# Research Papers — 2026-06 · bundle page 92 of 260 > Full-text markdown of papers #4551–4600 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/92 [← Previous bundle](https://aipod.dev/papers/archive/2026-06/page/91.md) [Next bundle →](https://aipod.dev/papers/archive/2026-06/page/93.md) ### Real-time pedestrian attribute recognition with YOLOv8 and ResNet18 Authors: Houssam El Mir Published: 2026-06-19 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2606.21200v1 Pedestrian attribute recognition (PAR) assigns semantic labels to detected pedestrians and is useful in surveillance, video retrieval, and human-centered graphics applications. This paper presents a two-stage framework in which YOLOv8n detects pedestrians and ResNet18-based models classify gender, estimate apparent age, and predict 61 binary attributes from each pedestrian crop. PETA and PA-100K are combined through semantic attribute mapping, producing a unified training corpus of more than 100,000 pedestrian images while retaining the PETA attribute space. On the reported test splits, the system obtains 99.89% gender classification accuracy, a 4.23-year apparent-age mean absolute error, and 89.96% multi-attribute accuracy with a 36.32% macro F1-score and 58.80% micro F1-score. Runtime measurements indicate 25-30 FPS on an NVIDIA RTX 5060 GPU. The results show that a lightweight detector-classifier pipeline can support real-time PAR, while low macro F1 indicates that rare attributes remain challenging. --- ### Orthogonal Discrepancy Kernels for Learning with Partial Physics Authors: Swapnil Manna, Timothy J. Rogers, Lawrence Bull Published: 2026-06-19 Categories: stat.ML, cs.LG, eess.SP arXiv: https://arxiv.org/abs/2606.21199v2 We introduce a semi-parametric framework for nonlinear system identification, which decouples discrepancy functions from physics-based components. Orthogonal Gaussian process regression balances sparse parameter selection (the white box) with discrepancy learning (the black box) to produce interpretable models from incomplete physics. --- ### Extraction and Analysis of Multimodal Concepts in Vision Language Models through Sparse Autoencoders Authors: Sergio Lanza, Jae Hee Lee, Stefan Wermter Published: 2026-06-19 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2606.21197v1 Vision Language Models (VLMs) have demonstrated impressive performance in tasks requiring joint understanding of images and text, such as image captioning and Visual Question Answering (VQA), but our understanding of their internal processes remains limited. Recently, Sparse Autoencoders (SAEs) have emerged as a promising tool to support the interpretation of concepts encoded in VLMs. However, most SAE-based approaches focus only on textual or visual concepts separately, ignoring multimodal concepts. This limitation hinders a comprehensive understanding of VLMs, since concepts that integrate both modalities can be misclassified. Moreover, previous visual approaches often produce low-quality visual concept descriptions that are vague or incomplete, limiting their usefulness for understanding model reasoning. We propose a framework based on SAEs to extract and analyze visual, textual, and multimodal concepts from VLMs. For each neuron, we propose a candidate human-interpretable concept and compute the alignment between the concept and the dataset samples using cosine similarity scores. Experiments on a VQA dataset (LLaVA-NeXT) demonstrate that our framework improves visual concept quality by up to 45\% compared to existing SAE-based methods, while maintaining high textual concept quality and enabling systematic identification of multimodal concepts. This work contributes new insights into the conceptual space of VLMs, providing a structured approach to distinguish between visual, textual, and multimodal concepts. The code is available at https://github.com/PHDLanza/Multidata_SAE --- ### Beyond Hooking Onto the World: Referential Profiles and the Numerical Structure of LLM Grounding Authors: Joo Yull Rhee Published: 2026-06-19 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2606.21195v1 This paper revisits the grounding problem for large language models in light of recent vector-grounding accounts. I accept the shift from classical symbol grounding to vector grounding, but argue that the current debate remains incomplete in two respects. First, reference is often treated too thinly, as if it were a fixed link between an isolated expression and an object. I argue instead that reference is profile-based, context-sensitive, discourse-level, affectively shaped, and norm-governed. Even in the human case, reference is publicly stabilized through patterns of use, correction, distinction, inference, and continuation rather than through identical private representations. Second, vector grounding requires an account of numerical realization. LLMs do not acquire reference through human perception, memory, intention, embodiment, or understanding. Rather, through optimization, they parameterize linguistic traces of human world-directed practice. In a finite vector system, referential profiles must be