# Research Papers — 2026-05 · bundle page 295 of 326 > Full-text markdown of papers #14701–14750 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/295 [← Previous bundle](https://aipod.dev/papers/archive/2026-05/page/294.md) [Next bundle →](https://aipod.dev/papers/archive/2026-05/page/296.md) ### The Counterexample Game: Iterated Conceptual Analysis and Repair in Language Models Authors: Daniel Drucker, Kyle Mahowald Published: 2026-05-05 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2605.03936v1 Conceptual analysis -- proposing definitions and refining them through counterexamples -- is central to philosophical methodology. We study whether language models can perform this task through iterated analysis and repair chains: one model instance generates counterexamples to a proposed definition, another repairs the definition, and the process repeats. Across 20 concepts and thousands of counterexample-repair cycles, we find that, although many LM-generated counterexamples are judged invalid by both expert humans and an LM judge, the LM judge accepts roughly twice as many as humans do. Nonetheless, per-item validity judgments are moderately consistent across humans and between humans and the LM. We further find that extended iteration produces increasingly verbose definitions without improving accuracy. We also see that some concepts resist stable definitions in general. These findings suggest that while LMs can engage in philosophical reasoning, the counterexample-repair loop hits diminishing returns quickly and could be a fruitful test case for evaluating whether LMs can sustain high-level iterated philosophical reasoning. --- ### Towards Open World Sound Event Detection Authors: P. H. Hai, L. T. Minh, L. H. Son Published: 2026-05-05 Categories: cs.SD, cs.AI arXiv: https://arxiv.org/abs/2605.03934v2 Sound Event Detection (SED) plays a vital role in audio understanding, with applications in surveillance, smart cities, healthcare, and multimedia indexing. However, conventional SED systems operate under a closed-world assumption, limiting their effectiveness in real-world environments where novel acoustic events frequently emerge. Inspired by the success of open-world learning in computer vision, we introduce the Open-World Sound Event Detection (OW-SED) paradigm, where models must detect known events, identify unseen ones, and incrementally learn from them. To tackle the unique challenges of OW-SED, such as overlapping and ambiguous events, we propose a 1D Deformable architecture that leverages deformable attention to adaptively focus on salient temporal regions. Furthermore, we design a novel Open-World Deformable Sound Event Detection Transformer (WOOT) framework incorporating feature disentanglement to separate class-specific and class-agnostic representations, together with a one-to-many matching strategy and a diversity loss to enhance representation diversity. Experimental results demonstrate that our method achieves marginally superior performance compared to existing leading techniques in closed-world settings and significantly improves over existing baselines in open-world scenarios. --- ### Magic-Informed Quantum Architecture Search Authors: Vincenzo Lipardi, Domenica Dibenedetto, Georgios Stamoulis, Mark H. M. Winands Published: 2026-05-05 Categories: quant-ph, cs.AI arXiv: https://arxiv.org/abs/2605.03932v1 Nonstabilizerness, commonly referred to as magic, is a fundamental resource underpinning quantum advantage. In this paper, we propose a magic-informed quantum architecture search (QAS) technique that enables control over a quantum resource within the general framework of circuit design. Inspired by the AlphaGo approach, we tackle the problem with a Monte Carlo Tree Search technique equipped with a Graph Neural Network (GNN) that estimates the magic of candidate quantum circuits. The GNN model induces a magic-based bias that steers the search toward either high- or low-magic regimes, depending on the target objective. We benchmark the proposed magic-informed QAS technique on both the structured ground-state energy problem and on the more general quantum state approximation problem, spanning different sizes and target magic levels. Experimental results show that the proposed technique effectively influences the magic across the search tree and notably also on the resulting final circuit, even in regimes where the GNN operates on out-of-distribution instances. Although introducing a problem-agnostic magic bias could, in principle, constrain the search dynamics, we observe consistent improvements in solution quality across all problems tested. --- ### PHALAR: Phasors for Learned Musical Audio Representations Authors: Davide Marincione, Michele Mancusi, Giorgio Strano, Luca Cerovaz, Donato Crisostomi, Roberto Ribuoli, Emanuele Rodolà Published: 2026-05-05 Categories: cs.SD, cs.AI, cs.LG, eess.SP arXiv: https://arxiv.org/abs/2605.03929v4 Stem retrieval, the task of matching missing stems to a given audio submix, is a key challenge currently limited by models that discard temporal information. We introduce PHALAR, a contrastive framework achieving a relative accuracy increase of up to $\approx 70\%$ over the state-of-the-art while requiring $<50\%$ of the parameters and a 7$\times$ training speedup. By utilizing a Learned Spectral Pooling layer and a complex-valued head, PHALAR enforces pitch-equivariant and phase-equivariant biases. PHALAR establishes new retrieval state-of-the-art across MoisesDB, Slakh, and ChocoChorales, correlating significantly higher with human coherence judgment than semantic baselines. Finally, zero-shot beat tracking and linear chord probing confirm that PHALAR captures robust musical structures beyond the retrieval task. --- ### StateVLM: A State-Aware Vision-Language Model for Robotic Affordance Reasoning Authors: Xiaowen Sun, Matthias Kerzel, Mengdi Li, Xufeng Zhao, Paul Striker, Stefan Wermter Published: 2026-05-05 Categories: cs.CV arXiv: https://arxiv.org/abs/2605.03927v3 Vision-language models have demonstrated strong performance across robotic perception and instruction-following tasks. However, they still struggle with precise spatial reasoning, particularly in predicting object locations and fine-grained object states. We propose StateVLM, a vision-language model designed to learn fine-grained object representations, including object localization and grasp-relevant region prediction. We introduce a joint training objective that integrates an auxiliary regression loss (ARL) with the standard causal language modeling (CLM) objective to improve numerical reasoning and spatial understanding. To evaluate whether models can move beyond category-level grounding toward state-aware spatial understanding, we introduce an open-source benchmark, Object State Affordance Reasoning (OSAR), comprising 1,172 scenes with 7,746 individual objects and their corresponding bounding boxes. Empirical experiments on the Referring Expression Comprehension datasets demonstrate that integrating ARL improves model performance compared with CLM only. Experiments on the OSAR benchmark further demonstrate that StateVLM with ARL achieves an average improvement of 5.2% over models trained with CLM only. These results show that ARL is particularly beneficial for the complex affordance reasoning tasks that require object state understanding. The joint training objective in StateVLM demonstrates that integrating an auxiliary regression objective into VLM training improves numerical reasoning, and the OSAR benchmark provides a new testbed for understanding object state affordances in robotics. --- ### StateVLM: A State-Aware Vision-Language Model for Robotic Affordance Reasoning Authors: Xiaowen Sun, Matthias Kerzel, Mengdi Li, Xufeng Zhao, Paul Striker, Stefan Wermter Published: 2026-05-05 Categories: cs.CV arXiv: https://arxiv.org/abs/2605.03927v2 Vision-language models (VLMs) have shown remarkable performance in various robotic tasks, as they can perceive visual information and understand natural language instructions. However, when applied to robotics, VLMs remain subject to a fundamental limitation inherent in large language models (LLMs): they struggle with numerical reasoning, particularly in object detection and object-state localization. To explore numerical reasoning as a regression task in VLMs, we propose a novel training strategy to adapt VLMs for object detection and object-state localization. This approach leverages box decoder outputs to compute an Auxiliary Regression Loss (ARL) during fine-tuning, while preserving standard sequence prediction at inference. We leverage this training strategy to develop StateVLM (State-aware Vision-Language Model), a novel model designed to perceive and learn fine-grained object representations, including precise localization of objects and their states, as well as graspable regions. Due to the lack of a benchmark for object-state affordance reasoning, we introduce an open-source benchmark, Object State Affordance Reasoning (OSAR), which contains 1172 scenes with 7746 individual objects and corresponding bounding boxes. Comparative experiments on adapted benchmarks (RefCOCO, RefCOCO+, and RefCOCOg) demonstrate that ARL improves model performance by an average of 1.6% compared to models without ARL. Experiments on the OSAR benchmark further support this finding, showing that StateVLM with ARL achieves an average of 5.2% higher performance than models without ARL. In particular, ARL is also important for the complex task of affordance reasoning in OSAR, where it enhances the consistency of model outputs. --- ### Optimal Posterior Sampling for Policy Identification in Tabular Markov Decision Processes Authors: Cyrille Kone, Kevin Jamieson Published: 2026-05-05 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2605.03921v1 We study the $(\varepsilon, δ)$-PAC policy identification problem in finite-horizon episodic Markov Decision Processes. Existing approaches provide finite-time guarantees for approximate settings ($\varepsilon>0$) but suffer from high computational cost, rendering them hard to implement, and also suffer from suboptimal dependence on $\log(1/δ)$. We propose a randomized and computationally efficient algorithm for best policy identification that combines posterior sampling