# Research Papers — 2026-05 · bundle page 105 of 326 > Full-text markdown of papers #5201–5250 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/105 [← Previous bundle](https://aipod.dev/papers/archive/2026-05/page/104.md) [Next bundle →](https://aipod.dev/papers/archive/2026-05/page/106.md) ### Mode-Shape Expansion Using Physics-Constrained Gaussian Process Regression Authors: Farid Ghahari Published: 2026-05-21 Categories: math.NA, stat.ML arXiv: https://arxiv.org/abs/2605.23101v1 This paper addresses the challenge of reconstructing full-field structural mode shapes from sparse sensor data. While Gaussian Process Regression (GPR) offers a robust non-parametric framework for spatial interpolation and uncertainty quantification, standard formulations often yield physically inconsistent mode-shape reconstructions under sparse sensing conditions. A Physics-Constrained Single-Output Gaussian Process (CONS-SOGP) framework is derived that utilizes independent modal kernels while coupling the optimization via a mass-orthogonality penalty. The paper presents derivations for the marginal likelihood, hyperparameter gradients, and penalty coupling. Numerical verification on a multi-degree-of-freedom structure demonstrates that the proposed method overcomes existing limitations in GP-based prediction, providing more accurate and reliable expanded mode shapes. --- ### Encrypted Neural Networks without Overflows Authors: Philipp Kern, Lorenzo Rovida, Samuel Teuber, Edoardo Manino, Carsten Sinz, Alberto Leporati Published: 2026-05-21 Categories: cs.CR, cs.LG arXiv: https://arxiv.org/abs/2605.23096v2 The popular Cheon-Kim-Kim-Song (CKKS) scheme enables efficient private inference in neural networks by evaluating them on encrypted data. Since CKKS only supports addition, multiplication, and array rotation operations, turning neural networks into CKKS circuits requires approximating all activation functions (e.g. ReLU) with polynomials over fixed input ranges. Traditionally, these ranges are estimated via heuristic sampling techniques. In this paper, we empirically demonstrate that sampled ranges leave the CKKS network exposed to overflow events, i.e. legitimate inputs that exceed the ranges of the circuit and cause corrupted outputs, and propose an improved design technique that completely avoids them. First, we propose a practical algorithm to induce overflow events in a CKKS circuit, i.e. we automatically craft legitimate inputs that exceed the design ranges within the circuit and cause corrupted outputs. As an example, our algorithm can quickly corrupt around 47% of benign inputs in a CIFAR10 neural network. Second, we propose an end-to-end formal verification approach that constructs executable CKKS circuits. These circuits are guaranteed to be overflow-free and come with certified error bounds on the output difference w.r.t. the original neural network. Our experiments demonstrate that our approach supports a larger set of neural network architectures than prior certified techniques, while also delivering executable CKKS artifacts. --- ### Encrypted Neural Networks without Overflows Authors: Philipp Kern, Lorenzo Rovida, Samuel Teuber, Edoardo Manino, Carsten Sinz, Alberto Leporati Published: 2026-05-21 Categories: cs.CR, cs.LG arXiv: https://arxiv.org/abs/2605.23096v1 Fully homomorphic encryption (FHE) enables private inference by evaluating neural networks on encrypted data. In this way, we can delegate the computation to a third party server without ever revealing the user's data. Currently, the CKKS scheme is the backbone of most efficient FHE implementations, but it only supports addition, multiplication, and array rotation operations, thus requiring all activation functions of the neural network to be approximated by polynomials within a certain interval, imposing strict design tolerances. In this paper, we demonstrate for the first time that this scheme is vulnerable to overflow attacks, i.e., seemingly benign inputs that can exceed such tolerances of the FHE circuit, thereby causing corrupt and unusable outputs. To avoid them, we propose a formal verification technique that computes certified bounds on the ranges of all neurons in the network. By construction, our method eliminates overflows and, in our experiments, removed observed overflows on all benchmarks, reducing failure rates from up to 47% to 0%. Moreover, our overflow-free solution is compatible with most CKKS-based frameworks, as it allows to simply substitute standard polynomials by polynomials with rigorously designed ranges. --- ### Do Synthetic Brain MRIs Reliably Improve Tumour Classification? A StyleGAN2-ADA Class-Plane Augmentation Study on BRISC 2025 Authors: José Rafael Noriega Cedeño Published: 2026-05-21 Categories: eess.IV, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2605.23094v1 Generative augmentation is often proposed as a remedy for small medical-image datasets, but synthetic images are only useful when they improve downstream task performance. "Augmentation" here means synthetic supplementation: GAN-generated samples added to the real training pool, not geometric or photometric transforms of existing images. Twelve class-plane StyleGAN2-ADA generators were trained on constrained BRISC 2025 partitions to test whether their output, with or without InceptionV3 feature-space filtering, improves held-out tumour classification across three classifier families: a random forest (RF) on InceptionV3 features, a compact two-headed convolutional neural network (CNN), and MobileViTV2, a mobile hybrid convolutional-transformer. Each was evaluated at 1:1 and 1:2 real-to-synthetic ratios. An independent GPT-5.5 blind test placed gated real-versus-synthetic discrimination at 57.73% (95% CI: 54.48--60.92%) on the model-legible subset -- modestly above chance. The RF classifier did not benefit from the synthetic MRIs. The CNN showed consistent mean gains that did not survive Holm correction. MobileViTV2 showed the clearest benefit: filtered 1:1 augmentation improved tumour classification accuracy by 1.02% absolute (95% CI: 0.54--1.54%; Holm-corrected p = 0.0104). A secondary efficiency analysis found that every augmented CNN condition selected its checkpoint 42--64% earlier than baseline, while compute-matched MobileViTV2 runs reached selection after 50--67% fewer real-data epochs. Overall, augmentation utility was found to be architecture- and ratio-dependent, not guaranteed by visual fidelity alone. --- ### A Comparative Evaluation of Structural Topic Models and BERTopic for Short, Open-Ended Survey Responses Authors: Yan Jiang, Sihong Liu, Philip A. Fisher Published: 2026-05-21 Categories: cs.CL, cs.CY arXiv: https://arxiv.org/abs/2605.23093v1 Topic modeling in applied psychology increasingly spans two methodological traditions: probabilistic bag-of-words models and newer embedding-based approaches. Yet many evaluations of these methods rely on longer and cleaner benchmark corpora, leaving less guidance for short, open-ended survey responses. This paper compares Structural Topic Models (STM), a probabilistic topic model, and BERTopic, an embedding-based model, for analyzing open-ended survey responses. We evaluated three STM conditions and five BERTopic conditions, varying typographical correction, stemming, embedding choice, and contextual augmentation, a strategy we introduced to provide additional semantic context for very short responses. Results indicate that BERTopic consistently produced higher topic coherence than STM, with contextual augmentation yielding the strongest performance gains. In contrast, higher-dimensional embeddings alone did not improve coherence and were associated with greater data loss. Qualitative evaluation showed that BERTopic generated more interpretable and stable topics, while STM topics were often broader and more mixed. However, STM provides stronger support for inferential covariate analysis, whereas BERTopic covariate comparisons are primarily descriptive. These findings suggest that STM and BERTopic offer complementary strengths. We conclude with practical guidance for selecting and combining topic modeling approaches in applied social science research. --- ### Security of LLM-generated Code: A Comparative Analysis Authors: Srivathsan G Morkonda, Mahmoud Selim, Hala Assal Published: 2026-05-21 Categories: cs.SE, cs.AI, cs.CR arXiv: https://arxiv.org/abs/2605.23091v1 The majority of software developers use or are planning to use Artificial Intelligence (AI) tools in their development processes. Their top reasons include improving productivity and faster learning. In fact, Large Language Model (LLM)-generated code is currently in production, including in major tech companies. However, concerns were raised about the risks associated with the use of AI tools to generate code. In this paper, we focus our attention on the risks to software security. We empirically evaluate the security of code generated by seven popular LLMs. We build upon previous work to mimic the behaviours of developers when using LLMs to generate code. Our results show that all seven LLMs that we have evaluated generate code that contains vulnerabilities, the majority of which are of critical or high severity. --- ### Dreaming Smoothly and Sample Efficiently with Gradient Penalized Latent Dynamics Authors: Romil V. Sonigra, P. R. Kumar Published: 2026-05-21 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2605.23089v1 Model-based reinforcement learning improves sample efficiency by learning a world model. However, existing latent world models such as DreamerV3 do not explicitly enforce local smoothness in their learned transition dynamics, leaving a useful inductive bias for transition dynamics learning unexploited. We propose GPLD, a gradient-penalized latent dynamics regularizer for DreamerV3 that applies a row-wise Jacobian penalty to the posterior latent distribution to encourage locally smooth transition learning. We show that this penalty can be interpreted as the continuous-latent analog of finite-difference smoothing of transition laws in discrete embedded-state MDPs, and estimate it efficiently using Hutchinson-style