# Research Papers — 2026-05 · bundle page 217 of 326 > Full-text markdown of papers #10801–10850 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/217 [← Previous bundle](https://aipod.dev/papers/archive/2026-05/page/216.md) [Next bundle →](https://aipod.dev/papers/archive/2026-05/page/218.md) ### The Cognitive Kardashev Scale: Quantifying the Material Envelope of Civilisational Computation Authors: Sachin Sharma Published: 2026-05-11 Categories: physics.soc-ph, cs.AI, cs.CY arXiv: https://arxiv.org/abs/2605.22840v2 How much thinking can a civilisation do? Kardashev ranked civilisations by the energy they command. This paper borrows his ladder and asks how much machine cognition each rung could support. The arithmetic is deliberately simple. A civilisation has some total power. Only a fraction of that can be spared for computing, and each joule spent buys computation at whatever efficiency the hardware of the day has reached. The product of the three sets a ceiling on machine thought. To keep the resulting quantities intelligible, I express them in units of the human brain's own processing rate, as a rough yardstick rather than a claim about minds. Calibrating the ceiling against present-day supercomputers and AI accelerators led me to two conclusions I did not expect at the outset. Even today's energy supply could support far more machine cognition than humanity actually uses, so physical capacity is not what binds. And whether energy or hardware efficiency becomes the constraint over the coming decade turns on engineering choices that have not yet been made. On the question that may matter most, who gets access to the cognition it describes, the scale is silent. That is a matter of political economy, and the calibration is offered as an input to that debate. --- ### Network-Based Interventions for HIV Prevention via Cascade-Aware Suppression of Transmission Authors: Akseli Kangaslahti, Davin Choo, Milind Tambe, Alastair van Heerden, Cheryl Johnson Published: 2026-05-11 Categories: physics.soc-ph, cs.AI, cs.SI arXiv: https://arxiv.org/abs/2605.20218v1 Treating and preventing Human Immunodeficiency Virus (HIV) remains a critical global health challenge. While antiretroviral therapy provides a path toward viral suppression -- effectively eliminating an individual's transmission risk -- systemic resource constraints limit the reach of intervention efforts. This work addresses the strategic distribution of intensive resources among virally unsuppressed individuals to minimize the expected cascade of new infections within a transmission network. We formalize this challenge as a novel constrained optimization problem where we have resources to "treat" $k$ out of a set $\mathbf{P}$ of virally unsuppressed individuals, and establish its theoretical connections to existing computational literature. We then propose Cascade-Aware Suppression of Transmission (CAST), a polynomial-time $(δ, ε)$-approximation algorithm that achieves a $2\sqrt{|\mathbf{P}|}$ approximation ratio by leveraging connections to the Minimum-$k$-Union (MkU) problem and Hoeffding-style concentration bounds. Extensive evaluations on real-world HIV networks demonstrate that CAST outperforms standard public health and computer science baselines. Furthermore, we show that CAST is empirically robust across diverse infectious disease networks, varied edge probability initializations, and settings involving imperfect network data. --- ### Compositional Literary Primitives in Instruction-Tuned LLMs: Cross-Architectural SAE Features for Self, Style, and Affect Authors: Joao Paulo Cavalcante Presa, Savio Salvarino Teles de Oliveira Published: 2026-05-11 Categories: cs.LG, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2605.18808v1 We characterize a compositional architecture of literary primitives in two instruction-tuned large language models (Llama 3.1 8B-Instruct and Gemma 2 9B-IT) via sparse autoencoders on mid-depth residual streams. Four feature classes emerge: naming-gates that promote lexical tokens of a target affect, an eleven-self cluster of first-person register features, stylistic register modulators (show-don't-tell and defamiliarization), and compositional emotions that arise only from multi-feature steering. Under a forced-choice 5-LLM judge panel applied to a 27-category emotion taxonomy (Cowen-Keltner), Llama reaches full 27/27 coverage by combining naming-gates, multi-feature recipes, and single self-feature steering; Gemma reaches 23/27 with adoration as the single residual strict-fail. Under random judging, the per-cell pass probability is on the order of $10^{-3}$ and the expected number of two-seed false-positive cells across the catalog is negligible, so the observed coverage is not consistent with chance. A cross-architectural asymmetry sits in the strict-versus-soft judge contrast: on the same generations, judges agree more often on Llama outputs than on Gemma outputs because Llama outputs name the target affect more directly while Gemma outputs evoke it through scene and imagery. Both architectures contain self-features that serve simultaneously as register markers and as emotion emitters, including a single most-RLHF-loaded self-feature per architecture that intensifies the institutional Helper-AI persona at one operating regime and produces affect-categorizable output at the same calibrated coefficient. Methodologically, the paper presents a three-stage validation pipeline (logit-lens, LLM-rate, 5-LLM judge) with documented anti-patterns; the total compute is single-GPU and about 15 minutes per emotion-feature discovery cycle. --- ### Block-Based Double Decoders Authors: Asher Labovich, Benjamin Bradley, Vanessa Alexander, Chaitanya Harsha Published: 2026-05-11 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2605.18807v2 Encoder-decoder models offer substantial inference-time savings over decoder-only models, but their pretraining objectives suffer from sparse supervision and dynamic sequence lengths, keeping them out of practice at scale. We propose block-based double decoders, a novel transformer architecture that utilizes doubly-causal block-based attention masks to train with full loss supervision and static sequence packing, combining decoder-only training efficiency with encoder-decoder inference efficiency. In scaling law experiments, block-based double decoders strongly outperform encoder-decoders and closely track decoder-only models across scales. At inference time, they cut KV-cache memory and per-token compute by at least 2/3 without sacrificing prefill caching or other existing inference optimizations available to decoder-only models. --- ### RecoAtlas: From Semantic Plausibility to Set-Level Utility in LLM Recommendation Agents Authors: Imad Aouali, Flavian Vasile, Otmane Sakhi, Alexandre Gilotte, Benjamin Heymann Published: 2026-05-11 Categories: cs.IR, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2605.18805v1 LLM recommendation agents increasingly produce structured recommendation reports: sets of items accompanied by natural-language justifications. Yet existing evaluations often reduce this setting to reranking small shortlisted candidate sets or judge reports mainly by semantic plausibility. We introduce Recommendation Atlas (Agentic Tool-Level Assessment for Shopping), or RecoAtlas, a benchmark and toolkit for evaluating shopping agents with behavior-grounded metrics. RecoAtlas complements held-out interaction metrics with learned utility proxies for relevance, complementarity, and diversity derived from interaction data, while separately measuring semantic coherence and explanation quality. Its controlled tool environment exposes agents to either semantic, behavior-aligned, or faulty tools, enabling diagnosis of whether performance gains arise from stronger reasoning, better signals, or more effective tool-use policies. Across controlled experiments, we show that RecoAtlas exhibits key properties of a meaningful benchmark for agentic systems: performance scales with model capacity and test-time compute, improves with stronger and better-aligned tools, degrades under noisy or misaligned signals, and reveals that semantic plausibility does not necessarily capture behavior-grounded utility. RecoAtlas provides a foundation for developing and evaluating shopping assistants that optimize not only for plausible recommendations, but also for coherent, behaviorally grounded recommendation sets. --- ### Adaptive Multi-Scale Goodness Aggregation for Forward-Forward Learning Authors: Salar Beigzad, Vansh Verma Published: 2026-05-11 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2605.18804v1 We propose Adaptive Multi-Scale Goodness Aggregation (AMSGA), a novel extension of the Forward-Forward (FF) algorithm designed to improve stability, robustness, and generalization in local-learning neural networks. AMSGA addresses several limitations of the original FF framework by introducing multi-scale goodness aggregation across local, intermediate, and global representations; adaptive curriculum-guided hard negative mining; layer-dependent adaptive thresholds; and a warm-up cosine annealing learning-rate schedule for improved optimization stability. Together, these modifications strengthen the FF paradigm while preserving its biologically plausible and memory-efficient properties. Experiments on MNIST and Fashion-MNIST demonstrate consistent performance improvements over the baseline FF algorithm, achieving up to +1.45% improvement on MNIST and +1.50% improvement on Fashion-MNIST without significant computational overhead. Our results suggest that local learning methods can become substantially more competitive when goodness estimation and training dynamics are carefully designed. --- ### PROWL: Prioritized Regret-Driven Optimization for World Model Learning Authors: Ahmet H. Güzel, Jenny Seidenschwarz, Benjamin Graham, Jonathan Sadeghi, Jeffrey Hawke, Ilija Bogunovic Published: 2026-05-11 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2605.18803v2 Modern action-conditioned video world models achieve strong short-horizon visual realism, yet remain unreliable on rare, interaction-critical transitions that dominate downstream planning and policy performance. Because passive demonstration data systematically under-samples these high-impact regimes, improving robustness requires actively eliciting model failures rather than relying on their natural occurrence. We introduce a KL-constrained adversarial curriculum in which a policy is trained to expose high-error trajectories of a diffusion-based