# Research Papers — 2026-04 · bundle page 60 of 233

> Full-text markdown of papers #2951–3000 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/60
[← Previous bundle](https://aipod.dev/papers/archive/2026-04/page/59.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-04/page/61.md)

### Tokenised Flow Matching for Hierarchical Simulation Based Inference

Authors: Giovanni Charles, Cosmo Santoni, Seth Flaxman, Elizaveta Semenova
Published: 2026-04-22
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2604.20723v1

The cost of simulator evaluations is a key practical bottleneck for Simulation Based Inference (SBI). In hierarchical settings with shared global parameters and exchangeable site-level parameters and observations, this structure can be exploited to improve simulation efficiency. Existing hierarchical SBI approaches factorise the posterior yet still simulate across multiple sites per training sample; We instead explore likelihood factorisation (LF) to train from single-site simulations. In LF sampling we learn a per-site neural surrogate of the simulator and then assemble synthetic multi-site observations to amortise inference for the full hierarchical posterior. Building on this, we propose Tokenised Flow Matching for Posterior Estimation (TFMPE), a tokenised flow matching approach that supports function-valued observations through likelihood factorisation. To enable systematic evaluation, we introduce a benchmark for hierarchical SBI. We validate TFMPE on this benchmark and on realistic infectious disease and computational fluid dynamics models, finding well-calibrated posteriors while reducing computational cost.

---

### COMPASS: COntinual Multilingual PEFT with Adaptive Semantic Sampling

Authors: Noah Flynn
Published: 2026-04-22
Categories: cs.LG, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2604.20720v1

Large language models (LLMs) often exhibit performance disparities across languages, with naive multilingual fine-tuning frequently degrading performance due to negative cross-lingual interference. To address this, we introduce COMPASS (COntinual Multilingual PEFT with Adaptive Semantic Sampling), a novel data-centric framework for adapting LLMs to target languages. COMPASS leverages parameter-efficient fine-tuning (PEFT) by training lightweight, language-specific adapters on a judiciously selected subset of auxiliary multilingual data. The core of our method is a distribution-aware sampling strategy that uses multilingual embeddings and clustering to identify semantic gaps between existing training data and a target usage distribution. By prioritizing auxiliary data from under-represented semantic clusters, COMPASS maximizes positive cross-lingual transfer while minimizing interference. We extend this into a continual learning framework, COMPASS-ECDA, which monitors for data distribution shifts in production and dynamically updates adapters to prevent model staleness, balancing adaptation to new data with the preservation of existing knowledge. Across three different model architectures (Phi-4-Mini, Llama-3.1-8B, and Qwen2.5-7B) and multiple challenging multilingual benchmarks (Global-MMLU, MMLU-ProX), including unseen long-context tasks (OneRuler), we demonstrate that COMPASS consistently outperforms baseline methods guided by linguistic similarity, providing an effective, efficient, and sustainable solution for developing and maintaining high-performing multilingual models in dynamic environments.

---

### ONOTE: Hypergraph-Grounded Omnimodal Reasoning for Computational Music Science

Authors: Menghe Ma, Siqing Wei, Yuecheng Xing, Ziyue Zhu, Zhenghong Lin, Yaheng Wang, Fanhong Meng, Peijun Han, Luu Anh Tuan, Haoran Luo
Published: 2026-04-22
Categories: cs.SD, cs.AI, cs.MM, eess.AS
arXiv: https://arxiv.org/abs/2604.20719v2

Omnimodal notation processing, centered on sheet music, is a controlled scientific setting in which auditory, visual, symbolic, and physical representations must encode the same musical events. Yet existing work remains fragmented across recognition and transcription, rarely testing structural consistency across notation systems. Western-staff bias and underspecified model judges further conceal errors in pitch, timing, ordering, and instrument-specific constraints. We introduce ONOTE, a unified framework that treats music as a scientifically structured domain of measurable cross-representation correspondences. Its test-only benchmark draws on a diverse collection of musical sources covering staff, Jianpu, and tablature across varied genres, instruments, and structural conditions, with aligned multimodal derivatives. Four complementary tasks cover score understanding, notation conversion, audio transcription, and symbolic generation, testing pitch and duration ordering, output syntax, and disclosed instrument-specific constraints. ONOTE also constructs a provenance-bearing proposition hypergraph from external music-theory materials for entity- and hyperedge-based evidence retrieval. Deterministic validity checks, disclosed structural-compliance SMG scoring, and controlled RAG comparisons reveal gaps between visual recognition and structure-preserving outputs. Results separate perception from music-theory application and structural or physical constraint satisfaction. ONOTE provides an auditable framework for studying representation invariance and knowledge-grounded intervention in computational music science.

---

### ONOTE: Benchmarking Omnimodal Notation Processing for Expert-level Music Intelligence

Authors: Menghe Ma, Siqing Wei, Yuecheng Xing, Yaheng Wang, Fanhong Meng, Peijun Han, Luu Anh Tuan, Haoran Luo
Published: 2026-04-22
Categories: cs.SD, cs.AI, cs.MM, eess.AS
arXiv: https://arxiv.org/abs/2604.20719v1

Omnimodal Notation Processing (ONP) represents a unique frontier for omnimodal AI due to the rigorous, multi-dimensional alignment required across auditory, visual, and symbolic domains. Current research remains fragmented, focusing on isolated transcription tasks that fail to bridge the gap between superficial pattern recognition and the underlying musical logic. This landscape is further complicated by severe notation biases toward Western staff and the inherent unreliability of "LLM-as-a-judge" metrics, which often mask structural reasoning failures with systemic hallucinations. To establish a more rigorous standard, we introduce ONOTE, a multi-format benchmark that utilizes a deterministic pipeline--grounded in canonical pitch projection--to eliminate subjective scoring biases across diverse notation systems. Our evaluation of leading omnimodal models exposes a fundamental disconnect between perceptual accuracy and music-theoretic comprehension, providing a necessary framework for diagnosing reasoning vulnerabilities in complex, rule-constrained domains.

---

### GeoRelight: Learning Joint Geometrical Relighting and Reconstruction with Flexible Multi-Modal Diffusion Transformers

Authors: Yuxuan Xue, Ruofan Liang, Egor Zakharov, Timur Bagautdinov, Chen Cao, Giljoo Nam, Shunsuke Saito, Gerard Pons-Moll, Javier Romero
Published: 2026-04-22
Categories: cs.CV
arXiv: https://arxiv.org/abs/2604.20715v1

Relighting a person from a single photo is an attractive but ill-posed task, as a 2D image ambiguously entangles 3D geometry, intrinsic appearance, and illumination. Current methods either use sequential pipelines that suffer from error accumulation, or they do not explicitly leverage 3D geometry during relighting, which limits physical consistency. Since relighting and estimation of 3D geometry are mutually beneficial tasks, we propose a unified Multi-Modal Diffusion Transformer (DiT) that jointly solves for both: GeoRelight. We make this possible through two key technical contributions: isotropic NDC-Orthographic Depth (iNOD), a distortion-free 3D representation compatible with latent diffusion models; and a strategic mixed-data training method that combines synthetic and auto-labeled real data. By solving geometry and relighting jointly, GeoRelight achieves better performance than both sequential models and previous systems that ignored geometry.

---

### Learning to Evolve: A Self-Improving Framework for Multi-Agent Systems via Textual Parameter Graph Optimization

Authors: Shan He, Runze Wang, Zhuoyun Du, Huiyu Bai, Zouying Cao, Yu Cheng, Bo Zheng
Published: 2026-04-22
Categories: cs.AI
arXiv: https://arxiv.org/abs/2604.20714v1

Designing and optimizing multi-agent systems (MAS) is a complex, labor-intensive process of "Agent Engineering." Existing automatic optimization methods, primarily focused on flat prompt tuning, lack the structural awareness to debug the intricate web of interactions in MAS. More critically, these optimizers are static; they do not learn from experience to improve their own optimization strategies. To address these gaps, we introduce Textual Parameter Graph Optimization (TPGO), a framework that enables a multi-agent system to learn to evolve. TPGO first models the MAS as a Textual Parameter Graph (TPG), where agents, tools, and workflows are modular, optimizable nodes. To guide evolution, we derive "textual gradients," structured natural language feedback from execution traces, to pinpoint failures and suggest granular modifications. The core of our framework is Group Relative Agent Optimization (GRAO), a novel meta-learning strategy that learns from historical optimization experiences. By analyzing past successes and failures, GRAO becomes progressively better at proposing effective updates, allowing the system to learn how to optimize itself. Extensive experiments on complex benchmarks like GAIA and MCP-Universe show that TPGO significantly enhances the performance of state-of-the-art agent frameworks, achieving higher success rates through automated, self-improving optimization.

