# Research Papers — 2026-06 · bundle page 133 of 260 > Full-text markdown of papers #6601–6650 of 12993 published in 2026-06, newest first. AI-readable mirrors of the full 12993-paper 2026-06 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2026-06/page/133 [← Previous bundle](https://aipod.dev/papers/archive/2026-06/page/132.md) [Next bundle →](https://aipod.dev/papers/archive/2026-06/page/134.md) ### PreLort: Prefix-Nested LoRA for Federated Fine-Tuning under Rank Heterogeneity Authors: Muhammad Waseem, Nurbek Tastan, Andrej Jovanovic, Nicholas D. Lane, Nils Lukas, Karthik Nandakumar, Samuel Horvath Published: 2026-06-14 Categories: cs.DC, cs.AI, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2606.15963v1 Federated fine-tuning of large language models using parameter-efficient methods such as LoRA enables privacy-preserving adaptation of foundation models. Heterogeneous hardware resources introduce challenges, as clients with different adapter ranks cannot be directly aggregated. While existing methods enable aggregation under heterogeneous ranks, they fail to control how information is distributed across rank dimensions, leading to suboptimal use of shared low-rank representations. Instead, we propose PreLort: a nested low-rank formulation for federated LoRA that organizes adapter dimensions into a prefix hierarchy. Our approach ensures that lower-rank dimensions encode task-relevant information, while higher-rank dimensions capture additional capacity. Building on this, we introduce (i) a segment-wise aggregation rule that averages only over clients contributing to each rank segment, avoiding dilution from zero-padded lower-rank clients, and (ii) a prefix-nested training strategy that optimizes each adapter under multiple rank truncations, encouraging useful signal to concentrate in low-rank prefix dimensions. Together, these components encourage a consistent low-rank prefix capturing the most task-relevant information, while higher-rank dimensions learn additional capacity. This allows low-rank clients to benefit from richer information contributed by higher-rank clients, as prefix dimensions are consistently learned and aggregated. Experiments demonstrate that our method consistently outperforms prior heterogeneous federated LoRA methods in accuracy and ROUGE-L, while achieving lower or comparable perplexity across multiple base models. --- ### p-PSO: A Penalized Particle Swarm Optimization Technique for Finding D-Optimal Designs with Mixed Factors in Generalized Linear Models Authors: Shrabanti Chowdhury, Abhyuday Mandal Published: 2026-06-14 Categories: stat.ME, cs.LG arXiv: https://arxiv.org/abs/2606.15962v1 Finding D-optimal designs for generalized linear models (GLMs) is challenging due to the dependence of the Fisher information matrix on unknown parameters and the lack of closed-form solutions, particularly when input factors include both discrete and continuous variables. Although classical algorithms and recent metaheuristic approaches have offered partial solutions, there remains a need for robust and computationally efficient methods. In this paper, we propose a penalized Particle Swarm Optimization (PSO) approach, named $p$-PSO. Here we introduce a new, general-purpose penalty formulation for constrained optimization and demonstrate its effectiveness in optimal design problems. The formulation is algorithm-agnostic and applicable to a broad class of black-box optimization methods. Results show that the method is highly efficient, with its primary contribution being a penalty formulation that enables the direct use of an off-the-shelf PSO algorithm and extends naturally to more general constrained optimization tasks. --- ### Quantifying the Impact of Lossy Compression on Neural Generative Surrogate Modeling Authors: Zhimin Li, Harshitha Menon, Charles Jekel, Valerio Pascucci, Peter Lindstrom Published: 2026-06-14 Categories: cs.DC, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2606.15959v1 Neural networks are used as generative surrogate models for scientific discovery, which are trainable approximations of scientific simulations. These models enable users to replace time-consuming numerical simulations with learned alternatives, providing quick solutions. However, high-fidelity generative surrogate models require massive training datasets, which can create storage and I/O challenges. Lossy compression is a promising way to reduce this burden, but compression errors may affect the model quality in subtle ways, making it challenging to quantify their impact. In this work, we examine how lossy compression of training data impacts the quality of generative surrogate models. We begin by characterizing the uncertainty inherent in training neural networks, showing that identical training configurations can produce different models. By exploiting this variability, we propose a method to estimate how much compression-induced error a surrogate model can tolerate without affecting its accuracy. Evaluation of two application simulations demonstrates that our approach significantly reduces memory/storage requirements and speeds up training while producing high-quality surrogate models. These results show that lossy compression saves data storage up to 23.7x and 39x with negligible impact on the quality of the surrogate model. Meanwhile, reducing the size of the training data set also enhances the data loading speed and reduces the training time by up to 3x. --- ### You Don't Need Strong Assumptions: Visual Representation Learning via Temporal Differences Authors: Ninad Daithankar, Alexi Gladstone, Yann LeCun, Heng Ji Published: 2026-06-14 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2606.15956v1 Progress in AI has largely been driven by methods that assume less. As compute and data increase, approaches with weaker inductive biases generally outperform those with stronger assumptions. This is particularly characteristic of the field of Visual Representation Learning, where approaches have gone from being dominated by Supervised Learning, to Weakly Supervised Learning, to the now widespread success of Self-Supervised Learning without human labels. Yet, even modern Self-Supervised Learning approaches still depend on strong inductive biases such as augmentations, masking, or cropping. If this trend holds, even these remaining biases should become bottlenecks at scale -- and our experiments confirm this: the optimal strength of inductive biases decreases as data grows. This motivates the search for approaches that rely on fewer assumptions. To this end, we introduce Temporal Difference in Vision (TDV), a new paradigm for self-supervised learning from video that avoids existing inductive biases, relying instead on a causal assumption that the past causes the future. TDV functions by jointly training an image encoder and a motion encoder so that the current frame's representation plus the encoded motion equals the next frame's representation. Despite not leveraging any strong inductive biases, TDV matches state-of-the-art recipes on dense spatial tasks, laying the foundation for representation learning without strong assumptions. --- ### Green SARC: Predictive Cost and Carbon Governance for Agentic AI Systems Authors: Gaston Besanson Published: 2026-06-14 Categories: cs.SE, cs.AI, cs.DC, cs.LG arXiv: https://arxiv.org/abs/2606.15954v1 Agentic AI systems act through tools and sub-agents, yet the controls meant to bound their financial and environmental cost still sit on dashboards evaluated beside or after execution. Green SARC applies the SARC governance-by-architecture framework -- four enforcement sites in the agent loop -- to FinOps and GreenOps, contributing the theory of what to enforce and how to predict it. We report four policy-independent results. (i) The unconstrained "State Snowball" is $Θ(n^2)$ in loop depth; on 3,000 real multi-step plans (SWE-rebench) it holds on 100%, with median curvature $\hat{c}_2=216$ exceeding the linear-accretion prediction $p/2=134$ -- real plans accrete faster than the model. (ii) On real residuals the Normal-$σ$ gate under-covers (92% at nominal 95%); split-conformal calibration holds (95.2%). (iii) A soft Lagrangian penalty tuned to the budget in expectation breaches it on 91.5% of seeds; the architectural gate breaches 0%. (iv) Under binding budgets the gate's over-budget incidence is 0% on synthetic and real (BurstGPT) arrivals. End-to-end token/USD/carbon savings (47--55%) are real but policy-dependent in magnitude -- set by a scope-cap knob, not by gate rejections. The library is open-source, dependency-free, and ships a regeneration script for every cited number. --- ### Spectral Adaptive Conformal Prediction for Structured Non-Exchangeable Data Authors: Jeffery Opoku, David Banahene Published: 2026-06-14 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2606.15950v2 Conformal prediction gives prediction intervals with finite-sample coverage when the data are exchangeable. Many time-indexed datasets are not exchangeable: they have seasons, recurring regimes, changing frequencies, or other forms of structured dependence. This paper studies a simple way to use that structure. We propose spectral adaptive conformal prediction, a method that forms weighted conformal quantiles using local spectral similarity and then updates the target miscoverage level online. The spectral weights choose calibration residuals that look relevant to the current test point. The adaptive update corrects the long-run miss rate when uncertainty changes over time. The theory makes both parts controllable. We give an approximate coverage bound that splits the error into a spectral mismatch term and an effective-sample-size term, prove that kernel spectral weighting never increases the mismatch term relative to uniform weighting, show that a bandwidth of order N^(-1/(d+2)) balances the two terms, and establish an unconditional long-run calibration bound for the adaptive update that holds for every sample path without independence or stationarity. Simulations with recurring regimes and slowly changing frequencies, together with four real-data examples spanning monthly, weekly, and daily U.S. and European series, show when the hybrid method improves on strong adaptive baselines and when it does not, and an effective-sample-size safeguard, computable at prediction time without outcomes, detects and repairs the one observed failure. --- ### FinBalance: A Multi-Document Accounting Reconciliation Benchmark Authors: Sasank Tumpati, Devansh Agarwal, Ayush Kedia, Arjun Neekhra, Murari Mandal, Krishna