with an online learning algorithm to guide exploration in the MDP. Our method achieves asymptotic optimality in sample complexity, also in terms of posterior contraction rate, and runs in $O(S^2AH)$ per episode, matching standard model-based approaches. Unlike prior algorithms such as MOCA and PEDEL, our guarantees remain meaningful in the asymptotic regime and avoid sub-optimal polynomial dependence on $\log(1/δ)$. Our results provide both theoretical insights and practical tools for efficient policy identification in tabular MDPs. --- ### Robustness and Transferability of Pix2Geomodel for Bidirectional Facies Property Translation in a Complex Reservoir Authors: Abdulrahman Al-Fakih, Nabil Sariah, Ardiansyah Koeshidayatullah, Sherif Hanafy, SanLinn I. Kaka Published: 2026-05-05 Categories: physics.geo-ph, cs.CC, cs.CV, physics.comp-ph arXiv: https://arxiv.org/abs/2605.03919v1 Reservoir geomodeling is central to subsurface characterization, but it remains challenging because conditioning data are sparse, geological heterogeneity is strong, and conventional geostatistical workflows often struggle to capture nonlinear relationships between facies and petrophysical properties. This study evaluates the robustness and transferability of Pix2Geomodel on a different and more complex reservoir dataset with reduced vertical support. The new case includes a heterogeneous reservoir-quality classification and only 54 retained layers, providing a stricter test of whether Pix2Pix-based image-to-image translation can preserve facies-property relationships under constrained data conditions. Facies, porosity, permeability, and clay volume (VCL) were extracted from a reference reservoir model, exported as aligned two-dimensional slices, augmented using consistent geometric transformations, and assembled into paired image datasets. Six bidirectional tasks were evaluated: facies to porosity, facies to permeability, facies to VCL, porosity to facies, permeability to facies, and VCL to facies. The Pix2Pix model, consisting of a U-Net generator and PatchGAN discriminator, was evaluated using image-based metrics, visual comparison, and variogram-based spatial-continuity validation. Results show that the model preserves the dominant geological architecture and main spatial-continuity trends. Facies to porosity achieved the highest pixel accuracy and frequency-weighted intersection over union of 0.9326 and 0.8807, while VCL to facies achieved the highest mean pixel accuracy and mean intersection over union of 0.8506 and 0.7049. These findings show that Pix2Geomodel can transfer beyond its original case study as a practical framework for rapid bidirectional facies-property translation in complex reservoir modeling. --- ### Exact ReLU realization of tensor-product refinement iterates Authors: Tsogtgerel Gantumur Published: 2026-05-05 Categories: math.CA, cs.LG arXiv: https://arxiv.org/abs/2605.03917v1 We study scalar dyadic refinement operators on R^2 of the form (Vf)(x,y) = sum_{(j,k) in Z^2} c_{j,k} f(2x-j, 2y-k), where only finitely many mask coefficients c_{j,k} are nonzero. Under a fixed support-window hypothesis, we prove that for every compactly supported continuous piecewise linear seed g:R^2->R, the iterates V^n g admit exact ReLU realizations of fixed width and depth O(n). This gives a first genuinely two-dimensional extension of the exact realization theory for refinement cascades. Using the one-dimensional exact loop-controller framework, the proof transports the tensor-product residual dynamics exactly on the product of two polygonal loops and reduces the remaining seam ambiguity to a final readout and selector step. The matrix cascade is then handled by a fixed-depth recursive block, and general compactly supported continuous piecewise linear seeds are reduced to a finite decomposition together with exact clamped gluing on the support window. This identifies the tensor-product dyadic case as a natural first multivariate instance of the loop-controller method for refinement iterates. --- ### Atomic Fact-Checking Increases Clinician Trust in Large Language Model Recommendations for Oncology Decision Support: A Randomized Controlled Trial Authors: Lisa C. Adams, Linus Marx, Erik Thiele Orberg, Keno Bressem, Sebastian Ziegelmayer, Denise Bernhardt, Markus Graf, Marcus R. Makowski, Stephanie E. Combs, Florian Matthes, Jan C. Peeken Published: 2026-05-05 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2605.03916v1 Question: Does atomic fact-checking, which decomposes AI treatment recommendations into individually verifiable claims linked to source guideline documents, increase clinician trust compared to traditional explainability approaches? Findings: In this randomized trial of 356 clinicians generating 7,476 trust ratings, atomic fact-checking produced a large effect on trust (Cohen's d = 0.94), increasing the proportion of clinicians expressing trust from 26.9% to 66.5%. Traditional transparency mechanisms showed a dose-response gradient of improvement over baseline (d = 0.25 to 0.50). Meaning: Decomposing AI recommendations into individually verifiable claims linked to source guidelines produces substantially higher clinician trust than traditional explainability approaches in high-stakes clinical decisions. --- ### Ecologically-Constrained Task Arithmetic for Multi-Taxa Bioacoustic Classifiers Without Shared Data Authors: Ragib Amin Nihal, Benjamin Yen, Runwu Shi, Takeshi Ashizawa, Kazuhiro Nakadai Published: 2026-05-05 Categories: cs.SD, cs.LG arXiv: https://arxiv.org/abs/2605.03914v1 Training data for bioacoustics is scattered across taxa, regions, and institutions. Centralizing it all is often infeasible. We show that independently fine-tuned BEATs encoders can be composed into a unified 661-species classifier via task vector arithmetic without sharing data. We find that bioacoustic task vectors are near-orthogonal (cosine 0.01-0.09). Their separation aligns closely with spectral distribution distance, a gradient consistent with the acoustic niche hypothesis. This geometry makes simple averaging optimal while sign-conflict methods reduce accuracy by one to six percentage points. Composition also creates an asymmetric gap: species-rich groups lose accuracy relative to joint training while underrepresented taxa gain, a redistribution useful for equitable biodiversity monitoring. We verify linear mode connectivity across all taxonomic pairs, demonstrate zero-shot transfer to new regions, and identify domain negation as a boundary condition where composition fails. These results enable a collaborative paradigm for bioacoustics where institutions share only task vectors to assemble multi-taxa classifiers, preserving data privacy. --- ### Task-Aware Scanning Parameter Configuration for Robotic Inspection Using Vision Language Embeddings and Hyperdimensional Computing Authors: Zhiling Chen, David Gorsich, Matthew P. Castanier, Yang Zhang, Jiong Tang, Farhad Imani Published: 2026-05-05 Categories: cs.RO, cs.CV arXiv: https://arxiv.org/abs/2605.03909v1 Robotic laser profiling is widely used for dimensional verification and surface inspection, yet measurement fidelity is often dominated by sensor configuration rather than robot motion. Industrial profilers expose multiple coupled parameters, including sampling frequency, measurement range, exposure time, receiver dynamic range, and illumination, that are still tuned by trial-and-error; mismatches can cause saturation, clipping, or missing returns that cannot be recovered downstream. We formulate instruction-conditioned sensing parameter recommendation; given a pre-scan RGB observation and a natural-language inspection instruction, infer a discrete configuration over key parameters of a robot-mounted profiler. To benchmark this problem, we develop Instruct-Obs2Param, a real-world multimodal dataset linking inspection intents and multi-view pose and illumination variation across 16 objects to canonical parameter regimes. We then propose ScanHD, a hyperdimensional computing framework that binds instruction and observation into a task-aware code and performs parameter-wise associative reasoning with compact memories, matching discrete scanner regimes while yielding stable, interpretable, low-latency decisions. On Instruct-Obs2Param, ScanHD achieves 92.7% average exact accuracy and 98.1% average Win@1 accuracy across the five parameters, with strong cross-split generalization and low-latency inference suitable for deployment, outperforming rule-based heuristics, conventional multimodal models, and multimodal large language models. This work enables autonomous, instruction-conditioned sensing configuration from task intent and scene context, eliminating manual tuning and elevating sensor configuration from a static setting to an adaptive decision variable. --- ### Steer Like the LLM: Activation Steering that Mimics Prompting Authors: Geert Heyman, Frederik Vandeputte Published: 2026-05-05 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2605.03907v1 Large language models can be steered at inference time through prompting or activation interventions, but activation steering methods often underperform compared to prompt-based approaches. We propose a framework that formulates prompt steering as a form of activation steering and investigates whether distilling successful prompt steering behavior into simpler, interpretable models can close this gap. Our analysis reveals that popular activation steering methods are not faithful to the mechanics of prompt steering, which applies strong interventions on some tokens while barely affecting others. Based on these insights, we introduce Prompt Steering Replacement (PSR) models that estimate token-specific steering coefficients from the activations themselves and are trained to imitate prompt-based interventions. Experiments on three steering benchmarks across multiple language models show that PSR models outperform existing activation steering methods, especially when controlling for high-coherence completions, and also compare favorably to prompting on AxBench and persona steering. --- ### CC-OCR V2: Fine-Grained Attribution of LMM Failures in Real-World Visual Document Understanding Authors: Chunyi Peng, Zhipeng Xu, Yuqi Xiong, Zulong Chen, Junhao Ji, Qing Liu, Zhenghao