world model while remaining close to the behavior distribution. The world model is continuously fine-tuned on these adversarially discovered trajectories, yielding an adversarial training loop that converts rare failures into a stable, near-distribution training signal without drifting into out-of-distribution exploitation. To maintain pressure on unresolved weaknesses as the model improves, we propose a Prioritized Adversarial Trajectory (PAT) buffer that re-ranks trajectories based on prediction error, action fidelity, and learning progress, focusing training on unresolved failure modes rather than repeatedly revisiting solved cases. We implement our approach in the MineRL framework and evaluate it on held-out out-of-distribution trajectories; PROWL improves robustness over models trained on passive data alone, reveals reward-hacking behaviors under weak behavioral constraints, and demonstrates that effective adversarial world-model training critically depends on balancing exploratory failure discovery with explicit behavioral regularization. Our results suggest that scalable world models benefit not only from larger datasets, but also from selectively generating informative training data. --- ### A Nonlinear Complexity Index for Wearable PPG Cardiovascular Stability: Multiscale Validation, Systematic Evaluation Correction, and Bayesian Parameter Optimization Authors: Timothy Oladunni, Farouk Ganiyu Adewumi Published: 2026-05-11 Categories: eess.SP, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2605.18802v1 Cardiovascular stability estimation from wearable photoplethysmography (PPG) requires a principled nonlinear framework, yet major gaps persist in heuristic parameter selection and evaluation protocols that inflate reported performance. We introduce a Stability-Constrained Cardiovascular Stability Index (SCSI) grounded in Cardiac Stability Theory and validate it across 176,742 segments from four heterogeneous PPG datasets at three temporal scales. Cross-dataset analysis demonstrates a large Kruskal-Wallis effect size (eta2 = 0.351, p < 0.001), strong cross-scale consistency (kappa > 0.97), and significant correlation with respiratory rate across 53 ICU records (Spearman r = 0.346, p = 0.011). We identify three evaluation artifacts that inflate heuristic AUC from a true baseline of 0.573 to 0.752: segment-level cross-validation leakage, test-set normalization leakage, and pooled-AUC overweighting that conceals per-patient failure. Correcting these artifacts and applying Bayesian optimization over 15 joint parameters yields SCSI with cross-validation AUC of 0.720. On 18 held-out records, SCSI achieves pooled AUC of 0.757 (95% CI: 0.686-0.828) and negative predictive value of 0.966 for tachypnea screening, while per-record AUC of 0.497 +/- 0.207 is disclosed for transparency. External validation on 42 elective-surgery records yields AUC of 0.621, confirming cross-population generalization. Ablation analysis identifies the nonlinear complexity module as the dominant component. A sparse three-component architecture is proposed as the minimal deployable configuration. The corrected protocol provides a reproducible benchmark for future wearable cardiovascular stability indices. --- ### Position: Let's Develop Data Probes to Fundamentally Understand How Data Affects LLM Performance Authors: Shiqiang Wang, Herbert Woisetschläger, Hans Arno Jacobsen, Mingyue Ji Published: 2026-05-11 Categories: cs.AI, cs.IR, cs.LG arXiv: https://arxiv.org/abs/2605.18801v1 Data is fundamental to large language models (LLMs). However, understanding of what makes certain data useful for different stages of an LLM workflow, including training, tuning, alignment, in-context learning, etc., and why, remains an open question. Current approaches rely heavily on extensive experimentation with large public datasets to obtain empirical heuristics for data filtering and dataset construction. These approaches are compute intensive and lack a principled way of understanding the essence of how specific data characteristics drive LLM behavior. In this position paper, we advocate for the need of developing systematic methodologies for generating synthetic sequences from appropriately defined random processes, with the goal that these sequences can reveal useful characteristics when they are used in one or multiple stages of the LLM workflow. We refer to such sequences as data probes. By observing LLM behavior on data probes, researchers can systematically conduct studies on how data characteristics influence model performance, generalization, and robustness. The probing sequences exhibit statistical properties that can be viewed using theoretical concepts, such as typical sets, which are generalized to describe the behaviors of LLMs. This data-probe approach provides a pathway for uncovering foundational insights into the role of data in LLM training and inference, beyond empirical heuristics. --- ### Theory-optimal Quantization Based on Flatness Authors: Xiusheng Huang, Zhe Li, Xuanwu Yin, Lu Wang, Yequan Wang, Dong Li, Emad Barsoum, Kang Liu Published: 2026-05-11 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2605.18800v1 Post-training quantization has emerged as a widely adopted technique for compressing and accelerating the inference of Large Language Models (LLMs). The primary challenges in LLMs quantization stem from activation outliers, which significantly degrade model performance especially at lower bit precision. While recent approaches attempt to mitigate outliers through linear transformations across feature dimensions, our analysis reveals that the transformed weights and activations still exhibit persistent outlier patterns with concentrated magnitude distributions. In this paper, we first model the mathematical relationship between quantization error and outliers, and then introduce a new metric Flatness to quantify the distribution of outliers. Based on this, we derive the theoretical optimal solution with respect to Flatness. Building on these insights, we propose Bidirectional Diagonal Quantization (BDQ), a novel post-training quantization framework that effectively disperses outlier patterns through optimized matrix transformations. BDQ strategically distributes outlier magnitudes across matrix dimensions via learned diagonal operations. Extensive experiments demonstrate that BDQ establishes a new quantization benchmark. It achieves less than 1\% accuracy drop in W4A4 quantization on the LLaMA-3-8B model. In the more challenging W2A4KV16 experiment, compared to state-of-the-art approaches, BDQ reduces the performance gap by 39.1\% on the DeepSeek-R1-Distill-LLaMA-70B model. --- ### ReCrit: Transition-Aware Reinforcement Learning for Scientific Critic Reasoning Authors: Wanghan Xu, Yuhao Zhou, Hengyuan Zhao, Shuo Li, Dianzhi Yu, Zhenfei Yin, Yaowen Hu, Fengli Xu, Wanli Ouyang, Wenlong Zhang, Lei Bai Published: 2026-05-11 Categories: cs.LG, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2605.18799v1 Large language models can fail in critic interaction not only by answering incorrectly, but also by abandoning an initially correct scientific solution after user criticism. This is especially risky in scientific reasoning, where user criticism can turn a valid answer into an incorrect one. We frame critic interaction as an inter-turn correctness-transition problem rather than a final-answer accuracy problem, and identify three challenges: transition awareness, decoupling useful correction from harmful sycophancy, and scalable rollout. We propose ReCrit, a transition-aware reinforcement learning framework that decomposes Initial-to-Critic behavior into four quadrants: Correction, Sycophancy, Robustness, and Boundary. ReCrit rewards correction and robustness, penalizes sycophancy, and treats persistent errors as weak boundary signals. To make interaction training practical, ReCrit further uses dynamic asynchronous rollout with tail-adaptive completion to reduce rollout waiting. On three scientific reasoning benchmarks, ChemBench, TRQA, and EarthSE, ReCrit improves average Critic accuracy from 38.15 to 51.49 on Qwen3.5-4B and from 45.40 to 55.59 on Qwen3.5-9B. Ablations show that final-answer rewards provide little interaction-level gain, while transition-aware rewards and quadrant weighting produce more distinguishable training signals and larger net Critic-stage improvement. The code is available at https://github.com/black-yt/ReCrit . --- ### Accurate Evaluation of Quickest Changepoint Detectors via Non-parametric Survival Analysis Authors: Taiki Miyagawa, Akinori F. Ebihara Published: 2026-05-11 Categories: cs.LG, cs.IT, math.ST, stat.ML arXiv: https://arxiv.org/abs/2605.18798v1 We propose non-parametric estimators for the average run length (ARL) and average detection delay (ADD) in quickest changepoint detection (QCD) under finite and irregular sequence lengths. Although ARL and ADD are widely used as optimality criteria in theoretical and simulation studies, their application to real-world datasets is hindered by limited and irregular sequence lengths. To address this issue, we propose non-parametric estimators for the ARL and ADD, termed KM-ARL and KM-ADD, by drawing an analogy between QCD and survival analysis to model detection probabilities under sequence truncation. We derive estimation bias bounds and prove that they are asymptotically unbiased unless extrapolation is required. Experiments on simulated and real-world datasets demonstrate their practical utility, enhancing robustness against limited and irregular sequence lengths, improving interpretability, and facilitating empirical, intuitive model selection. Our Python code is provided at https://github.com/TaikiMiyagawa/Kaplan-Meier-Average-Run-Length, offering ready-to-use implementations for practitioners. --- ### Simply Stabilizing the Loop via Fully Looped Transformer Authors: Rao Fu, Zixuan Yang, Jiankun Zhang, Jing Ma, Hechang Chen, Yu Li, Yi Chang Published: 2026-05-11 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2605.18797v2 Scaling model performance typically requires increasing model size. Looped Transformer offers a compelling alternative by iteratively reusing the same Transformer blocks, trading additional computation for improved performance without increasing parameter count or context length. Because the number of loop iterations can be adjusted at inference, it also provides a natural mechanism for balancing performance and test-time compute. However, Looped Transformer still suffers from training instability