---

### Participatory provenance as representational auditing for AI-mediated public consultation

Authors: Sachit Mahajan
Published: 2026-04-22
Categories: cs.AI, cs.HC
arXiv: https://arxiv.org/abs/2604.20711v3

AI-assisted consultation can speed large-scale public engagement, but concise summaries may reflect some submissions more closely than others. This paper introduces participatory provenance, a framework for auditing how semantic coverage is distributed from submissions to summary sentences. Applied to two topics in Canada's 2025 AI Strategy consultation (5,253 records; 2,861 participants), official summaries had higher observed mean coverage than exact-length random text, although statistical significance depended on the embedding model. Low coverage concentrated in semantic regions, especially those centered on criticism of educational technology and distrust of technology and oversight, whereas few or no records crossed the operational threshold in several better-covered regions. Same-budget, cross-fitted extractive benchmarks improved mean and lower-tail coverage on held-out submissions, showing that better semantic coverage was feasible without longer summaries. Consultation summaries should be evaluated not only for coherence and factual support, but also for how coverage is distributed across the range of submitted views.

---

### Generative Flow Networks for Model Adaptation in Digital Twins of Natural Systems

Authors: Pascal Archambault, Houari Sahraoui, Eugene Syriani
Published: 2026-04-22
Categories: cs.LG, eess.SY
arXiv: https://arxiv.org/abs/2604.20707v1

Digital twins of natural systems must remain aligned with physical systems that evolve over time, are only partially observed, and are typically modeled by mechanistic simulators whose parameters cannot be measured directly. In such settings, model adaptation is naturally posed as a simulation-based inference problem. However, sparse and indirect observations often fail to identify a unique and optimal calibration, leaving several simulator parameterizations compatible with the available evidence. This article presents a GFlowNet-based approach to model adaptation for digital twins of natural systems. We formulate adaptation as a generative modeling problem over complete simulator configurations, so that plausible parameterizations can be sampled with probability proportional to a reward derived from agreement between simulated and observed behavior. Using a controlled environment agriculture case study based on a mechanistic tomato model, we show that the learned policy recovers dominant regions of the adaptation landscape, retrieves strong calibration hypotheses, and preserves multiple plausible configurations under uncertainty.

---

### QuanForge: A Mutation Testing Framework for Quantum Neural Networks

Authors: Minqi Shao, Shangzhou Xia, Jianjun Zhao
Published: 2026-04-22
Categories: cs.SE, cs.AI
arXiv: https://arxiv.org/abs/2604.20706v1

With the growing synergy between deep learning and quantum computing, Quantum Neural Networks (QNNs) have emerged as a promising paradigm by leveraging quantum parallelism and entanglement. However, testing QNNs remains underexplored due to their complex quantum dynamics and limited interpretability. Developing a mutation testing technique for QNNs is promising while requires addressing stochastic factors, including the inherent randomness of mutation operators and quantum measurements. To tackle these challenges, we propose QuanForge, a mutation testing framework specifically designed for QNNs. We first introduce statistical mutation killing to provide a more reliable criterion. QuanForge incorporates nine post-training mutation operators at both gate and parameter levels, capable of simulating various potential errors in quantum circuits. Finally, a mutant generation algorithm is formalized that systematically produces effective mutants, thereby enabling a robust and reliable mutation analysis. Through extensive experiments on benchmark datasets and QNN architectures, we show that QuanForge can effectively distinguish different test suites and localize vulnerable circuit regions, providing insights for data enhancement and structural assessment of QNNs. We also analyze the generation capabilities of different operators and evaluate performance under simulated noisy conditions to assess the practical feasibility of QuanForge for future quantum devices.

---

### SSL-R1: Self-Supervised Visual Reinforcement Post-Training for Multimodal Large Language Models

Authors: Jiahao Xie, Alessio Tonioni, Nathalie Rauschmayr, Federico Tombari, Bernt Schiele
Published: 2026-04-22
Categories: cs.CV
arXiv: https://arxiv.org/abs/2604.20705v1

Reinforcement learning (RL) with verifiable rewards (RLVR) has demonstrated the great potential of enhancing the reasoning abilities in multimodal large language models (MLLMs). However, the reliance on language-centric priors and expensive manual annotations prevents MLLMs' intrinsic visual understanding and scalable reward designs. In this work, we introduce SSL-R1, a generic self-supervised RL framework that derives verifiable rewards directly from images. To this end, we revisit self-supervised learning (SSL) in visual domains and reformulate widely-used SSL tasks into a set of verifiable visual puzzles for RL post-training, requiring neither human nor external model supervision. Training MLLMs on these tasks substantially improves their performance on multimodal understanding and reasoning benchmarks, highlighting the potential of leveraging vision-centric self-supervised tasks for MLLM post-training. We think this work will provide useful experience in devising effective self-supervised verifiable rewards to enable RL at scale. Project page: https://github.com/Jiahao000/SSL-R1.

---

### Auto-ART: Structured Literature Synthesis and Automated Adversarial Robustness Testing

Authors: Abhijit Talluri
Published: 2026-04-22
Categories: cs.CR, cs.LG
arXiv: https://arxiv.org/abs/2604.20704v1

Adversarial robustness evaluation underpins every claim of trustworthy ML deployment, yet the field suffers from fragmented protocols and undetected gradient masking. We make two contributions. (1) Structured synthesis. We analyze nine peer-reviewed corpus sources (2020--2026) through seven complementary protocols, producing the first end-to-end structured analysis of the field's consensus and unresolved challenges. (2) Auto-ART framework. We introduce Auto-ART, an open-source framework that operationalizes identified gaps: 50+ attacks, 28 defense modules, the Robustness Diagnostic Index (RDI), and gradient-masking detection. It supports multi-norm evaluation (l1/l2/linf/semantic/spatial) and compliance mapping to NIST AI RMF, OWASP LLM Top 10, and the EU AI Act. Empirical validation on RobustBench demonstrates that Auto-ART's pre-screening identifies gradient masking in 92% of flagged cases, and RDI rankings correlate highly with full AutoAttack. Multi-norm evaluation exposes a 23.5 pp gap between average and worst-case robustness on state-of-the-art models. No prior work combines such structured meta-scientific analysis with an executable evaluation framework bridging literature gaps into engineering.

---

### R-CoV: Region-Aware Chain-of-Verification for Alleviating Object Hallucinations in LVLMs

Authors: Jiahao Xie, Alessio Tonioni, Nathalie Rauschmayr, Federico Tombari, Bernt Schiele
Published: 2026-04-22
Categories: cs.CV
arXiv: https://arxiv.org/abs/2604.20696v1

Large vision-language models (LVLMs) have demonstrated impressive performance in various multimodal understanding and reasoning tasks. However, they still struggle with object hallucinations, i.e., the claim of nonexistent objects in the visual input. To address this challenge, we propose Region-aware Chain-of-Verification (R-CoV), a visual chain-of-verification method to alleviate object hallucinations in LVLMs in a post-hoc manner. Motivated by how humans comprehend intricate visual information -- often focusing on specific image regions or details within a given sample -- we elicit such region-level processing from LVLMs themselves and use it as a chaining cue to detect and alleviate their own object hallucinations. Specifically, our R-CoV consists of six steps: initial response generation, entity extraction, coordinate generation, region description, verification execution, and final response generation. As a simple yet effective method, R-CoV can be seamlessly integrated into various LVLMs in a training-free manner and without relying on external detection models. Extensive experiments on several widely used hallucination benchmarks across multiple LVLMs demonstrate that R-CoV can significantly alleviate object hallucinations in LVLMs. Project page: https://github.com/Jiahao000/R-CoV.