Liu, Zubao Qin, Bing Zhao, Jianqiang Wan, Jun Tang, Zhibo Yang et al. Published: 2026-05-05 Categories: cs.CL arXiv: https://arxiv.org/abs/2605.03903v2 Recent Large Multimodal Models (LMMs) have achieved remarkable progress on OCR-centric document understanding and processing tasks. Existing benchmarks primarily evaluate LMMs across diverse tasks to reflect practical document-processing workflows or analyze how document characteristics influence model performance. However, they provide limited insight into the reliability of LMMs under real-world document acquisition conditions, where factors such as lighting, screen displays, imaging quality, and capture methods can substantially affect performance. To bridge this gap, we present CC-OCR v2, a comprehensive benchmark for attributing LMM failures in real-world document processing. CC-OCR v2 provides a unified evaluation framework covering five core document-processing capabilities through 16 subtasks, 74 application scenarios, and 7,093 samples. The benchmark spans five evaluation tracks, ten document categories, and 32 languages in the recognition suite. Beyond task-level evaluation, each sample is annotated with ten fine-grained document factors, enabling systematic attribution of model failures across document types and acquisition conditions. Extensive experiments on 17 representative LMMs reveal substantial performance variation across tasks, document categories, and real-world conditions. Moreover, models with comparable overall accuracy often exhibit fundamentally different failure patterns under specific document factors, highlighting a significant gap between benchmark-level performance and reliable deployment in practical applications. The dataset and evaluation toolkit are publicly available at https://github.com/eioss/CC-OCR-V2. --- ### CC-OCR V2: Benchmarking Large Multimodal Models for Literacy in Real-world Document Processing Authors: Zhipeng Xu, Junhao Ji, Zulong Chen, Zhenghao Liu, Qing Liu, Chunyi Peng, Zubao Qin, Ze Xu, Jianqiang Wan, Jun Tang, Zhibo Yang, Shuai Bai et al. Published: 2026-05-05 Categories: cs.CL arXiv: https://arxiv.org/abs/2605.03903v1 Large Multimodal Models (LMMs) have recently shown strong performance on Optical Character Recognition (OCR) tasks, demonstrating their promising capability in document literacy. However, their effectiveness in real-world applications remains underexplored, as existing benchmarks adopt task scopes misaligned with practical applications and assume homogeneous acquisition conditions. To address this gap, we introduce CC-OCR V2, a comprehensive and challenging OCR benchmark tailored to real-world document processing. CC-OCR V2 focuses on practical enterprise document processing tasks and incorporates hard and corner cases that are critical yet underrepresented in prior benchmarks, covering 5 major OCR-centric tracks: text recognition, document parsing, document grounding, key information extraction, and document question answering, comprising 7,093 high-difficulty samples. Extensive experiments on 14 advanced LMMs reveal that current models fall short of real-world application requirements. Even state-of-the-art LMMs exhibit substantial performance degradation across diverse tasks and scenarios. These findings reveal a significant gap between performance on current benchmarks and effectiveness in real-world applications. We release the full dataset and evaluation toolkit at https://github.com/eioss/CC-OCR-V2. --- ### Graph Neural Networks in the Wilson Loop Representation of Abelian Lattice Gauge Theories Authors: Ali Rayat, Gia-Wei Chern Published: 2026-05-05 Categories: cond-mat.str-el, cs.LG, hep-lat, quant-ph arXiv: https://arxiv.org/abs/2605.03901v1 Local gauge structures play a central role in a wide range of condensed matter systems and synthetic quantum platforms, where they emerge as effective descriptions of strongly correlated phases and engineered dynamics. We introduce a gauge-invariant graph neural network (GNN) architecture for Abelian lattice gauge models, in which symmetry is enforced explicitly through local gauge-invariant inputs, such as Wilson loops, and preserved throughout message passing, eliminating redundant gauge degrees of freedom while retaining expressive power. We benchmark the approach on both $\mathbb{Z}_2$ and $\mathrm{U}(1)$ lattice gauge models, achieving accurate predictions of global observables and spatially resolved quantities despite the nonlocal correlations induced by gauge-matter coupling. We further demonstrate that the learned model serves as an efficient surrogate for semiclassical dynamics in $\mathrm{U}(1)$ quantum link models, enabling stable and scalable time evolution without repeated fermionic diagonalization, while faithfully reproducing both local dynamics and statistical correlations. These results establish gauge-invariant message passing as a compact and physically grounded framework for learning and simulating Abelian lattice gauge systems. --- ### Contextual Multi-Objective Optimization: Rethinking Objectives in Frontier AI Systems Authors: Jie Zhou, Qin Chen, Liang He Published: 2026-05-05 Categories: cs.AI arXiv: https://arxiv.org/abs/2605.03900v1 Frontier AI systems perform best in settings with clear, stable, and verifiable objectives, such as code generation, mathematical reasoning, games, and unit-test-driven tasks. They remain less reliable in open-ended settings, including scientific assistance, long-horizon agents, high-stakes advice, personalization, and tool use, where the relevant objective is ambiguous, context-dependent, delayed, or only partially observable. We argue that many such failures are not merely failures of scale or capability, but failures of objective selection: the system optimizes a locally visible signal while missing which objectives should govern the interaction. We formulate this problem as \emph{contextual multi-objective optimization}. In this setting, systems must consider multiple, context-dependent objectives, such as helpfulness, truthfulness, safety, privacy, calibration, non-manipulation, user preference, reversibility, and stakeholder impact, while determining which objectives are active, which are soft preferences, and which must function as hard or quasi-hard constraints. These examples are not intended as an exhaustive taxonomy: different domains and deployment settings may activate different objective dimensions and different conflict-resolution procedures. Our framework models AI behavior as a context-dependent choice rule over candidate actions, objective estimates, active constraints, stakeholders, uncertainty, and conflict-resolution procedures. We outline an implementation pathway based on decomposed objective representations, context-to-objective routing, hierarchical constraints, deliberative policy reasoning, controlled personalization, tool-use control, diagnostic evaluation, auditing, and post-deployment revision. --- ### From Data Lifting to Continuous Risk Estimation: A Process-Aware Pipeline for Predictive Monitoring of Clinical Pathways Authors: Pasquale Ardimento, Mario Luca Bernardi, Marta Cimitile, Samuele Latorre Published: 2026-05-05 Categories: cs.LG, cs.SE arXiv: https://arxiv.org/abs/2605.03895v2 This paper presents a reproducible and process-aware pipeline for predictive monitoring of clinical pathways. The approach integrates data lifting, temporal reconstruction, event log construction, prefix-based representations, and predictive modeling to support continuous reasoning on partially observed patient trajectories, overcoming the limitations of traditional retrospective process mining. The framework is evaluated on COVID-19 clinical pathways using ICU admission as the prediction target, considering 4,479 patient cases and 46,804 prefixes. Predictive models are trained and evaluated using a case-level split, with 896 patients in the test set. Logistic Regression achieves the best performance (AUC 0.906, F1-score 0.835). A detailed prefix-based analysis shows that predictive performance improves progressively as new clinical events become available, with AUC increasing from 0.642 at early stages to 0.942 at later stages of the pathway. The results highlight two key findings: predictive signals emerge progressively along clinical pathways, and process-aware representations enable effective early risk estimation from evolving patient trajectories. Overall, the findings suggest that predictive monitoring in healthcare is best conceived as a continuous, dynamically aware process, in which risk estimates are progressively refined as the patient journey evolves. --- ### Raising the Ceiling: Better Empirical Fixation Densities for Saliency Benchmarking Authors: Susmit Agrawal, Jannis Hollman, Matthias Kümmerer Published: 2026-05-05 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2605.03885v1 Empirical fixation densities, spatial distributions estimated from human eye-tracking data, are foundational to saliency benchmarking. They directly shape benchmark conclusions, leaderboard rankings, failure case analyses, and scientific claims about human visual behavior. Yet the standard estimation method, fixed-bandwidth isotropic Gaussian KDE, has gone essentially unchanged for decades. This matters now more than ever: as the field shifts toward sample-level evaluation (failure case analysis, inverse benchmarking, per-image model comparison), reliable per-image density estimates become critical. We propose a principled mixture model that combines an adaptive-bandwidth KDE based on Abramson's method, center bias and uniform components, and a state-of-the-art saliency model, to capture different spatial and semantic types of interobserver consistency, and optimize all parameters per image via leave-one-subject-out cross-validation. Our method yields substantially higher interobserver consistency estimates across multiple benchmarks, with median per-image gains of 5-15% in log-likelihood and up to 2 percentage points in AUC. For the most affected images -- precisely those most relevant to failure case analysis -- improvements exceed 25%. We leverage these improved estimates to identify and analyze remaining failure cases of state-of-the-art saliency models, demonstrating that significant headroom for model improvement