stochastic probes. Empirically, across DeepMind Control proprioceptive tasks, GPLD improves aggregate sample efficiency, with particularly strong gains on higher-complexity locomotion environments. On more challenging quadruped tasks, GPLD reaches high-return behavior earlier and exhibits more consistent late-stage learning over longer horizons. Explicit local smoothness regularization is a simple and effective way to improve latent world models for smooth continuous control environments. Code for GPLD is available at github.com/romils9/gpld-mbrl . --- ### The Implicit Bias of Depth: From Neural Collapse to Softmax Codes Authors: Connall Garrod, Jonathan P. Keating, Christos Thrampoulidis Published: 2026-05-21 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.23087v1 Neural collapse (NC) describes the structured geometry that emerges in the features and weights of trained classifiers. Recent theory suggests NC can be suboptimal in deep architectures, attributing this to an explicit low-rank bias from L2 regularization. We study the deep unconstrained feature model (UFM)-equivalent to a deep linear network with orthogonal inputs-trained without regularization, to isolate how gradient descent and depth alone shape NC. We show that depth induces an implicit low-rank bias: low-rank matrices propagate norm more efficiently through successive multiplications, promoting low-rank alternatives to NC. These alternatives, we argue, correspond to softmax codes: max-margin solutions previously found in width-bottlenecked networks. Analyzing training dynamics under spectral initialization, we identify an early-time repulsion among singular values that drives low-rank emergence, and characterize how depth shrinks NC's basin of attraction. Finally, we show that some effects act in the opposite direction: for randomly initialized networks, increasing width biases training toward higher-rank solutions. Our results provide the first asymptotic and dynamic characterization of implicit bias in deep UFMs trained with unregularized multiclass cross-entropy. --- ### KAPLAN: Kolmogorov-Arnold Prognostic Learnable Activation Networks for Survival Analysis Authors: Stelios Boulitsakis Logothetis, Angela Wood, Pietro Liò Published: 2026-05-21 Categories: stat.ML, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2605.23082v2 Survival analysis aims to model how covariates and time jointly shape the time-to-event distribution under right censoring. Classical methods such as the Cox model and generalised additive models (GAMs) require interactions and time-varying effects to be manually specified, which is increasingly impractical on rich clinical datasets. We introduce KAPLAN-HR, a B-spline Kolmogorov-Arnold Network (KAN) for nonparametric estimation of the conditional hazard as a joint function of covariates and time. A single-layer KAPLAN-HR model recovers a GAM, while deeper architectures capture interactions and time-varying effects through composition. We establish a convergence rate for the nonparametric KAN hazard estimator that depends only on the smoothness of the underlying KAN representation and not on the covariate dimension, thereby mitigating the curse of dimensionality for KAN-representable targets. In evaluations over six clinical benchmark datasets, KAPLAN-HR matches or exceeds the predictive performance of established statistical and deep learning survival methods. --- ### ThriftAttention: Selective Mixed Precision for Long-Context FP4 Attention Authors: Joe Sharratt Published: 2026-05-21 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.23081v1 Efficient attention algorithms are critical to mitigate the quadratic cost of attention in long-context workloads. Prior work utilises block-scaled quantisation techniques on Blackwell GPUs to move attention computation to 4-bit precision to accelerate inference. However, these techniques result in significant quality degradation in long-context settings. We show that the output impact of quantisation error is highly non-uniform and increases with the importance of each query-key interaction, concentrating functionally relevant error in a small number of attention blocks that contain the most important tokens. We propose ThriftAttention, a low-bit attention variant that delivers near-FP16 long-context quality at FP4 inference efficiency. This approach proceeds in two stages. First, a heuristic rapidly selects a small number of important query-key block pairs for FP16 precision. Second, the selected blocks are computed in FP16 and the remaining blocks in FP4, with both paths merged via online softmax into a single output. We demonstrate across long-context benchmarks and model families that by computing only 5% of query-key blocks in FP16, ThriftAttention recovers on average 89.1% of the FP4-to-FP16 performance gap. We show ThriftAttention's advantage grows with sequence length, mitigating the systematic FP4 quality degradation observed at longer contexts. The code is available at https://github.com/joesharratt1229/ThriftAttention. --- ### The Attribution Contract for Generative Language Models Authors: Giang Nguyen Published: 2026-05-21 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.23080v3 Feature attribution scores each part of an input by how much it explains a model's output. We argue that in generative language models these scores carry no fixed meaning. A classifier has a single output to explain, but a generative model produces its output token by token, and each generated token is both an output and an input, so explaining the output becomes several distinct questions. We support this claim by proposing the Attribution Contract, a framework that names the question a set of attribution scores answers. A contract specifies the model score being explained, what is held fixed, the target output, the generation process, and which features can receive attribution, choices that matter in practice. For example, eligible features decide what a score explains: under a local next-token contract, the model's own generated tokens receive $29\%$ of the attribution mass, comparable to the $25\%$ on the input question, and reading this as a prompt-level explanation is a mistake we name the self-attribution fallacy. The generative process also shapes feature attribution: on a mixture-of-experts model, Integrated Gradients completeness is unreliable, since recomputing expert routing along the attribution path leaves a large residual that holding the routing fixed substantially lowers, while a masked-diffusion model, which fixes its choices at generation, has a residual that instead decreases with more steps. These results show that Attribution Contracts should be carefully specified when proposing and evaluating attribution methods for generative language models, since the meaning and evaluation of an attribution depend on its explanatory setting. --- ### The Attribution Contract: Feature Attribution for Generative Language Models Authors: Giang Nguyen Published: 2026-05-21 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.23080v2 Feature attribution methods promise to identify which input features matter for a model output. In generative language models, however, it is often unclear what should count as a feature in the first place. In autoregressive language models, earlier generated tokens are both outputs of the model and inputs to later predictions. In diffusion language models, generation proceeds through iterative denoising or unmasking rather than fixed left-to-right prediction, so local explanation may target a state of diffusion rather than a next token. We argue that this ambiguity is not merely an implementation detail, but a conceptual limitation of carrying classifier-era feature attribution directly into generative language modeling. We introduce the Attribution Contract, a specification for feature-attribution claims that names what output is being explained, which features are eligible to receive attribution, what generative process is assumed, what is held fixed, and what model score is being attributed. The contract clarifies why the same attribution method can answer different questions depending on how it is instantiated. We argue that many disagreements about feature attribution in generative language models are not disagreements about attribution algorithms, but about unstated explanatory contracts. Using autoregressive and diffusion language models as case studies, we show when attribution to earlier generated tokens, intermediate states, or denoising stages is informative, when it is misleading, and why feature-attribution methods in generative language models should be evaluated as method-contract pairs. --- ### GEMQ: Global Expert-Level Mixed-Precision Quantization for MoE LLMs Authors: Jianing Deng, Song Wang, Dongwei Wang, Zijie Liu, Tianlong Chen, Huanrui Yang, Jingtong Hu Published: 2026-05-21 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2605.23078v1 Mixture-of-Experts Large Language Models (MoE-LLMs) achieve strong performance but incur substantial memory overhead due to massive expert parameters. Mixed-precision quantization mitigates this cost by allocating expert-wise bit-widths based on their importance, approaching the accuracy-memory Pareto frontier and enabling extreme low-bit quantization. However, existing methods rely on layer-wise importance estimation and overlook router shifts induced by quantization, resulting in suboptimal allocation and routing. In this work, we propose Global Expert-level Mixed-precision Quantization (GEMQ) to overcome these limitations via (1) a global linear-programming formulation that captures model-wide expert importance based on quantization error analysis, and (2) efficient router fine-tuning to adapt routing to quantized experts. These components are integrated into a progressive quantization framework that iteratively refines importance estimation and allocation. Experiments demonstrate that GEMQ significantly reduces memory and accelerates inference with minimal accuracy degradation. Source code is available at https://github.com/jndeng/GEMQ . --- ### PathCal: State-Aware Reflection-Marker