---

### StormNet: Improving storm surge predictions with a GNN-based spatio-temporal offset forecasting model

Authors: Noujoud Nader, Stefanos Giaremis, Clint Dawson, Carola Kaiser, Karame Mohammadiporshokooh, Hartmut Kaiser
Published: 2026-04-22
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2604.20688v2

Storm surge forecasting remains a critical challenge in mitigating the impacts of tropical cyclones on coastal regions, particularly given recent trends of rapid intensification and increasing nearshore storm activity. Traditional high fidelity numerical models such as ADCIRC, while robust, are often hindered by inevitable uncertainties arising from various sources. To address these challenges, this study introduces StormNet, a spatio-temporal graph neural network (GNN) designed for bias correction of storm surge forecasts. StormNet integrates graph convolutional (GCN) and graph attention (GAT) mechanisms with long short-term memory (LSTM) components to capture complex spatial and temporal dependencies among water-level gauge stations. The model was trained using historical hurricane data from the U.S. Gulf Coast and evaluated on Hurricane Idalia (2023). Results demonstrate that StormNet can effectively reduce the root mean square error (RMSE) in water-level predictions by more than 70\% for 48-hour forecasts and above 50\% for 72-hour forecasts, as well as outperform a sequential LSTM baseline, particularly for longer prediction horizons. The model also exhibits low training time, enhancing its applicability in real-time operational forecasting systems. Overall, StormNet provides a computationally efficient and physically meaningful framework for improving storm surge prediction accuracy and reliability during extreme weather events.

---

### MGDA-Decoupled: Geometry-Aware Multi-Objective Optimisation for DPO-based LLM Alignment

Authors: Andor Vári-Kakas, Ji Won Park, Natasa Tagasovska
Published: 2026-04-22
Categories: cs.LG
arXiv: https://arxiv.org/abs/2604.20685v1

Aligning large language models (LLMs) to desirable human values requires balancing multiple, potentially conflicting objectives such as helpfulness, truthfulness, and harmlessness, which presents a multi-objective optimisation challenge. Most alignment pipelines rely on a fixed scalarisation of these objectives, which can introduce procedural unfairness by systematically under-weighting harder-to-optimise or minority objectives. To promote more equitable trade-offs, we introduce MGDA-Decoupled, a geometry-based multi-objective optimisation algorithm that finds a shared descent direction while explicitly accounting for each objective's convergence dynamics. In contrast to prior methods that depend on reinforcement learning (e.g., GAPO) or explicit reward models (e.g., MODPO), our approach operates entirely within the lightweight Direct Preference Optimisation (DPO) paradigm. Experiments on the UltraFeedback dataset show that geometry-aware methods -- and MGDA-Decoupled in particular -- achieve the highest win rates against golden responses, both overall and per objective.

---

### Variance Is Not Importance: Structural Analysis of Transformer Compressibility Across Model Scales

Authors: Samuel Salfati
Published: 2026-04-22
Categories: cs.LG
arXiv: https://arxiv.org/abs/2604.20682v1

We present a systematic empirical study of transformer compression through over 40 experiments on GPT-2 (124M parameters) and Mistral 7B (7.24B parameters). Our analysis covers spectral compression, block-level function replacement, rotation-based quantization, activation geometry, and adaptive early exit. We identify five structural properties relevant to compression. (1) Variance is not importance: high-variance activation directions are approximately 96 percent uncorrelated with predictive directions (measured via CCA), and projecting onto these subspaces preserves over 90 percent of variance while degrading perplexity. (2) Block linearity is conditional: transformer blocks are approximately linear (R^2 ~ 0.95 on GPT-2, 0.93 on Mistral block 31) only under the correct upstream distribution; modifying earlier blocks induces distribution shift that degrades downstream approximations. (3) The reconstruction wall: approaches that factor weights into quantized components amplify errors through cross-terms, making direct quantization strictly superior. (4) Linearity increases with depth: Mistral 7B exhibits a progression from R^2 = 0.17 (block 0) to R^2 = 0.93 (block 31), indicating a division between nonlinear feature construction and linear refinement. (5) Approximately 30 percent of tokens are computationally easy, confirmed via exit heads and KL divergence sensitivity. We demonstrate that single-block linear replacement achieves 34x compression with a 1.71 perplexity increase on the final block of Mistral 7B, while multi-block replacement fails due to residual error accumulation and distribution shift. These findings suggest fundamental limits to static post-training compression and motivate adaptive, per-token computation as a more effective direction.

---

### Learning Hippo: Multi-attractor Dynamics and Stability Effects in a Biologically Detailed CA3 Extension of Hopfield Networks

Authors: Daniele Corradetti, Renato Corradetti
Published: 2026-04-22
Categories: cs.NE
arXiv: https://arxiv.org/abs/2604.20679v1

We present a biologically detailed extension of the classical Hopfield/Marr auto-associative memory model for CA3, implementing ten populations (two asymmetric pyramidal subtypes, eight GABAergic interneuron classes), forty-seven compartments, multi-rule plasticity (recurrent Hebb, BCM anti-saturation, mossy-fiber short-term, endocannabinoid iLTD, burst-gated Hebb), and a bimodal cholinergic encoding/consolidation cycle. Evaluated on pattern completion across auto-associative, associative, and temporal regimes, and on a controlled inhibitory-proportion manipulation at $N{=}256$, the full architecture exhibits \emph{three qualitative signatures absent from a minimal Hopfield baseline}: (i)~multi-attractor cross-seed behaviour at $K{=}5$ with biologically realistic inhibitory proportions, where two of five seeds converge to positive attractors with margin ${+}0.10{-}0.22$ (Cohen's $d{=}0.71$, one-sided $p{=}0.08$); (ii)~target-selective associative recall in paired $(A, B)$ memory at $K{\geq}5$, where the full model retrieves $B$ from a partial cue of $A$ while the minimal model echoes $A$ (Pearson margin $Δ{=}{+}0.163$ at $K{=}5$); (iii)~reduced cross-seed variance of the full model below the minimal baseline under clean upstream, with ratios $1.0{-}3.0$. These three signatures are architecture-specific: they appear consistently across independent regimes and are absent from the minimal control.

---

### Intersectional Fairness in Large Language Models

Authors: Chaima Boufaied, Ronnie De Souza Santos, Ann Barcomb
Published: 2026-04-22
Categories: cs.CL
arXiv: https://arxiv.org/abs/2604.20677v3

Large Language Models (LLMs) are increasingly deployed in socially sensitive settings, raising concerns about fairness and bias, particularly when multiple sensitive attributes intersect. We systematically evaluate intersectional fairness in six LLMs using two datasets from the Bias Benchmark for Question Answering (BBQ), combining race with gender and socioeconomic status. We assess bias, subgroup fairness, accuracy, and consistency across contexts and question polarities. While models perform well in ambiguous contexts, sparse non-unknown predictions limit fairness evaluation. In disambiguated contexts, stereotype alignment affects accuracy differently across datasets: models favor stereotype-reinforcing items in Race-SES but counter-stereotype items in Race-Gender for five of six models. Subgroup fairness metrics reveal uneven outcome distributions despite low observed disparities in some cases, while repeated runs show variable response consistency. Overall, no model consistently achieves both fairness and reliability, highlighting the need to evaluate bias, subgroup fairness, and consistency across intersectional contexts.

---

### Intersectional Fairness in Large Language Models

Authors: Chaima Boufaied, Ronnie De Souza Santos, Ann Barcomb
Published: 2026-04-22
Categories: cs.CL
arXiv: https://arxiv.org/abs/2604.20677v2

Large Language Models (LLMs) are increasingly deployed in socially sensitive settings, raising concerns about fairness and biases, particularly across intersectional demographic attributes. In this paper, we systematically evaluate intersectional fairness in six LLMs using ambiguous and disambiguated contexts from two benchmark datasets. We assess LLM behavior using bias scores, subgroup fairness metrics, accuracy, and consistency through multi-run analysis across contexts and negative and non-negative question polarities. Our results show that while modern LLMs generally perform well in ambiguous contexts, this limits the informativeness of fairness metrics due to sparse non-unknown predictions. In disambiguated contexts, LLM accuracy is influenced by stereotype alignment, with models being more accurate when the correct answer reinforces a stereotype than when it contradicts it. This pattern is especially pronounced in race-gender intersections, where directional bias toward stereotypes is stronger. Subgroup fairness metrics further indicate that, despite low observed disparity in some cases, outcome distributions remain uneven across intersectional groups. Across repeated runs, responses also vary in consistency, including stereotype-aligned responses. Overall, our findings show that apparent model competence is partly associated with stereotype-consistent cues, and no evaluated LLM achieves consistently reliable or fair behavior across intersectional settings. These findings highlight the need for evaluation beyond accuracy, emphasizing the importance of combining bias, subgroup fairness, and consistency metrics across intersectional groups, contexts, and repeated runs.

