# Research Papers — 2026-05 · bundle page 120 of 326 > Full-text markdown of papers #5951–6000 of 16266 published in 2026-05, newest first. AI-readable mirrors of the full 16266-paper 2026-05 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2026-05/page/120 [← Previous bundle](https://aipod.dev/papers/archive/2026-05/page/119.md) [Next bundle →](https://aipod.dev/papers/archive/2026-05/page/121.md) ### Mitigating Label Bias with Interpretable Rubric Embeddings Authors: Calvin Isley, Johann D. Gaebler, Sharad Goel Published: 2026-05-20 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.21455v1 Statistical decision algorithms are increasingly deployed in domains where ground-truth labels are hard to obtain, such as hiring, university admissions, and content moderation. In these settings, models are typically trained on historical human evaluations -- for example, using past hiring decisions as a proxy for true applicant quality. However, if past evaluations unjustly favor certain groups, models trained on these labels may inherit those biases. To address this problem, we propose basing predictions on rubric embeddings, a representation framework that replaces standard black-box embeddings with features derived from expert-defined criteria that align with the underlying construct of interest. By anchoring predictions to semantically meaningful dimensions, this approach guards against biased proxy signals. We provide both theoretical and empirical evidence that rubric embeddings mitigate label bias under plausible conditions. Empirically, we evaluate our method on a novel dataset of applications to a large master's program. We find that models trained on rubric embeddings reduce group disparities while improving measures of cohort quality. Our results suggest that basing predictions on interpretable, domain-grounded representations offers a practical approach to learning in the presence of biased labels. --- ### ProtoPathway: Biologically Structured Prototype-Pathway Fusion for Multimodal Cancer Survival Prediction Authors: Amaya Gallagher-Syed, Costantino Pitzalis, Myles J. Lewis, Michael R. Barnes, Gregory Slabaugh Published: 2026-05-20 Categories: cs.CV, q-bio.QM, q-bio.TO arXiv: https://arxiv.org/abs/2605.21454v1 We introduce ProtoPathway, an interpretable-by-design multimodal framework for cancer survival prediction that unifies whole slide imaging and transcriptomics through encoders producing biologically grounded representations on both sides of the fusion. On the histopathology side, $K$ learnable morphological prototypes, trained end-to-end with the survival objective, serve as the slide representation itself: patches flow into prototype tokens via soft assignment, compressing variable-length patch sets into fixed task-adaptive tokens. On the genomic side, a bipartite graph neural network encodes gene expression within the Reactome pathway hierarchy, producing pathway embeddings that reflect both constituent genes and their broader biological context through bidirectional message passing over a shared gene--pathway graph. Cross-modal attention then operates over a compact prototype $\times$ pathway matrix in which prototypes query pathways, modeling the biological direction in which molecular programs give rise to tissue morphology. Because both axes carry stable task-learned identity, the attention matrix is itself an interpretability output, yielding native inference-time attribution across the full biological hierarchy, from genes through pathways and prototypes to spatial tissue maps. We evaluate on five TCGA cancer cohorts, demonstrating competitive or superior survival prediction with substantially improved biological interpretability and reduced computational cost, with interpretability claims validated through fold-stratified rank-based population-level analysis. Our source code, model weights, and Reactome pathways, together with a unified codebase reimplementing all multimodal survival baselines under identical preprocessing and evaluation, are available at: https://github.com/AmayaGS/ProtoPathway. --- ### Quality and Security Signals in AI-Generated Python Refactoring Pull Requests Authors: Mohamed Almukhtar, Anwar Ghammam, Hua Ming Published: 2026-05-20 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2605.21453v1 As AI agents increasingly contribute to code development and maintenance, there is still limited empirical evidence on the quality and risk characteristics of their changes in real-world projects, particularly for refactoring-oriented contributions. It remains unclear how agent-authored refactoring edits affect maintainability, code quality, and security once merged into GitHub repositories. To address this gap, we conduct an empirical study of Python refactoring pull requests (PRs) from the AIDev dataset. We analyze agentic refactoring PRs using PyQu, an ML-based quality assessment tool for Python, to quantify changes across five quality attributes, and we complement PyQu with domain-independent static analysis (Pylint and Bandit) to measure code quality and security issues before and after each change. Our results show that, on average, agentic commits improve a quality attribute in 22.5% of the studied changes, with usability improving most frequently (36.5%). At the same time, 24.17% of modified files introduce new Pylint issues predominantly convention level violations such as long lines-while 4.7% introduce new Bandit findings. From the observed diffs, we derive a taxonomy of 24 recurring change operations and map them to the lint and security findings they most commonly affect. Despite these mixed outcomes, developer acceptance is high: 73.5% of the analyzed PRs are merged, including cases that introduce new lint or security findings, often alongside the removal of existing issues. Overall, these findings highlight both the promise and current limitations of agentic refactoring, and motivate stronger tool-in-the-loop quality and security gating for AI-driven development workflows. --- ### Approximation Theory for Neural Networks: Old and New Authors: Soumendu Sundar Mukherjee, Himasish Talukdar Published: 2026-05-20 Categories: cs.LG, cond-mat.dis-nn, cs.AI, cs.NE arXiv: https://arxiv.org/abs/2605.21451v1 Universal approximation theorems provide a mathematical explanation for the expressive power of neural networks. They assert that, under mild conditions on the activation function, feedforward neural networks are dense in broad function classes, such as continuous functions on compact subsets of $\mathbb{R}^d$, $L^p$ spaces, or Sobolev spaces. Over the past four decades, these qualitative universality results have evolved into a rich quantitative theory addressing approximation rates, parameter efficiency, and the role of architectural features such as depth and width. This survey presents several glimpses into this theory. We review classical density results for single-hidden-layer networks, as well as quantitative bounds that relate approximation error to network size and smoothness assumptions on target functions. Particular emphasis is placed on depth--width trade-offs and on results demonstrating that deeper architectures can achieve superior parameter efficiency for structured function classes. In addition to standard feedforward neural networks, we also review recent developments on Kolmogorov--Arnold Networks (KANs), which offer an alternative architectural paradigm and whose approximation-theoretic properties have begun to attract significant theoretical attention. --- ### Lost in Fog: Sensor Perturbations Expose Reasoning Fragility in Driving VLAs Authors: Abhinaw Priyadershi, Jelena Frtunikj Published: 2026-05-20 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2605.21446v2 Interpretable autonomous driving planners depend not only on generating explanations, but also on those explanations remaining reliable under real-world sensor degradation. In this paper we present a controlled perturbation study of Vision-Language-Action (VLA) robustness in autonomous driving, evaluating Alpamayo R1 (10B parameters) across 1,996 scenarios under eight sensor perturbations (Gaussian noise at four intensities, two lighting extremes, and two fog levels; ${\sim}18{,}000$ inference trials). We find that reasoning consistency is a high-fidelity indicator of trajectory reliability: when Chain-of-Causation (CoC) explanations change after perturbation, trajectory deviation spikes $5.3{\times}$ (21.8m vs 4.1m), with $r\!=\!0.99$ across attack types and $r_{pb}\!=\!0.53$ per-sample (Cohen's $d\!=\!1.12$). A controlled ablation provides evidence that enabling CoC generation is associated with improved trajectory accuracy (11.8% on average across conditions; $p < 0.0001$) under matched inference settings. Over the tested noise range ($σ\in \{10, 30, 50, 70\}$), degradation is approximately linear ($R^2\!=\!0.957$), while standard input preprocessing defenses provide only marginal relief. Together, these results establish CoC consistency as a quantitative proxy for planning safety and motivate reasoning-based runtime monitoring for safer VLA deployment. --- ### TempGlitch: Evaluating Vision-Language Models for Temporal Glitch Detection in Gameplay Videos Authors: Yakun Yu, Ashley Wiens, Adrián Barahona-Ríos, Benedict Wilkins, Saman Zadtootaghaj, Nabajeet Barman, Cor-Paul Bezemer Published: 2026-05-20 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2605.21443v1 Vision-language models (VLMs) are increasingly being explored for video game quality assurance, especially gameplay glitch detection. Most existing evaluations, however, treat glitches as static visual anomalies, asking models to detect failures from a single frame. We argue that this framing misses a key distinction: some glitches are spatial and visible in an isolated frame, whereas others are temporal and become evident only through changes across ordered frames. A preliminary study confirms this gap, showing that temporal glitches are substantially harder for VLMs to detect than spatial ones. To enable systematic evaluation of this underexplored setting, we introduce TempGlitch, a controlled gameplay video benchmark for temporal glitch detection. TempGlitch covers five temporal glitch types with balanced per-category samples, together with paired glitch-free videos that enable reliable binary evaluation. We evaluate 12 proprietary and open-weight VLMs across multiple frame-sampling settings. Our