remains. More broadly, our findings highlight that empirical fixation densities should not be treated as fixed ground truths but as evolving estimates that improve with better methodology. --- ### QKVShare: Quantized KV-Cache Handoff for Multi-Agent On-Device LLMs Authors: Pratik Honavar, Tejpratap GVSL Published: 2026-05-05 Categories: cs.AI, cs.MA arXiv: https://arxiv.org/abs/2605.03884v1 Multi-agent LLM systems on edge devices need to hand off latent context efficiently, but the practical choices today are expensive re-prefill or full-precision KV transfer. We study QKVShare, a framework for quantized KV-cache handoff between agents that combines token-level mixed-precision allocation, a self-contained CacheCard representation, and a HuggingFace-compatible cache injection path. Our current results support a narrower but clearer story than the original draft: on 150 GSM8K problems with Llama-3.1-8B-Instruct, adaptive quantization remains competitive under repeated handoff and shows its clearest gains against uniform quantization in deeper-hop, higher budget settings; for handoff latency, the QKVShare path reduces TTFT relative to full re prefill at every tested context, from 130.7 ms vs. 150.2 ms at nominal 1K context to 397.1 ms vs. 1029.7 ms at nominal 8K context;. Stage timing shows that post-injection generation, not card creation, dominates the current QKVShare latency path. These results position quantized KV handoff as a promising on-device systems direction while also highlighting the need for stronger controller ablations and apples-to-apples runtime comparisons. --- ### Deco: Extending Cherished Physical Objects into AI Companion Agents through Dual Embodiment Authors: Zhihan Jiang, Mengyuan Millie Wu, Ruishi Zou, Shiyu Xu, Xun Qian, Emma Macmanus, Steven Liao, Ping Zhang, Bingsheng Yao, Tingyu Cheng, James L. David, Nabila El-Bassel et al. Published: 2026-05-05 Categories: cs.HC, cs.AI, cs.CY arXiv: https://arxiv.org/abs/2605.03882v2 Physical objects (e.g., plush toys) can transcend materiality to become emotional anchors and provide companionship. However, these bonds remain one-sided because most physical objects cannot reciprocate. AI companions offer responsiveness and personalization, but typically entail building bonds from scratch. We investigated how AI companions might inherit and extend users' existing bonds with physical objects. A formative study (N=9) informed four design principles (Faithful Identity, Calibrated Agency, Ambient Presence, Reciprocal Memory), shaping our Dual-Embodiment Companion Framework. We instantiated it as Deco to create digital embodiments of physical companions. In a within-subjects lab study (N=25), Deco was rated higher than a personalized digital-only companion on six companion-related measures (all p<.01). A subsequent seven-day field deployment (N=17) showed sustained engagement, higher post-deployment well-being (p=.040), and three key relational patterns: digital activities retroactively vitalized physical objects, bond deepening centered on emotional engagement depth, and participants sustained bonds while navigating companions' AI nature. Dual embodiment offers a promising framework for revitalizing physical objects with AI agents. --- ### Deco: Extending Personal Physical Objects into Pervasive AI Companion through a Dual-Embodiment Framework Authors: Zhihan Jiang, Mengyuan Millie Wu, Ruishi Zou, Shiyu Xu, Xun Qian, Emma Macmanus, Steven Liao, Ping Zhang, Bingsheng Yao, Tingyu Cheng, James L. David, Nabila El-Bassel et al. Published: 2026-05-05 Categories: cs.HC, cs.AI, cs.CY arXiv: https://arxiv.org/abs/2605.03882v1 Individuals frequently form deep attachments to physical objects (e.g., plush toys) that usually cannot sense or respond to their emotions. While AI companions offer responsiveness and personalization, they exist independently of these physical objects and lack an ongoing connection to them. To bridge this gap, we conducted a formative study (N=9) to explore how digital agents could inherit and extend the emotional bond, deriving four design principles (Faithful Identity, Calibrated Agency, Ambient Presence, and Reciprocal Memory). We then present the Dual-Embodiment Companion Framework, instantiated as Deco, a mobile system integrating multimodal Large Language Models (LLMs) and Augmented Reality to create synchronized digital embodiments of users' physical companions. A within-subjects study (N=25) showed Deco significantly outperformed a personalized LLM-empowered digital companion baseline on perceived companionship, emotional bond, and design-principle scales (all p<0.01). A seven-day field deployment (N=17) showed sustained engagement, subjective well-being improvement (p=.040), and three key relational patterns: digital activities retroactively vitalized physical objects, bond deepening was driven by emotional engagement depth rather than interaction frequency, and users sustained bonds while actively navigating digital companions' AI nature. This work highlights a promising alternative for designing digital companions: moving from creating new relationships to dual embodiment, where digital agents seamlessly extend the emotional history of physical objects. --- ### DMGD: Train-Free Dataset Distillation with Semantic-Distribution Matching in Diffusion Models Authors: Qichao Wang, Yunhong Lu, Hengyuan Cao, Junyi Zhang, Min Zhang Published: 2026-05-05 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2605.03877v1 Dataset distillation enables efficient training by distilling the information of large-scale datasets into significantly smaller synthetic datasets. Diffusion based paradigms have emerged in recent years, offering novel perspectives for dataset distillation. However, they typically necessitate additional fine-tuning stages, and effective guidance mechanisms remain underexplored. To address these limitations, we rethink diffusion based dataset distillation and propose a Dual Matching Guided Diffusion (DMGD) framework, centered on efficient training-free guidance. We first establish Semantic Matching via conditional likelihood optimization, eliminating the need for auxiliary classifiers. Furthermore, we propose a dynamic guidance mechanism that enhances the diversity of synthetic data while maintaining semantic alignment. Simultaneously, we introduce an optimal transport (OT) based Distribution Matching approach to further align with the target distribution structure. To ensure efficiency, we develop two enhanced strategies for diffusion based framework: Distribution Approximate Matching and Greedy Progressive Matching. These strategies enable effective distribution matching guidance with minimal computational overhead. Experimental results on ImageNet-Woof, ImageNet-Nette, and ImageNet-1K demonstrate that our training-free approach achieves significant improvements, outperforming state-of-the-art (SOTA) methods requiring additional fine-tuning by average accuracy gains of 2.1%, 5.4%, and 2.4%, respectively. --- ### Spatiotemporal Convolutions on EEG signal -- A Representation Learning Perspective on Efficient and Explainable EEG Classification with Convolutional Neural Nets Authors: Laurits Dixen, Stefan Heinrich, Paolo Burelli Published: 2026-05-05 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2605.03874v1 Classification of EEG signals using shallow Convolutional Neural Networks (CNNs) is a prevalent and successful approach across a variety of fields. Most of these models use independent one-dimensional (1D) convolutional layers along the spatial and temporal dimensions, which are concatenated without a non-linear activation layer between. In this paper, we investigate an alternative encoding that operates a bi-dimensional (2D) spatiotemporal convolution. While 2D convolutions are numerically identical to two concatenated 1D convolutions along the two dimensions, the impact on learning is still uncertain. We test 1D and 2D CNNs and a CNN+transformer hybrid model in a low-dimensional (3-channel) and a high-dimensional (22-channel) BCI motor imagery classification task. We observe that 2D convolutions significantly reduce training time in high-dimensional tasks while maintaining performance. We investigate the root of this improvement and find no difference in spectral feature importance. However, a clear pattern emerges in representational similarity across models: 1D and 2D models yield vastly different representational geometries. Overall, we suggest an improved model with a 2D convolutional layer for faster training and inference. We also highlight the importance of architecturally-driven encoding when processing complex multivariate signals, as reflected in internal representations rather than purely in performance metrics. --- ### EvoLM: Self-Evolving Language Models through Co-Evolved Discriminative Rubrics Authors: Shuyue Stella Li, Rui Xin, Teng Xiao, Yike Wang, Rulin Shao, Zoey Hao, Melanie Sclar, Sewoong Oh, Faeze Brahman, Pang Wei Koh, Yulia Tsvetkov Published: 2026-05-05 Categories: cs.AI arXiv: https://arxiv.org/abs/2605.03871v1 Language models encode substantial evaluative knowledge from pretraining, yet current post-training methods rely on external supervision (human annotations, proprietary models, or scalar reward models) to produce reward signals. Each imposes a ceiling. Human judgment cannot supervise capabilities beyond its own, proprietary APIs create dependencies, and verifiable rewards cover only domains with ground-truth answers. Self-improvement from a model's own evaluative capacity is a reward source that scales with the model itself, yet remains largely untapped by current methods. We introduce EVOLM, a post-training method that structures this capacity into explicit discriminative rubrics and uses them as training signal. EVOLM trains two capabilities within a single language model in alternation: (1) a rubric generator producing instance-specific evaluation criteria optimized for discriminative utility, which maximizes a small frozen judge's ability to distinguish preferred from dispreferred responses; and (2) a policy trained using those rubric-conditioned scores as reward. All preference signals are constructed from the policy's own outputs via temporal contrast with earlier checkpoints, requiring no human annotation or external