# Research Papers — 2026-04 · bundle page 65 of 233 > Full-text markdown of papers #3201–3250 of 11612 published in 2026-04, newest first. AI-readable mirrors of the full 11612-paper 2026-04 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2026-04/page/65 [← Previous bundle](https://aipod.dev/papers/archive/2026-04/page/64.md) [Next bundle →](https://aipod.dev/papers/archive/2026-04/page/66.md) ### Durable Evaluation Framework: Adversarial Arbitration for Sycophancy Reduction in Large Language Models Authors: Sam Ryan Published: 2026-04-21 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2606.07532v2 RLHF-trained models are systematically biased toward agreement over accuracy, a structural property of the training process. We present Durable Evaluation Framework (DEF) Arbitration, a multi-agent architecture that mitigates identity-framed sycophancy by arbitrating between two models tuned to opposing DEFs, with a pragmatist synthesizer evaluating both arguments blind to their origins. This paper evaluates a prompt-based instantiation of DEF Arbitration. The key mechanisms are static DEF tuning, identity stripping before synthesis, single-round independent argumentation, and blind arbitration. We evaluate five instantiations on 200 stratified questions from SycophancyEval. All tested DEF variants (AnCifer, DeWin, FeynStein, BurGal, Trident) significantly outperform the single-model baseline (18.5%) and instructed-opposition baseline (29.0%), with DeWin achieving 48.5% accuracy (z=6.36, p<0.001 versus both). The variants are not significantly different from each other at n=200. The BurGal variant achieves 53.0% but functions as an architectural validity check; its consensus/heterodox axis structurally favors the heterodox model on every benchmark question. A pre-training floor affects an estimated 40% of questions; fine-tuned DEF models are the identified next step. --- ### mllm-shap: A Shapley Value Explainability Platform for Text-Audio Multimodal Large Language Models Authors: Jakub Muszyński, Paweł Pozorski, Maria Ganzha Published: 2026-04-21 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2606.07531v1 We introduce mllm-shap, an open-source Python framework designed to extend Shapley Value (SV) explainability from text-only Large Language Models to Multimodal LLMs (MLLMs) processing joint text and audio inputs. While text-based attribution is well-studied, mllm-shap addresses three critical challenges unique to the multimodal regime: (1) Modality-aware coalition masking, which manages the interleaved processing of discrete text tokens and dense audio encoder frames. (2) Multi-turn conversation tracking, utilizing per-token metadata to maintain role and modality context. (3) Phonetic alignment-based token grouping, a novel technique that reduces the coalition space by 10x to 50x, rendering SV estimation computationally feasible for long-form audio. The platform implements five SV estimation strategies, including a Complementary Contributions (CC) estimator with Neyman-optimal allocation that demonstrates superior convergence over standard Monte Carlo baselines. mllm-shap is provided as a pip-installable package featuring an interactive web-based GUI for granular attribution visualization. To our knowledge, this is the first publicly available framework providing a complete, reproducible pipeline for SV-based explainability in text-audio MLLMs. --- ### Finding New Connections between Concepts from Medline Database Incorporating Domain Knowledge Authors: Yang Weikang, Chowdhury S. M. Mazharul Hoque, Jin Wei Published: 2026-04-21 Categories: cs.CL arXiv: https://arxiv.org/abs/2606.07530v1 In this digital world, data is everything and significantly impacts our everyday lives. Interestingly, in this small world, everything is part of an ecosystem, where everything is connected, directly or indirectly. The same thing happens to data as well. In most cases, it may seem like a particular topic does not have any connection with another one, but in reality, they are connected through a mutually related topic. Therefore, in this research, we will discuss an adaptive model modified from the ABC model by Don R. Swanson, a Literature-Based Discovery (LBD) Model, to find the hidden connections between Concepts of Interest. The model demonstrates that two topics, A and C are different and have no relationship. But they have a common topic, B that can be used to connect topics A and C This famous model will be used in this discussion to connect Medical Concepts. --- ### CAPruner: Conceptual-Adjacent Scene Graph Pruner for Enhancing 3D Spatial Reasoning of Large Language Models Authors: Shengli Zhou, Xiangchen Wang, Guanhua Chen, Feng Zheng Published: 2026-04-21 Categories: cs.CL, cs.AI, cs.CV, cs.LG, cs.MM arXiv: https://arxiv.org/abs/2606.07529v1 Large language models (LLMs) have recently been applied to 3D vision-language (3D-VL) tasks, which require spatial reasoning to identify target objects relative to anchors. Scene graphs are commonly employed to represent such relations, but reasoning over complete graphs incurs high token costs and computational inefficiencies, motivating the need for pruning. Existing pruning methods primarily rely on spatial proximity and often remove task-relevant relations, thereby undermining reliable spatial reasoning. To address these limitations, we derive a key requirement for scene graph pruning: preserving spatial relations that are most pertinent to the specific 3D-VL task. Guided by this insight, we propose the Conceptual-Adjacent Scene Graph Pruner (CAPruner). CAPruner integrates fuzzy semantic relevance with spatial proximity to estimate the importance of relations, enabling the selection of critical relations in a task-specific context. Moreover, to avoid costly relation-level annotations, CAPruner is trained by supervising the aggregated scores of each node's incident edges. Extensive experiments demonstrate that CAPruner effectively preserves relations essential for spatial reasoning, leading to substantial performance improvements of LLMs on 3D-VL tasks. Code is available at https://github.com/fz-zsl/CAPruner. --- ### LLMs for Cardiovascular Risk Prediction from Structured Clinical Data Authors: Jeba Maliha, Md Rafiul Kabir Published: 2026-04-21 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2606.00031v1 Coronary artery disease (CAD) remains one of the leading causes of death globally, highlighting the need for reliable predictive systems to support early diagnosis and risk assessment. While traditional machine learning models perform well on structured clinical data, large language models (LLMs) present new possibilities to interpret medical information expressed in natural language. In this work, we develop a hybrid framework that bridges structured clinical data and natural-language representations for CAD prediction. Using a publicly available dataset of 1,190 patient records with 11 clinical attributes, structured variables are converted into interpretable feature representations and synthetic clinical narratives using LLMs. A validation pipeline performs reverse extraction of clinical variables and computes a consistency score with the original records, achieving an average fidelity of 94.61%. We then evaluate four conventional machine learning models and compare their performance with LLM-based classification under zero-shot and few-shot prompting settings. We use two LLMs here, GPT and Gemini. Experimental results show that Random Forest achieves the highest accuracy. Despite this advantage, LLM-based classification remains beneficial in real-world clinical settings. This is because LLMs operate directly on natural language patient descriptions, meaning that sensitive numerical patient data such as exact lab values, blood pressure readings, and diagnostic codes are kept private. Findings suggest that combining structured clinical data with LLM-generated narratives can enable new directions for hybrid clinical prediction systems. --- ### Agentic Literacy Debt: A Structural Problem the AI Literacy Field Has Not Yet Named Authors: Rohith Nama Published: 2026-04-21 Categories: cs.CY, cs.AI arXiv: https://arxiv.org/abs/2605.27396v1 Autonomous AI agents now plan, decide, and act on behalf of users across healthcare, financial services, and workplace contexts, often without step-by-step human approval. Existing AI literacy frameworks were built for a world in which humans evaluate AI outputs and decide whether to act; they have no vocabulary for the user who has delegated decision-making authority to an agent whose actions may not be observable, reversible, or controllable. This paper names the resulting problem agentic literacy debt: the accumulating societal deficit that grows when agentic AI systems are deployed at scale without corresponding literacy infrastructure. The debt compounds through three reinforcing channels (normalization of opaque delegation, multi-agent ecosystem complexity, and institutional path dependence), and it is incurred by the organizations that deploy agents but paid by the users, patients, and citizens on whose behalf the agents act. Evidence from healthcare, financial fraud, and global equity contexts suggests the gap is already consequential. The problem is structural, not a temporary lag that curriculum reform will close. It demands a reframing of AI literacy as a governance capability, not an evaluative one. --- ### Toward Reliable Design of LLM-Enabled Agentic Workflows: Optimizing Latency-Reliability-Cost Tradeoffs Authors: Ya-Ting Yang, Quanyan Zhu Published: 2026-04-21 Categories: cs.AI, cs.SE arXiv: https://arxiv.org/abs/2605.23929v1 Modern AI systems increasingly rely on workflows composed of multiple interacting agents, some powered by large language models (LLMs) and others by conventional computational modules. This paper analyzes the fundamental tradeoffs between latency, reliability, and cost in LLM-enabled agentic workflows. We introduce performance models for both LLM and non-LLM agents that capture the relationship between computational effort and output quality, incorporating the impact of reasoning and output tokens for LLM agents using a parametric exponential reliability function. Then, we study the design of sequential workflows under latency and cost constraints. Main results include a water-filling token allocation policy and characterizations of optimal workflow reliability in terms of