distributed, may be superposed, and are recovered through context-sensitive computation. Weights, activations, attention-mediated hidden states, softmax-trained contrasts, and inner-product alignments are the mathematical sites at which inherited linguistic relations become stable and causally active. Mechanistic interpretability findings, including entity-like features, knowledge neurons, and emotion-related activation directions, provide indirect support for this view. They do not show that LLMs possess human reference. They support a more limited thesis: LLMs may possess derivative, language-mediated, profile-based, and numerically structured forms of reference. --- ### MEDLAYXPLAIN: Benchmarking the Expert-Lay Gap in Medical Vision-Language Models Authors: Han Jang, Junhyeok Lee, Songsoo Kim, Chae Young Lim, Hyeonjin Goh, Heeseong Eum, Kyu Sung Choi Published: 2026-06-19 Categories: cs.CV, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2606.21194v1 Medical Vision-Language Models (Med-VLMs) achieve strong expert-level performance, yet their ability to generate patient-accessible descriptions remains underexplored. With the 21st Century Cures Act now mandating immediate patient access to diagnostic imaging results, evaluating whether Med-VLMs can bridge this Expert-Lay Gap is both urgent and clinically consequential for patient education and shared decision-making. To this end, we introduce MedLayXPlain, the first large-scale multimodal benchmark and evaluation framework for Medical Lay Language Generation (MLLG). MedLayXPlain-122K provides 122,789 region-grounded samples across 8 imaging modalities from 12 publicly available source datasets, each comprising a medical image with paired expert and lay captions anchored in a three-level Unified Medical Language System (UMLS) ontology hierarchy spanning 7 semantic groups, 43 semantic types, and 2,411 medical concepts. Lay captions are constructed via Hierarchical Ontology-Verified Refinement (HOVER), a three-step pipeline combining patient-centric vocabulary mapping, LLM-based constrained rewriting, and cross-model visual verification to enforce semantic equivalence while preventing hallucination. We further introduce MedLayEval, a lightweight 3B evaluator distilled from a 27B verifier that scores expert-lay alignment across five clinically grounded attributes, addressing the poor correlation between standard NLG metrics and clinical judgment. Benchmarking 33 VLMs on MedLayXPlain-122K reveals a systematic Expert-Lay Gap: medical VLMs achieve strong expert captioning but suffer significant lay-register degradation, while general-purpose VLMs produce more accessible language yet lack clinical precision, confirming that neither current paradigm adequately serves patient-facing communication. --- ### TF-SNO: Time-Frequency Gated Spectral Neural Operators for Learning Non-Stationary Partial Differential Equations Authors: Yitian Zhou, Chaoning Zhang, Zhenzhen Huang, Haoxuan Yu, Jiaquan Zhang, Yiran Li, Fan Mo, Kuien Liu, Jie Zou, Caiyan Qin, Yang Yang Published: 2026-06-19 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2606.21189v1 Non-stationary partial differential equations (PDEs) arise throughout scientific computing, where the dominant frequency content and energy distribution can drift over time. While efficient in PDE solving, many spectral neural operators apply a shared spectral response across rollout stages, leading to mismatch with time-varying spectra in non-stationary systems. To address this issue, we propose Time-Frequency Gated Spectral Neural Operator (TF-SNO), a state-adaptive framework with learnable time-frequency gating inside spectral blocks. TF-SNO extracts compact frequency-domain and physical-space statistics from the current state to generate modulation coefficients, enabling the spectral response to evolve with the dynamics. TF-SNO learns temporal variation implicitly from the evolving state without introducing an explicit time dimension or time embedding, keeping the modeling complexity low. We further embed the adaptive operator blocks to accurately capture the multi-scale features, thereby improving long-horizon stability. Experiments on six non-stationary PDE benchmarks in 1D and 2D demonstrate that TF-SNO significantly reduces prediction errors and improves robustness compared to strong baselines, with particularly clear gains in long rollout, suggesting the effectiveness of state-dependent spectral adaptation in modeling non-stationary physical systems. --- ### Two Layers of Instability in Causal Estimation Authors: Alexis Bellot Published: 2026-06-19 Categories: stat.ML, cs.LG, stat.ME arXiv: https://arxiv.org/abs/2606.21185v2 There is a precise sense in which drawing causal inferences from observational data is hard, even when identifiability is assumed. In particular, Robins and Ritov (1997) and Robins et al. (2003) showed that causal effects can be discontinuous as a function of the data distribution: two arbitrarily close data distributions might correspond to different causal effects. This is a fact independent of the choice of estimator; however, not all estimators