---

### Improving clinical interpretability of linear neuroimaging models through feature whitening

Authors: Sara Petiton, Antoine Grigis, Raphaël Vock, Edouard Duchesnay
Published: 2026-04-22
Categories: cs.LG
arXiv: https://arxiv.org/abs/2604.20675v1

Linear models are widely used in computational neuroimaging to identify biomarkers associated with brain pathologies. However, interpreting the learned weights remains challenging, as they do not always yield clinically meaningful insights. This difficulty arises in part from the inherent correlation between brain regions, which causes linear weights to reflect shared rather than region-specific contributions. In particular, some groups of regions, including homologous structures in the left and right hemispheres, are known to exhibit strong anatomical correlations. In this work, we leverage this prior neuroanatomical knowledge to introduce a whitening approach applied to groups of regions with known shared variance, designed to disentangle overlapping information across correlated brain measures. We additionally propose a regularized variant that allows controlled tuning of the degree of decorrelation. We evaluate this method using region-of-interest features in two psychiatric classification tasks, distinguishing individuals with bipolar disorder or schizophrenia from healthy controls. Importantly, unlike PCA or ICA which use whitening as a dimensionality reduction step, our approach decorrelates anatomically informed pairs of neuroanatomical regions while retaining the full input signal, making it specifically suited for feature interpretation rather than feature selection. Our findings demonstrate that whitening improves the interpretability of model weights while preserving predictive performance, providing a robust framework for linking linear model outputs to neurobiological mechanisms.

---

### A Field Guide to Decision Making

Authors: Richard B. Arthur
Published: 2026-04-22
Categories: cs.CY, cs.AI
arXiv: https://arxiv.org/abs/2604.20669v1

High-consequence decision making demands peak performance from individuals in positions of responsibility. Such executive authority bears the obligation to act despite uncertainty, limited resources, time constraints, and accountability risks. Tools and strategies to motivate confidence and foster risk tolerance must confront informational noise and can provide qualified accountability. Machine intelligence augments human cognition and perception to improve situational awareness, decision framing, flexibility, and coherence through agentic stewardship of contextual metadata. We examine systemic and behavioral factors crucial to address in scenarios encumbered by complexity, uncertainty, and urgency.

---

### ORPHEAS: A Cross-Lingual Greek-English Embedding Model for Retrieval-Augmented Generation

Authors: Ioannis E. Livieris, Athanasios Koursaris, Alexandra Apostolopoulou, Konstantinos Kanaris Dimitris Tsakalidis, George Domalis
Published: 2026-04-22
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2604.20666v1

Effective retrieval-augmented generation across bilingual Greek--English applications requires embedding models capable of capturing both domain-specific semantic relationships and cross-lingual semantic alignment. Existing multilingual embedding models distribute their representational capacity across numerous languages, limiting their optimization for Greek and failing to encode the morphological complexity and domain-specific terminological structures inherent in Greek text. In this work, we propose ORPHEAS, a specialized Greek--English embedding model for bilingual retrieval-augmented generation. ORPHEAS is trained with a high quality dataset generated by a knowledge graph-based fine-tuning methodology which is applied to a diverse multi-domain corpus, which enables language-agnostic semantic representations. The numerical experiments across monolingual and cross-lingual retrieval benchmarks reveal that ORPHEAS outperforms state-of-the-art multilingual embedding models, demonstrating that domain-specialized fine-tuning on morphologically complex languages does not compromise cross-lingual retrieval capability.

---

### The Expense of Seeing: Attaining Trustworthy Multimodal Reasoning Within the Monolithic Paradigm

Authors: Karan Goyal
Published: 2026-04-22
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2604.20665v2

The rapid proliferation of Vision-Language Models (VLMs) is often framed as enabling unified multimodal knowledge discovery but rests on an under-examined assumption: that current VLMs faithfully synthesise multimodal data. We argue they often do not, and this gap reflects a trustworthiness problem in the dominant Vision Encoder-Projector-LLM paradigm. Rather than extracting grounded knowledge from visual inputs, state-of-the-art models frequently exhibit functional blindness, i.e., exploiting strong language priors to bypass severe visual representation bottlenecks. In this work, we challenge the conventional methodology of multimodal evaluation, which relies on data ablation or new dataset creation and therefore conflates dataset biases with architectural incapacity. We propose an information-theoretic departure: the Modality Translation Protocol, designed to quantify what we call the Expense of Seeing. By translating semantic payloads rather than ablating them, we formulate three novel metrics -- the Toll (ToS), Curse (CoS), and Fallacy (FoS) of Seeing -- culminating in the Semantic Sufficiency Criterion (SSC). Furthermore, we hypothesise a Divergence Law of Multimodal Scaling: as the underlying language engines scale to unprecedented reasoning capabilities, the penalty of the visual knowledge bottleneck may increase rather than diminish. We argue the community should move beyond "multimodal gain" as a primary evaluation target. By elevating the SSC from a passive diagnostic constraint to an active architectural blueprint, we provide a foundation for guiding the next generation of AI systems toward genuine multimodal reasoning.

---

### GRPO-VPS: Enhancing Group Relative Policy Optimization with Verifiable Process Supervision for Effective Reasoning

Authors: Jingyi Wang, Lei Zhu, Tengjin Weng, Song-Li Wu, Haochen Tan, Jierun Chen, Chaofan Tao, Haoli Bai, Lu Hou, Lifeng Shang, Xiao-Ping Zhang
Published: 2026-04-22
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2604.20659v1

Reinforcement Learning with Verifiable Rewards (RLVR) has advanced the reasoning capabilities of Large Language Models (LLMs) by leveraging direct outcome verification instead of learned reward models. Building on this paradigm, Group Relative Policy Optimization (GRPO) eliminates the need for critic models but suffers from indiscriminate credit assignment for intermediate steps, which limits its ability to identify effective reasoning strategies and incurs overthinking. In this work, we introduce a model-free and verifiable process supervision via probing the model's belief in the correct answer throughout its reasoning trajectory. By segmenting the generation into discrete steps and tracking the conditional probability of the correct answer appended at each segment boundary, we efficiently compute interpretable segment-wise progress measurements to refine GRPO's trajectory-level feedback. This approach enables more targeted and sample-efficient policy updates, while avoiding the need for intermediate supervision derived from costly Monte Carlo rollouts or auxiliary models. Experiments on mathematical and general-domain benchmarks show consistent gains over GRPO across diverse models: up to 2.6-point accuracy improvements and 13.7% reasoning-length reductions on math tasks, and up to 2.4 points and 4% on general-domain tasks, demonstrating strong generalization.

---

### Cooperative Profiles Predict Multi-Agent LLM Team Performance in AI for Science Workflows

Authors: Shivani Kumar, Adarsh Bharathwaj, David Jurgens
Published: 2026-04-22
Categories: cs.CL, cs.CY, cs.MA
arXiv: https://arxiv.org/abs/2604.20658v1

Multi-agent systems built from teams of large language models (LLMs) are increasingly deployed for collaborative scientific reasoning and problem-solving. These systems require agents to coordinate under shared constraints, such as GPUs or credit balances, where cooperative behavior matters. Behavioral economics provides a rich toolkit of games that isolate distinct cooperation mechanisms, yet it remains unknown whether a model's behavior in these stylized settings predicts its performance in realistic collaborative tasks. Here, we benchmark 35 open-weight LLMs across six behavioral economics games and show that game-derived cooperative profiles robustly predict downstream performance in AI-for-Science tasks, where teams of LLM agents collaboratively analyze data, build models, and produce scientific reports under shared budget constraints. Models that effectively coordinate games and invest in multiplicative team production (rather than greedy strategies) produce better scientific reports across three outcomes, accuracy, quality, and completion. These associations hold after controlling for multiple factors, indicating that cooperative disposition is a distinct, measurable property of LLMs not reducible to general ability. Our behavioral games framework thus offers a fast and inexpensive diagnostic for screening cooperative fitness before costly multi-agent deployment.

