# Research Papers — 2026-05 · bundle page 97 of 326 > Full-text markdown of papers #4801–4850 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/97 [← Previous bundle](https://aipod.dev/papers/archive/2026-05/page/96.md) [Next bundle →](https://aipod.dev/papers/archive/2026-05/page/98.md) ### QUEST: Training Frontier Deep Research Agents with Fully Synthetic Tasks Authors: Jian Xie, Tianhe Lin, Zilu Wang, Yuting Ning, Yuekun Yao, Tianci Xue, Zhehao Zhang, Zhongyang Li, Kai Zhang, Yufan Wu, Shijie Chen, Boyu Gou et al. Published: 2026-05-22 Categories: cs.CL arXiv: https://arxiv.org/abs/2605.24218v1 Deep research agents extend the role of search engines from retrieving keyword-matched pages to synthesizing knowledge, fundamentally changing how humans interact with information. However, frontier systems remain proprietary, while existing open agents often generalize poorly across different task types, leaving unclear how to train a broadly capable deep research agent. We release QUEST, a family of open models (ranging from 2B to 35B) that serve as general-purpose deep research agents designed to handle a wide range of long-horizon search tasks, with strong capabilities in fact seeking, citation grounding, and report synthesis. To build QUEST, we propose an effective training recipe combining mid-training, supervised fine-tuning, and reinforcement learning. Central to this recipe is a curated data synthesis pipeline based on unified rubric trees, which applies to different task types and enables synthesizing training data with verifiable rewards without human annotation. In addition, QUEST incorporates a built-in context management mechanism that enables effective long-horizon reasoning and knowledge synthesis. Using only 8K synthesized tasks, QUEST approaches or even surpasses frontier closed-source agents across eight deep research benchmarks spanning diverse task types, and achieves the best overall performance among recent open-weight agents. We released everything: models, data, and training scripts. --- ### Identifying and Mitigating Systemic Measurement Bias in Production LLM Inference Benchmarks Authors: Ashok Chandrasekar, Jason Kramberger Published: 2026-05-22 Categories: cs.AI, cs.DC arXiv: https://arxiv.org/abs/2605.24217v2 As Large Language Models (LLMs) transition from research environments to production deployments, evaluating their performance against strict Service Level Objectives (SLOs) has become critical. However, current evaluation methodologies suffer from severe measurement bias at scale. We demonstrate that widely used benchmarking utilities rely on single-process, asyncio-driven architectures that introduce fundamental client-side queuing bottlenecks under high concurrency. By modeling the benchmarking client as an $M/G/1$ queue, we mathematically demonstrate how the Python Global Interpreter Lock (GIL) artificially inflates Time to First Token (TTFT) and Time Per Output Token (TPOT) metrics as request rates scale. To resolve this systematic inaccuracy, we propose an unbiased, multi-process evaluation framework that effectively distributes client-side load, ensuring negligible queuing overhead. Furthermore, we formalize a composite metric, Normalized Time Per Output Token (NTPOT), to robustly amortize end-to-end latency, including prefill and scheduling delays across sequence lengths. Our empirical evaluation demonstrates that this methodology successfully isolates pure serving engine performance, enabling accurate, reproducible profiling of LLMs at production scales exceeding thousands of queries per second. --- ### Agent-ToM: Learning to Monitor Autonomous LLM Agents via Theory-of-Mind Reasoning Authors: Nesreen K. Ahmed, Nima Nafisi Published: 2026-05-22 Categories: cs.LG, cs.AI, cs.CL, cs.CR arXiv: https://arxiv.org/abs/2605.24216v1 Monitoring autonomous large language model (LLM) agents for covert malicious behavior is challenging due to delayed, context-dependent, and long-horizon attack patterns. Agents may pursue hidden objectives while maintaining superficially benign behavior, making detection difficult even with full trajectory access. Prior monitoring approaches improve scaffolding or ensemble aggregation, but treat each trajectory independently and do not learn from prior monitoring experience. Moreover, standard reasoning methods explain observed behavior without explicitly reasoning about agent beliefs, intentions, and goal alignment required to distinguish benign task execution from covert deviation. We propose \textbf{Agent-ToM}, a learning-to-monitor framework grounded in Theory-of-Mind (ToM) reasoning for security analysis of autonomous agents. Agent-ToM performs structured full-trajectory analysis by inferring beliefs, intent hypotheses with calibrated confidence, expected actions, and deviations from task-consistent behavioral baselines. At inference time, it employs a \textit{Reason-Verify-Refine} pipeline to construct and validate monitoring decisions. At training time, Agent-ToM distills critique signals into a persistent \textit{semantic guardrail memory}, enabling reusable belief- and intent-conditioned constraints across episodes. We evaluate Agent-ToM on adversarial agent monitoring benchmarks (SHADE-Arena and CUA-SHADE-Arena). Agent-ToM achieves strong precision-recall balance and outperforms state-of-the-art monitoring baselines, including ensemble methods, while using a coherent two-call reasoning pipeline. These results demonstrate that learning at the monitoring layer, combined with structured ToM reasoning and verification, provides an effective and deployable foundation for securing autonomous LLM agents. --- ### Towards Evaluation Engineering: An Empirical Study of ML Evaluation Harnesses in the Wild Authors: Zhimin Zhao, Zehao Wang, Abdul Ali Bangash, Bram Adams, Ahmed E. Hassan Published: 2026-05-22 Categories: cs.SE, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2605.24213v1 Evaluation harnesses are software systems that orchestrate model evaluation by managing model invocation, data loading, metric computation, and result reporting. Despite their critical role in machine learning infrastructure, their operational challenges and engineering concerns have received limited attention so far. We present an empirical study of 57 evaluation harnesses, deriving a five-stage harness model and classifying 16,560 issues by workflow stage and root cause. Most harness operational challenges concentrate in the Specification stage (41.4% of issues), where harnesses integrate external models, datasets, and scoring judges. The three most frequent root causes of operational challenges are unimplemented features (24.3%), documentation gaps (20.3%), and missing input validation (17.2%), which together account for 61.7% of classified issues, spanning both defects in existing functionality and capability gaps that block intended workflows. Root causes also vary by workflow stage: environment incompatibility and external dependency breakage account for 36.2% of provisioning issues, whereas algorithmic error (25.9%) and validation gap (22.5%) dominate assessment issues. Together, these contributions establish an empirical foundation for treating evaluation engineering as a distinct software engineering concern. --- ### Distributionally Robust Transfer Learning with Structurally Missing Covariates, with Application to Cross-National Cardiac Arrest Prediction Authors: Siqi Li, Chuan Hong, Ziye Tian, Benjamin Sieu-Hon Leong, Koshi Nakagawa, Hideharu Tanaka, Sang Do Shin, Khuong Quoc Dai, Do Ngoc Son, Marcus Eng Hock Ong, Nan Liu, Molei Liu Published: 2026-05-22 Categories: stat.AP, cs.AI, cs.LG, stat.ML arXiv: https://arxiv.org/abs/2605.24212v2 Deploying clinical prediction models across healthcare systems often fails when key training covariates are unavailable at deployment and labeled outcomes are limited in the target domain. For example, high-performing models for out-of-hospital cardiac arrest (OHCA) rely on detailed prehospital measurements routinely collected in high-resource settings but unavailable in many international registries. Existing methods either discard missing covariates, sacrificing predictive information, or rely on untestable assumptions about their target distribution. We propose DRUM (\underline{D}istributionally \underline{R}obust \underline{U}nsupervised transfer learning with structurally \underline{M}issing covariates), a framework that transfers prediction models to target populations where certain covariates are structurally absent and outcome labels are unavailable. DRUM partitions covariates into shared components ($X$), observed across all settings, and missing components ($A$), observed only in the source. Rather than imputing missing covariates, DRUM optimizes worst-case predictive performance over the unknown target distribution of $A \mid X$ using a neural network generator, with a robustness parameter controlling allowable deviation from the source conditional. We further develop a bias correction procedure that reduces sensitivity to nuisance estimation error. Simulations show substantial improvements in both mean and worst-case prediction error under distribution shift. Applied to cross-national OHCA prediction, transferring models from a US registry to multiple Asian registries where prehospital variables are unrecorded, DRUM yields better-calibrated predictions and improved clinical classification performance across sites. --- ### Teaching Through Analogies: A Modular Pipeline for Educational Analogy Generation Authors: Mariam Barakat, Ekaterina Kochmar Published: 2026-05-22 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2605.24211v1 Analogies help learners understand unfamiliar concepts by relating them to known concepts. Despite recent advances, large language models (LLMs) continue to struggle to generate analogies of comparable quality to those produced by humans. We present a modular pipeline for educational analogy generation, decomposing the task into four stages: source finding, sub-concept generation, explanation generation, and evaluation. Grounded in Structure Mapping Theory, the pipeline enables systematic, stage-by-stage analysis of how model choice and input configuration affect analogy quality. We evaluate 12 state-of-the-art LLMs across six model families on two datasets with structured sub-concept annotations (SCAR and ParallelPARC), alongside seven embedding models for closed-setting retrieval. Our results show that sub-concepts substantially improve explanation quality and closed setting retrieval precision but provide limited benefit in open-ended source generation. We further introduce an LLM-as-a-judge evaluation methodology