supervision. EVOLM trains a Qwen3-8B model to generate rubrics that outperform GPT-4.1 on RewardBench-2 by 25.7%. The co-trained policy achieves 69.3% average on the OLMo3-Adapt suite, outperforming policies trained with GPT-4.1 prompted rubrics by 3.9% and with the state-of-the-art 8B reward model SkyWork-RM by 16%. Overall, EVOLM demonstrates that structuring a model's evaluative capacity into co-evolving discriminative rubrics enables self-improvement without external supervision. --- ### On Adaptivity in Zeroth-Order Optimization Authors: Hassan Dbouk, Nidham Gazagnadou, Matthias Reisser, Christos Louizos Published: 2026-05-05 Categories: cs.LG, math.OC arXiv: https://arxiv.org/abs/2605.03869v1 We investigate the effectiveness of adaptive zeroth-order (ZO) optimization for memory-constrained fine-tuning of large language models (LLMs). Contrary to prior claims, we show that adaptive ZO methods such as ZO-Adam offer no convergence advantage over well-tuned ZO-SGD, while incurring significant memory overhead. Our analysis reveals that in high dimensions, ZO gradients lack coordinate-wise heterogeneity, rendering adaptive mechanisms memory inefficient. Leveraging this insight, we propose MEAZO, a memory-efficient adaptive ZO optimizer that tracks only a single scalar for global step size adaptation. We support our method with theoretical convergence guarantees under standard assumptions. Experiments across multiple LLM families and tasks demonstrate that MEAZO matches ZO-Adam's performance with the memory footprint of ZO-SGD. Additional experiments on synthetic quadratic problems and LLM fine-tuning further demonstrate MEAZO's enhanced robustness to step size choices, particularly in grouped or block-structured optimization settings. --- ### Memory-Efficient Continual Learning with CLIP Models Authors: Ryan King, Gang Li, Bobak Mortazavi, Tianbao Yang Published: 2026-05-05 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.03866v1 Contrastive Language-Image Pretraining (CLIP) models excel at understanding image-text relationships but struggle with adapting to new data without forgetting prior knowledge. To address this, models are typically fine-tuned using both new task data and a memory buffer of past tasks. However, CLIP's contrastive loss suffers when the memory buffer is small, leading to performance degradation on previous tasks. We propose a memory-efficient, distributionally robust method that dynamically reweights losses per class during training. Our approach, tested on class incremental settings (CIFAR-100, ImageNet1K) and a domain incremental setting (DomainNet) adapts CLIP models quickly while minimizing catastrophic forgetting, even with minimal memory usage. --- ### Quantifying the human visual exposome with vision language models Authors: Christian Rominger, Andreas R. Schwerdtfeger, Malay Gaherwar Singh, Dimitri Khudyakow, Elizabeth A. M. Michels, Fabian Wolf, Jakob Nikolas Kather, Magdalena Katharina Wekenborg Published: 2026-05-05 Categories: cs.AI, cs.CV arXiv: https://arxiv.org/abs/2605.03863v1 The visual environment is a fundamental yet unquantified determinant of mental health. While the concept of the environmental exposome is well established, current methods rely on coarse geospatial proxies or biased self reports, failing to capture the first person visual context of daily life. We addressed this gap by coupling ecological momentary assessment with vision language models (VLMs) to quantify the semantic richness of human visual experience. Across 2674 participant generated photographs, VLM derived estimates of greenness robustly predicted momentary affect and chronic stress, consistent with established benchmarks. We then developed a semi autonomous large language model (LLM) based pipeline that mined over seven million scientific publications to extract nearly 1000 environmental features empirically linked to mental health. When applied to real world imagery, up to 33 percent of VLM extracted context ratings significantly correlated with affect and stress. These findings establish a scalable objective paradigm for visual exposomics, enabling high throughput decoding of how the visible world is associated with mental health. --- ### Correct Is Not Enough: Training Reasoning Planners with Executor-Grounded Rewards Authors: Tianyang Han, Hengyu Shi, Junjie Hu, Xu Yang, Zhiling Wang, Junhao Su Published: 2026-05-05 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2605.03862v4 Reinforcement learning with verifiable rewards has become a common way to improve explicit reasoning in large language models, but final-answer correctness alone does not reveal whether the reasoning trace is faithful, reliable, or useful to the model that consumes it. This outcome-only signal can reinforce traces that are right for the wrong reasons, overstate reasoning gains by rewarding shortcuts, and propagate flawed intermediate states in multi-step systems. To this end, we propose TraceLift, a planner-executor training framework that treats reasoning as a consumable intermediate artifact. During planner training, the planner emits tagged reasoning. A frozen executor turns this reasoning into the final artifact for verifier feedback, while an executor-grounded reward shapes the intermediate trace. This reward multiplies a rubric-based Reasoning Reward Model (RM) score by measured uplift on the same frozen executor, crediting traces that are both high-quality and useful. To make reasoning quality directly learnable, we introduce TRACELIFT-GROUPS, a rubric-annotated reason-only dataset built from math and code seed problems. Each example is a same-problem group containing a high-quality reference trace and multiple plausible flawed traces with localized perturbations that reduce reasoning quality or solution support while preserving task relevance. Extensive experiments on code and math benchmarks show that this executor-grounded reasoning reward improves the two-stage planner-executor system over execution-only training, suggesting that reasoning supervision should evaluate not only whether a trace looks good, but also whether it helps the model that consumes it. Our code is available at: https://github.com/MasaiahHan/TraceLift --- ### MCJudgeBench: A Benchmark for Constraint-Level Judge Evaluation in Multi-Constraint Instruction Following Authors: Jaeyun Lee, Junyoung Koh, Zeynel Tok, Hunar Batra, Ronald Clark Published: 2026-05-05 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2605.03858v1 Multi-constraint instruction following requires verifying whether a response satisfies multiple individual requirements, yet LLM judges are often assessed only through overall-response judgments. We introduce MCJudgeBench, a benchmark for constraint-level judge evaluation in multi-constraint instruction following. Each instance includes an instruction, a candidate response, an explicit constraint list, per-constraint gold labels in {yes, partial, no}, and controlled response-side perturbations. The evaluation protocol further includes evaluation prompt variants to test judge stability. We evaluate proprietary and open-source LLM judges using both correctness and inconsistency metrics, distinguishing intrinsic inconsistency under stochastic decoding from procedural inconsistency under prompt and response perturbations. Our results show that judge reliability has multiple dimensions: strong overall performance does not guarantee equally reliable detection across label categories, especially for rarer partial and no cases. Judges with higher correctness do not always have lower inconsistency. Evaluation with reasoning improves correctness but does not uniformly improve stability. These findings motivate evaluating LLM judges at the constraint level to study these failure modes. --- ### A Deeper Dive into the Irreversibility of PolyProtect: Making Protected Face Templates Harder to Invert Authors: Vedrana Krivokuća Hahn, Jérémy Maceiras, Sébastien Marcel Published: 2026-05-05 Categories: cs.CV, cs.CR arXiv: https://arxiv.org/abs/2605.03857v1 This work presents a deeper analysis of the "irreversibility" property of PolyProtect, a biometric template protection method initially proposed for securing face embeddings. PolyProtect transforms embeddings into protected templates via multivariate polynomials, whose coefficients and exponents are distinct for each subject enrolled in the face recognition system. A polynomial is applied to consecutive sets of elements from a given embedding, where the amount of overlap between the sets is a tunable parameter. We begin our irreversibility analysis by demonstrating that PolyProtected templates are easier to invert using a numerical solver based on cosine distance, as opposed to Euclidean distance (used in the earlier PolyProtect work). To make this inversion more difficult, we then propose a "key selection algorithm", which tries to choose "keys" (coefficients and exponents of the PolyProtect polynomial) that enhance the irreversibility of PolyProtected templates, compared to when the keys are purely random. Our experiments show that this algorithm is effective at generating PolyProtected templates that are significantly more difficult to invert, and that it approximately equalises the irreversibility of PolyProtected templates generated using different "overlap" parameters. This allows for better control of the irreversibility versus accuracy trade-off, known to exist across different overlaps. We also show that accuracy in the PolyProtected domain can be affected by the range in which the embedding elements lie, but that this can be improved by normalizing the embeddings prior to applying PolyProtect. This work is reproducible using our open-source code. --- ### Stream-R1: Reliability-Perplexity Aware Reward Distillation for Streaming Video Generation Authors: Bin Wu, Mengqi Huang, Shaojin Wu, Weinan Jia, Yuxin Wang, Zhendong Mao, Yongdong Zhang Published: 2026-05-05 Categories: cs.CV arXiv: https://arxiv.org/abs/2605.03849v1 Distillation-based acceleration has become foundational for making autoregressive streaming video diffusion models practical, with distribution matching distillation (DMD) as the de facto choice. Existing methods, however, train the student to match the teacher's output indiscriminately, treating