Calibration for Efficient Reasoning Authors: Lingyu Jiang, Zirui Li, Shuo Xing, Peiran Li, Tsubasa Takahashi, Dengzhe Hou, Zhengzhong Tu, Kazunori Yamada, Fangzhou Lin Published: 2026-05-21 Categories: cs.AI arXiv: https://arxiv.org/abs/2605.23074v1 The emergence of Large Reasoning Language Models (LRMs) has paved the way for tackling complex reasoning tasks through test-time scaling by generating long-form Chain-of-Thought (CoT) trajectories during inference. Meanwhile, these trajectories often contain explicit reflection markers such as ``wait'', ``but'', and ``alternatively'', signaling hesitation, revision, and the consideration of alternative explorations, respectively. Recent studies on test-time control leverage such markers as lightweight handles for steering reasoning, typically treating them as a single coarse-grained category rather than distinguishing their distinct functional roles. In this paper, we conduct type-wise suppression and fixed-prefix intervention, revealing that reflection markers differ not only in their functional roles but also in when they exert the greatest influence. Specifically, different marker classes affect accuracy and generation length in distinct ways, and marker choices are most consequential before the model settles into a stable reasoning trajectory. Motivated by these findings, we introduce PathCal, a novel training-free decoding controller that calibrates reasoning paths by distinguishing marker types and intervening only at locally uncertain states. At each decoding step, PathCal utilizes the distribution over reflection-markers to estimate local competition between maintaining the current reasoning trajectory and initiating a competing branch, and softly rebalances marker logits when competing-branch evidence becomes excessive. Experiments across six reasoning benchmarks demonstrate that PathCal achieves a better efficiency--performance trade-off, improving or preserving accuracy while reducing generation length, without relying on external verifiers or additional sampling. --- ### The Efficiency Frontier: A Unified Framework for Cost-Performance Optimization in LLM Context Management Authors: Binqi Shen, Lier Jin, Hanyu Cai, Lan Hu, Yuting Xin Published: 2026-05-21 Categories: cs.CL arXiv: https://arxiv.org/abs/2605.23071v2 Large language models (LLMs) increasingly rely on long-context processing, but expanding context windows introduces substantial computational and financial costs. Existing context reduction approaches, including retrieval and memory compression methods, are typically evaluated using performance and efficiency metrics independently, limiting systematic comparison and deployment-aware decision-making. This paper introduces The Efficiency Frontier, a unified framework for cost--performance optimization in LLM context management. The framework models context strategy selection as a deployment-aware optimization problem that jointly accounts for task performance, token cost, and preprocessing reuse through amortized cost modeling. Unlike existing evaluations that compare methods in isolation, the proposed framework enables decision-oriented analysis. It identifies when different context management strategies become preferable under varying operational conditions. Experiments on HotpotQA reveal distinct operational regimes and transition boundaries between retrieval-based and preprocessing-based strategies. Results show that deployment-aware optimization reduces effective token usage by approximately 25% at comparable performance, enabling more cost-efficient deployment of large language model systems, while amortized memory compression achieves over 50% lower token cost relative to full-context prompting in higher-performance settings. Overall, the proposed framework provides a principled and practical foundation for evaluating and deploying scalable, efficient, and sustainable LLM systems across enterprise, scientific, and public-sector applications. --- ### Flow Mismatching: Unsupervised Anomaly Detection via Velocity Discrepancies in Flow Matching Models Authors: Shengzhe Chen, Mehrdad Moradi, Kamran Paynabar, Hao Yan Published: 2026-05-21 Categories: cs.CV arXiv: https://arxiv.org/abs/2605.23070v1 We propose Flow Mismatching, an unsupervised anomaly detection method that deliberately avoids reconstruction-based paradigms. Instead, we treat flow matching as geometric dynamics and leverage a key insight: anomalies occur at places where the learned normal flow disagrees with the geometric path toward a test image. Given a flow matching model trained only on normal images, we probe its learned velocity field along affine paths from Gaussian noise to a target image. Along each path, we compare the model-predicted velocity, which follows normal generative dynamics, with the geometric velocity toward the target, which includes any anomalous content. Anomalies induce strong local disagreement between these velocities. Aggregating the mismatch over different time steps and multiple paths yields pixel-wise heatmaps and image-level scores without test-time optimization, feature memories, or additional calibration. Our analysis shows that the population mismatch decomposes into an irreducible denoising term and a Fisher-divergence term between the test-path and normal-path score functions, which identifies the score-gap component that drives anomaly separation and explains the effectiveness of robust path aggregation. Extensive experiments on MVTec-AD and VisA demonstrate superior performance compared with SOTA reconstruction-based and recent flow matching-based approaches. --- ### DFKI-MLT at SemEval-2026 TASK 7: Steering Multilingual Models Towards Cultural Knowledge Authors: Yusser Al Ghussin, Daniil Gurgurov, Yasser Hamidullah, Josef van Genabith, Cristina España-Bonet, Simon Ostermann Published: 2026-05-21 Categories: cs.CL arXiv: https://arxiv.org/abs/2605.23069v1 Large language models (LLMs) are increasingly used across diverse linguistic and cultural contexts, yet their cultural knowledge remains uneven across regions and languages. We present the DFKI-MLT system for SemEval-2026 Task 7 on cultural awareness, where we apply activation steering to multilingual LLMs using language vectors extracted from parallel FLORES data. Our method performs inference-time adaptation by adding language-specific steering vectors to the residual stream at a selected transformer layer, without any parameter updates. We participated in both the short-answer (SAQ) and multiple-choice (MCQ) tracks; however, only our MCQ submission received an official score. In the official MCQ track, we achieved 86.96% accuracy, ranking 7th out of 17 teams. To better understand system behavior, we conduct post-hoc analyses on the shared-task MCQ and SAQ settings. These analyses show that activation steering yields modest and heterogeneous improvements on cultural reasoning: gains are strongly layer-sensitive, vary substantially across language-region pairs, with some configurations even degrading performance, and interact with prompt formulation, comparing generic and culturally conditioned prompts. Our findings suggest that prompt design and activation steering should be jointly optimized for culturally aware multilingual inference. --- ### RoboSurg-VQA: A Multimodal Benchmark for Surgical Segmentation-Aware Visual Question Answering Authors: Chengyi Zhang, Zi Ye, Ziyang Wang Published: 2026-05-21 Categories: cs.CV arXiv: https://arxiv.org/abs/2605.23068v1 Reliable visual understanding in robot-assisted and minimally invasive surgery (RMIS/MIS) demands more than accurate masks: in clinical practice, clinicians pose language-like questions about procedural context, visibility, artefacts, and the presence of anatomical structures and surgical instruments, often under degraded views caused by occlusion, smoke, bleeding, and specular highlights. We present \textbf{RoboSurg-VQA}, a segmentation-aware visual question answering (VQA) benchmark built by repurposing public surgical segmentation datasets under a shared schema. Each frame is paired with a fixed set of clinically motivated questions spanning procedure context, anatomy (including region), imaging modality/view, surgical artefacts, image quality, and basic visibility and spatial attributes, with closed answer sets to enable consistent evaluation. To scale annotation, we generate candidate answers via constrained prompting with automatic validity and consistency checks, followed by human auditing to improve plausibility and label consistency. We report benchmark statistics, sanity baselines, and common evaluation challenges under challenging surgical conditions. The code will be available on https://github.com/ziyangwang007/Robosurg-VQA. --- ### What Training Data Teaches RL Memory Agents: An Empirical Study of Curriculum Effects in Memory-Augmented QA Authors: Xinjie He, Zhiyuan Lin, Su Liu, Jialun Wu, Qiyang Xie, Weikai Zhou, Shuai Xiao Published: 2026-05-21 Categories: cs.CL arXiv: https://arxiv.org/abs/2605.23067v1 Reinforcement learning (RL) has emerged as a viable recipe for training LLM agents to reason over external memory banks in multi-session dialogue. Existing work trains exclusively on a single benchmark, leaving open how the composition of training data shapes the skills a memory agent acquires. We present a controlled empirical study that holds architecture, RL algorithm, and all hyperparameters fixed and varies only the training curriculum across three conditions: in-domain (LoCoMo), mixed-benchmark (LoCoMo + LongMemEval), and out-of-domain (LongMemEval only). Across two benchmarks and ten question types, curriculum composition acts as a fine-grained lever on specialization rather than a uniform scaling factor on performance. The mixed curriculum yields the strongest overall F1 on both evaluation sets. Training on a narrow out-of-domain set transfers a targeted skill - temporal reasoning - despite weak aggregate performance. Per-type differences substantially exceed aggregate differences, indicating that single-number benchmark comparisons systematically underreport curriculum effects. We further report two