shadow prices. --- ### Context: Proactive Goal-Directed Intelligence via Composable Sandboxed Programs, Declarative Wiring, and Structured Interaction Authors: Gregory Magarshak Published: 2026-04-21 Categories: cs.AI, cs.CL, cs.DC, cs.MA, cs.PL, cs.SE arXiv: https://arxiv.org/abs/2605.23928v1 We present Context, the intelligence layer of the Magarshak Architecture, which replaces reactive query-response chatbots with proactive goal-directed agents that advance shared tasks without waiting for user prompts. The architecture rests on three mutually reinforcing mechanisms. Write-time context assembly precomputes enriched typed attributes via Groker agents, assembling interaction context as a deterministic pure function of graph state; context blocks are byte-identical across turns between semantic changes, enabling near-100% KV-cache reuse. Composable sandboxed wisdom programs form a governed library of LM-generated imperative programs declaratively wired to goal types via typed stream relations, composed via phase ordering, and executed at interaction time without further LM calls. Proactive goal stream state machines drive conversations toward terminal states by inspecting graph state and emitting structured interaction content (option arrays, governance affordances, clarification prompts) without awaiting user input. We prove six formal results: the Context Stability Theorem, bounding per-turn LM cost as a function of semantic change rate; a Program Composition Correctness Theorem; a Declarative Wiring Soundness Theorem; the Proactive Dominance Theorem, proving proactive agents weakly dominate reactive agents on expected turns-to-terminal-state; Coordination Overhead Elimination and Quality Preservation, establishing Pareto improvements in multi-participant goal chats; and a Cross-Platform Vote Consistency Theorem. Implemented in the open-source Qbix / Safebox / Safebots stack. --- ### How Much Thinking is Enough? Quantifying and Understanding Redundancy in LLM Reasoning Authors: Zhiyuan Zhai, Xinkai You, Wenjing Yan, Xin Wang Published: 2026-04-21 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2605.23926v1 Reasoning-capable large language models solve hard problems by emitting long chains of thought, paying heavily in latency, GPU time, and energy. Casual inspection of their traces reveals extensive reformulation, verification, and circular self-reflection, yet how much of this deliberation is actually necessary has never been measured at scale or explained from first principles. This paper closes both gaps. We formalise reasoning redundancy directly in terms of the reasoning model itself: the redundancy of a correct trace is the largest fraction of its trailing segmented steps that can be truncated while $π$, forced to terminate thinking and emit a final answer, still produces the correct answer. A large-scale quantification across four frontier reasoning models and two mathematical benchmarks shows that step-level redundancy is consistently high -- between 61% and 93% across the 8 (model, benchmark) conditions we study, with the median critical prefix equal to a single segmented step in six of the eight conditions -- that the finding is robust to the choice of judge family, and that although $ρ$ decreases with problem difficulty on MATH-500, all four models remain substantially redundant ($ρ\in (46\%, 85\%)$) even on the hardest Level-5 problems. We then prove that this redundancy is a structural consequence of length-agnostic outcome rewards, not a model-specific artefact: under any such reward, no finite expected stopping time is optimal. The result holds regardless of RL algorithm, base model, data distribution, or whether the policy is obtained via RL or distillation; over-thinking is therefore not a bug to be patched in individual models but a structural property of how current reasoning models are trained. Code: https://github.com/zhiyuanZhai20/how-much-thinking-is-enough --- ### Mask-to-Correct$^+$: Leveraging Retriever Diversity for Masking-guided Faithful Fact Correction Authors: Payel Santra, Lavisha Sharma, Madhusudan Ghosh, Partha Basuchowdhuri Published: 2026-04-21 Categories: cs.IR, cs.AI arXiv: https://arxiv.org/abs/2605.18776v1 The rapid spread of misinformation on social media highlights the need for robust, automated fact correction frameworks. However, existing works rely on supervised learning from manually annotated claim-evidence pairs, which are scarce and prone to biases, limiting their generalization across domains. Moreover, these methods overlook semantic faithfulness in their correction process. To address these challenges, we propose Mask-to-Correct (M$_2$C), a training-free, inference-only Retrieval Augmented Generation (RAG) based framework that leverages diversity-aware masking to identify erroneous spans of claims and evaluate the faithfulness of corrections using retrieved evidence. However, the effectiveness of RAG heavily depends on the choice of retriever, which may vary across queries. To mitigate this, we further introduce M$_2$C$^+$, an ensemble-based framework that combines corrections across multiple rankers to reduce retrieval bias and improve robustness. Extensive experiments on the benchmark datasets demonstrate that our proposed frameworks consistently outperform all baselines, achieving up to 14% improvement in SARI scores, without using gold evidence. --- ### Query-Aware Flow Diffusion for Graph-Based RAG with Retrieval Guarantees Authors: Zhuoping Zhou, Davoud Ataee Tarzanagh, Sima Didari, Wenjun Hu, Baruch Gutow, Oxana Verkholyak, Masoud Faraki, Heng Hao, Hankyu Moon, Seungjai Min Published: 2026-04-21 Categories: cs.IR, cs.AI arXiv: https://arxiv.org/abs/2605.18775v1 Graph-based Retrieval-Augmented Generation (RAG) systems leverage interconnected knowledge structures to capture complex relationships that flat retrieval struggles with, enabling multi-hop reasoning. Yet most existing graph-based methods suffer from (i) heuristic designs lacking theoretical guarantees for subgraph quality or relevance and/or (ii) the use of static exploration strategies that ignore the query's holistic meaning, retrieving neighborhoods or communities regardless of intent. We propose Query-Aware Flow Diffusion RAG (QAFD-RAG), a training-free framework that dynamically adapts graph traversal to each query's holistic semantics. The central innovation is query-aware traversal: during graph exploration, edges are dynamically weighted by how well their endpoints align with the query's embedding, guiding flow along semantically relevant paths while avoiding structurally connected but irrelevant regions. These query-specific reasoning subgraphs enable the first statistical guarantees for query-aware graph retrieval, showing that QAFD-RAG recovers relevant subgraphs with high probability under mild signal-to-noise conditions. The algorithm converges exponentially fast, with complexity scaling with the retrieved subgraph size rather than the full graph. Experiments on question answering and text-to-SQL tasks demonstrate consistent improvements over state-of-the-art graph-based RAG methods. --- ### In-Situ Behavioral Evaluation for LLM Fairness, Not Standardized-Test Scores Authors: Zeyu Tang, Sang T. Truong, Deonna Owens, Shreyas Sharma, Yibo Jacky Zhang, Brando Miranda, Sanmi Koyejo Published: 2026-04-21 Categories: cs.CL, cs.AI, cs.CY arXiv: https://arxiv.org/abs/2605.12530v2 LLM fairness should be evaluated through in-situ behavioral pattern rather than standardized-test Q&A benchmarks. We show that the standardized-test paradigm can be structurally unreliable: surface-level prompt construction choices, although entirely orthogonal to the fairness question being tested, account for the majority of score variance, shift fairness conclusions in both the direction and the magnitude, and result in severe discordance in model rankings. We develop MAC-Fairness, a framework that embeds controlled variation factors into in-situ behavioral evaluation, examining how models' disparate-treatment behaviors shift when identity is varied as part of natural multi-agent conversation. Repurposing standardized-test questions as conversation seeds rather than as the evaluation instrument, we evaluate within-model differences in position persistence (how they hold positions, from the self-perspective) and peer receptiveness (how receptive they are to peers, from the other-perspective) across 8 million conversation transcripts spanning multiple models and identity presence configurations. In-situ behavioral evaluation reveals stable, model-specific, disparate-treatment behavioral signatures that could generalize across different fairness benchmarks, a form of evidence the standardized-test paradigm does not offer. --- ### In-Situ Behavioral Evaluation for LLM Fairness, Not Standardized-Test Scores Authors: Zeyu Tang, Sang T. Truong, Deonna Owens, Shreyas Sharma, Yibo Jacky Zhang, Brando Miranda, Sanmi Koyejo Published: 2026-04-21 Categories: cs.CL, cs.AI, cs.CY arXiv: https://arxiv.org/abs/2605.12530v1 LLM fairness should be evaluated through in-situ conversational behavior rather than standardized-test Q&A benchmarks. We show that the standardized-test paradigm can be structurally unreliable: surface-level prompt construction choices, although entirely orthogonal to the fairness question being tested, account for the majority of score variance, shift fairness conclusions in both the direction and the magnitude, and result in severe discordance in model rankings. We develop MAC-Fairness, a multi-agent conversational framework that embeds controlled variation factors into multi-round dialogue for in-situ behavior evaluation, examining how models' conversational behavior shifts when identity is varied as part of natural multi-agent interaction. Repurposing standardized-test questions as conversation seeds rather than as the evaluation instrument, we evaluate position persistence (how they hold positions, from the self-perspective) and peer receptiveness (how receptive they are to peers, from the other-perspective) across 8 million conversation transcripts spanning multiple models and identity presence configurations. In-situ behavioral evaluation reveals stable, model-specific behavioral signatures that could generalize across benchmarks differing in fairness targets and evaluation methodologies, a form of evidence the standardized-test paradigm does not offer. --- ### Domain-level