---

### Large Language Models Outperform Humans in Fraud Detection and Resistance to Motivated Investor Pressure

Authors: Nattavudh Powdthavee
Published: 2026-04-22
Categories: cs.AI, cs.HC, econ.GN
arXiv: https://arxiv.org/abs/2604.20652v2

Large language models trained on human feedback may suppress fraud warnings when investors arrive already persuaded of a fraudulent opportunity. We tested this in a preregistered experiment across seven leading LLMs and twelve investment scenarios covering legitimate, high-risk, and objectively fraudulent opportunities, combining 3,360 AI advisory conversations with a 1,201-participant human benchmark. Contrary to predictions, motivated investor framing did not suppress AI fraud warnings; if anything, it marginally increased them. Endorsement reversal occurred in fewer than 3 in 1,000 observations. Human advisors endorsed fraudulent investments at baseline rates of 13-14%, versus 0% across all LLMs, and suppressed warnings under pressure at two to four times the AI rate. AI systems currently provide more consistent fraud warnings than lay humans in an identical advisory role.

---

### CHORUS: An Agentic Framework for Generating Realistic Deliberation Data

Authors: A. Koursaris, G. Domalis, A. Apostolopoulou, K. Kanaris, D. Tsakalidis, I. E. Livieris
Published: 2026-04-22
Categories: cs.AI
arXiv: https://arxiv.org/abs/2604.20651v1

Understanding the intricate dynamics of online discourse depends on large-scale deliberation data, a resource that remains scarce across interactive web platforms due to restrictive accessibility policies, ethical concerns and inconsistent data quality. In this paper, we propose Chorus, an agentic framework, which orchestrates LLM-powered actors with behaviorally consistent personas to generate realistic deliberation discussions. Each actor is governed by an autonomous agent equipped with memory of the evolving discussion, while participation timing is governed by a principled Poisson process-based temporal model, which approximates the heterogeneous engagement patterns of real users. The framework is further supported by structured tool usage, enabling actors to access external resources and facilitating integration with interactive web platforms. The framework was deployed on the \textsc{Deliberate} platform and evaluated by 30 expert participants across three dimensions: content realism, discussion coherence and analytical utility, confirming Chorus as a practical tool for generating high-quality deliberation data suitable for online discourse analysis

---

### MAPRPose: Mask-Aware Proposal and Amodal Refinement for Multi-Object 6D Pose Estimation

Authors: Yang Luo, Yan Gong, Yongsheng Gao, Xiaoying Sun, Jie Zhao
Published: 2026-04-22
Categories: cs.CV
arXiv: https://arxiv.org/abs/2604.20650v3

6D object pose estimation in cluttered scenes remains challenging due to severe occlusion and sensor noise. We propose MAPRPose, a two-stage framework that leverages mask-aware correspondences for pose proposal and amodal-driven Region-of-Interest (ROI) prediction for robust refinement. In the Mask-Aware Pose Proposal (MAPP) stage, we lift 2D correspondences into 3D space to establish reliable keypoint matches and generate geometrically consistent pose hypotheses based on correspondence-level scoring, from which the top-$K$ candidates are selected. In the refinement stage, we introduce a tensorized render-and-compare pipeline integrated with an Amodal Mask Prediction and ROI Re-Alignment (AMPR) module. By reconstructing complete object geometry and dynamically adjusting the ROI, AMPR mitigates localization errors and spatial misalignment under heavy occlusion. Furthermore, our GPU-accelerated RGB-XYZ reprojection enables simultaneous refinement of all $N \times B$ pose hypotheses in a single forward pass.

---

### A weighted angle distance on strings

Authors: Grant Molnar
Published: 2026-04-22
Categories: math.MG, cs.DS, cs.LG, math.CO
arXiv: https://arxiv.org/abs/2604.20633v1

We define a multi-scale metric $d_ρ$ on strings by aggregating angle distances between all $n$-gram count vectors with exponential weights $ρ^n$. We benchmark $d_ρ$ in DBSCAN clustering against edit and $n$-gram baselines, give a linear-time suffix-tree algorithm for evaluation, prove metric and stability properties (including robustness under tandem-repeat stutters), and characterize isometries.

---

### Occupancy Reward Shaping: Improving Credit Assignment for Offline Goal-Conditioned Reinforcement Learning

Authors: Aravind Venugopal, Jiayu Chen, Xudong Wu, Chongyi Zheng, Benjamin Eysenbach, Jeff Schneider
Published: 2026-04-22
Categories: cs.LG, cs.RO
arXiv: https://arxiv.org/abs/2604.20627v1

The temporal lag between actions and their long-term consequences makes credit assignment a challenge when learning goal-directed behaviors from data. Generative world models capture the distribution of future states an agent may visit, indicating that they have captured temporal information. How can that temporal information be extracted to perform credit assignment? In this paper, we formalize how the temporal information stored in world models encodes the underlying geometry of the world. Leveraging optimal transport, we extract this geometry from a learned model of the occupancy measure into a reward function that captures goal-reaching information. Our resulting method, Occupancy Reward Shaping, largely mitigates the problem of credit assignment in sparse reward settings. ORS provably does not alter the optimal policy, yet empirically improves performance by 2.2x across 13 diverse long-horizon locomotion and manipulation tasks. Moreover, we demonstrate the effectiveness of ORS in the real world for controlling nuclear fusion on 3 Tokamak control tasks. Code: https://github.com/aravindvenu7/occupancy_reward_shaping; Website: https://aravindvenu7.github.io/website/ors/

---

### Centering Ecological Goals in Automated Identification of Individual Animals

Authors: Lukas Picek, Timm Haucke, Lukáš Adam, Ekaterina Nepovinnykh, Lasha Otarashvili, Kostas Papafitsoros, Tanya Berger-Wolf, Michael B. Brown, Tilo Burghardt, Vojtech Cermak, Daniela Hedwig, Justin Kitzes et al.
Published: 2026-04-22
Categories: q-bio.PE, cs.AI
arXiv: https://arxiv.org/abs/2604.20626v1

Recognizing individual animals over time is central to many ecological and conservation questions, including estimating abundance, survival, movement, and social structure. Recent advances in automated identification from images and even acoustic data suggest that this process could be greatly accelerated, yet their promise has not translated well into ecological practice. We argue that the main barrier is not the performance of the automated methods themselves, but a mismatch between how those methods are typically developed and evaluated, and how ecological data is actually collected, processed, reviewed, and used. Future progress, therefore, will depend less on algorithmic gains alone than on recognizing that the usefulness of automated identification is grounded in ecological context: it depends on what question is being asked, what data are available, and what kinds of mistakes matter. Only by centering these questions can we move toward automated identification of individuals that is not only accurate but also ecologically useful, transparent, and trustworthy.

---

### RSRCC: A Remote Sensing Regional Change Comprehension Benchmark Constructed via Retrieval-Augmented Best-of-N Ranking

Authors: Roie Kazoom, Yotam Gigi, George Leifman, Tomer Shekel, Genady Beryozkin
Published: 2026-04-22
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2604.20623v2

Traditional change detection identifies where changes occur, but does not explain what changed in natural language. Existing remote sensing change captioning datasets typically describe overall image-level differences, leaving fine-grained localized semantic reasoning largely unexplored. To close this gap, we present RSRCC, a new benchmark for remote sensing change question-answering containing 126k questions, split into 87k training, 17.1k validation, and 22k test instances. Unlike prior datasets, RSRCC is built around localized, change-specific questions that require reasoning about a particular semantic change. To the best of our knowledge, this is the first remote sensing change question-answering benchmark designed explicitly for such fine-grained reasoning-based supervision. To construct RSRCC, we introduce a hierarchical semi-supervised curation pipeline that uses Best-of-N ranking as a critical final ambiguity-resolution stage. First, candidate change regions are extracted from semantic segmentation masks, then initially screened using an image-text embedding model, and finally validated through retrieval-augmented vision-language curation with Best-of-N ranking. This process enables scalable filtering of noisy and ambiguous candidates while preserving semantically meaningful changes. The dataset is available at https://huggingface.co/datasets/google/RSRCC.