practical lessons from adapting GRPO to a single-GPU regime: cross-benchmark mixing requires filtering format-specific noise from memory banks to preserve training signal, and binary exact-match reward produces no learning signal at the small group sizes (G = 4) required on one GPU, motivating continuous reward functions in this regime. --- ### Orbax: Distributed Checkpointing with JAX Authors: Colin Gaffney, Shutong Li, Daniel Ng, Anastasia Petrushkina, Niket Kumar, Adam Cogdell, Mridul Sahu, Yaning Liang, Nikhil Bansal, Justin Pan, Angel Mau, Abhishek Agrawal et al. Published: 2026-05-21 Categories: cs.DC, cs.LG arXiv: https://arxiv.org/abs/2605.23066v2 In a landscape of high-performance distributed ML systems, JAX has emerged as a framework of choice. However, JAX's modular design philosophy leaves it without a standardized checkpointing solution. In this paper, we introduce Orbax, a modular, JAX-native checkpointing library that abstracts the complexities of distributed accelerator systems while also providing flexibility for user-friendly checkpoint manipulations throughout the ML model lifecycle. We demonstrate performance exceeding comparable PyTorch competitors by up to 3.5$\times$ for saving and 2$\times$ for loading. The library is available at https://github.com/google/orbax. --- ### Dithering Defense: Adversarial Robustness of Vision Foundation Models via Multi-Level Floyd-Steinberg Dithering Authors: Yury Belousov, Brian Pulfer, Vitaliy Kinakh, Slava Voloshynovskiy Published: 2026-05-21 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2605.23065v1 Vision foundation models are widely used as frozen backbones across many downstream tasks, making them a single point of failure under adversarial attack. We study multi-level Floyd-Steinberg error-diffusion dithering as a lightweight, model-agnostic input transformation that disrupts adversarial perturbations while preserving semantic content. Unlike prior work, which was limited to binary dithering, grayscale CIFAR-10, and a single small model trained from scratch, we evaluate across six tasks (classification, segmentation, depth estimation, retrieval, captioning, visual question answering), two model families (DINOv2, PaliGemma), and three attacks of increasing strength (PGD, MI-FGSM, SIA), as well as an adaptive attacker using a straight-through estimator. Our results show that Floyd-Steinberg dithering at intermediate quantization levels, especially when combined with post-processing blur, exceeds or matches all tested baselines, including diffusion-based denoising, with substantially less degradation on clean inputs. --- ### Millimeter-wave Imaging for Anthropometric Body Measurement Authors: Miriam Senne, Benjamin D. Killeen, Christoph Baur, Nassir Navab, Azade Farshad Published: 2026-05-21 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2605.23064v1 Body shape and circumferences are clinically informative biomarkers for risk stratification, including measures such as waist to hip ratio, limb and trunk girths, yet conventional tools such as manual tape measures and optical scanners often require undressing and sustained poses. These demands slow workflows, compromise dignity, and exclude many older adults and people with limited mobility. To make measurement fast and contactless, we leverage millimeter-wave (mmWave) radar, which preserves privacy and operates through typical clothing, enabling quick full-body acquisition. In this work, we present a new optimization-based framework to recover 3D human shape and extract a comprehensive set of anthropometric measurements from volumetric mmWave data. Our method introduces a weighted registration pipeline that fits a parametric body model (SMPL) directly to the noisy mmWave point cloud. The core of our contribution is a vertex-weighting strategy that modulates a Chamfer energy function for reliable surface alignment and noise elimination. We further stabilize the fit by incorporating a foot-ground plane constraint and pose priors, optimizing directly for the SMPL parameters. Together, these components enable a fast, privacy preserving workflow that delivers high fidelity body shape and measurements through clothing without cameras or disrobing and with minimal cooperation, supporting frequent risk oriented assessments in clinics and care facilities for patients of all ages and mobility levels. --- ### Anytime Training with Schedule-Free Spectral Optimization Authors: Anuj Apte, Pranav Deshpande, Niraj Kumar, Shouvanik Chakrabarti, Junhyung Lyle Kim Published: 2026-05-21 Categories: cs.LG, cs.AI, math.OC, stat.ML arXiv: https://arxiv.org/abs/2605.23061v2 Standard neural network training relies on learning-rate schedules tied to a fixed horizon, leading to strong path dependence and costly re-tuning as data availability changes. Schedule-Free (SF) methods address this by removing explicit schedules, yet SF-AdamW, the current state-of-the-art anytime optimizer, consistently underperforms well-tuned AdamW baselines. We propose SF-NorMuon, a schedule-free spectral optimizer that closes this gap: with a single hyperparameter configuration, SF-NorMuon matches or exceeds tuned AdamW on 125M and 772M parameter language models across $1$--$8\times$ Chinchilla horizons, and trails horizon-aware, cosine-scheduled NorMuon by only $\sim 0.03$ nats, substantially narrowing the gap between anytime and scheduled spectral optimizers. On the theoretical side, we prove a stationarity guarantee for schedule-free spectral dynamics and identify weight decay at the fast iterate as essential for long-horizon stability. SF-NorMuon enables practitioners to obtain high-quality checkpoints at any point during training without committing to a horizon in advance. Fully matching horizon-aware spectral optimizers without a schedule remains an open problem, which we highlight as a direction for future work. By closing the performance gap with tuned AdamW baselines, SF-NorMuon makes horizon-free optimization more practical, taking a step towards truly open-ended, continual learning. --- ### Anytime Training with Schedule-Free Spectral Optimization Authors: Anuj Apte, Pranav Deshpande, Niraj Kumar, Shouvanik Chakrabarti, Junhyung Lyle Kim Published: 2026-05-21 Categories: cs.LG, cs.AI, math.OC, stat.ML arXiv: https://arxiv.org/abs/2605.23061v1 Standard neural network training relies on learning-rate schedules tied to a fixed horizon, leading to strong path dependence and costly re-tuning as data availability changes. Schedule-Free (SF) methods address this by removing explicit schedules, yet SF-AdamW, the current state-of-the-art anytime optimizer, consistently underperforms well-tuned AdamW baselines. We propose SF-NorMuon, a schedule-free spectral optimizer that closes this gap: with a single hyperparameter configuration, SF-NorMuon matches or exceeds tuned AdamW on 125M and 772M parameter language models across $1$--$8\times$ Chinchilla horizons. On the theoretical side, we prove a stationarity guarantee for schedule-free spectral dynamics and identify weight decay at the fast iterate as essential for long-horizon stability. SF-NorMuon enables practitioners to obtain high-quality checkpoints at any point during training without committing to a horizon in advance. By closing the performance gap with tuned baselines, SF-NorMuon makes horizon-free optimization more practical, taking a step towards truly open-ended, continual learning. --- ### A measurement substrate for agentic Kubernetes operations: Methodology and a case study in retrieval-compounding falsification Authors: Joshua Odmark, Gideon Rubin, Deon van der Vyver Published: 2026-05-21 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2605.23058v1 Empirical claims about autonomous Kubernetes operations agents are largely unfalsifiable. Published work reports observational results without controlled comparisons against an agent-disabled baseline, selection bias is endemic, pre-registered decision matrices are absent, and samples are typically too small for the noise level of the underlying scoring system. The cause is the same gap that limits the agents themselves: code agents have a verification substrate that turns "did it work" into a fast, falsifiable, ground-truth signal, and operations has nothing equivalent. We present agent-breakage, a closed-loop measurement framework that injects faults into a target Kubernetes cluster, observes how an autonomous agent responds, scores the response on four axes against ground truth, and accumulates outcome-labeled (state, action, outcome) tuples. The framework distinguishes framework error from reasoning error, supports a true off-condition control via a deterministic-embedder mechanism, and enforces pre-registered decision matrices. We use it as a case study to test whether retrieval over past postmortems compounds an agent's capability. The methodological payload is three confounds the substrate caught during that case study, each of which would have produced a wrong published claim on a less instrumented version of the same work: a pgvector index bug, a +19% selection-bias artifact, and small-sample estimates that overstated effects by roughly 3x. The retrieval result itself is a partial falsification: 1 of 3 dense-corpus scenarios significant at p<0.05, pooled effect +3.9 percentage points, not significant at n=60. A within-scenario corpus-density sweep at 360 runs shows that mechanistic alignment of near-neighbors dominates raw count. The framework is released open source. --- ### RequestRouter: Request-Boundary Routing for Efficient Single-GPU LLM Inference Authors: Aman Sunesh, Ali Alshehhi, Hivansh Dhakne Published: 2026-05-21 Categories: cs.LG, cs.CL, cs.PF arXiv: https://arxiv.org/abs/2605.23057v2 RequestRouter is a lightweight request-boundary controller for reducing the latency and energy cost of single-GPU large language model inference. Rather than serving all requests with one static configuration, the system uses cheap request-level features to select one fixed inference mode per request, including FP16, quantized inference, speculative decoding, prefix caching, continuous batching, and hybrid modes such as GPTQ plus prefix caching and INT8 plus continuous batching. We evaluate RequestRouter using an 8B instruction-tuned language model served through vLLM on NVIDIA A100 GPUs. Across the full-scale A100 evaluation--26,500 fixed-mode evaluations followed by 3,500 online-controller evaluations, for 30,000 measured inference executions in total--the controller achieves a 2.10x mean latency speedup over FP16 and a 0.48x energy ratio on deployment-style workloads. A smaller matched evaluation with repeated measurements provides a controlled statistical check of this result: RequestRouter retains a 1.93x latency speedup (95% CI: 1.88--1.98x) and a 0.523 energy ratio (95% CI: 0.506--0.540), showing that the gains persist under a more tightly controlled protocol. On a separate expanded automatic benchmark evaluation, the routed policy retains 99.6% of FP16 macro accuracy. A 100,000-call CPU microbenchmark measures only 0.00475 ms mean routing overhead (0.00532 ms p99). Thus, simple request-aware routing can recover substantial serving efficiency without retraining or modifying the underlying LLM. --- ### ModeSwitch-LLM: A Lightweight Phase-Aware Controller for Cross-Mode LLM Inference on a Single GPU Authors: Aman Sunesh, Ali Alshehhi, Hivansh Dhakne Published: 2026-05-21 Categories: cs.LG, cs.CL, cs.PF arXiv: https://arxiv.org/abs/2605.23057v1 ModeSwitch-LLM is a lightweight request-boundary controller for improving single-GPU large language model inference efficiency by routing each request to an appropriate fixed inference mode. Instead of relying on one static serving configuration, the system selects among FP16, quantized modes, speculative decoding, and hybrid modes such as GPTQ plus prefix caching and INT8 plus continuous batching using cheap workload-level features. We evaluate ModeSwitch-LLM on Meta-Llama-3.1-8B-Instruct served on a single NVIDIA A100 GPU. On deployment-style synthetic workloads, the online controller achieves a 2.10x mean latency speedup over FP16 and a 0.48x mean energy ratio, corresponding to 51.7% lower energy per token. On automatic benchmarks used as a quality gate, accuracy remains close to FP16 with a mean delta of +0.17 percentage points. We also evaluate lightweight learned routers, but find that they do not clearly outperform the rule-based controller because they add routing overhead and more often select modes that violate quality, energy, or memory constraints. These results show that simple request-aware routing can recover substantial efficiency from existing inference modes without retraining the model or changing its architecture. --- ### DRL-Driven Edge-Aware Utility Optimization for Multi-Slice 6G Networks Authors: Khaled M. Naguib, Soumaya Cherkaoui, Mahmoud M. Elmessalawy, Ahmed M. Abd El-Haleem, Ibrahim I. Ibrahim Published: 2026-05-21 Categories: cs.NI, cs.AI arXiv: https://arxiv.org/abs/2605.23056v1 Virtual Reality (VR) services delivered over 6G networks demand ultra-low latency and high bandwidth to ensure seamless user experiences. This paper presents an intelligent resource allocation and edge caching framework for 6G O-RAN networks, leveraging Deep Q-Network (DQN) learning for optimizing edge caching and dynamic resource provisioning across multiple network slices within an O-RAN-compliant architecture. By incorporating DRL agents into the network control plane, the proposed system enables proactive and adaptive content distribution as well as real-time computational resource allocation that meets the quality-of-service demands of eMBB, URLLC, and especially the emerging MBRLLC slices essential for VR. Simulation results demonstrate that the DQN-based framework consistently outperforms traditional methods in reducing latency and improving throughput, leading to more reliable and responsive support for immersive VR applications in 6G environments. --- ### Decomposing and Measuring Evaluation Awareness Authors: Changling Li, Terry Jingchen Zhang, Jie Zhang, Zhijing Jin, Sahar Abdelnabi, Maksym Andriushchenko Published: 2026-05-21 Categories: cs.LG, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2605.23055v2 Frontier language models sometimes recognize that they are being evaluated and adjust their behavior, undermining validity of benchmark results. Yet the field studies it without a shared foundation, conflating properties of the evaluation with properties of the model, and detection with behavioral response. We ground evaluation awareness in social psychology, decomposing it into an environment component (how recognizable the task is) and a model component that separates recognition from propensity to act on it. We operationalize the environment component through eight categorized trigger factors, such as placeholder entities and grading-style output formats, and study recognition and behavior through chain-of-thought monitoring. Across nine frontier models and four benchmarks, recognition rates depend on the specific pairing of model and benchmark rather than on either in isolation. Recognition rarely leads to behavioral change, and when it does, the direction depends on the type of evaluation perceived. Models are also more sensitive to safety than capability evaluations, placing safety benchmark validity at greater risk. To study which factors each model is sensitive to and how they interact, we propose \textbf{EvalAwareBench}, a factor-controlled benchmark of 100 paired safety-capability tasks where each of the eight factors can be independently toggled, varying evaluative signals while holding the underlying request fixed. Through EvalAwareBench, we find that no single factor uniformly affects all models, but stacking factors progressively raises evaluation awareness across all of them. Our framework and EvalAwareBench provide the tools to measure, attribute, and mitigate evaluation awareness, pointing to behavioral consistency under recognition as a promising path forward. --- ### Model Collapse as Cultural Evolution Authors: Dongxin Guo, Jikun Wu, Siu Ming Yiu Published: 2026-05-21 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2605.23054v1 Model collapse, the progressive degradation of LLMs trained on their own outputs, has been characterized statistically but lacks a linguistic explanation for which structures degrade, in what order, and why. We show that iterated learning theory from cultural evolution fills this gap. We derive five falsifiable predictions, distinguish those uniquely discriminative for the theory from confirmatory ones, and test them by self-training LLaMA-2-7B and Mistral-7B over 10 generations in English, German, and Turkish. The critical discriminative finding: compositionality follows a non-monotonic trajectory (initially rising, then falling) under unfiltered self-training. This signature persists with maximally regular seed data (ruling out noise removal) and is sustained only by task-grounded filtering, not random filtering, providing the first LLM-scale evidence for the compression-communication tradeoff. All predictions are confirmed with large effect sizes (Hedges' $g > 1.6$; $\mathrm{BF}_{10} > 100$), and LLM regularization gradients closely match human behavioral data ($R^2 = 0.94$). These results reframe model collapse as a cultural transmission phenomenon and yield concrete principles for self-training pipeline design. --- ### DreamerNLplus: Interpretable Modeling of Mental Health Dynamics from Social Media Timelines using Hybrid Rule-Based and RAG Methods Authors: Maryia Zhyrko, Daisy Monika Lal, Erik van Mulligen, Lifeng Han Published: 2026-05-21 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2605.23052v1 We present DreamerNLplus, a hybrid framework for modeling mental health dynamics from social media timelines in the CLPsych 2026 shared task. Our system addresses three tasks: psychological state modeling, temporal change detection, and sequence-level summarization. For Task 1, we combine LLM-based data augmentation, DeBERTa classification, and Random Forest regression for structured state prediction. For Task 2, we use few-shot prompting with a locally deployed Llama 3.1 model to detect Switch and Escalation events using short-term temporal context. For Task 3.1, we explore both a deterministic rule-based summarization pipeline and a few-shot LLM-based approach, ranking \textbf{2nd} officially. Our RAG-based method achieves strong performance in Task 3.2, ranking \textbf{1st} for Improvement and \textbf{3rd} for Deterioration, demonstrating its ability to capture recurrent psychological change patterns across timelines. Our analysis reveals key challenges, including the mismatch between classification and regression performance, the difficulty of modeling temporal transitions, and the disagreement between semantic and similarity-based evaluation metrics. These findings highlight the complexity of modeling mental health dynamics and motivate future work on unified evaluation frameworks. We share our code and prompts at https://github.com/4dpicture/CLPsych2026 --- ### The TIME Machine: On The Power of Motion for Efficient Perception Authors: Mantas Skackauskas, Xinyue Hao, Laura Sevilla-Lara Published: 2026-05-21 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2605.23045v3 Video representation learning has seen tremendous progress in recent years. This has been driven by many factors, including the scale of training and the success of visual models trained contrastively with language. While these factors have pushed the boundaries of what video models can do, they also introduce their own set of limitations: first, scaling video models can reach prohibitive costs and second, learning from language restricts the range of concepts that can be learned to those in captions. As a result, video models still struggle with temporal understanding. In this paper we propose a novel approach that uses motion as the central modality for video representation. In particular, given the motion in a video in the form of point-tracks, we use a masked-autoencoder to mask some of the tracks and train the autoencoder to reconstruct the missing tracks. This allows us to learn a representation in a self-supervised manner. We