and validate its scoring against human annotations from seven annotators, finding that Claude Sonnet 4.6 aligns more reliably with human rankings than with fine-grained absolute scores. Taken together, our findings reveal cross-stage interactions that isolated studies cannot capture, and highlight sub-concept grounding as a key driver of analogy quality generation. --- ### Characterizing the Representational Capacity of Neural Processes Authors: Robin Young Published: 2026-05-22 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2605.24210v1 What functions can Neural Processes represent? We analyze the representational capacity of popular NP architectures: Conditional Neural Processes (CNPs), Attentive Neural Processes (ANPs), Transformer Neural Processes (TNPs), and their latent variants. We prove these architectures form a strict hierarchy. CNP-representable functions are exactly those depending on finitely many expected features of the context distribution. ANPs strictly generalize CNPs via query-dependent reweighting, enabling kernel smoothers. ConvCNPs and ANPs are incomparable; each contains functions outside the other, separated by stationarity versus translation equivariance. TNPs with $L$ self-attention layers capture $L$-hop context interactions. For latent NPs, we show finite-dimensional latents provide coherent sampling but do not circumvent encoder limitations; matching GP posterior distributions requires latent dimension scaling with context size. These results provide a theoretical foundation for architecture selection based on task structure. --- ### Incorporating Deep Learning Design in Database Queries Authors: Yuval Lev Lubarsky, Dean Light, Boaz Berger, Shunit Agmon, Benny Kimelfeld Published: 2026-05-22 Categories: cs.DB, cs.LG arXiv: https://arxiv.org/abs/2605.24207v1 Deep learning over relational databases is conventionally realized by translating data into graph representations and applying graph-based neural networks within external frameworks. This round-trip between the database and external machine learning (ML) systems introduces non-trivial engineering overhead. In effect, these graph neural networks operate on tuple embeddings and manipulate them in ways that capture the interactions induced by relational joins. Given this natural correspondence, there is no fundamental reason why specifying a neural network over relational data should be substantially harder than querying it. We propose an approach that naturally integrates deep learning with database queries. The key idea is to associate each tuple with provenance, represented as a vector embedding with learnable parameters. Queries are lifted to operate jointly on data and embeddings, mapping input relations with embedded tuples to output relations with embedded tuples. This approach provides a declarative foundation for relational deep learning, facilitating integration with database systems, optimization, and wide adoption. We describe RelaNN, a proof-of-concept implementation of this approach built on top of PyTorch and cuDF. We illustrate the utility of RelaNN by implementing various graph-learning models, including graph convolutional networks, heterogeneous graph transformers, hypergraph neural networks and deep homomorphism networks. The simplicity of the programs and their competitive runtime performance demonstrate a concrete path toward making the implementation of state-of-the-art neural networks over databases as simple as writing a query. --- ### When Does Multi-Agent RL Improve LLM Workflows? Workflow, Scale, and Policy-Sharing Tradeoffs Authors: Yifan Zeng, Yiran Wu, Yaolun Zhang, Wentian Zhao, Kun Wan, Qingyun Wu, Huazheng Wang Published: 2026-05-22 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2605.24202v2 Multi-agent LLM workflows route inference through specialized roles to lift end-task accuracy, but jointly training those roles with reinforcement learning is unstable in ways that are poorly understood. We study when end-to-end RL training of multi-agent LLM workflows improves over their base models, comparing Shared-Policy training, where all roles update one policy, with Isolated-Policy training, where each role has its own parameters. Our experimental matrix spans Eval-Opt, Voting, and Orch-Workers workflows, math and code tasks, and three model scales (0.6B, 1.7B, 4B). We find that multi-agent RL usually improves over base models, but gains depend jointly on workflow, task, and scale, not on policy sharing alone. Isolated-Policy tends to reach higher peak accuracy yet more often falls off a terminal accuracy cliff, while Shared-Policy training does not eliminate failure; it redistributes failure into qualitatively different patterns. We then explain the strongest of these patterns through role-level gradient dynamics induced by workflow topology and policy routing: under Isolated-Policy, parallel same-role agents on shared prompts amplify per-role gradients and drive terminal degradation in Voting and Orch-Workers workflows; under Shared-Policy, asymmetric per-step gradient mass causes the shared policy to be captured by the dominant role, producing different failure signatures by task and workflow. Together, the empirical map and its underlying mechanisms show that policy sharing routes training pressure through different channels rather than offering uniform stability, making it a design choice with workflow- and task-conditional tradeoffs. --- ### Radiuma: A Unified Zero-Code Executable Graphical Workflow Generator for Reproducible and Shareable Medical Image Analysis and Machine Learning Authors: Mohammad Salmanpour, Mehrdad Oveisi, Isaac Shiri, Arman Rahmim Published: 2026-05-22 Categories: cs.CV, physics.med-ph arXiv: https://arxiv.org/abs/2605.24201v1 Medical image computing software is essential for identifying imaging biomarkers that can support diagnosis, prognosis, treatment planning, and clinical research. However, the lack of standardized, user-friendly, and reproducible software environments has limited the broader adoption of advanced medical image analysis workflows. We present Radiuma, a freely available modular platform designed to support reliable and reproducible medical image analysis across multiple modalities and file formats. Radiuma integrates image reading, visualization, registration, fusion, processing, segmentation, radiomics feature extraction, and machine learning modules for classification, regression, and clustering. Its modular design allows users to execute each component independently or connect modules through a visual workflow system, where the output of one step can be graphically passed to the next. This enables the creation of custom, executable, and reproducible multi-step pipelines without requiring extensive programming expertise. Results from each module can be inspected directly in the visualization window, providing immediate feedback on processing quality and workflow accuracy. Radiuma also supports saving and sharing customized workflows, promoting transparency, reusability, and consistency across collaborative studies. By combining flexibility, usability, and standardized analysis tools, Radiuma provides a practical environment for radiomics and machine learning research in clinical and translational settings. The platform is designed to be accessible to users with diverse expertise, including radiologists, physicists, clinicians, and data scientists. --- ### A Sober Look at Agentic Misalignment in Automated Workflows Authors: Wenqian Ye, Bo Yuan, Zhichao Xu, Yijun Tian, Yawei Wang, Henry Kautz, Aidong Zhang Published: 2026-05-22 Categories: cs.AI arXiv: https://arxiv.org/abs/2605.24197v2 We study a class of emergent misalignment in multi-agent systems (MAS), with a focus on automated workflows, which we refer to agentic misalignment. Although these systems can solve complex tasks, they often fail because agents act according to implicit proxy utilities that do not align with the intended human goals. We formally define these behaviors and analyze them within a Bayesian framework, showing that generic utilities naturally lead to posterior collapse of agents in automated workflows. To address this issue, we propose Agentic Evidence Attribution (AEA), a novel alignment paradigm that improves agent posteriors using context-specific evidence. AEA reasons over agent actions and provides structured evidence to correct misaligned behavior during collaboration. To better understand the role of evidence, we study two instantiations of AEA: self-reflection (internal evidence from the model) and weak-to-strong generalization (external evidence on the agentic trajectory). We show that a small evidence model effectively aligns the MAS by providing orthogonal failure attribution. Our results clarify the sources of agentic misalignment in automated workflows and show that evidence-based alignment can effectively improve agent collaboration and leads to reliable multi-agent systems built on automated workflows. --- ### Single View Seafloor Recovery from Imaging Sonar via Differentiable Rendering Authors: Sevan Brodjian, Michael Hobley, Pietro Perona Published: 2026-05-22 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2605.24195v1 Sonar is often the only modality suitable for high-resolution imaging underwater due to light attenuation and turbidity. Forward-looking imaging sonar provides measurements over range and horizontal angle but collapses vertical structure into a flat image, creating ambiguities that make 3D recovery challenging. A common use case for imaging sonar is underwater terrain mapping (bathymetry), yet current methods require many views, expensive multi-sensor setups, or significant training data, which limits use and adaptability to new environments. We present a training-free method that recovers bathymetry from a single sonar image in under 30 seconds via differentiable rendering, conditioned on a known seafloor tilt. To our knowledge, this is the first differentiable rendering approach for single-view height recovery in sonar. Our method implements differentiable sonar ray tracing and optimizes an explicit height field to reproduce the target image. On synthetic datasets, our approach outperforms a supervised CNN under distribution shift and remains close on rough terrain, while the CNN wins in-distribution. By modeling physically grounded priors of the sonar process, our method adapts across sensor configurations and environments without training data. --- ### Music Transcription with (Almost) No Supervision Authors: Saebyeol Shin, Chao Wan, Zhenzhen Liu, Justin Lovelace, Daniel C. Lin, Kilian Q. Weinberger, John Thickstun Published: 2026-05-22 Categories: cs.SD, cs.LG arXiv: https://arxiv.org/abs/2605.24193v1 Competitive music transcription models require large amounts of paired audio-score data, which is scarce due to collection costs, alignment difficulty, and copyright restrictions. Meanwhile, vast quantities of unpaired audio recordings and symbolic scores are freely available but have gone unused. We adopt a cycle-consistent translation framework in which a small amount of paired data acts as a minimal anchor, unlocking the full potential of the unpaired pool. We find that: unpaired data yields surprisingly large gains, especially under limited supervision; unpaired audio contributes more than unpaired scores; incorporating unlabeled audio from a new instrument during training improves transcription for that instrument without any paired supervision. Together, these results suggest that scaling unpaired data offers a practical path toward high-quality transcription for instruments where labeled data remains scarce. --- ### Filtered Posterior Mean Collections: A Unified Framework for Analytical Models of Diffusion Generalization Authors: Matthew Niedoba, Berend Zwartsenberg, Frank Wood Published: 2026-05-22 Categories: cs.LG, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2605.24192v1 The neural-network denoising functions which form the backbone of image diffusion models are remarkably consistent in their generalization behaviour across a wide variety of network architectures and training procedure hyperparameters. A recent line of research has sought to model the outputs of these networks by aggregating posterior weighted averages of training dataset patches. In this work, we consolidate these approaches into a unified model class which we call Filtered Posterior Mean Collections (FPMCs). We define this model class using query precision vectors, response weights, and source distributions, and illustrate that existing methods are recoverable with specific choices of these design axes. Investigating each axis in turn, we find that FPMC performance can be improved with soft relaxations of prior patch-based methods, and through augmentations of source distributions. Applying these findings to an existing FPMC, we demonstrate consistent sample improvement across three natural image datasets. --- ### AvalancheBench: Evaluating Enterprise Data Agents Through Latent World Recovery Authors: Darek Kleczek, Fuheng Zhao, Alexander W. Lee, Julien Tissier, Pawel Liskowski, Ugur Cetintemel, Anupam Datta Published: 2026-05-22 Categories: cs.DB, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2605.24183v1 We introduce AvalancheBench, a benchmark for evaluating enterprise data agents through \emph{latent world recovery}. AvalancheBench improves on existing benchmarks in three ways. First, it evaluates analytical understanding rather than pipeline completion: systems are scored on whether they recover the segments, drivers, temporal events, and relationships that explain the data, not merely on whether they execute a workflow or produce a plausible report. Second, it provides ground truth for goal-driven analytics by generating observations from a known latent world, enabling partial credit for incomplete but valid recoveries. Third, it exposes how early analytical mistakes propagate into later conclusions: missed segments, merged events, or wrong attributions can lead to systematically wrong recommendations. In this sense, AvalancheBench complements real-data benchmarks by providing a controlled setting for diagnosing whether agents recover the analytical structure behind enterprise data. On a first e-commerce use case, the strongest configuration of a leading coding agent recovers only 26\% of the rubric, with failures concentrated in generic customer segmentations and merged temporal events. --- ### Human-AI Collaboration in Science at Scale: A Global Large-scale Randomized Field Experiment Authors: Binglu Wang, Weixin Liang, Jiahui Xue, Yuhui Zhang, Hancheng Cao, Dashun Wang, Yian Yin Published: 2026-05-22 Categories: physics.soc-ph, cs.AI, cs.DL, cs.HC arXiv: https://arxiv.org/abs/2605.24180v1 Collaboration is the defining mode of modern science, yet its core mechanism -- feedback -- remains hard to observe, difficult to scale, and unequally distributed. Here we test whether large language models (LLMs) can contribute to this hidden but vital practice and reallocate scientific feedback, an essential yet scarce resource for knowledge production. In a global large-scale randomized field experiment, we delivered customized LLM-generated feedback for over 31,000 arXiv preprints across 150 fields and more than 45,000 researchers from 133 geographic regions. Relative to controls, authors who received feedback had a significantly higher likelihood of revising their manuscripts, corresponding to a 12.55% relative increase over the baseline revision rate. Exposure to AI feedback also increased authors' subsequent use of LLM tools in their future papers, suggesting longer-run shifts in scientific practice. These effects were strongest among authors from non-English-dominant research regions, manuscripts less embedded in the scholarly literature, and teams with lower h-indexes and earlier career stages, consistent with the idea that AI feedback may provide the greatest benefit where access to timely critique is otherwise limited. Together, these findings provide causal evidence that structured AI-based interventions can transform access to scientific feedback from a largely private advantage into a more widely distributed resource, with broader implications for productivity, equity, and capacity across the global research system. --- ### Loki: Representation over Architecture for Diffusion-Based Portrait Animation Authors: Pouyan Navard, Sernam Lim Published: 2026-05-22 Categories: cs.CV arXiv: https://arxiv.org/abs/2605.24176v1 Portrait animation transfers a driver clip's facial expression and head pose onto a single reference image while preserving the reference's identity. State-of-the-art diffusion systems address this by stacking trained modules for expression, pose, and identity in turn, paying for it in trainable parameters, proprietary corpora, and residual entanglement between the very axes the system is meant to control independently. This complexity compensates for an upstream choice -- learning facial expression and head pose from RGB, a representation in which identity, pose, and expression are inseparable without being learned apart. Loki steps out of RGB on the conditioning path. Driver expression and head pose are encoded by a face model whose parameter axes are identity-orthogonal by construction, then rasterised into a spatial map that the diffusion backbone consumes natively. Identity is routed separately through the diffusion backbone's own pretrained features via lightweight key-value injection. Because the parametric representation factorises identity from expression and pose, cross ID reenactment reduces to a coefficient substitution at inference, requiring no cross ID training data. Loki requires ~43% fewer inference parameters than leading diffusion baselines and trained on 1496x less video samples. We define two metrics that directly measure whether the generated head pose trajectory and facial expression followed the driver's -- the questions portrait animation actually asks; Loki leads or co-leads on both. --- ### Extracting Training Data from Diffusion Language Models via Infilling Authors: Yihan Wang, N. Asokan Published: 2026-05-22 Categories: cs.CL, cs.AI, cs.CR, cs.LG arXiv: https://arxiv.org/abs/2605.24173v1 Memorization in large language models has been studied almost exclusively through prefix-conditioned extraction, a natural choice for autoregressive models. However, diffusion language models (DLMs) can denoise masked tokens at arbitrary positions. Thus, prefix-only probing reveals only one facet of memorization in DLMs and significantly underestimates the risk of training-data extraction. In order to realistically model extractability of training data in DLMs, we introduce \emph{infilling extraction}, a data-extraction protocol parameterized by an arbitrary binary mask that subsumes prefix-only probing and accounts for the bidirectional inductive bias of DLMs. Instantiating it on LLaDA-8B and Dream-7B across five extraction modes, three training pipelines, and three corpora covering verbatim and partial leakage, we find that mask geometry governs extractability: edge-conditioned masks \emph{extract up to three times more} verbatim sequences than prefix-conditioned ones, and bidirectional access opens channels inaccessible in autoregressive models. In particular, we show that a realistic adversary with access to training data where personally identifiable information has been redacted, can even achieve higher recall on extracting redacted email addresses from DLMs than from scale-matched autoregressive models. Tunable parameters for decoding measurably affect extraction performance, while a follow-up supervised finetuning stage does not eliminate the prior memorization. --- ### EPPC-OASIS: Ontology-Aware Adaptation and Structured Inference Refinement for Electronic Patient-Provider Communication Mining in Secure Messages Authors: Samah Fodeh, Sreeraj Ramachandran, Elyas Irankhah, Muhammad Arif, Afshan Khan, Ganesh Puthiaraju, Linhai Ma, Srivani Talakokkul, Jordan Alpert, Sarah Schellhorn Published: 2026-05-22 Categories: cs.AI arXiv: https://arxiv.org/abs/2605.24172v1 Secure patient-provider messages contain clinically important communication behaviors that are difficult to characterize manually at scale. The Electronic Patient-Provider Communication (EPPC) framework provides an ontology for coding these behaviors, but automated extraction remains challenging because predictions must preserve fine-grained code/sub-code structure while grounding annotations in message text. We developed EPPC-OASIS, an ontology-aware adaptation approach for structured EPPC extraction, and combined it with deployable inference-refinement procedures designed to improve the coherence of final annotations. EPPC-OASIS augments supervised fine-tuning with a Wasserstein alignment objective that encourages alignment between model representation neighborhoods and EPPC ontology-derived neighborhoods, while inference refinement uses verification, self-consistency, hybrid correction, and selection or ensembling to address residual prediction errors. We evaluated the framework on a de-identified corpus of secure patient-provider messages against prompting, supervised fine-tuning, preference-based, and robustness-oriented baselines across multiple open-weight language models. Across model