when the number of loop iterations increases. Our analysis reveals that this instability stems from two sources: gradient oscillation and residual explosion. To address these two problems, we propose the Fully Looped Transformer, which introduces two parameter-free modifications: (1) Fully Looped Architecture, which distributes inter-loop signals across all layers to mitigate residual explosion; (2) Attention Injection, which reuses the existing attention block to suppress gradient oscillation. These modifications stabilize training dynamics, enabling the Fully Looped Transformer to be trained stably up to 12 loop iterations, whereas other baseline looped models collapse in this regime. In milder settings where Looped Transformer does not collapse, Fully Looped Transformer still improves average downstream-task performance by up to 13.2\%. Overall, our experiments demonstrate that Fully Looped Transformer improves training stability, enhances downstream performance, and provides preliminary adaptability under different test-time compute budgets by varying loop iterations at inference. --- ### UCCI: Calibrated Uncertainty for Cost-Optimal LLM Cascade Routing Authors: Varun Kotte Published: 2026-05-11 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2605.18796v1 LLM cascades and model routing promise lower inference cost by sending easy queries to a small model and escalating hard ones to a large model, but most deployed routers use uncalibrated confidence scores and require per-workload threshold tuning. We present UCCI, a calibration-first router that maps token-level margin uncertainty to a per-query error probability via isotonic regression and selects the escalation threshold by constrained cost minimization. Under three explicit assumptions, threshold policies on the calibrated score are cost-optimal, and isotonic calibration achieves O(n^{-1/3}) sample complexity for expected calibration error (ECE). On a production named entity recognition workload of 75,000 queries served by 4B and 12B instruction-tuned LLMs on H100 GPUs, UCCI cuts inference cost by 31% (95% CI: (27%, 35%)) at micro-F1 = 0.91 while reducing ECE from 0.12 to 0.03. At the same operating point, UCCI beats entropy thresholding, split-conformal routing, and a FrugalGPT-style learned threshold. All cascade results use end-to-end routing on actual model outputs and measured H100 latency, not simulated routing from global accuracies or nominal API prices. --- ### HELLoRA: Hot Experts Layer-Level Low-Rank Adaptation for Mixture-of-Experts Models Authors: Jia Wei, Zhonghao Zhang, Ping Chen, Qianyang li, Yancheng Pan, Shaoxun Wang, Ziyi Qiu, Longxiang Wang Published: 2026-05-11 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2605.18795v1 Low-Rank Adaptation (LoRA) dominates parameter-efficient fine-tuning of large language models, yet most variants target dense architectures. Mixture-of-Experts (MoE) models scale parameters at near-constant per-token compute, and their sparse activation patterns create untapped opportunities for more efficient adaptation. We propose Hot-Experts Layer-level Low-Rank Adaptation (HELLoRA), which attaches LoRA modules only to the most frequently activated experts at each layer. This simple mechanism reduces trainable parameters and adapter-induced FLOPs while improving downstream performance, an effect we attribute to a form of structured regularization that preserves pretrained expert specialization. To stress-test HELLoRA under extreme parameter budgets, we further compose it with LoRI to form HELLoRI, which freezes the up-projection and sparsifies the down-projection. Across three MoE backbones, namely OlMoE-1B-7B, Mixtral-8x7B, and DeepSeekMoE, and three task families covering mathematical reasoning, code generation, and safety alignment, HELLoRA consistently outperforms strong PEFT baselines. Relative to vanilla LoRA on OlMoE, HELLoRA uses 15.7% of the trainable parameters, reduces adapter FLOPs by 38.7%, achieves 1.9x the training throughput, and improves accuracy by 9.2%. On DeepSeekMoE, HELLoRA outperforms LoRA while using only 23.2% of its trainable parameters. These results demonstrate that activation-aware adapter placement is an effective and practical route to scaling PEFT for MoE language models. --- ### Robust Basis Spline Decoupling for the Compression of Transformer Models Authors: Joppe De Jonghe, Van Tien Pham, Mariya Ishteva Published: 2026-05-11 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2605.18794v1 Decoupling is a powerful modeling paradigm for representing multivariate functions as compositions of linear transformations and univariate nonlinear functions. A single-layer decoupling can be viewed as a fully connected neural network with a single hidden layer and flexible activation functions, providing a direct link with neural networks. Because of this, the use of decoupling methods has gained increasing attention in neural network domains, particularly compression, since it enables structured approximations with reduced parameter complexity. Existing tensor-based decoupling methods typically rely on polynomial or piecewise-linear parameterizations of the internal nonlinear functions, which can suffer from numerical instability or limited expressiveness. In this work, we introduce a B-spline-based decoupling framework that generalizes these existing approaches. By exploiting the local support and flexible smoothness control of B-splines, the proposed formulation yields a more numerically stable and expressive representation. We derive a constrained coupled matrix-tensor factorization and propose a robust alternating least-squares algorithm, called R-CMTF-BSD, incorporating normalization and Tikhonov regularization. The proposed method is validated through experiments on synthetic data and transformer model compression. Results on the Vision and Swin Transformer architectures demonstrate that B-spline decoupling enables substantial parameter reduction while maintaining competitive accuracy, making the R-CMTF-BSD algorithm a promising tool for structured neural network compression. --- ### Dimensional Balance Improves Large Scale Spatiotemporal Prediction Performance Authors: Jing Chen, Shixiang Pan, Yujie Fan, Haocheng Ye, Haitao Xu, Wenqiang Xu Published: 2026-05-11 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2605.18793v3 Accurate spatiotemporal pattern analysis is critical in fields such as urban traffic, meteorology, and public health monitoring. However, existing methods face performance bottlenecks, typically yielding only incremental gains and often exhibiting limited cross-domain transferability. We analyze this bottleneck through spatial and temporal entropy measures, which are used as diagnostic indicators of spatiotemporal complexity mismatch rather than as guarantees that entropy alignment alone yields better forecasting. Empirically, larger mismatch is often accompanied by higher prediction uncertainty, especially under a fixed model-capacity budget. Guided by this diagnostic, we propose a scalable, adaptive framework that harmonizes spatial and temporal feature representations. Spatial dimensionality is compressed via low-rank matrix embedding to preserve essential structure, while an extended temporal horizon captures long-range dependencies and mitigates cumulative errors arising from temporal heterogeneity. Extensive experiments on urban traffic, meteorological, and epidemic datasets demonstrate substantial accuracy gains and broad applicability across the evaluated domains, suggesting that the framework is promising for a wide range of spatiotemporal tasks beyond the current study. The code is available on GitHub at https://github.com/ST-Balance/ST-Balance. --- ### Dimensional Balance Improves Large Scale Spatiotemporal Prediction Performance Authors: Jing Chen, Shixiang Pan, Yujie Fan, Haocheng Ye, Haitao Xu, Wenqiang Xu Published: 2026-05-11 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2605.18793v1 Accurate spatiotemporal pattern analysis is critical in fields such as urban traffic, meteorology, and public health monitoring. However, existing methods face performance bottlenecks, typically yielding only incremental gains and often exhibiting limited cross-domain transferability. We analyze this bottleneck through spatial and temporal entropy measures, which are used as diagnostic indicators of spatiotemporal complexity mismatch rather than as guarantees that entropy alignment alone yields better forecasting. Empirically, larger mismatch is often accompanied by higher prediction uncertainty, especially under a fixed model-capacity budget. Guided by this diagnostic, we propose a scalable, adaptive framework that harmonizes spatial and temporal feature representations. Spatial dimensionality is compressed via low-rank matrix embedding to preserve essential structure, while an extended temporal horizon captures long-range dependencies and mitigates cumulative errors arising from temporal heterogeneity. Extensive experiments on urban traffic, meteorological, and epidemic datasets demonstrate substantial accuracy gains and broad applicability across the evaluated domains, suggesting that the framework is promising for a wide range of spatiotemporal tasks beyond the current study. The code is available on GitHub at https://github.com/ST-Balance/ST-Balance. --- ### Trust or Abstain? A Self-Aware RAG Approach Authors: Xi Zhu, Ziqi Wang, Kai Mei, Wujiang Xu, Minghao Guo, Bangji Yang, Jiajun Fan, Dimitris N. Metaxas Published: 2026-05-11 Categories: cs.IR, cs.CL arXiv: https://arxiv.org/abs/2605.18792v1 Retrieval-augmented generation (RAG) improves large language models (LLMs) by incorporating external evidence, but it also introduces knowledge conflicts when retrieved contextual knowledge (CK) and parametric knowledge (PK) disagree or are both unreliable. Existing approaches mainly coordinate which source to use, without explicitly asking whether each answer path is correct. We argue that faithful RAG requires LLM self-awareness, namely the ability to recognize the limits of its own knowledge and reasoning. To ground this problem, we construct a model-specific, ground-truth-aligned knowledge-conflict benchmark by evaluating LLM backbones on PK-only and CK-conditioned answer paths over approximately 69K query-context instances per backbone, drawn from five conflict-QA datasets. We then introduce SABER, a Self-Aware Belief Estimator for RAG that requires no LLM fine-tuning. SABER combines a self-prior with PK-side and CK-side conditional