show that using motion to represent videos actually addresses both of the core limitations of video technology. First, it allows us to massively reduce the scale of training data, as motion is inherently appearance-independent and hence needs fewer examples to generalize well. Second, motion allows us to bypass the language-dependent training paradigm, learning better fine-grained concepts. The result is an embedding that we call TIME (Temporally Informed Motion Embedding), a representation trained exclusively on synthetic motion data. We test this embedding on a wide set of tasks in a zero-shot manner. We observe that without bells and whistles, performance is on par with state-of-the-art models using up to 4 orders of magnitude less training data. This is a stepping stone towards a new paradigm of video models that are both more temporally aware as well as more scalable. --- ### HawkesLLM: Semantic Uncertainty Propagation in Agentic Text Simulation Authors: Zewei Deng, Tinghan Ye, Liyan Xie Published: 2026-05-21 Categories: cs.CL, stat.ML arXiv: https://arxiv.org/abs/2605.23043v1 Agentic text-simulation systems write in sequence, with each item becoming possible context for later steps. That makes uncertainty path-dependent: an early ambiguity can affect later outputs. This paper studies this problem with HawkesLLM, a framework that separates temporal influence modeling from text generation. We represent the cascade as a network whose nodes are text-generating agents. A multivariate Hawkes process models how these nodes activate over time and which earlier node outputs should influence later prompts. A language model then writes each new event from the compact memory selected by this temporal model. We evaluate the framework on a held-out Global Database of Events, Language, and Tone (GDELT) news-cascade case study. The diagnostics track semantic alignment with local held-out references and separate local drift from global drift. In this setting, HawkesLLM improves late-stage semantic alignment under a compact prompt-memory budget. --- ### Steered Generation via Gradient-Based Optimization on Sparse Query Features Authors: Sumanta Bhattacharyya, Pedram Rooshenas Published: 2026-05-21 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.23040v1 Latent steering exploits internal representations of Large Language Models (LLMs) to guide generation, yet interventions on dense states can entangle distinct semantic features. In this paper, we investigate attention query activations as a high-fidelity site for precise control, hypothesizing that manipulating the attention mechanism itself offers sharper steerability than general state interventions. We introduce Prototype-Based Sparse Steering, a framework that applies Sparse Autoencoders (SAEs) specifically to query activations, to decompose them into interpretable features, then apply gradient-based optimization during inference to align the sparse representation with class prototypes of target behaviors. To validate this architectural insight, we first analyze the mechanism in Textualized Gridworld, a controlled environment for verifiable planning constraints. We demonstrate that optimizing sparse query features enables effective navigation of rigid planning requirements (i.e., safe vs. short paths), confirming the method's ability to satisfy objective rules. We then demonstrate the framework's versatility by training SAEs on a high-dimensional educational domain, where the framework steers the cognitive complexity of feedback (i.e., Bloom's Taxonomy). Our experiments establish that sparse query representations provide the necessary disentanglement for unified, interpretable control over both logical planning and stylistic nuance. --- ### Do Language Models Know What Not to Say? Causal Evidence for Statistical Preemption in LLMs Authors: Dongxin Guo, Jikun Wu, Siu Ming Yiu Published: 2026-05-21 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2605.23039v1 How do learners acquire knowledge of what is unacceptable without negative evidence? Construction Grammar proposes statistical preemption: exposure to a conventional form (e.g., "donated the books to the library") preempts structurally possible but unattested alternatives ("*donated the library the books"). We present a computational study that, for the first time, directly dissociates statistical preemption from the competing entrenchment hypothesis in large language models within a single converging design. Across four experiments spanning 120 English verb-construction pairings (dative, causative, locative), we show that (1) LLM surprisal patterns correlate strongly with human acceptability judgments ($r = 0.79$), validated against three independent behavioral datasets; (2) these patterns are driven by competing-form frequency rather than overall verb frequency, confirmed by non-circular partial correlations; (3) preemption sensitivity scales as a power law with model size; and (4) a controlled fine-tuning intervention causally demonstrates that manipulating competing-form frequencies shifts preemption behavior in the predicted direction, with reverse-direction controls ruling out frequency-sensitivity confounds. These results provide converging evidence that neural language models acquire negative linguistic knowledge through distributional competition, the core mechanism posited by Construction Grammar. --- ### Open datasets and machine learning for two-phase heat transfer: a review following a spatial-temporal taxonomy Authors: Christy Dunlap, Ridwan Olabiyi, Firas Al-Hindawi, Hari Pandey, Stephen Pierson, Daniel Curl, Braden Stevens, Mohammad Ishraq Hossain, Annapurna Parjuli, Chinmaya Joshi, Ashif Iquebal, Han Hu Published: 2026-05-21 Categories: cs.LG, physics.flu-dyn arXiv: https://arxiv.org/abs/2605.23037v2 Two-phase heat transfer underpins boiling, condensation, immersion cooling, flow boiling, energy conversion, and electronics thermal management, but its coupled interfacial physics make data reuse and model comparison difficult. This narrative review synthesizes open datasets, machine-learning methods, and reusable software for two-phase heat-transfer research, with emphasis on boiling, multimodal sensing, and thermal-management datasets. We organize the review around a spatial-plus-temporal dimensionality taxonomy, denoted S+TD, that classifies data objects by the dimensionality of the measured, simulated, or derived fields, including 0+0D point values, 0+1D time series, 1+1D profiles, 2+0D images, 2+1D videos, 3+0D/3+1D fields, and mixed multimodal records. The taxonomy is used to connect dataset types to AI tasks such as tabular regression, acoustic sequence learning, image segmentation, video analysis, inverse heat-flux reconstruction, surrogate modeling, and multimodal fusion. The review also develops a roadmap for physics-aware open data, including metadata definitions, evidence and reuse-maturity labels, benchmark splits, decoders, baseline models, and community databanks. NED3 resources are discussed as one implementation case within a broader open-data ecosystem rather than as a complete solution. The main conclusion is that progress in two-phase AI now depends as much on findable, decodable, benchmarkable, and physically interpretable data infrastructure as on model architecture. --- ### Open Multimodal Datasets and Open-Source Software for Data-Driven Modeling of Multiphase Transport and Thermal Systems Authors: Christy Dunlap, Hari Pandey, Stephen Pierson, Daniel Curl, Braden Stevens, Mohammad Ishraq Hossain, Annapurna Parjuli, Chinmaya Joshi, Han Hu Published: 2026-05-21 Categories: cs.LG, physics.flu-dyn arXiv: https://arxiv.org/abs/2605.23037v1 Data-driven modeling is becoming central to multiphase transport, electronics cooling, acoustic diagnostics, and thermal-fluid digital twins, but progress is limited by fragmented datasets and raw instrument files that are difficult to decode, reuse, or benchmark. This paper presents an open ecosystem of multimodal datasets and open-source software packages developed by the Nano Energy and Data-Driven Discovery (NED3) Laboratory for reproducible AI-enabled thermal-fluid research. We introduce a spatial-plus-temporal dimensionality framework, denoted S+TD, to classify datasets by the dimensionality of measured or simulated fields, including 0+0D point values, 0+1D time series, 1+0D profiles, 2+0D images, 2+1D videos, 3+0D volumetric fields, and multimodal combinations. We organize public NED3 datasets spanning boiling images, acoustic and thermal measurements, high-speed videos, infrared thermography, thermal-resistance measurements, CFD-generated fields, design files, and acoustic-emission data. We also describe complementary software packages, including BubbleID, SeqReg, CFDTwin, IRISApp, decode-wfs, AELab, and FlowLab, which support computer vision, sequence regression, surrogate modeling, infrared analysis, waveform decoding, acoustic-emission analysis, and multimodal diagnostics. Particular emphasis is placed on SeqReg, a general sequence-regression library for 0+1D, 1+1D, and 2+1D data, with applications such as nonintrusive heat-flux estimation. Finally, we discuss future community efforts to build interoperable thermal-fluid databanks and curated AI/ML tool libraries that connect datasets, metadata, decoders, baselines, benchmarks, and physically interpretable models. --- ### Multilingual Steering by Design: Multilingual Sparse Autoencoders and Principled Layer Selection Authors: Yusser Al Ghussin, Daniil Gurgurov, Tanja Baeumel, Josef van Genabith, Patrick Schramowski, Simon Ostermann Published: 2026-05-21 Categories: cs.CL arXiv: https://arxiv.org/abs/2605.23036v1 Sparse autoencoders (SAEs) enable feature-level mechanistic interpretability and activation steering in large language models (LLMs), but SAE-based language control remains unreliable in multilingual settings: most SAEs are trained on English-only data, and steering layers are chosen heuristically. We address these limitations by advancing a principled, mechanistic account of multilingual language steering with SAEs. First, we show that training SAEs on multilingual data