every rollout, frame, and pixel as equally reliable supervision. We argue that this caps distilled quality, since it overlooks two complementary axes of variance in DMD supervision: Inter-Reliability across student rollouts whose supervision varies in reliability, and Intra-Perplexity across spatial regions and temporal frames that contribute unequally to where quality can still be improved. The objective thus conflates two questions under a uniform weight: whether to learn from each rollout, and where to concentrate optimization within it. To address this, we propose Stream-R1, a Reliability-Perplexity Aware Reward Distillation framework that adaptively reweights the distillation objective at both rollout and spatiotemporal-element levels through a single shared reward-guided mechanism. At the Inter-Reliability level, Stream-R1 rescales each rollout's loss by an exponential of a pretrained video reward score, so that rollouts with reliable supervision dominate optimization. At the Intra-Perplexity level, it back-propagates the same reward model to extract per-pixel gradient saliency, which is factored into spatial and temporal weights that concentrate optimization pressure on regions and frames where refinement yields the largest expected gain. An adaptive balancing mechanism prevents any single quality axis from dominating across visual quality, motion quality, and text alignment. Stream-R1 attains consistent improvements on all three dimensions over distillation baselines on standard streaming video generation benchmarks, without architectural modification or additional inference cost. --- ### Parameter-Efficient Multi-View Proficiency Estimation: From Discriminative Classification to Generative Feedback Authors: Edoardo Bianchi, Antonio Liotta Published: 2026-05-05 Categories: cs.CV arXiv: https://arxiv.org/abs/2605.03848v1 Estimating how well a person performs an action, rather than which action is performed, is central to coaching, rehabilitation, and talent identification. This task is challenging because proficiency is encoded in subtle differences in timing, balance, body mechanics, and execution, often distributed across multiple views and short temporal events. We discuss three recent contributions to multi-view proficiency estimation on Ego-Exo4D. SkillFormer introduces a parameter-efficient discriminative architecture for selective multi-view fusion; PATS improves temporal sampling by preserving locally dense excerpts of fundamental movements; and ProfVLM reformulates proficiency estimation as conditional language generation, producing both a proficiency label and expert-style feedback through a gated cross-view projector and a compact language backbone. Together, these methods achieve state-of-the-art accuracy on Ego-Exo4D with up to 20x fewer trainable parameters and up to 3x fewer training epochs than video-transformer baselines, while moving from closed-set classification toward interpretable feedback generation. These results highlight a shift toward efficient, multi-view systems that combine selective fusion, proficiency-aware sampling, and actionable generative feedback. --- ### Mechanical Conscience: A Mathematical Framework for Dependability of Machine Intelligence Authors: Munkhdelgerekh Batzorig, Purevbaatar Ganbold, Kyungbin Park, Pilkong Jeong, Kangbin Yim Published: 2026-05-05 Categories: cs.AI arXiv: https://arxiv.org/abs/2605.03847v3 Distributed collaborative intelligence (DCI), encompassing edge-to-edge architectures, federated learning, transfer learning, and swarm systems, creates environments in which emergent risk is structurally unavoidable: locally correct decisions by individual agents compose into globally unacceptable behavioral trajectories under uncertainty. Existing approaches such as constrained optimization, safe reinforcement learning, and runtime assurance evaluate acceptability at the level of individual actions rather than across behavioral trajectories, and none addresses the multi-participant, uncertainty-laden nature of DCI deployments. This paper introduces mechanical conscience (MC), a novel concept and simplified mathematical framework that operationalizes trajectory-level normative regulation for both single-agent and distributed intelligent systems. Mechanical conscience is defined as a supervisory filter that minimally corrects a baseline policy's actions to reduce cumulative deviation from a normatively admissible region, while accounting for epistemic uncertainty. We introduce associated constructs, conscience score, mechanical guilt, and resonant dependability, that provide an interpretable vocabulary and computable governance signals for this emerging field. Core theoretical properties are established: admissibility equivalence, existence of optimal regulation, and monotonic deviation reduction. Illustrative results demonstrate that MC-regulated agents maintain trajectory-level normative acceptability where conventional controllers drift outside admissible bounds, and that the framework naturally extends to suppress interaction-induced emergent risk in multi-agent DCI settings. --- ### SOAR: Real-Time Joint Optimization of Order Allocation and Robot Scheduling in Robotic Mobile Fulfillment Systems Authors: Yibang Tang, Yifan Yang, Jingyuan Wang, Junhua Chen, Zhen Zhao Published: 2026-05-05 Categories: cs.AI, cs.RO arXiv: https://arxiv.org/abs/2605.03842v1 Robotic Mobile Fulfillment Systems (RMFS) rely on mobile robots for automated inventory transportation, coordinating order allocation and robot scheduling to enhance warehousing efficiency. However, optimizing RMFS is challenging due to strict real-time constraints and the strong coupling of multi-phase decisions. Existing methods either decompose the problem into isolated sub-tasks to guarantee responsiveness at the cost of global optimality, or rely on computationally expensive global optimization models that are unsuitable for dynamic industrial environments. To bridge this gap, we propose SOAR, a unified Deep Reinforcement Learning framework for real-time joint optimization. SOAR transforms order allocation and robot scheduling into a unified process by utilizing soft order allocations as observations. We formulate this as an Event-Driven Markov Decision Process, enabling the agent to perform simultaneous scheduling in response to asynchronous system events. Technically, we employ a Heterogeneous Graph Transformer to encode the warehouse state and integrate phased domain knowledge. Additionally, we incorporate a reward shaping strategy to address sparse feedback in long-horizon tasks. Extensive experiments on synthetic and real-world industrial datasets, in collaboration with Geekplus, demonstrate that SOAR reduces global makespan by 7.5\% and average order completion time by 15.4\% with sub-100ms latency. Furthermore, sim-to-real deployment confirms its practical viability and significant performance gains in production environments. The code is available at https://github.com/200815147/SOAR. --- ### Complex Equation Learner: Rational Symbolic Regression with Gradient Descent in Complex Domain Authors: Sergei Garmaev, Maurice Gauché, Olga Fink Published: 2026-05-05 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.03841v1 Symbolic regression aims to discover interpretable equations from data, yet modern gradient-based methods fail for operators that introduce singularities or domain constraints, including division, logarithms, and square roots. As a result, Equation Learner-type models typically avoid these operators or impose restrictions, e.g. constraining denominators to prevent poles, which narrows the hypothesis class. We propose a complex weight extension of the Equation Learner that mitigates real-valued optimization pathologies by allowing optimization trajectories to bypass real-axis degeneracies. The proposed approach converges stably even when the target expression has real-domain poles, and it enables unconstrained use of operations such as logarithm and square root. We Validate the method on symbolic regression benchmarks and show it can recover singular behavior from experimental frequency response data. --- ### On Computing Total Variation Distance Between Mixtures of Product Distributions Authors: Weiming Feng, Yucheng Fu, Minji Yang, Anqi Zhang Published: 2026-05-05 Categories: cs.DS, cs.LG, math.PR arXiv: https://arxiv.org/abs/2605.03839v1 We study the problem of approximating the total variation distance between two mixtures of product distributions over an $n$-dimensional discrete domain. Given two mixtures $\mathbb{P}$ and $\mathbb{Q}$ with $k_1$ and $k_2$ product distributions over $(q)^n$, respectively, we give a randomized algorithm that approximates $d_{\mathrm{TV}}\left({\mathbb{P}},{\mathbb{Q}}\right)$ within a multiplicative error of $(1\pm \varepsilon)$ in time $\mathrm{poly}((nq)^{k_1+k_2},1/\varepsilon)$. We also study the special case of mixtures of Boolean subcubes over $\{0,1\}^n$. For this class, we give a deterministic algorithm that exactly computes the total variation distance in time $\mathrm{poly}(n,2^{O(k_1+k_2)})$, and show that exact computation is $\#\mathsf{P}$-hard when $k_1+k_2=Θ(n)$. --- ### TRACE: A Metrologically-Grounded Engineering Framework for Trustworthy Agentic AI Systems in Operationally Critical Domains Authors: Serhii Zabolotnii Published: 2026-05-05 Categories: cs.CL, cs.AI, cs.HC arXiv: https://arxiv.org/abs/2605.03838v1 We introduce TRACE, a cross-domain engineering framework for trustworthy agentic AI in operationally critical domains. TRACE combines a four-layer reference architecture with an explicit classical-ML vs. LLM-validator split (L2a/L2b), a stateful orchestration-and-escalation policy (L3), and bounded human supervision (L4); a metrologically grounded trust-metric suite mapped to GUM/VIM/ISO 17025; and a Model-Parsimony principle quantified by the Computational Parsimony Ratio (CPR). Three instantiations--clinical decision support, industrial multi-domain operations, and a judicial AI assistant--transfer the samearchitecture and metrics across principally different governance contexts. The L2a/L2b separation makes the use of large language models a deliberate design decision rather than an architectural default, with parsimony quantified through