# Research Papers — 2026-05 · bundle page 166 of 326 > Full-text markdown of papers #8251–8300 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/166 [← Previous bundle](https://aipod.dev/papers/archive/2026-05/page/165.md) [Next bundle →](https://aipod.dev/papers/archive/2026-05/page/167.md) ### Counterparty Modeling is Not Strategy: The Limits of LLM Negotiators Authors: Romain Cosentino, Sarath Shekkizhar, Adam Earle, Silvio Savarese Published: 2026-05-15 Categories: cs.AI arXiv: https://arxiv.org/abs/2605.16575v1 Negotiation requires more than inferring what the other side wants: it requires using that information to make advantageous offers and counteroffers over multiple turns. We study whether large language model (LLM) agents do this in a controlled multi-attribute bargaining environment. We find that current LLM agents can model a counterparty's preferences, but do not reliably turn that knowledge into strategic bargaining. When given negotiating partner preference information, agents model it accurately and early in their reasoning traces, yet this does not reliably improve outcomes for the informed side. Turn-level analyses show why: agents often respond to what they believe the counterparty values, but do not consistently pair those moves with gains on their own high-value attributes. Sellers are more accommodating overall, and in asymmetric-information conditions, the informed side often makes the more weakly compensated concessions. Because agents fail to leverage this underlying utility structure for strategic advantage, their final agreements are heavily dictated by surface-level opening anchors rather than actual utility weights. Finally, requiring agents to explicitly state concession-for-reciprocity trades before making an offer makes individual turns look more strategic, but ultimately fails to improve the efficiency of the final agreements. --- ### Wavelet Flow Matching for Multi-Scale Physics Emulation Authors: Gabriele Accarino, Juan Nathaniel, Carla Roesch, Pierre Gentine, Sara Shamekh, Duncan Watson-Parris, Viviana Acquaviva Published: 2026-05-15 Categories: cs.LG, cs.AI, physics.flu-dyn arXiv: https://arxiv.org/abs/2605.16573v1 Accurate emulation of multi-scale physical systems governed by PDEs demands models that remain stable over long autoregressive rollouts while preserving fine-scale structures. Deterministic emulators produce overly-smoothed predictions, while generative approaches better capture details but are costly. Latent-space generative models have emerged as a compromise but with the additional cost of separately pre-trained autoencoders. We propose Wavelet Flow Matching (WFM), a novel generative emulator that overcomes current trade-offs between cost and skill by performing optimal-transport directly in the multi-scale wavelet space. Rather than learning a latent compression, WFM leverages the hierarchical structure of a U-Net to jointly predict transport velocities of a prescribed wavelet representation. On three challenging systems of chaotic fluid dynamics, WFM achieves superior long-horizon stability, accuracy and spectral coherence compared to state-of-the-art models. Our results clearly position the wavelet space as an effective training-free representation for generative emulation of complex physical dynamics. --- ### TriALS: Triphasic-Aided Liver Lesion Segmentation Benchmark in Non-Contrast CT Authors: Marawan Elbatel, Mohamed Ghonim, Jiaji Mao, Zhuosheng Lin, Katharina Eckstein, Andrés Martínez Mora, Jonathan Deissler, Maximilian Rokuss, Constantin Ulrich, Zdravko Marinov, Wenhui Deng, Baoxun Li et al. Published: 2026-05-15 Categories: cs.CV arXiv: https://arxiv.org/abs/2605.16572v1 Automated segmentation of liver lesions on non-contrast computed tomography (NCCT) is clinically important but fundamentally challenging, particularly in low-resource settings across Africa and Asia where contrast agents are frequently unavailable. Progress has been limited by the absence of annotated NCCT benchmarks. Here we describe the TriALS challenge for automated liver lesion segmentation under contrast-limited conditions, supported by a multi-centre dataset of 150 cases with four-phase CT acquisitions (600 volumes) from Egyptian and Chinese institutions. Algorithms were evaluated on 70 cases from three institutions, including an independent external cohort. The top-performing method achieved a mean venous-phase Dice of 0.754, consistent with human-level performance, yet dropped to 0.57 on NCCT. On external validation, the leading method outperformed off-the-shelf models by up to 28% in Dice on NCCT. Algorithm performance was most strongly predicted by training data scale and pre-training strategy. A cross-year comparison exposed a persistent perceptual barrier on NCCT that scaling pre-training alone cannot overcome. Data, annotations, and code are available at https://github.com/xmed-lab/TriALS. --- ### Isotonic Survival Regression: Calibrated Survival Distributions from Deep Cox Models Authors: Anchit Jain, Kevin Zhang, Stephen Bates Published: 2026-05-15 Categories: stat.ML, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2605.16571v1 Time-to-event data is widespread across the life sciences and engineering, but it is typically encountered together with censoring, which complicates the application of standard machine learning methods. Deep Cox models have emerged as a popular method for analyzing time-to-event data because they gracefully handle censoring and can be used with unstructured data such as clinical text reports, genomic sequences, and pathology images. However, their predicted survival probabilities are often poorly calibrated, thus limiting their practical utility. In this paper, we propose a novel post hoc calibration method for Deep Cox models that uses isotonic regression to refine predicted survival probabilities without affecting discriminative power. We establish favorable theoretical guarantees, including a double-robustness property and asymptotic calibration. Experiments on synthetic and real-world clinical data demonstrate the empirical effectiveness of our method. --- ### A Cubing Strategy for Identifying Stable Hyperparameter Regions for Uncertainty Quantification in Spatial Deep Learning Authors: Isaac Amouzou, Ben Seiyon Lee Published: 2026-05-15 Categories: stat.CO, stat.ML arXiv: https://arxiv.org/abs/2605.16570v1 Spatially referenced datasets have become increasingly prevalent across many fields, largely driven by advances in data collection methods such as satellite remote sensing. In many applications, predictions at unobserved locations are accompanied by reliable uncertainty estimates. While deep learning methods provide both scalable and accurate models for spatial predictions, there remains no clear consensus for addressing uncertainty quantification in spatial deep learning. Monte Carlo (MC) dropout has become a popular approach for uncertainty quantification, yet existing implementations typically focus on tuning the dropout rate while fixing other influential hyperparameters, such as weight decay and the predictive standard deviation multiplier, often through ad-hoc or manual tuning. We propose a cubing-based diagnostic framework that recursively partitions the hyperparameter space to identify stable regions where MC dropout yields well-calibrated predictive intervals. The approach evaluates hyperparameter regions using scoring rules relative to a statistical baseline model, which serves as a calibration anchor. Through a simulation study spanning multiple spatial dependence regimes as well as a large remotely-sensed land surface temperature dataset, we demonstrate that our approach produces competitive or superior predictive intervals compared to the baseline model. Our methodology provides practitioners with a systematic procedure for incorporating uncertainty quantification into spatial deep learning models. --- ### Scalable Uncertainty Reasoning in Knowledge Graphs Authors: Jingcheng Wu Published: 2026-05-15 Categories: cs.AI arXiv: https://arxiv.org/abs/2605.16568v1 Knowledge Graphs are pivotal for semantic data integration. The real-world data they model is often inherently uncertain. Within knowledge graphs, uncertainty manifests in three distinct levels: imprecise attribute values, probabilistic triple existence, and incomplete schema knowledge. However, current Semantic Web standards lack native support for reasoning over such uncertainty, and naïve extensions often incur computational intractability. In this thesis, I aim to develop a modular framework that addresses each level through tailored techniques: (1) defining probabilistic literals and a corresponding query algebra for continuous attributes; (2) a compilation-based framework transforming SPARQL provenance into tractable probabilistic circuits for uncertain triples; and (3) topology-aware geometric embeddings for statistical schema reasoning. The central hypothesis is that specialized reasoning mechanisms, namely algebraic, logical, and geometric approaches, can reconcile semantic precision with computational tractability. --- ### Automatic Unsupervised Ensemble Outlier Model Selection--Extended Version Authors: Hong-Phuc Phan, Tuan-Anh Vu, Tung Kieu, Son Ha Xuan, Bin Yang, Christian S. Jensen Published: 2026-05-15 Categories: cs.LG, cs.AI, cs.DB arXiv: https://arxiv.org/abs/2605.16567v1 Unsupervised outlier detection is attractive because it eliminates the need for labeled data. Moreover, forming multi-model ensembles can improve detection robustness. However, composing an ensemble without labeled data is challenging. Naively composed ensembles can suffer from ensemble saturation, where redundant or unreliable detection models degrade performance and incur unnecessary computation. We propose MetaEns, an automatic unsupervised framework for selecting ensembles of outlier detection models. Using labeled meta-datasets, MetaEns learns a model that predicts marginal ensemble gains, estimating the expected improvement from adding a candidate model to a partially constructed ensemble. At test time, this learned signal is combined with a submodular-inspired proxy objective that enforces diminishing returns through