families, the best deployable pipeline achieved 77.13% Code+Sub-code F1 and 63.83% Triplet F1, corresponding to modest but consistent absolute gains of +1.39 and +2.12 F1 points over the strongest supervised fine-tuning baseline. These results suggest that ontology-aware adaptation with structured inference refinement can support scalable retrospective EPPC mining, although external validation is needed before operational use. --- ### PromptAudit: Auditing Prompt Sensitivity in LLM-Based Vulnerability Detection Authors: Steffen J. Camarato, Yahya Hmaiti, Mandana Ghadamian, David Mohaisen Published: 2026-05-22 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2605.24171v1 Large language models are increasingly used for vulnerability detection, yet their reliability under different prompt formulations remains uncharacterized. We present PromptAudit, a controlled evaluation framework that isolates prompt effects by fixing the dataset, decoding, and parsing while varying only the prompting strategy. Using five prompting strategies across five open-weight models on 1,000 CVEs (6,074 code samples spanning 16 programming languages), we evaluate accuracy, recall, abstention, coverage, and effective F1. We find that standard chain-of-thought prompting achieves the strongest overall operational performance, while few-shot prompting provides model-dependent benefits that are most pronounced for prompt-sensitive models. In contrast, adaptive chain-of-thought frequently suppresses recall and self-consistency induces excessive abstention, sharply reducing effective performance. These results show that vulnerability detection behavior is jointly determined by the model and the prompt, and that prompt sensitivity is a first-class system property that must be explicitly characterized in evaluation and deployment. --- ### Learning dynamical systems with biochemically informed neural ordinary differential equations Authors: Luis L. Fonseca, Reinhard C. Laubenbacher, Lucas Böttcher Published: 2026-05-22 Categories: math.DS, cs.LG, q-bio.QM arXiv: https://arxiv.org/abs/2605.24170v1 Ordinary differential equation models of biochemical reactions are often formulated as stoichiometric systems in which the dynamics arise from a collection of interacting processes. A central challenge is that the functional form of each process is rarely known a priori and may be difficult to infer from data. We propose biochemically informed neural ordinary differential equations (BINODEs), a neural-ODE framework that retains the stoichiometric structure of mechanistic models while representing individual processes by neural networks. In BINODEs, the outputs of neural network processes (NNPs) are mapped to state derivatives through a linear layer analogous to a stoichiometric matrix. This architecture allows biological side information, such as process-specific inputs, sign constraints, and monotonicity assumptions, to be built directly into the model. We characterize the approximation properties of NNPs for several standard biochemical rate laws and show that the proposed framework recovers both trajectories and process-level structure in Monod, Lotka--Volterra, pharmacokinetic, and ultradian endocrine models. These results suggest that BINODEs offer a useful compromise between mechanistic interpretability and data-driven flexibility for modeling partially known biochemical or biological dynamical systems. --- ### Inference Time Context Sparsity: Illusion or Opportunity? Authors: Sahil Joshi, Prithvi Dixit, Agniva Chowdhury, Anshumali Shrivastava, Joseph E. Gonzalez, Ion Stoica, Kumar Krishna Agrawal, Aditya Desai Published: 2026-05-22 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2605.24168v1 Sparsity has long been a central theme in LLM efficiency, but its role in context processing remains unresolved. As LLM workloads shift toward longer contexts and agentic interactions, the compute and memory bottlenecks of attention become increasingly critical, raising the question of whether these constraints are fundamental. Our position is that these constraints are artificial and unnecessary, and that the future of LLM inference lies in extreme but principled sparsity along the context dimension. This position is supported by several strands of empirical and theoretical evidence. First, we find the insistence on dense attention unreasonable, since in a long context a query effectively projects O(N) attention information into a hidden space of dimension d << N, making the process inherently lossy. Second, we perform an extensive study of sparsity in LLMs spanning 20 models across five model families, varying context lengths, and different sparsity levels. We empirically demonstrate a strong trend: current LLMs, despite not being trained for context sparsity, are remarkably robust to inference-time decode sparsity across tasks of varying complexity, including retrieval, multi-hop QA, mathematical reasoning, and agentic coding. Importantly, we also show that current hardware is already sufficient to realize substantial gains from this sparsity. For example, our sparse decode kernels accelerate large-context processing by up to 10x over FlashInfer at 50x sparsity levels on hardware such as the H100. Overall, these results position extreme context sparsity not as a heuristic, but as a principled foundation for LLM inference, training, and architecture design: one that is both feasible and beneficial, and a compelling direction for future systems. --- ### CUNY at CLPsych 2026: A Pipeline Approach to Classification and Summarization of Mental Health Changes Authors: Amirmohammad Ziaei Bideh, Shameed Charlomar Job, Ava Yahyapour, Alla Rozovskaya Published: 2026-05-22 Categories: cs.CL arXiv: https://arxiv.org/abs/2605.24164v1 We describe our submission to the CLPsych~2026 Shared Task on capturing and characterizing mental health changes through social media timeline dynamics. To infer the dominant self-states in posts (Tasks 1.1 and 1.2), we ensemble in-context learning of three open-weight large language models using majority voting. For predicting moments of change in a timeline (Task~2), we train supervised classifiers on features derived from Task~1.1 predictions. To summarize the patterns of mood dynamics and their progression over time within a timeline (Task 3.1), we augment in-context example labels predicted by upstream systems (Tasks 1.1, 1.2, and 2), yielding performance gains over zero-shot and unaugmented in-context learning baselines. Our submission ranked first on Task~1.1, fourth on Task~1.2, fourth on Task~2, and third on Task~3.1.\footnote{The source code for the experiments is available at https://github.com/amirzia/clpsych26-cuny --- ### Knowledge Graph Modulated Deep Learning for Limited-Sample Clinical Data Analysis Authors: Yuwei Xue, Sakib Mostafa, James Zou, Joseph Liao, Maximilian Diehn, Ash A. Alizadeh, Lei Xing, Md. Tauhidul Islam Published: 2026-05-22 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2605.24162v1 Biological systems are governed by structured molecular interactions, where pathways, regulatory circuits, and functional gene relationships shape cellular behavior and disease progression. Much of this knowledge is naturally represented as graphs. However, most biomedical AI models cannot directly use graph-encoded biological knowledge and instead require compressed low-dimensional representations, which can lose important structure and reduce performance, especially in limited-sample clinical studies. Here, we introduce Graph-in-Graph (GiG), a knowledge graph-modulated deep learning framework for data-efficient clinical prediction. GiG represents each patient as a standalone modular graph, in which curated biological knowledge graphs define edges and patient-specific measurements, such as gene expression, define node features. This design allows multiple biological knowledge graphs to be integrated while preserving gene-gene interactions and pathway topology during patient-level representation learning. Across cohorts comprising nearly 9,700 patients and five clinical tasks, including liquid biopsy cancer detection, prostate cancer diagnosis, and 32-class pan-cancer classification, GiG consistently outperforms traditional and state-of-the-art methods, with the largest gains in limited-sample settings. On the challenging prostate cancer diagnosis task, GiG improves macro-F1 by up to 49 percentage points relative to competing methods. Control experiments replacing real pathway graphs with random topologies confirm that these gains arise from biologically grounded knowledge graph structure rather than graph modeling alone. These findings show that knowledge graph-modulated deep learning can improve robustness, interpretability, and sample efficiency in clinical data analysis, and provide a principled framework for integrating biological knowledge graphs into predictive modeling. --- ### EchoVQA: Enabling Conversational Assistance for Point-of-Care Cardiac Ultrasound Authors: Filippos Bellos, Yutong Li, Jessie N Dong, Zaiyang Guo, Emily Mackay, Yayuan Li, Yannis Avrithis, Alison Pouch, Jason J. Corso Published: 2026-05-22 Categories: cs.CV arXiv: https://arxiv.org/abs/2605.24159v1 Point-of-care transthoracic echocardiography (TTE) enables cardiac assessment in virtually any clinical setting, yet its diagnostic utility remains constrained by the expertise required for image acquisition and interpretation. Visual question answering (VQA) offers a promising paradigm for bridging this expertise gap through interactive clinical assistance, but existing echocardiography VQA datasets are limited in scale, restricted to high-quality images, and only cover a few views. We introduce EchoVQA, the first large-scale VQA dataset for echocardiography, comprising 14,299 images and 74,819 question-answer pairs. The dataset integrates public sources (EchoNet-Dynamic, CAMUS) with our own point-of-care acquisitions from two handheld probes (Lumify, Clarius), spanning diverse views and including both high-quality and suboptimal images. Uniquely, EchoVQA includes acquisition guidance questions to help users optimize transducer positioning toward a diagnostic apical 4-chamber view for left ventricular ejection fraction estimation -- a challenging task for novice operators in point-of-care settings. We further develop a parameter-efficient method based on multimodal learnable prompts achieving state-of-the-art performance on most benchmarks, including EchoVQA, with significantly less trainable parameters than existing state-of-the-art approaches. --- ### An Interpretable CF-RL-TOPSIS Fusion Model for Skills-Aware Talent Recommendation Authors: Özkan Canay Published: 