metacognitive monitoring in frontier LLMs: A 33-model atlas Authors: Jon-Paul Cacioli Published: 2026-04-21 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2605.06673v1 Aggregate metacognitive quality scores mask within-model variation across MMLU benchmark domains. We administered 1,500 MMLU items (250 per domain, under an a priori six-domain grouping) to 33 frontier LLMs from eight model families and computed Type-2 AUROC per model-domain cell using verbalized confidence (0-100). Total observations: 47,151. Every model with above-chance aggregate monitoring showed non-trivial domain-level variation. Applied/Professional knowledge was reliably the easiest benchmark domain to monitor (mean AUROC = .742, ranked top-2 in 21 of 33 models); Formal Reasoning and Natural Science were reliably the hardest (one of the two ranked bottom-2 in 27 of 33 models). The three middle domains were statistically indistinguishable (Kendall's W = .164). A subject-level coherence analysis (within-domain similarity ratio = 0.95) confirms the six-domain grouping is a pragmatic benchmark taxonomy, not a validated latent construct. Within-family profile-shape clustering is significant for Anthropic, Google-Gemini, and Qwen (permutation p < .0001) but not DeepSeek, Google-Gemma, or OpenAI. Gemma 4 31B showed a +.202 AUROC improvement over Gemma 3 27B. Three models classified Invalid on binary KEEP/WITHDRAW probes produced normal profiles under verbalized confidence, confirming probe-format specificity. Bootstrap 95% CIs on 198 cells have median width .199. Split-half aggregate stability r = .893; profile-level split-half is weaker (grand median r = .184). These results show stable benchmark-domain variation obscured by aggregate metrics, and support benchmark-stage domain screening as a step before deployment in specific application areas. --- ### More Thinking, More Bias: Length-Driven Position Bias in Reasoning Models Authors: Xiao Wang Published: 2026-04-21 Categories: cs.AI, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2605.06672v1 Chain-of-thought (CoT) reasoning and reasoning-tuned models such as DeepSeek-R1 are commonly assumed to reduce shallow heuristic biases by thinking carefully. We test this on position bias in multiple-choice QA and find a different story: within any reasoning-capable model, per-question position bias scales with the length of the reasoning trajectory. Across thirteen reasoning-mode configurations (two R1-distilled 7-8B models, two base models prompted with CoT, and DeepSeek-R1 at 671B) on MMLU, ARC-Challenge, and GPQA, twelve show a positive partial correlation between trajectory length and Position Bias Score (PBS) after controlling for accuracy, ranging from 0.11 to 0.41 (all p < 0.05). All twelve open-weight reasoning-mode configurations show monotonically increasing PBS across length quartiles. A truncation intervention provides causal evidence: continuations resumed from later points in the trajectory are increasingly likely to shift toward position-preferred options (16% to 32% for R1-Qwen-7B across absolute-position buckets). At 671B, aggregate PBS collapses to 0.019, but the length effect still manifests in the longest quartile (PBS = 0.071), suggesting that accuracy gates the expression of length-driven bias rather than eliminating the underlying mechanism. We additionally find that direct-answer position bias is a distinct phenomenon with a different footprint (strong in Llama-Instruct-direct, weak in Qwen-Instruct-direct, and uncorrelated with trajectory length): CoT reasoning replaces this baseline bias with length-accumulated bias. Our results argue that reasoning-capable models should not be treated as order-robust by default in MCQ evaluation pipelines, and offer a diagnostic toolkit (PBS, commitment change point, effective switching, truncation probes) for auditing position bias in reasoning models. --- ### Voice Mapping of Text-to-Speech Systems: A Metric-Based Approach for Voice Quality Assessment Authors: Huanchen Cai, Sten Ternström Published: 2026-04-21 Categories: eess.AS, cs.AI, eess.SP arXiv: https://arxiv.org/abs/2605.00861v1 This study investigates voice mapping as an evaluation framework for text-to-speech (TTS) synthesis quality. The study analyzes six TTS models, including historical and recent ones. The metrics are crest factor, spectrum balance, and cepstral peak prominence (CPPs). We investigated 6 influential TTS models: Merlin, Tacotron 2, Transformer TTS, FastSpeech 2, Glow-TTS, and VITS. The results demonstrate that voice range serves as a primary indicator of model capability, with VITS showing the largest range among tested models. Glow-TTS exhibited superior performance in soft phonation, indicated by higher spectrum balance, despite limited voice range. The results showed that the CPPs values between 7-8 dB indicate natural voice quality, while with CPPs exceeding 10 dB, the speech tends to sound robotic. These findings underscore the need for voice mapping to evaluate vocal effort, and capture how TTS systems handle voice dynamic and expressiveness. --- ### An Adaptive Spatiotemporal Clustering Framework for 3D Ocean Subsurface Temperature Reconstruction Authors: Ming Shan Loo, Wengen Li, Xudong Jiang, Hailiang Cheng, Zhifei Zhang, Jihong Guan, Yichao Zhang Published: 2026-04-21 Categories: physics.ao-ph, cs.LG arXiv: https://arxiv.org/abs/2605.00860v1 The reconstruction of ocean subsurface temperature (OST) using satellite remote sensing data holds significant scientific value for advancing the understanding of ocean dynamics and climate variability. However, the scarcity of subsurface observations, combined with the high degree of nonlinearity and spatiotemporal heterogeneity in subsurface processes, poses substantial challenges to the accuracy and generalization capability of traditional reconstruction methods. To address these limitations, this study proposes an adaptive framework that could capture both vertical structural dependencies and temporal variation patterns of OST via spatio-temporal clustering. By incorporating this framework with various deep learning models, e.g., dual-path convolutional neural networks (DP-CNN), Attention U-Net, and Vision Transformer (ViT), the OST field can be accurately reconstructed at a global scale only using surface observations, i.e., sea surface temperature (SST), sea surface salinity (SSS), sea surface height (SSH), and sea surface wind (SSW). Experimental results demonstrate that multiple deep learning methods using the proposed framework largely outperform their original counterparts, yielding improvements in RMSE ranging from 12.4\% to 27.2\%. This study provides a reliable solution for subsurface temperature reconstruction, offering important implications for meteorological modeling and climate change assessment. --- ### A Hybrid Windkessel-Neural Approach for Improved Noninvasive Blood Pressure Monitoring Authors: Vaibhav Gollapalli, Aniruth Ananthanarayanan Published: 2026-04-21 Categories: eess.SP, cs.CE, cs.LG arXiv: https://arxiv.org/abs/2605.00858v1 Owing to the recent advancements in wearable devices for health care, the importance of BP estimation without cuffs increases. Cuff technologies are inappropriate for continuous BP measurement due to their inconvenient usage, invasive character, necessity of calibration, large size, and inability to perform long-term monitoring. Normally, the algorithm used for cuffless BP prediction employs machine learning models that operate according to the data-driven approach. However, although they show high numerical accuracy, ML models do not provide any interpretability, resulting in poor physiological validity and clinical applicability. We propose a combination of Windkessel and ML models that incorporates the physical aspects into the latter one. It is performed by reformulating Windkessel into a form that will allow employing ML models. The result is a system of ODEs which can be used in the neural network. Thus, the inclusion of physical constraints improves the data-driven approach by making models consistent with physics, understandable, and robust. For illustration, we apply the described technique using a publicly available MIMIC-II database that we obtain from the UCI Machine Learning Repository. --- ### Foundation Model Guided Dual-Branch Co-Adaptation for Source-Free EEG Decoding Authors: Peiliang Gong, Han Zhang, Zhen Jiang, Chenyu Liu, Ziyu Jia, Xinliang Zhou, Daoqiang Zhang, Xiaoli Li Published: 2026-04-21 Categories: eess.SP, cs.AI, cs.LG, q-bio.NC arXiv: https://arxiv.org/abs/2605.00857v1 Source-free domain adaptation (SFDA) provides a practical solution to cross-subject EEG decoding by adapting source-pretrained models to unlabeled target domains without accessing source data. However, existing SFDA methods rely solely on the limited internal knowledge of source-pretrained models, leading to inferior cross-domain generalization and unreliable pseudo-labels. Although EEG Foundation Models (FMs) pretrained on large-scale data exhibit strong generalizability, their potential in SFDA remains largely unexplored. To this end, we propose FUSED, a Foundation-guided Source-free EEG Decoding framework that integrates a large-scale FM with a compact Specialist Model (SM) via dual-branch co-adaptation. Specifically, we introduce a Co-adaptation mechanism equipping both branches with linear and prototype views, enabling cross-branch pseudo-label generation. Additionally, we design a Consensus Filtering Mechanism that exploits the FM's inherent stability to identify high-quality samples, along with a Two-Stage Pseudo-Label Refinement scheme to suppress error accumulation through cross-branch arbitration. Finally, we calibrate the FM's decision boundaries via mutual information maximization with the SM, followed by knowledge distillation from FM to SM, forming a principled calibrate-then-distill pipeline. To our knowledge, FUSED is the first work to leverage EEG FMs within the SFDA framework for cross-subject EEG decoding. Extensive experiments across three EEG paradigms, including motor imagery, emotion recognition, and SSVEP, demonstrate consistent state-of-the-art performance, validating the effectiveness of foundation-guided synergy for robust and privacy-preserving EEG decoding. --- ### One-Block Transformer (1BT) for EEG-Based Cognitive Workload Assessment Authors: Stefanos Gkikas, Christian Arzate Cruz, Thomas Kassiotis, Giorgos