Reinforcement learning (RL) seeks to optimize sequential decisions to maximize population-level benefits over time. However, when deployed in high-stakes settings such as healthcare, RL decisions might systematically restrict some subpopulation's access to valuable services in a manner contrary to the values and goals of stakeholders. Counterfactual fairness (CF) offers a promising framework to address this problem based on causal reasoning. This paper develops a data preprocessing algorithm that, when used in tandem with policy learning, enables CF in RL. Our algorithm relies on a novel quantile distribution mapping method for sequentially estimating the counterfactual states and rewards in the data preprocessing step, subsuming common additivity assumptions used for counterfactual prediction as a special case. We theoretically prove that the per-step level of counterfactual unfairness and infinite-horizon suboptimality gap can be bounded under mild regularity conditions. We also empirically test our algorithm in numerical experiments as well as in application to a real-world interventional digital health dataset.
The search for new crystalline materials spans an enormous compositional and structural space. Generating candidates in this space requires modeling the relationships between elemental composition, crystallographic symmetry, and crystal geometry. The space group specifies the crystal's symmetry and determines the admissible Wyckoff positions and geometric degrees of freedom; fixing it in advance prevents this global symmetry choice from being revised using information from evolving Wyckoff occupations and elemental composition. We introduce DynaCrys, the first framework for complete crystal generation in which the space group co-evolves with Wyckoff occupations and elements. We develop physics-informed space-group diffusion that explicitly incorporates crystallographic group-subgroup relations, and a legality-constrained stochastic decoder that jointly samples compatible space groups, Wyckoff occupations, and elements, followed by symmetry-constrained geometry generation. In large-scale evaluations on standard benchmarks, DynaCrys achieves state-of-the-art performance in symmetry-aware crystal generation while supporting fast sampling.
Large language models can generate fluent responses to Islamic questions while introducing factual errors that are difficult to identify. This paper presents our system for \textsc{HalluScoring 2026} Task 2.1, \textit{Islamic Hallucination Detection and Find the Truth}. The task requires a unified two-step prediction: determining whether an Arabic answer generated by an LLM is hallucinated and selecting the verified answer from six closely related candidate options. We use the Islamic knowledge dataset provided by the shared task, which contains 600 question--answer instances, including 341 hallucinated and 259 non-hallucinated answers. Our system is based on the fine-tuned \texttt{google/gemma-4-12B-it} model and uses deterministic decoding during inference. The generated outputs are normalized to extract the hallucination label and the selected option. The system achieves a Macro-F1 score of 0.928 and a label accuracy of 0.935 for hallucination detection, together with an option accuracy of 0.895 for answer selection. These results yield a combined score of 0.912, demonstrating strong performance across both stages of the task. The lower option-selection accuracy indicates that distinguishing the verified answer from plausible alternatives remains more challenging than detecting hallucinated responses.
Focal cortical dysplasia (FCD) type II is an important cause of drug-resistant focal epilepsy, but its small size and subtle magnetic resonance imaging (MRI) appearance make automated segmentation difficult. Conventional multimodal networks concatenate T1-weighted (T1w) and fluid-attenuated inversion recovery (FLAIR) images and rely on subsequent layers to learn their relationships implicitly. We propose Compact Ratio-Interaction Learning U-Net (CRIL-U-Net), a 3D U-Net extension incorporating a Compact Ratio-Interaction Learning module that combines local spatial features, voxel-wise cross-modal mixing, and bidirectional ratio-inspired interactions. CRIL-U-Net was compared with a 3D U-Net and a U-Net with input-level self-attention using five-fold cross-validation on 85 FCD subjects and 25 healthy controls. Each architecture was trained independently with Dice-binary cross-entropy (Dice-BCE) and Focal Tversky-Focal (FTF) losses. With FTF, CRIL-U-Net achieved the highest mean Dice score ($0.196\pm0.262$), compared with $0.136\pm0.224$ for the U-Net and $0.135\pm0.214$ for the attention comparator. It localised 44 of 85 lesions, compared with 36 for the U-Net, and significantly outperformed both comparison architectures after false-discovery-rate correction. CRIL adds only 4,320 parameters to the backbone, indicating that compact cross-modal representation learning can improve FCD segmentation when combined with an imbalance-aware objective. The remaining 48.2\% miss rate nevertheless requires further methodological development and external validation.