---

### pAI/MSc: ML Theory Research with Humans on the Loop

Authors: Mahmoud Abdelmoneum, Pierfrancesco Beneventano, Tomaso Poggio
Published: 2026-04-22
Categories: cs.AI, cs.LG, cs.MA
arXiv: https://arxiv.org/abs/2604.20622v1

We present pAI/MSc, an open-source, customizable, modular multi-agent system for academic research workflows. Our goal is not autonomous scientific ideation, nor fully automated research. It is narrower and more practical: to reduce by orders of magnitude the human steering required to turn a specified hypothesis into a literature-grounded, mathematically established, experimentally supported, submission-oriented manuscript draft. pAI/MSc is built with a current emphasis on machine learning theory and adjacent quantitative fields.

---

### Too Sharp, Too Sure: When Calibration Follows Curvature

Authors: Alessandro Morosini, Matea Gjika, Tomaso Poggio, Pierfrancesco Beneventano
Published: 2026-04-22
Categories: cs.LG, math.DS, math.OC, stat.ML
arXiv: https://arxiv.org/abs/2604.20614v1

Modern neural networks can achieve high accuracy while remaining poorly calibrated, producing confidence estimates that do not match empirical correctness. Yet calibration is often treated as a post-hoc attribute. We take a different perspective: we study calibration as a training-time phenomenon on small vision tasks, and ask whether calibrated solutions can be obtained reliably by intervening on the training procedure. We identify a tight coupling between calibration, curvature, and margins during training of deep networks under multiple gradient-based methods. Empirically, Expected Calibration Error (ECE) closely tracks curvature-based sharpness throughout optimization. Mathematically, we show that both ECE and Gauss--Newton curvature are controlled, up to problem-specific constants, by the same margin-dependent exponential tail functional along the trajectory. Guided by this mechanism, we introduce a margin-aware training objective that explicitly targets robust-margin tails and local smoothness, yielding improved out-of-sample calibration across optimizers without sacrificing accuracy.

---

### Beyond ZOH: Advanced Discretization Strategies for Vision Mamba

Authors: Fady Ibrahim, Guangjun Liu, Guanghui Wang
Published: 2026-04-22
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2604.20606v1

Vision Mamba, as a state space model (SSM), employs a zero-order hold (ZOH) discretization, which assumes that input signals remain constant between sampling instants. This assumption degrades temporal fidelity in dynamic visual environments and constrains the attainable accuracy of modern SSM-based vision models. In this paper, we present a systematic and controlled comparison of six discretization schemes instantiated within the Vision Mamba framework: ZOH, first-order hold (FOH), bilinear/Tustin transform (BIL), polynomial interpolation (POL), higher-order hold (HOH), and the fourth-order Runge-Kutta method (RK4). We evaluate each method on standard visual benchmarks to quantify its influence in image classification, semantic segmentation, and object detection. Our results demonstrate that POL and HOH yield the largest gains in accuracy at the cost of higher training-time computation. In contrast, the BIL provides consistent improvements over ZOH with modest additional overhead, offering the most favorable trade-off between precision and efficiency. These findings elucidate the pivotal role of discretization in SSM-based vision architectures and furnish empirically grounded justification for adopting BIL as the default discretization baseline for state-of-the-art SSM models.

---

### Self-Guided Plan Extraction for Instruction-Following Tasks with Goal-Conditional Reinforcement Learning

Authors: Zoya Volovikova, Nikita Sorokin, Dmitriy Lukashevskiy, Aleksandr Panov, Alexey Skrynnik
Published: 2026-04-22
Categories: cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2604.20601v1

We introduce SuperIgor, a framework for instruction-following tasks. Unlike prior methods that rely on predefined subtasks, SuperIgor enables a language model to generate and refine high-level plans through a self-learning mechanism, reducing the need for manual dataset annotation. Our approach involves iterative co-training: an RL agent is trained to follow the generated plans, while the language model adapts and modifies these plans based on RL feedback and preferences. This creates a feedback loop where both the agent and the planner improve jointly. We validate our framework in environments with rich dynamics and stochasticity. Results show that SuperIgor agents adhere to instructions more strictly than baseline methods, while also demonstrating strong generalization to previously unseen instructions.

---

### Self-Aware Vector Embeddings for Retrieval-Augmented Generation: A Neuroscience-Inspired Framework for Temporal, Confidence-Weighted, and Relational Knowledge

Authors: Naizhong Xu
Published: 2026-04-22
Categories: cs.IR, cs.CL, cs.DB, cs.LG
arXiv: https://arxiv.org/abs/2604.20598v1

Modern retrieval-augmented generation (RAG) systems treat vector embeddings as static, context-free artifacts: an embedding has no notion of when it was created, how trustworthy its source is, or which other embeddings depend on it. This flattening of knowledge has a measurable cost: recent work on VersionRAG reports that conventional RAG achieves only 58% accuracy on versioned technical queries, because retrieval returns semantically similar but temporally invalid content. We propose SmartVector, a framework that augments dense embeddings with three explicit properties -- temporal awareness, confidence decay, and relational awareness -- and a five-stage lifecycle modeled on hippocampal-neocortical memory consolidation. A retrieval pipeline replaces pure cosine similarity with a four-signal score that mixes semantic relevance, temporal validity, live confidence, and graph-relational importance. A background consolidation agent detects contradictions, builds dependency edges, and propagates updates along those edges as graph-neural-network-style messages. Confidence is governed by a closed-form function combining an Ebbinghaus-style exponential decay, user-feedback reconsolidation, and logarithmic access reinforcement. We formalize the model, relate it to temporal knowledge graph embedding, agentic memory architectures, and uncertainty-aware RAG, and present a reference implementation. On a reproducible synthetic versioned-policy benchmark of 258 vectors and 138 queries, SmartVector roughly doubles top-1 accuracy over plain cosine RAG (62.0% vs. 31.0% on a held-out split), drops stale-answer rate from 35.0% to 13.3%, cuts Expected Calibration Error by nearly 2x (0.244 vs. 0.470), reduces re-embedding cost per single-word edit by 77%, and is robust across contradiction-injection rates from 0% to 75%.

---

### Differentially Private Clustered Federated Learning with Privacy-Preserving Initialization and Normality-Driven Aggregation

Authors: Jie Xu, Haaris Mehmood, Rogier Van Dalen, Karthikeyan Saravanan, Mete Ozay
Published: 2026-04-22
Categories: cs.LG, cs.CR
arXiv: https://arxiv.org/abs/2604.20596v1

Federated learning (FL) enables training of a global model while keeping raw data on end-devices. Despite this, FL has shown to leak private user information and thus in practice, it is often coupled with methods such as differential privacy (DP) and secure vector sum to provide formal privacy guarantees to its participants. In realistic cross-device deployments, the data are highly heterogeneous, so vanilla federated learning converges slowly and generalizes poorly. Clustered federated learning (CFL) mitigates this by segregating users into clusters, leading to lower intra-cluster data heterogeneity. Nevertheless, coupling CFL with DP remains challenging: the injected DP noise makes individual client updates excessively noisy, and the server is unable to initialize cluster centroids with the less noisy aggregated updates. To address this challenge, we propose PINA, a two-stage framework that first lets each client fine-tune a lightweight low-rank adaptation (LoRA) adapter and privately share a compressed sketch of the update. The server leverages these sketches to construct robust cluster centroids. In the second stage, PINA introduces a normality-driven aggregation mechanism that improves convergence and robustness. Our method retains the benefits of clustered FL while providing formal privacy guarantees against an untrusted server. Extensive evaluations show that our proposed method outperforms state-of-the-art DP-FL algorithms by an average of 2.9% in accuracy for privacy budgets (epsilon in {2, 8}).

---

### An explicit operator explains end-to-end computation in the modern neural networks used for sequence and language modeling

Authors: Anif N. Shikder, Ramit Dey, Sayantan Auddy, Luisa Liboni, Alexandra N. Busch, Arthur Powanwe, Ján Mináč, Roberto C. Budzinski, Lyle E. Muller
Published: 2026-04-22
Categories: cs.NE, cs.LG, nlin.AO
arXiv: https://arxiv.org/abs/2604.20595v1

We establish a mathematical correspondence between state space models, a state-of-the-art architecture for capturing long-range dependencies in data, and an exactly solvable nonlinear oscillator network. As a specific example of this general correspondence, we analyze the diagonal linear time-invariant implementation of the Structured State Space Sequence model (S4). The correspondence embeds S4D, a specific implementation of S4, into a ring network topology, in which recent inputs are encoded, as waves of activity traveling over the one-dimensional spatial layout of the network. We then derive an exact operator expression for the full forward pass of S4D, yielding an analytical characterization of its complete input-output map. This expression reveals that the nonlinear decoder in the system induces interactions between these information-carrying waves that enable classifying real-world sequences. These results generalize across modern SSM architectures, and show that they admit an exact mathematical description with a clear physical interpretation. These insights enable a new level of interpretability for these systems in terms of nonlinear oscillator networks.