reasoning representations from multi-trace inference, then estimates reliability beliefs with two lightweight predictors to drive a 4-cell decision over trust PK, trust CK, trust either, or abstain. Across four LLM backbones, SABER improves end-to-end accuracy and conflict-specific faithfulness over ten inference-time and fine-tuning baselines, with the largest gains on conflict-heavy datasets. Under abstention, SABER's risk-coverage curve Pareto-dominates every prompt-based abstainer, providing a tunable balance between coverage and answer risk. Our code is available at https://github.com/xizhu1022/SABER. --- ### SpecX: A Large-Scale Benchmark for Multi-Modal Spectroscopy and Cross-Paradigm Evaluation Authors: Chengrui Xiang, Tengfei Ma, Yujie Chen, Tong Wang, Haowen Chen, Xiangxiang Zeng Published: 2026-05-11 Categories: eess.IV, cs.CV, cs.LG, q-bio.OT arXiv: https://arxiv.org/abs/2605.18791v1 Existing spectral benchmarks are limited in scale, modality alignment, and evaluation scope, and typically focus on either specialized models or multimodal language models (MLLMs). We introduce SpecX, a large-scale benchmark for multi-modal spectroscopy with cross-paradigm evaluation. SpecX contains 1.7M molecules with diverse spectral modalities, including NMR (1H, 13C, HSQC), IR, MS,UV,Raman and FL, and is organized into three tiers: a large-scale dataset for pretraining, an aligned multi-spectral subset for benchmarking, and a high-quality experimental subset for evaluation. SpecX supports a range of tasks such as molecular elucidation, spectrum simulation, and spectral understanding, and enables unified evaluation across both specialized spectral models and MLLMs. Experiments show that specialized models excel at signal-level modeling, while MLLMs exhibit strengths in high-level reasoning but lack precise spectral grounding. SpecX establishes a unified benchmark for spectral intelligence and highlights the need for spectrum-native foundation models. --- ### VVitCutLER: Towards Unsupervised Object Detection and Segmentation in Videos Authors: Zhijing Lu, Khurram Azeem Hashmi, Didier Stricker, Muhammad Zeshan Afzal Published: 2026-05-11 Categories: cs.CV arXiv: https://arxiv.org/abs/2605.17584v1 Unsupervised pixel-level video understanding remains challenging in real-world scenarios, where motion blur, occlusion, and fast object dynamics often cause temporal drift and flickering pseudo-labels.We propose VVitCutLER, an unsupervised framework for video object detection and instance segmentation, which improves the quality of pseudo-labels through temporal consistency. Our core contribution is VitCut, a temporarily stable pseudo-label generator that reduces error accumulation during field degradation through cross-frame region consistency. Meanwhile, VitCut uses a distillation decoder to achieve effective instance mask prediction. Then, based on VitCut, VVitCutLER further integrates cross-frame feature aggregation to enhance video-level robustness. Extensive experiments on standard video benchmarks demonstrate that VVitCutLER significantly improves detection and segmentation performance while reducing temporal instability. These results highlight the importance of temporally consistent supervision for robust pixel-level video understanding. --- ### Inducing Spatial Locality in Vision Transformers through the Training Protocol Authors: Eduardo Santiago Toledo, Asael Fabian Martínez Published: 2026-05-11 Categories: cs.CV, cs.LG, stat.ML arXiv: https://arxiv.org/abs/2605.16390v1 We investigate whether the training protocol can induce spatial locality in the early layers of a Vision Transformer (ViT) trained from scratch, without large-scale pretraining. Keeping the architecture and optimization procedure fixed, we compare a Baseline protocol with a Modern protocol (AutoAugment/ColorJitter, CutMix, and Label Smoothing) on CIFAR-10, CIFAR-100, and Tiny-ImageNet, characterizing each attention head via Mean Attention Distance (MAD) and normalized entropy. Across all three datasets, the Modern protocol produces more local and more concentrated attention in early layers; on CIFAR-100, the minimum MAD drops from 0.316 (Baseline) to 0.008 (Modern). To identify the source of this effect, we conduct an ablation study on CIFAR-100 by adding or removing each component individually. The results identify CutMix as the determining component within our experiments: all conditions with CutMix exhibit MAD 0.024, while all conditions without CutMix remain at MAD 0.210. AutoAugment and Label Smoothing show no independent effect on locality. Taken together, these findings suggest that the pressure to classify from partial image regions, induced by CutMix, can promote the emergence of local attention in Vision Transformers. --- ### Haptic Rendering of Fractional-Order Viscoelasticity: Passivity and Rendering Fidelity Authors: Gorkem Gemalmaz, Harun Tolasa, Volkan Patoglu Published: 2026-05-11 Categories: cs.RO, cs.AI, eess.SY arXiv: https://arxiv.org/abs/2605.16389v1 Haptic rendering of viscoelastic materials that exhibit creep and stress relaxation is crucial for many applications, such as medical training with realistic biological tissue models. Fractional-order viscoelastic models provide an effective means of describing intrinsically time-dependent dynamics with few parameters, as these models can naturally capture memory effects. In this study, we present analyses of passivity and rendering performance for fractional-order viscoelastic models under finite-memory discretization. We derive closed-form expressions to ensure the passivity of haptic rendering with a fractional-order (FO) standard linear solid (SLS) model based on Grunwald-Letnikov derivative under short-memory discretization. We also provide symbolic expressions for the effective stiffness and damping of such FO-SLS models. The resulting passivity conditions constitute a unified framework that generalizes previously reported results for integer-order Kelvin-Voigt, Maxwell, and SLS models, since these results are special cases of the newly derived condition. Furthermore, we provide experimental validations of the theoretical passivity bounds and human-subject evaluations of perceived realism of FO-SLS models. Overall, this study establishes a unified theoretical framework and experimental evaluations for FO viscoelastic rendering under short-memory discretization. --- ### ChronoSC: Task-Oriented Semantic Communication via Temporal-to-Color Encoding Authors: Phuc H. Nguyen, Trung T. Nguyen, Quy N. Duong, Van-Dinh Nguyen Published: 2026-05-11 Categories: cs.CV arXiv: https://arxiv.org/abs/2605.16388v1 Semantic communication (SC) aims to reduce transmission overhead by conveying task-relevant information rather than raw data. However, existing SC approaches for video largely focus on pixel-level reconstruction or rely on complex spatiotemporal pipelines, leading to excessive bandwidth usage and latency that are unsuitable for low-resource deployments. In this paper, we propose ChronoSC, a task-oriented semantic communication framework for Video Question Answering (VideoQA). ChronoSC introduces Chrono-Color Stacking, a lightweight and lossless projection scheme that encodes temporal video dynamics into a single static image, enabling extreme temporal compression before transmission. This compact semantic representation is transmitted using a lightweight Deep Joint Source-Channel Coding (DeepJSCC) transceiver and explicitly reconstructed at the receiver. Unlike latent-space methods, explicit visual reconstruction enables the direct reuse of pre-trained vision-language models; specifically, a pre-trained BLIP model is employed to infer answers from noisy, reconstructed chrono-images. Experiments on the CLEVRER dataset show that ChronoSC achieves up to 192 times bandwidth reduction compared to raw video transmission while maintaining high VideoQA accuracy. --- ### Stabilizing Temporal Inference Dynamics for Online Surgical Phase Recognition Authors: Yang Liu, Ning Zhu, Jingjing Peng, Xiwu Chen, Alejandro Granados, Guotai Wang, Sebastien Ourselin Published: 2026-05-11 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2605.16387v1 Online Surgical Phase Recognition (SPR) models can reach high frame-wise accuracy, yet their predictions often lack temporal stability, fragmenting workflow understanding and reducing the reliability of downstream assistance. We show that this instability is not random noise but arises from two mechanisms: early misclassifications corrupt temporal feature states and propagate forward to form error cascades, and phase transitions follow evidence-accumulation dynamics whereas most online SPR systems rely on memoryless frame-wise decisions, making them sensitive to transient confidence fluctuations. We propose a unified Train-Inference-Evaluation framework that explicitly stabilizes temporal inference dynamics using model-agnostic, plug-and-play components. For training, the Temporal Error-Cascade (TEC) loss suppresses error onset and mitigates forward error propagation by stabilizing temporal feature evolution. For inference, the Evidence-Gated Transition Predictor (EGTP) enforces evidence-driven state transitions, allowing phase changes only when accumulated evidence exceeds a confidence boundary. For evaluation, we introduce the Temporal Fragmentation Index (TFI), a reliability-aware metric that quantifies instability-induced temporal disagreement beyond conventional frame-wise and token-based measures. Experiments on Cholec80 and AutoLaparo across three representative backbones show that the proposed framework substantially improves temporal stability and reduces prediction fragmentation, while maintaining or modestly improving frame-wise performance. --- ### Auditing Multimodal LLM Raters: Central Tendency Bias in Clinical Ordinal Scoring Authors: Jiaqing Zhang, Sandeep Elluri, Bhanu Cherukuvada, Yonah Joffe, Jessica Sena, Miguel Contreras, Scott Siegel, Subhash Nerella, Catherine Price, Parisa Rashidi Published: 2026-05-11 Categories: cs.CV arXiv: https://arxiv.org/abs/2605.16386v1 Multimodal large language models (LLMs) are increasingly explored as automated evaluators in clinical settings, yet their scoring behavior on ordinal clinical scales remains poorly understood. We benchmark three frontier LLM families against supervised deep learning models for scoring Clock Drawing Test (CDT) images on two public datasets using the Shulman rubric. While fully fine-tuned Vision Transformers achieve the best calibration (MAE 0.52, within-1 accuracy 