2026-05-22 Categories: cs.IR, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2605.24155v1 Effective skills-aware talent recommendation must balance behavioral transition patterns, trajectory-sensitive adaptation, and inspectable occupation-level criteria. Evidence from public benchmarks on how these signals interact, however, remains limited. This study proposes CF-RL-TOPSIS, an interpretable late-fusion model that integrates a transition-aware collaborative branch, a compact reinforcement-style occupation-family bandit, and an entropy-weighted TOPSIS branch constructed from six semantic proxies; the validation-selected fusion coefficients remain auditable. The model is evaluated on two frozen public ICT talent-history benchmarks, JobHop and Karrierewege, using repeated chronological top-5 ranking and paired Wilcoxon tests. On JobHop the full hybrid attains NDCG@5 = 0.3040 +/- 0.0073 and significantly surpasses repeat-last, item Markov, transition-aware collaborative filtering, the CF+TOPSIS hybrid, GRU4Rec, and SASRec (p <= 0.0039 across planned comparisons). On Karrierewege the hybrid remains competitive but does not significantly exceed the strongest Markov baseline, revealing a persistence-dominated setting in which the bandit branch appropriately shrinks to near-zero weight. Proxy-sensitivity, family-level deep Q-network, and runtime checks support this interpretation, and a worked user-level case shows how branch scores, criterion weights, and rank shifts can be inspected for an individual recommendation. The contribution is not a benchmark-agnostic superiority claim, but a reproducible account of the conditions under which transparent late fusion adds value beyond simple continuation heuristics. In semantically rich, non-saturating talent-history regimes the three branches reinforce one another; in persistence-dominated regimes the same architecture remains competitive through its collaborative backbone, with the adaptive branch correctly inactive. --- ### Palette: A Modular, Controllable, and Efficient Framework for On-demand Authorized Safety Alignment Relaxation in LLMs Authors: Qitao Tan, Xiaoying Song, Arman Akbari, Arash Akbari, Yanzhi Wang, Xiaoming Zhai, Lingzi Hong, Zhen Xiang, Jin Lu, Geng Yuan Published: 2026-05-22 Categories: cs.AI, cs.SE arXiv: https://arxiv.org/abs/2605.24154v1 Current safety alignment of foundation models largely follows a \emph{one-size-fits-all} paradigm, applying the same refusal policy across users and contexts. As a result, models may refuse requests that are unsafe for general users but legitimate for authorized professionals, limiting helpfulness in specialized professional settings. Existing approaches either require costly realignment or rely on inference-time steering that suffers from imprecise control and added latency. To this end, we propose \textsc{Palette}, a modular, controllable, and efficient framework that selectively relaxes refusal behavior on authorized target domains while preserving standard safety elsewhere. Our method identifies a refusal direction via multi-objective search and internalizes it into the model through lightweight adaptation. \textsc{Palette} further supports modular composition: it learns domain-specific safety controls independently and composes them through parameter merging, enabling on-demand multi-domain authorization without retraining. Experiments across four safety benchmarks, multiple model variants, and both LLMs and VLMs show that \textsc{Palette} delivers precise safety control without sacrificing general utility, offering a practical path toward foundation models that adapt to diverse professional needs. --- ### Neuro-Inspired Inverse Learning for Planning and Control Authors: Maryna Kapitonova, Tonio Ball Published: 2026-05-22 Categories: cs.AI arXiv: https://arxiv.org/abs/2605.24152v2 We present a neuro-inspired framework for embodied planning and control. Building on three principles that enable fast and highly effective goal-directed behavior in the mammalian brain - paired forward/inverse internal models, open-loop multi-step motor commands, and sequential, hierarchical organization of action - our Inverter framework uses learned components, trained end-to-end through Inverse Learning (IL) and supplemented where natural by analytic or algorithmic modules; we formalize IL and delineate it from supervised, reinforcement, and imitation learning. IL bridges Reinforcement Learning (RL)-style amortization, which runs in a single forward pass but emits only one action at a time, and Optimal Control (OC)-style sequence planning over whole trajectories, but with iterative test-time computation. Single Inverters or hierarchical n=2 Inverter stacks match or improve on offline-RL and diffusion-planner baselines on all 3 maze2d and 6 antmaze D4RL variants by an average of +24.2% (range -1.9% to +78.2%), at one-to-two orders of magnitude less inference compute time. Distinctively, optimizing through the Forward Model (FoM) over the entire T-step action sequence - rather than per step - lets Inverters produce smooth, goal-coherent, trajectory-wide structure and reach control policies closer to the analytic optimum than the policy underlying the training data itself. We also identify a failure mode of IL: FoM hacking under narrow training-data coverage, which we mitigate by using random training data with broader coverage. As an application example, a Pulse Inverter synthesizes arbitrary single-qubit quantum gates with fidelity matching the standard iterative numerical baseline (GRAPE), at more than 1000x lower per-gate compute time. In summary, we conclude that IL enables a versatile class of world-interfaces, especially for latency- and resource-critical embodied AI. --- ### EVA: Accelerating LLM Decoding via an Efficient Vector Quantization Architecture Authors: Bowen Duan, Cong Guo, Chiyue Wei, Haoxuan Shan, Yuzhe Fu, Xinhua Chen, Yifan Xu, Ziyue Zhang, Changchun Zhou, Hai Li, Yiran Chen Published: 2026-05-22 Categories: cs.AR, cs.LG arXiv: https://arxiv.org/abs/2605.24144v1 Large Language Models (LLMs) have achieved impressive performance across diverse domains but remain inefficient during the autoregressive decoding phase. Unlike the prefill stage, which employs compute-bound GEMM operations, decoding executes a sequence of small GEMV-like computations that are memory-bound and underutilize modern accelerators. Weight-only vector quantization (VQ) has emerged as an effective compression technique that clusters model weights into a shared codebook and replaces the original weight matrix with low-precision indices, enabling 2-bit-level weight compression. While this approach substantially reduces model size and memory bandwidth, it still suffers from two critical inefficiencies: the low utilization of GEMV computation and frequent memory conflicts during codebook lookups. This paper presents EVA, an efficient vector-quantization-based architecture that addresses both computational and memory bottlenecks in LLM decoding. EVA builds on a simple yet effective insight that combines input-codebook computation with conflict-free memory access. Instead of reconstructing quantized weights from indices, EVA directly performs dot products between input vectors and the weight codebook, transforming LLM decoding from GEMV to GEMM computation. It then performs structured lookups from an intermediate output buffer, eliminating memory bank conflicts. We further design a hardware-software co-optimized architecture specialized for LLM decoding while remaining compatible with conventional prefill execution. Evaluations show that EVA achieves up to 11.17$\times$ speedup and 7.17$\times$ higher energy efficiency compared with the SOTA lookup-based architecture, while preserving arithmetic precision after vector quantization. Our code is available at https://github.com/dbw6/Eva.git. --- ### HyperGuide: Hyperbolic Guidance for Efficient Multi-Step Reasoning in Large Language Models Authors: Yuyu Liu, Haotian Xu, Yanan He, Sarang Rajendra Patil, Mengjia Xu, Tengfei Ma Published: 2026-05-22 Categories: cs.AI arXiv: https://arxiv.org/abs/2605.24140v3 Multi-step reasoning remains a central challenge for large language models: single-pass generation is efficient but lacks accuracy; tree-search methods explore multiple paths but are computation-heavy. We address this gap by distilling reasoning progress into a hyperbolic geometric signal that guides step-by-step generation. Our approach is motivated by a structural observation: in combinatorial reasoning trees, solution-bearing states are few while dead ends are exponentially numerous. The hyperbolic space matches this asymmetry, with compact volume near the origin and exponentially expanding capacity toward the boundary, so that distance-to-origin naturally encodes solution proximity while angular separation distinguishes branches requiring different next operations. We train a lightweight head to project LLM hidden states into this space, then fine-tune a low-rank adapter interactively on its own reasoning attempts to act on the injected signal. Across multiple benchmarks, the geometric signal yields consistent gains, with larger improvements on deeper reasoning chains. Our code is publicly available at https://github.com/yuyuliu11037/HyperGuide. --- ### MAPLE: Multi-State Aggregated Policy Evaluation for AlphaZero in Imperfect-Information Games Authors: Qian-Rong Li, Hung Guei, I-Chen Wu, Ti-Rong Wu Published: 2026-05-22 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2605.24139v1 Imperfect-information games (IIGs) are challenging, as players must make decisions without fully observing the true game state. While AlphaZero has achieved remarkable success in perfect-information games, extending it to IIGs remains difficult. Existing search-based approaches, such as Perfect Information Monte Carlo (PIMC), suffer from strategy fusion, while Information Set Monte Carlo Tree Search (IS-MCTS) incurs high computational cost when combined with neural networks. In this paper, we propose Multi-State Aggregated PoLicy Evaluation (MAPLE), a tree search method that aggregates policy and value evaluations from multiple sampled world states within a single search tree, combining the advantages of PIMC and IS-MCTS while maintaining a controllable computational cost. We further incorporate a Siamese-based sampling strategy to select informative world states from the information set. Experiments on Phantom Go and Dark Hex show that MAPLE significantly outperforms the PIMC-based AlphaZero baseline, achieving Elo improvements of 291 and 136, respectively. These results demonstrate that MAPLE is an effective approach for AlphaZero-style