consistently strengthens cross-lingual representations and yields more reliable, quality-preserving language control across layers and model families. Second, we introduce an \emph{a priori} steering layer-selection rule based on the intersection of multilingual alignment and language separability, which predicts effective intervention depths without exhaustive layerwise search. We evaluate our approach on LLaMA-3.1-8B and Gemma-2-9B across machine translation and cross-lingual summarization (CrossSumm), using SpBLEU, ROUGE-L, COMET, and LaSE. Our results show that multilingual SAEs combined with intersection-selected layers stabilize the trade-off between language identification accuracy and generation quality, providing a principled, predictive, representation-level account of multilingual SAE steering. --- ### Sparse Autoencoders Map Brain-LLM Alignment onto Cortical Semantic Topography Authors: Dongxin Guo, Jikun Wu, Siu Ming Yiu Published: 2026-05-21 Categories: cs.CL, cs.AI, q-bio.NC arXiv: https://arxiv.org/abs/2605.23035v1 Intermediate layers of large language models (LLMs) best predict human brain responses to language, one of the most robust findings in computational neurolinguistics, yet why remains mechanistically unexplained. We address this gap by bridging sparse autoencoders (SAEs) from mechanistic interpretability with neural encoding models, decomposing GPT-2 XL and Llama-3.1-8B into 16K-32K interpretable features per layer. A human-validated taxonomy ($κ\geq 0.74$) reveals that semantic features alone recover 94% of peak encoding performance ($r=0.285$), substantially exceeding variance-matched baselines ($p<0.001$, $d=1.31$). Beyond this aggregate dominance, we test a novel cortical topography prediction: five semantic subcategories derived a priori from three independent neuroscience programs should map onto distinct brain regions. A formal convergence test confirms this alignment (Spearman $ρ=0.72$, $p<0.001$; hypergeometric $p=0.007$), demonstrating that SAE-discovered features recapitulate known cortical semantic organization at a granularity inaccessible to prior methods. SAE features further predict human reading times beyond lexical controls ($Δ\mathrm{logLik}=38.4$, $p<0.001$), and an exploratory prediction-error analysis provides preliminary evidence that the brain additionally encodes unexpected semantic content. Results generalize across English, Chinese, and French. --- ### Uncovering the Latent Potential of Deep Intermediate Representations Authors: Arnesh Batra, Arush Gumber, Aniket Khandelwal, Jashn Khemani, Anubha Gupta Published: 2026-05-21 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2605.23033v1 Foundational Models pretrained on huge amount of data learn representations that evolve across depth, forming a hierarchy of embeddings with distinct semantic content and geometric structure. Contrary to the widespread practice of using only the final layer or shallow mixtures, we show that task-relevant information is distributed non-monotonically across layers and cannot be recovered by naïve aggregation. Through a geometric and empirical study across multiple modalities, we show that effective transfer depends on identifying which layers encode task-discriminative structure and how their embeddings are geometrically organized. We introduce Layer-wise Optimal Embedding Selection (LOES), a constructive spectral method that identifies task-discriminative subspaces by minimizing residual error under orthogonality and isotropy constraints. To align fine-tuning with this selection principle, we further propose Geometric Regularization Loss (GeoReg), which enforces a simplicial structure on class manifolds and stabilizes representation geometry during fine-tuning. Across a wide range of architectures, depths, modalities, and data regimes, LOES consistently outperforms standard baselines, with gains that grow as model depth increases. Beyond accuracy, our method reveals how semantic factors are distributed across layers, thereby enabling cross-lingual and cross-modal interpretability analyses. Together, our results provide strong evidence that layerwise embedding geometry is not incidental but central to how deep models represent and transfer knowledge. --- ### Brain-LLM Alignment Tracks Training Data, Not Typology Authors: Dongxin Guo, Jikun Wu, Siu Ming Yiu Published: 2026-05-21 Categories: cs.CL, cs.AI, q-bio.NC arXiv: https://arxiv.org/abs/2605.23032v1 Brain-LLM alignment is well established in English, yet the brain's language network is neuroanatomically universal across languages. Does alignment also generalize cross-linguistically, and what governs the variation? We test this using fMRI data from 112 participants across English, Chinese, and French (the Le Petit Prince corpus) and seven LLMs spanning English-dominant, Chinese-dominant, and multilingual architectures. Our central finding is that training-language dominance, not an inherent property of English, drives the alignment pattern: a Chinese-dominant model (Baichuan2-7B), architecture-matched to LLaMA-2-7B, reverses the gradient entirely, aligning best with Chinese brains and worst with English. Beyond training dominance, formal typological distance independently covaries with alignment degradation, syntax-associated brain regions (IFG) show $2.3\times$ steeper typological gradients than lexico-semantic regions (PTL), and tokenization fertility accounts for $\sim$60% of a cross-linguistic shift in optimal encoding layer. These results reveal that the apparent "English advantage" in brain-LLM alignment is an artifact of training data composition, while the remaining variation reflects genuine typological structure concentrated in syntactic processing. --- ### RADAR: Relative Angular Divergence Across Representations Authors: Xavier Cadet, Mateusz Nowak, Peter Chin Published: 2026-05-21 Categories: cs.LG, cs.CL, cs.CV arXiv: https://arxiv.org/abs/2605.23028v1 Machine learning methods rely on data. However, gathering suitable data can be challenging due to availability constraints, cost, or the need for domain expertise. Expanding datasets with additional sources is a common response to limited data, yet this practice does not always improve downstream performance and can sometimes lead to a loss of performance, known as negative transfer. We propose RADAR, a simple, geometrically grounded metric for estimating cross-domain transferability in foundation models. RADAR analyzes the layer-wise evolution of representations by measuring angular alignments and relative changes in distance along layer-to-layer displacement trajectories, and by comparing empirical distributions of within-domain and cross-domain dynamics. We hypothesize that domain transferability is related to the divergence between these trajectory distributions. We evaluate the metric across multiple modalities, including cross-lingual sentiment classification with text embedding models and cross-domain image classification with foundation vision models. Across several settings, RADAR provides competitive predictive performance relative to existing transferability metrics on several vision and text benchmarks, with particularly strong results when domain transitions are smooth or cleanly separated. Our ablations further suggest that the effectiveness of transferability estimation depends on the geometry of the model's internal representation space, with different modalities favoring different topological formulations. --- ### World Machine: Towards Generative World Modeling for Time-Series Authors: Elton Cardoso do Nascimento, Alexandre da Silva Simões, Esther Luna Colombini, Ricardo Ribeiro Gudwin, Paula Dornhofer Paro Costa Published: 2026-05-21 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.23025v1 World models represent a paradigm shift in generative AI, pursuing predictive understanding and controllable simulation of environments in a structured and generalizable way. We present World Machine, a generative world-modeling architecture for time series. It is a transformer-based architecture with latent states that enables adaptation to different amounts of observed data and contexts. This shows an improvement over traditional transformers, which have a computational and memory cost that scales quadratically with the context. Experiments on a proposed synthetic dataset, Toy1D, validate the approach's feasibility, demonstrate capabilities not found in conventional transformers, and highlight the contributions of each component of the training protocol. --- ### The Deterministic Horizon: Impossibility Results as Design Specifications for Trustworthy AI Systems Authors: Dongxin Guo Published: 2026-05-21 Categories: cs.AI, cs.CC, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2605.23024v1 Large language models now write software, draft legal documents, and produce clinical notes, yet fundamental limits, from Turing and Arrow to the No Free Lunch theorems, shape what computation can do. This thesis turns such impossibility results from curiosities into design rules. Its flagship result proves an accuracy ceiling set by architecture alone: past a critical reasoning depth, no amount of training moves it, at any adapter rank, sample size, or loss function. Computable before deployment from layer count and embedding width, this Deterministic Horizon is measured between nineteen and thirty-one across twelve transformer architectures, and fine-tuning on optimal-length traces recovers under four percentage points. The mechanism is a capacity invariant of the residual stream, and an information-theoretic conversion yields super-exponential accuracy decay past the horizon. An unconditional circuit-complexity lower bound for modular exponentiation against constant-depth prime-modulus circuits complements this result. The same argument recasts across subfields: preference learning under any misspecified model jumps discontinuously in sample complexity; multi-stage retrieval pipelines require at least as many independent metrics as stages; standard truthful auctions fail for agents with prompt-dependent valuations; and zero-knowledge verification of neural