91%), zero-shot LLMs remain competitive on tolerance-based agreement (GPT-5 MAE 0.67, within-1 accuracy 92%) despite higher absolute error. However, per-score analysis reveals that all three LLM families exhibit a pronounced central tendency effect (systematic endpoint compression): predictions are systematically compressed toward the middle of the scale, with over-prediction at the low end (score 0 to 1) and under-prediction at the high end (score 5 to 4). This effect disproportionately affects the clinically critical extremes where accurate scoring most impacts screening decisions for cognitive impairment. Targeted ablations show that neither few-shot exemplars spanning the full score range nor removing clinical terminology from the prompt eliminates the effect. Our findings extend the LLM-as-a-judge bias literature from NLP evaluation to clinical assessment, and highlight the need for calibration-aware evaluation and post-hoc calibration before deploying LLM-based raters in high-stakes screening workflows. --- ### Hilbert-Geo: Solving Solid Geometric Problems by Neural-Symbolic Reasoning Authors: Ruoran Xu, Haoyu Cheng, Bin Dong, Qiufeng Wang Published: 2026-05-11 Categories: cs.CV, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2605.16385v3 Geometric problem solving, as a typical multimodal reasoning problem, has attracted much attention and made great progress recently, however most of works focus on plane geometry while usually fail in solid geometry due to 3D spatial diagrams and complex reasoning. To bridge this gap, we introduce Hilbert-Geo, the first unified formal language framework for solid geometry, including an extensive predicate library and a dedicated theorem bank. Based on this framework, we propose a Parse2Reason method containing two steps of first parsing then reasoning. In the parsing step, we utilize conditional description language (CDL), a formalized language composed of predicates specifically designed to construct geometric conditions, to represent both problem description (natural text) and solid diagrams (visual image). In the reasoning step, we leverage those formal CDL and the theorem bank to perform relational inference and algebraic computation, generating strictly correct, verifiable, and human-readable reasoning processes. Notably, our proposed Hilbert-Geo is also applicable to plane geometry. To advance geometric reasoning, we curate two expert-annotated dataset SolidFGeo2k and PlaneFGeo3k, which are furnished with geometric formal language annotations, solutions and answers. Extensive experiments show that our proposed method achieves the state-of-the-art (SOTA) performance 77.3% in SolidFGeo2k and 84.1% in MathVerse-Solid (one small subset in MathVerse dedicated to solid geometry), substantially outperforming leading MLLMs, such as Gemini-2.5-pro (54.2% on SolidFGeo2k) and GPT-5 (62.9% on MathVerse-Solid). In addition, our method achieves the SOTA accuracy 80.2% in PlaneFGeo3k, demonstrating the generality of the Hilbert-Geo in geometric reasoning. Our code and datasets are released at https://github.com/PremiLab-Math/Hilbert-Geo. --- ### Mutual Enhancement Between Global Tokens and Patch Tokens: From Theory to Practice Authors: Xiusheng Huang, Xin Jiang, Jun Zhao, Kang Liu, Yequan Wang Published: 2026-05-11 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2605.16384v1 Accurate and effective discrete image tokenization is crucial for long image sequence processing. However, current methods rigidly compress all content at a fixed rate, ignoring the variable information density of images and leading to either redundancy or information loss. Inspired by information entropy, we propose TaTok, a Theoretically grounded adaptive image Tokenization framework. We rigorously identify two key drawbacks in existing methods: information insufficiency when reconstructing images with patch tokens alone, and information redundancy among patch tokens. To address these, we introduce global tokens that model mutual information across patch tokens, and a Dynamic Token Filtering (DTF) algorithm based on cumulative conditional entropy to eliminate redundancy. Experiments confirm TaTok's state-of-the-art performance, delivering a 1.3x gFID improvement and 8.7x inference speedup. By allocating tokens according to information richness, TaTok enables more compressed yet accurate image tokenization, offering valuable insights for future research. --- ### A neurosymbolic Approach with Epistemic Deep Learning for Hierarchical Image Classification Authors: Ezel Kilicdere, Shireen Kudukkil Manchingal, Fabio Cuzzolin Published: 2026-05-11 Categories: cs.CV, cs.AI, stat.ML arXiv: https://arxiv.org/abs/2605.16383v1 Deep neural networks achieve high accuracy on image classification tasks. Yet, they often produce overconfident predictions as which fail to express epistemic uncertainty, and frequently violate logical or structural constraints present in the data. These limitations are particularly pronounced in hierarchical classification, where predictions across fine and coarse levels must remain coherent. We propose, for the first time, a unified neurosymbolic and epistemic modelling framework that augments Swin Transformers with focal set reasoning and differentiable fuzzy logic. Rather than treating labels as isolated categories, our method induces data-driven focal sets within the learnt embedding space, which helps capture epistemic uncertainty over multiple plausible fine-grained classes. These focal sets form the basis of a belief-theoretic layer that uses fuzzy membership functions and t-norm conjunctions to encourage consistency between fine- and coarse-grained predictions. A learnable loss further balances calibration, mass regularisation, and logical consistency, allowing the model to adaptively trade off symbolic structure with data-driven evidence. In experiments on hierarchical image classification, our framework maintains accuracy on par with transformer baselines while providing more calibrated and interpretable predictions, reducing overconfidence and enforcing high logical consistency across hierarchical outputs. Our experimental results show that combining focal set reasoning with fuzzy logic provides a practical step toward deep learning models that are both accurate and epistemically aware. --- ### StreamPro: From Reactive Perception to Proactive Decision-Making in Streaming Video Authors: Ao Li, Zihan Xiao, Zihao Yue, Boshen Xu, Linli Yao, Jiaze Li, Pei Fu, Jianzhong Ju, Jian Luan, Qin Jin Published: 2026-05-11 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2605.16381v1 Proactive streaming video understanding requires models to continuously process video streams and decide when to respond, rather than merely what to respond. This naturally introduces a decision-making problem under partial observations, where models must balance early prediction against sufficient evidence. However, existing benchmarks largely follow a "see-then-answer" paradigm, where responses are triggered only after explicit evidence appears, effectively reducing proactive reasoning to delayed perception. As a result, they fail to evaluate a model's ability to make timely and reliable decisions under incomplete observations. Moreover, training proactive models is inherently challenging due to the extreme imbalance between silence and response signals in streaming trajectories, as well as the need to jointly optimize response correctness and timing. To address these challenges, we introduce StreamPro-Bench, a new benchmark that evaluates streaming models from three complementary perspectives: Perception Understanding, Temporal Reasoning, and Proactive Agency, where the last measures a model's ability to make early yet reliable decisions under partial observations. We further propose StreamPro, a two-stage training framework for proactive learning. First, we introduce CB-Stream Loss to mitigate the severe supervision imbalance during supervised fine-tuning (SFT). Then, we apply Group Relative Policy Optimization (GRPO) with a multi-grained reward design that involves both turn-level and trajectory-level rewards. Experiments show that StreamPro significantly improves proactive performance. On StreamPro-Bench, it achieves 41.5, substantially outperforming the previous best (10.4), while also maintaining strong performance on real-time streaming benchmarks, achieving 78.9 on StreamingBench-RTVU. --- ### ReTAMamba: Reliability-Aware Temporal Aggregation with Mamba for Irregular Clinical Time Series Prediction Authors: Jinwoong Kim, Sangjin Park Published: 2026-05-11 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2605.16380v1 Clinical time-series data are difficult to model with methods designed for regular sequences because they exhibit irregular sampling, frequent missing values, and heterogeneous observation patterns across variables. Existing approaches commonly use observation masks and time-gap information, but they do not continuously capture the decaying reliability of past observations or consistently organize multi-resolution information within a coherent temporal context during aggregation. To address these limitations, we propose Reliability-aware Temporal Aggregation with Mamba (ReTAMamba), which reconstructs clinical time series as time-variable token sequences, estimates observation reliability from missingness and elapsed time, and augments interval summaries with statistical descriptors. Chronological Weaving is used to integrate short- and long-term temporal information within a coherent temporal context, and a budgeted token router is applied to constrain sequence length while preserving informative summaries. Experiments on MIMIC-IV, eICU, and PhysioNet 2012 show that ReTAMamba consistently improves AUPRC over strong baselines, with average relative gains of 7.51%, 7.80%, and 10.15%, respectively. Cohort-level and patient-level analyses on eICU further showed that the learned mean decay for more dynamic signals, such as heart rate and blood pressure, was 24.3% larger than that for relatively static signals, such as laboratory test variables. These findings suggest that effective prediction in irregular clinical time series requires modeling not only what was measured, but also when and how it was observed, including information freshness and observation timeliness. --- ### An Information-Theoretic Criterion for Efficient Data Synthesis Authors: Hanyu Li, Zhengqi Sun, Xiaotie Deng Published: 2026-05-11 Categories: cs.LG, cs.AI, cs.IT arXiv: https://arxiv.org/abs/2605.16379v1 