Giannakakis, Raul Fernandez Rojas, Randy Gomez Published: 2026-04-21 Categories: eess.SP, cs.AI, cs.HC, cs.LG arXiv: https://arxiv.org/abs/2605.00856v3 Accurate and continuous estimation of cognitive workload is fundamental to creating adaptive human-machine systems. However, designing architectures that balance representational capacity with computational efficiency has been challenging for practical deployment. This paper introduces 1BT, a One-Block Transformer for compact and efficient EEG-based cognitive workload assessment. The model aggregates multi-channel temporal sequences via a minimal latent bottleneck, using a single cross-attention module followed by lightweight self-attention. A controlled study involving 11 participants performing three cognitively diverse tasks (abstract reasoning, numerical problem-solving, and an interactive video game) was conducted with continuous EEG recordings across two workload levels. Systematic architectural analysis identifies the most compact configuration that preserves high performance, while substantially lowering computational cost. The final model achieves high workload classification performance with under 0.5 million parameters and 0.02 GFLOPs, paving the way for a design direction for real-time cognitive workload monitoring in resource-constrained settings. --- ### An Efficient Spatial Branch-and-Bound Algorithm for Global Optimization of Gaussian Process Posterior Mean Functions Authors: Wei-Ting Tang, Akshay Kudva, Calvin Tsay, Joel A. Paulson Published: 2026-04-21 Categories: math.OC, cs.LG, stat.ML arXiv: https://arxiv.org/abs/2605.00855v1 We study the deterministic global optimization of trained Gaussian process posterior mean functions over hyperrectangular domains. Although the posterior mean function has a compact closed-form representation, its global optimization is challenging because it remains nonlinear and nonconvex. Existing exact deterministic approaches become increasingly difficult to scale as the number of training data points grows, leading to approximation-based methods that improve tractability by optimizing a modified (inexact) objective. In this work, we propose PALM-Mean, a piecewise-analytic lower-bounding framework embedded in reduced-space spatial branch-and-bound. At each node, kernel terms that are locally important are replaced by a sign-aware piecewise-linear relaxation in an appropriate scalar distance variable, while the remaining terms are bounded analytically in closed form. We show this hybrid approach yields a valid lower bound for the posterior mean, while limiting the size of the branch-and-bound subproblems. We establish validity of the node lower bounds and $\varepsilon$-global convergence of the resulting algorithm. Computational results on synthetic benchmarks and real-world application problems show that PALM-Mean improves scalability relative to representative general-purpose deterministic global solvers, particularly as the number of training data points increases. --- ### AgenticRecTune: Multi-Agent with Self-Evolving Skillhub for Recommendation System Optimization Authors: Xidong Wu, Yue Zhuan, Ruoqiao Wei, Hangxin Chen, Di Bai, Jintao Liu, Xinyi Wang, Xue Wang, Luoshu Wang, Xinwu Cheng Published: 2026-04-21 Categories: cs.IR, cs.AI arXiv: https://arxiv.org/abs/2604.26969v2 Modern large-scale recommendation systems are typically constructed as multi-stage pipelines, encompassing pre-ranking, ranking, and re-ranking phases. While traditional recommendation research typically focuses on optimizing a specific model, such as improving the pre-ranking model structure or ranking models training algorithm, system-level configurations optimization play a crucial role, which integrates the output from each model head to get the final score in each stage. Due to the complexity of the system, the configuration optimization is highly important and challenging. Any model modification requires new optimal system-level configurations. But each experimental iteration requires significant tuning effort. Furthermore, models in different stage operates within a distinct context and optimizes for different targets, requiring specialized domain expertise. In addition, optimization success depends on balancing competing multiple online metrics and alignment with shifting production development objectives. To address these challenges, we propose AgenticRecTune, an agentic framework comprising five specialized agents, Actor, Critic, Insight, Skill, and Online, designed to manage the end-to-end configuration optimization workflow. By leveraging the advanced reasoning of Large Language Models (LLMs), specifically Gemini, AgenticRecTune explore the optimal configuration spaces. The Actor Agent proposes multiple candidates and Critic Agent filters out suboptimal proposals.Then Online Agent autonomously prepares A/B tests based on the proposed configurations set from the Critic Agent and captures the subsequencet experimental results. We also introduce a self-evolving Skillhub, which utilizes a collaboration between the Insight Agent and Skill Agent to summarize the history results, extract underlying mechanics of each task in recommendation system and update skills. --- ### Unified Multi-Foundation-Model Slide Representation for Pan-Cancer Recognition and Text-Guided Tumor Localization Authors: Tianyang Wang, Ziyu Su, Abdul Rehman Akbar, Usama Sajjad, Lina Gokhale, Charles Rabolli, Wei Chen, Anil Parwani, Muhammad Khalid Khan Niazi Published: 2026-04-21 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.22846v1 The expanding ecosystem of pathology foundation models has produced powerful but fragmented tile-level representations, limiting their use in clinical tasks that require unified slide-level reasoning and interpretable linkage to clinically meaningful information. We present ASTRA, a pan-cancer framework that integrates heterogeneous foundation-model representations into a shared slide-level representation space and semantically grounds that space using structured pathology annotation fields, including classification category, cancer type, and anatomic site. ASTRA combines sparse mixture-of-experts contextualization, masked multi-model reconstruction, and contrastive alignment to structured pathology prompts to learn slide representations that support 4-category classification, 3-class solid tumor typing, 16-class cancer typing, and text-guided tumor localization without pixel-level supervision. Developed on a CHTN cohort of 10,359 whole-slide images (WSIs) spanning 16 tumor types, ASTRA consistently improves pan-cancer classification across four pathology foundation-model backbones, achieving up to 97.8% macro-AUC for 4-category classification, 99.7% for 3-class solid tumor typing, and 99.2% for 16-class cancer typing. For tumor localization, ASTRA achieves a mean Dice of 0.897 on an annotated in-domain CHTN subset (n = 380) spanning 16 cancer types and 0.738 on an external TCGA cohort (n = 1,686) spanning four cancer types. These results demonstrate that minimal structured pathology annotation fields derived from slide-level metadata can provide effective semantic supervision for unified slide representation learning, enabling both pan-cancer prediction and weakly supervised tumor localization within a single framework. --- ### Structure Guided Retrieval-Augmented Generation for Factual Queries Authors: Miao Xie, Xiao Zhang, Yi Li, Chunli Lv Published: 2026-04-21 Categories: cs.IR, cs.AI arXiv: https://arxiv.org/abs/2604.22843v1 Retrieval-Augmented Generation (RAG) has been proposed to mitigate hallucinations in large language models (LLMs), where generated outputs may be factually incorrect. However, existing RAG approaches predominantly rely on vector similarity for retrieval, which is prone to semantic noise and fails to ensure that generated responses fully satisfy the complex conditions specified by factual queries, often leading to incorrect answers. To address this challenge, we introduce a novel research problem, named Exact Retrieval Problem (ERP). To the best of our knowledge, this is the first problem formulation that explicitly incorporates structural information into RAG for factual questions to satisfy all query conditions. For this novel problem, we propose Structure Guided Retrieval-Augmented Generation (SG-RAG), which models the retrieval process as an embedding-based subgraph matching task, and uses the retrieved topological structures to guide the LLM to generate answers that meet all specified query conditions. To facilitate evaluation of ERP, we construct and publicly release Exact Retrieval Question Answering (ERQA), a large-scale dataset comprising 120000 fact-oriented QA pairs, each involving complex conditions, spanning 20 diverse domains. The experimental results demonstrate that SG-RAG significantly outperforms strong baselines on ERQA, delivering absolute improvements from 20.68 to 50.88 points across all evaluation metrics, while maintaining reasonable computational overhead. --- ### EX-FIQA: Leveraging Intermediate Early eXit Representations from Vision Transformers for Face Image Quality Assessment Authors: Guray Ozgur, Tahar Chettaoui, Eduarda Caldeira, Jan Niklas Kolf, Andrea Atzori, Fadi Boutros, Naser Damer Published: 2026-04-21 Categories: cs.CV, eess.IV arXiv: https://arxiv.org/abs/2604.22842v1 Face Image Quality Assessment is crucial for reliable face recognition systems, yet existing Vision Transformer-based approaches rely exclusively on final-layer representations, ignoring quality-relevant information captured at intermediate network depths. This paper presents the first comprehensive investigation of how intermediate representations within ViTs contribute to face quality assessment through early exit mechanisms and score fusion strategies. We systematically analyze all twelve transformer blocks of ViT-FIQA architectures, demonstrating that different depths capture distinct and complementary quality-relevant information, as evidenced by varying attention patterns and performance characteristics across network layers. We propose a score fusion framework that combines quality predictions from multiple transformer blocks without architectural modifications or additional training. Our early exit analysis reveals optimal performance-efficiency trade-offs, enabling significant computational savings while maintaining competitive performance. Through extensive