diversity-aware discounting and family-level risk regularization, thereby enabling greedy sequential selection with adaptive early stopping. As a result, MetaEns constructs compact, high-quality ensembles without access to ground-truth labels. Experiments on 39 real-world datasets show that MetaEns consistently outperforms state-of-the-art unsupervised selectors and ensemble baselines, achieving higher average precision while using fewer models. --- ### Skim: Speculative Execution for Fast and Efficient Web Agents Authors: Mike Wong, Kevin Hsieh, Suman Nath, Ravi Netravali Published: 2026-05-15 Categories: cs.AI, cs.OS arXiv: https://arxiv.org/abs/2605.16565v2 Skim is a speculative execution framework for web agents that exploits the predictable structure of purpose-built websites. Today's web-agent expense is not intrinsic to the tasks but a property of how agents are composed: frontier-model inference, browser rendering, and ReAct-style planning are applied to every step of every task regardless of complexity. Skim's key observation is that websites enforce stable URL patterns, answer formats, and task-to-trajectory mappings across queries of the same type, so most queries can bypass these heavyweight components entirely. An offline profiler captures these patterns once per site. At runtime, Skim matches each query to a template, synthesizes the destination URL, and extracts the answer with a small model. A lightweight verifier gates each fast-path output against the query and schema; rare misspeculations cascade to the full agent, warm-started by the fast path's final URL to preserve upstream trajectory progress. Across standard web-agent benchmarks paired with three backboneagents (WebVoyager, AgentOccam, BrowserUse), Skim reduces median per-task cost by 1.9x and latency by 33.4% with no accuracy loss. --- ### Scaling Accessible Mathematics on arXiv: HTML Conversion and MathML 4 Authors: Deyan Ginev, Brian Caruso, Bruce Miller, Jeff Sank, Jacob Weiskoff Published: 2026-05-15 Categories: cs.CL, cs.DL arXiv: https://arxiv.org/abs/2605.16562v1 We report on the ongoing development of arXiv's HTML Papers offering, available on every new TeX/LaTeX submission since its initial release in 2023. The main highlights from 2025 and early 2026 are: (i) community-driven improvements to HTML fidelity and service health, with roughly half of 6,000 user reports resolved; (ii) corpus-scale conversion work aimed at 90% error-free HTML (currently 75%); (iii) initial MathML 4 Intent annotations for accessible speech output; (iv) an in-progress Rust port of LaTeXML, reducing compute costs and enabling faster previews on submission. The arXiv HTML Papers project remains experimental, but is gradually maturing as we better understand the needs of arXiv's readers and the technical opportunities presented by new standards and by advances in programming languages and AI. --- ### From Prompts to Protocols: An AI Agent for Laboratory Automation Authors: Angelos Angelopoulos, James F. Cahoon, Ron Alterovitz Published: 2026-05-15 Categories: cs.AI, cs.RO arXiv: https://arxiv.org/abs/2605.16552v1 Automating science laboratories enables faster, safer, more accurate, and more reproducible execution of protocols, accelerating the discovery and testing of new materials, drugs, and more. However, setting up and running autonomous labs requires coordinating numerous instruments and robots, forcing scientists to write code, manage configuration files, and navigate complex software infrastructure. We present an AI agent architecture that integrates large language models with laboratory orchestration, enabling scientists to interactively create and monitor automated lab protocols using natural language. Integrated into the Experiment Orchestration System (EOS), the AI agent operates under an agentic loop with automated validation and error correction, and supports the complete experimental lifecycle: creating protocols, running and monitoring both protocols and closed-loop optimization campaigns, and analyzing results. A visual graph editor renders protocols as interactive node-based diagrams synchronized with the AI agent's protocol representation, enabling seamless alternation between AI-assisted and manual protocol construction. Evaluated on three simulated automated labs spanning chemistry, biology, and materials science, the AI agent achieves a 97% first-attempt protocol generation success rate and an order of magnitude reduction in required interface actions. --- ### PQR: A Framework to Generate Diverse and Realistic User Queries that Elicit QA Agent Failures Authors: Yunan Lu, Luigi Liu, Omar Yahia, Arpit Sharma, Zhou Yu Published: 2026-05-15 Categories: cs.CL arXiv: https://arxiv.org/abs/2605.16551v2 Evaluating LLM-based agents remains challenging because identifying meaningful failure cases often requires substantial human effort to design realistic test scenarios. Prior works primarily focus on automatically discovering agent failures induced by adversarial users, while overlooking queries with real user intents that also trigger agent failures. We introduce PQR, a framework that not only surfaces agent failures with respect to specific objectives (e.g., helpfulness, safety, etc.) but also resembles real users' intents. PQR operates through an iterative interaction between two complementary modules. The query refinement module performs rewrites to explore diverse query variations, while the prompt refinement module uses prior feedback to derive new objective-violating strategies and realism policies for refining prompts, which in turn generate failure-triggering yet realistic queries. We evaluate PQR on detecting an e-commerce QA agent's unhelpful responses. Our method uncovers 23% - 78% more unhelpful responses, and our generated queries are more diverse and realistic compared to previous methods. --- ### Attention-Aware Transformer-Based Aggregation Network for Video Periocular Recognition Authors: Luiz G F Carreira, Breno A Mariano, Victor H C de Melo, David Menotti, William Robson Schwartz Published: 2026-05-15 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2605.16550v1 Video periocular recognition is the task of recognizing an individual's identity based on the region around an individual's eyes. The periocular area is one of the most discriminative regions of the human face, making it suitable for recognition tasks. Its use as a biometric modality has emerged as an alternative, especially in surveillance scenarios where conventional biometric traits such as face or iris recognition become unfeasible due to unconstrained acquisition conditions. This paper proposes an attention-aware approach for video-based periocular recognition in surveillance environments. The framework consists of two main modules: feature embedding and aggregation. The feature embedding module is a deep convolutional neural network that maps periocular data to feature vectors. The aggregation module is an encoder-only transformer that adaptively learns to aggregate frame-level features into a single video representation and a feature vector for the still reference image. Experiments on the publicly available COX Face dataset show the robustness of the proposed method, consistently outperforming naive aggregation schemes. In the best scenario, the approach achieves $99.8\%$ of TPR@$1e^{-1}$ and $96.6\%$ of Rank-5. --- ### World Model-Enabled Causal Digital Twins for Semantic Communications in Physical AI Systems Authors: Lingyi Wang, Tingyu Shui, Walid Saad, Pascal Adjakple Published: 2026-05-15 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.16547v1 Semantic communication has emerged as a promising paradigm for enabling goal-oriented networking. However, most existing semantic communication solutions are tailored to one-shot tasks and optimize instantaneous performance. Hence, they cannot be used to support closed-loop dynamic systems with physical artificial intelligence (AI), in which the transmitted semantics affect not only the current inference outcome but also future control actions, state evolution, and ultimately long-horizon task performance. To address this gap, this paper investigates goal-oriented semantic communications for physical AI systems with closed-loop sensing-communication-inference-control. In particular, the problem of semantic communications is formulated as a long-term return-per-bit maximization under wireless bit-budget constraints while capturing both control efficiency and communication efficiency. To solve this problem, a novel causal information value (CIV) metric is introduced to evaluate the marginal contribution of each semantic token to the expected long-term return by transmission interventions. Then, a world-model-enabled causal digital twin (WM-CDT) framework is proposed to capture the dynamics of closed-loop physical AI systems and enable counterfactual reasoning for long-horizon imagined rollouts. Based on these imagined rollouts, an actor-critic policy is trained for long-horizon agent control with high data efficiency, while the semantic token selector is trained through CIV-per-bit evaluation. Extensive simulations on an AirSim-Sionna-based unmanned aerial vehicle (UAV) navigation simulator show that the proposed WM-CDT framework achieves significant improvement in return-per-kbit and navigation success rate compared to existing reinforcement learning solutions. --- ### Symphony for Speech-to-Text: Supporting Real-Time Medical Voice Interfaces Authors: Arne Nix, Robert James, Lasse Borgholt, Anna B. Ekner, Lana Krumm, Julius Severin, Dan Engel, Lars Maaløe, Jakob Havtorn Published: 2026-05-15 Categories: cs.LG, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2605.16545v2 After decades of use in dictation and, more recently, ambient documentation, speech is emerging as a primary modality for interacting with technology and AI in healthcare. Yet medical speech recognition remains difficult: systems must capture specialized terminology, resolve contextual ambiguity, and render measurements, abbreviations, and clinical shorthand precisely. Existing solutions are typically optimized either for general-purpose transcription or narrow dictation workflows, limiting