Garg, Yash Sinha, Suman Gupta, Dhruv Kumar Published: 2026-06-14 Categories: cs.CL arXiv: https://arxiv.org/abs/2606.15949v1 Existing financial-NLP benchmarks mostly evaluate prepared artifacts such as filings, tables, or extracted values. Real accounting begins earlier: source documents must be reconciled into cited journal entries, aggregated into a balance sheet, and checked for contradictions. We introduce FinBalance, a multi-document accounting reconciliation benchmark built from source-document bundles across eight industries, three period types, and five difficulty levels. Human-authored business scenarios, accounting policies, tax/FX treatments, document schemas, distractors, and inconsistency templates are composed by a deterministic generator whose ledger produces journal entries,balance sheets, and 23 inconsistency-code labels. On a 710-record evaluation split, six contemporary LLMs reach at most 46% exact final-balance-sheet accuracy. Four models show a 26-41 pp gap between BS_exact, the model's reported balance sheet, and BS_recon, the balance sheet obtained by replaying its entries through our ledger. Models often recover numerically plausible entries but fail to bind them to supporting documents and aggregate them consistently. Citation-pressure prompting barely changes document-linking errors, while ledger-feedback ablations substantially improve reported balance sheets and expose inconsistency-detection trade-offs. Expert finance reviewers validate the benchmark design and labels. --- ### Graphical-Probabilistic Modeling of Generative Flows in LLM-Native Software Systems Authors: Víctor A. Braberman, Flavia Bonomo-Braberman Published: 2026-06-14 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2606.15943v1 Engineering LLM-native software remains a challenging and immature field. Current practice is largely exploratory, relying on experimentation and heuristic techniques such as prompting and context engineering. These, however, are low-level and lack the principled structure needed to support design-level reasoning or analysis. In contrast, traditional software engineering leverages modularity and abstraction to communicate and analyze system behavior. To bring similar rigor to LLM-native development, we propose methods for documenting generative flows and for stating properties of LLM-based software designs. Such methods must account for the stochastic, prompt-dependent behavior of large language models while remaining expressive enough to capture emergent phenomena. Our initial approach is based on graphical probabilistic models, tailored to capture phenomena characteristic of LLM-native systems. This framework -- what we term Generation Networks -- aims to provide a foundation for principled reasoning about generative interactions and system-level properties in LLM-centric software architectures. --- ### Causal-Privacy Audit Workflow for Synthetic and Distilled Data in Dropout Support Authors: Hanghang Zheng, Xiwei Zhuang, Zhong Wang, Hong Liu, Xiao Chen, Jingwen He, Xia Li Published: 2026-06-14 Categories: cs.LG arXiv: https://arxiv.org/abs/2606.15940v1 Synthetic and distilled student data are increasingly used to enable privacy-conscious learning analytics, yet their suitability for decision-facing institutional support remains uncertain. In dropout support, generated data must preserve not only predictive utility or distributional resemblance, but also the financial-status evidence used to guide advising, payment-plan assistance, and scholarship-related decisions. Method: This study introduces CaP-Eval, a decision-facing causal-privacy audit workflow for evaluating generated student data under a fixed estimand, timing-aware adjustment design, estimator set, and empirical privacy-governance screen. The workflow compares original, distilled, adversarial synthetic, statistical synthetic, and DPGNet privacy-oriented generated data on predictive utility, treatment-effect fidelity, robustness to alternative estimators, and local training-record proximity. Results: DPGNet and distilled data preserved the original financial-status treatment-effect structure more reliably than the adversarial and Gaussian Copula baselines. DPGNet preserved full direction and rank agreement across epsilon levels; epsilon = 10 produced the smallest non-original IPW and DML deviations, while epsilon = 1 and epsilon = 5 amplified several financial-status contrasts. Distilled data remained highly faithful but retained the strongest local training-record proximity signal. TabularGNet preserved qualitative directions with moderate attenuation, and Gaussian Copula compressed effect magnitudes. Conclusions: Predictive utility, privacy orientation, empirical disclosure signals, and causal fidelity diverged; generated student data require joint audits of direction, magnitude, overlap, and release-governance risk before decision use. --- ### Learning Directional Semantic Transitions for Longitudinal Chest X-ray Analysis Authors: Zhangfeng Hu, Zefan Yang, Ge Wang, Tanveer Syeda-Mahmood, Anushree Burade, Mannudeep Kalra, Pingkun Yan Published: 2026-06-14 Categories: cs.CV, cs.MM arXiv: https://arxiv.org/abs/2606.15938v1 Chest X-ray (CXR) interpretation often requires longitudinal comparison to assess disease progression. Existing approaches typically rely on temporal feature fusion or inter-study discrepancy modeling, yet remain limited in capturing subtle progression semantics and overlook the inherently directional nature of disease trajectories. In this paper, we propose ProTrans, a novel vision-language pretraining framework that formulates disease progression as a directional semantic transition between paired CXR studies. ProTrans leverages radiology reports to anchor individual CXR representations within interpretable disease states, and introduces a learnable progression feature map to explicitly encode semantic shifts between states, aligned with report-derived progression descriptions. To enforce direction-aware perception, ProTrans incorporates a reversed temporal modeling process and imposes bidirectional reconstruction consistency across states and transitions, thereby disentangling directional semantics and promoting coherent trajectory modeling. Extensive experiments on longitudinal downstream tasks, including disease progression classification and progression captioning, demonstrate that ProTrans consistently outperforms existing methods, establishing a unified pretraining framework for longitudinal CXR understanding. https://github.com/RPIDIAL/ProTrans --- ### GOOSE-M2F: Adapting Mask2Former for High-Fidelity, Long-Tailed Fine-Grained Semantic Segmentation in Unstructured Outdoor Terrain Authors: Jyothiraditya Lingam, Nikhileswara Rao Sulake, Sai Manikanta Eswar Machara Published: 2026-06-14 Categories: cs.CV arXiv: https://arxiv.org/abs/2606.15937v2 We present GOOSE-M2F, a task-specific adaptation of Mask2Former for the GOOSE 2D Fine-Grained Semantic Segmentation (FGSS) Challenge at ICRA 2026. The GOOSE benchmark spans 64 fine-grained classes across unstructured outdoor terrain with a severely long-tailed distribution, where rare classes occupy fewer than 50 pixels per image. We extend the Swin-Large Mask2Former baseline with three targeted contributions: (1) 200 object queries to eliminate representational saturation; (2) a Feature Refinement Module (FRM) combining ASPP-lite and CBAM dual-attention; and (3) an Auxiliary Supervision Head that delivers direct per-pixel gradients for rare classes. A multi-stage training strategy pairs Distribution-Balanced loss, Rare-Class Copy-Paste augmentation, dynamic IoU-aware re-weighting, and EMA. At inference, a dense sliding-window engine with 2D Gaussian kernel blending and 4-scale TTA adds +10.57%. GOOSE-M2F achieves 70.08% Official Composite mIoU (63.55% fine, 76.61% coarse), placing 3rd on the GOOSE 2D FGSS leaderboard. Code and trained models are publicly available at GitHub: https://github.com/Aditya-Lingam-9000/GOOSE-M2F and Hugging Face: https://huggingface.co/XYZ9843/GOOSE-M2F. --- ### Beyond NL2Code: A Structured Survey of Multimodal Code Intelligence Authors: Xuanle Zhao, Qiushi Sun, Jingyu Xiao, Xuexin Liu, Haoyue Yang, Qiaosheng Chen, Xianzhen Luo, Jing Huang, Yufeng Zhong, Lei Chen, Shuai Fu, Zhenlin Wei et al. Published: 2026-06-14 Categories: cs.CL arXiv: https://arxiv.org/abs/2606.15932v2 While Large Language Models (LLMs) have substantially advanced text-to-code synthesis, many real programming tasks specify intent through visual artifacts such as screenshots, charts, vector drawings, videos, and interactive states. These tasks require models to connect visual perception to executable programs, because correctness depends not only on syntax but also on layout, data semantics, interaction behavior, and domain-specific constraints that apply after execution. This survey examines Multimodal Code Intelligence, covering systems that generate, edit, refine, or reason with code under visually grounded inputs and outputs. We first formulate the field by the role that code plays in each task, distinguishing code as a rendered artifact, an editable symbolic structure, a scientific representation, an intermediate reasoning trace, or an executable policy or tool interface. We then organize benchmarks and methods into four domains: Graphical User Interface, Scientific Visualization, Structured Graphics, and Frontier Tasks and Frameworks. This taxonomy connects mature artifact-generation problems to emerging agentic and unified settings and allows us to compare how different tasks treat evidence of correctness. Looking ahead, we argue that future research may benefit from four verification-centered directions. Multi-signal validation can combine complementary evidence of correctness, multi-state verification can test behavior across execution trajectories, cross-task transfer testing can probe reusable visual-code skills, and verifiable agent traces can reveal whether agent actions are grounded in visual evidence. Together, these directions may move this field from single-output imitation toward evidence-grounded executable systems. An ongoing project and resources are available on \href{https://github.com/xjywhu/Awesome-Multimodal-LLM-for-Code}{GitHub}. --- ### DeepRoot: A KG-Coordinated Multi-Agent System for Therapeutic Reasoning over Historical Medical Texts Authors: Zijian Carl Ma, Sean J. Wang, Sijbren Kramer, Li Erran Li Published: 2026-06-14 Categories: cs.MA, cs.AI arXiv: https://arxiv.org/abs/2606.15931v1 Historical medical archives and traditional medicines hold immense