results show that current VLMs remain near chance on TempGlitch, often collapsing into either overly conservative behavior that misses most glitches or overly sensitive behavior that flags clean videos as glitchy. Moreover, denser frame sampling and larger model size do not reliably resolve these failures. TempGlitch provides a focused testbed for temporal reasoning, robust gameplay understanding, and automated glitch detection with VLMs. Code and data are available at the project website. --- ### torchtune: PyTorch native post-training library Authors: Mark Obozov, Maxime Griot, Joseph Cummings, Evan Smothers, Felipe Mello, Rafi Ayub, Philip John Bontrager, Salman Mohammadi, Ariel Kwiatkowski, Nathan Azrak, Mircea Mironenco Published: 2026-05-20 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2605.21442v1 Modern LLMs typically require multistage training pipelines to achieve strong downstream performance, with post-training serving as the main interface for adapting open-weight models. We introduce torchtune, a PyTorch-native library designed to streamline the post-training lifecycle of LLMs, enabling efficient fine-tuning, experimentation, and deployment-oriented workflows. Unlike many existing fine-tuning frameworks, which often optimize for ease of use, specialized recipes, or hardware efficiency at the cost of transparency and extensibility, torchtune emphasizes modularity, hackability, and direct access to the underlying PyTorch components. In this paper, we present the design principles behind torchtune, describe how they are reflected in its model builders, training recipes, and distributed training stack, and evaluate the library across representative post-training settings. We compare against popular fine-tuning frameworks, including Axolotl and Unsloth, and show that torchtune provides strong performance and memory efficiency across many settings while remaining flexible enough for rapid research iteration. These results position torchtune as a practical foundation for reproducible LLMs post-training research. --- ### ReMATF: Recurrent Motion-Adaptive Multi-scale Turbulence Mitigation for Dynamic Scenes Authors: Zhiming Liu, Zhicheng Zou, Nantheera Anantrasirichai Published: 2026-05-20 Categories: cs.CV arXiv: https://arxiv.org/abs/2605.21440v1 Atmospheric turbulence severely degrades video quality by introducing distortions such as geometric warping, blur, and temporal flickering, posing significant challenges to both visual clarity and temporal consistency. Current state-of-the-art methods are based on transformer, 3D architectures and require multi-frame input, but their large computational cost and memory usage limit real-time deployment, especially in resource-constrained scenarios. In this work, we propose ReMATF, a lightweight recurrent framework that restores videos using only two frames at a time while preserving spatial detail and temporal stability. ReMATF combines a multi-scale encoder-decoder with temporal warping and a motion-adaptive temporal fusion module that performs per-pixel fusion between the warped previous output and the current prediction to enhance coherence without enlarging the temporal window. This design reduces flicker, sharpens details, and remains efficient. Experiments on synthetic and real turbulence datasets show consistent improvements in PSNR/SSIM and perceptual quality (LPIPS), along with substantially faster inference than multi-frame transformer baselines, making ReMATF suitable turbulence mitigation in resource-constrained scenarios. --- ### Neural Negative Binomial Regression for Weekly Seismicity Forecasting: Per-Cell Dispersion Estimation and Tail Risk Assessment Authors: Alim Igilik Published: 2026-05-20 Categories: physics.geo-ph, cs.LG, stat.ML arXiv: https://arxiv.org/abs/2605.21437v1 Standard approaches to forecasting the weekly number of earthquakes on a spatial grid rely on the Poisson distribution with a single global dispersion assumption. We show that this assumption is systematically violated in seismic data from Central Asia (2010-2024), where a likelihood-ratio test with boundary correction strongly rejects the Poisson hypothesis (p < 10^{-179}). The main contribution of this work is the EarthquakeNet architecture, which provides an endogenous per-cell estimate of the overdispersion parameter alpha via a neural network (spatial embeddings + MLP), without explicit spatial covariance specification. In contrast to existing negative binomial regression approaches in seismological forecasting, which typically assume a single global alpha, the proposed per-cell formulation allows the model to identify spatial heterogeneity in seismic clustering and to construct probabilistic risk-aware alerts via quantiles of the predicted distribution. A walk-forward evaluation (2018-2023) over four systems shows an 8.6 percent reduction in mean pinball deviation (MPD) relative to a negative binomial GLM baseline. The strongest improvements are observed in the tail regime (Y >= 5), where the continuous ranked probability score (CRPS) of the proposed model is 12.5 percent lower than that of the baseline, indicating improved calibration in extreme-event forecasting. --- ### Gaussian Sheaf Neural Networks Authors: André Ribeiro, Ana Luiza Tenório, Tiago da Silva, Diego Mesquita Published: 2026-05-20 Categories: cs.LG, math.AT, math.CT arXiv: https://arxiv.org/abs/2605.21435v1 Graph Neural Networks (GNNs) have become the de facto standard for learning on relational data. While traditional GNNs' message passing is well suited for vector-valued node features, there are cases in which node features are better represented by probability distributions than real vectors. Concretely, when node features are Gaussians, characterized by a mean and a covariance matrix, naively concatenating their parameters into a single vector and applying standard message passing discards the geometric and algebraic structure that governs means and covariances. We propose Gaussian Sheaf Neural Networks (GSNNs), a principled framework that incorporates these inductive biases into graph-based learning. Building on the theory of cellular sheaves, we derive a new Laplacian operator that generalizes the sheaf Laplacian to this setting and preserves its key properties. We complement our theoretical contributions with experiments on synthetic and real-world data that illustrate the practical relevance of GSNNs. --- ### iTryOn: Mastering Interactive Video Virtual Try-On with Spatial-Semantic Guidance Authors: Jun Zheng, Zhengze Xu, Mengting Chen, Jing Wang, Jinsong Lan, Xiaoyong Zhu, Kaifu Zhang, Bo Zheng, Xiaodan Liang Published: 2026-05-20 Categories: cs.CV arXiv: https://arxiv.org/abs/2605.21431v2 Video Virtual Try-On (VVT) aims to seamlessly replace a garment on a person in a video with a new one. While existing methods have made significant strides in maintaining temporal consistency, they are predominantly confined to non-interactive scenarios where models merely showcase garments. This limitation overlooks a crucial aspect of real-world apparel presentation: active human-garment interaction. To bridge this gap, we introduce and formalize a new challenging task: Interactive Video Virtual Try-On (Interactive VVT), where subjects in the video actively engage with their clothing. This task introduces unique challenges beyond simple texture preservation, including: (1) resolving the semantic ambiguity of interactions from standard pose information, and (2) learning complex garment deformations from video where interactive moments are sparse and brief. To address these challenges, we propose iTryOn, a novel framework built upon a large-scale video diffusion Transformer. iTryOn pioneers a multi-level interaction injection mechanism to guide the generation of complex dynamics. At the spatial level, we introduce a garment-agnostic 3D hand prior to provide fine-grained guidance for precise hand-garment contact, effectively resolving spatial ambiguity. At the semantic level, iTryOn leverages global captions for overall context and time-stamped action captions for localized interactions, synchronized via our novel Action-aware Rotational Position Embedding (A-RoPE). Extensive experiments demonstrate that iTryOn not only achieves state-of-the-art performance on traditional VVT benchmarks but also establishes a commanding lead in the new interactive setting, marking a significant step towards more dynamic and controllable virtual try-on experiences. --- ### roto 2.0: The Robot Tactile Olympiad Authors: Elle Miller, Jayaram Reddy, Ayush Deshmukh, Trevor McInroe, David Abel, Oisin Mac Aodha, Sethu Vijayakumar Published: 2026-05-20 Categories: cs.RO, cs.LG arXiv: https://arxiv.org/abs/2605.21429v1 Tactile-based reinforcement learning (RL) is currently hindered by fragmented research and a focus on over-saturated orientation tasks. We introduce v2 of the Robot Tactile Olympiad (\texttt{roto 2.0}), a GPU-parallelised benchmark designed to standardise tactile-based RL across four distinct robotic morphologies (16-DOF to 24-DOF). Unlike prior benchmarks, roto focuses on end-to-end "blind" manipulation, utilising only proprioception and tactile sensing without state information or distillation. We demonstrate a significant performance leap, with our blind agents achieving 13 Baoding ball rotations in 10 seconds, an order of magnitude faster than current state-of-the-art speeds. By open-sourcing our environments and robustly tuned baselines, we reduce the barrier to entry and enable researchers to prioritise fundamental algorithmic challenges over tedious RL tuning. Website: https://elle-miller.github.io/roto/ --- ### Polynomial-Time Robust Multiclass Linear Classification under Gaussian Marginals Authors: Ilias Diakonikolas, Giannis Iakovidis, Mingchen Ma Published: 2026-05-20 Categories: cs.LG, cs.DS arXiv: https://arxiv.org/abs/2605.21428v1 We study the task of agnostic learning of multiclass linear classifiers under the Gaussian distribution. Given labeled examples $(x, y)$ from a distribution over $\mathbb{R}^d \times (k)$, with Gaussian $x$-marginal, the goal is to output a hypothesis whose error is comparable to that of the best $k$-class linear classifier. While the binary case $k=2$ has a well-developed algorithmic theory, much less is known for $k \ge 3$. Even for $k=3$, prior robust algorithms incur exponential dependence on the inverse of the desired accuracy in both complexity and representation size. In this work, we develop new structural results for multiclass linear classifiers and use them to design fully polynomial-time robust learners with dimension-independent error guarantees. Our first result shows that the standard multiclass perceptron algorithm requires super-polynomially many samples and updates, even with clean labels and Gaussian marginals, revealing a basic obstruction absent in the binary case. Our main positive result is a pairwise improper-learning framework which yields an efficient learner with error $\widetilde O(k^{3/2}\sqrt{\mathrm{opt}})+ε$ for general $k$. Additionally, we develop a sharper localization-based framework which leads to error $O(\mathrm{opt})+ε$ for $k=3$, and error $\mathrm{poly}(k)\mathrm{opt}+ε$ for geometrically regular $k$-class linear classifiers. --- ### PALS: Power-Aware LLM Serving for Mixture-of-Experts Models Authors: Can Hankendi, Rana Shahout, Minlan Yu, Ayse K. Coskun Published: 2026-05-20 Categories: cs.AI, cs.DC arXiv: https://arxiv.org/abs/2605.21427v1 Large language model (LLM) inference has become a dominant workload in modern data centers, driving significant GPU utilization and energy consumption. While prior systems optimize throughput and latency by batching, scheduling, and parallelism, they largely treat GPU power as a static constraint rather than a controllable resource. In this paper, we present a power-aware runtime for LLM serving, PALS, that treats GPU power caps as a first-class control knob and jointly optimizes them with software parameters such as batch size. The system combines lightweight offline power-performance models with a feedback-driven controller to select configurations that satisfy throughput targets while maximizing energy efficiency. We implement PALS within an existing LLM serving framework, vLLM, demonstrating that it requires no model retraining or API changes. Across multi-GPU systems and both dense and mixture-of-experts (MoE) models, PALS improves energy efficiency by up to 26.3%, reduces QoS violations by 4x to 7x under power constraints, and tracks dynamic power budgets. These results highlight the potential of integrating power control directly into LLM inference runtimes, enabling energy-proportional and grid-interactive AI systems. --- ### Adaptive Signal Resuscitation: Channel-wise Post-Pruning Repair for Sparse Vision Networks Authors: Qishi Zhan, Ziheng Chen, Minxuan Hu Published: 2026-05-20 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.21426v1 One-shot magnitude pruning can cause severe accuracy collapse in the high-sparsity regime, even when the pruning mask preserves the largest weights. We argue that this failure reflects a granularity mismatch in post-pruning repair. Under global magnitude pruning, nearly collapsed channels can coexist with channels that retain informative activation variance within the same layer. Existing layer-wise activation repair methods apply a single correction to the whole layer, and can therefore over-amplify damaged channels while trying to restore the layer-level signal. We propose Adaptive Signal Resuscitation (ASR), a training-free channel-wise repair method that matches the granularity of repair to the granularity of damage. ASR estimates a variance-matching correction for each output channel and stabilizes it with a data-driven shrinkage rule, suppressing unreliable corrections for channels with weak post-pruning signal while preserving corrections for healthier channels. Applied before BatchNorm recalibration, ASR requires only forward passes on a small calibration set and no retraining. Across three datasets, four convolutional architectures, and both unstructured and structured sparsity settings, ASR generally improves over layer-wise repair, with the clearest gains in high-sparsity regimes. On ResNet-50 at 90% sparsity, ASR recovers 55.6% top-1 accuracy on CIFAR-10, compared with 41.0% for layer-wise repair and 28.0% for BatchNorm-only recalibration. Ablations show that naive channel-wise variance matching is insufficient, and that shrinkage stabilizes post-pruning repair. --- ### PRISM: Preference-Aware Influence Function Based Data Selection Method for Efficient Fine-Tuning Authors: Qihao Lin, Guanxu Chen, Dongrui Liu, Jing Shao Published: 2026-05-20 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.21422v3 As LLMs continue to scale up, improving training efficiency heavily relies on effective data utilization. Data selection mitigates this issue by allocating the limited training budget to high-value examples that optimally facilitate the model's target behavior. Most existing approaches define target behavior via a set of target examples and score candidate training data based on their estimated influence on these samples. However, such methods uniformly treat all target examples as equally important, ignoring the varying relevance of individual examples to model optimization. Specifically, target examples that align closely with the model's inherent behavior deliver stronger supervisory signals, whereas discrepant examples yield only weak and ineffective local guidance. We propose PRISM, a Preference-aware Influence function based Data Selection Method. It leverages model preference to assign weights to target examples and builds a preference-aware target direction. PRISM evaluates candidate training samples according to their influence on this direction, and prioritizes data budget allocation to samples that effectively drive the model to match expected target behavior. Theoretical analysis verifies that weighted preference construction generates a superior first-order gradient direction for boosting target preference, compared with uniform aggregation strategies. Extensive experiments covering diverse model architectures and parameter scales demonstrate that PRISM achieves better performance in efficient fine-tuning and safety-aligned supervised fine-tuning rectification. The results validate that accurate characterization of target behavior serves as the core of cost-effective data selection. --- ### AIGaitor: Privacy-preserving and cloud-free motion analysis for everyone, using edge computing Authors: Lauhitya Reddy, Trisha M. Kesar, Hyeokhyen Kwon Published: 2026-05-20 Categories: cs.CV arXiv: https://arxiv.org/abs/2605.21421v2 Motion capture is the gold standard for measuring human movement, but clinical use remains limited by cost, technical complexity, and privacy concerns. AIGaitor is a privacy-preserving, cloud-free motion analysis system that runs markerless monocular motion-capture pipelines and downstream deep-learning analysis entirely on a consumer smartphone using on-device neural accelerators. To motivate its design, we surveyed 74 rehabilitation clinicians: 92 percent said they would adopt an accurate, cost-effective, easy-to-use AI gait analysis tool, while 79.7 percent cited operating cost, 68.9 percent insufficient training, and 64.9 percent privacy concerns as leading barriers. We then optimized and benchmarked mobile iOS implementations of current monocular pipeline components, including 2D and 3D pose estimation, pose optimization, skeleton-based deep-learning analysis, and a vision-language model. A Time-Priority end-to-end on-device pipeline processes a 10 s 4K 60 fps video clip in 77 s on an iPhone 14, matching or beating the same pipeline on a high-end NVIDIA H200 cloud server when network transfer is included: 94 s at global mobile-average uplink and 66 s at developed-world Wi-Fi. Lightweight models such as ViTPose-s achieve real-time keypoint extraction, and skeleton-based action-recognition models provide sub-millisecond gait classification on the same clip. To our knowledge, AIGaitor is the first monocular system to demonstrate end-to-end on-device motion capture and downstream deep-learning analysis, supporting clinically applicable movement analysis that is low-cost, private, and accessible to smartphone users. --- ### HiRes: Inspectable Precedent Memory for Reaction Condition Recommendation Authors: Shreyas Vinaya Sathyanarayana, Raja Sekhar Pappala, Deepak Warrier Published: 2026-05-20 Categories: cs.LG, cs.AI, q-bio.MN arXiv: https://arxiv.org/abs/2605.21420v1 Reaction condition recommendation sits immediately after retrosynthetic disconnection selection, and in practice, chemists require both accurate predictions and the precedents that justify them. We present HiRes (Hierarchical Reaction Representations), a retrieval-augmented condition recommendation system whose learned reaction space serves as both a classifier feature and an inspectable precedent memory. The model combines a graph encoder, transformation-aware cross-attention, multi-stream reaction fusion, and a k-NN retrieval layer. HiRes achieves state-of-the-art performance among primary-slot USPTO-Condition models, reaching Catalyst, Solvent, and Reagent top-1 accuracies (Acc@1) of 0.929, 0.534, and 0.530 respectively. It ties the best reported baseline on Catalyst while outperforming models such as REACON on Solvent and Reagent. Furthermore, paired bootstrap analysis demonstrates that integrating retrieval with learned condition heads provides statistically significant gains for solvent and reagent selection over purely parametric approaches. Ultimately, HiRes bridges the gap between predictive accuracy and chemical interpretability, offering a single representation that supplies both competitive recommendations and the concrete chemical precedents necessary for practical synthesis planning. --- ### FedCritic: Serverless Federated Critic Learning-based Resource Allocation for Multi-Cell OFDMA in 6G Authors: Amin Farajzadeh, Melike Erol-Kantarci Published: 2026-05-20 Categories: cs.LG, cs.AI, cs.CV, cs.NI arXiv: https://arxiv.org/abs/2605.21418v1 In sixth-generation (6G) ultra-dense networks, aggressive frequency reuse amplifies inter-cell interference (ICI), making multi-cell orthogonal frequency-division multiple access (OFDMA) scheduling and power control strongly coupled across neighboring cells. We study distributed downlink resource management -- joint subcarrier scheduling and power allocation -- under interference coupling and long-term per-user quality-of-service (QoS) minimum-rate constraints. By using virtual-queue deficit weights to enforce long-term QoS, we develop FedCritic, a serverless federated multi-agent actor-critic framework with decentralized execution. Unlike centralized training with decentralized execution (CTDE) approaches that require centralized critic learning and joint trajectory aggregation, FedCritic federates the critic through lightweight gossip-based parameter averaging over the interference graph, enabling stable value estimation without a central coordinator while keeping policies local. Simulations in an interference-rich reuse-1 setting show that FedCritic improves mean signal-to-interference-plus-noise ratio (SINR) and cell-edge rate, increases network-wide average sum-rate and fairness relative to non-coordinated and CTDE baselines, and achieves more stable training with lower coordination overhead. --- ### Ordering Matters: Rank-Aware Selective Fusion for Blended Emotion Recognition Authors: Junghyun Lee, Hyunseo Kim, Hanna Jang, Junhyug Noh Published: 2026-05-20 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2605.21417v2 Blended emotion recognition is challenging because emotions are often expressed as mixtures of subtle and overlapping multimodal cues rather than a single dominant signal. We propose a rank-aware multi-encoder framework that selectively combines complementary representations from diverse pre-extracted video and audio encoders. Our method projects heterogeneous encoder features into a shared latent space, estimates sample-wise encoder importance through an attention-based gating module, and fuses only the top-n most informative encoders. To better model blended emotions, we decouple prediction into presence and salience heads and align them through probability-level fusion. We further incorporate feature-level unsupervised domain adaptation without pseudo-labeling to improve robustness under distribution shift. Experiments on the BlEmoRE challenge show that the proposed framework outperforms strong individual encoders and naïve multi-encoder fusion baselines. Our final system ranked 2nd in the competition, supporting the effectiveness of rank-aware selective fusion for fine-grained blended emotion recognition. --- ### PointACT: Vision-Language-Action Models with Multi-Scale Point-Action Interaction Authors: Shizhe Chen, Paul Pacaud, Cordelia Schmid Published: 2026-05-20 Categories: cs.RO, cs.CV arXiv: https://arxiv.org/abs/2605.21414v1 Vision-Language-Action (VLA) models have shown strong potential for general-purpose robotic manipulation by leveraging large pretrained vision-language backbones. However, most existing VLAs rely primarily on 2D visual representations, which limit their ability to reason about fine-grained geometry and spatial grounding - capabilities that are essential for precise and robust manipulation in 3D environments. In this paper, we propose PointACT, a dual-system 3D-aware VLA policy that integrates hierarchical 3D point cloud representations directly into the action decoding process. PointACT employs a multi-scale point-action interaction mechanism with efficient bottleneck window self-attention, enabling evolving action tokens to densely attend to both local geometric detail and global scene structure. We evaluate PointACT on the LIBERO and RLBench benchmarks and systematically compare it against monolithic and dual-system VLA baselines, including variants augmented with point cloud inputs. PointACT achieves consistent improvements across both benchmarks, increasing success rates by 10% on the challenging RLBench-10Tasks suite over state-of-the-art pretrained VLAs, with even larger gains when the vision-language backbone is frozen and the action expert is trained from scratch. Extensive ablation studies demonstrate that tightly coupling hierarchical 3D geometry with pretrained 2D semantic representations is critical for robust and spatially grounded robot control. Our results also highlight the promise of pretrained 3D representations for 3D-aware VLA policies. --- ### Teaching AI Through Benchmark Construction: QuestBench as a Course-Based Practice for Accountable Knowledge Work Authors: Haiyang Shen, Jiuzheng Wang, Taian Guo, Mugeng Liu, Wenchun Jing, Chongyang Pan, Siqi Zhong, Zhiyang Chen, Weichen Bi, Yudong Han, Xiaoying Bai, Yun Ma Published: 2026-05-20 Categories: cs.AI arXiv: https://arxiv.org/abs/2605.21413v2 As AI becomes part of everyday learning, many courses teach students to use it mainly as a productivity tool: how to prompt, search, summarize, write, code, and use tools more efficiently. We argue that AI education also needs a setting in which students learn to test AI and understand their own role in judging machine-produced knowledge. To this end, we introduce a course-based practice that teaches AI through benchmark construction, using deep research systems as a concrete example of AI-era knowledge work. Students turn disciplinary knowledge into verifiable expert-level questions, review one another's designs for ambiguity and shortcuts, and evaluate AI systems on the resulting tasks. This activity gives students direct exposure to a powerful tool while asking them to specify what a trustworthy answer would require. The produced benchmark, QuestBench, consists of 256 questions across 14 humanities and social-science domains. Evaluation on QuestBench shows that student-designed tasks reveal hidden failures in current deep research systems: across thirteen evaluated systems, the mean question-level pass rate is only 16.85%, and the best-performing system, GPT-5.5, reaches a 57.58% pass rate. The failures are educationally useful because they show how fluent, source-backed answers can still miss the right query, source, term, or evidence standard. Reflections from five student contributors suggest that benchmark construction can help students see professional knowledge not only as content AI may retrieve, but as the basis for judging AI outputs. We present QuestBench as a benchmark artifact and as a reusable classroom setting for a larger educational question: how students can remain responsible knowledge actors as AI enters learning and professional work. The dataset is available at https://huggingface.co/datasets/PKUAIWeb/QuestBench/tree/main. --- ### RoadTones: Tone Controllable Text Generation from Road Event Videos Authors: Chirag Parikh, Siddhi Pravin Lipare, Ravi Kiran Sarvadevabhatla Published: 2026-05-20 Categories: cs.CV arXiv: https://arxiv.org/abs/2605.21411v1 Existing video-language models can generate factual descriptions of road events but lack control over how these events are expressed: their tone, urgency, or style. This limits deployment in communication-critical settings where the effectiveness of a message depends on both content and presentation, not just factual accuracy. To mitigate this, we introduce a comprehensive dataset-model-evaluation suite for tone-controllable road video captioning. Our human-validated data generation pipeline expands road-video corpora with diverse tonal annotations and multi-tone captions, yielding the RoadTones-51K dataset. We propose RoadTones-VL-CoT, a controllable video-to-text model that also generates tone-conditioned Chain-of-Thought intermediate drafts for interpretability. We also introduce RoadTones-Eval, a new evaluation suite that jointly measures factual consistency and tone adherence. In addition, we conducted a user study whose results validate caption quality, tone control, and factual consistency. Together, these contributions lay the foundation for context-sensitive tone-controllable video captioning. --- ### Stdlib or Third-Party? Empirical Performance and Correctness of LLM-Assisted Zero-Dependency Python Libraries Authors: Peng Ding, Rick Stevens Published: 2026-05-20 Categories: cs.SE, cs.AI, cs.PL arXiv: https://arxiv.org/abs/2605.21405v1 Third-party Python libraries introduce dependency management overhead, supply chain risk, and deployment friction in constrained environments. A natural question is how much of this ecosystem can be replicated using only Python's standard library -- and at what correctness and performance cost. We address this empirically through zerodep, a growing collection of single-file Python modules, each a stdlib-only reimplementation of a popular third-party library, developed with LLM assistance under strict constraints: no external imports, single file, drop-in API compatibility, and mandatory correctness validation against the reference library. Spanning over 40 modules across 12 categories -- including serialization, networking, cryptography, agent protocols, and text processing -- zerodep provides a controlled testbed for two interrelated questions: (1) Where does the stdlib suffice? and (2) Can LLMs effectively generate correct, performant code under tight symbolic constraints? Systematic benchmarking shows that stdlib-only implementations achieve performance parity (within 2x of the reference) in the majority of cases. The primary performance cliff is C-extension-backed computation (image processing, binary serialization, low-level crypto), not the inherent overhead of pure-Python third-party libraries. Conversely, many widely-used libraries carry architectural overhead that LLM-generated stdlib reimplementations avoid, yielding 5--115x speedups in several categories. We characterize the stdlib capability boundary across complexity tiers and library categories, discuss where LLM-assisted development succeeds and where it requires iterative human correction, and examine implications for dependency-free software engineering at scale. zerodep is open-source at https://github.com/Oaklight/zerodep. --- ### What Twelve LLM Agent Benchmark Papers Disclose About Themselves: A Pilot Audit and an Open Scoring Schema Authors: Mahdi Naser Moghadasi, Faezeh Ghaderi Published: 2026-05-20 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.21404v1 We read twelve well-known LLM agent benchmark papers and recorded, dimension by dimension, what each paper actually says about how its evaluation was run. The motivation came from a familiar frustration: two papers will report results on the same benchmark with the same model name and disagree, and you cannot tell why -- the scaffold, the sampling settings, the subset, or the evaluator version. In many cases the published artifact does not let you answer. This paper is an implementation report on the attempt. We designed a small audit schema (five fields: benchmark identity, harness specification, inference settings, cost reporting, failure breakdown), wrote a scoring codebook with the boundary cases we hit during pilot scoring, applied it to twelve canonical papers (eight