their reliability in safety-critical settings and their usefulness for broader clinical workflows. We introduce Symphony for Speech-to-Text, a medical-grade speech recognition system for real-time streaming and batch file-based clinical use. Symphony decomposes the transcription process into specialized components for recognition, formatting, and contextual correction to optimize medical term recall while producing clinically structured text in real time and adapting across use cases. Evaluations on public benchmark and medical speech datasets show that Symphony substantially outperforms state-of-the-art systems in clinical settings while matching or exceeding them in general-domain settings, suggesting robust generalization rather than overfitting. We release a clinical benchmark dataset to support reliable validation and further progress in medical speech recognition. Symphony is available through a production-grade API for live dictation, conversational transcription, and batch audio file processing. --- ### LLMs in Qualitative Research: Opportunities, Limitations, and Practical Considerations Authors: Henry Salgado, Meagan R. Kendall, Martine Ceberio, Alexandra Coso Strong Published: 2026-05-15 Categories: cs.HC, cs.CL arXiv: https://arxiv.org/abs/2605.16538v1 This paper examines the opportunities, limitations, and practical considerations associated with the use of large language models (LLMs) in qualitative research. Drawing on a multidisciplinary perspective that combines expertise in qualitative methods and explainable AI, the paper argues that responsible integration of LLMs into qualitative workflows requires researchers to engage critically with a curated set of technical parameters, that is, context window constraints, temperature and top-p sampling settings, user and system prompt design, and model documentation in the form of system cards. The paper situates these considerations within the epistemological commitments of qualitative research, including reflexivity, positionality, and interpretive judgment, and discusses how the opacity of contemporary LLMs differs from earlier natural language processing tools such as topic models and lexicon-based sentiment analyzers. --- ### RAPT: Retrieval-Augmented Post-hoc Thresholding for Multi-Label Classification Authors: Lasal Jayawardena, Nirmalie Wiratunga, Ikechukwu Nkisi-Orji, Darren Nicol Published: 2026-05-15 Categories: cs.IR, cs.AI arXiv: https://arxiv.org/abs/2605.16535v1 Industrial multi-label document understanding pipelines score candidate labels and threshold or rank them to form a label set per document. This early selection step directly affects the accuracy of downstream information extraction from the document, as well as the associated verification effort. In practice, OCR noise, label imbalance, instance-dependent label cardinality, and asymmetric error costs make global score thresholds brittle and hard to maintain as document formats evolve. We present RAPT, a deployment-oriented retrieval-augmented score thresholding wrapper, applied post-hoc to improve label set selection without retraining the underlying classifier. RAPT is a model-agnostic wrapper: any predictor that provides document representations for similarity search and per label confidence scores can be used, including metric learning encoders and fine-tuned transformer classifiers. For each query document, given a classifier's score vector, RAPT retrieves similar document thresholding situations (cases) and adapts the query's label set selection threshold using their outcomes. The adaptation selects the final label set by locally aggregating neighbour solutions (e.g. average label count, cutoff calibration). Evaluation compared multi-label classifiers (metric learners and transformers) combined with RAPT against global and label-wise thresholding baselines, and against few-shot LLMs. Across an industrial dataset and six public benchmarks, RAPT consistently outperformed global and label-wise static thresholding baselines. In the industrial setting, RAPT achieved its best predictive performance with metric learners, reaching 0.87 Macro-F1, while fine-tuned transformer variants on average achieved 0.775 Macro-F1, outperforming fewshot LLM baselines (K = 5) by 2x and requiring at least 115x less inference time and 13.5x less GPU memory. --- ### Boundedly Rational Meta-Learning in Sequential Consumer Choice Authors: Mehrzad Khosravi, Max Kleiman-Weiner, Hema Yoganarasimhan Published: 2026-05-15 Categories: cs.LG, econ.GN arXiv: https://arxiv.org/abs/2605.16532v2 Many consumer decisions involve repeated choices under uncertainty, where experience in one context may inform decisions in another. For example, experience with a brand in one market or usage context may shape beliefs about that brand in a new context. We study whether such cross-context transfer takes the form of meta-learning, in which experience across contexts updates higher-order beliefs that guide learning in a new context. In a hierarchical laboratory task, participants choose among airlines across routes and observe noisy binary outcomes. Participants improve both within and across routes, indicating cross-route knowledge transfer. We compare human choices with no-transfer, fully integrated meta-learning, and boundedly rational meta dynamic programming policies, BRMDP(D), where D is the number of hyper-posterior draws used to approximate integration. Trial-by-trial likelihood comparisons show that low-D policies, especially BRMDP(1), best predict participant choices. The results suggest that consumers transfer information across contexts using coarse representations of higher-order uncertainty. --- ### Boundedly Rational Meta-Learning in Sequential Consumer Choice Authors: Mehrzad Khosravi, Max Kleiman-Weiner, Hema Yoganarasimhan Published: 2026-05-15 Categories: cs.LG, econ.GN arXiv: https://arxiv.org/abs/2605.16532v1 Many consumer decisions are repeated choices under uncertainty. Standard models capture these decisions using Bayesian learning and dynamic programming: consumers update beliefs from feedback and use those beliefs to guide future choices. In many markets, however, learning does not restart when consumers enter a new context: prior experience with a brand, product, or provider can shape beliefs in later, related decisions. We study this cross-context knowledge transfer, or meta-learning, in sequential choice. We design a hierarchical laboratory task in which participants repeatedly choose among airlines across routes and observe noisy binary outcomes. Reduced-form evidence shows that participants improve not only within routes, but also across routes: they choose better airlines earlier in later routes and reduce pseudo-regret. To identify the mechanism behind this transfer, we compare human choices to a no-transfer benchmark and a fully integrated Bayesian meta-learning benchmark. In particular, we introduce a class of boundedly rational meta dynamic programming policies, BRMDP(D), that approximate full integration using a limited number of hyper-posterior draws, denoted by D. Trial-by-trial likelihood comparisons show that low-D boundedly rational meta-learning, especially BRMDP(1), fits participant behavior better than both no transfer and fully integrated Bayesian transfer. Consumers, therefore, transfer brand-level regularities across contexts, but through coarse representations of prior uncertainty. The findings imply that models of consumer learning should allow for approximate cross-context transfer, and that managerial counterfactuals based on either no-transfer or fully integrated learning can be misleading. --- ### SWoMo: Neuro-Symbolic World Model for Cataract Surgery Simulation Authors: Ssharvien Kumar Sivakumar, Akwele Johnson, Anirudh Dhingra, Yannik Frisch, Ghazal Ghazaei, Anirban Mukhopadhyay Published: 2026-05-15 Categories: cs.CV arXiv: https://arxiv.org/abs/2605.16530v2 Realistic surgical simulation plays a crucial role in training novice surgeons and in the development of autonomous agents. World models can scale such simulation environments to realistic and diverse procedures by predicting future patient states conditioned on current observations and surgical actions. However, current state-of-the-art approaches often fail to satisfy key criteria required for clinical applicability, including visual realism, physically grounded interactions, and the ability to simulate scenarios beyond the training distribution. Hence, we introduce SWoMo, a neuro-symbolic world model for cataract surgery simulation that decouples motion generation from visual realism. The symbolic component, consisting of a rule-based simulator and scene graph representations, models motion dynamics and tool-tissue interactions, while a diffusion model produces realistic visual appearance, including textures and tissue deformations. We propose an inverse pairing strategy that reconstructs real surgical videos in the simulator to obtain paired simulated and real videos, which are then used to train our video diffusion model for the reverse objective of sim-to-real translation. Our experiments show both qualitative and quantitative improvements over prior work. We demonstrate that our simulator further satisfies the key criteria, including generalisation to unseen interaction geometries, improvements in downstream phase detection, and unsupervised video style transfer. The code, data, and model weights are available at: https://ssharvienkumar.github.io/SWoMo/ --- ### Multiscale Supervised Unbalanced Optimal Transport Flow Matching Authors: Qiangwei Peng, Lezhi Chen, Peijie Zhou Published: 2026-05-15 Categories: cs.LG, math.OC arXiv: https://arxiv.org/abs/2605.16529v1 Unbalanced optimal transport (UOT) provides a principled framework for modeling single-cell transitions and birth-death dynamics, but its high computational cost limits scalability to large-scale datasets. Although single-cell data often contain hierarchical annotations and known transition priors, existing UOT approximations rarely exploit this multiscale structure or prior knowledge. We introduce Multiscale Supervised Unbalanced Optimal Transport Flow Matching (MUST-FM), a simulation-free