Raman spectroscopy enables label-free molecular characterization across materials science, analytical chemistry, biomedicine, and industrial process monitoring. However, machine learning for high-dimensional spectroscopy remains constrained by limited labeled data and a mismatch between the physical organization of spectra and feature-agnostic models. Tabular foundation models such as TabPFN predict in context without parameter updates, but on wide spectra feature subsampling preserves channel coverage while losing joint visibility: in the five widest tasks, every channel was covered, yet only 4.4% of random channel pairs co-occurred in any forward pass. We present RamanPFN, a general-purpose spectral foundation framework for unified in-context inference through physics-guided spectral learning, which encodes the additive mixing of constituent spectra and the locality of vibrational bands. Global Compositional Unmixing decomposes distributed, multi-band mixture signatures into shared non-negative bases to couple covarying peaks across the full spectrum, while Local Vibrational Subspace Encoding extracts orthogonal modes within contiguous spectral neighborhoods to preserve peak morphology, intensity fluctuations, and peak shifts. Posterior marginalization over admissible unmixings unifies both scales into in-context prediction without updating the model. Across 74 public Raman datasets exceeding 330,000 spectra, RamanPFN outperformed 26 methods spanning chemometrics, spectral neural networks, deep tabular learners, and tabular foundation models on 129 regression targets, reducing backbone RMSE by 13.2%. We demonstrate across TabPFN-3, TabICLv2, and Kumo-Tabular that this advantage generalizes to both regression and classification tasks, reducing regression error by 12.3%-25.7% and multiclass log loss by 42.4%-63.5% to enable data-efficient quantitative analysis and sample identification.
Fault-tolerant quantum computing relies on quantum error correction to protect logical information, requiring classical decoders that keep pace with syndrome generation. Heterogeneous, changing hardware noise and the distribution shift from simulation to experiment challenge the accuracy and robustness of fixed neural decoders. We present QAdapt, a noise-adaptive neural pre-decoding framework for surface-code quantum error correction. QAdapt learns local spatiotemporal correlations, continually adapts across noise environments, and passes the residual syndrome to a conventional global decoder. Online elastic weight consolidation limits forgetting as training moves between measurement, idle, CNOT, and Pauli-bias noise regimes. At distance nine, the HTNet pre-decoder reduces equivalent per-round logical error by 15.64% relative to Ising-Fast, with 28.75% fewer parameters and 9.07% less matching-backend time. Online EWC reduces average forgetting by 76.52% relative to sequential fine-tuning. With weights frozen, it reduces equivalent per-round logical error by 5.66% relative to continued base-environment training on a fixed valid domain of 331 unseen compound-noise conditions; whole-sequence failure probability falls by 2.54% over all 396 conditions. On native Willow records, the corresponding per-round reductions are 19.44%, 17.47%, and 17.95% at 10, 30, and 50 rounds, without target-domain fine-tuning. These results show how adaptive neural pre-decoding can improve logical accuracy, preserve performance across noise regimes, and reduce residual matching workload within an established decoding pipeline.
Large language models trained with reinforcement learning (RL) to reason step by step have been increasingly shown to outperform their supervised fine-tuned (SFT) counterparts on mathematical reasoning tasks. Yet the mechanistic basis for this improvement remains unclear. We therefore ask, what internal representational differences enable RL-trained reasoning language models to reason better? Our work presents two primary lines of evidence: First, layer-wise linear probes tend to predict answer correctness more accurately in RL-trained reasoning language models than in instruction-tuned models on synthetic math problems, although output length alone matches the DeepSeek-Math-RL probe on two templates. Second, mean ablation studies suggest that accuracy drop rises with layer depth in DeepSeek-Math-RL but not in DeepSeek-Math-Instruct. Finally, we analyse token-count variability across accuracy bins for RL-trained reasoning language models and instruction-tuned models to measure whether token counts vary more on harder problems. Token counts tend to vary more on lower-accuracy problems, although in DeepSeek-Math-Instruct only with truncated responses included. At high accuracy, we observe lower variability in DeepSeek-Math-RL than in DeepSeek-Math-Instruct, and we observe higher variability in Olmo-3-Think than in Olmo-3-Instruct.
Comprehensively evaluating AI agents across interactive environments is difficult due to fragmented tasks, scaffolds, verifiers, and scoring rules. Unfortunately, existing efforts to unify these evaluations are limited in scale and domain, making costly reruns necessary and leaving available data incomparable. We introduce Messier, a unified corpus of 923,158 records spanning 30 benchmarks, 745 agents, 11,891 tasks, and 71,969 verifiers. Messier combines public evaluation results with new runs on six underrepresented professional and scientific benchmarks, standardizing their heterogeneous components into a common schema. Using this corpus, we show that frontier progress is uneven across benchmark groups, with function-calling evaluations largely saturated, programming improving fastest, and enterprise workflows remaining most challenging. Counterfactual rescoring further shows that reported performance can be highly sensitive to how verifier results are aggregated. Finally, we derive capability scores from our corpus that correlate with Epoch's Evaluation Capability Index rankings at Spearman \r{ho} = 0.84. The scores can also be estimated for subsets defined by domain, occupation, action space, or verifier type. In essence, Messier is a reusable resource for studying agent performance at scale, and a basis for designing better evaluations.