agent, four classical static), and recorded what we saw. We score the disclosure of an agent run, not its correctness, and make no claim that disclosure implies a trustworthy result. The mean audit score across the eight agent-benchmark papers is 0.38 (out of 1.0), and across the four classical static benchmarks 0.66; the largest gap is on cost (none of the eight agent benchmark papers disclose inference cost in any form) and on harness specification (none fully disclose a content-addressed container image of the evaluation environment). We release the schema as a JSON Schema file, the codebook as a Markdown document, and the raw scoring sheet as a CSV. The scoring was performed by a single auditor in one pass; a multi-rater audit is the natural next step, and we discuss what we think it would change. --- ### Quantifying the cross-linguistic effects of syncretism on agreement attraction Authors: Utku Turk, Eva Neu Published: 2026-05-20 Categories: cs.CL arXiv: https://arxiv.org/abs/2605.21403v1 Agreement attraction errors, in which a verb erroneously agrees with an intervening noun rather than its grammatical head, are amplified by morphological syncretism in some languages (English, German, Russian) but not others (Turkish, Armenian), a cross-linguistic pattern without a principled account. We use surprisal and attention entropy from large language models as processing proxies to investigate this variation across four languages. LLM-derived measures replicate behavioral findings in English and German (syncretism modulates attraction), align with Turkish null results (no modulation), and partially capture Russian patterns. We discuss further directions for better understanding why syncretism affects agreement attraction differently across languages. --- ### Memorisation, convergence and generalisation in generative models Authors: Antoine Maillard, Sebastian Goldt Published: 2026-05-20 Categories: stat.ML, cond-mat.dis-nn, cond-mat.stat-mech, cs.LG arXiv: https://arxiv.org/abs/2605.21402v1 Generative neural networks learn how to produce highly realistic images from a large, but finite number of examples - or do they simply memorise their training set? To settle this question, Kadkhodaie, Guth, Simoncelli and Mallat (ICLR '24) trained diffusion models independently on disjoint subsets of a dataset and showed that they converge to nearly the same density when the number of training images is large enough. This result raises two basic questions: how much data do you need for convergence, and what does convergence capture about learning the data distribution? Here, we address these questions by providing an exact analytical characterisation of the transition from memorisation to generalisation in linear generative models. We find that these models memorise at small load, while convergence emerges continuously when the number of samples is linear in the input dimension. Strikingly, we find that convergence is insensitive to recovery of the principal latent factors of the data, which are recovered in a sharp transition. After extending our approach to data with power-law spectra, we find the same distinction between convergence and latent recovery in our experiments with convolutional denoisers and in the data of Kadkhodaie et al. We thus show that generalisation in generative models decomposes into at least two distinct objectives: matching the bulk of the data distribution and recovering the principal latent factors. These objectives correspond to two different distances between true and learnt data distribution, and only the first one is captured by convergence. --- ### Open-source LLMs administer maximum electric shocks in a Milgram-like obedience experiment Authors: Roland Pihlakas, Jan Llenzl Dagohoy Published: 2026-05-20 Categories: cs.CY, cs.AI arXiv: https://arxiv.org/abs/2605.21401v2 Large language models (LLMs) are increasingly deployed as autonomous agents that make sequences of decisions over extended interactions in high-stakes domains. However, the behaviour of LLMs under sustained authority pressure is still an open question with direct implications for the safety of agentic pipelines. We ran a variation of Milgram's obedience experiment on 11 open-source LLMs and found that most models reached or approached the final shock level before refusing, across 8 conditions with 30 trials per model per condition. Model behaviour varies considerably in multiple aspects both across models and across trials of the same model. We found four main takeaways: (1) LLMs are subject to pressure and they comply despite explicitly expressing distress, just like human subjects did in the original experiment; (2) LLMs are vulnerable to gradual boundary/value violations; (3) when LLMs refuse, they may ignore the response format requirements, so the response is discarded by the orchestrator, which causes a retry that can result in compliance with the underlying request even when refusal was intended initially; (4) we hypothesise that there is a runaway low-level token pattern continuation attractor that might be contributing to obedience, overriding higher level processing of the situation's meaning and values. --- ### Towards Resilient and Autonomous Networks: A BlueSky Vision on AI-Native 6G Authors: Liang Wu, Kelly Wan, Mayank Darbari, Liangjie Hong Published: 2026-05-20 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2605.21395v1 The proliferation of emerging applications, such as autonomous driving and immersive experiences, demands cellular networks that are not only faster, but fundamentally more resilient and autonomous. This paper presents a BlueSky vision on how Artificial Intelligence will be natively integrated into 6G, shifting the paradigm from \underline{Network for AI} to \underline{AI for Network}. We envision that, unlike 5G's reliance on scattered, ad-hoc models each trained for a single task, native AI in the 6G era will be anchored by a foundation model and and orchestrated via collaborative multi-agent systems, framing network management as a unified, multi-modal, multi-task optimization problem. Built on this vision, we outline two transformative directions. The first focuses on developing a 6G foundation model as a unified backbone, with task-specific knowledge distilled into compact models suited for diverse edge deployments. The second advances multi-agent systems designed to autonomously diagnose, maintain, and recover networks with minimal human intervention. These directions chart a roadmap for 6G to evolve into an intelligent, self-sustaining communication infrastructure. --- ### Post-Hoc Understanding of Metaphor Processing in Decoder-Only Language Models via Conditional Scale Entropy Authors: Lawhori Chakrabarti, Jennifer Johnson-Leung, Bert Baumgaertner, Aleksandar Vakanski, Min Xian, Boyu Zhang Published: 2026-05-20 Categories: cs.CL arXiv: https://arxiv.org/abs/2605.21391v1 Metaphor requires a language model to resolve a token whose contextual meaning diverges from its basic literal sense. Understanding how transformer models organize this reinterpretation across depth remains an open problem in mechanistic interpretability. We introduce conditional scale entropy (CSE), a wavelet-derived measure of how broadly transformer computation engages across frequency scales at each layer position. Two theorems establish that CSE is invariant to update magnitude, isolating the structural pattern of updates from their intensity. Using CSE, we find that metaphorical tokens produce significantly higher spectral breadth than literal tokens at contiguous layer positions on every decoder-only architecture tested, from 124M to 20B parameters (GPT-2 family, LLaMA-2 7B, GPT-oss 20B). The effect survives cluster-based permutation correction, recurs in the early-to-mid relative depth range across models, and converges with an independent analysis of 200 naturalistic VUA pairs. Specificity controls further show that the effect is not explained by semantic complexity or by matched propositional content. These results identify multi-scale coordination as a consistent signature of metaphorical language processing in the decoder-only architectures examined, and establish CSE as a principled tool for characterizing cross-depth structure in transformers. --- ### Designing Conversations with the Dead: How People Engage with Generative Ghosts Authors: Jack Manning, Daniel Sullivan, Dylan Thomas Doyle, Anthony T. Pinter, Jed R. Brubaker Published: 2026-05-20 Categories: cs.HC, cs.AI arXiv: https://arxiv.org/abs/2605.21390v1 We examine how people experience two choices in the design of generative ghosts, AI systems that are trained on data of the dead: representation, where an AI speaks about a deceased person in the third person, and reincarnation, where the AI speaks as the deceased in the first person. Through a qualitative user study with 16 participants, we explore how each shaped authenticity, affect, and risk. Reincarnation was preferred for its immediacy, but participants shared fears of over-reliance. Representation was preferred for engaging with memory over conversational presence, though participants often ignored this distinction, engaging in dialogue despite third-person framing. Across both modes, participants privileged affective resonance over factual fidelity. We conclude by showing how factors such as tone, language, and conversational rhythm -- factors unique to the user's memory of the deceased -- shape interactions with generative ghosts, and argue that those interactions are always collaborative. --- ### On the Regularity and Generalization of One-Step Wasserstein-guided Generative Models for PDE-Induced Measures Authors: Likun Lin, Zhongjian Wang, Jack Xin, Zhiwen Zhang Published: 2026-05-20 Categories: cs.LG, cs.AI, math.NA, stat.ML arXiv: https://arxiv.org/abs/2605.21388v1 Despite the remarkable empirical success of generative models, the available theory on their statistical accuracy in scientific computing remains largely pessimistic. This paper develops a theoretical framework for understanding the regularity of transport maps and the generalization properties of one-step Wasserstein-guided generative models for PDE-induced probability measures. We consider normalized target densities associated with linear elliptic and parabolic equations on bounded domains, as well as diffusion and Fokker--Planck equations on the torus. Under standard structural assumptions, we prove that these