inference pays a measured overhead of one hundred ten to one hundred ninety times per non-linear activation. Together these form a catalogue of sixteen specifications, each pairing a computable boundary, a quantified violation cost, and a constructive design rule: two compositions are proved, one pairing is an honest obstruction, and four remain open. The impossibility-specification methodology is offered for the generative research programme that trustworthy AI may need. Every fundamental limit of AI is also a design rule. --- ### PACE: Two-Timescale Self-Evolution for Small Language Model Agents Authors: Chen Ling, Pei Chen, Albert Guan, Jiaming Qu, Shayan Ali Akbar, Madhu Gopinathan, Erwin Cornejo Published: 2026-05-21 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.23019v1 Deploying language-model agents in production often requires substantial compute and human effort to tune prompts, parsers, validators, and other components of the agent pipeline. Self-evolution offers a promising alternative, but most existing frameworks assume access to frontier models that can reliably diagnose failures, propose revisions, and judge their own updates. We study whether frozen small language models (SLMs) can serve as effective self-evolving agents under resource constraints. We propose PACE (Prompt And Control Logic Evolution), a two-timescale framework that coordinates low-risk prompt refinement with higher-risk control-logic updates. PACE evolves prompts under fixed control logic until prompt-level gains saturate, then considers constrained control-logic updates that are accepted through held-out validation. Across three frozen SLM backbones ranging from 4B to 14B parameters and four controlled benchmarks, PACE achieves the best performance on all 12 backbone--benchmark combinations, improving over vanilla SLM agents by up to +9.2% relative improvement and over the stronger single-mode evolution baseline by up to +5.4% relative improvement. A tau-bench case study further shows that PACE improves multi-turn tool-use success over vanilla and prompt-only evolution. These results suggest that reliable SLM agent self-evolution is possible without updating model weights or relying on frontier-model teachers, and that the key benefit is not any single final solver pattern but autonomous, validated discovery of task-appropriate inference strategies. --- ### Smoothed Elicitation Complexity for Approximate $Γ$-calibration of Discrete Classification Tasks Authors: Jessica Finocchiaro, Victor Ganson, Drona Khurana Published: 2026-05-21 Categories: cs.LG, cs.GT arXiv: https://arxiv.org/abs/2605.23017v1 One prominent method of evaluating machine learning model trustworthiness is the notion of calibration. In the binary outcome setting, a probabilistic predictor is calibrated if outcomes are realized according to a model's distributional prediction, conditioned on this prediction. Straightforward extensions of binary calibration definitions to probabilistic multiclass classifiers suffer from an exponential complexity blowup as the space of predictions grows exponentially in the number of classes $n$. As a remedy, Noarov and Roth (2023) propose multiclass calibration with predictions that are properties of the outcome distribution, reducing complexity from growing in the number of classes $n$ to the dimension $d$ of the property, called its elicitation complexity. Previous work on approximate property calibration is generally limited to continuous scalar properties, despite many relevant properties of interest being discrete, like the mode or rankings. We characterize the approximate property calibration of discrete properties which are strongly orderable by using Lipschitz continuous properties as an intermediary. This work is the first to our knowledge to provide approximate calibration results for discrete properties. Along the way, we characterize the Lipschitz elicitation complexity of strongly orderable discrete properties by constructing algorithms for designing these Lipschitz properties, which we prove can be post-processed to obtain the original discrete property. --- ### MadEvolve: Evolutionary Optimization of Trading Systems with Large Language Models Authors: Yurii Kvasiuk, Tianyi Li, Owen Colegrove, Moritz Münchmeyer Published: 2026-05-21 Categories: q-fin.TR, cs.AI, cs.LG, q-fin.PM arXiv: https://arxiv.org/abs/2605.23007v1 We explore the application of LLM-driven algorithm optimization to several common tasks in quantitative finance. MadEvolve, a general-purpose algorithm optimization framework inspired by DeepMind's Alpha-Evolve, was recently developed to optimize algorithms in computational cosmology. Here we demonstrate the utility of MadEvolve to optimize algorithmic trading strategies and alpha generation at the example of Bitcoin trading. On our simulation and backtesting setup, we achieve significant improvements on all tasks we considered, such as evolving feature sets for signal generation, optimizing separate components of the trading strategy, and jointly evolving the feature pipeline together with the execution strategy. Additionally, we compare our method to other agentic search approaches, specifically Claude Code, and carefully evaluate p-hacking probabilities on our simulation setup. Our findings strongly support the utility of AI-driven agentic and evolutionary algorithms for algorithmic trading and quantitative finance. --- ### Scene Reconstruction as Mapping Priors for 3D Detection Authors: Yang Fu, Yuliang Zou, Hao Xiang, Xin Huang, Yijing Bai, Chen Song, Weijing Shi, Govind Thattai, Dragomir Anguelov, Mingxing Tan, Yingwei Li Published: 2026-05-21 Categories: cs.CV arXiv: https://arxiv.org/abs/2605.22997v1 In autonomous driving, mapping is critical for motion planning but remains an under-utilized resource for perception tasks such as 3D object detection. Maps can provide robust structural priors of the static environment, helping resolve ambiguities and correct for sensor data sparsity or noise, especially for distant objects or under adverse weather conditions. However, conventional High-Definition (HD) maps are resource-intensive to obtain and maintain, which presents a challenge for efficient, large-scale deployment. In this paper, we propose a scalable solution to systematically leverage mapping to improve 3D detection by overcoming two primary challenges. First, we introduce a pipeline to automatically build dense mapping priors from aggregated sensor data, eliminating the need for human labeling. Second, we design a novel Mapping Priors Augmented 3D Detection (MPA3D) framework to effectively integrate mapping priors with different sensor modalities. Extensive experiments on the Waymo Open Dataset demonstrate that our approach achieves new state-of-the-art results, proving the effectiveness of scalable reconstructed scene priors for enhancing 3D detection. --- ### CoMoGen: COntrollable MOtion Dynamics and Interactions with Mask-Guided Video GENeration Authors: Adil Meric, Lin Geng Foo, Mert Kiray, Benjamin Busam, Rishabh Dabral, Christian Theobalt Published: 2026-05-21 Categories: cs.CV arXiv: https://arxiv.org/abs/2605.22996v1 We present CoMoGen, a controllable video generation framework that generates realistic interactive dynamics from a single binary mask sequence conditioned on an input image. CoMoGen introduces a lightweight MaskAdapter that encodes binary mask sequences into a latent residual signal, injected into the Multi Modal Diffusion Transformer (MMDiT) model through a cosine-weighted schedule. Unlike the hierarchical coarse-to-fine design of UNet architectures, MMDiT operates as a sequence of uniform transformer blocks, making it difficult to identify which layers are responsible for the motion generation. Therefore, we propose a novel way to determine "Motion Layers" operating in the attention space of MMDiT. We fine-tune the model by using Low-Rank Adaptation (LoRA) to the Motion Layers, without requiring any architecture change in the MMDiT. This selective adaptation enables our method to focus on motion-critical components, yielding reduced computational cost. Despite its simplicity, CoMoGen enables precise subject motion and plausible interactions with surrounding humans, objects, and scenes. Comprehensive experiments on different datasets show that CoMoGen consistently outperforms prior controllable video generation methods and achieves state-of-the-art performance in motion fidelity and perceptual realism. Project page: mericadil.github.io/CoMoGen. --- ### Whose Good, Whose Place? The Moral Geography of Agentic AI for Social Good Authors: Poli Nemkova, Haeshitha Indukuri, Jaedon Charles Published: 2026-05-21 Categories: cs.CY, cs.AI arXiv: https://arxiv.org/abs/2605.22995v1 Agentic AI systems are increasingly proposed for social-good domains, often invoking the United Nations Sustainable Development Goals (SDGs) as a vocabulary of global benefit. Yet claims of social good do not establish accountability to the communities a system claims to serve. We present a structured survey of 112 papers on agentic AI for social good published between 2015 and 2026. We find a moral-geographic asymmetry: papers are least likely to specify geographic context in precisely the domains where local political, legal, and cultural context matters most. Across the corpus, 82 of 112 papers (73%) specify no geographic context. Papers aligned with health or physical/ecological SDGs specify geography 37-40% of the time, while papers aligned with institutional and social-policy SDGs do so only 13%. SDG 16, peace, justice, and strong institutions, is both the most-covered goal in the corpus and the one with the lowest geographic-specification rate. We interpret this as moral abstraction: agentic AI for social good often treats institutional good as universal in ways it does not treat health or ecological good. A second finding compounds this: only 28 of 112 papers (25%) report any real-world deployment or small-scale test. We identify five accountability gaps and propose a minimal reporting standard for more context-specific, participatory, and accountable agentic AI for social good. ---