Parametric retrieval enables LLMs to retrieve tools implicitly by assigning each API a unique virtual token and training the model to generate it via constrained beam search. Toolsense shows that this regime has two critical drawbacks: it destroys parametric tool knowledge during training, and its beam-search decoding is too slow for real-time deployment. We introduce TRACE (Tool Retrieval via Augmented Chain-of-thought and Enterprise rules), a two-stage curriculum that resolves this dissociation. Stage 1 reuses the multi-format memorization SFT from ToolSense to seed tool knowledge with LoRA. Stage 2 is our core contribution: the model is trained to emit a thinking trace before producing a JSON list of tool tokens, using two data sources -- RRB pairs from ToolSense and queries synthesized to target business rules curated by domain experts -- both augmented with reasoning traces. This training objective preserves Stage 1 MCQ and QA probing accuracy while enabling single-beam greedy decoding at production latency. Evaluated on a combined enterprise catalog of 8,300+ tools across two enterprise product lines, TRACE training for Stage 2 not only preserves but improves tool understanding: MCQ accuracy gains +3.2 pp and QA probing gains +9 pp over Stage 1. On retrieval, TRACE achieves ~86% recall on Domain A and ~60% on Domain B -- compared to embedding baseline performance of ~27% & ~52% -- both with single-beam greedy decoding, making it directly deployable at production latency.
Large Language Models (LLMs) have demonstrated remarkable ability in generating personalized content by leveraging user histories and contextual cues. However, most existing personalization approaches rely on implicit representations within model parameters, making it difficult to interpret user-specific preferences or effectively handle long-context dependencies. To address these challenges, we propose PrefReward, a novel preference-aware generative framework that explicitly models user styles through a structured preference matrix and integrates it into the decoding process as a reward signal. PrefReward consists of two stages: (1) extracting a user-specific preference matrix that summarizes individual stylistic tendencies, and (2) using the matrix to guide generation via a KL-divergence-based reward function. Experiments on the LongLaMP dataset show that PrefReward outperforms retrieval-based baselines and context steering method in both generation quality and personalization interpretability.
Modern LLM deployments use a number of implementation choices and inference optimizations (e.g., batching, custom kernels, and quantization) on top of fixed weights, so two engines serving "the same model" can produce meaningfully different distributions. We study the problem of estimating the total variation (TV) distance between two length-$n$ autoregressive distributions to additive error $\varepsilon$, under three access models. (1) Under sample access, we use $\widetilde{O}(n^2 K/\varepsilon^2)$ queries, where $K$ is the maximum support of the next-token distribution. This improves upon the $\widetilde{O}(n^3 m/\varepsilon^5)$-query estimator of Meel et al. (2025), where $m \geq K$ is the total size of the token alphabet. (2) Under logit access, we use $O(n/\varepsilon^2)$ queries, and this is tight. (3) Under noisy logit access, we smoothly interpolate between the above two guarantees: if probability values are given to relative error $\sigma$, we use $\widetilde{O}((n+n^2\sigma^2)/\varepsilon^2)$ queries. We complement our theoretical results with an empirical evaluation of our algorithms, for example measuring the distance between SGLang and vLLM serving identical weights. Our experiments highlight the robustness and practicality of estimating the total variation distance, which remains estimable where the KL divergence is infinite. Our code is available at https://github.com/XunZhiyang/llm-tv-estimation.
Neural machine translation (NMT) in the legal domain is a linguistically and conceptually demanding task, primarily due to the complexity of legal language and the high level of precision it requires. The recent emergence of reasoning-capable language models opens new possibilities for tackling such challenges. They add to a set of other previously proposed techniques to enhance the translation quality, which includes supervised fine-tuning and reinforcement learning. In this work, we perform a comparison between these various approaches. More particularly, we evaluate small language models such as Qwen3.5 4B, Qwen3.5 9B, and Gemma 3 12B enhanced with various re-training paradigms and compare their performances against frontier reasoning models. We focus on the Swiss legal system, which -- with its unique multilingual statutes -- offers a particularly challenging testbed for reasoning-augmented models. Our results show that the quality of small ``base'' models can be greatly enhanced, and that reinforcement learning with verifiable rewards can be applied to NMT in the legal domain and surpasses the translation quality of supervised fine-tuning. The performance of enhanced small models is close to the one of state-of-the-art reasoning models yet remains inferior. We also note that re-training paradigms yield diminishing returns as model size increase. The code and models are publicly available at https://github.com/aixiuxiuxiu/Legal-MT-SFT-RL.