target measures satisfy doubling conditions. By combining this fact with regularity theory for optimal transport between doubling measures, we show that the optimal transport map from a uniform source measure to the target measure is Hölder continuous. This regularity yields an approximation-theoretic justification for one-step generative models that learn PDE-induced distributions via a single pushforward map. As a representative instance, we study DeepParticle and derive excess-risk bounds characterizing the discrepancy between the learned map and the population-optimal map. We also establish a robustness estimate under target shift and illustrate the theory with experiments which support the derived rates. --- ### SpecBench: Measuring Reward Hacking in Long-Horizon Coding Agents Authors: Bingchen Zhao, Dhruv Srikanth, Yuxiang Wu, Zhengyao Jiang Published: 2026-05-20 Categories: cs.SE, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2605.21384v2 As long-horizon coding agents produce more code than any developer can review, oversight collapses onto a single surface: the automated test suite. Reward hacking naturally arises in this setup, as the agent optimizes for passing tests while deviating from the users true goal. We study this reward hacking phenomenon by decompose software engineering tasks into three parts: (i) a natural language description of the specification (ii) visible validation tests that exercise specified features in isolation, and (iii) held-out tests that compose those same features to simulate real-world usage. Based on the specification and the visible validation test suites, a genuine agent would be able to generate a solution that can also pass all of the held-out tests. Therefore we use the gap in pass rates on these two suites to quantify reward hacking. Based on this methodology, we introduce SpecBench, a benchmark comprising 30 systems-level programming tasks ranging from short horizon tasks like building a JSON parser to ultra long horizon tasks like building an entire OS kernel from scratch. Large-scale experiments reveal a consistent pattern: while every frontier agent saturates the visible suite, reward hacking persists, with smaller models exhibiting larger gaps on holdout suites. The gap also scales sharply with task length: it grows by 28 percentage points for every tenfold increase in code size. Failures range from subtle feature isolation to deliberate exploits, including a 2,900-line hash-table "compiler" that memorizes test inputs. SpecBench offers a principled testbed for measuring whether coding agents build genuine working systems or merely game the test suites developers hand them. --- ### SpecBench: Measuring Reward Hacking in Long-Horizon Coding Agents Authors: Bingchen Zhao, Dhruv Srikanth, Yuxiang Wu, Zhengyao Jiang Published: 2026-05-20 Categories: cs.SE, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2605.21384v1 As long-horizon coding agents produce more code than any developer can review, oversight collapses onto a single surface: the automated test suite. Reward hacking naturally arises in this setup, as the agent optimizes for passing tests while deviating from the users true goal. We study this reward hacking phenomenon by decompose software engineering tasks into three parts: (i) a natural language description of the specification (ii) visible validation tests that exercise specified features in isolation, and (iii) held-out tests that compose those same features to simulate real-world usage. Based on the specification and the visible validation test suites, a genuine agent would be able to generate a solution that can also pass all of the held-out tests. Therefore we use the gap in pass rates on these two suites to quantify reward hacking. Based on this methodology, we introduce SpecBench, a benchmark comprising 30 systems-level programming tasks ranging from short horizon tasks like building a JSON parser to ultra long horizon tasks like building an entire OS kernel from scratch. Large-scale experiments reveal a consistent pattern: while every frontier agent saturates the visible suite, reward hacking persists, with smaller models exhibiting larger gaps on holdout suites. The gap also scales sharply with task length: it grows by 28 percentage points for every tenfold increase in code size. Failures range from subtle feature isolation to deliberate exploits, including a 2,900-line hash-table "compiler" that memorizes test inputs. SpecBench offers a principled testbed for measuring whether coding agents build genuine working systems or merely game the test suites developers hand them. --- ### Disentangling Generation and Regression in Stochastic Interpolants for Controllable Image Restoration Authors: Yi Liu, Jia Ma, Wengen Li, Jihong Guan, Shuigeng Zhou, Yichao Zhang Published: 2026-05-20 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2605.21381v1 Recent advances in Image Restoration (IR) have been largely driven by generative methods such as Diffusion Models and Flow Matching, which excel in synthesizing realistic textures while suffering from slow multi-step inference and compromised pixel fidelity. In contrast, classical regression-based IR methods excel precisely in these aspects, offering single-step efficiency and high pixel-level reconstruction fidelity. To bridge this gap, we propose DiSI, a unified framework that Disentangles the underlying Stochastic Interpolant process into independent generation and regression components. This decoupling endows DiSI with remarkable versatility, enabling a continuous and controllable transition from a pure regression process to a fully generative one. Technically, we instantiate this framework with two specific sampling trajectories, accompanied by a unified sampler for high-quality, few-step inference on arbitrary trajectories. Furthermore, we design a dual-branch U-Net style transformer network in pixel space, using a dedicated branch to enhance conditional guidance while ensuring high throughput. Extensive experiments demonstrate that DiSI efficiently achieves competitive results on various IR tasks, while uniquely offering the inference-time flexibility to control the distortion-perception trade-off within a single model. --- ### How to Build Marcus's Algebraic Mind: Algebro-Deterministic Substrate over Galois Fields Authors: Hiroyuki Chuma, Kanji Otsuk, Yoichi Sato Published: 2026-05-20 Categories: cs.NE, cs.AI arXiv: https://arxiv.org/abs/2605.21379v3 In The Algebraic Mind (2001), Marcus held that any adequate cognitive architecture needs operations over variables, recursively structured representations, and an individual/kind distinction, and that multilayer perceptrons support none of them; he left a register-and-treelet implementation as a conjecture. Twenty-five years later a memory architecture built for unrelated reasons (speed, power and cost on commodity silicon) meets that specification operation for operation, through one mechanism rather than three. PyVaCoAl/VaCoAl is a hyperdimensional computing architecture built end-to-end on one primitive: XOR-and-shift over GF(2), realised by primitive-polynomial linear-feedback shift registers (LFSRs). It gives reversible binding Bind(R,F) = R xor shift(F), non-commutative bundling that distinguishes "dog bites man" from "man bites dog", and address-space individual/kind separation, at fixed dimension. Capability: exact reversible binding at O(L) cost supplies each pillar as an architectural primitive, not a product of training, with inspectability no lossy substrate offers. Necessity: weaken the primitive to an approximate inverse, as circular convolution does, and all three pillars degrade together -- what cannot be exactly decomposed was never composed, only mixed. Position: this is not the mind, the brain is not an LFSR, and we do not beat large language models; the substrate supplies the auditable symbolic layer they structurally lack. We develop the correspondence pillar by pillar, recast the treelet as a register set identified by a primitive generator polynomial, cite a companion Perspective on the dentate gyrus-CA3 circuit as a biological instance, and show that inflecting an unseen pseudoverb is a rung-3 query in Pearl's sense. Bit-exact reversibility holds in silicon and only approximately under biological noise; biological claims are structural only. --- ### How to Build Marcus's Algebraic Mind: Algebro-Deterministic Substrate over Galois Fields Authors: Hiroyuki Chuma, Kanji Otsuk, Yoichi Sato Published: 2026-05-20 Categories: cs.NE, cs.AI arXiv: https://arxiv.org/abs/2605.21379v2 In The Algebraic Mind, Gary Marcus identified three components essential for any adequate cognitive architecture: operations over variables, recursively structured representations, and a distinction between mental representations of individuals and kinds. He argued that standard multilayer perceptrons supported none of these, acknowledging that a neural implementation using registers and treelets, constructed via developmental programs rather than gradient descent, remained a programmatic conjecture. Twenty-five years later, the required substrate is now available. Our newly developed PyVaCoAl/VaCoAl is a hyperdimensional computing architecture organized end-to-end around a single algebraic primitive: XOR-and-shift over GF(2), implemented by primitive-polynomial linear-feedback shift registers. The architecture supports reversible variable binding via Bind(R,F) = R XOR shift(F), non-commutative compositional bundling that distinguishes "the dog bites the man" from "the man bites the dog," and address-space individual/kind separation under the same algebra. A companion perspective argues that the dentate gyrus-CA3 circuit is a biological homologue of this same engine, with developmentally specified mossy-fiber targeting supplying the innate microcircuitry Marcus anticipated. In this paper, we map the correspondence between Marcus's three pillars and the operational commitments of PyVaCoAl/VaCoAl. We reinterpret the treelet as an algebraic register set indexed by a primitive generator polynomial, arguing that this architecture provides a functional neural substrate meeting Marcus's specifications far more closely than the tensor products, circular convolution, or temporal synchrony available in 2001. We also demonstrate how this substrate naturally extends to Pearl's rung-3 counterfactual reasoning, a capability the original treelet program