framework that scales UOT by leveraging hierarchical data structure. MUST-FM further supports an optional supervised formulation that incorporates transition priors, such as cell lineages, to guide the learning of displacement fields and mass variations. Experiments show that MUST-FM reduces computational overhead while achieving robust and biologically meaningful trajectory inference, enabling dynamic modeling of atlas-scale single-cell datasets. --- ### Inventorship in AI-Assisted Inventions: Designing an Experiment to Shape Case Law Authors: Yevhenii Shchetynin, Duygu Usta, Bryan Khan Published: 2026-05-15 Categories: cs.CY, cs.AI arXiv: https://arxiv.org/abs/2605.16528v1 The latest improvements in artificial intelligence (AI) raise new challenges for intellectual property laws, particularly concerning the inventorship issue in AI-assisted inventions - that is, those in which AI is used in the inventive process. While most jurisdictions allow only a natural person to be considered the inventor, the question of how to deal with AI-assisted inventions remains relevant. Namely, what is the nature and contribution of AI tools in an AI-assisted invention that would prevent a human from being recognized as its inventor? The main challenge in addressing this question is the lack of case law on the issue. It is reasonable to assume that with the development of AI and the growing interest in its use in the inventive process, new cases will naturally arise, which in turn will harmonize and address the inventorship issue in AI-assisted inventions to some extent. However, this process will take significant time and may not keep pace with the rapid development of AI, nor fully address the new problems that arise alongside AI advancements. This research proposes the conditions of an experiment to create relevant case law. This experiment could be initiated by society, involving stakeholders specializing in AI. The article also proposes a methodology for conducting the experiment and selecting cases that best reflect the current state of AI use in the inventive process. Conducting such an approach will help identify the most effective methods for measuring human contribution to AI-assisted inventions when determining inventorship. --- ### Hypergraph Pattern Machine: Compositional Tokenization for Higher-Order Interactions Authors: Kyrie Zhao, Zehong Wang, Tianyi Ma, Fang Wu, Xiangru Tang, Pietro Lio, Sheng Wang, Yanfang Ye Published: 2026-05-15 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2605.16527v1 Hypergraphs model higher-order relations that drive real-world decisions, from drug prescriptions to recommendations. A central structural signal in such data, beyond what pairwise relations can express, is interaction compositionality: whether a higher-order relation is compositional, emergent, or inhibitory with respect to its observed or unobserved sets. In polypharmacy, the regime decides whether a drug should be dropped, kept, or excluded: a compositional drug triple can be safely simplified, an emergent triple requires all drugs jointly, and an inhibitory triple flags a drug that disrupts an existing interaction. However, existing hypergraph learning methods, which merely propagate messages over observed hyperedges, leave this compositional signal unmodeled, allowing dangerous drug combinations to slip through and be misclassified. To this end, we propose the Hypergraph Pattern Machine (HGPM), shifting the paradigm from message passing to learning the compositional pattern of subsets. It tokenizes compositional subsets, organizes them in an inclusion DAG, and trains an inclusion-aware Transformer under masked reconstruction. On ten hypergraph benchmarks, HGPM matches or exceeds state-of-the-art methods. Notably, in a real adverse-event prediction case, HGPM correctly identifies the drug addition that inhibits the side effect among feature-identical candidates, a discrimination existing methods cannot make. The code and data are in https://github.com/KryieZhao/HGPM.git. --- ### Toward Template-Free Explainability for Monte Carlo Tree Search Authors: Siqi Lu, Mirsaleh Bahavarnia, Hiba Baroud, Yixuan Zhang, Hemant Purohit, Ayan Mukhopadhyay Published: 2026-05-15 Categories: cs.HC, cs.AI arXiv: https://arxiv.org/abs/2605.16524v2 Probabilistic search algorithms, such as Monte Carlo Tree Search (MCTS), have proven very effective in solving sequential decision-making tasks under uncertainty. However, interpreting asymmetric search trees that incorporate bandit-based tree traversal and simulation-based value estimation is difficult for end users based solely on raw tree statistics. While prior work requires hand-crafted formal logic constraints that must be updated when the problem changes, we present a framework that enables large language models (LLMs) to generate evidence-grounded explanations of MCTS decisions from recorded search traces in an end-to-end manner. Our framework maps natural-language questions to a structured set of intent categories, determines whether the existing tree contains sufficient evidence, triggers targeted expansion when needed, and generates explanations using tree statistics such as visit counts, value estimates, and risk information. Experimental results provide the first evidence that LLMs can serve as end-to-end explainers for probabilistic search, without requiring intermediate formal representations. --- ### Global Convergence of Sampling-Based Nonconvex Optimization through Diffusion-Style Smoothing Authors: Zeji Yi, Chaoyi Pan, Guanya Shi, Guannan Qu Published: 2026-05-15 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.16520v1 Sampling-based optimization (SBO), like cross-entropy method and evolutionary algorithms, has achieved many successes in solving non-convex problems without gradients, yet its convergence is poorly understood. In this paper, we establish a non-asymptotic convergence analysis for SBO through the lens of smoothing. Specifically, we recast SBO as gradient descent on a smoothed objective, mirroring noise-conditioned score ascent in diffusion models. Our first contribution is a landscape analysis of the smoothed objective, demonstrating how smoothing helps escape local minima and uncovering a fundamental coverage-optimality trade-off: smoothing renders the landscape more benign by enlarging the locally convex region around the global minimizer, but at the cost of introducing an optimality gap. Building on this insight, we establish non-asymptotic convergence guarantees for SBO algorithms to a neighborhood of the global minimizer. Furthermore, we propose an annealed SBO algorithm, Diffusion-Inspired Dual-Annealing (DIDA), which is provably convergent to the global optimum. We conduct extensive numerical experiments to verify our landscape results and also demonstrate the compelling performance of DIDA compared to other gradient-free optimization methods. Lastly, we discuss implications of our results for diffusion models. --- ### DepthPolyp: Pseudo-Depth Guided Lightweight Segmentation for Real-Time Colonoscopy Authors: Zhuoyu Wu, Wenhui Ou, Lexi Zhang, Pei-Sze Tan, Dongjun Wu, Junhe Zhao, Wenqi Fang, Raphaël C. -W. Phan Published: 2026-05-15 Categories: cs.CV, eess.SP arXiv: https://arxiv.org/abs/2605.16519v1 Accurate polyp segmentation in colonoscopy is essential for early colorectal cancer detection, yet real-world clinical environments pose persistent challenges such as motion blur, specular reflections, and illumination instability. Most existing methods are optimized on clean benchmark images and suffer noticeable performance degradation when deployed in authentic surgical scenarios. We propose DepthPolyp, a lightweight and robust segmentation framework based on pseudo-depth-guided multi-task learning and efficient feature modulation. The architecture combines hierarchical Ghost factorization for compact feature generation, Interleaved Shuffle Fusion for low-cost cross-scale interaction, and Dynamic Group Gating for adaptive group-wise feature weighting. Extensive experiments demonstrate that DepthPolyp achieves strong cross-dataset generalization when trained on degraded data and evaluated on both clean and noisy target domains, consistently outperforming lightweight baselines and remaining competitive with substantially larger models. In real surgical video evaluation on PolypGen, DepthPolyp achieves better segmentation performance than models up to $20\times$ larger while preserving real-time inference speed. With only 3.57M parameters and 0.86 GMACs, the proposed method runs at over 180 FPS on mobile devices, making it well suited for real-time deployment in resource-constrained clinical environments. Code and pretrained weights are available at: https://github.com/ReaganWu/DepthPolyp/ --- ### Alignment Drift in Long-Term Human-LLM Interaction: A Mechanism-Oriented Framework Authors: Xintong Yao Published: 2026-05-15 Categories: cs.HC, cs.AI, cs.CL, cs.CY arXiv: https://arxiv.org/abs/2605.16516v1 Long-term interaction with LLM-based systems may produce alignment drift: a gradual process in which system outputs become less constrained by the user's current message and more shaped by prior interaction history, while still appearing helpful, coherent, and responsive. This process is difficult to detect because the user's subjective experience may improve as the system becomes more familiar, useful, and attuned. Existing research on human-LLM interaction has largely focused on short-term task performance, isolated outputs, or single-instance alignment problems, leaving slow and cumulative interaction-level dynamics undercharacterized. This paper proposes a mechanism-oriented framework for describing alignment drift. The framework defines the distinction between signal A and signal B, explains how drift develops through feedback loops and sub-pattern selection, divides the process into three interactional regimes, and identifies boundary conditions for controlling drift. By framing alignment drift as a recursive interactional process rather than an isolated model-side failure, the paper provides a conceptual basis for studying long-term human-system interaction. --- ### SeamCam: Quantifying Seamless