learning in imperfect-information games. --- ### Understanding Conversational Patterns in Multi-agent Programming: A Case Study on Fibonacci Game Development Authors: Srijita Basu, Viktor Kjellberg, Simin Sun, Bengt Haraldsson, Md. Abu Ahammed Babu, Wilhelm Meding, Farnaz Fotrousi, Miroslaw Staron Published: 2026-05-22 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2605.24138v1 Large Language Models (LLMs) are increasingly applied to software engineering (SE), yet their potential for autonomous, role-oriented collaboration remains largely underexplored. Understanding how multiple LLM-based agents coordinate, maintain role alignment, and converge on solutions is critical for SE, as naively allowing agents to interact does not reliably lead to correct or stable outcomes. Recent empirical studies show that unstructured or poorly understood interaction dynamics can result in error propagation, premature consensus on incorrect solutions, or prolonged disagreement that prevents convergence, even when correct partial solutions are present early in the interaction. As an initial step towards addressing this underexplored area, we undertake a systematic analysis of conversations between two agents, a Designer and a Programmer across 12 model combinations from 7 open-source LLMs (Gemma 2, Gemma 3, LLaMA 3.2, LLaMA 3.3, DeepSeek-R1, MiniCPM, and Qwen3). Our systematic approach reveals three key dimensions of multi-agent interaction: efficiency (the speed and stability of convergence), consistency (the degree of role alignment visualized by BLEU and ROUGE), and effectiveness (the extent of compilation success and error resolution). Results show that the DeepSeek-R1:DeepSeek-R1 pair was unique in converging to the correct solution from the very first iteration and sustaining it consistently to the final iteration, while LLaMA 3.2:LLaMA 3.2 and Qwen3:Qwen3 demonstrated strong Designer:Programmer role alignment despite of diverging from the correct solution. The other pairs deviated from the task, never to converge to a result. These findings advance understanding of agentic programming and highlight the need for further research on understanding and calibrating convergence and stop conditions essential for future autonomous SE. --- ### Empirical Analysis and Detection of Hallucinations in LLM-Generated Bug Report Summaries Authors: Hinduja Nirujan, Shreyas Patil, Abdallah Ayoub, Ahmad Abdel Latif, Gouri Ginde Published: 2026-05-22 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2605.24137v1 Large Language Models (LLMs) are increasingly used to generate summaries of software bug reports, including sections such as Steps-to-Reproduce (S2R), Actual Behavior (AB), and Expected Behavior (EB). However, these models frequently produce hallucinations that can be convincing but unsupported by the source report. This can mislead developers and reduce trust in automated maintenance tools. Existing hallucination detection approaches typically evaluate outputs at the full-response level and do not consider the structure of technical documents. An initial exploratory study on 80 structured bug report summaries found that approximately 47.9% contained missing information, while 12.3% included fabricated content, highlighting the need for systematic hallucination analysis in bug report summarization. In this work, we empirically investigate hallucinations in LLM-generated bug report summaries from a section-aware perspective. Using the BugsRepo dataset, derived from Mozilla OSS projects, we introduce controlled synthetic hallucination injection to construct a benchmark for training and evaluation. We propose a section-aware hallucination detection approach that jointly predicts whether a summary contains hallucinated content, identifies affected sections, and classifies hallucination types. Experimental results across multiple pretrained language models show that the proposed approach achieves strong performance across all tasks, with the best model obtaining 0.89 report-level Macro-F1, 0.83 section-level Macro-F1, and 0.84 hallucination-type Macro-F1. We further analyze common hallucination patterns and model failure modes to better understand limitations of current LLM-generated bug report summaries. The findings highlight the importance of section-aware hallucination analysis for improving the reliability of LLM-assisted bug report summarization in software maintenance workflows. --- ### Detecting Metastable Basins in High Dimensions via Marginal Trajectory Distribution Discrimination Authors: Taj Jones-McCormick Published: 2026-05-22 Categories: stat.ML, cs.LG, stat.CO arXiv: https://arxiv.org/abs/2605.24136v1 We study the problem of identifying dynamically distinct basins of attraction in high dimensional time-homogeneous Markov processes using only trajectory sampling. This problem is fundamental in the analysis of metastable dynamical systems, where the process rapidly mixes within basins while transitions between basins occur rarely on the timescale of interest, or even when the state space is reducible. Existing approaches typically rely on spatial discretization or spectral analysis of estimated transition operators, which can become unreliable in high dimensional settings or when the underlying basin geometry is highly nonlinear. We propose a discriminative approach to basin identification based on marginal trajectory distribution comparison. We prove a simple risk separation result: if two initial states belong to the same basin, the Bayes-optimal classifier distinguishing their marginal trajectory distributions achieves risk close to 1/2, whereas if they lie in distinct basins, the optimal risk is close to zero. This observation reduces basin detection to a two-sample discrimination problem between marginal trajectory distributions. Motivated by this principle, we develop a neural algorithm that receives a set of candidate basin representatives and iteratively merges them by estimating classification risk with a neural network that approximates the Bayes classifier. We evaluate the method on various metastable systems. These include synthetic systems constructed by embedding low-dimensional dynamics into high dimensional noisy ambient spaces. In these settings, standard spectral and clustering-based methods often fail, while our approach accurately recovers the underlying basin structure. These results display a shortcoming of existing methods and highlight trajectory discrimination as an effective tool for identifying dynamical basins in high dimensional stochastic systems. --- ### ImPartial: Multi-channel Whole-Cell Segmentation using Partial Annotations Authors: Gunjan Shrivastava, Saad Nadeem Published: 2026-05-22 Categories: cs.CV arXiv: https://arxiv.org/abs/2605.24128v1 Accurate cell segmentation in pathology images typically requires dense pixel-wise annotations, which are costly and time-consuming to obtain. This challenge is especially important for emerging biological imaging modalities and multiplexed datasets with variable channel configurations, where expert-labeled data are scarce. In this work, we introduce ImPartial, a deep learning framework designed to achieve state-of-the-art segmentation performance in low-annotation regimes using sparse scribbles and limited supervision. ImPartial augments the segmentation objective via self-supervised multi-channel quantized imputation. This approach leverages the observation that perfect pixel-wise reconstruction or denoising of the image is not needed for accurate segmentation, and thus, introduces a self-supervised classification objective that better aligns with the overall segmentation goal. We demonstrate that ImPartial achieves performance at par with fully supervised models while requiring substantially fewer annotations. Extensive experiments on benchmark multiplexed cellular imaging and single-plex clinical brightfield immunohistochemistry datasets show consistent improvements over strong baselines with only partial annotations. All benchmark datasets and code are available via our Github: https://github.com/nadeemlab/ImPartial. --- ### SkillEvolBench: Benchmarking the Evolution from Episodic Experience to Procedural Skills Authors: Yingtie Lei, Zhongwei Wan, Jiankun Zhang, Samiul Alam, Zixuan Zhong, Peizhou Huang, Xin Wang, Jingxuan Zhang, Donghao Zhou, Yunta Hsieh, Zhihao Dou, Hui Shen et al. Published: 2026-05-22 Categories: cs.AI arXiv: https://arxiv.org/abs/2605.24117v1 Large language model (LLM) agents accumulate rich episodic trajectories while solving real-world tasks, but it remains unclear whether such experience can be distilled into reusable procedural skills. We introduce SkillEvolBench, a diagnostic benchmark for evaluating this step from experience reuse to skill formation. It contains 180 tasks across six real-world agent environments, organized into role-conditioned task families with shared latent procedures. Agents learn from acquisition tasks, update an external skill library using compacted trajectories and verifier feedback, and then face frozen deployment tasks testing context shift, adversarial shortcuts, and composition. By comparing self-generated and curated-start skill evolution against no-skill and raw-trajectory controls, SkillEvolBench separates procedural abstraction from base capability, curated prior knowledge, and direct reuse of episodic traces. Across ten model configurations and three agent harnesses, we find that current agents often adapt locally but rarely form robust reusable skills. Skill-based conditions can improve acquisition or replay, and individual models sometimes gain on specific deployment axes, but these gains are unstable under frozen deployment. Raw-trajectory reuse frequently outperforms distilled skills, suggesting that current abstraction procedures discard contextual and procedural cues that remain useful for future tasks. Capacity and cost analyses further show that writing more skills or larger Tier-3 resource libraries is not sufficient: additional updates can improve coverage while introducing episode-specific drift and procedural clutter. These findings position SkillEvolBench as a testbed for measuring when one-off experience becomes durable procedural knowledge rather than task-local memory. --- ### COSY: Compositional 3DGS Synthesis for Disentangled Human Head Editing Authors: Florian Barthel, Shalini De Mello, Koki Nagano, Wieland Morgenstern, Anna Hilsmann, Peter Eisert Published: 2026-05-22 Categories: cs.CV arXiv: https://arxiv.org/abs/2605.24114v1 Recent 3D Gaussian Splatting (3DGS) GANs for human heads synthesize and render photorealistic 3D models in real-time and offer a vast variety in identity and