are equally unstable. Our contribution is to surface a second layer of instability that depends on the choice of estimator. We show that many standard point estimates can be read as point summaries of multimodal distributions over the space of structural causal models. As such, estimators can jump discontinuously in the data distribution. This defines a taxonomy of estimators that admits a decision-theoretic reading: stability depends on whether the implicit loss function an estimator optimizes is aligned with the causal effect itself. Specifically, inverse propensity weighted estimators and regression estimators are examples of discontinuous summaries, while explicit posterior means and medians are shown to be continuous. --- ### Rejections Based on Predictive Uncertainty Enable Reliable Routine Soil Spectroscopy Authors: Jonas Schmidinger, Robin Gebbers, Marc-Olivier Gasser, Viacheslav Barkov, G. Mick Wu, Viacheslav I. Adamchuk Published: 2026-06-19 Categories: cs.LG arXiv: https://arxiv.org/abs/2606.21179v1 Soil properties relevant to agricultural and environmental applications are conventionally measured using elaborate laboratory methods involving physical and chemical processing. While highly accurate, these conventional methods are costly and time-consuming. In contrast, optical spectroscopy paired with machine learning enables rapid and cost-effective predictions of multiple soil properties. However, spectroscopic modelling is often considered unreliable, as the predictive accuracy varies between soil properties and individual samples. To balance this trade-off between cost and reliability, we introduce reject-to-remeasure: an AI-based measurement framework that combines probabilistic modelling with uncertainty-guided rejection. In this framework, soil samples are first analysed using spectroscopy, after which predictions are rejected if their predictive uncertainty exceeds predefined quality constraints. Rejected samples are subsequently remeasured using conventional laboratory procedures. On a regional visible-near-infrared spectral soil library from Québec, we demonstrate that reject-to-remeasure with modern foundation models (TabPFNv2.5 and TabICLv2) can facilitate the integration of optical spectroscopy into routine laboratory workflows while meeting user-defined accuracy requirements and reducing measurement costs. --- ### Anatomically Consistent TMJ Disc Segmentation via Semantic Anchoring and Clinical Priors Authors: Dayun Ju, Chanyoung Kim, Sunyoung Jung, Hyo-Jung Jung, Chena Lee, Younjung Park, Seong Jae Hwang Published: 2026-06-19 Categories: eess.IV, cs.AI, cs.CV, physics.med-ph arXiv: https://arxiv.org/abs/2606.21177v1 Segmenting the temporomandibular joint (TMJ) disc from MRI is essential for accurate diagnosis of internal derangement, yet it remains unreliable in practice due to its small size, low contrast, and morphological variability. Existing methods, primarily adapted from general segmentation architectures, often produce fragmented or anatomically inconsistent masks, leading to unstable measurements of disc position and shape for downstream diagnosis. To address these challenges, we propose TISC, a TMJ disc segmentation framework that integrates semantic anchoring with clinical metadata-guided boundary refinement. The framework first establishes robust disc localization in the foundation model feature space via a Prototypical Semantic Anchoring (PSA) module that aggregates adjacent-slice MedDINOv3 features and derives a prototype-driven similarity map. It then performs targeted boundary refinement through a Clinical-Metadata Point Refinement (C-MPR) module, with point-wise predictions modulated by Mouth Open Limitation (MOL), a clinical indicator associated with disc displacement without reduction. On a large-scale cohort of 2,488 PD MRI volumes from 1,300 patients, our method achieves up to a 4.96 Dice improvement over strong baselines across diverse architectures, delivering more anatomically coherent and clinically reliable TMJ disc segmentation. --- ### HERO: Hypothesis-Driven Evidence Retrieval from Omics for Multi-Task Breast Cancer Analysis Authors: Xiangyu Li, Ran Su Published: 2026-06-19 Categories: cs.CV, q-bio.GN arXiv: https://arxiv.org/abs/2606.21174v1 Matched multi-omics can improve WSI-based biomarker and prognosis prediction, but most existing pipelines use omics as a paral lel feature stream or textual context rather than as an explicit retrieval constraint. HERO asks whether observed omics can be a testable mor phology hypothesis: a sparse pathway-to-morphology prior maps DNA methylation and miRNA into a K-dimensional intent vector m (K=16), TF-IDF retrieval over structured 10 captions selects endpoint-relevant regions, and a cosine gate c=cos(m,v) triggers deterministic deficit driven repair when c<τc. This closed-loop design bounds VLM calls, reduces reliance on embedding-based semantic matching, and makes every retrieval and verification step lexically auditable. On TCGA-BRCA (930WSIs, patient-level 5-fold CV), HERO sets new state-of-the-art across ER, PR, HER2, subtype, and risk prediction, outperforming