potential for drug discovery and remain a primary source for current drug development. However, pre-ontological prose and idiosyncratic taxonomies prevent the standardization and medical modernization of the data for use in current biomedical pipelines. Furthermore, no existing LLM agent system, whether tool-calling, retrieval-augmented, or agentic deep-research, can convert such text into verifiable drug-discovery leads at scale. We close this gap with DeepRoot, a multi-agent LLM system that jointly builds and utilizes a verified knowledge graph, showing that grounding and reasoning -- often conflated -- are separable axes the system can compose for therapeutic reasoning. Applied to the Shen Nong Ben Cao Jing, DeepRoot recovers $10$ of $21$ held-out compound-disease treatment pairs at R@$20$ ($47.6\%$ vs $4.8\%$ for a raw corpus LLM and $\sim\!2.4\%$ random) and dominates an LLM-as-judge audit for reasoning quality over baseline LLMs and LLMs with direct tool-call access to the same APIs DeepRoot itself queries. Tool-using LLMs hallucinate evidence on $87\%$ of claims, versus 7-10% for DeepRoot. Graph-only inference hallucinates $0\%$ but ranks lowest on reasoning coherence; DeepRoot KG+LLM is the only condition to win on both axes, pointing toward a route for systematic mining and repurposing of historical medical knowledge. --- ### ControlMap: Controllable High-Definition Map Generation for Traffic Scenario Simulation Authors: Marwan Farag, Steffen Wäldele, Yu Yao Published: 2026-06-14 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2606.15930v1 Simulation is central to validating autonomous driving systems, yet current pipelines are limited by insufficient scenario diversity due to costly High Definition (HD) map creation. Scaling HD maps requires expensive data collection and manual processing. Moreover, existing generative models lack the fine-grained control necessary to target specific road topologies during generation. This paper presents a data-driven pipeline for controllable HD map generation using latent diffusion and ControlNet for spatial conditioning. To our knowledge, we are the first to inject spatial guidance signals into a diffusion model for HD map synthesis. Furthermore, our model supports adjustable conditioning strength through classifier-free guidance and city-level style transfer via city label conditioning. To complement existing metrics, we introduce two novel metrics to evaluate adherence to the control signal and similarity to ground-truth maps. Experiments demonstrate that our model generates realistic HD maps that faithfully follow input road topologies while accurately preserving city-specific details. --- ### An Exploratory Study of Blood Glucose Estimation from Photoplethysmography Signals using Machine Learning Authors: Ruhani Bhatia, Vijval Ekbote Published: 2026-06-14 Categories: cs.LG arXiv: https://arxiv.org/abs/2606.15927v1 Diabetes and extreme blood sugar levels are some of the major health problems faced by humans today across the world. While Continuous Glucose Monitoring (CGM) has emerged as an effective technology for management of diabetes as well as for monitoring blood sugar levels, this technology has traditionally been invasive (that is, requiring the piercing of the skin) and carries the risk of irritation, induration, etc. This highlights the need for accurate and non-invasive CGM methods that can be deployed at scale. With the emergence of various sensing technologies and their integration in wearables like the smart-watch, we now have the capability to continuously monitor body signals like the Photoplethysmogram (PPG) in a non-invasive manner. Having the ability to continuously monitor blood glucose through CGMs and continuously monitor PPG signals through a smart-watch offers an opportunity to get dense data on these two, opening the possibility of building machine learning and deep learning based models to estimate blood glucose level from PPG signals. In this work, we first present a paired dataset comprising continuous PPG signals from a smartwatch along with glucose values recorded using a CGM device. We also present the results of some preliminary experimental explorations performed on our dataset. These preliminary results suggest that some predictive signals may exist, though more exploration is needed with more data from a larger number of individuals. The dataset can be accessed at https://zenodo.org/records/20577959 --- ### TurboGS: Accelerating 3D Gaussian Splatting via Error-Guided Sparse Pixel Sampling and Optimization Authors: Zheng Dong, Daifei Qiu, Pinxuan Dai, Ke Xu, Jiamin Xu, Lili He, Rynson W. H. Lau, Weiwei Xu Published: 2026-06-14 Categories: cs.CV, cs.GR arXiv: https://arxiv.org/abs/2606.15924v1 Consumer-level applications require fast optimization of 3D Gaussian Splatting (3DGS) with high-fidelity novel view rendering. However, existing 3DGS acceleration approaches still incur substantial computation on redundant pixels while sacrificing fine details. In this paper, we present TurboGS, an error-guided training framework that accelerates 3DGS by concentrating optimization on perceptually informative pixels. TurboGS is built upon four core components: (1) a tile-wise sparse pixel sampling, which, driven by multi-view reconstruction errors during training, prioritizes challenging regions and skips well-reconstructed ones to avoid redundant gradient computation; (2) a tile-wise structure-aware loss with sparse Normalized Cross-Correlation, which provides sparse yet effective supervision to preserve fine details and stabilize training; (3) an error-driven Gaussian density control strategy, which dynamically allocates model capacity and removes redundant primitives; and (4) a tailored hybrid optimizer that couples Hessian-informed updates with Adam moment damping to stabilize and improve convergence under sparse supervision. Experiments on standard benchmarks demonstrate that TurboGS can deliver on par or superior rendering quality within 100 seconds on a single RTX 5090 GPU card (up to 10x training speedup over vanilla 3DGS). --- ### Runtime Analysis of Cartesian Genetic Programming in Evolving Boolean Functions Authors: Duc-Cuong Dang, Roman Kalkreuth, Andre Opris Published: 2026-06-14 Categories: cs.NE, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2606.15923v1 Cartesian Genetic Programming (CGP) is among the practical and popular forms of Genetic Programming as it uses a graph-based representation of programs. This paper presents a first runtime analysis of CGP in evolving Boolean functions using complete training sets. We prove an asymptotic bound $O(n D^5)$ for the expected number of fitness evaluations of CGP to construct a conjunction of $n$ inputs using at most $D \geq n-1$ binary gates, a minimal function set, and even with a strict survival selection. When the non-strict selection is used, the bound is improved to $O(n D^4)$. Our analysis reveals interesting characteristics of CGP induced search, which have been only observed empirically. In particular, enabling the acceptance of equally good solutions, including those with connected gates non-contributing to fitness, can lead to a speedup, and consequently a better asymptotic time bound. In contrast to conjunctions, we also prove a negative result which shows that CGP requires exponential time to evolve an exclusive disjunction. Experiments evolving conjunctions complement our theoretical findings. The use of incomplete training sets is found to further reduce the average number of fitness evaluations while maintaining a good level of generalisation. --- ### OmniOPSD: Rationale-Privileged On-Policy Self-Distillation for Affective Computing Authors: Zebang Cheng, Shuimu Chen, Boxue Yang, Yuanshen Guan, Jingyi Chen, Zheng Lian, Xiaojiang Peng, Fei Ma, LaiZhong Cui, Qi Tian Published: 2026-06-14 Categories: cs.CV arXiv: https://arxiv.org/abs/2606.15920v2 Reinforcement learning for multimodal large language models (MLLMs) is often hindered by severe reward sparsity in complex reasoning tasks. This challenge is particularly pronounced in human-centered scenarios involving states, emotions, intentions, and behaviors, where heterogeneous multimodal signals and subjective human factors make high-quality chain-of-thought (CoT) annotations expensive and difficult to obtain. Although many multimodal datasets provide expert-annotated ground-truth labels, directly using these labels for supervised fine-tuning may encourage shortcut learning in multimodal perception and provides limited transparency for safety-critical human--AI interaction. To address these limitations, we propose OmniOPSD, a Rationale-Privileged On-Policy Self-Distillation framework that uses frontier-generated rationales as teacher-side privileged evidence rather than student imitation targets. OmniOPSD uses frontier-generated evidence-aware rationales only as training-time privileged evidence context for a local teacher. The student samples its own rollout from the original multimodal input, while the rationale-privileged teacher scores the same tokens and provides dense token-level supervision. Thus, the student learns on its own trajectory distribution without directly imitating frontier-model completions, and inference requires no labels, rationales, CoT annotations, or closed-source model access. Experiments on MER-UniBench show that OmniOPSD achieves state-of-the-art performance with an average score of $84.19$, and ablations further support the value of rationale-privileged teacher guidance. --- ### Reinforcement Learning for LLM-based Event Forecasting Authors: Amit Arnold Levy Published: 2026-06-14 Categories: cs.LG arXiv: https://arxiv.org/abs/2606.15917v1 We use Group Relative Policy Optimization (GRPO), a recently devised sample and memory efficient reinforcement learning method, to finetune pretrained LLMs in the range of 1.5B to 14B parameters equipped with the ability to get current information through the use of a Wikipedia revisions tool, or news summaries, to forecast real events beyond the knowledge cutoff of the LLM, as well as problems made to simulate different aspects of the dynamics of that training. We use the results of these experiments to comment on the scaling capability of LLMs for forecasting, as well as classify how judgmental forecasting fits into the verifiable/unverifiable domain taxonomy, considering the impact of the inherent aleatoric uncertainty when forecasting future events (e.g. the roll of a die). As a result of the GRPO training, we manage to bring a 1.5B parameter transformer (Qwen 