Separating externally forced trends from internal climate variability is a fundamental challenge in climate science, particularly when analyzing observational records that exist only as a single realization. We show that a single climate realization can be decomposed into forced and internal components by treating external forcing as a dynamical driver within a linear stochastic system, an idea grounded in pullback attractor theory. This addresses a central challenge for climate projection and for detecting and attributing the forced response. Existing single-realization methods rely on linear inverse models (LIMs), which ignore forcing, or linear regression, which omits dynamics. Here we introduce PullbackDMDc, a method grounded in non-autonomous dynamical systems theory and dynamic mode decomposition with control (DMDc), incorporating pullback attractor estimation to decompose a single climate realization into spatial modes and their associated forced and internal components, yielding a physically interpretable picture of the underlying dynamics. After testing on a synthetic system with a known forced response, we illustrate the utility of PullbackDMDc for Earth System Model (ESM) evaluation by applying it to near-surface air temperature and sea-level pressure from reanalysis and four ESM large ensembles. PullbackDMDc estimates the forced response with skill matching or exceeding established baselines and helps select forcing predictors against model-based ground truth. Its internal-variability components reveal that ESMs qualitatively capture interannual and decadal modes while exhibiting systematic differences relative to each other and to observations. Skillful forced-response estimation and a novel decomposition position PullbackDMDc as a practical tool for single-realization climate analysis and ESM evaluation.
Generalised object counting aims to estimate the number of instances of an arbitrary object category from a single image, but many recent methods can struggle on structurally complex objects due to limited spatial modelling. We present \textit{UpCount}, a class-agnostic counter designed to better preserve spatial structure. UpCount strengthens the visual representation by extracting multi-layer features from a ViT-B/16 encoder and reassembling them into a refined multi-scale pyramid that is spatially refined using Dense Prediction Transformers and FeatUp, yielding features with improved structural and spatial sensitivity; a proposal--verification counting head then identifies repeated patterns and produces a density map for the final count. On FSC-147, UpCount achieves 12.39 MAE and 100.89 RMSE on the test set, and it transfers effectively to vehicle counting on CARPK (6.27 MAE, 8.79 RMSE). Code: https://github.com/r28112072-rgb/upcount
Graph Neural Networks (GNNs) have emerged as a powerful, differentiable class of learning models for graph-structured systems. Their ability to generalize across topologies opens the prospect of a surrogate for combined structural and parametric optimization, which classical metamodels cannot offer. Supply chains are a natural target, yet the use of GNN surrogates for supply chain problems is largely unexplored. This paper lays the foundation, presents initial steps, and discusses key research directions. As a foundation, we formulate the problem and create a large public training dataset of programmatically generated supply chain graphs with input parameters and steady-state performance metrics obtained using our SupplyNetPy simulation library. As initial steps, we explore GNN architectures that work well as surrogates for node- and network-level predictions, and analyze their accuracy-compute trade-off against simulation. Most importantly, we outline the exciting directions this opens, namely gradient-based optimization over topology, fast design-space exploration, and sensitivity analysis.
As Ultra-High-Definition (UHD) displays and immersive media services become ubiquitous in the Internet of Things (IoT) and Consumer Electronics (CE) sectors, including 8K display and mobile devices, the demand for high-efficiency video coding is unprecedented. While Deep Learning-based Filtering (DLF) has emerged as a promising solution to mitigate compression artifacts inherent in standards like High Efficiency Video Coding (HEVC/H.265) and Versatile Video Coding (VVC/H.266), its deployment in CE devices is severely constrained by computational complexity, memory bandwidth, and power consumption. To bridge the gap between academic research and practical deployment, this paper presents a comprehensive, hardware-oriented survey of DLF techniques. We propose a systematic three-dimensional taxonomy classifying methods into (1) Integration Scheme within the Video Coding, (2) Coding Information Utilization, and (3) Network Design Strategy. Unlike prior reviews, this work critically analyzes the trade-offs between Rate-Distortion (RD) performance and hardware feasibility, highlighting the evolution from heavy, performance-oriented models to lightweight, hardware-friendly architectures targeting Neural Processing Units (NPUs). Furthermore, we incorporate the latest standardization activities from the Joint Video Experts Team (JVET) on Neural Network-based Video Coding (NNVC) to provide realistic guidelines. We also identify open challenges such as real-time inference latency and error propagation, providing a roadmap toward robust, low-power intelligent video coding in next-generation CE vision endpoints.