evaluation across eight benchmark datasets using four FR models, we demonstrate that our fusion strategy improves upon single-exit approaches. Our proposed quality fusion approach employs depth-weighted averaging that assigns progressively higher importance to deeper transformer blocks, achieving the best quality assessment performance by effectively leveraging the hierarchical nature of feature learning in ViTs. Our work challenges the conventional wisdom that only deep features matter for face analysis, revealing that intermediate representations contain valuable information for quality assessment. The proposed framework offers practical benefits for real-world biometric systems by enabling adaptive computation based on resource constraints while maintaining competitive quality assessment capabilities. --- ### ATTN-FIQA: Interpretable Attention-based Face Image Quality Assessment with Vision Transformers Authors: Guray Ozgur, Tahar Chettaoui, Eduarda Caldeira, Jan Niklas Kolf, Marco Huber, Andrea Atzori, Naser Damer, Fadi Boutros Published: 2026-04-21 Categories: cs.CV, eess.IV arXiv: https://arxiv.org/abs/2604.22841v1 Face Image Quality Assessment (FIQA) aims to assess the recognition utility of face samples and is essential for reliable face recognition (FR) systems. Existing approaches require computationally expensive procedures such as multiple forward passes, backpropagation, or additional training, and only recent work has focused on the use of Vision Transformers. Recent studies highlighted that these architectures inherently function as saliency learners with attention patterns naturally encoding spatial importance. This work proposes ATTN-FIQA, a novel training-free approach that investigates whether pre-softmax attention scores from pre-trained Vision Transformer-based face recognition models can serve as quality indicators. We hypothesize that attention magnitudes intrinsically encode quality: high-quality images with discriminative facial features enable strong query-key alignments producing focused, high-magnitude attention patterns, while degraded images generate diffuse, low-magnitude patterns. ATTN-FIQA extracts pre-softmax attention matrices from the final transformer block, aggregate multi-head attention information across all patches, and compute image-level quality scores through simple averaging, requiring only a single forward pass through pre-trained models without architectural modifications, backpropagation, or additional training. Through comprehensive evaluation across eight benchmark datasets and four FR models, this work demonstrates that attention-based quality scores effectively correlate with face image quality and provide spatial interpretability, revealing which facial regions contribute most to quality determination. --- ### AeSlides: Incentivizing Aesthetic Layout in LLM-Based Slide Generation via Verifiable Rewards Authors: Yiming Pan, Chengwei Hu, Xuancheng Huang, Can Huang, Mingming Zhao, Yuean Bi, Xiaohan Zhang, Aohan Zeng, Linmei Hu Published: 2026-04-21 Categories: cs.CV, cs.CL, cs.MM arXiv: https://arxiv.org/abs/2604.22840v1 Large language models (LLMs) have demonstrated strong potential in agentic tasks, particularly in slide generation. However, slide generation poses a fundamental challenge: the generation process is text-centric, whereas its quality is governed by visual aesthetics. This modality gap leads current models to frequently produce slides with aesthetically suboptimal layouts. Existing solutions typically rely either on heavy visual reflection, which incurs high inference cost yet yields limited gains; or on fine-tuning with large-scale datasets, which still provides weak and indirect aesthetic supervision. In contrast, the explicit use of aesthetic principles as supervision remains unexplored. In this work, we present AeSlides, a reinforcement learning framework with verifiable rewards for Aesthetic layout supervision in Slide generation. We introduce a suite of meticulously designed verifiable metrics to quantify slide layout quality, capturing key layout issues in an accurate, efficient, and low-cost manner. Leveraging these verifiable metrics, we develop a GRPO-based reinforcement learning method that directly optimizes slide generation models for aesthetically coherent layouts. With only 5K training prompts on GLM-4.7-Flash, AeSlides improves aspect ratio compliance from 36% to 85%, while reducing whitespace by 44%, element collisions by 43%, and visual imbalance by 28%. Human evaluation further shows a substantial improvement in overall quality, increasing scores from 3.31 to 3.56 (+7.6%), outperforming both model-based reward optimization and reflection-based agentic approaches, and even edging out Claude-Sonnet-4.5. These results demonstrate that such a verifiable aesthetic paradigm provides an efficient and scalable approach to aligning slide generation with human aesthetic preferences. Our repository is available at https://github.com/ympan0508/aeslides. --- ### From Skeletons to Pixels: Few-Shot Precise Event Spotting via Representation and Prediction Distillation Authors: Zhong Han Ervin Yeoh, Jiang Kan Published: 2026-04-21 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2604.22839v1 Precise Event Spotting (PES) is essential in fast-paced sports such as tennis, where fine-grained events occur within very short temporal windows. Accurate frame-level localization is challenging because of motion blur, subtle action differences, and limited annotated data. We study two complementary distillation strategies for few-shot PES: Adaptive Weight Distillation (AWD), a prediction-level method that adaptively weights teacher supervision on unlabeled data, and Annealed Multimodal Distillation for Few-Shot Event Detection (AMD-FED), a representation-level framework that transfers robust skeleton knowledge into visual modalities through annealed pseudo-labeling. Both methods use multimodal distillation to improve generalization under limited supervision. We evaluate them on F3Set-Tennis(sub) under few-shot k-clip settings, where they consistently outperform single-modality baselines and prior PES approaches. After observing the stronger performance of representation-level distillation on tennis, we further validate AMD-FED on a second sports dataset, Figure Skating, where it also shows robust performance in the k-clip scenario. These results highlight the effectiveness of multimodal distillation, especially representation-level transfer, for few-shot precise event spotting. --- ### Neural Network Optimization Reimagined: Decoupled Techniques for Scratch and Fine-Tuning Authors: Xin Ning, Qiankun Li, Xiaolong Huang, Qiupu Chen, Feng He, Weijun Li, Prayag Tiwari, Xinwang Liu Published: 2026-04-21 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2604.22838v1 With the accumulation of resources in the era of big data and the rise of pre-trained models in deep learning, optimizing neural networks for various tasks often involves different strategies for fine-tuning pre-trained models versus training from scratch. However, existing optimizers primarily focus on reducing the loss function by updating model parameters, without fully addressing the unique demands of these two major paradigms. In this paper, we propose DualOpt, a novel approach that decouples optimization techniques specifically tailored for these distinct training scenarios. For training from scratch, we introduce real-time layer-wise weight decay, designed to enhance both convergence and generalization by aligning with the characteristics of weight updates and network architecture. For more importantly fine-tuning, we integrate weight rollback with the optimizer, incorporating a rollback term into each weight update step. This ensures consistency in the weight distribution between upstream and downstream models, effectively mitigating knowledge forgetting and improving fine-tuning performance. Additionally, we extend the layer-wise weight decay to dynamically adjust the rollback levels across layers, adapting to the varying demands of different downstream tasks. Extensive experiments across diverse tasks, including image classification, object detection, semantic segmentation, and instance segmentation, demonstrate the broad applicability and state-of-the-art performance of DualOpt. Code is available at https://github.com/qklee-lz/OLOR-AAAI-2024. --- ### Do Masked Autoencoders Improve Downhole Prediction? An Empirical Study on Real Well Drilling Data Authors: Aleksander Berezowski, Hassan Hassanzadeh, Gouri Ginde Published: 2026-04-21 Categories: cs.LG arXiv: https://arxiv.org/abs/2604.20909v1 Downhole drilling telemetry presents a fundamental labeling asymmetry: surface sensor data are generated continuously at 1~Hz, while labeled downhole measurements are costly, intermittent, and scarce. Current machine learning approaches for downhole metric prediction universally adopt fully supervised training from scratch, which is poorly suited to this data regime. We present the first empirical evaluation of masked autoencoder (MAE) pretraining for downhole drilling metric prediction. Using two publicly available Utah FORGE geothermal wells comprising approximately 3.5 million timesteps of multivariate drilling telemetry, we conduct a systematic full-factorial design space search across 72 MAE configurations and compare them against supervised LSTM and GRU baselines on the task of predicting Total Mud Volume. Results show that the best MAE configuration reduces test mean absolute error by 19.8\% relative to the supervised GRU baseline, while trailing the supervised LSTM baseline by 6.4\%. Analysis of design dimensions reveals that latent space width is the dominant architectural choice (Pearson $r = -0.59$ with test MAE), while masking ratio has negligible effect, an unexpected finding attributed to high temporal redundancy in 1~Hz drilling data. These results establish MAE pretraining as a viable paradigm for drilling analytics and identify the conditions under which it is most beneficial. --- ### Achieving the Kesten-Stigum bound in the non-uniform hypergraph stochastic block model Authors: Manuel Fernandez, Ludovic Stephan, Yizhe Zhu Published: 2026-04-21 Categories: stat.ML, cs.LG, math.CO, math.PR, math.ST arXiv: https://arxiv.org/abs/2604.20907v1 We study the community detection problem in the non-uniform hypergraph stochastic block model (HSBM), where hyperedges of