2.5 1.5B) to forecasting performance superior to Claude Sonnet 3.5 over the same dataset as measured by cross entropy from the market agreed probabilities. We also discuss various dead ends on the path to this result. --- ### Contaminated Collaboration: Measuring Gender Bias Transfer in LLM-Assisted Student Writing Authors: Ariyan Hossain, Kazi Kamruzzaman Rabbi, Farig Sadeque, S M Taiabul Haque Published: 2026-06-14 Categories: cs.CL, cs.HC arXiv: https://arxiv.org/abs/2606.15914v1 Gender bias in LLMs has been studied extensively in model outputs, with biased prompts shown to amplify stereotyped generations. Whether such bias propagates into text produced by humans who use these systems, however, remains underexplored. We investigate whether gender bias in an LLM writing assistant transfers into career plan essays written by students. We first verify that a gender-biased prompt induces gender-differentiated language in LLM-generated essays, while a neutral prompt does not. We then recruited participants (N = 123) in a controlled environment to write career plan essays for paired biographical profiles differing only in gender under three conditions: no AI assistance, neutral LLM assistance, or gender-biased LLM assistance. Students in the biased condition produced essays with a significantly larger agentic gap and more gender-stereotypic occupation suggestions than those in the control and neutral conditions. Our results also reveal that this bias transfer is asymmetric: agency is suppressed in female-target essays while male-target writing remains largely unaffected. Our findings highlight the risk of bias propagation in AI-assisted writing, calling for fairness-aware design in educational AI tools. --- ### On-Policy Distillation with Curriculum Turn-level Guidance for Multi-turn Agents Authors: Gengsheng Li, Mao Zheng, Mingyang Song, Ruiqi Liu, Tianyu Yang, Jie Sun, Qiyong Zhong, Haiyun Guo, Junfeng Fang, Dan Zhang, Jinqiao Wang Published: 2026-06-14 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2606.15912v1 Multi-turn agents that plan, invoke tools, and interact with environments offer a promising paradigm for solving complex tasks, yet their capabilities typically rely on very large models whose inference cost is prohibitive in practice.On-Policy Distillation (OPD) is a natural recipe for transferring such capabilities to smaller students, but we find that it suffers a characteristic failure mode in this setting: small student errors compound across turns and push the trajectory out of the teacher's familiar state distribution, so the teacher's supervision becomes least reliable precisely where the student needs it most.We propose Guided On-Policy Distillation (Guided-OPD), a simple yet effective algorithm that mixes teacher- and student-generated turns within each rollout and schedules the teacher's intervention probability along a curriculum that decays to zero.Strong guidance keeps early trajectories close to the teacher distribution and is then gradually withdrawn to recover the purely on-policy regime used at inference.On ALFWorld, ScienceWorld, and WebShop, distilling Qwen3 students from a Qwen3-30B-A3B teacher, Guided-OPD improves Score by 21.1\% and Success Rate by 25.5\% over vanilla OPD on average, with larger gains on smaller students. --- ### Interactor: Agentic RL oriented Iterative Creation for Ad Description Generation in Sponsored Search Authors: Penghui Wei, Jiayu Wu, Chao Ye, Zhi Guo, Shuanglong Li, Lin Liu Published: 2026-06-14 Categories: cs.CL, cs.IR arXiv: https://arxiv.org/abs/2606.15911v1 This paper focuses on automatically generating informative ad descriptions in sponsored search. Unlike ad titles which are usually optimized to attract user click feedbacks, ad descriptions have a longer text span and possess the potential of incorporating world knowledge to address user search intents while presenting the fine-grained selling points of the ads. We propose Interactor, a multi-turn iterative creation framework optimized with agentic RL for ad description generation. The generation model acts as a policy that interacts with a customized environment consisting of multiple generative reward models. Given initial generations by the policy, the customized GenRMs evaluate multi-dimensional qualities including knowledge capacity and landing page consistency, providing both binary signals and reasoning feedbacks. The policy then iteratively refines the descriptions based on such feedbacks to ensure continuous improvement. Experiments on industrial datasets show that the Interactor framework significantly outperforms state-of-the-art approaches in generating knowledge-rich and faithful ad descriptions. Since May 2026, it has been deployed online in a leading search ads system, contributing to both ad revenue and user experience. --- ### Calibrated Triage, Not Autonomy: Confidence Estimation for Medical Vision-Language Models Authors: Reza Khanmohammadi, Kundan Thind, Mohammad M. Ghassemi Published: 2026-06-14 Categories: cs.CL arXiv: https://arxiv.org/abs/2606.15910v1 A vision-language model can answer a question about a medical image fluently and confidently while barely using the image, leaning instead on language priors. In medicine this is the failure that matters most, because the answer looks trustworthy and is not, and the only protection is a confidence score reliable enough to tell the system when to abstain. We ask a deployment question rather than an accuracy one: how much imaging work a model can safely handle alone, and which confidence signal makes that possible. We evaluate seven confidence estimators across five open-weight LVLMs and three medical visual-question-answering datasets spanning broad clinical imaging, radiology, and pathology, with every probe trained only on natural images and applied without adaptation. Recast as bounded selective prediction (automate a case only when confidence clears a threshold, defer the rest), the comparison is cautionary. The standard metrics are poor guides: discrimination barely separates the methods, and the weak calibration of a cheap self-report is cheaply removed by off-domain temperature scaling without changing deployable yield. What distinguishes a usable estimator is the high-confidence region a clinician acts on: the weakest baselines are confidently wrong on 41 to 45 percent of their errors against 1 to 4 percent for the best probe, and no estimator is reliably best across domains or models. Safe handoff is governed at two levels: base-model competence sets a ceiling, so a well-calibrated score recovers roughly a third of radiology cases at a 20 percent error tolerance but almost none of pathology; the confidence layer then decides how much of that ceiling is reachable. The usable role today is calibrated triage, not autonomy: automate the cases a calibrated score marks safe, route the rest to a clinician. We release all outputs, correctness judgments, and confidence scores, with code. --- ### High-Fidelity 4D Hand-Object Capture via Multi-View Spatiotemporal Tracking and Physics-Aware Gaussians Authors: Bo Peng, Xu Chen, Yi Gu, Hidenobu Matsuki, Mingsong Dou, Jingjing Shen, Deying Kong, Juyong Zhang, Zhengyang Shen Published: 2026-06-14 Categories: cs.CV arXiv: https://arxiv.org/abs/2606.15908v2 The growing demand for high-fidelity 4D hand-object interaction (HOI) data in embodied AI and spatial computing is currently bottlenecked by the reliance on pre-scanned object templates and physical markers. While recent methods have demonstrated promising results in reconstructing 4D hand-object interaction from videos, they are highly sensitive to initial estimates of hand and object poses. Yet, estimating these poses from images is challenging, in particular under severe occlusion which is inherent in hand-object interaction scenarios. We propose a novel system for the robust and accurate reconstruction of hands and objects from synchronized and calibrated multi-view videos without requiring any templates or markers. Our system consists of two main components with key innovations: (1) a multi-view feed-forward transformer model that aggregates cross-view geometry and temporal cues to provide a reliable, metric-consistent initialization for both poses and dense object geometry, and (2) a hand-object physics-aware Gaussian-based optimization framework to refine the initial estimates, integrating tetrahedral constraints, collision refinement, and appearance decomposition to produce physically plausible and visually accurate reconstruction. Validated on public benchmarks and an extensive internal dataset, our pipeline achieves highly robust, artifact-free reconstruction, providing an efficient foundation for automated 4D asset generation. Our project page are available at https://zyshen021.github.io/HOSTPG/. --- ### MAGE-RAG: Multigranular Adaptive Graph Evidence for Agentic Multimodal RAG in Long-Document QA Authors: Yilong Zuo, Xunkai Li, Jing Yuan, Qiangqiang Dai, Hongchao Qin, Ronghua Li Published: 2026-06-14 Categories: cs.IR, cs.AI, cs.CL, cs.DB, cs.MM arXiv: https://arxiv.org/abs/2606.15906v1 Long-document multimodal question answering requires a system to locate sparse evidence in long PDFs and integrate clues from text, tables, images, charts, and complex layouts. Existing RAG methods mostly rely on fixed Top-k retrieval over text chunks or pages. Text retrieval can compress the context but often loses visual and layout information; page-level visual retrieval preserves the original page, yet it also sends large irrelevant regions to the reader, leading to a static trade-off among evidence coverage, noise, and inference cost. This paper proposes MAGE-RAG, a multigranular adaptive graph evidence framework for long-document multimodal QA. MAGE-RAG uses page retrieval as the entry point for query-time evidence construction. Offline, it builds an evidence graph with page nodes and element nodes, encoding containment, reading order, layout adjacency, section hierarchy, and semantic-neighbor relations. At query time, an online evidence controller iteratively activates, opens, searches, and prunes evidence under explicit budgets. The resulting evidence subgraph is then rendered into structured multimodal reader input, allowing the LVLM to consume compact and relevant evidence within a limited context. On LongDocURL and MMLongBench-Doc, we establish a unified comparison and analysis protocol covering Direct MLLM, Text RAG, Page-level Visual RAG, and Graph/Agentic RAG. Experiments show that MAGE-RAG achieves 52.75 overall accuracy on LongDocURL, and 