CPR. TRACE introduces CPR as a first-class design principle in trustworthy-AI engineering. --- ### Conditions for well-posed color recovery in scattering media Authors: Grigory Solomatov, Derya Akkaynak Published: 2026-05-05 Categories: cs.CV arXiv: https://arxiv.org/abs/2605.03837v1 Recovering scene color from images captured in scattering media is a fundamental inverse problem in optical imaging. Yet the problem is intrinsically ill-posed as multiple solutions can explain the same observation, and prediction error cannot be controlled without understanding the space of candidate solutions. Here, we present sufficient conditions under which color recovery in a scattering medium becomes well-posed. Observing that ill-posedness stems from (i) projection of spectral signals onto pixel intensities, and (ii) unknown medium parameters, we demonstrate that sensor improvements alone cannot resolve medium-induced distortions without additional constraints. We identify recovery patterns, cross-pixel relationships that naturally occur in images, and prove, for an ideal hyperspectral camera, that they restrict the solution to a unique candidate. This opens the door to a new class of vision algorithms grounded in first principles, enabling quantitative analysis of images in scattering environments. --- ### A Domain Incremental Continual Learning Benchmark for ICU Time Series Model Transportability Authors: Ryan King, Conrad Krueger, Ethan Veselka, Tianbao Yang, Bobak J. Mortazavi Published: 2026-05-05 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.03832v1 In recent years, machine learning has made significant progress in clinical outcome prediction, demonstrating increasingly accurate results. However, the substantial resources required for hospitals to train these models, such as data collection, labeling, and computational power, limit the feasibility for smaller hospitals to develop their own models. An alternative approach involves transferring a machine learning model trained by a large hospital to smaller hospitals, allowing them to fine-tune the model on their specific patient data. However, these models are often trained and validated on data from a single hospital, raising concerns about their generalizability to new data. Our research shows that there are notable differences in measurement distributions and frequencies across various regions in the United States. To address this, we propose a benchmark that tests a machine learning model's ability to transfer from a source domain to different regions across the country. This benchmark assesses a model's capacity to learn meaningful information about each new domain while retaining key features from the original domain. Using this benchmark, we frame the transfer of a machine learning model from one region to another as a domain incremental learning problem. While the task of patient outcome prediction remains the same, the input data distribution varies, necessitating a model that can effectively manage these shifts. We evaluate two popular domain incremental learning methods: data replay, which stores examples from previous data sources for fine-tuning on the current source, and Elastic Weight Consolidation (EWC), a model parameter regularization method that maintains features important for both data sources. --- ### Identity-Consistent Multi-Pose Generation of Contactless Fingerprints Authors: Zhiyu Pan, Xiongjun Guan, Jianjiang Feng, Jie Zhou Published: 2026-05-05 Categories: cs.CV arXiv: https://arxiv.org/abs/2605.03830v1 Contactless fingerprint recognition has gained increasing attention due to its advantages in hygiene and acquisition flexibility. However, the absence of physical contact constraints introduces severe nonlinear geometric distortions caused by free finger poses in 3D space, resulting in a substantial cross-modal domain gap between contactless and conventional contact-based fingerprints. Existing solutions largely rely on explicit geometric correction or image enhancement, which are fragile under extreme pose variations. In this paper, we propose Identity-Consistent Multi-Pose Generation of Contactless Fingerprints (IMPOSE), a physics-inspired framework that synthesizes identity-preserving, multi-pose contactless fingerprint samples to empower recognition models. IMPOSE consists of three stages: (1) rolled fingerprint identity generation via latent diffusion with discrete codebook representations, (2) cross-modal translation from rolled to contactless modality guided by Sauvola-based local adaptive binarization as an identity anchor, and (3) physics-based multi-pose simulation through 3D finger model texture mapping and projection. The generated samples maintain strict identity consistency at the ridge topology level and spatial alignment with standard fingerprint coordinate space. Extensive experiments on the UWA and PolyU CL2CB databases demonstrate that fine-tuning fixed-length dense descriptors (FDD) with IMPOSE-synthesized data achieves state-of-the-art cross-modal matching, reducing EER to 8.74% on UWA and 2.26% on PolyU CL2CB. Synthetic data also yields consistent gains across mainstream representations including DeepPrint and AFRNet, and the hybrid strategy combining synthetic and real data achieves the best overall results. The code and generated samples are available at https://github.com/Yu-Yy/IMPOSE. --- ### Reproducing Complex Set-Compositional Information Retrieval Authors: Vincent Degenhart, Dewi Timman, Arjen P. de Vries, Faegheh Hasibi, Mohanna Hoveyda Published: 2026-05-05 Categories: cs.CL, cs.IR arXiv: https://arxiv.org/abs/2605.03824v1 Complex information needs may involve set-compositional queries using conjunction, disjunction, and exclusion, yet it remains unclear whether current retrieval paradigms genuinely satisfy such constraints or exploit `semantic shortcuts'. We conduct a reproducibility study to benchmark major retrieval families and reasoning-targeted methods on QUEST and QUEST+Variants, and introduce LIMIT+, a controlled benchmark where relevance depends on arbitrary attribute predicates and constraint satisfaction, and less on pretrained knowledge. Our findings show that (i) on QUEST, the best neural retrievers achieve an effectiveness that is more than double what can be achieved with BM25 (Recall@100 ${>}$0.41 vs.\ 0.20), but reasoning-targeted methods like ReasonIR and Search-R1 do not outperform general-purpose retrievers uniformly; (ii) on LIMIT+, gains fail to transfer, where the strongest QUEST method collapses from Recall@100${\approx}$0.42 to below 0.02, while classic lexical retrieval gains to ${\sim}$0.96. Lastly, (iii) stratifying by compositional depth reveals a consistent degradation across all methods, where algebraic sparse and lexical methods show more stable performance while dense approaches collapse. We release code and LIMIT+ data generation scripts to support future reproducibility and controlled evaluation. --- ### Realizable Bayes-Consistency for General Metric Losses Authors: Dan Tsir Cohen, Steve Hanneke, Aryeh Kontorovich Published: 2026-05-05 Categories: cs.LG, cs.IT, math.ST arXiv: https://arxiv.org/abs/2605.03823v3 We study strong universal Bayes-consistency in the realizable setting for learning with general metric losses, extending classical characterizations beyond $0$-$1$ classification (Bousquet et al., 2020; Hanneke et al., 2021) and real-valued regression (Attias et al., 2024). Given an instance space $(X,ρ)$, a label space $(Y,\ell)$ with possibly unbounded loss, and a hypothesis class $H \subseteq Y^{X}$, we resolve the realizable case of an open problem presented in Tsir Cohen and Kontorovich (2022). Specifically, we find the necessary and sufficient conditions on the hypothesis class $H$ under which there exists a distribution-free learning rule whose risk converges almost surely to the best-in-class risk (which is zero) for every realizable data-generating distribution. Our main contribution is this sharp characterization in terms of a combinatorial obstruction: Similarly to Attias et al. (2024), we introduce the notion of an infinite non-decreasing $(γ_k)$-Littlestone tree, where $γ_k \to \infty$. This extends the Littlestone tree structure used in Bousquet et al. (2020) to the metric loss setting. --- ### RoboAlign-R1: Distilled Multimodal Reward Alignment for Robot Video World Models Authors: Hao Wu, Yuqi Li, Yuan Gao, Fan Xu, Fan Zhang, Kun Wang, Penghao Zhao, Qiufeng Wang, Yizhou Zhao, Weiyan Wang, Yingli Tian, Xian Wu et al. Published: 2026-05-05 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2605.03821v2 Existing robot video world models are typically trained with low-level objectives such as reconstruction and perceptual similarity, which are poorly aligned with the capabilities that matter most for robot decision making, including instruction following, manipulation success, and physical plausibility. They also suffer from error accumulation in long-horizon autoregressive prediction. We present RoboAlign-R1, a framework that combines reward-aligned post-training with stabilized long-horizon inference for robot video world models. We construct RobotWorldBench, a benchmark of 10,000 annotated video-instruction pairs collected from four robot data sources, and train a multimodal teacher judge, RoboAlign-Judge, to provide fine-grained six-dimensional evaluation of generated videos. We then distill the teacher into a lightweight student reward model for efficient reinforcement-learning-based post-training. To reduce long-horizon rollout drift, we further introduce Sliding Window Re-encoding (SWR), a training-free inference strategy that periodically refreshes the generation context. Under our in-domain evaluation protocol, RoboAlign-R1 improves the aggregate six-dimension score by 10.1% over the strongest baseline, including gains of 7.5% on Manipulation Accuracy and 4.6% on Instruction Following; these ranking improvements are further supported by an external VLM-based cross-check and a blinded human study. Meanwhile, SWR improves long-horizon prediction quality with only about 1% additional latency, yielding a 2.8% gain in SSIM and a 9.8% reduction in LPIPS. Together, these results show that reward-aligned post-training and stabilized long-horizon decoding improve task consistency, physical