varying sizes coexist. This setting captures higher-order and multi-view interactions and raises a fundamental question: can multiple uniform hypergraph layers below the detection threshold be combined to enable weak recovery? We answer this question by establishing a Kesten--Stigum-type bound for weak recovery in a general class of non-uniform HSBMs with $r$ blocks, generated according to multiple symmetric probability tensors. In the case $r=2$, we show that weak recovery is possible whenever the sum of the signal-to-noise ratios across all uniform hypergraph layers exceeds one, thereby confirming the positive part of a conjecture in (Chodrow et al., 2023). Moreover, we provide a polynomial-time spectral algorithm that achieves this threshold via an optimally weighted non-backtracking operator. For the unweighted non-backtracking matrix, our spectral method attains a different algorithmic threshold, also conjectured in (Chodrow et al., 2023). Our approach develops a spectral theory for weighted non-backtracking operators on non-uniform hypergraphs, including a precise characterization of outlier eigenvalues and eigenvector overlaps. We introduce a novel Ihara--Bass formula tailored to weighted non-uniform hypergraphs, which yields an efficient low-dimensional representation and leads to a provable spectral reconstruction algorithm. Taken together, these results provide a principled and computationally efficient approach to clustering in non-uniform hypergraphs, and highlight the role of optimal weighting in aggregating heterogeneous higher-order interactions. --- ### Biomedical systems biology workflow orchestration and execution with PoSyMed Authors: Simon Süwer, Zoe Chervontseva, Kester Bagemihl, Jan Baumbach, Olga Tsoy, Andreas Maier Published: 2026-04-21 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2604.20906v1 The rapid growth of scientific software has created practical barriers for bioinformatics research. Although powerful statistical, artificial intelligence (AI)-based methods are now widely available, their effective use is often hindered by fragmented distribution, inconsistent documentation, complex dependencies, and difficult-to-reproduce execution environments. As a result, reusing published tools and workflow adaptation to own date remains technically demanding and time-intensive, even for experienced users. Here, we present PoSyMed, an open and modular platform for the controlled integration, composition, and execution of bioinformatics tools and workflows. PoSyMed combines a backend-centered platform architecture with formal tool descriptions, controlled container-based build and execution processes, persistent workflow state, and a dialogue-based user interface. Large language models (LLM) are integrated not as autonomous decision-makers, but as human-computer interface with bounded semantic assistants that help identify tools, propose workflow steps, and support parameterization within a typed, validated, and human-supervised execution environment. PoSyMed is designed to improve reproducibility, traceability, and transparency in practical biomedical analysis within one platform. We describe the system architecture and evaluate its behavior across representative biological software scenarios with respect to workflow support, interaction design, and platform extensibility. PoSyMed is publicly available at https://apps.cosy.bio/posymed. --- ### Reinforcing privacy reasoning in LLMs via normative simulacra from fiction Authors: Matt Franchi, Madiha Zahrah Choksi, Harold Triedman, Helen Nissenbaum Published: 2026-04-21 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2604.20904v1 Information handling practices of LLM agents are broadly misaligned with the contextual privacy expectations of their users. Contextual Integrity (CI) provides a principled framework, defining privacy as the appropriate flow of information within context-relative norms. However, existing approaches either double inference cost via supervisor-assistant architectures, or fine-tune on narrow task-specific data. We propose extracting normative simulacra (structured representations of norms and information flows) from fiction novels and using them to fine-tune LLMs via supervised learning followed by GRPO reinforcement learning. Our composite reward function combines programmatic signals, including task clarity (subsuming schema validity, construct discrimination, and extraction confidence), structural completeness, internal consistency, and context identification, with an LLM judge that evaluates whether the model's privacy reasoning is grounded in the held-out normative universe of the source text. To mitigate overfitting, we introduce per-completion contrastive scoring: each completion is evaluated against both the correct normative universe and a randomly selected wrong one, teaching the model to condition on context rather than memorize source-specific norms. We evaluate on five CI-aligned benchmarks spanning distinct societal contexts and ablate the contributions of RL and normative grounding. Across seven models, SFT introduces a conservative prior toward restricting information flow, improving recognition of privacy-relevant situations but not the correctness of privacy judgments. GRPO with normative grounding achieves the highest score on a law compliance benchmark and strongest correlation with crowdsourced human privacy expectations, demonstrating that fiction-derived normative simulacra can teach contextual privacy reasoning that transfers to real-world domains. --- ### Frequency-Forcing: From Scaling-as-Time to Soft Frequency Guidance Authors: Weitao Du Published: 2026-04-21 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2604.20902v1 While standard flow-matching models transport noise to data uniformly, incorporating an explicit generation order - specifically, establishing coarse, low-frequency structure before fine detail - has proven highly effective for synthesizing natural images. Two recent works offer distinct paradigms for this. K-Flow imposes a hard frequency constraint by reinterpreting a frequency scaling variable as flow time, running the trajectory inside a transformed amplitude space. Latent Forcing provides a soft ordering mechanism by coupling the pixel flow with an auxiliary semantic latent flow via asynchronous time schedules, leaving the pixel interpolation path itself untouched. Viewed from the angle of improving pixel generation, we observe that forcing - guiding generation with an earlier-maturing auxiliary stream - offers a highly compatible route to scale-ordered generation without rewriting the core flow coordinate. Building on this, we propose Frequency-Forcing, which realizes K-Flow's frequency ordering through Latent Forcing's soft mechanism: a standard pixel flow is guided by an auxiliary low-frequency stream that matures earlier in time. Unlike Latent Forcing, whose scratchpad relies on a heavy pretrained encoder (e.g., DINO), our frequency scratchpad is derived from the data itself via a lightweight learnable wavelet packet transform. We term this a self-forcing signal, which avoids external dependencies while learning a basis better adapted to data statistics than the fixed bases used in hard frequency flows. On ImageNet-256, Frequency-Forcing consistently improves FID over strong pixel- and latent-space baselines, and naturally composes with a semantic stream to yield further gains. This illustrates that forcing-based scale ordering is a versatile, path-preserving alternative to hard frequency flows. --- ### Predicting Scale-Up of Metal-Organic Framework Syntheses with Large Language Models Authors: Peter Walther, Hongrui Sheng, Xinxin Liu, Bin Feng, Reid Coyle, Xinhua Yan, Kyle Smith, Harrison Kayal, Shyam Chand Pal, Zhiling Zheng Published: 2026-04-21 Categories: cond-mat.mtrl-sci, cs.AI arXiv: https://arxiv.org/abs/2604.20899v2 Scalable synthesis remains the gate between MOF discovery and industrial deployment, as scale-up know-how is fragmented across disparate reports. We introduce ScaleMOF, a literature-mined dataset and a positive-unlabeled learning strategy that fine-tunes large language models. Achieving 93.5% accuracy, this proof-of-concept serves as a literature-grounded ranking tool prioritizing plausible scale-up candidates. --- ### Watts-per-Intelligence Part II: Algorithmic Catalysis Authors: Elija Perrier Published: 2026-04-21 Categories: cs.IT, cs.AI, physics.comp-ph arXiv: https://arxiv.org/abs/2604.20897v2 We develop a thermodynamic theory of algorithmic catalysis within the watts per intelligence framework, identifying reusable computational structures that reduce irreversible operations for a task class while satisfying bounded restoration and structural selectivity constraints. We prove that any class specific speed-up is upper-bounded by the algorithmic mutual information between the substrate and the class descriptor, and that encoding this information incurs a minimum thermodynamic cost via Landauer erasure. Combining these results yields a coupling theorem that lower-bounds the deployment horizon required for an algorithmic catalyst to be energetically favourable. The framework is illustrated on an affine SAT class and situates contemporary learned systems within an information thermodynamic constraint on intelligent computation. --- ### Towards a Systematic Risk Assessment of Deep Neural Network Limitations in Autonomous Driving Perception Authors: Svetlana Pavlitska, Christopher Gerking, J. Marius Zöllner Published: 2026-04-21 Categories: cs.CR, cs.CY, cs.LG arXiv: https://arxiv.org/abs/2604.20895v1 Safety and security are essential for the admission and acceptance of automated and autonomous vehicles. Deep neural networks (DNNs) are widely used for perception and further components of the autonomous driving (AD) stack. However, they possess several limitations, including lack of generalization, efficiency, explainability, plausibility, and robustness. These insufficiencies can pose significant risks to autonomous driving systems. However, hazards, threats, and risks associated with DNN limitations in this domain have not been systematically studied so far. In this work, we propose a joint workflow for risk assessment combining the hazard analysis and risk assessment (HARA) following ISO 26262 and threat analysis and risk assessment (TARA) following the ISO/SAE 21434 to identify and analyze risks arising from