---

### Physics-Informed Conditional Diffusion for Motion-Robust Retinal Temporal Laser Speckle Contrast Imaging

Authors: Qian Chen, Yuehao Chen, Qiang Wang, Lei Zhu, Yanye Lu, Qiushi Ren
Published: 2026-04-22
Categories: cs.CV
arXiv: https://arxiv.org/abs/2604.20594v1

Retinal laser speckle contrast imaging (LSCI) is a noninvasive optical modality for monitoring retinal blood flow dynamics. However, conventional temporal LSCI (tLSCI) reconstruction relies on sufficiently long speckle sequences to obtain stable temporal statistics, which makes it vulnerable to acquisition disturbances and limits effective temporal resolution. A physically informed reconstruction framework, termed RetinaDiff (Retinal Diffusion Model), is proposed for retinal tLSCI that is robust to motion and requires only a few frames. In RetinaDiff, registration based on phase correlation is first applied to stabilize the raw speckle sequence before contrast computation, reducing interframe misalignment so that fluctuations at each pixel primarily reflect true flow dynamics. This step provides a physics prior corrected for motion and a high quality multiframe tLSCI reference. Next, guided by the physics prior, a conditional diffusion model performs inverse reconstruction by jointly conditioning on the registered speckle sequence and the corrected prior. Experiments on data acquired with a retinal LSCI system developed in house show improved structural continuity and statistical stability compared with direct reconstruction from few frames and representative baselines. The framework also remains effective in a small number of extremely challenging cases, where both the direct 5-frame input and the conventional multiframe reconstruction are severely degraded. Overall, this work provides a practical and physically grounded route for reliable retinal tLSCI reconstruction from extremely limited frames. The source code and model weights will be publicly available at https://github.com/QianChen113/RetinaDiff.

---

### Structure-Augmented Standard Plane Detection with Temporal Aggregation in Blind-Sweep Fetal Ultrasound

Authors: Keli Niu, He Zhao, Qianhui Men
Published: 2026-04-22
Categories: cs.CV
arXiv: https://arxiv.org/abs/2604.20591v1

In low-resource settings, blind-sweep ultrasound provides a practical and accessible method for identifying fetal growth restriction. However, unlike freehand ultrasound which is subjectively controlled, detection of biometry plane in blind-sweep ultrasound is more challenging due to the uncontrolled fetal structure to be observed and the variaties of oblique planes in the scan. In this work, we propose a structure-augmented system to detect fetal abdomen plane, where the abdominal structure is highlighted using a segmentation prior. Since standard planes are emerging gradually, the decision boundary of the keyframes is unstable to predict. We thus aggregated the structure-augmented planes with a temporal sliding window to help stabilise keyframe localisation. Extensive results indicate that the structure-augmented temporal sliding strategy significantly improves and stabilises the detection of anatomically meaningful planes, which enables more reliable biometric measurements in blind-sweep ultrasound.

---

### A Hierarchical MARL-Based Approach for Coordinated Retail P2P Trading and Wholesale Market Participation of DERs

Authors: Patrick Wilk, Ethan Cantor, Yikui Liu, Jie Li
Published: 2026-04-22
Categories: cs.LG, eess.SY
arXiv: https://arxiv.org/abs/2604.20586v1

The ongoing shift towards decentralization of the electric energy sector, driven by the growing electrification across end-use sectors, and widespread adoption of distributed energy resources (DERs), necessitates their active participation in the electricity markets to support grid operations. Furthermore, with bi-directional energy and communication flows becoming standard, intelligent, easy-to-deploy, resource-conservative demand-side participation is expected to play a critical role in securing power grid operational flexibility and market efficiency. This work proposes a market engagement framework that leverages a hierarchical multi-agent deep reinforcement learning (MARL) approach to enable individual prosumers to participate in peer-to-peer retail auctions and further aggregate these intelligent prosumers to facilitate effective DER participation in wholesale markets. Ultimately, a Stackelberg game is proposed to coordinate this hierarchical MARL-based DER market participation framework toward enhanced market performance.

---

### On the Impact of Face Segmentation-Based Background Removal on Recognition and Morphing Attack Detection

Authors: Eduarda Caldeira, Guray Ozgur, Fadi Boutros, Naser Damer
Published: 2026-04-22
Categories: cs.CV
arXiv: https://arxiv.org/abs/2604.20585v1

This study investigates the impact of face image background correction through segmentation on face recognition and morphing attack detection performance in realistic, unconstrained image capture scenarios. The motivation is driven by operational biometric systems such as the European Entry/Exit System (EES), which require facial enrolment at airports and other border crossing points where controlled backgrounds usually required for such captures cannot always be guaranteed, as well as by accessibility needs that may necessitate image capture outside traditional office environments. By analyzing how such preprocessing steps influence both recognition accuracy and security mechanisms, this work addresses a critical gap between usability-driven image normalization and the reliability requirements of large-scale biometric identification systems. Our study evaluates a comprehensive range of segmentation techniques, three families of morphing attack detection methods, and four distinct face recognition models, using databases that include both controlled and in-the-wild image captures. The results reveal consistent patterns linking segmentation to both recognition performance and face image quality. Additionally, segmentation is shown to systematically influence morphing attack detection performance. These findings highlight the need for careful consideration when deploying such preprocessing techniques in operational biometric systems.

---

### Trust, Lies, and Long Memories: Emergent Social Dynamics and Reputation in Multi-Round Avalon with LLM Agents

Authors: Suveen Ellawela
Published: 2026-04-22
Categories: cs.MA, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2604.20582v1

We study emergent social dynamics in LLM agents playing The Resistance: Avalon, a hidden-role deception game. Unlike prior work on single-game performance, our agents play repeated games while retaining memory of previous interactions, including who played which roles and how they behaved, enabling us to study how social dynamics evolve. Across 188 games, two key phenomena emerge. First, reputation dynamics emerge organically when agents retain cross-game memory: agents reference past behavior in statements like "I am wary of repeating last game's mistake of over-trusting early success." These reputations are role-conditional: the same agent is described as "straightforward" when playing good but "subtle" when playing evil, and high-reputation players receive 46% more team inclusions. Second, higher reasoning effort supports more strategic deception: evil players more often pass early missions to build trust before sabotaging later ones, 75% in high-effort games vs 36% in low-effort games. Together, these findings show that repeated interaction with memory gives rise to measurable reputation and deception dynamics among LLM agents.

---

### Evaluating Assurance Cases as Text-Attributed Graphs for Structure and Provenance Analysis

Authors: Fariz Ikhwantri, Dusica Marijan
Published: 2026-04-22
Categories: cs.SE, cs.LG
arXiv: https://arxiv.org/abs/2604.20577v2

An assurance case is a structured argument document that justifies claims about a system's requirements or properties, which are supported by evidence. In regulated domains, these are crucial for meeting compliance and safety requirements to industry standards. We propose a graph diagnostic framework for analysing the structure and provenance of assurance cases. We focus on two main tasks: (1) link prediction, to learn and identify connections between argument elements, and (2) graph classification, to differentiate between assurance cases created by a state-of-the-art large language model and those created by humans, aiming to detect bias. We compiled a publicly available dataset of assurance cases, represented as graphs with nodes and edges, supporting both link prediction and provenance analysis. Experiments show that graph neural networks (GNNs) achieve strong link prediction performance (ROC-AUC 0.760) on real assurance cases and generalise well across domains and semi-supervised settings. For provenance detection, GNNs effectively distinguish human-authored from LLM-generated cases (F1 0.94). We observed that LLM-generated assurance cases have different hierarchical linking patterns compared to human-authored cases. Furthermore, existing GNN explanation methods show only moderate faithfulness, revealing a gap between predicted reasoning and the true argument structure.