Low-Gain Avalanche Diodes (LGADs) and AC-coupled Low-Gain Avalanche Diodes (AC-LGADs) are promising technologies for precision timing and four-dimensional tracking. In AC-LGADs, the AC pad is coupled to the resistive n$^{+}$ layer through a dielectric layer, while the gain layer remains unsegmented. This structure provides a 100\% fill factor and enables good spatial resolution with a relaxed readout pitch. The same signal-sharing mechanism that makes interpolation possible complicates the readout: charge spreads across multiple pads, the useful information can approach the electronic-noise threshold, and matrix-inversion approaches can become computationally challenging and sensitive to off-diagonal noise. In this work, we study machine-learning-based reconstruction and compression for resistive silicon sensors. We use full-waveform information from correlated pads to regularise the reconstruction and extract spatial information beyond what is available from binary readouts or reduced-amplitude summaries. We first introduce recurrent neural network models based on LSTM layers, which provide a proof-of-concept implementation for full-waveform reconstruction and have been tested for FPGA deployment using \hls. We also study routes towards bandwidth reduction with waveform rasterisation and window-selection methods, and extend the approach beyond the first model to topology-agnostic transformer-based architectures that use pad coordinates as part of the input. These models are designed to support arbitrary pad counts and geometries, mitigate edge distortions, preserve approximately $10~\mu\mathrm{m}$ position resolution for $500~\mu\mathrm{m}\times500~\mu\mathrm{m}$ pitched sensors, and guide future resistive-silicon sensor designs
Large Vision Language Models (LVLMs) require strong reasoning over both visual and textual inputs. Recent work suggests that cognitive elements, especially diverse representations and metacognition, correlate with better performance. Many required perceptual functions are already provided by specialized domain-specific computer vision models, which can serve as the perceptual subsystem for detecting objects, localizing them, inferring states, recovering spatial layout, and reading text. The key challenge is integrating these multi-encoder experts into a trustworthy, interpretable, and coherent representation that improves verifiability and reduces hallucinations. This is difficult because vision-language questions span different cognitive levels, yet most LVLM pipelines apply the same perception-reasoning routing regardless of the query's demands. We propose an evidence-driven multimodal reasoning framework that uses a Bloom-inspired taxonomy as a hierarchical reasoning protocol. Our two-stage cognitive verbalization first produces a Literal Evidence Summary by decomposing expert outputs into short, atomic evidence statements, then performs Bloom Verbalization to convert these items into a staged reasoning trace. A lightweight Reasoning Trace Module quantitatively analyzes the trace, making evidence usage and reasoning progression explicit. Experiments show improvements in both perception and reasoning and diagnostics indicate that different queries induce different cognitive entry levels and evidence-use trajectories.
The paper presents a voice anonymization model focusing on preserving content rather than producing realistic speech. It relies on content embeddings extracted from a frozen pretrained wav2vec2 encoder. These embeddings are decoded into an anonymized signal using vector quantization and a HiFi-GAN vocoder, both trained on LibriTTS without any waveform reconstruction loss or speaker embedding mapping. The training objective enforces that embeddings of the anonymized signal match those of the original one. While training, an auxiliary speaker classification branch with a gradient reversal layer is used to discard speakerspecific information. Results show that this straightforward embedding-based approach achieves very low WER (2.53) with an anonymization performance (EER 13.39) ranking within first level for VPC. Notably, emotions are partially preserved (UAR 43.91), even without a supporting training objective, while the anonymized voice is audible without reconstruction loss.
This paper introduces SupplyNetPy, an open-source, well-documented Python library for modeling and discrete-event simulation of supply chain networks with arbitrary multi-echelon structures. It supports multiple replenishment policies, perishable inventory, node disruptions, and stochastic demand and lead times. All components are extensible via inheritance. Users describe a supply chain as a graph with node and link attributes, while the library handles simulation, providing logs and extensive node and network level performance reports. This paper presents the motivation, design, key features, and architecture of SupplyNetPy, along with detailed validation results (against analytical benchmarks, a commercial tool, and a published case study). A key motivation behind SupplyNetPy's development is programmatic generation and simulation of complex models, enabling design-space exploration, what-if analysis, training data generation, and supply chain digital twins.