53.26 accuracy with 51.19 F1 on MMLongBench-Doc. Fine-grained breakdowns, budget-performance curves, ablations, and trace-based analysis further show that query-time evidence subgraph construction can balance dispersed evidence coverage with context-noise control. Our code is available at https://github.com/laonuo2004/MAGE-RAG.git. --- ### Control-Plane Placement Shapes Forgetting: An Architectural Study of Agent Memory Across Thirteen System Configurations Authors: Dongxu Yang Published: 2026-06-14 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2606.15903v2 Where an LLM sits in an agent memory pipeline -- between the recall plane that retrieves stored facts (extensively benchmarked) and the control plane that mutates them via supersede, release, purge (largely untested) -- shapes which forgetting failure modes the system recovers. Comparing thirteen system configurations on a 385-case adversarial surface, we observe three placement regimes with partly complementary coverage: deterministic primitives suffice for lexical/temporal categories but fail canonicalization (5% on identifier-obfuscation, 0% on cross-lingual); inscribe-time LLM recovers canonicalization (100%) but cannot help intent-aware deletion (0% on prefix-collision and compound-fact); a mutation-time hook recovers intent-aware deletion (78-85%) and brightens nearly all categories simultaneously (91.7-93.2% overall, $0.17 per 385-case run, 2.3s/case mutation latency vs. 64-191ms/case deterministic, recall path unchanged). We expose the trade-off via ForgetEval, a 1000-case templated suite plus a 385-case adversarial layer (132 hand-crafted + 253 LLM-drafted oracle-validated) scored by deterministic substring match, paired with a six-method Adapter Protocol with honest N/A scoring that lets heterogeneous memory stores enter in 130 lines. Admission is corroborated by 10-annotator IAA (Fleiss' kappa = 0.958) and a 77-case external-authored subset (four blind contributors) that replicates the canonicalization asymmetry and amplifies the joint-placement lift (+27.8 pt). Production failures are predominantly forgetting failures rather than recall failures, yet existing benchmarks measure only recall. ForgetEval and all adapters are released under MIT. --- ### SkillVetBench: LLM-as-Judge for Multi-Dimensional Security Risk Evaluation in Open-Source LLM Agent Skills Authors: Ismail Hossain, Sai Puppala, Md Jahangir Alam, Tanzim Ahad, Sajedul Talukder Published: 2026-06-14 Categories: cs.CR, cs.AI, cs.HC, cs.LG, cs.MA arXiv: https://arxiv.org/abs/2606.15899v1 Open-source LLM agent ecosystems are growing rapidly, yet the security of community-contributed skills - modular tool definitions that extend agent capabilities - remains largely unvetted. The gap we fill: existing scanners operate at the code layer and are structurally blind to instruction-layer and multi-agent risk - natural-language directives that hijack an agent, exfiltrate data through encoded side channels, or chain harm across pipelines - so what is needed is a semantic, multi-dimensional vetting system rather than another signature matcher. We present SKILLVETBENCH, a live public leaderboard on Hugging Face that uses an LLM-as-Judge to vet agent skills. What is new: SARS (Skill Agentic Risk Score), a five-dimensional agentic-risk metric with a principled weighted formula for instruction-following systems. What is integrated: full CVSS v4.0 vector decomposition and a ClawHub dual-view that places our LLM-generated review beside the official marketplace verdict. What is demonstrated: drawing on our companion benchmark paper ( 1), the LLM-as-Judge stage achieves zero false negatives across 78 confirmed-malicious skills and zero false positives across 22 benign controls, while the best static baseline (SKILLSIEVE) still misses 15%; for instruction-layer categories such as Prompt Injection and Memory Poisoning, conventional tools miss between 89% and 100% of threats (e.g., CODEBERT detects none of nine memory-poisoning skills). Detection rates vary from 35% to 95% across four LLM evaluators, motivating ensemble scoring in production deployments. --- ### Topological Flow Matching Authors: Kacper Wyrwal, İsmail İlkan Ceylan, Alexander Tong Published: 2026-06-14 Categories: cs.LG, cs.AI, stat.ML arXiv: https://arxiv.org/abs/2606.15897v1 Flow matching is a powerful generative modeling framework, valued for its simplicity and strong empirical performance. However, its standard formulation treats signals on structured spaces, such as fMRI data on brain graphs, as points in Euclidean space, overlooking the rich topological features of their domains. To address this, we introduce topological flow matching, a topology-aware generalization of flow matching. We interpret flow matching as a framework for solving a degenerate Schrödinger bridge problem and inject topological information by augmenting the reference process with a Laplacian-derived drift. This principled modification captures the structure of the underlying domain while preserving the desirable properties of flow matching: a stable, simulation-free objective and deterministic sample paths. As a result, our framework serves as a drop-in replacement for standard flow matching. We demonstrate its effectiveness on diverse structured datasets, including brain fMRIs, ocean currents, seismic events, and traffic flows. --- ### LoComposition: Terrain-Adaptive Energy-Efficient Quadruped Locomotion without Gait Priors Authors: Loukas Kordos, Leonard T. Franz, Simon Rappenecker, Oliver Hausdoerfer, Angela P. Schoellig, Pavel Kolev, Georg Martius Published: 2026-06-14 Categories: cs.RO, cs.LG arXiv: https://arxiv.org/abs/2606.15896v1 Learning-based quadrupedal locomotion typically relies on complex reward formulations that entangle task specification, operational limits, gait preference, and terrain adaptation within a single optimization objective. We instead treat these functions through distinct mechanisms: rewards for task specification, constraints for operational limits, energy minimization for gait preference, and exteroceptive perception for adapting energy use to terrain difficulty. We show that these components jointly enable efficient, terrain-adaptive locomotion, and that removing each component exposes a distinct failure mode. Our formulation removes explicit gait priors (including air-time, contact-count, and foot-clearance targets) in favor of emergent behavior. Compared to a conventional complex-reward baseline, our formulation achieves comparable terrain traversal while reducing cost of transport by 56% and operational-limit violations by 96%. The resulting policies transfer zero-shot to a physical Unitree Go2 using LiDAR-based elevation mapping. Project website with videos: https://tinyurl.com/locomposition. --- ### BALTO: Balanced Token-Level Policy Optimization for Hallucination Mitigation Authors: Ning Li, Zixuan Guo, Yan Xu, Wenbo Fei, Yifan Niu, Chang Luo, Yasheng Wang, Weiwen Liu, Yong Yu, Weinan Zhang Published: 2026-06-14 Categories: cs.CL arXiv: https://arxiv.org/abs/2606.15893v2 Hallucinations remain a major obstacle to deploying large language models (LLMs) in knowledge-intensive settings, where generated responses must be faithfully grounded in provided evidence. Reinforcement learning (RL) is a promising direction for hallucination mitigation, but response-level faithfulness rewards suffer from a granularity mismatch: localized hallucinations can cause supported content to receive spurious penalties. Although recent work introduces fine-grained feedback such as claim-level verification and token-level rewards, unbalanced credit assignment can still induce length, verbosity, or optimization-noise biases. We propose BALTO, a Balanced Token-level Policy Optimization framework for hallucination mitigation. BALTO extracts checkable factual claims, verifies them against the reference context, and projects claim-level judgments to token-level labels. A balanced token-level credit assignment mechanism is introduced into the framework. This design redistributes probability mass from unsupported content toward faithful content, rather than suppressing the entire response. We systematically analyze the limitations of response-level rewards from a theoretical standpoint, and prove BALTO's advantages in training stability and optimization efficiency for hallucination mitigation. Experiments on ConFiQA, RAGTruth, and FinLLM-Eval show that BALTO achieves the highest faithfulness across all six model--benchmark settings and consistently outperforms existing post-training baselines in Q-Score, demonstrating a stronger faithfulness--informativeness trade-off. --- ### Scalar-pathway fidelity improves physical accuracy in short-range equivariant interatomic potentials Authors: Jia Bi, Alin Marin Elena, Samuel Pinilla Published: 2026-06-14 Categories: cs.LG arXiv: https://arxiv.org/abs/2606.15892v1 Accurate interatomic potentials enable molecular dynamics of materials, molecules, and interfaces beyond density-functional-theory length and time scales. Equivariant neural network potentials have improved the representation of local geometry. However, their deployable energy surfaces ultimately manifest through invariant scalar channels, whose aggregation and spectral resolution remain comparatively underexamined. Here we use Physics-Aware Neighborhood (PAN) pooling and Physics-Guided Spectral (PGS) mixers as controlled scalar-pathway probes: lightweight, symmetry-preserving modifications that act only on \(\ell=0\) channels while leaving the equivariant tensor backbone unchanged. Using MACE as a high-body-order mechanistic scaffold, PAN adds coordination-sensitive amplitude modulation, whereas PGS augments edge and readout scalar features with radial and tapered spectral bases. Across metallic Ag, covalent Si, a short-range ionic LiF/Li--F subset, and MD17/rMD17 molecules, this scalar-pathway correction reduces MACE force errors by 22--27\% and energy errors by 19--22\%; on systems with stress labels, stress errors decrease by 27--28\%, at approximately 5\% additional inference-FLOPs cost. Directionally consistent gains in Allegro and NequIP further indicate that the correction is portable across distinct short-range equivariant backbones, although effect sizes remain architecture-dependent. These results identify scalar-pathway fidelity as a practical design dimension for short-range equivariant interatomic potentials. --- ### UrbanWell: Benchmarking Multimodal Large Language Models for Spatio-Temporal Urban Wellbeing Analytics Authors: Yanxin Xi, Xiang Su, Jie