appearance. However, controlling specific semantic attributes such as hair color or glasses remains challenging, as edits in the entangled latent space often induce unintended changes in identity or appearance. Although there are several methods that aim to disentangle the latent space post training by estimating directions that only modify certain features, these methods cannot guarantee complete disentanglement and often require pre-trained classifiers. In our approach, we propose a new generator architecture that synthesizes components, such as hair, skin, glasses, and torso, completely independently. This allows for changing the latent vector for one region while keeping the remaining parts fixed. Further, we achieve this separation using only sparse information such as the hair or skin color, eliminating the requirement of segmentation masks or geometric priors, often seen in prior work. To ensure matching shape and lighting conditions during editing, we allow minimal shared information via context tokens between the independent generators. These tokens even allow us to control the shape and light, without any prior annotation. Compared to existing works on GAN-based generation and editing, our method shows better disentanglement, more precise editing control, and competitive visual quality. --- ### Riemannian Archetypal Analysis: Interpretable non-linear data analysis on deformed star distributions Authors: Willem Diepeveen, Deanna Needell Published: 2026-05-22 Categories: cs.LG, math.DG, math.OC, math.ST arXiv: https://arxiv.org/abs/2605.24113v1 Classical archetypal analysis is appealing for its interpretability, but its linear geometry can limit performance on data with strongly non-linear structure; at the same time, existing neural extensions improve flexibility while often weakening the geometric meaning of archetypes and interpolations. In this work, we develop a Riemannian version of archetypal analysis based on data-driven pullback geometry for real-valued data, with the goal of combining the interpretability of classical archetypal analysis with the expressive power of modern non-linear models. We introduce a class of deformed star distributions together with associated pullback Riemannian geometry to provide a statistical interpretation of the resulting manifold mappings, define the Riemannian archetypal mapping (RAM) as a projection onto the manifold of geodesically convex combinations of archetypes, and propose a practical optimization scheme based on convex relaxation followed by non-convex refinement. We further propose a learning scheme that yields reasonable, albeit generally suboptimal, deformed star distributions from data. Experiments on synthetic examples and MNIST show that the resulting framework produces meaningful geodesics, useful denoising projections, and geometry-aware classifications, while also clarifying where current optimization limitations remain. --- ### MASt3R-Nav: WayPixel Navigation in Relative 3D Maps Authors: Vansh Garg, Rohit Jayanti, Krish Pandya, Sarthak Chittawar, Siddharth Tourani, Muhammad Haris Khan, Sourav Garg, Madhava Krishna Published: 2026-05-22 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2605.24111v1 Visual navigation ability is strongly tied to its underlying representation of the world. Unlike classical 3D maps that require globally-consistent geometry, image- or object-relative topological graphs almost entirely do away with geometric understanding. But, this comes at the cost of navigation capability, often limiting it to merely teach-and-repeat. In this work, we propose a novel map representation in the form of pixel-relative connectivity, which is geometrically accurate but does not require global geometric consistency. Inspired by recent progress in 3D grounded image matching, we construct a map from an image sequence through inter-image connectivity based on pixel correspondences in the relative 3D coordinate systems of individual image pairs. We then use this pixel-level graph to perform global path planning by approximating and sparsifying intra-image pixel connectivity. Through this, we derive a ''WayPixel Costmap'' representation and train a controller conditioned on it to predict a trajectory rollout. We show that this dense pixel-level costmap based on relative geometry is a more accurate conditioning variable for control prediction than its image- and object-level counterparts. This enables a highly capable navigation system, as validated on four types of navigation tasks in the simulator and through real world demonstrations. --- ### EvoCode-Bench: Evaluating Coding Agents in Multi-Turn Iterative Interactions Authors: Haiyang Shen, Xuanzhong Chen, Wendong Xu, Yun Ma, Liang Chen, Kuan Li Published: 2026-05-22 Categories: cs.AI arXiv: https://arxiv.org/abs/2605.24110v1 Coding agents are increasingly used as iterative development partners, but most benchmarks still evaluate one specification followed by one final assessment. This leaves out a basic question: can an agent keep its own codebase working as requirements change? We introduce EvoCode-Bench, a benchmark of 26 stateful coding tasks and 227 evaluated rounds. Each task preserves the agent's workspace for 5-15 rounds, states requirements through observable behavior, and uses cumulative executable tests to check new requirements and still-active prior ones. We evaluate 13 coding agents with two metrics: MT@4, a four-attempt fail-stop multi-round score, and SR, a single-round score from a reference-completed prior state. For most agents, SR exceeds MT@4 by 22-40 points. The gap also changes rankings: the highest-SR agent (78.9) ranks only third in persistent execution (44.0 MT@4). Even the strongest agents achieve only about 50% success on multi-turn metrics, and aggregate pass rate drops below half of round-1 performance by round 5. Failure analysis shows tier-dependent behavior: weaker agents fail early, while stronger agents survive long enough to expose specification-tracking and regression failures. We release the benchmark data and Harbor multi-turn infrastructure. --- ### Overcoming "Physics Shock" in Earth Observation A Heteroscedastic Uncertainty Framework for PINN-based Flood Inference Authors: Tewodros Syum Gebre, Jagrati Talreja, Matilda Anokye, Leila Hashemi-Beni Published: 2026-05-22 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2605.24106v1 Rapid and accurate flood extent mapping from Remote Sensing data, such as Synthetic Aperture Radar (SAR), is critical for operational disaster response, but standard Deep Learning models often produce physically impossible predictions due to a lack of hydrological constraints. While PhysicsInformed Neural Networks (PINNs) attempt to address this by embedding governing laws directly into the loss function, their application to real-world remote sensing data frequently fails. Enforcing rigid spatial derivatives (e.g., the 2D Shallow Water Equations) onto unconditioned latent spaces attempting to fit noisy SAR speckle causes catastrophic gradient divergence, a phenomenon we term Physics Shock. In this paper, we propose a novel Uncertainty-Aware PINN framework tailored specifically for applied Earth Observation that addresses this instability. By integrating a dynamic Warm-Start protocol and modeling heteroscedastic aleatoric uncertainty via a negative log-likelihood objective, the network learns to dynamically relax physical constraints in regions of high sensor noise while strictly enforcing them in high-confidence areas. Evaluated on the Sen1Floods11 dataset, our probabilistic Attention-Gated FNO-UNet successfully stabilizes multi-objective optimization, achieving a +25% relative improvement in Intersection over Union (IoU) compared to deterministic baselines. Furthermore, through Deep Ensembles, we successfully disentangle intrinsic sensor noise from out-of-distribution terrain ignorance, providing operational agencies with highly calibrated, physically consistent confidence bounds for robust disaster mitigation and real-time decision-making. --- ### D2-V2X: Depth-Driven Cooperative V2X Reasoning for Autonomous Driving Authors: Kevin Richard, Alphin Varghese, Colin Pham, David Oh, Srijan Das Published: 2026-05-22 Categories: cs.CV arXiv: https://arxiv.org/abs/2605.24098v1 Single-vehicle Vision-Language Models (VLMs) are fundamentally constrained by sensor occlusions. While Vehicle-to-Everything (V2X) systems mitigate this, current benchmarks lack the cooperative reasoning required for resolving ambiguities in complex environments. We introduce D2-V2X, a spatially-aware Question-Rationale-Answer (QRA) benchmark featuring 8,500 triplets derived from multimodal vehicle and infrastructure sensors. We additionally establish a baseline that aligns 3D LiDAR features with the VLM's latent space. By enforcing natural language Chain-of-Thought rationales prior to structured JSON outputs, our model is forced to explicitly articulate spatial relations. Our experiments demonstrate that grounding VLMs in cooperative LiDAR achieves 24.4% recall in identifying occluded hazards compared to near-zero in zero-shot models and reduces spatial estimation error for visible objects by 77% compared to the zero-shot baseline. While the model achieves a functional decision-making F1-score of 53.5, we identify 3D-to-2D projection as a fundamental bottleneck in current VLM architectures, establishing a new baseline for future innovation. Data, code, and trained models available at https://github.com/KevinRichard1/D2-V2X --- ### The Time is Here for Just-in-Time Systems: Challenges and Opportunities Authors: Shu Liu, Alexander Krentsel, Shubham Agarwal, Mert Cemri, Ziming Mao, Soujanya Ponnapalli, Alexandros G. Dimakis, Sylvia Ratnasamy, Matei Zaharia, Aditya Parameswaran, Ion Stoica Published: 2026-05-22 Categories: cs.DB, cs.AI, cs.DC, cs.SE arXiv: https://arxiv.org/abs/2605.24096v1 Core systems like key-value stores have historically taken years to build, and are designed to be general so as to amortize cost across deployments, paying a significant performance cost. We argue that LLM-based coding agents now make a different approach tractable: Just-in-Time Systems, in which the entire system is synthesized from scratch, specialized to the environment, workload, and required system properties. We present a JIT system synthesis pipeline, Jitskit, and explore its effectiveness in synthesizing key-value stores from spec cards that span different YCSB workloads, deployment constraints (e.g., compute resources), and system properties (e.g., consistency and durability). Jitskit iteratively refines a system implementation to match the specification against an evolving evaluation