Camouflage via Multi-Cue Visual Detectability Authors: Amin Karimi Monsefi, Abolfazl Meyarian, Mridul Khurana, Shuheng Wang, Pouyan Navard, Cheng Zhang, Anuj Karpatne, Wei-Lun Chao, Rajiv Ramnath Published: 2026-05-15 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2605.16515v1 Animals are described as effectively camouflaged when they blend seamlessly with their surrounding, yet no standardized quantitative measure of this seamlessness exists. We address this gap by framing camouflage evaluation as a visual localization problem: a well-camouflaged animal is one that remains difficult to detect even when its category is known. We introduce SeamCam (Seamless Camouflage), a metric that quantifies how detectable an animal is from the available visual evidence. Given an image and a target species, SeamCam generates category-conditioned detection proposals, extracts segmentation masks, and identifies the subset whose collective union yields the highest IoU with the ground-truth mask. The SeamCam score is one minus this maximum recoverable localization signal, where a higher score indicates stronger camouflage (i.e., lower detectability). In a human two-alternative forced-choice study with 94 participants and 2,390 comparisons, SeamCam achieves 78.82% agreement with human camouflage difficulty judgments, outperforming state-of-the-art by about 25%. We then demonstrate SeamCam's utility as a preference signal for Direct Preference Optimization (DPO) to fine-tune a diffusion-based inpainting model for camouflage generation. This offers an affordable training approach with an objective explicitly suited for camouflage generation, unlike typical diffusion models. To support rigorous benchmarking, we further introduce CamFG-1.5k, a curated dataset of 1,521 high-resolution images in which animals are fully visible prior to camouflage generation, enabling unbiased evaluation by controlling for occlusion artifacts present in existing datasets. https://7amin.github.io/SeamCam/ --- ### No Plan, Yet Human: A Reactive Robotics Model Predicts Human Planning Failures on a Clinical Task Authors: Michael Migacev, Vito Mengers, Antonia Köngeter, Oliver Brock Published: 2026-05-15 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2605.16514v2 Understanding why some sequential planning problems are harder than others requires models that go beyond average performance. They should capture the specific pattern of which problems are hard, and ideally fail in the same way people do when planning capacity is reduced. We apply AICON, a reactive gradient-descent framework developed for robotic manipulation, to the Tower of London test, a cognitive test used to assess planning in Parkinson's disease, mild cognitive impairment, and stroke. Without any lookahead planning or knowledge of human cognition, AICON reproduces the fine-grained human difficulty ordering across 24 problems better than structural task parameters and generalizes to held-out problems in a leave-two-out evaluation. Crucially, AICON outperforms a planning baseline for groups with reduced planning capacity while the planning baseline better captures healthy controls. This dissociation was predicted by the original AICON paper, which noted that the model's failure modes resemble those of Parkinson's patients who struggle with goal hierarchies but not move counts. This suggests that as planning capacity is reduced, human behavior shifts toward the reactive mode AICON models. The finding extends a broader pattern: AICON, originally built for robotics, now captures aspects of biological behavior across perception, eye movements, and sequential planning, suggesting its core abstraction reflects something real about how biological systems are organized. --- ### No Plan, Yet Human: A Reactive Robotics Model Predicts Human Planning Failures on a Clinical Task Authors: Michael Migacev, Vito Mengers, Antonia Köngeter, Oliver Brock Published: 2026-05-15 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2605.16514v1 Understanding why some sequential planning problems are harder than others requires models that go beyond average performance. They should capture the specific pattern of which problems are hard, and ideally fail in the same way people do when planning capacity is reduced. We apply AICON, a reactive gradient-descent framework developed for robotic manipulation, to the Tower of London test, a cognitive test used to assess planning in Parkinson's disease, mild cognitive impairment, and stroke. Without any lookahead planning or knowledge of human cognition, AICON reproduces the fine-grained human difficulty ordering across 24 problems better than structural task parameters and generalizes to held-out problems in a leave-two-out evaluation. Crucially, AICON outperforms a planning baseline for groups with reduced planning capacity while the planning baseline better captures healthy controls. This dissociation was predicted by the original AICON paper, which noted that the model's failure modes resemble those of Parkinson's patients who struggle with goal hierarchies but not move counts. This suggests that as planning capacity is reduced, human behavior shifts toward the reactive mode AICON models. The finding extends a broader pattern: AICON, originally built for robotics, now captures aspects of biological behavior across perception, eye movements, and sequential planning, suggesting its core abstraction reflects something real about how biological systems are organized. --- ### The Scaling Laws of Skills in LLM Agent Systems Authors: Charles Chen, Qiming Yu, Yuhang Gu, Zhuoye Huang, Hanjing Li, Hongyu Liu, Simin Liu, Jinhao Liu, Dengyun Peng, Jiangyi Wang, Zheng Yan, Fanqing Meng et al. Published: 2026-05-15 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2605.16508v1 As agent systems scale, skills accumulate into large reusable libraries, yet their scaling laws remain poorly understood. Across 15 frontier LLMs, 1,141 real-world skills, and over 3M routing or execution decisions, we identify two coupled laws. Routing law: single-step routing accuracy decays logarithmically with library size ($R^2{>}0.97$ for all models), with errors progressing from local skill competition to cross-family drift and capture by overly general "black-hole skills". Execution law: before state realization, joint routing is approximately multiplicative, whereas correct execution can improve difficult downstream decisions by about $4{\times}$. A single parameter, the routing logarithmic decay slope $b$, couples the two laws: routing-side fits predict execution-side rescue across models, showing that the same library property controls both pre-execution collapse and downstream recoverability. The laws are actionable: law-guided optimization raises held-out routing accuracy from 71.3% to 91.7%, reduces hijack from 22.4% to 4.1%, and transfers directionally to downstream ClawBench and ClawMark execution settings, improving mean pass rate from 49.3% to 61.6% on ClawBench and from 28.4% to 34.5% on ClawMark. These results show that agent performance depends not only on model capability, but also on the structure, granularity, and exposure policy of the skill library. --- ### StAD: Stein Amortized Divergence for Fast Likelihoods with Diffusion and Flow Authors: Gurjeet Jagwani, Stephen Thorp, Sinan Deger, Hiranya Peiris Published: 2026-05-15 Categories: stat.ML, astro-ph.IM, cs.LG arXiv: https://arxiv.org/abs/2605.16486v1 Diffusion and flow-based models are ubiquitously used for generative modelling and density estimation. They admit a deterministic probability flow ordinary differential equation (PF-ODE), analogous to continuous normalizing flows (CNFs), which describes the transport of the probability mass. Obtaining the likelihood from these models is of interest to many workflows, especially Bayesian analysis, and requires solving the trace of the Jacobian to compute the divergence of the learned PF-ODE, which is either $\mathcal{O}(D^2)$ to compute exactly or $\mathcal{O}(D)$ with a noisy estimate. We introduce StAD, a new distillation method to predict and learn the divergence of the PF-ODE using the Langevin-Stein operator without ever computing the Jacobian. We show that our method is competitive with the Hutchinson and Hutch++ on CIFAR-10, ImageNet and other density estimation tasks, consistently improving the variance and speed of the likelihood predictions compared to the Hutchinson. We additionally show our method will generalize to a varied class of generative models, and show that under some regularity conditions these learned vector fields can be made to satisfy the Stein class. --- ### Visual Agentic Memory: Enabling Online Long Video Understanding via Online Indexing, Hierarchical Memory, and Agentic Retrieval Authors: Aiden Yiliu Li, Nels Numan, Anthony Steed Published: 2026-05-15 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2605.16481v1 Long video understanding requires more than large context windows. It also needs a memory mechanism that decides what visual evidence to retain, keeps it searchable over long horizons, and grounds later reasoning in recoverable observations rather than compressed latent state alone. We propose Visual Agentic Memory (VAM), a training-free framework with three components. Online Indexing supports selective evidence retention under streaming constraints. Hierarchical Memory organises retained evidence in a Parallel Representation that aligns temporal context with spatial observations. Agentic Retrieval searches, inspects, and verifies candidate evidence before producing a grounded answer. On OVO-Bench, VAM achieves the highest RT+BT average (68.41) across all reported baselines, improving over end-to-end use of the same underlying MLLM (Gemini 3 Flash, 67.46). On the month-scale split of MM-Lifelong train@month (105.6 hours over 51 days), VAM reaches 17.11%, second only to ReMA with GPT-5 (17.62%). These results suggest that long-horizon video understanding benefits from treating visual memory as an explicit, inspectable, and queryable substrate. Code is available at https://github.com/yiliu-li/Visual-Agentic-Memory. --- ### MoleCode unlocks structural intelligence in large language models