Feng, Yu Liu, Sasu Tarkoma, Pan Hui Published: 2026-06-14 Categories: cs.AI arXiv: https://arxiv.org/abs/2606.15890v1 Understanding urban wellbeing from multimodal data requires integrating heterogeneous spatial and temporal signals, posing significant challenges for current multimodal large language models (MLLMs). We introduce UrbanWell, a large-scale benchmark designed to systematically evaluate the spatio-temporal reasoning capabilities of MLLMs for urban wellbeing analytics through joint modeling of satellite and street view imagery. UrbanWell spans 38 cities across multiple years and includes diverse indicators covering (1) environmental conditions (CO$_2$, NO$_2$, PM${2.5}$, and Normalized Difference Vegetation Index), (2) spatial accessibility (minimum distance to supermarkets and restaurants), (3) urban form (road length, road density, and land use), (4) urban vitality (population, economic activity diversity, and land use diversity), and (5) subjective perception attributes (e.g., safety, beauty, liveliness, wealth, and quietness). All indicators are aligned at grid level to enable standardized evaluation. Beyond static prediction, UrbanWell defines temporal reasoning tasks, including future value forecasting from historical observations and temporal trend classification. We benchmark 15 state-of-the-art representative MLLMs in a zero-shot setting, providing a comprehensive comparative evaluation across spatial and temporal dimensions. Experimental results indicate that while MLLMs capture salient spatial and perceptual cues, their performance varies substantially across heterogeneous urban indicators spanning environment and subjective perception. UrbanWell serves as a unified benchmark for evaluating multimodal spatial and temporal reasoning in urban wellbeing analytics, offering a standardized testbed for systematic assessment and future research on multimodal urban intelligence. Our codes and datasets are accessible via https://github.com/axin1301/UrbanWell-Benchmark. --- ### SiGnature: Explicit Motion Diffusion for Stylized Semantic Gesture Authors: Adi Rosenthal, Tomer Koren, Nadav Shaked, Doron Friedman, Ariel Shamir Published: 2026-06-14 Categories: cs.CV arXiv: https://arxiv.org/abs/2606.15889v1 While recent advances in co-speech gesture generation have achieved impressive rhythmic synchronization, synthesizing gestures that are both semantically meaningful and faithful to a speaker's unique non-verbal style remains an open challenge. Semantic gestures, such as iconic shapes or deictic pointing, are statistically sparse, making them difficult to learn effectively within standard generative models. We present SiGnature, a framework for Stylized and Semantic Gesture generation that reconciles precise semantic control with high-fidelity style preservation. Unlike prevalent methods that rely on entangled latent representations, SiGnature operates in an explicit joint-rotation space. This design enables our core contribution, Joint Motion Integration (JMI), a training-free inference mechanism capable of injecting any external motion sequence, particularly in-the-wild semantic gestures, directly into the diffusion process. JMI automatically identifies the specific ``active joints'' conveying a semantic action and injects them into the generation, while relying on the diffusion backbone to synthesize the remaining body dynamics, including posture and flow, in accordance with the pre-learned style of the target speaker. This allows for the plug-and-play integration of arbitrary motions, including complex semantic gestures, without retraining or introducing the ``Frankenstein'' artifacts typical of cut-and-paste methods. Extensive experiments and perceptual studies demonstrate that SiGnature offers superior semantic motion control while maintaining smooth and natural co-speech gesture generation and preserving the distinct characteristics of the speaker, thereby outperforming state-of-the-art baselines. --- ### NVMOS: Non-Verbal Vocalization Quality Assessment in Speech Authors: Jialong Mai, Jinxin Ji, Xiaofen Xing, Wencui Liu, Xiangmin Xu Published: 2026-06-14 Categories: cs.SD, cs.AI, eess.AS arXiv: https://arxiv.org/abs/2606.15888v1 Non-verbal vocalizations (NVs), such as laughter, sighs, and coughs, are important acoustic cues for emotion and intent. Existing speech quality assessment methods typically focus on overall naturalness, while non-verbal TTS evaluations mainly examine whether a target NV appears with the correct type and position. However, the perceptual quality of NV events themselves remains underexplored. To address this gap, we construct an NV-MOS dataset containing outputs from multiple NV-TTS systems and naturally occurring NV samples, with ratings collected from three acoustic experts on a perceptual quality scale. We further analyze audio-capable multimodal large language models such as Gemini and find clear inconsistencies between their scores and expert ratings. These results suggest that general-purpose multimodal models cannot reliably replace human judgments for NV quality assessment. We then propose NVMOS, to our knowledge the first model that can reliably predict the perceptual quality of NV events in speech. Experimental results show that, with a local NV-event focusing module, NVMOS reaches expert-level or stronger agreement with human MOS. --- ### Intelligence Is Not the Bottleneck: Validating an LLM First-Pass Manuscript Score Against Peer-Review Outcomes Authors: Costa Georgantas Published: 2026-06-14 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2606.15887v1 Large language model (LLM) systems are increasingly proposed to assist peer review, yet most evaluations judge the prose of machine-generated review text, not the validity of the numeric score a system assigns. We validate AIPR, which reads a submitted manuscript and emits five 0-100 quality dimensions and a weighted overall score, against the public decision outcomes of a major machine learning venue. AIPR grades by prompting alone, with no fine-tuning on reviews or decisions. Across 300 ICLR submissions with public decision tiers and reviewer ratings, graded under a frozen pipeline with hypotheses pre-registered before any score met any outcome, the overall score separates rejected from accepted submissions (AUROC 0.82, 95% CI 0.78-0.87), rises monotonically across tiers, and tracks the mean reviewer rating. The signal is strongest where we claim it: the lowest-scoring fifth is rejected far above the base rate, with oral papers absent. The validity comes mostly from the model: a one-paragraph prompt on the same model discriminates almost as well as the full pipeline (the small gap favours the pipeline but does not meet the pre-declared criterion, p = 0.09). What the engineering adds is reliability and a grounded review: AIPR's score barely moves across repeated runs (0.7 vs. 2.8 points within-paper SD) where the bare prompt swings, and the same pass returns a rubric-structured, evidence-grounded review rather than a bare number, with the human keeping the decision. --- ### Text region detection in historical astronomical diagrams Authors: Zeynep Sonat Baltacı, Raphaël Baena, Fei Meng, Somkéo Norindr, Florence Somer, Matthieu Husson, Mathieu Aubry Published: 2026-06-14 Categories: cs.CV arXiv: https://arxiv.org/abs/2606.15886v1 Text detection is a crucial task in the analysis of historical documents. While datasets and benchmarks exist for text detection in manuscripts and maps, the study of text in mathematical diagrams has received little attention. To address this, we introduce a large-scale, diverse, open-access dataset of 948 historical astronomical diagrams containing 10,940 oriented polygonal text regions. Our dataset spans ten centuries (8th to 18th) and seven main linguistic traditions: Arabic and Persian (115), Chinese (332), Byzantine (233), Latin (185), Hebrew (48), and Sanskrit (35). It captures a wide range of diagram styles and textual content, from symbols to multi-line paragraphs. Each text instance is annotated with ordered polygons that precisely delineate text regions and encode the reading direction. In addition, we annotated the 2,293 regions in Latin diagrams with 20 class labels. We evaluated several strong baselines on our dataset, including TESTR, DeepSolo++, and Poly-DETR, a simple extension of DINO-DETR that we design to predict ordered polygon vertices. Poly-DETR achieves state-of-the-art performance on the MTHv2 and cBAD2019 benchmarks and provides a solid, simple baseline on our dataset. Code and dataset available online. --- ### Neuron Level Analysis of Large Language Model in Legal Domain Reasoning Authors: Eri Onami, Youmi Ma, Shuhei Kurita, Naoaki Okazaki Published: 2026-06-14 Categories: cs.CL arXiv: https://arxiv.org/abs/2606.15884v1 We presented a neuron-level analysis of legal-domain reasoning in LLMs, comparing it with other applied domain tasks across seven open-weight models. Using neuron attribution scores to rank and suppress influential neurons, we confirmed that suppressing the identified neurons collapses accuracy on the target task, whereas suppressing the same number of random neurons does not. We further found a small subset of neurons influential across all seven tasks; once these are removed, suppressing the remaining neurons degrades only the task they were identified from, revealing genuinely task-specific neurons in every model studied. Within the legal domain, the three benchmarks exhibit relatively high neuron overlap and tend to be affected jointly, suggesting of legal components neurons that span jurisdictions. The distribution of identified neurons in our experiments suggests that the hypothesis that influential neurons are concentrated in middle MLP layers may depend on the input format and content, rather than being a universal phenomenon. --- ### Koshur Diacritizer: A Byte-Level Sequence-to-Sequence Model for Kashmiri Diacritic Restoration Authors: Haq Nawaz Malik, Nahfid Nissar, Faizan Iqbal Published: 2026-06-14 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2606.15883v2 Kashmiri, an Indo-Aryan language written in a modified Perso-Arabic script, frequently omits diacritic marks in digital text, creating ambiguity and challenging downstream NLP applications. We present Koshur Diacritizer, a ByT5-small byte-level sequence-to-sequence model for restoring diacritics in Kashmiri text. To support this task, we release a publicly available dataset of 23.7k aligned undiacritized diacritized Kashmiri sentence pairs. The proposed framework combines script-aware