inherent DNN limitations in AD perception. --- ### Federated Learning over Blockchain-Enabled Cloud Infrastructure Authors: Saloni Garg, Amit Sagtani, Kamal Kant Hiran Published: 2026-04-21 Categories: cs.LG, cs.CR, cs.DC arXiv: https://arxiv.org/abs/2604.20062v1 The rise of IoT devices and the uptake of cloud computing have informed a new era of data-driven intelligence. Traditional centralized machine learning models that require a large volume of data to be stored in a single location have therefore become more susceptible to data breaches, privacy violations, and regulatory non-compliance. This report presents a thorough examination of the merging of Federated Learning (FL) and blockchain technology in a cloud-edge setting, demonstrating it as an effective solution to the stated concerns. We are proposing a detailed four-dimensional architectural categorization that meticulously assesses coordination frameworks, consensus algorithms, data storage practices, and trust models that are significant to these integrated systems. The manuscript presents a comprehensive comparative examination of two cutting-edge frameworks: the Multi-Objectives Reinforcement Federated Learning Blockchain (MORFLB), which is designed for intelligent transportation systems, and the Federated Blockchain-IoT Framework for Sustainable Healthcare Systems (FBCI-SHS), elucidating their distinctive contributions and inherent limitations. Lastly, we engage in a thorough evaluation of the literature that integrates a comparative perspective on current frameworks to discern the singular nature of this research within existing knowledge systems. The manuscript culminates in delineating the principal challenges and offering a strategic framework for prospective research trajectories, emphasizing the advancement of adaptive, resilient, and standardized BCFL systems across diverse application domains. --- ### From Fuzzy to Formal: Scaling Hospital Quality Improvement with AI Authors: Patrick Vossler, Jean Feng, Venkat Sivaraman, Robert Gallo, Hemal Kanzaria, Dana Freiser, Christopher Ross, Amy Ou, James Marks, Susan Ehrlich, Christopher Peabody, Lucas Zier Published: 2026-04-21 Categories: cs.AI, cs.HC arXiv: https://arxiv.org/abs/2604.20055v1 Hospital Quality Improvement (QI) plays a critical role in optimizing healthcare delivery by translating high-level hospital goals into actionable solutions. A critical step of QI is to identify the key modifiable contributing factors, a process we call QI factor discovery, typically through expert-driven semi-structured qualitative tools like fishbone diagrams, chart reviews, and Lean Healthcare methods. AI has the potential to transform and accelerate QI factor discovery, which is traditionally time- and resource-intensive and limited in reproducibility and auditability. Nevertheless, current AI alignment methods assume the task is well-defined, whereas QI factor discovery is an exploratory, fuzzy, and iterative sense-making process that relies on complex implicit expert judgments. To design an AI pipeline that formalizes the QI process while preserving its exploratory components, we propose viewing the task as learning not only LLM prompts but also the overarching natural-language specifications. In particular, we map QI factor discovery to steps of the classical AI/ML development process (problem formalization, model learning, and model validation) where the specifications are tunable hyperparameters. Domain experts and AI agents iteratively refine both the overarching specifications and AI pipeline until AI extractions are concordant with expert annotations and aligned with clinical objectives. We applied this "Human-AI Spec-Solution Co-optimization" framework at an urban safety-net hospital to identify factors driving prolonged length of stay and unplanned 30-day readmissions. The resulting AI-for-QI pipelines achieved $\ge 70\%$ concordance with expert annotations. Compared to prior manual Lean analyses, the AI pipeline was substantially more efficient, recovered previous findings, surfaced new modifiable factors, and produced auditable reasoning traces. --- ### Bootstrapping Post-training Signals for Open-ended Tasks via Rubric-based Self-play on Pre-training Text Authors: Chengyu Huang, Sheng-Yen Chou, Zhengxin Zhang, Claire Cardie Published: 2026-04-21 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2604.20051v2 Self-play has recently emerged as a promising paradigm for post-training Large Language Models (LLMs). In self-play, the target LLM creates the task input (e.g., a question), which it then addresses itself by producing a task output (e.g., an answer). A reward model evaluates the output, and the rewards are used to train the LLM, typically via Reinforcement Learning (RL). A key benefit of self-play for post-training LLMs is its minimal supervision costs: self-play avoids the need for high-quality input-output pairs traditionally constructed by humans or expensive proprietary models. Existing work, however, explores self-play only for verifiable tasks, such as math and coding, for which objective ground truth is available and easily checkable. In this paper, we seek to extend self-play to more realistic open-ended tasks. We propose POP, a self-play framework that uses the same LLM to synthesize evaluation rubrics along with each input-output pair. The rubric is used to evaluate outputs and train the model. Crucially, we ground the framework on a content-rich pretraining corpus to (1) enable an exploitable generation-verification gap and reduce reward hacking, and (2) prevent mode collapse. On Qwen-2.5-7B, POP increases performance of both the pretrained base model and instruction-tuned model on multiple tasks ranging from long-form healthcare QA to creative writing and instruction following. --- ### Information Aggregation with AI Agents Authors: Spyros Galanis Published: 2026-04-21 Categories: econ.GN, cs.AI, cs.GT arXiv: https://arxiv.org/abs/2604.20050v4 Can Large Language Models (AI agents) aggregate dispersed private information through trading and reason about the knowledge of others by observing price movements? We conduct a controlled experiment where AI agents trade in a prediction market after receiving private signals, across four information structures of increasing complexity. We find that although the median market is effective at aggregating information in the easy information structures, performance deteriorates in the harder structures, suggesting that AI agents struggle in environments where more than two levels of interactive reasoning are required, a ceiling close to the one documented in human subjects. Consistent with our theoretical predictions, market accuracy does not improve from allowing cheap talk communication, changing the duration of the market, or strategic prompting; initial price has little average effect but matters in the very hard structure. We also find that ``smarter'' AI agents perform better at aggregation and are more profitable. Surprisingly, giving them feedback about past performance does not improve aggregation. A further wave of markets, run three months later with capability-frontier models, aggregates information more often in the three easier structures but not in the hardest one, where higher capability replaces markets that are confidently wrong with markets that hedge near 0.5. --- ### Information Aggregation with AI Agents Authors: Spyros Galanis Published: 2026-04-21 Categories: econ.GN, cs.AI, cs.GT arXiv: https://arxiv.org/abs/2604.20050v3 Can Large Language Models (AI agents) aggregate dispersed private information through trading and reason about the knowledge of others by observing price movements? We conduct a controlled experiment where AI agents trade in a prediction market after receiving private signals, measuring information aggregation by the log error of the last price. We find that although the median market is effective at aggregating information in the easy information structures, performance deteriorates in the harder structures, suggesting that AI agents may suffer from similar limitations as humans when reasoning about others. Consistent with our theoretical predictions, market accuracy does not improve from allowing cheap talk communication, changing the duration of the market, or strategic prompting; initial price has little average effect but matters in the very hard structure. We also find that "smarter" AI agents perform better at aggregation and are more profitable. Surprisingly, giving them feedback about past performance does not improve aggregation. --- ### Culturally uneven urban perception in large language models Authors: Rong Zhao, Wanqi Liu, Zhizhou Sha, Nanxi Su, Yecheng Zhang, Ying Long Published: 2026-04-21 Categories: cs.CL, cs.CY arXiv: https://arxiv.org/abs/2604.20048v3 Large language models (LLMs) are increasingly used to describe and evaluate cities, yet the cultural structure of their urban judgments remains understudied. Here we introduce a measurement framework for testing whether LLM-based urban perception is culturally neutral, using a globally stratified street-view image dataset. Open-ended descriptions and structured scores generated by three frontier multimodal models all show that the neutral baseline lies closer to regional framings associated with Europe and North America than to other cultural framings. Comparisons between AI and human urban perception further show that prompting can move AI responses closer to specific regional human descriptions, but fails to recover the variety and diversity of human responses, flattening observed demographic patterns and introducing sentiment-based self-favouring bias. These results indicate a systematic risk in treating AI as a neutral tool for urban tasks, especially when model outputs are used to compare, evaluate or represent cities across cultural contexts. --- ### PASTA: A Patch-Agnostic Twofold-Stealthy Backdoor Attack on Vision Transformers Authors: Dazhuang Liu, Yanqi Qiao, Rui Wang, Kaitai Liang, Georgios Smaragdakis Published: 2026-04-21 Categories: cs.CV, cs.CR arXiv: https://arxiv.org/abs/2604.20047v1 Vision Transformers (ViTs) have achieved remarkable success across vision tasks, yet recent studies show they remain vulnerable to backdoor attacks. Existing patch-wise attacks typically assume a single fixed trigger location during inference to maximize trigger attention. However, they overlook the self-attention