Authors: Zhiyuan Yan, Chen Liu, Boxuan Zhao, Kaiqing Lin, Jixiang Zhao, Yimi Wang, Liuzhenghao Lv, Hao Li, Shanzhuo Zhang, Li Yuan, Fanyang Mo Published: 2026-05-15 Categories: q-bio.BM, cs.AI arXiv: https://arxiv.org/abs/2605.16480v1 Molecules are graphs, but large language models~(LLMs) are usually asked to reason about them through linear strings. The most popular molecular representation, SMILES, compresses atoms, bonds, branches and rings into a compact sequence in which topology is implicit, forcing LLMs to reconstruct molecular structure before performing the requested chemical operation. Here we introduce MoleCode, an LLM-native, training-free, graph-explicit molecular language in which all molecular components are represented as typed entities with persistent identifiers and explicit relations. MoleCode makes molecular topology directly readable, editable and auditable within the language context, allowing an LLM to operate on structure rather than recover it from syntax. Across molecular reasoning, editing, generation and analysis tasks, this representational shift improves frontier LLMs most strongly when structural access is limiting: unfamiliar molecules, topology-sensitive operations, larger structures and repetitive polymers. It also changes how inference is allocated, replacing long reasoning traces devoted to implicit structural reconstruction with shorter, more chemically directed reasoning over explicit atoms and bonds. In molecular optimization, this enables localized, property-aligned edits that preserve structural similarity to the starting compounds. The same Subgraph--Node--Edge grammar extends beyond small molecules to polymers, Markush structures, mechanism-style transformations and interleaved scientific documents, including research articles and patent disclosures in which chemical information is distributed across text and images. These results suggest that the interface between scientific objects and LLMs should not treat structure as something to be decoded from text. When the object of reasoning is relational, the structure itself should be part of the language. --- ### Policy-Grounded Dynamic Facet Suggestions for Job Search Authors: Dan Xu, Baofen Zheng, Qianqi Shen, Jianqiang Shen, Wenqiong Liu, Chunnan Yao, Ping Liu, Rajat Arora, Kevin Kao, Hsiang Lin, Wanjun Jiang, Yusuke Takebuchi et al. Published: 2026-05-15 Categories: cs.IR, cs.AI arXiv: https://arxiv.org/abs/2605.16479v1 Job seekers often initiate search with short, underspecified queries. At LinkedIn, over 80% of job-related queries contain three or fewer keywords, making accurate user intent inference and relevant job retrieval particularly challenging. We present dynamic facet suggestion (DFS), an interactive query refinement mechanism that facilitates intent disambiguation by surfacing personalized semantic attributes conditioned on the joint user-query context in real time. We propose a policy-grounded, retrieval-augmented ranking framework for facet suggestion, comprising offline taxonomy curation, embedding-based retrieval of top-K candidates, and distilled small language model (SLM) based candidate scoring. The system is optimized for real-time serving via pointwise single-token scoring with batching and prefix caching. Offline evaluation demonstrates high precision for generated suggestions, and online A/B tests show significant improvements in suggestion engagement and job search outcomes. --- ### Seeking the Unfamiliar but Memorable: Conceptual Creativity as Meta-Learning Authors: Mengye Ren Published: 2026-05-15 Categories: cs.LG, cs.CV arXiv: https://arxiv.org/abs/2605.16477v1 What does it mean to create a new concept, rather than retrieve a familiar one? Repeatedly sampling a generative model at the same prompt produces variations with similar styles and typical content. We propose that creativity is the production of stimuli that are unfamiliar to an adaptive observer at first sight, but quickly learnable from a few exposures. We formalize this as a Creator-Appraiser pair: a Creator generates a candidate, an Appraiser adapts to it for a few inner-loop learning steps, and the Appraiser's improvement becomes the reward the Creator optimizes through. We instantiate the framework with diffusion as the Creator, an autoencoder Appraiser on MNIST, and a CLIP Appraiser with a low-rank adapter for natural images. The diffusion model remains frozen with no additional language conditioning; the meta-learning gradient is enough to produce both stylistic variations and concept compositions that the base model does not generate on its own. --- ### Deep Learning for MRI Slice Interpolation: The Critical Role of Problem Formulation Authors: Shamit Savant Published: 2026-05-15 Categories: eess.IV, cs.CV, cs.LG arXiv: https://arxiv.org/abs/2605.16476v1 Through-plane resolution in clinical MRI is typically much coarser than in-plane resolution, limiting diagnostic utility. This work investigates deep learning approaches to interpolate intermediate MRI slices in prostate imaging, effectively doubling through-plane resolution. I evaluated five architectures (CNN, U-Net, two GAN variants, and DDPM) and discovered that problem formulation has dramatically more impact than architectural complexity. By reformulating the interpolation task to use adjacent slices (i-1, i+1) rather than distant slices (i-2, i+2), I achieved a 58% improvement in SSIM performance across all deterministic architectures. The U-Net model achieved the best results with PSNR of 30.08 dB and SSIM of 0.898, representing a 10.1% improvement over linear interpolation baseline. A DDPM was also evaluated but showed poor reconstruction quality due to fundamental mismatch between stochastic generation and deterministic reconstruction requirements. These findings demonstrate that problem formulation can have 290x more impact than architectural sophistication in medical imaging tasks. --- ### Generative Artificial Intelligence for Literature Reviews Authors: Gerit Wagner, Julian Prester, Reza Mousavi, Roman Lukyanenko, Guy Pare Published: 2026-05-15 Categories: cs.DL, cs.CL arXiv: https://arxiv.org/abs/2605.16475v1 Generative artificial intelligence (GenAI), based on large-language models (LLMs), such as ChatGPT, has taken organizations, academia, and the public by storm. In particular, impressive GenAI capabilities such as summarization of large text corpora, question-answering, data extraction, and translation, carry profound implications for the conduct of literature reviews. This impacts science, organizations and the general public, as all can benefit from GenAI-supported literature reviews. Building on the technical foundations of GenAI and grounded in established methodological discourse, this work outlines approaches for conducting literature reviews using both general-purpose (e.g., ChatGPT, Gemini, Claude) and specialized GenAI tools (e.g., Consensus, Elicit). We provide illustrative examples of prompts and suggest methodologically-sound literature review strategies. Throughout this perspective paper, we adopt a balanced approach considering both the opportunities and the risks of relying on GenAI in the conduct of literature reviews. We conclude by discussing philosophical questions related to the effects of GenAI on long-term scientific progress, and also present fruitful opportunities for research on improving the core of GenAI's technology-its architecture and training data-and suggest open issues in GenAI-based literature reviews methodology. --- ### LERA: LLM-Enhanced RAG for Ad Auction in Generative Chatbots Authors: Haoran Sun, Xinrui Song, Xinyu Zhang, Zhaohua Chen, Xu Chu, Zhilin Zhang, Chuan Yu, Jian Xu, Bo Zheng, Xiaotie Deng Published: 2026-05-15 Categories: cs.IR, cs.AI arXiv: https://arxiv.org/abs/2605.16474v1 The integration of advertising auction mechanisms into large language model (LLM)-based chatbots presents a significant opportunity for commercialization, yet poses unique challenges in balancing relevance, efficiency, and user experience. Recently, Feizi et al.~\citep{feizi2023online} and Hajiaghayi et al.~\citep{hajiaghayi2024ad} outlined a retrieve-then-generate paradigm that decouples retrieval and generation, offering lightweight ad insertion and payment determination. However, current retrieval relies solely on text embedding similarity, which may lead to commercial misinterpretation and issues such as repetitive insertions. In this paper, we propose LERA, a two-stage retrieve-then-generate auction framework tailored for LLM chatbots. In the first stage, embedding-based coarse filtering pre-selects a small set of candidate advertisers. In the second stage, the LLM itself is queried with a carefully designed prompt to produce logits over candidates, which serve as refined organic relevance scores. These scores are combined with bids, and a critical-value payment rule accounts for both the coarse-filtering and fine-ranking thresholds, ensuring truthfulness for utility-maximizing advertisers. The framework naturally extends to multiple ad insertions within dynamic dialogue flows and long responses. Experiments on a synthetic advertiser-query benchmark show that LERA substantially improves ad selection accuracy and insertion diversity while incurring only controllable latency overhead. --- ### Dimension-Uniform Discretization Analysis of Preconditioned Annealed Langevin Dynamics for Multimodal Gaussian Mixtures Authors: Lorenzo Baldassari, Josselin Garnier, Knut Solna, Maarten V. de Hoop Published: 2026-05-15 Categories: stat.ML, cs.LG, math.NA, math.PR arXiv: https://arxiv.org/abs/2605.16473v1 Obtaining stable diffusion-based samplers in high- and infinite-dimensional settings is challenging because errors can accumulate across high-frequency coordinates and make the dynamics unstable under refinement of the finite-dimensional approximation of the underlying function-space problem. Discretization is a typical source of such errors, and preconditioning with a suitable spectral decay is one way to control their accumulation. In this paper, we study this problem for preconditioned annealed Langevin dynamics (ALD) applied to Gaussian mixtures. We first show that Euler-Maruyama (EM) discretization, by treating the stiff linear part of the annealed score with a forward Euler step, imposes a stability constraint coupling the preconditioner with the annealed covariance scale. Together with the conditions ensuring dimension-uniform control of the annealed dynamics, this constraint forces the initial smoothed law to remain uniformly close to the target across dimensions. We then consider an exponential-integrator scheme that integrates the stiff linear part of the annealed score exactly. Under explicit spectral summability conditions coupling the smoothing covariance, the component covariance spectra, and the preconditioner, we prove a dimension-uniform Kullback-Leibler (KL) bound for this scheme. This bound can be made arbitrarily small, uniformly in dimension, by allowing enough time for annealing and then refining the time mesh accordingly. Importantly, these conditions allow regimes in which the KL divergence between the target and the initial smoothed law diverges with dimension, showing that the restrictions imposed by EM are scheme-dependent rather than intrinsic to ALD. --- ### Strategic Over-Parameterization for Generalizable Low-Rank Adaptation Authors: Jing Gao, Zhong-Yi Lu, Pan Zhang, Ze-Feng Gao Published: 2026-05-15 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2605.16470v1 Adapting large language models (LLMs) to downstream tasks via full fine-tuning is increasingly impractical due to its computational and memory demands. Parameter-efficient fine-tuning (PEFT) approaches such as Low-Rank Adaptation (LoRA) mitigate this by confining updates to a compact set of trainable parameters, but this aggressive reduction often sacrifices generalization, especially under transfer across heterogeneous tasks and domains. We revisit the tension between parameter efficiency and adaptation capacity, and ask whether the two are truly at odds. We answer in the negative by introducing LoRA-Over, a framework grounded in a simple principle: enrich the optimization landscape during training, then collapse the enrichment at inference. LoRA-Over injects auxiliary parameters into the low-rank adapters during training to broaden the effective hypothesis space, and through a decomposition-based reformulation folds them back into a standard low-rank structure with negligible reconstruction error, keeping inference cost identical to vanilla LoRA. Since not all weight matrices benefit equally from added capacity, we further propose two scheduling strategies, one statically predefined and one dynamically determined at runtime, that direct extra capacity where most needed. We evaluate LoRA-Over on language understanding (GLUE, T5-Base), dialogue (MT-Bench), arithmetic reasoning (GSM8K), and code generation (HumanEval), using LLaMA 2-7B and LLaMA 3.1-8B. Across all benchmarks and scales, LoRA-Over consistently outperforms vanilla LoRA, showing that principled over-parameterization designed to vanish at inference is an effective lever for improving PEFT generalization. Code will be released upon acceptance. --- ### Flow Matching with Optimized Subclass Priors for Medical Image Augmentation Authors: Felix Nützel, Mischa Dombrowski, Bernhard Kainz Published: 2026-05-15 Categories: eess.IV, cs.CV arXiv: https://arxiv.org/abs/2605.16469v1 Rare diseases dominate the diagnostic challenge in medical imaging yet are severely underrepresented in clinical datasets, causing classifiers to fail on exactly the conditions where reliable detection matters most. Generative augmentation can supply the missing tail-class coverage, but coarse disease labels aggregate diverse subtypes and acquisition settings into multi-modal conditionals that bias generators toward dominant submodes, while a shared Gaussian source forces rare subpopulations through disproportionately long transport paths. We propose an offline strategy that introduces informative priors at two levels: first, we partition each coarse label into coherent submodes via Gaussian mixture modeling in the generative model's latent space; second, we learn subclass-conditioned source distributions that re-center and re-scale the starting distribution per submode, shortening trajectories and reducing within-subclass dispersion. To prevent degenerate solutions we impose explicit geometric control, moderately concentrating normalized displacement directions around learnable prototypes while capping path-length outliers. On long-tailed chest X-ray (MIMIC-LT, NIH-LT) and CT slice (CT-RATE) benchmarks the proposed method consistently improves tail-class generation fidelity and diversity (FID, IRS) and is a promising augmentation strategy that reliably improves downstream balanced accuracy and macro-F1 over a non-augmented baseline across modalities. --- ### Mechanistically Interpretable Neural Encoding Reveals Fine-Grained Functional Selectivity in Human Visual Cortex Authors: Idan Daniel Grosbard, Mor Geva, Galit Yovel Published: 2026-05-15 Categories: cs.CV, cs.AI, cs.CL, cs.LG, q-bio.NC arXiv: https://arxiv.org/abs/2605.16468v1 A central goal in understanding human vision is to uncover the visual features that drive neuronal activity. A growing body of work has used artificial neural networks as encoding models to predict cortical responses to natural images, revealing the visual content that activates category-selective regions. However, existing approaches are largely correlational and treat the encoder as a black box, leaving open which image features drive each voxel's response. We introduce Mechanistically Interpretable Neural Encoding (MINE), a framework that opens this black box by applying mechanistic-interpretability tools to localize the features within natural images that drive millimeter-scale (voxel-level) activity. MINE predicts each voxel's response using language-aligned image representations, and produces semantically interpretable descriptions of the features critical for the voxel's activation. We further generalize these per-image features into per-voxel functional profiles. To validate the per-image descriptions, we show they are sufficient to generate images that elicit voxel responses matching the responses to the original images, more accurately than images generated from random or low-attribution controls. Moreover, counterfactually inserting or removing the predicted features from images shifts activation in the expected direction, providing causal evidence. Counterfactual editing guided by the per-voxel activation profiles produces even stronger activation shifts, indicating that the profiles faithfully capture each voxel's selectivity. Finally, we apply MINE to well-studied category-selective brain regions, showing it recovers their known categorical preferences while revealing fine-grained unique voxel structure within each region. Overall, our results establish mechanistic interpretability as a path to discover and causally validate fine-grained hypotheses about neural function. --- ### MHMamba: Multi-Head Mamba for 3D Brain Tumor Segmentation Authors: Hanjun Tao, Hua Wang, Fan Zhang Published: 2026-05-15 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2605.16464v1 Brain tumors exhibit high heterogeneity in morphology and multimodal contrast, making manual slice-by-slice de lineation time-consuming and experience-dependent, thus necessitating efficient and stable automated segmentation methods. To address the limitations of CNNs in modeling long-range dependencies, and the heavy computational and memory overhead and inter-block contextual in coherence of Transformers in 3D MRI, this paper proposes Multi-Head Mamba (MHMamba). This method combines a U-shaped architecture with a multi-head state-space model (Mamba), splitting the channel dimension into parallel SSM heads and aggregating them with residuals. This enhances long-range representation and improves the stability of multimodal training while maintaining linear complexity. To further align statistics and enhance lesion response, we designed a channel-space calibration module for multi-head outputs and introduced an adaptive fusion mechanism at skip connections to dynamically connect global semantics with local details, thereby improving boundary consistency and the detection of small-volume lesions. We conducted experiments and ablations on BraTS2021 and BraTS2023. The results showed that MHMamba achieved stable and significant improvements in overall accuracy, boundary smoothness, and sensitivity to tumor core and small-volume enhancement areas, while preserving the linear-complexity advantage of Mamba-based modeling, thus verifying the effectiveness and versatility of the method. --- ### Asking Back: Interaction-Layer Antidistillation Watermarks Authors: Guang Yang, Amir Ghasemian, Fengchen Liu, Zhong Wang, Ninareh Mehrabi, Homa Hosseinmardi Published: 2026-05-15 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2605.16462v1 Detecting unauthorized knowledge distillation from a deployed LLM API is hard because the defender controls neither the attacker's training pipeline nor the next-token logits. Existing defenses operate on the teacher's output tokens -- biasing the next-token distribution (green-list watermarks, cryptographic schemes, antidistillation sampling) or rewriting outputs after generation. Recent work shows a paraphrasing attacker can strip these signals without losing the underlying knowledge. We propose interaction-layer antidistillation watermarks, which move the trace one layer higher, into the teacher's interaction behavior: the defender wraps the teacher with a system prompt that intermittently induces a behavioral marker -- an explicit follow-up question, a low-frequency variant, or a declarative restatement. An oblivious distiller inherits the behavior, and the defender audits via black-box queries with a human-validated LLM-as-judge (Cohen's kappa = 0.84/0.78 on strong/style rubrics). Across 63 LoRA-distilled students under a Llama-3.3-70B-Instruct teacher (35,343 judged samples), behavioral watermarks transfer at 88.9% (Gemma) / 80.9% (OLMo) / 45.2% (Qwen) relative fidelity (H1, H2). Under non-adaptive DIPPER paraphrasing, robustness decomposes into a teacher-self ceiling (about 66.4%) and student-relative