Synthetic data becomes crucial for large language model training, but its effectiveness is highly inconsistent. We provide an information-theoretic account of this inconsistency: synthetic data improves a model only when the generation-training loop is information-open, i.e., shaped by external signals (verifiers, environments, or rubrics) that inject task-relevant information beyond the model's current distribution. When the loop is information-closed (relying on the model's own outputs without such signals), the data processing inequality ensures that task-relevant information can only decrease, making collapse a predicted outcome. Among information-open pipelines, both efficiency and generalization hinge on the meta-level of supervision: a coarser signal such as binary correctness treats all acceptable outputs as equivalent, so the behavior it teaches is not tied to any particular domain or surface form and generalizes naturally across tasks and domains. These observations lead to a guiding thesis: learning preferentially converges to the most information-efficient signal component available, which accelerates learning when that component is the intended one, but causes reward hacking when a spurious pattern happens to be simpler. --- ### Mixing Times of Glauber Dynamics on Masked Language Models Authors: Suvadip Sana, Sami Wolf, Neer Mehta, Alina Shah, Aitzaz Shaikh, Janna Goodman, Lionel Levine Published: 2026-05-11 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2605.16378v1 Masked language models (MLMs) define local conditional distributions over tokens but do not, in general, correspond to any consistent joint distribution over sequences. This raises a fundamental question: what global distributional behavior is induced when such conditionals are used iteratively for generation? We address this question by modeling iterative masked-token resampling as a Glauber dynamics Markov chain on the discrete space of token sequences. We first show that MLM conditionals are intrinsically incompatible: we introduce a rectangle test that certifies this incompatibility and empirically verify its prevalence across modern MLMs. We then provide a theoretical analysis of the induced Markov chain. Under bounded cross-token influence, we establish a high-temperature contraction result implying $O(n\log n)$ mixing time where $n$ is the sequence length. In contrast, we prove that under a uniform local margin condition, the chain exhibits metastability, with exponentially slow escape from semantic basins at low temperatures. Empirically, we demonstrate a phase transition in mixing behavior as a function of temperature and sequence length, consistent with the theoretical predictions. We further characterize the induced stationary behavior through semantic trajectories, identifying persistent structures such as long-lived traps and recurrent semantic basins, with political content serving as a measurable case study. --- ### An LLM-RAG Approach for Healthy Eating Index-Informed Personalized Food Recommendations Authors: Yibin Wang, Yanjie Yang, Grace Melo Guerrero, Rodolfo M. Nayga, Azlan Zahid Published: 2026-05-11 Categories: cs.IR, cs.AI arXiv: https://arxiv.org/abs/2605.15213v1 Diet quality is a leading determinant of chronic disease risk. Advances in artificial intelligence (AI) have enabled food recommendation systems to adapt suggestions to user preferences and health goals. However, most current systems rely on loosely curated food databases and provide limited connection to a validated index. In this study, we propose a Healthy Eating Index (HEI) informed retrieval-augmented generation (RAG) framework that combines standardized nutrition databases with large language models (LLMs) for personalized food recommendations. Our proposed method anchors retrieval in the National Health and Nutrition Examination Survey (NHANES) and the Food Patterns Equivalents Database (FPED). A food-level embedding space is constructed from FPED-derived textual descriptions. For each entity, the system computes baseline HEI scores, retrieves candidate foods for intake recommendations, and estimates the HEI impact of simple substitutions or additions. A constrained RAG pipeline instantiated with a pretrained OpenAI LLM generates personalized recommendations and sources based on nutrient profiles and HEI contributions. The simulation results showed a mean HEI improvement of 6.45, with the proportion of users HEI over 50 increasing from 45.12 to 61.26. Quantile analysis revealed consistent improved shifts across the HEI distribution. Our findings suggest that the proposed LLM-RAG-based AI systems can support more precise, explainable, and personalized nutrition guidance to improve diet quality. --- ### Consciousness as Uncommon Self-Knowledge: A Synergistic Information Framework Authors: Krti Tallam Published: 2026-05-11 Categories: q-bio.NC, cs.AI arXiv: https://arxiv.org/abs/2605.13884v1 We propose uncommon self-knowledge (USK) as a candidate criterion for consciousness: synergistic information a system carries about itself that exists only in the joint of its subsystems and is destroyed by decomposition. Drawing on Gottwald's partition-lattice grounding of Partial Information Decomposition (PID), where redundancy corresponds to Aumann's common knowledge and synergy to the gap between separate and joint observation, we propose the synergistic component of self-directed information as a candidate formal signature for conscious processing. If correct, the framework would (1) offer a clean separation between consciousness and metacognition (synergistic vs. redundant self-knowledge), (2) provide principled resolutions to counterexamples that challenge IIT, GWT, and HOT, (3) be operationalizable via Partial Information Rate Decomposition (PIRD) with self-targeting, and (4) generate distinctive empirical predictions, the strongest being a GWT timing dissociation (consciousness correlates with pre-broadcast synergy formation, not broadcast itself) and a specific dissociation between self-report disruption and task-performance disruption under middle-layer perturbation in LLMs. The proposal is consistent with recent empirical findings that both anaesthesia and Alzheimer's disease specifically reduce synergistic information processing while preserving or increasing redundancy. --- ### PREPING: Building Agent Memory without Tasks Authors: Yumin Choi, Sangwoo Park, Minki Kang, Jinheon Baek, Sung Ju Hwang Published: 2026-05-11 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2605.13880v1 Agent memory is typically constructed either offline from curated demonstrations or online from post-deployment interactions. However, regardless of how it is built, an agent faces a cold-start gap when first introduced to a new environment without any task-specific experience available. In this paper, we study pre-task memory construction: whether an agent can build procedural memory before observing any target-environment tasks, using only self-generated synthetic practice. Yet, synthetic interaction alone is insufficient, as without controlling what to practice and what to store, synthetic tasks become redundant, infeasible, and ultimately uninformative, and memory further degrades quickly due to unfiltered trajectories. To overcome this, we present Preping, a proposer-guided memory construction framework. At its core is proposer memory, a structured control state that shapes future practice. A Proposer generates synthetic tasks conditioned on this state, a Solver executes them, and a Validator determines which trajectories are eligible for memory insertion while also providing feedback to guide future proposals. Experiments on AppWorld, BFCL v3, and MCP-Universe show that Preping substantially improves over a no-memory baseline and achieves performance competitive with strong playbook-based methods built from offline or online experience, with deployment cost $2.99\times$ lower on AppWorld and $2.23\times$ lower on BFCL v3 than online memory construction. Further analyses reveal that the main benefit does not come from synthetic volume alone, but from proposer-side control over feasibility, redundancy, and coverage, combined with selective memory updates. --- ### Learning When to Act: Communication-Efficient Reinforcement Learning via Run-Time Assurance Authors: Adam Haroon, Erick J. Rodríguez-Seda, Cody Fleming, Tristan Schuler Published: 2026-05-11 Categories: cs.LG, cs.RO arXiv: https://arxiv.org/abs/2605.12561v1 Safe reinforcement learning (RL) typically asks $\textit{what}$ an agent should do. We ask $\textit{when}$ it needs to act, and show that a single policy can jointly learn control inputs and communication-efficient timing decisions under a pointwise Lyapunov safety shield. We focus on stabilization around a known equilibrium, where CARE-based LQR backups, Lyapunov certificates, and classical Lyapunov-STC are well defined, enabling clean comparison against analytical baselines. A run-time assurance (RTA) layer overrides the policy via a one-step-ahead Lyapunov prediction and a precomputed LQR backup, providing a strictly stronger guarantee than constrained MDP methods that enforce safety only in expectation. On an inverted pendulum, cart--pole, and planar quadrotor, the learned policy achieves $1.91\times$, $1.45\times$, and $3.51\times$ higher mean inter-sample interval (MSI) than a Lyapunov-triggered baseline; a fixed LQR controller at the same average rate is unstable on all three plants, showing that adaptive timing, not a lower average rate, makes sparsity safe. A CARE-derived Lyapunov reward transfers across environments without redesign, with a single weight $w_c$ controlling the stability--communication tradeoff; ablations confirm the RTA shield is essential, with its removal reducing MSI by $1.27$--$1.84\times$ and degrading state norms. A preference-conditioned extension recovers the full tradeoff frontier from one model at $\tfrac{2}{11}$ of training compute, and SAC experiments show the results are algorithm-agnostic across discrete and continuous domains. A 12-state 3D quadrotor case study extends the framework to higher-dimensional systems where classical STC is intractable, and robustness to $\pm30\%$ mass variation and disturbances shows graceful degradation, with the RTA absorbing what the learned policy cannot. --- ### Brain Tumor Classification in MRI Images: A Computationally Efficient Convolutional Neural Network Authors: Md Fahimul Kabir Chowdhury, Jannatul Ferdous Published: 2026-05-11 Categories: eess.IV, cs.CV, cs.LG arXiv: https://arxiv.org/abs/2605.12560v1 Improving patient outcomes depends on the prompt and accurate diagnosis of brain tumors, but manual MRI scan analysis is still time-consuming and unreliable. Although deep learning has shown promise, many of the models that are now in use are computationally intensive and have difficulty handling the intrinsic complexity and variety of different types of brain tumors. In this work, we propose a lightweight yet high-performing Convolutional Neural Network (CNN) for multi-class brain tumor classification, employing MRI images to target gliomas, meningiomas, pituitary tumors, and healthy (no tumor) instances. The model was rigorously evaluated on two publicly accessible datasets from Figshare and Kaggle. Leveraging efficient feature extraction and optimized training strategies, our CNN achieved classification accuracies of 99.03% and 99.28%, along with ROC scores of 99.88% and 99.94% on Dataset 1 and Dataset 2, respectively-all while utilizing significantly fewer parameters than popular pre-trained architectures. In contrast to cutting-edge models like DenseNet201, MobileNetV2, VGG19, Xception, InceptionV3, and ResNet50, our approach consistently demonstrated superior performance with reduced computational overhead. These findings highlight the potential of the proposed model as a practical and reliable diagnostic aid in clinical environments. --- ### M2Retinexformer: Multi-Modal Retinexformer for Low-Light Image Enhancement Authors: Youssef Aboelwafa, Hicham G. Elmongui, Marwan Torki Published: 2026-05-11 Categories: cs.CV arXiv: https://arxiv.org/abs/2605.12556v1 Low-light image enhancement is challenging due to complex degradations, including amplified noise, artifacts, and color distortion. While Retinex-based deep learning methods have achieved promising results, they primarily rely on single-modality RGB information. We propose M2Retinexformer (Multi-Modal Retinexformer), a novel framework that extends Retinexformer by incorporating depth cues, luminance priors, and semantic features within a progressive refinement pipeline. Depth provides geometric context that is invariant to lighting variations, while luminance and semantic features offer explicit guidance on brightness distribution and scene understanding. Modalities are extracted at multiple scales and fused through cross-attention, with adaptive gating dynamically balancing illumination-guided self-attention and cross-attention based on the reliability of auxiliary cues. Evaluations on the LOL, SID, SMID, and SDSD benchmarks demonstrate overall improvements over Retinexformer and recent state-of-the-art methods. Code and pretrained weights are available at https://github.com/YoussefAboelwafa/M2Retinexformer --- ### ChannelKAN: Multi-Scale Dual-Domain Channel Prediction via Hybrid CNN-KAN Architecture Authors: Nanqing Jiang, Zhangyao Song, Tao Guo, Xiaoyu Zhao, Yinfei Xu Published: 2026-05-11 Categories: eess.SP, cs.AI arXiv: https://arxiv.org/abs/2605.12553v1 Accurate channel state information (CSI) prediction is essential for improving the reliability and spectral efficiency of massive MIMO-OFDM systems in high-mobility scenarios. Existing deep learning methods struggle to jointly capture short-term local variations and long-range nonlinear dependencies in CSI sequences. To address this challenge, we propose ChannelKAN, a hybrid CNN-KAN channel prediction model with multi-scale frequency domain information enhancement. The key insight is that CNNs and Kolmogorov-Arnold Networks (KANs) are naturally complementary: CNNs extract intra-time-step local spatial-frequency correlations, while KANs with learnable Chebyshev polynomial activations fit inter-time-step nonlinear temporal evolution in a holistic manner. Specifically, a dual-domain expansion module first generates complementary frequency-domain and delay-domain CSI representations. A multi-scale frequency information enhancement module then retains dominant spectral components at multiple scales to strengthen key features and suppress noise. Next, a CNN-KAN feature extraction module captures local correlations via cascaded convolutions and models long-range dependencies via Chebyshev KAN layers. Finally, a dual-domain fusion module adaptively integrates features from both branches to produce the prediction. Experiments on 3GPP-compliant QuaDRiGa datasets demonstrate that ChannelKAN outperforms RNN, LSTM, GRU, CNN, and Transformer baselines in normalized mean square error (NMSE), spectral efficiency (SE), and bit error rate (BER) across various velocities and signal-to-noise ratios. Ablation studies further confirm the effectiveness of each proposed module. --- ### Physics-Informed Teacher-Student Ensemble Learning for Traffic State Estimation with a Varying Speed Limit Scenario Authors: Archie J. Huang, Dongdong Wang, Shaurya Agarwal, Mohamed Abdel-Aty, Md Mahmudul Islam, Muhammad Shahbaz Published: 2026-05-11 Categories: cs.LG, cs.AI, cs.CE arXiv: https://arxiv.org/abs/2605.11346v1 Physics-informed deep learning (PIDL) neural networks have shown their capability as a useful instrument for transportation practitioners in utilizing the underlying relationship between the state variables for traffic state estimation (TSE). Another efficient traffic management approach is implementing varying speed limits (VSLs) on transportation corridors to control traffic and mitigate congestion. However, the existing training architecture of PIDL in the literature cannot accommodate the changing traffic characteristics on a freeway with VSL. To tackle this challenge, we propose a novel framework integrating teacher-student ensemble training with PIDL neural networks for TSE under VSL scenarios. The physics of flow conservation law is encoded locally in the teacher models by PIDL, and the student model uses a multi-layer perceptron classifier (MLP) to identify traffic characteristics and selects the ensemble member of PIDL neural networks for TSE. This integrated framework provides a natural solution for capturing the heterogeneity of VSL and accurately addressing the TSE problem. The case study results validate the proposed ensemble approach, demonstrating its superior performance in TSE compared to other popular baseline methods, as indicated by relative L2 error. --- ### CPEMH: An Agentic Framework for Prompt-Driven Behavior Evaluation and Assurance in Foundation-Model Systems for Mental Health Screening Authors: Giuliano Lorenzoni, Ivens Portugal, Paulo Alencar, Donald Cowan Published: 2026-05-11 Categories: cs.AI arXiv: https://arxiv.org/abs/2605.11341v1 This paper presents CPEMH, an agentic framework designed to evaluate prompt-driven behavior in foundation-model systems operating on transcript-based datasets for mental-health screening. CPEMH serves as an engineering methodology for behavioral assurance in large-scale language systems, introducing an orchestrated architecture that autonomously performs the design, evaluation, and selection of prompt strategies, enabling systematic control of behavioral variability across contexts. Its modular agentic design, combining orchestrator, inference, and evaluation agents, ensures traceability, reproducibility, and robustness throughout the prompting lifecycle. A case study on automated depression screening from interview transcripts demonstrates the framework's capacity to stabilize and audit foundation-model behavior in conversational and clinically sensitive domains. Lessons learned emphasize the role of modular orchestration in behavioral assurance, the prioritization of stability over architectural complexity, and the integration of F1, bias, and robustness as core acceptance criteria. --- ### Much of Geospatial Web Search Is Beyond Traditional GIS Authors: Ilya Ilyankou, Stefano Cavazzi, James Haworth Published: 2026-05-11 Categories: cs.IR, cs.AI, cs.CL, cs.HC arXiv: https://arxiv.org/abs/2605.11336v2 Web search queries concern place far more often than existing labelling schemes suggest, yet the landscape of geospatial web search queries - what people ask of place, and how often - remains poorly characterised at scale. We apply dense sentence embeddings, a lightweight SetFit classifier, and density-based clustering to the full MS MARCO corpus of 1.01 million real Bing queries without prior filtering for toponyms or spatial keywords, identifying 181,827 geospatial queries (18.0%), nearly threefold the 6.17% labelled as Location in the original annotations. The resulting taxonomy of 88 query categories reveals that geospatial web search is dominated by transactional and practical lookups: costs and prices alone account for 15.3% of geospatial queries, nearly twice the size of the entire physical geography theme. Much of this activity - costs, opening hours, contact details, weather, travel recommendations - falls outside the scope of what traditional GIS and knowledge graphs are built to serve. The categories vary substantially in the kind of answer they admit, from deterministic lookups answerable from spatial databases or knowledge graphs to evaluative or temporally volatile queries that require generative or real-time systems. We discuss implications for hybrid retrieval architectures and for benchmarks of geographic reasoning in large language models. We openly release the labelled dataset, classifier, and taxonomy. --- ### ChunkFlow: Communication-Aware Chunked Prefetching for Layerwise Offloading in Distributed Diffusion Transformer Inference Authors: Han Meng, Danny Willow Liu, Dong Li Published: 2026-05-11 Categories: cs.DC, cs.LG arXiv: https://arxiv.org/abs/2605.11335v1 Layerwise offloading reduces the GPU memory footprint of large diffusion transformer (DiT) inference by prefetching upcoming layers from host memory, but its effectiveness hinges on hiding prefetch latency behind per-layer computation. This assumption breaks down when the per-GPU compute workload is small. Moreover, on PCIe-only nodes, prefetch and inter-GPU collective communications such as all-reduce and all-to-all contend on the shared PCIe path, exposing prefetch latency even when compute would otherwise hide it. We revisit layerwise offloading as a co-scheduling problem between prefetch and communication, guided by a first-order analytical model that predicts when prefetch can be hidden by computation. Building on this model, we design ChunkFlow, a communication-aware, chunk-granular offloading runtime that adaptively yields to collective communication and smoothly trades GPU memory for prefetch volume. On