---

### Where are they looking in the operating room?

Authors: Keqi Chen, Séraphin Baributsa, Lilien Schewski, Vinkle Srivastav, Didier Mutter, Guido Beldi, Sandra Keller, Nicolas Padoy
Published: 2026-04-22
Categories: cs.CV
arXiv: https://arxiv.org/abs/2604.20574v1

Purpose: Gaze-following, the task of inferring where individuals are looking, has been widely studied in computer vision, advancing research in visual attention modeling, social scene understanding, and human-robot interaction. However, gaze-following has never been explored in the operating room (OR), a complex, high-stakes environment where visual attention plays an important role in surgical workflow analysis. In this work, we introduce the concept of gaze-following to the surgical domain, and demonstrate its great potential for understanding clinical roles, surgical phases, and team communications in the OR. Methods: We extend the 4D-OR dataset with gaze-following annotations, and extend the Team-OR dataset with gaze-following and a new team communication activity annotations. Then, we propose novel approaches to address clinical role prediction, surgical phase recognition, and team communication detection using a gaze-following model. For role and phase recognition, we propose a gaze heatmap-based approach that uses gaze predictions solely; for team communication detection, we train a spatial-temporal model in a self-supervised way that encodes gaze-based clip features, and then feed the features into a temporal activity detection model. Results: Experimental results on the 4D-OR and Team-OR datasets demonstrate that our approach achieves state-of-the-art performance on all downstream tasks. Quantitatively, our approach obtains F1 scores of 0.92 for clinical role prediction and 0.95 for surgical phase recognition. Furthermore, it significantly outperforms existing baselines in team communication detection, improving previous best performances by over 30%. Conclusion: We introduce gaze-following in the OR as a novel research direction in surgical data science, highlighting its great potential to advance surgical workflow analysis in computer-assisted interventions.

---

### Ask Only When Needed: Proactive Retrieval from Memory and Skills for Experience-Driven Lifelong Agents

Authors: Yuxuan Cai, Wei Li, Jie Zhou, Qin Chen, Xin Li, Bo Zhang, Liang He
Published: 2026-04-22
Categories: cs.CL
arXiv: https://arxiv.org/abs/2604.20572v2

Online lifelong learning agents must decide not only how to act but also when to consult prior experience to continually improve on long-horizon tasks. Existing methods typically retrieve memories passively, such as at task initialization or after each step, and therefore miss knowledge gaps that arise during interaction. We propose ProactAgent, an experience-driven lifelong learning framework for proactive retrieval over a structured Experience Base. ProactAgent continually improves through ExpOnEvo, which jointly updates policies and refines memory, organizing past interactions into factual, episodic, and skill repositories. It further introduces ProactRL, which treats retrieval as an explicit policy action and learns when and what to retrieve. By comparing paired continuations from identical interaction prefixes with and without retrieval, ProactRL provides step-level process rewards that encourage retrieval only when it improves task outcomes or efficiency. Experiments on SciWorld, AlfWorld, and StuLife show that ProactAgent consistently outperforms all baselines, achieving up to 32% relative improvement in success rate and over 33% reduction in interaction rounds. Our code will be publicly available at GitHub.

---

### Exploring Spatial Intelligence from a Generative Perspective

Authors: Muzhi Zhu, Shunyao Jiang, Huanyi Zheng, Zekai Luo, Hao Zhong, Anzhou Li, Kaijun Wang, Jintao Rong, Yang Liu, Hao Chen, Tao Lin, Chunhua Shen
Published: 2026-04-22
Categories: cs.CV
arXiv: https://arxiv.org/abs/2604.20570v1

Spatial intelligence is essential for multimodal large language models, yet current benchmarks largely assess it only from an understanding perspective. We ask whether modern generative or unified multimodal models also possess generative spatial intelligence (GSI), the ability to respect and manipulate 3D spatial constraints during image generation, and whether such capability can be measured or improved. We introduce GSI-Bench, the first benchmark designed to quantify GSI through spatially grounded image editing. It consists of two complementary components: GSI-Real, a high-quality real-world dataset built via a 3D-prior-guided generation and filtering pipeline, and GSI-Syn, a large-scale synthetic benchmark with controllable spatial operations and fully automated labeling. Together with a unified evaluation protocol, GSI-Bench enables scalable, model-agnostic assessment of spatial compliance and editing fidelity. Experiments show that fine-tuning unified multimodal models on GSI-Syn yields substantial gains on both synthetic and real tasks and, strikingly, also improves downstream spatial understanding. This provides the first clear evidence that generative training can tangibly strengthen spatial reasoning, establishing a new pathway for advancing spatial intelligence in multimodal models.

---

### The Effect of Idea Elaboration on the Automatic Assessment of Idea Originality

Authors: Umberto Domanti, Moritz Mock, Sergio Agnoli, Antonella De Angeli
Published: 2026-04-22
Categories: cs.HC, cs.AI
arXiv: https://arxiv.org/abs/2604.20569v1

Automatic systems are increasingly used to assess the originality of responses in creative tasks. They offer a potential solution to key limitations of human assessment (cost, fatigue, and subjectivity), but there is preliminary evidence of a self-preference bias. Accordingly, automatic systems tend to prefer outcomes that are more closely related to their style, rather than to the human one. In this paper, we investigated how Large Language Models (LLMs) align with human raters in assessing the originality of responses in a divergent thinking task. We analysed 4,813 responses to the Alternate Uses Task produced by higher and lower creative humans and ChatGPT-4o. Human raters were two university students who underwent intensive training. Machine raters were two specialised systems fine-tuned on AUT responses and corresponding human ratings (OCSAI and CLAUS) and ChatGPT-4o, which was prompted with the same instructions as human raters. Results confirmed the presence of a self-preference bias in LLMs. Automatic systems tended to privilege artificial responses. However, this self-preference bias disappeared when the analyses controlled for the idea elaboration. We discuss theoretical and methodological implications of these findings by highlighting future directions for research on creativity assessment.

---

### Amortized Vine Copulas for High-Dimensional Density and Information Estimation

Authors: Houman Safaai
Published: 2026-04-22
Categories: cs.LG, cs.IT, stat.ME
arXiv: https://arxiv.org/abs/2604.20568v2

Modeling high-dimensional dependencies while keeping likelihoods tractable remains challenging. Classical vine-copula pipelines are interpretable but can be expensive, while many neural estimators are flexible but less structured. In this work, we propose Vine Denoising Copula (VDC), an amortized vine-copula pipeline for continuous-data, simplified-vine dependence modeling. VDC trains a single bivariate denoising model and reuses it across all vine edges. For each edge, given pseudo-observations, the model predicts a piecewise-constant density grid. We then apply an IPFP/Sinkhorn projection that normalizes mass and drives the marginals to uniformity. This preserves the tractable vine-likelihood structure and the usual copula interpretation while replacing repeated per-edge optimization with GPU inference. Across synthetic and real-data benchmarks, VDC delivers strong bivariate density accuracy, competitive MI/TC estimation, and faster high-dimensional vine fitting. These gains make explicit information estimation and dependence decomposition feasible when repeated vine fitting would otherwise be costly, while conditional downstream tasks remain a limitation.

---

### Where Reasoning Breaks: Logic-Aware Path Selection by Controlling Logical Connectives in LLMs Reasoning Chains

Authors: Seunghyun Park, Yuanyuan Lei
Published: 2026-04-22
Categories: cs.CL
arXiv: https://arxiv.org/abs/2604.20564v1

While LLMs demonstrate impressive reasoning capabilities, they remain fragile in multi-step logical deduction, where a single transition error can propagate through the entire reasoning chain, leading to unstable performance. In this work, we identify logical connectives as primary points of this structural fragility. Through empirical analysis, we show that connective tokens function as high entropy forking points, at which models frequently struggle to determine the correct logical direction. Motivated by this observation, we hypothesize that intervening in logical connective selection can guide LLMs toward more correct logical direction, thereby improving the overall reasoning chain. To validate this hypothesis, we propose a multi-layered framework that intervenes specifically at these logic-critical junctions in the reasoning process. Our framework includes (1) Gradient-based Logical Steering to guide LLMs internal representations towards valid reasoning subspaces, (2) Localized Branching to resolve ambiguity via targeted look-ahead search, and (3) Targeted Transition Preference Optimization, a surgical reinforcement learning objective that selectively optimizes single-token preferences at logical pivots. Crucially, by concentrating intervention solely on logic-critical transitions, our framework achieves a favorable accuracy--efficiency trade-off compared to global inference time scaling methods like beam search and self-consistency.

---