normalization, alignment validation, and skeleton-preserving inference to ensure reliable restoration while maintaining the original base-letter sequence. Experimental results on a held-out test set achieve a DERm of 0.2012 and a WER of 0.2159. Additionally, evaluation by a native Kashmiri linguistic expert yields a mean accuracy of 77.5%. The dataset, model, and source code are publicly released to provide a reproducible baseline for Kashmiri diacritic restoration and future low-resource language research. --- ### Biarchetype analysis for univariate functional data. An application to macroeconomic financial time series Authors: Aleix Alcacer, Rafael Benitez, Vicente J. Bolos, Irene Epifanio Published: 2026-06-14 Categories: stat.ME, cs.LG, stat.AP arXiv: https://arxiv.org/abs/2606.15881v1 We introduce biarchetype analysis for the first time in the context of univariate functional data. This unsupervised methodology extends archetype analysis by simultaneously identifying archetypal structures across both the cases (countries, in our application) and the temporal argument. Both cases and time points are expressed as mixtures of biarchetypes, yielding a concise and highly interpretable representation of complex functional observations. Although biarchetype analysis is not intended as a clustering technique, it offers superior interpretability compared with biclustering approaches, as it is based on extreme, representative patterns rather than average centroids, thereby enhancing human comprehension. We apply the proposed method to 10-year government bond yields of European countries over the period 2001-2025. The results identify three distinct time regimes (the pre-crisis period, the euro-area sovereign debt crisis, and the post-crisis period), and reveal Germany, Greece, and Hungary as country archetypes. --- ### Deep Residual Injection for Full-Spectrum Forensic Signal Perception in Multimodal Large Language Models Authors: Kaiqing Lin, Zhiyuan Yan, Ruoxin Chen, Ke-Yue Zhang, Yue Zhou, Caiyong Piao, Bin Li, Taiping Yao, Bo Wang, Youchang Xiao, Shouhong Ding Published: 2026-06-14 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2606.15880v1 Multimodal large language models (MLLMs) have been increasingly adopted in forensics for their robust semantic understanding. As AI-generated images become realistic, semantic-level inconsistencies alone are often insufficient for reliable detection. This motivates a critical question: whether MLLMs can achieve full-spectrum forensic signal perception, i.e., capturing low-level generator artifacts without sacrificing pre-trained semantic knowledge. We further perform a layer-wise analysis of forensic signal perception in MLLMs, showing that semantic information is primarily formed in the early-to-middle layers, whereas direct fine-tuning for artifact learning disrupts these semantic representations. Based on this insight, we propose Deep Visual Residual MLLM (Deep-VRM) to preserve early semantic processing while injecting artifact-specific visual signals as a residual path into an intermediate layer, where they are fused with semantic token representations and propagated through subsequent trainable layers. This enables later layers to jointly model semantic reasoning and signal-level forensic cues, and surprisingly, the model learns to adaptively leverage different levels of forensic signals depending on the input, achieving robust and generalizable detection performance. Extensive experiments show that our method achieves state-of-the-art across most benchmarks. The code and data are available at https://github.com/KQL11/Deep-VRM. --- ### Free Energy Heuristics: Fast-And-Frugal Cognition as Active Inference Under Uncertain Precision Authors: Alex Bogdan Published: 2026-06-14 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2606.15877v1 Chain-of-thought (CoT) improves large language models' performance in math and symbolic reasoning. But on planning, contested ethics, and tasks where the model cannot check itself, more reasoning makes things worse. Both effects are documented; what has been missing is a principled account of which property decides the outcome. We argue it is meta-uncertainty: how unsure the model is about the reliability of its own evidence. When that uncertainty is high, extra reasoning stops adding signal and starts manufacturing false confidence. We prove that the policy minimizing expected free energy under uncertain precision stops integrating cues after a finite number of high-validity ones when the precision prior is heavy-tailed (Theorem 2.6.1), and under a Descending Dominance condition, is sample-wise identical to take-the-best (Theorem 2.7.4). Fast-and-frugal heuristics and active inference are, then, two descriptions of the same computation. The prediction is that on high-meta-uncertainty items, longer CoT should degrade accuracy. We score the regime per item (simulate-and-recover rho > 0.96), build FEH-79, a benchmark of Knightian frames with matched controls, and run a pre-registered study across seven models (five open-weight 3B-32B, two frontier), five CoT lengths, and 7,875 responses. The gate, fixed before any data, required a negative interaction with posterior probability above 0.95 and an accuracy drop of more than 6 points. It held. The high-regime drop is 17.3 points (95% CI (7.7, 25.5)); matched items with definite answers show no cost. The effect is regime-dependent: decisive in capable mid-to-large models, directional in the two frontier systems, absent-to-reversed in the weakest. The framework answers when CoT helps and unifies the Bayesian and fast-and-frugal traditions: less-is-more effects are evidence about the meta-uncertainty regime, not against Bayesian cognition. --- ### LLM-as-Code: Agentic Programming for Agent Harness Authors: Junjia Qi, Zichuan Fu, Jingtong Gao, Wenlin Zhang, Hanyu Yan, Xian Wu, Xiangyu Zhao Published: 2026-06-14 Categories: cs.AI, cs.SE arXiv: https://arxiv.org/abs/2606.15874v2 Every major LLM agent framework gives the LLM the role of orchestrator; the model decides what to do next, when to call tools, and when to stop. We argue that token explosion, control-flow hallucination, and unreliable completion are not implementation bugs but architectural consequences of assigning the deterministic work of looping, branching, and sequencing to a probabilistic system. A better prompt or a stronger model cannot guarantee the reliability of the LLM agent. We therefore propose Agentic Programming, in which the program governs all control flow, and the LLM is itself part of it, an adaptive component we call LLM-as-Code and invoke only where a task calls for reasoning or generation. Within each call the model keeps full flexibility, but it cannot alter the program's execution path. With control in the program, the LLM's context is built from the execution history's call tree and forms a directed acyclic graph (DAG). Each call's context length is then determined by its call depth rather than by accumulation over steps. A case study of computer-use agents shows that the design is practical, not just a theoretical stance, substantially improving the stability of long visual operation sequences. --- ### SciOrch: Learning to Orchestrate Expert LLMs for Solving Frontier Multimodal Scientific Reasoning Tasks Authors: Jingru Guo, Xiangyuan Xue, Lian Zhang, Wanghan Xu, Siki Chen, Philip Torr, Wanli Ouyang, Lei Bai, Zhenfei Yin Published: 2026-06-14 Categories: cs.CL arXiv: https://arxiv.org/abs/2606.15872v1 Frontier scientific reasoning remains a major challenge for large language models (LLMs), where even the strongest commercial systems fall short of expert-level performance. A closer look at model behavior reveals substantial complementarity that single-model evaluation hides: different frontier models excel on different question types, and no single model captures the full picture. We present SciOrch, a framework that trains a lightweight 8B model to orchestrate frontier LLMs for scientific reasoning. The orchestrator decomposes each question, delegates sub-problems to selected commercial models through API calls, and synthesizes a final answer. Training such an orchestrator is fundamentally harder than conventional agentic RL: each action triggers an API call that is expensive in both dollar cost and latency, making standard online rollouts infeasible. We address this with MCTS-based approach, producing diverse orchestration trajectories, extracting per-node single-turn samples, and optimizing the orchestrator with GRPO-style training. On a 240-question test set spanning SGI-Reasoning and Scientists' First Exam, SciOrch reaches 56.66% average accuracy, outperforming the strongest single commercial model by 3.74% and the strongest multi-agent baseline by 3.33%. It also attains the best accuracy on both SGI and SFE with less than half the API cost of typical multi-agent methods. --- ### Amortized mean-shift interacting particles Authors: Ali Siahkoohi Published: 2026-06-14 Categories: stat.CO, cs.LG, stat.ML arXiv: https://arxiv.org/abs/2606.15871v1 Bayesian inference for inverse problems is run to evaluate integrals -- posterior expectations, tail probabilities, and risks -- across a stream of observations. The standard estimate averages the integrand over posterior samples, a Monte-Carlo average whose error decays only as the square root of the sample size, so accuracy demands many samples -- prohibitive when each one calls a partial-differential-equation forward model. Mean-shift interacting particles need far fewer: they return a small set of signed-weight nodes -- a deterministic quadrature whose weighted averages estimate those integrals. Finding the nodes, however, is a per-observation optimization that, in its most accurate form, reads the posterior score at every step -- returning the cost it meant to save. We introduce amortized mean-shift interacting particles, a learned map that emits the weighted nodes from an observation and a few posterior samples in a single forward pass. Training asks only for joint parameter-observation samples and a posterior to draw from -- a conditional normalizing flow, an empirical conditional, or any reference the user can sample -- and the map learns to integrate that posterior from samples alone, evaluating neither its density nor its score. Once trained, it generalizes to unseen observations and integrands at any node budget and improves on independent samples in two ways: by reweighting them, provably no worse than the equal weights of Monte-Carlo; and by moving them, which empirically lowers