three representative diffusion transformers running on two H100 GPUs over PCIe with Ulysses sequence parallelism, ChunkFlow delivers up to 1.28x step-time speedup over SGLang's existing layerwise offloading, reduces peak GPU memory by up to 49% over the no-offload baseline at near-identical step time once the workload is large enough, and exposes a tunable memory-latency tradeoff that recovers near-zero step-time overhead in the small-workload regime. --- ### VERDI: Single-Call Confidence Estimation for Verification-Based LLM Judges via Decomposed Inference Authors: Jasmine Qi, Danylo Dantsev, Muyang Sun Published: 2026-05-11 Categories: cs.LG, cs.CL, cs.IR arXiv: https://arxiv.org/abs/2605.11334v1 LLM-as-Judge systems are widely deployed for automated evaluation, yet practitioners lack reliable methods to know when a judge's verdict should be trusted. Token log-probabilities, the standard post-hoc confidence signal, are unavailable for many commercial LLMs and, even when accessible, saturate above 0.999 with structured JSON output. We introduce VERDI (VERification-Decomposed Inference), a method that extracts confidence from the reasoning trace a structured judge already produces, with no additional inference calls. VERDI decomposes each verification-style evaluation into sub-checks and derives three structural signals: Step-Verdict Alignment, Claim-Level Margin, and Evidence Grounding Score. We combine them with Platt-scaled logistic regression. On three public benchmarks, VERDI achieves AUROC 0.72-0.91 on GPT-4.1-mini and 0.66-0.80 on GPT-5.4-mini. On Qwen3.5-4B/9B/27B, where answer-token logprobs are anti-calibrated (higher confidence on errors, AUROC 0.32-0.49), VERDI achieves 0.56-0.70. We additionally validate on a production system with eight rubrics (AUROC 0.73-0.88 on factual rubrics), demonstrate cross-model transfer (AUROC 0.66-0.69), and show that a 33M-parameter NLI (Natural Language Inference) model provides a scalable alternative to regex extraction. --- ### MLCommons Chakra: Advancing Performance Benchmarking and Co-design using Standardized Execution Traces Authors: Srinivas Sridharan, Theodor-Adrian Badea, Andy Balogh, Bradford M. Beckmann, Brian Coutinho, Louis Feng, Sheng Fu, Sanshan Gao, Mehryar Garakani, Taekyung Heo, David Kanter, Josh Ladd et al. Published: 2026-05-11 Categories: cs.DC, cs.LG, cs.PF arXiv: https://arxiv.org/abs/2605.11333v3 The fast pace of artificial intelligence~(AI) innovation demands an agile methodology for observation, reproduction and optimization of distributed machine learning~(ML) workload behavior in production AI systems and enables efficient software-hardware~(SW-HW) co-design for future systems. We present Chakra, an open and portable ecosystem for performance benchmarking and co-design. The core component of Chakra is an open and interoperable graph-based representation of distributed AI/ML workloads, called Chakra execution trace~(ET). These ETs represent key operations, such as compute, memory, and communication, data and control dependencies, timing, and resource constraints. Additionally, Chakra includes a complementary set of tools and capabilities to enable the collection, analysis, generation, and adoption of Chakra ETs by a broad range of simulators, emulators, and replay tools. We present analysis of Chakra ETs collected on production AI clusters and demonstrate value via real-world case studies. Chakra has been adopted by MLCommons and has active contributions and engagement across the industry, including but not limited to NVIDIA, AMD, Meta, Keysight, HPE, and Scala, to name a few. --- ### Rethinking Evaluation for LLM Hallucination Detection: A Desiderata, A New RAG-based Benchmark, New Insights Authors: Wenbo Chen, Veena Padmanabhan, Tootiya Giyahchi, Elaine Wong, Leman Akoglu Published: 2026-05-11 Categories: cs.AI arXiv: https://arxiv.org/abs/2605.11330v1 Hallucination, broadly referring to unfaithful, fabricated, or inconsistent content generated by LLMs, has wide-ranging implications. Therefore, a large body of effort has been devoted to detecting LLM hallucinations, as well as designing benchmark datasets for evaluating these detectors. In this work, we first establish a desiderata of properties for hallucination detection benchmarks (HDBs) to exhibit for effective evaluation. A critical look at existing HDBs through the lens of our desiderata reveals that none of them exhibits all the properties. We identify two largest gaps: (1) RAG-based grounded benchmarks with long context are severely lacking (partly because length impedes human annotation); and (2) Existing benchmarks do not make available realistic label noise for stress-testing detectors although real-world use-cases often grapple with label noise due to human or automated/weak annotation. To close these gaps, we build and open-source a new RAG-based HDB called T RIVIA+ that underwent a rigorous human annotation process. Notably, our benchmark exhibits all desirable properties including (1) T RIVIA+ contains samples with the longest context in the literature; and (2) we design and share four sets of noisy labels with different, both sample-dependent and sampleindependent, noise schemes. Finally, we perform experiments on RAG-based HDBs, including our T RIVIA+, using popular SOTA detectors that reveal new insights: (i) ample room remains for current detectors to reach the performance ceiling on RAG-based HDBs, (ii) the basic LLM-as-a-Judge baseline performs competitively, and (iii) label noise hinders detection performance. We expect that our findings, along with our proposed benchmark 1 , will motivate and foster needed research on hallucination detection for RAG-based tasks. --- ### Epistemic Uncertainty for Test-Time Discovery Authors: Kainat Riaz, Muhammad Ahmed Mohsin, Ahsan Bilal, Muhammad Umer, Ayesha Mohsin, Aqib Riaz, Ali Subhan, John M. Cioffi Published: 2026-05-11 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2605.11328v1 Automated scientific discovery using large language models relies on identifying genuinely novel solutions. Standard reinforcement learning penalizes high-variance mutations, which leads the policy to prioritize familiar patterns. As a result, the maximum reward plateaus even as the average reward increases. Overcoming this limitation requires a signal that distinguishes unexplored regions from intrinsically difficult problems. This necessitates measuring disagreement across independently adapted weight hypotheses rather than relying on a single network's confidence. UG-TTT addresses this challenge by maintaining a small ensemble of low-rank adapters over a frozen base model. The per-token disagreement, quantified as the mutual information between ensemble predictions and weight hypotheses, isolates epistemic uncertainty and identifies positions where insufficient coverage leads to adapter divergence rather than intrinsic problem difficulty. This measure is incorporated as an exploration bonus into the policy gradient, directing the policy toward positions where persistent adapter disagreement signals low training coverage, the same frontier where genuine discovery is possible. A nuclear norm regularizer ensures the adapters remain distinct from one another, thereby preserving the exploration signal throughout training. Across four scientific discovery benchmarks, UG-TTT increases the maximum reward on three tasks, maintains substantially higher solution diversity, and an ablation study confirms that the regularizer is essential for sustaining this behavior. --- ### Neural Statistical Functions Authors: Daniel Xu, Yuxin Xie, Minghao Guo, Haixu Wu, Wojciech Matusik Published: 2026-05-11 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.11327v1 Classical deep learning typically operates on individual cases. Despite its success, real-world usage often requires repeated inference to estimate statistical quantities for complex decision-making tasks involving uncertainty or extreme-value analysis, resulting in substantial latency. We introduce neural statistical functions, a new family of models learned from pre-trained single-sample predictors and scattered data samples, which can directly infer statistics over continuous operating condition ranges without explicit sampling. By introducing the notion of prefix statistics, we transform and unify diverse statistical functions (e.g., integrals, quantiles, and maxima) into an interval-conditional framework, in which a principled identity between the prefix statistics and the individual-case regression serves as the learning objective. Neural statistical functions achieve strong performance in estimating essential statistics of complex physical processes, including accumulated energy in dynamical systems, quantiles of aerodynamic responses, and maximum stress in crash processes, while achieving up to a 100$\times$ reduction in model evaluations. --- ### Structured Belief State and the First Precision-Aware Benchmark for LLM Memory Retrieval Authors: Jeffrey Flynt Published: 2026-05-11 Categories: cs.IR, cs.AI arXiv: https://arxiv.org/abs/2605.11325v4 Current LLM memory benchmarks evaluate answer quality rather than retrieval accuracy. Consequently, a system that dumps its entire belief store can achieve perfect recall and mask severe precision failures. We show this evaluation gap persists across multiple embedding models where similarity-based retrieval over domain-specific corpora inherently struggles to isolate target beliefs from semantically proximate ones. Furthermore, multi-turn topic drift compounds this retrieval noise while driving up latency and operational costs. To decouple retrieval quality from generative performance, we introduce PrecisionMemBench, an 89-case benchmark measuring precision, noise isolation, session latency, and belief mutability. We also present Tenure, a structured belief-store proxy that resolves scope and retrieval before inference and injects typed belief state as ambient instruction before the model sees the prompt, removing model-side discretion over whether memory is consulted. Evaluated across 13 configurations, Tenure achieves perfect retrieval passes across all active, non-session, and session test cases. In contrast, the baseline configurations fail to reach even half of the active passes, with precision scores clustering at 0.22 and below. Our results demonstrate that while current memory systems successfully store information, they fail to retrieve it cleanly; a structural vulnerability that traditional answer-quality benchmarks conceal. ---