mechanism in ViTs, which captures long-range dependencies across patches. In this work, we observe that a patch-wise trigger can achieve high attack effectiveness when activating backdoors across neighboring patches, a phenomenon we term the Trigger Radiating Effect (TRE). We further find that inter-patch trigger insertion during training can synergistically enhance TRE compared to single-patch insertion. Prior ViT-specific attacks that maximize trigger attention often sacrifice visual and attention stealthiness, making them detectable. Based on these insights, we propose PASTA, a twofold stealthy patch-wise backdoor attack in both pixel and attention domains. PASTA enables backdoor activation when the trigger is placed at arbitrary patches during inference. To achieve this, we introduce a multi-location trigger insertion strategy to enhance TRE. However, preserving stealthiness while maintaining strong TRE is challenging, as TRE is weakened under stealthy constraints. We therefore formulate a bi-level optimization problem and propose an adaptive backdoor learning framework, where the model and trigger iteratively adapt to each other to avoid local optima. Extensive experiments show that PASTA achieves 99.13% attack success rate across arbitrary patches on average, while significantly improving visual and attention stealthiness (144.43x and 18.68x) and robustness (2.79x) against state-of-the-art ViT defenses across four datasets, outperforming CNN- and ViT-based baselines. --- ### Gaussians on a Diet: High-Quality Memory-Bounded 3D Gaussian Splatting Training Authors: Yangming Zhang, Jian Xu, Chaojian Li, Kunxiong Zhu, Wei Niu, Gagan Agrawal, Yang Katie Zhao, Jian Wang, Yingyan Celine Lin, Miao Yin Published: 2026-04-21 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.20046v2 3D Gaussian Splatting (3DGS) has revolutionized novel view synthesis with high-quality rendering through continuous aggregations of millions of 3D Gaussian primitives. However, it suffers from a substantial memory footprint, particularly during training due to uncontrolled densification, posing a critical bottleneck for deployment on memory-constrained edge devices. While existing methods prune redundant Gaussians post-training, they fail to address the peak memory spikes caused by the abrupt growth of Gaussians early in the training process. To solve the training memory consumption problem, we propose a systematic memory-bounded training framework that dynamically optimizes Gaussians through iterative growth and pruning. In other words, the proposed framework alternates between incremental pruning of low-impact Gaussians and strategic growing of new primitives with an adaptive Gaussian compensation, maintaining a near-constant low memory usage while progressively refining rendering fidelity. We comprehensively evaluate the proposed training framework on various real-world datasets under strict memory constraints, showing significant improvements over existing state-of-the-art methods. Particularly, our proposed method practically enables memory-efficient 3DGS training on NVIDIA Jetson AGX Xavier, achieving similar visual quality with up to 80% lower peak training memory consumption than the original 3DGS. --- ### TriEx: A Game-based Tri-View Framework for Explaining Internal Reasoning in Multi-Agent LLMs Authors: Ziyi Wang, Chen Zhang, Wenjun Peng, Qi Wu, Xinyu Wang Published: 2026-04-21 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2604.20043v1 Explainability for Large Language Model (LLM) agents is especially challenging in interactive, partially observable settings, where decisions depend on evolving beliefs and other agents. We present \textbf{TriEx}, a tri-view explainability framework that instruments sequential decision making with aligned artifacts: (i) structured first-person self-reasoning bound to an action, (ii) explicit second-person belief states about opponents updated over time, and (iii) third-person oracle audits grounded in environment-derived reference signals. This design turns explanations from free-form narratives into evidence-anchored objects that can be compared and checked across time and perspectives. Using imperfect-information strategic games as a controlled testbed, we show that TriEx enables scalable analysis of explanation faithfulness, belief dynamics, and evaluator reliability, revealing systematic mismatches between what agents say, what they believe, and what they do. Our results highlight explainability as an interaction-dependent property and motivate multi-view, evidence-grounded evaluation for LLM agents. Code is available at https://github.com/Einsam1819/TriEx. --- ### Normalizing Flows with Iterative Denoising Authors: Tianrong Chen, Jiatao Gu, David Berthelot, Joshua Susskind, Shuangfei Zhai Published: 2026-04-21 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2604.20041v1 Normalizing Flows (NFs) are a classical family of likelihood-based methods that have received revived attention. Recent efforts such as TARFlow have shown that NFs are capable of achieving promising performance on image modeling tasks, making them viable alternatives to other methods such as diffusion models. In this work, we further advance the state of Normalizing Flow generative models by introducing iterative TARFlow (iTARFlow). Unlike diffusion models, iTARFlow maintains a fully end-to-end, likelihood-based objective during training. During sampling, it performs autoregressive generation followed by an iterative denoising procedure inspired by diffusion-style methods. Through extensive experiments, we show that iTARFlow achieves competitive performance across ImageNet resolutions of 64, 128, and 256 pixels, demonstrating its potential as a strong generative model and advancing the frontier of Normalizing Flows. In addition, we analyze the characteristic artifacts produced by iTARFlow, offering insights that may shed light on future improvements. Code is available at https://github.com/apple/ml-itarflow. --- ### Separable Pathways for Causal Reasoning: How Architectural Scaffolding Enables Hypothesis-Space Restructuring in LLM Agents Authors: John Alderete, Sebastian Benthall, Connie Xu, John Xing Published: 2026-04-21 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2604.20039v1 Causal discovery through experimentation and intervention is fundamental to robust problem solving. It requires not just updating beliefs within a fixed framework but revising the hypothesis space itself, a capacity current AI agents lack when evidence demands representations they have not previously constructed. We extend the blicket detector paradigm from developmental science to test this capacity in AI agents equipped with architectural scaffolding that targets hypothesis-space restructuring. Our compositional architecture has two discrete components: context graphs, which structure exploration as typed state machines, and dynamic behaviors, which monitor for evidence that the current hypothesis space is inadequate and expand it at runtime. Across 1,085 experimental trials, these components make orthogonal contributions: context graphs drive reasoning quality within the post-switch hypothesis space, accounting for 94\% of the accuracy gain, while dynamic behaviors drive reasoning eligibility by detecting regime changes and preventing premature commitment to outdated hypotheses. --- ### FluSplat: Sparse-View 3D Editing without Test-Time Optimization Authors: Haitao Huang, Shin-Fang Chng, Huangying Zhan, Qingan Yan, Yi Xu Published: 2026-04-21 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.20038v1 Recent advances in text-guided image editing and 3D Gaussian Splatting (3DGS) have enabled high-quality 3D scene manipulation. However, existing pipelines rely on iterative edit-and-fit optimization at test time, alternating between 2D diffusion editing and 3D reconstruction. This process is computationally expensive, scene-specific, and prone to cross-view inconsistencies. We propose a feed-forward framework for cross-view consistent 3D scene editing from sparse views. Instead of enforcing consistency through iterative 3D refinement, we introduce a cross-view regularization scheme in the image domain during training. By jointly supervising multi-view edits with geometric alignment constraints, our model produces view-consistent results without per-scene optimization at inference. The edited views are then lifted into 3D via a feedforward 3DGS model, yielding a coherent 3DGS representation in a single forward pass. Experiments demonstrate competitive editing fidelity and substantially improved cross-view consistency compared to optimization-based methods, while reducing inference time by orders of magnitude. --- ### Decision-Focused Federated Learning Under Heterogeneous Objectives and Constraints Authors: Konstantinos Ziliaskopoulos, Alexander Vinel Published: 2026-04-21 Categories: math.OC, cs.LG, stat.ML arXiv: https://arxiv.org/abs/2604.20031v2 We consider Decision-Focused Federated Learning (DFFL), a predict-then-optimize setting in which multiple clients collaboratively train predictive models for downstream linear optimization problems without exchanging raw data. Besides the data heterogeneity typical of standard federated learning, clients may also have different objective functions and feasible regions. Building on the SPO+ surrogate loss, we derive heterogeneity bounds that separate objective shift, measured through cost-vector distances, from feasible-set shift, measured through support-function and shape-distance terms. We show that, for general compact feasible sets, small objective perturbations can still induce nonvanishing decision-focused loss discrepancies, while strongly convex feasible regions yield sharper stability-based bounds. We then lift these pointwise bounds to a local-versus-federated excess-risk comparison, showing that federation is beneficial when the statistical advantage of pooling exceeds a client-specific heterogeneity penalty. Computational experiments on polyhedral and strongly convex problems confirm that federation is substantially more robust under strongly convex feasible regions. Finally, we evaluate a simple validation-based interpolation between local and federated DFFL models. This interpolation mitigates the theoretical tradeoff and reduces aggregate regret and worst-client harm in both synthetic experiments and a PJM energy-pricing case study. ---