it further. Across closed-form, sampled, learned, and physics-based posteriors -- up to a thousand-coefficient groundwater field -- it integrates more accurately than the same number of samples at every budget, and a posterior-whitened, dimension-aware kernel removes the high-dimensional wall. The result is a Pareto improvement on Monte-Carlo integration, not a competitor to drawing more samples. --- ### Metis: A Generalizable and Efficient World-Action Model for Autonomous Driving and Urban Navigation Authors: Jingyu Li, Zhe Liu, Dongnan Hu, Junjie Wu, Zipei Ma, Wenxiao Wu, Chao Han, Zhihui Hao, Zhikang Liu, Kun Zhan, Jiankang Deng, Xiatian Zhu et al. Published: 2026-06-14 Categories: cs.CV arXiv: https://arxiv.org/abs/2606.15869v1 World action models~(WAMs) have shown great promise for autonomous driving and urban navigation. Built upon Vision-Language-Action models or video generation models, existing approaches suffer key limitations: (1) High inference latency due to future observation prediction at test time, and (2) tightly coupled video and action modeling leading to representational mismatch and degraded generalization. To address both issues, we propose Metis, an end-to-end WAM framework that decouples video generation and action prediction. Specifically, Metis employs a Mixture-of-Transformers architecture with dedicated experts for video generation and action prediction, preserving the intrinsic distributional properties of each task. To enhance efficiency, we introduce an asymmetric attention mask that enables joint training of both experts while allowing the action model to bypass explicit video generation during inference. This design ensures training-inference consistency and significantly reduces computational costs without compromising planning performance. Extensive experiments demonstrate state-of-the-art performance on the NAVSIM navhard and navtest benchmarks and the CityWalker navigation benchmark, validating both the generalizability and efficiency across diverse tasks. Real-robot deployments further confirm the practical feasibility of our approach. --- ### David vs. Goliath in Next Activity Prediction: Argmax vs. LSTM, Transformer, and LLM Authors: Hans Weytjens, Ingo Weber Published: 2026-06-14 Categories: cs.LG arXiv: https://arxiv.org/abs/2606.15868v1 Next activity prediction (NAP) is a cornerstone of predictive process monitoring (PPM), enabling organizations to move from retrospective analysis to proactive process steering. The PPM field has progressed from classical machine learning through deep learning architectures such as LSTMs and Transformers to large language models (LLMs). Despite growing model complexity, no benchmark jointly compares LLMs, Transformers, LSTMs, and simple baselines in a direct sequence modeling setting for NAP. In this paper, we fill this gap with a systematic benchmark. We compare vocabulary-adapted LLMs, Transformers trained from scratch, LLM-distilled Transformers, and LSTMs against a simple counting-based argmax baseline across seven real-life event logs. Our results tell a David vs. Goliath story: pretraining confers no consistent improvement over training from scratch, model size shows little effect on performance, and on most datasets the argmax baseline matches or approaches the performance of billion-parameter LLMs. --- ### CogCanvas: A Benchmark for Evaluating Multi-Subject Reference-Based Image Generation Authors: Long-Bao Nguyen, Quang-Khai Tran, Tam V. Nguyen, Minh-Triet Tran, Trung-Nghia Le Published: 2026-06-14 Categories: cs.CV arXiv: https://arxiv.org/abs/2606.15867v1 Multi-subject reference-based image generation requires jointly preserving multiple human identities, binding per-person objects and fashion items, and respecting a specified background scene, a regime where current diffusion models remain brittle. Existing benchmarks evaluate only one axis at a time and none jointly captures multi-identity composition with human-object interaction, background grounding, and spatial plausibility. We introduce CogCanvas, a benchmark of 1,952 curated reference images spanning 100 celebrity identities, 115 distinctive objects and fashion items, and 29 real-world background scenes including landmarks, from which we construct 1,361 compositional prompts covering 2-5 person group sizes. The curation pipeline combines DINOv2-based deduplication, two-stage aesthetic filtering, and automated derivation of structured interaction and position graphs that serve as ground-truth supervision. CogCanvas supports three tasks, reference-based multi-human-object generation (primary), text-to-image compositional generation, and reference retrieval, under a unified six-axis evaluation protocol. We introduce two metrics tailored to the multi-reference setting: BG-Sim, which scores background fidelity on SAM 3-masked regions via DINOv3 feature similarity, and Attr-VQA, which uses a multimodal LLM to verify per-subject attribute binding and inter-person interactions against the structured graphs. Benchmarking five SOTA methods reveals that every model degrades substantially as group size grows from 2 to 5, with near-complete failure on object/fashion binding beyond three subjects. --- ### STRIDE: Strategic Trajectory Reasoning via Discriminative Estimation for Verifiable Reinforcement Learning Authors: Qinjian Zhao, Zhihao Dou, Dinggen Zhang, Xiangyu Li, Chaoda Song, Zhongwei Wan, Xinpeng Li, Yanyan Zhang, Kaijie Chen, Qingtao Pan, Chengcheng Feng, Zhiqiang Gao et al. Published: 2026-06-14 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2606.15866v1 Reinforcement Learning with Verifiable Rewards (RLVR) has become an effective post-training paradigm for improving the reasoning abilities of large language models. However, existing RLVR methods typically rely on final-answer correctness to assign trajectory-level rewards, providing sparse supervision and treating all tokens uniformly regardless of their actual contribution to reasoning. Although recent studies introduce intermediate signals such as process rewards, high-entropy tokens, and semantic uncertainty, these signals are often not inherently verifiable and may fail to distinguish beneficial strategic patterns from harmful ones. To address this limitation, we propose STRIDE (Strategic Trajectory Reasoning with Discriminative Estimation), a fine-grained RLVR framework that derives strategic reasoning supervision from verifiable outcomes. STRIDE contrasts successful and failed trajectories within each response group to estimate the outcome-discriminative preference of each $n$-gram strategic pattern, and further combines this signal with reasoning saliency entropy to identify decision-relevant strategic patterns. These patterns are assigned differentiated advantage values during RL optimization, enabling more precise credit assignment while preserving the verifiability of RLVR. Extensive experiments demonstrate that STRIDE consistently improves reasoning performance across diverse models, tasks, and extended settings, including VLMs and agent-based systems. --- ### RetailBench: Benchmarking long horizon reasoning and coherent decision making of LLM agents in realistic retail environments Authors: Linghua Zhang, Jun Wang, Jingtong Wu, Zhisong Zhang Published: 2026-06-14 Categories: cs.AI arXiv: https://arxiv.org/abs/2606.15862v3 Large language model (LLM) agents have made rapid progress on short-horizon, well-scoped tasks, yet their ability to sustain coherent decisions in dynamic long-horizon environments remains uncertain. We introduce RetailBench, a data-grounded simulation benchmark for evaluating tool-using LLM agents in single-store supermarket operation. RetailBench models retail management as a partially observable decision process and is designed to support thousand-day-scale simulations. In this environment, agents must manage pricing, replenishment, supplier selection, shelf assortment, inventory aging, customer feedback, external events, and cash-flow constraints. We evaluate seven contemporary LLMs under representative agent frameworks over a 180-day evaluation horizon and compare them with a privileged oracle policy. Results show substantial variation across models: only a small subset survives the full evaluation horizon, and even the strongest LLM runs remain substantially behind the oracle policy in final net worth and sales outcomes. Behavioral analysis attributes these gaps to incomplete evidence acquisition, surface-level decision making, and the lack of a consistent long-horizon policy. RetailBench provides a controlled testbed for studying reliable autonomy in economically grounded long-horizon decision-making. --- ### Object Tokens as a Bridge Between Segmentation and Visual Question Answering in Robotic Surgery Authors: Yiping Li, Ronald de Jong, Romy van Jaarsveld, Franco Badaloni, Gino Kuiper, Jelle Ruurda, Josien Pluim, Marcel Breeuwer Published: 2026-06-14 Categories: cs.CV arXiv: https://arxiv.org/abs/2606.15861v1 Visual Question Answering (VQA) in robotic surgery, referred to as surgical VQA, requires high-level understanding of complex surgical scenes and the integration of visual perception with language reasoning, with the potential to support surgical training and intraoperative decision-making. Recent Vision-Language Models (VLMs) have shown promising performance through parameter-efficient fine-tuning; however, most existing approaches rely on coarse visual grounding, typically limited to bounding boxes, which fails to capture the fine-grained spatial structure of surgical objects. In this work, we propose a unified framework that jointly performs pixel-level segmentation and visual question answering within a single framework. Our approach integrates a VLM with a Segment Anything Model (SAM)-based decoder and represents scene elements as object tokens generated by the VLM. These object tokens guide answer prediction and are further projected to the SAM-based decoder to produce segmentation masks. By optimizing the object token embeddings through both segmentation and question answering objectives, the model learns spatially grounded representations that enhance visual reasoning while providing explicit pixel-level grounding. We evaluate the proposed method on the private RAMIE (Robot-Assisted Minimally Invasive Esophagectomy) dataset and the public EndoVis18 dataset, where it consistently outperforms baseline methods for surgical VQA. These results demonstrate that incorporating context-aware object tokens into vision-language models improves fine-grained surgical scene understanding. ---