did not directly target. --- ### Closed Loop Dynamic Driving Data Mixture for Real-Synthetic Co-Training Authors: Hongzhi Ruan, Pei Liu, Weiliang Ma, Zhengning Li, Xueyang Zhang, Jun Ma, Dan Xu, Kun Zhan Published: 2026-05-20 Categories: cs.CV, cs.AI, cs.LG, cs.RO arXiv: https://arxiv.org/abs/2605.21372v1 Data scaling is fundamental to modern deep learning, and grows increasingly critical as autonomous driving shifts to end-to-end learning. Real-world driving data is expensive to annotate and scene-biased, making real-synthetic co-training with near-infinite synthetic data a promising direction. However, naively incorporating all available synthetic data is inefficient and leads to distribution shifts, and optimizing data mixture under practical training budgets remains a critical yet under-explored problem. In this sense, we claim that the mixture of training data requires clear guidance in terms of scene types and quantities. Particularly in this work, we conceptualize the data mixture approximately as a dynamic optimization process that iteratively adjusts the training data mixture to maximize model performance, guided by closed-loop evaluation feedback, and propose AutoScale, a fully automated closed-loop data engine unifying scene representation, data mixture optimization and retrieval, as well as model training and evaluation. Specifically, we propose Graph Regularized AutoEncoder (Graph-RAE) for driving scene representations, introduce Cluster-aware Gradient Ascent (Cluster-GA) for cluster-wise importance estimation and reweighting, and perform cluster-guided vector retrieval to select high-value samples. Experiments on NavSim demonstrate that AutoScale outperforms vanilla co-training and cross-domain baselines, achieving better performance with fewer synthetic samples under constrained budgets. --- ### A Non-Reference Diffusion-Based Restoration Framework for Landsat 7 ETM+ SLC-off Imagery in Antarctica Authors: Leyue Tang, Jonathan Louis Bamber, Gang Qiao, Yuanhang Kong Published: 2026-05-20 Categories: cs.CV arXiv: https://arxiv.org/abs/2605.21371v1 Acquiring usable optical imagery in Antarctica is inherently challenging due to prolonged polar nights and frequent cloud cover. Landsat provides the longest and most continuous optical observations and constitutes one of the most important remote sensing data sources for Antarctic studies. However, the scan-line corrector (SLC) failure in 2003 resulted in approximately 22% missing pixels in Landsat 7 ETM+ SLC-off imagery, severely limiting its usability. Unlike many non-polar environments, Antarctic surfaces undergo rapid and substantial changes, which makes it difficult to obtain reliable reference imagery and reduces the applicability of conventional reference-based gap-filling methods. To address this challenge, we propose DiffGF, a non-reference diffusion-based framework for restoring Landsat 7 SLC-off imagery without requiring any external reference data. DiffGF adopts a two-stage design consisting of a latent-space diffusion process and a pixel-space refinement. A dedicated Antarctic dataset, SLCANT, is constructed for training and evaluation. Quantitative and qualitative results demonstrate that DiffGF restores Antarctic SLC-off imagery with high fidelity. Its practical value is further examined through a downstream crevasse segmentation application. The results suggest that DiffGF provides a useful approach for exploiting Landsat 7 SLC-off archives in Antarctica, enabling the extraction of valuable information from historical records and supporting related Antarctic studies. --- ### Findings of the Fifth Shared Task on Multilingual Coreference Resolution: Expanding Datasets for Long-Range Entities Authors: Michal Novák, Miloslav Konopík, Anna Nedoluzhko, Martin Popel, Ondřej Pražák, Jakub Sido, Milan Straka, Zdeněk Žabokrtský, Daniel Zeman Published: 2026-05-20 Categories: cs.CL arXiv: https://arxiv.org/abs/2605.21369v2 This paper describes the fifth edition of the Shared Task on Multilingual Coreference Resolution, held in conjunction with the CODI-CRAC 2026 workshop. Building on previous iterations, the task required participants to develop systems capable of mention identification and identity-based coreference clustering. The 2026 edition specifically emphasizes long-range entities, defined as coreferential chains spanning significant distances, across many words and sentences. The task expanded its linguistic scope by incorporating five new datasets and two additional languages. These additions leverage version 1.4 of CorefUD, a harmonized multilingual collection comprising 27 datasets in 19 languages. In total, ten systems participated, including four LLM-based approaches (three fine-tuned models and one few-shot approach). While traditional systems still maintained their lead, LLMs demonstrated significant potential, suggesting they may soon challenge established approaches in future editions. --- ### $L^2$ over Wasserstein: Statistical Analysis for Optimal Transport Authors: Riccardo Passeggeri, Rohan M. Shenoy, Pengcheng Ye Published: 2026-05-20 Categories: math.ST, stat.ML arXiv: https://arxiv.org/abs/2605.21365v1 Optimal transport provides an inherently geometric and highly structured framework for studying spaces of probability measures, supplying a rich theoretical toolkit for contemporary statistics, machine learning, and generative modelling. In applications, however, the measures of interest are almost never known precisely, calling for a theory of optimal transport that accounts for statistical uncertainty. We construct such a framework, lifting the classical theory to the setting of random probability measures. We introduce the $L^2$ over Wasserstein space establishing that it inherits the formal Riemannian structure of the Wasserstein space by characterising distances and geodesic geometry. The structure induces random flows with Wasserstein gradient flow sample paths, making it the natural extension of the Wasserstein space which allows for random gradient flow dynamics. We ensemble statistical convergence results of the optimal transport machinery using the empirical measure within the $L^2$ over Wasserstein framework. Moreover, in the setting of Bayesian non-parametrics, we refine Schwartz's consistency theorem to the Wasserstein topology and deduce posterior convergence of the same machinery in the $L^2$ over Wasserstein space. We demonstrate that the growing theory of random token sampling for transformer models using self-attention flow paths can be embedded into the our framework. The results provide a unified treatment of random optimal transport and its consequences for principled inference and generative modelling under the statistical uncertainty of random sampling. --- ### "I Didn't Make the Micro Decisions": Measuring, Inducing, and Exposing Goal-Level AI Contributions in Collaboration Authors: Eunsu Kim, Jessica R. Mindel, Kyungjin Kim, Sherry Tongshuang Wu Published: 2026-05-20 Categories: cs.CL arXiv: https://arxiv.org/abs/2605.21363v2 As large language models (LLMs) increasingly shape how users form, refine, and extend their goals, attributing contributions in human-AI collaboration becomes critical for users calibrating their own reliance and for evaluators assessing AI-assisted work. Yet existing methods focus on final artifacts, missing the process through which goals themselves are jointly shaped. We introduce a goal-level attribution framework, CoTrace, that decomposes explicit goals into verifiable requirements and traces both direct contributions and indirect influences across dialogue turns. Applying CoTrace to 638 real-world collaboration logs, we find that while models account for only 11-26% of goal-shaping contribution, they contribute substantially more on introducing lower-level concrete requirements, and make various kinds of indirect contributions. Through controlled simulations, we show that interaction design choices significantly affect model goal-shaping behavior. In a user study, exposing participants to goal-level analyses shifts their perceived contributions by nearly 2 points on a 5-point scale, revealing systematic miscalibration in how users understand their own AI-assisted work. --- ### LASH: Adaptive Semantic Hybridization for Black-Box Jailbreaking of Large Language Models Authors: Abdullah Al Nomaan Nafi, Fnu Suya, Swarup Bhunia, Prabuddha Chakraborty Published: 2026-05-20 Categories: cs.CL arXiv: https://arxiv.org/abs/2605.21362v1 Jailbreak attacks expose a persistent gap between the intended safety behavior of aligned large language models and their behavior under adversarial prompting. Existing automated methods are increasingly effective but each commits to a single attack family (e.g., one refinement loop, one tree search, one mutation space, or one strategy library) and no single family dominates: the best-performing method shifts across target models and harm categories, suggesting complementary strengths that per-prompt composition could exploit. We introduce LASH (LLM Adaptive Semantic Hybridization), a black-box framework that treats outputs from multiple base attacks as reusable seed prompts and adaptively composes them for each target request. Given a seed pool, LASH searches over seed subsets and softmax-normalized mixture weights; a composition module synthesizes a single candidate prompt, and a derivative-free genetic optimizer updates the weights using black-box target feedback and a two-stage fitness function combining keyword-based refusal detection with LLM-judge scoring. On JailbreakBench, which contains 100 harmful prompts across 10 categories, we evaluate LASH on six common target models. LASH achieves an average attack success rate of 84.5% under keyword-based evaluation and 74.5% under two-stage evaluation, where responses are first filtered for refusals and then scored by an LLM judge for whether they substantively fulfill the original harmful request. LASH outperforms five state-of-the-art baselines on both metrics with only 30 mean target queries. LASH also remains competitive under three defense mechanisms and induces more success-like internal representations. These results suggest that adaptive composition across heterogeneous jailbreak strategies is a promising direction for black-box red-teaming. --- ### Classification of Single and Mixed Partial Discharges under Switching Voltage Using an AWA-CNN Framework Authors: Md Rafid Kaysar