test suite. The resulting synthesized systems are performant, beating comparable state-of-the-art systems on 18 of 18 specs tried, by up to 4.6x over the best off-the-shelf baseline on the most favorable spec. Naively running Claude Code either reward-hacks or underperforms Jitskit by up to 5.4x. We discuss the challenges we overcame in building Jitskit and our key takeaways. --- ### Verified SHAP: Provable Bounds for Exact Shapley Values of Neural Networks Authors: David Boetius, Shahaf Bassan, Guy Katz, Stefan Leue, Tobias Sutter Published: 2026-05-22 Categories: cs.LG, cs.AI, cs.LO arXiv: https://arxiv.org/abs/2605.24084v1 Shapley additive explanations (SHAP) are widely recognised as computationally intractable for neural networks, since they induce an exponential search space over the input features. In this work, we take a first step towards scaling exact SHAP computation to larger search spaces by introducing an algorithm that leverages recent advances in neural network verification to compute arbitrarily tight exact lower and upper bounds on SHAP values for neural networks, ultimately recovering the exact SHAP values. We demonstrate that our approach scales to orders of magnitude larger search spaces than state-of-the-art exact methods. This provides an important first step towards exact SHAP computation and establishes a principled cornerstone for evaluating statistical approximation methods on larger search spaces. --- ### TRACER: A Semantic-Aware Framework for Fine-Grained Contamination Detection in Code LLMs Authors: Yifeng Di, Xuliang Huang, Tianyi Zhang Published: 2026-05-22 Categories: cs.SE, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2605.24079v1 Data contamination is a known threat to the reliability of model evaluation. However, it remains underexplored in code large language models (LLMs), where contamination often goes beyond exact duplication. We present TRACER, a semantic-aware framework for fine-grained code contamination detection. TRACER models contamination using three levels of semantic overlap - Functionally Identical, Nearly Identical, and Shared Logic - and detects them through a coarse-to-fine pipeline. We also introduce the first benchmark for fine-grained code contamination detection, spanning three widely used benchmarks and three representative post-training datasets. TRACER achieves strong and consistent performance across multiple LLM backbones, with GPT-5 reaching an F1 score of 0.91 in fine-grained detection. In the binary setting, TRACER attains an F1 of 0.92, outperforming existing methods by 42%-217%. We further conduct ablation studies and error analysis to assess the contributions of individual components in TRACER. --- ### LWM-CDE: A Representation Space for Wireless Data Reasoning and Transferability Authors: Sadjad Alikhani, Akshay Malhotra, Shahab Hamidi-Rad, Ahmed Alkhateeb Published: 2026-05-22 Categories: eess.SP, cs.LG arXiv: https://arxiv.org/abs/2605.24077v1 Machine learning deployments in real-world wireless communication tasks face significant generalization challenges due to location and environment-specific signal structure, high diversity in data across different deployments, and limited availability of real-world data. Current approaches for assessing data similarity between training and inference (deployment) distributions, as well as evaluating model transferability, suffer from high computational costs and inconsistent performance, leaving critical model deployment and model life cycle management decisions without a principled foundation. To address this, we introduce a dataset similarity framework built upon the feature space of a pretrained wireless foundation model. Our method, LWM-CDE (Contrastive learning of Dataset Embedding), fine-tunes the dataset embeddings of the foundation model using a combination of contrastive and geometry-shaping losses, creating a structured manifold where distance reliably indicates transferability. Extensive experiments on wireless benchmarks show that LWM-CDE achieves stronger correlation with empirical transfer performance than existing metrics while being more computationally efficient. The learned representation space supports more effective and data-efficient decision-making for tasks like source dataset selection, label-aware augmentation, and budgeted pretraining, demonstrating its broader utility across different wireless communication applications. --- ### Causality as the Statistical Conscience of Artificial Intelligence: From Pearl's Ladder to Trustworthy Machines Authors: Ernest Fokoué Published: 2026-05-22 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2605.24076v1 Modern Artificial Intelligence achieves remarkable predictive power by optimizing statistical risk functionals over vast corpora. Yet a gap separates this from genuine intelligence: the inability to distinguish correlation from causation. This paper argues that causal inference (identifying mechanisms invariant under intervention) is AI's indispensable statistical conscience. Without causal grounding, AI systems are correlation machines: powerful in familiar domains, brittle under distribution shift, and biased in high-stakes settings. Three contributions develop this argument. First, a Statistical Necessity Theorem for Causal Generalization: any algorithm achieving out-of-distribution generalization must encode causal structure, formalizing the distinction between prediction P(Y|X) and intelligence P(Y|do(X)). Second, a unified framework connects Pearl's do-calculus, the Potential Outcomes framework, Double Machine Learning, and Invariant Risk Minimization as a family of Causal Statistical Estimators, each identifying interventional distributions under different assumptions. Third, three AI failure modes (hallucination in large language models, reward hacking in reinforcement learning from human feedback, and degradation under distribution shift) are manifestations of causal blindness, each admitting a principled statistical remedy. Trustworthy AI is, at its core, a problem of causal statistics. The statistical community is not merely equipped to solve it -- it is the only community with the foundational tools to do so rigorously. --- ### WideDepth: Millimeter-Accurate Benchmark for Fisheye Depth Estimation Authors: Ilia Indyk, Ignat Penshin, Ivan Sosin, Maxim Monastyrny, Aleksei Valenkov, Ilya Makarov Published: 2026-05-22 Categories: cs.CV, cs.RO arXiv: https://arxiv.org/abs/2605.24074v1 Fisheye cameras are increasingly adopted in robotics for near-field manipulation, navigation, and immersive perception, yet indoor depth benchmarks with accurate ground truth are still missing. To address this, we introduce WideDepth - the first indoor dataset for fisheye depth estimation, featuring 101 scenes containing 5K high-resolution stereo pairs labeled with millimeter-level ground truth depth and disparity. Our dataset also includes paired pinhole and fisheye samples across varying fields of view and baselines in both horizontal and vertical stereo setups. We further propose a method to adapt pinhole-trained stereo models to fisheye images and introduce a novel stereo fisheye image generation pipeline based on high-resolution LiDAR scans. Leveraging these methods, we thoroughly evaluate state-of-the-art monocular depth, stereo matching, and depth completion models on our benchmark. Additionally, we provide 18K LiDAR-derived sparse depth training samples, achieving up to a 62% performance boost on fisheye data when fine-tuning pinhole-based stereo models. In summary, the high precision and versatility of our benchmark set a strong foundation for advancing research in fisheye depth estimation and robotics perception. Project page: https://ilyaind.github.io/WideDepth --- ### Multitask learning with semiempirical orbital charges enables sample-efficient MLIPs Authors: Ihor Neporozhnii, Sjoerd Hoogland, Oleksandr Voznyy Published: 2026-05-22 Categories: physics.chem-ph, cs.LG arXiv: https://arxiv.org/abs/2605.24073v1 Machine learning interatomic potentials (MLIPs) require generating computationally expensive, large-scale training datasets to accurately simulate materials and molecules. Incorporating electronic structure information using multitask learning improves sample efficiency, however, training on full Hamiltonian matrices, which scale quadratically with the number of atoms, is intractable for large datasets. In this work, we show that multitask learning utilizing orbitally resolved semiempirical charges significantly improves sample efficiency and accuracy in MLIPs. To efficiently predict orbital charges, we implement a specialized equivariant model, reducing charge prediction error compared to an invariant baseline. By augmenting training with computationally inexpensive GFN1-xTB orbital charges, which scale linearly with the number of atoms, our model achieves a 46\% reduction in energy mean absolute error and requires five times less data to match the performance of energy-only models. Furthermore, our approach outperforms models trained on expensive density functional theory (DFT) atomic charges, capturing orbitally resolved electronic complexity and forcing the network to learn a physically accurate latent space that spontaneously clusters metals by shared chemical properties. Because orbital charges are only required during training, this approach preserves inference efficiency, providing a scalable recipe for developing accurate, data-efficient foundation models for complex chemical systems. --- ### Optimal Non-Asymptotic Edgeworth Expansions for Multivariate Neural Network Outputs Authors: Lucia Celli Published: 2026-05-22 Categories: stat.ML, cs.LG, math.PR arXiv: https://arxiv.org/abs/2605.24072v1 Finite-width fully connected neural networks with Gaussian-initialized weights deviate from their infinite-width Gaussian limit, exhibiting non-vanishing higher-order cumulants. We approximate these deviations, for a neural network evaluated in a finite number of inputs, using multidimensional Edgeworth expansions of arbitrary order $4m-1$, with $m\in\mathbb{N}$. Assuming that the corresponding Gaussian limit has an invertible covariance matrix and that the activation function is polynomially bounded, we establish a bound of order $n^{-m}$ on the total variation distance between the law of the true network output and its Edgeworth approximation, with matching lower bounds. As an application, we quantify the error in Bayesian posterior distributions when the prior is replaced by its Edgeworth expansion. Our results are more general and also apply to sequences of conditionally Gaussian vectors converging to a Gaussian vector with invertible covariance. ---