather forecasts as inputs without analyzing the source of the prediction error. To overcome this gap, we decompose
forecasting into a weather forecast model for environmental parameters such as
solar irradiance and temperature and a plant characteristic model that captures site-specific parameters like panel orientation, temperature influence, or regular shading. Satellite-based weather observation serves as an intermediate layer. We analyze the error distribution of the high-resolution rapid-refresh numerical weather prediction model that covers the United States as a black-box model for weather
forecasting and train an ensemble of neural networks on historical power output data for the plant characteristic model. Results show mean absolute error increases by 11% and 68% for two selected photovoltaic systems when using weather forecasts instead of satellite-based ground-truth weather observations as a perfect forecast. The generalized
hyperbolic and Student's t distributions adequately fit the forecast errors across lead times.
Read the full abstract ▾
Machine Learning
Data-Aware Random Feature Kernel for Transformers
Amirhossein Farzam, Hossein Mobahi, Nolan Andrew Miller et al. (+1 more)
Transformers excel across domains, yet their quadratic
attention complexity poses a barrier to scaling. Random-feature
attention, as in Performers, can reduce this cost to linear in the sequence length by approximating the softmax kernel with positive random features drawn from an isotropic distribution. In pretrained models, however, queries and keys are typically anisotropic. This induces high Monte Carlo variance in isotropic sampling schemes unless one retrains the model or uses a large feature budget. Importance sampling can address this by adapting the sampling distribution to the input geometry, but complex data-dependent proposal distributions are often intractable. We show that by data aligning the softmax kernel, we obtain an
attention mechanism which can both admit a tractable minimal-variance proposal distribution for importance sampling, and exhibits better training stability. Motivated by this finding, we introduce DARKFormer, a Data-Aware Random-feature Kernel
transformer that features a data-aligned kernel geometry. DARKFormer learns the random-projection covariance, efficiently realizing an importance-sampled positive random-feature
estimator for its data-aligned kernel. Empirically, DARKFormer narrows the performance gap with exact softmax
attention, particularly in finetuning regimes where pretrained representations are anisotropic. By combining random-feature efficiency with data-aware kernels, DARKFormer advances kernel-based
attention in resource-constrained settings.
Read the full abstract ▾
All authors Amirhossein Farzam, Hossein Mobahi, Nolan Andrew Miller, Luke Sernau
Machine Learning · Cross-listed from cs.AI
BeamPERL: Parameter-Efficient RL with Verifiable Rewards Specializes Compact LLMs for Structured Beam Mechanics Reasoning
Tarjei Paule Hage and Markus J. Buehler
Can reinforcement learning with hard, verifiable rewards teach a compact
language model to reason about physics, or does it primarily learn to pattern-match toward correct answers? We study this question by training a 1.5B-parameter
reasoning model on beam statics, a classic engineering problem, using parameter-efficient RLVR with binary correctness rewards from symbolic solvers, without teacher-generated
reasoning traces. The best BeamPERL checkpoint achieves a 66.7% improvement in Pass@1 over the base model. However, the learned competence is anisotropic: the model generalizes compositionally (more loads) but fails under topological shifts (moved supports) that require the same
equilibrium equations. Intermediate checkpoints yield the strongest
reasoning, while continued optimization degrades robustness while maintaining reward. These findings reveal a key limitation of outcome-level
alignment: reinforcement learning with exact physics rewards induces procedural solution templates rather than internalization of governing equations. The precision of the reward signal - even when analytically exact - does not by itself guarantee transferable physical
reasoning. Our results suggest that verifiable rewards may need to be paired with structured
reasoning scaffolding to move beyond template matching toward robust scientific
reasoning.
Read the full abstract ▾