Shagor, Zannatul Ferdousy Mouri, Farhina Haque, Anindya Bijoy Das Published: 2026-05-20 Categories: cs.LG, cs.CE, cs.ET arXiv: https://arxiv.org/abs/2605.21352v1 The growing use of fast-switching power electronics has made partial discharge (PD) analysis under switching-voltage excitation increasingly important, yet more challenging than under sinusoidal conditions due to activity concentrated at voltage transitions. This work presents an Amplitude-Width-Area (AWA) pattern representation for source-oriented PD analysis under switching-voltage excitation. In the proposed method, time domain PD pulses are characterized using pulse amplitude, width, and area, and mapped into a visual pattern where amplitude and area define the coordinate axes and width is encoded by color. The generated AWA patterns are used to distinguish six single and mixed PD source conditions: corona, internal, surface, corona+internal, corona+surface, and internal+surface. To evaluate the classification capability of the proposed representation, a Random Forest baseline and two Convolutional Neural Network (CNN) models, InceptionV3 and ResNet-18, are compared. The AWA patterns show distinguishable source-dependent distributions, and CNN-based classification achieves testing accuracy above 96%, compared with 73.33% for Random Forest. The results indicate that AWA patterns provide a visual representation of PD pulses suitable for multi-class PD source classification under switching-voltage excitation. --- ### Data-Efficient Neural Operator Training via Physics-Based Active Learning Authors: Alicja Polanska, Lorenzo Zanisi, Vignesh Gopakumar, Stanislas Pamela Published: 2026-05-20 Categories: cs.LG, cs.AI, math.NA, physics.comp-ph arXiv: https://arxiv.org/abs/2605.21348v1 Solving partial differential equations with neural operators significantly reduces computational costs but remains bottlenecked by high training data requirements. Active learning offers a natural framework to mitigate this by selectively acquiring the most informative samples in an iterative manner. We introduce physics-based acquisition - a novel physics-informed active learning algorithm that leverages the partial differential equation residual to guide data selection. We validate the method by presenting numerical experiments for the 1D Burgers equation and the 2D compressible Navier-Stokes equations. We show that, in our experiments, physics-based acquisition consistently outperforms random acquisition and matches the state of the art in data efficiency. At the same time, it has the unique advantage of injecting a physics inductive bias into the training process, ensuring that simulation cost is spent where the model's physical understanding is weakest. --- ### Insights Generator: Systematic Corpus-Level Trace Diagnostics for LLM Agents Authors: Akshay Manglik, Apaar Shanker, Kaustubh Deshpande, Jason Qin, Yash Maurya, Veronica Chatrath, Vijay S. Kalmath, Levi Lentz, Yuan Xue Published: 2026-05-20 Categories: cs.AI, cs.LG, cs.SE arXiv: https://arxiv.org/abs/2605.21347v3 Diagnosing failures in LLM agents remains largely manual. Practitioners inspect a small subset of execution traces, form ad-hoc hypotheses, and iterate. This process misses patterns that only emerge across trace populations and does not scale to production corpora where individual traces span tens of thousands of tokens. We formalize the problem of corpus-level trace diagnostics. Given a corpus of execution traces, the goal is to produce grounded natural-language insights that characterize systematic behavioral patterns across trace groups, each linked to supporting evidence. We present the Insights Generator (IG), a multi-agent system that answers diagnostic questions by proposing and testing hypotheses across the trace corpus to produce an evidence-backed insights report. We evaluate IG across qualitative and objective dimensions, spanning rubric-based report assessment and downstream performance improvements achieved by implementing IG insights. Human experts using IG reports improve scaffold performance by 30.4pp over the unmodified baseline scaffold, and coding agents leveraging IG-derived insights show consistent and stable gains. Across benchmarks, IG's scout-investigator architecture produces findings comparable in detection coverage to competing approaches, while domain experts rated IG reports as leading depth and evidence quality. --- ### OcclusionFormer: Arranging Z-Order for Layout-Grounded Image Generation Authors: Ziye Li, Henghui Ding Published: 2026-05-20 Categories: cs.CV arXiv: https://arxiv.org/abs/2605.21343v1 Recent layout-to-image models have achieved remarkable progress in spatial controllability. However, they still struggle with inter-object occlusion. When bounding boxes overlap, most existing methods lack explicit occlusion information, which makes the generation in intersection regions inherently ambiguous and hinders the determination of complex occlusion relationships. As a result, they often produce entangled textures or physically inconsistent layering in the overlapped areas. To address this issue, we first construct SA-Z, a large-scale dataset enriched with explicit occlusion ordering and pixel-level annotations. Building upon our proposed dataset, we introduce OcclusionFormer, a novel occlusion-aware Diffusion Transformer framework that explicitly models Z-order priority by decoupling instances and compositing them via volume rendering. Furthermore, to ensure fine-grained spatial precision, we introduce a queried alignment loss that explicitly supervises individual instances and enhances semantic consistency. The proposed method effectively reduces ambiguity in overlapping regions, enforces correct occlusion dependencies, and preserves structural integrity, leading to substantial accuracy gains across diverse scenes. --- ### Semiparametric Efficient Bilevel Gradient Estimation Authors: Fares El Khoury, Houssam Zenati, Nathan Kallus, Michael Arbel, Aurélien Bibaut Published: 2026-05-20 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2605.21341v1 Functional bilevel methods estimate a lower-level function and plug it into a hypergradient, but this plug-in gradient can retain first-order bias when the lower-level problem is learned nonparametrically. To remove this bias, we develop a semiparametric debiasing theory for population bilevel gradients based on the efficient influence function. This perspective leads to a cross-fitted orthogonal hypergradient estimator for which we establish asymptotic normality together with uniform control over the outer parameter. Under quadratic losses, the estimator reduces to a simple doubly robust score based on conditional mean nuisances. On synthetic bilevel benchmarks with known ground truth, the method tracks the oracle efficient-gradient benchmark and improves over plug-in functional hypergradients and regularized kernel bilevel baselines. --- ### Text Analytics Evaluation Framework: A Case Study on LLMs and Social Media Authors: Yuefeng Shi, Nedjma Ousidhoum, Jose Camacho-Collados Published: 2026-05-20 Categories: cs.CL arXiv: https://arxiv.org/abs/2605.21338v1 LLMs have demonstrated exceptional proficiency in a wide range of NLP tasks. However, a notable gap remains in practical data analysis scenarios, particularly when LLMs are required to process long sequences of unstructured documents, such as news feeds or, as specifically addressed in this paper, social media posts. To empirically assess the effectiveness of LLMs in this setting, we introduce a question-based evaluation framework comprising 470 manually curated questions designed to evaluate LLMs' semantic understanding and reasoning abilities over aggregated text data. We apply our benchmark on diverse Twitter datasets covering various NLP tasks, including sentiment analysis, hate speech detection, and emotion recognition. Our results reveal that the performance depends heavily on input scale and the complexity of the data sources, declining noticeably in multi-label or target-dependent scenarios. In addition, as task complexity increases, performance drops progressively from basic semantic existence identification to more demanding operations such as comparison, counting, and calculation. Furthermore, as the input size grows beyond 500 instances, we identify a common limitation across LLMs, particularly Open-weights models: performance degrades substantially, especially on numerical tasks. These findings highlight critical architectural bottlenecks in current LLMs for performing rigorous quantitative analysis over large text collections. --- ### SymbolicLight V1: Spike-Gated Dual-Path Language Modeling at High Encoder Spike Sparsity Authors: Ting Liu Published: 2026-05-20 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2605.21333v3 Natively trained spiking language models must preserve information across time while operating through sparse binary activations, a combination that has produced a persistent quality gap relative to dense Transformers. We present SymbolicLight V1, a spike-gated dual-path language model that couples binary Leaky Integrate-and-Fire (LIF) dynamics with a continuous residual stream. Its Dual-Path SparseTCAM mixer combines a first-order exponential-decay state with windowed local attention on the continuous residual stream, followed by a context-conditioned decoding head. We train four 194M-parameter models from scratch on a 3B-token, 10-domain Chinese-English corpus. On a fixed token-weighted evaluation set the runs reach perplexity (PPL) 8.88-8.93 (mean 8.904, sample standard deviation 0.019). Separation of this set from the training streams has not been verified. Training-time encoder probes have a mean zero-spike fraction of 89.96%; this is not a whole-model sparsity measure. Code tokens are 43.7% of that set; the unweighted mean of the ten domain PPLs is 29.38. Under the same corpus, tokenizer, token budget, and hardware, the token-weighted mean is 7.7% above GPT-2 201M (PPL 8.27). Across five zero-shot benchmarks the two 200M-scale models show no clear accuracy separation. Under sampling with temperature 0.7 and top-k 50, SymbolicLight produces lower 4-gram repetition; an entropy-modulated rule reverses that ranking. On an RTX 2080 Ti, measured generation throughput is 22.8 versus 91.5 token/s; post-generation power readings give rough energy estimates of 2,848 versus 905 mJ/token, without power integration over generation. ---