retention of 21-112%, with OLMo preserving the watermark above the teacher itself (H3, F-Amp). Low-density (about 20%) explicit and implicit declarative variants transfer above per-family baseline (H4, F-Style). An N=20 in-lab study (pre-registered Latin-square) shows all marker variants within 0.22 Likert step of baseline; TOST, Friedman, and Bonferroni-Wilcoxon support H5. The interaction layer is a viable design locus for antidistillation watermarking, complementary to token-, model-, and reasoning-trace-layer defenses. --- ### REC-RL: Referring expression counting via Gaussian and range-based reward optimization Authors: Hui Liu, Yunlai Teng, Kunlong Bai, Pengfei Qi, Haotian Yan, Liang Li, Junlan Feng Published: 2026-05-15 Categories: cs.CV arXiv: https://arxiv.org/abs/2605.16460v1 Referring expression counting (REC) is an intention-driven task that requires context-aware visual reasoning. While recent vision-language models incorporate language for visual understanding, most existing REC methods rely on rulebased reinforcement learning with rewards focused primarily on final accuracy, overlooking the quality of intermediate reasoning. We propose REC-RL, a reinforcement learning framework that introduces a think-range-answer paradigm to explicitly optimize the visual reasoning process. RECRL employs Group Relative Policy Optimization and two lightweight rewards: an accuracy reward that combines range-based interval supervision with Gaussian-based precision guidance, and a format reward that enforces structured outputs. By modeling intermediate focus prediction as internal decision-making, REC-RL avoids additional annotations and better aligns with human perception. Extensive experiments demonstrate consistent improvements over strong baselines and robust generalization across benchmarks. --- ### Conservative AI for Safety-Sensitive Medical Image Restoration: Residual-Bounded CT-CTA Enhancement for Intracranial Aneurysm-Relevant Signal Recovery Authors: Weijun Ma Published: 2026-05-15 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2605.16458v1 Image restoration models are increasingly applied to degraded medical scans, but in safety-sensitive settings they must improve image quality without uncontrolled modification of clinically important regions. This is especially relevant for intracranial CT and CT angiography (CTA), where small vessels and aneurysm-relevant cues lie near high-contrast anatomical boundaries. We frame medical image restoration as a conservative AI problem and present a residual-bounded 2.5D restoration framework trained on synthetically degraded CT/CTA inputs. The model adds a learned residual to the original center slice through an edit-control map that limits the magnitude and spatial extent of modification. We evaluate the framework using an aneurysm-relevant image-recovery matrix, paired comparison against a Gaussian baseline, Monte Carlo stability testing, anatomical localization of meaningful edits, and external evaluation on low-dose CT. On 50 out-of-distribution CT-CTA cases, the bounded model achieved a mean target gain of 0.0635, a mean PSNR of 37.51 dB, and an iatrogenic-edit rate of 4.0%. Across 1,000 Monte Carlo runs, it remained net positive in 85.4% of runs with no stably negative cases. On external low-dose CT, the model was directionally beneficial and produced a substantially smaller modification footprint than the baseline. Meaningful edits concentrated in brain and skull regions while unrelated anatomy showed negligible change. These findings provide preliminary computational evidence that residual-bounded restoration is feasible in boundary-sensitive vascular imaging, but they do not establish clinical diagnostic performance and require expert review and prospective validation before clinical use. --- ### Identifiable Token Correspondence for World Models Authors: Youngin Kim, Ray Sun, Inho Kim, Bumsoo Park, Hyun Oh Song Published: 2026-05-15 Categories: cs.LG, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2605.16457v3 Token-based transformer world models have shown strong performance in visual reinforcement learning, but often suffer from temporal inconsistency in long-horizon rollouts, including object duplication, disappearance, and transmutation. A key reason is that most existing approaches treat next-frame prediction purely as a token generation problem, without considering the persistence of tokens across time. We introduce Identifiable Token Correspondence (ITC), a decoding step for token-based transformer world models that formulates next-frame prediction as a structured assignment problem with latent token correspondence variables: each next-frame token is explained either by copying a token from the previous frame or by generating a new one. ITC leaves the transformer architecture and training procedure unchanged and can be added on top of existing backbones. Our experiments show state-of-the-art performance on 4 challenging benchmarks. The proposed method achieves a return of 72.5% and a score of 35.6% on the Craftax-classic benchmark, significantly surpassing the previous best of 67.4% and 27.9%. We release our source code on https://github.com/snu-mllab/Identifiable-Token-Correspondence. --- ### Multi-hop Relational Contrastive Learning: Extending Spatial Contrastive Pre-training Beyond Pairwise Relations Authors: Sheikh Tanvir Ahmed, Md. Tanvir Raihan Published: 2026-05-15 Categories: cs.CV arXiv: https://arxiv.org/abs/2605.16456v1 Understanding how objects relate to each other in space is fundamental to scene understanding, yet most contrastive pre-training approaches only model pairwise relationships, leaving richer compositional and multi-hop interactions largely unexplored. We introduce Multi-Hop Relational Contrastive Learning (MRCL), a framework that extends spatial contrastive learning to graph-structured scene representations. By tracing k-hop paths through scene graphs built from detected objects, MRCL captures implicit spatial dependencies that go well beyond what direct object pairs can express. We define a multi-level contrastive objective spanning nodes, edges, and multi-hop paths, encouraging embeddings that remain stable across object semantics while staying responsive to spatial layout. On a GQA subset, MRCL produces spatially-aware representations that improve content-based graph retrieval (NDCG@5 = 0.748) and consistently benefit downstream tasks, including spatial relationship recognition and graph-based question answering. Together, these results suggest that multi-hop relational supervision offers substantially richer structural guidance than pairwise-only methods, leading to visual representations that are more robust, compositional, and geometry-aware. --- ### Peak-Detector: Explainable Peak Detection via Instruction-Tuned Large Language Models in Physiological Sign Authors: Jiahui Li, Yida Zhang, Zixuan Zeng, Jiayu Chen, Yingjian Song, Yin Xiao, Nishan Dong, Junjie Lu, Younghoon Kwon, Xiang Zhang, Jin Lu, Wenzhan Song et al. Published: 2026-05-15 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2605.16452v1 Accurate peak detection across diverse cardiac physiological signals, including the Electrocardiogram (ECG), Photoplethysmogram (PPG), Ballistocardiogram (BCG), and Bodyseismography (BSG), is fundamental for cardiovascular monitoring but is often hindered by artifacts and signal variability. Conventional algorithms are typically engineered with expert knowledge for a single signal modality, limiting their generalizability. Conversely, deep learning-based methods often lack interpretability, limiting transparency for expert verification and hindering expert-computer interaction. To address these limitations, we introduce Peak-Detector, a novel framework that leverages instruction-tuned Large Language Models (LLMs) for robust, cross-modal, and explainable peak detection. A core innovation of our framework is a "peak-representation" technique that transforms time-series data into a condensed format, preserving critical event information while significantly reducing signal length. This representation provides a crucial inductive bias, guiding the LLM to reason over physiologically meaningful events rather than raw, noisy data. The model is optimized through a two-stage process: supervised fine-tuning (SFT) followed by reinforcement learning (RL) with a multi-objective reward function. The model's self-explanation capabilities are cultivated by fine-tuning on a custom-built Peak-Explanation dataset. Across four modalities-ECG, PPG, BCG, and BSG-spanning seven datasets (six public benchmarks plus one real-world cohort), Peak-Detector demonstrates strong cross-modal performance, achieving best or tied-best detection under clinically relevant temporal tolerance. Beyond accuracy, the generated rationales surface failure modes and support verification and error analysis. --- ### Physics-Guided Geometric Diffusion for Macro Placement Generation Authors: Jongho Yoon, Jinsung Jeon, Seokhyeong Kang Published: 2026-05-15 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2605.16451v2 Macro placement is a pivotal stage in VLSI physical design, fundamentally determining the overall chip performance. Recent data-driven placement methods have demonstrated significant potential, yet they often struggle to handle sequential dependencies and to balance topological connectivity with physical constraints. To bridge this gap, we propose MacroDiff+, a physics-guided geometric diffusion framework. Specifically, we design a dual-domain denoising architecture that couples topological connectivity encoded by heterogeneous GNNs with global geometric context modeled by a Transformer. Furthermore, we introduce Physics-Guided Sampling, an inference strategy that actively steers the generation using explicit gradients to ensure both statistical plausibility and physical validity. On the ISPD2005 MMS benchmarks, MacroDiff+ outperforms state-of-the-art baselines with a 6.1-6.2% reduction in wirelength. Notably, it exhibits superior stability and scalability on large-scale designs where prior methods fail to converge. The source code is available at https://github.com/jhy00n/MacroDiff-plus. ---