realism, and long-horizon prediction quality in robot video world models. --- ### RoboAlign-R1: Distilled Multimodal Reward Alignment for Robot Video World Models Authors: Hao Wu, Yuqi Li, Yuan Gao, Fan Xu, Fan Zhang, Kun Wang, Penghao Zhao, Qiufeng Wang, Yizhou Zhao, Weiyan Wang, Yingli Tian, Xian Wu et al. Published: 2026-05-05 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2605.03821v1 Existing robot video world models are typically trained with low-level objectives such as reconstruction and perceptual similarity, which are poorly aligned with the capabilities that matter most for robot decision making, including instruction following, manipulation success, and physical plausibility. They also suffer from error accumulation in long-horizon autoregressive prediction. We present RoboAlign-R1, a framework that combines reward-aligned post-training with stabilized long-horizon inference for robot video world models. We construct RobotWorldBench, a benchmark of 10,000 annotated video-instruction pairs collected from four robot data sources, and train a multimodal teacher judge, RoboAlign-Judge, to provide fine-grained six-dimensional evaluation of generated videos. We then distill the teacher into a lightweight student reward model for efficient reinforcement-learning-based post-training. To reduce long-horizon rollout drift, we further introduce Sliding Window Re-encoding (SWR), a training-free inference strategy that periodically refreshes the generation context. Under our in-domain evaluation protocol, RoboAlign-R1 improves the aggregate six-dimension score by 10.1% over the strongest baseline, including gains of 7.5% on Manipulation Accuracy and 4.6% on Instruction Following; these ranking improvements are further supported by an external VLM-based cross-check and a blinded human study. Meanwhile, SWR improves long-horizon prediction quality with only about 1% additional latency, yielding a 2.8% gain in SSIM and a 9.8% reduction in LPIPS. Together, these results show that reward-aligned post-training and stabilized long-horizon decoding improve task consistency, physical realism, and long-horizon prediction quality in robot video world models. --- ### Multimodal Learning on Low-Quality Data with Conformal Predictive Self-Calibration Authors: Xun Jiang, Yufan Gu, Disen Hu, Yuqing Hou, Yazhou Yao, Fumin Shen, Heng Tao Shen, Xing Xu Published: 2026-05-05 Categories: cs.CV, cs.LG, cs.MM arXiv: https://arxiv.org/abs/2605.03820v1 Multimodal learning often grapples with the challenge of low-quality data, which predominantly manifests as two facets: modality imbalance and noisy corruption. While these issues are often studied in isolation, we argue that they share a common root in the predictive uncertainty towards the reliability of individual modalities and instances during learning. In this paper, we propose a unified framework, termed Conformal Predictive Self-Calibration (CPSC), which leverages conformal prediction to equip the model with the ability to perform self-guided calibration on-the-fly. The core of our proposed CPSC lies in a novel self-calibrating training loop that seamlessly integrates two key modules: (1) Representation Self-Calibration, which decomposes unimodal features into components, and selectively fuses the most robust ones identified by a conformal predictor to enhance feature resilience. (2) Gradient Self-Calibration, which recalibrates the gradient flow during backpropagation based on instance-wise reliability scores, steering the optimization towards more trustworthy directions. Furthermore, we also devise a self-update strategy for the conformal predictor to ensure the entire system co-evolves consistently throughout the training process. Extensive experiments on six benchmark datasets under both imbalanced and noisy settings demonstrate that our CPSC framework consistently outperforms existing state-of-the-art methods. Our code is available at https://github.com/XunCHN/CPSC. --- ### The Manokhin Probability Matrix: A Diagnostic Framework for Classifier Probability Quality Authors: Valery Manokhin Published: 2026-05-05 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2605.03816v1 The Brier score conflates two distinct properties of probabilistic predictions: reliability (calibration error) and resolution (discriminatory power). We introduce the Manokhin Probability Matrix, a BCG-style two-dimensional diagnostic framework that separates them. Classifiers are placed on a 2x2 grid by Spiegelhalter Z-statistic and AUC-ROC expected rank, then assigned to one of four archetypes: Eagle (good on both axes), Bull (strong discrimination, poor calibration), Sloth (well-calibrated, weak discriminator), and Mole (poor on both). Each archetype carries a distinct prescription. We populate the matrix from a large-scale empirical study spanning 21 classifiers, 5 post-hoc calibrators, and 30 real-world binary classification tasks from the TabArena-v0.1 suite. The assignment is unambiguous. CatBoost, TabICL, EBM, TabPFN, GBC, and Random Forest are Eagles. XGBoost, LightGBM, and HGB are Bulls; Venn-Abers calibration cuts log-loss by 6.5 to 12.6% on Bulls but degrades Eagles by 2.1%. SVM, LR, LDA, and the empirical base-rate predictor are Sloths. MLP, KNN, Naive Bayes, and ExtraTrees are Moles. A theoretical asymmetry follows: no order-preserving post-hoc calibrator can add discriminatory power (Proposition 1), so calibration is the fixable part and discrimination is the hard part. The practical rule is direct: do not optimise aggregate Brier score without first decomposing it; optimise discrimination first, then fix calibration post-hoc. Code and raw experimental data are available at https://github.com/valeman/classifier_calibration. --- ### Agentic-imodels: Evolving agentic interpretability tools via autoresearch Authors: Chandan Singh, Yan Shuo Tan, Weijia Xu, Zelalem Gero, Weiwei Yang, Michel Galley, Jianfeng Gao Published: 2026-05-05 Categories: cs.AI, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2605.03808v1 Agentic data science (ADS) systems are rapidly improving their capability to autonomously analyze, fit, and interpret data, potentially moving towards a future where agents conduct the vast majority of data-science work. However, current ADS systems use statistical tools designed to be interpretable by humans, rather than interpretable by agents. To address this, we introduce Agentic-imodels, an agentic autoresearch loop that evolves data-science tools designed to be interpretable by agents. Specifically, it develops a library of scikit-learn-compatible regressors for tabular data that are optimized for both predictive performance and a novel LLM-based interpretability metric. The metric measures a suite of LLM-graded tests that probe whether a fitted model's string representation is "simulatable" by an LLM, i.e. whether the LLM can answer questions about the model's behavior by reading its string output alone. We find that the evolved models jointly improve predictive performance and agent-facing interpretability, generalizing to new datasets and new interpretability tests. Furthermore, these evolved models improve downstream end-to-end ADS, increasing performance for Copilot CLI, Claude Code, and Codex on the BLADE benchmark by up to 73% --- ### ScrapMem: A Bio-inspired Framework for On-device Personalized Agent Memory via Optical Forgetting Authors: Jiale Chang, Yuxiang Ren Published: 2026-05-05 Categories: cs.AI arXiv: https://arxiv.org/abs/2605.03804v2 Long-term personalized memory for LLM agents is challenging on resource-limited edge devices due to high storage costs and multimodal complexity. To address this, we propose ScrapMem, a framework that integrates multimodal data into "Scrapbook Page." ScrapMem introduces Optical Forgetting, an optical compression mechanism that progressively reduces the resolution of older memories, lowering storage cost while suppressing low-value details. To maintain semantic consistency, we construct an Episodic Memory Graph (EM-Graph) that organizes key events into a causal-temporal structure. Extensive experiments on the multimodal ATM-Bench showcase that ScrapMem provides three main benefits: (1) strong performance, achieving a new state-of-the-art with a 51.0% Joint@10 score; (2) high storage efficiency, reducing memory usage by up to 93% via optical forgetting; and (3) improved recall, increasing Recall@10 to 70.3% through structured aggregation. ScrapMem offers an effective and storage-efficient solution for on-device long-term memory in multimodal LLM agents. --- ### Towards accurate extreme event likelihoods from diffusion model climate emulators Authors: Peter Manshausen, Noah Brenowitz, Julius Berner, Karthik Kashinath, Mike Pritchard Published: 2026-05-05 Categories: physics.ao-ph, cs.LG arXiv: https://arxiv.org/abs/2605.03802v1 ML climate model emulators are useful for scenario planning and adaptation, allowing for cost-efficient experimentation. Recently, the diffusion model Climate in a Bottle (cBottle) has been proposed for generation of atmospheric states compatible with boundary conditions of solar position and sea surface temperatures. Crucially, cBottle can be guided to generate extreme events such as Tropical Cyclones (TCs) over locations of interest. Diffusion models such as cBottle work by approximating the probability density of the training data. Here, we show use cases of the probability density estimates of atmospheric states obtained from this climate emulator. Most importantly, these estimates allow us to calculate likelihoods of extreme events under guidance. When guiding the model towards states including TCs, comparing the probability density under the guided and unguided model enables us to quantify how much more likely the guidance has made the TC. We show how these odds ratios allow us to importance-sample from the TC distribution, reducing the standard error of the probability estimate compared to simple Monte Carlo sampling. Furthermore, we discuss results and limitations of the application of model probability densities to extreme event attribution-like experiments. We present these early but encouraging results hoping they will spur more research into probabilistic information that can be gained from diffusion models of the atmosphere. ---