both multimodal fusion and VLM-based baselines. --- ### Inverting the Bellman Equation: From $Q$-Values to World Models Authors: Alistair Letcher, Mattie Fellows, Alexander D. Goldie, Jonathan Richens, Jakob N. Foerster, Oliver Richardson Published: 2026-06-19 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2606.21173v1 Model-based and model-free reinforcement learning are traditionally viewed as separate paradigms: instead of learning a model of the transition kernel $P$, model-free agents typically estimate value functions tied to a specific policy and reward. In this paper, we challenge this dichotomy by proving that value-based agents trained on a sufficiently rich set of reward functions, e.g. using goal-conditioned RL, implicitly encode a unique and accurate world model. To extract this model in practice, we introduce \textit{$P$-learning}, an inverse analogue to $Q$-learning that samples from an agent's $Q$-values, policies and rewards to decode its internal model of the environment. We then provide sufficient conditions on the type and number of goals for which agents encode the true kernel $P$, covering both stochastic and deterministic MDPs over finite or continuous state spaces. Even when our assumptions are violated, we empirically demonstrate that agents trained on a handful of reward functions encode accurate dynamics in $\texttt{Reacher}$, $\texttt{MountainCar}$ and stochastic variants of $\texttt{FourRooms}$. Surprisingly, we find that policies trained exclusively on a \texttt{Reacher} agent's implicit world model are quasi-optimal on out-of-distribution, velocity-based goals despite position-only training -- suggesting that agents contain hidden generalisation capabilities and providing a new lens into the connection between model-based, model-free, and goal-conditioned RL. --- ### BadDreamer: Transferable Backdoor Attacks against Video World Models for Autonomous Driving Authors: Zhe Shuai, Xiaopeng Xie, Yikun Zeng Published: 2026-06-19 Categories: cs.CV arXiv: https://arxiv.org/abs/2606.21172v1 Video world models are increasingly used in autonomous driving to forecast future scene evolution and provide future-aware spatio-temporal representations for downstream action prediction. In perception-to-action pipelines, these representations can directly influence ego-vehicle waypoint planning, making the learned future dynamics a critical security-sensitive component. Despite their promise, the training-time security risks of autonomous-driving video world models remain largely unexplored. We present BadDreamer, a transferable spatio-temporal backdoor attack that targets the perception side of this pipeline. Unlike conventional backdoors that manipulate image labels, prompt outputs, or action supervision, BadDreamer poisons the learned transition dynamics of a video world model. It constructs trigger-erasure sequences in which an oncoming yellow delivery rider is visible in the observed context frames but erased from the future frames. After fine-tuning on a small fraction of such sequences, the compromised world model learns a hidden conditional association: when the physical trigger appears, it hallucinates a future where the rider disappears and the road appears clear. We further show that this corrupted future-aware representation can transfer to the downstream action module without directly modifying ego-trajectory labels, inducing unsafe non-evasive waypoint predictions. Our experiments instantiate this attack on a representative open-source perception-to-action pipeline, revealing a representation-level safety risk in autonomous-driving video world models and highlighting the need for backdoor-aware validation beyond clean generation quality. --- ### An Exploratory Case Study of LLM-Assisted Refactoring and Gameplay Feature Generation in an Endless Runner Game Authors: Jan Wunderlich, Markus Kleffmann, Sebastian Lempert Published: 2026-06-19 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2606.21171v1 Large language models (LLMs) are increasingly used to support software development, but their practical usefulness in applied game-development settings remains underexplored, especially when generated code must be integrated into an existing game software system. This paper presents an exploratory empirical case study of GPT-4o in a custom Python/Pygame endless runner. The study examines six selected development tasks: three localized refactoring tasks and three tasks involving gameplay feature generation. The resulting implementations were evaluated using software metrics, unit tests, and manual gameplay assessments. In this case study, all three selected refactoring tasks were completed successfully in functional terms, whereas only one of the three selected gameplay feature generation tasks resulted in a correctly integrated feature. The findings suggest that, in this setting, GPT-4o handled localized transformations more reliably than tasks requiring new gameplay interactions across multiple existing systems. Given the exploratory single-case design, these results are best interpreted as indicative observations rather than as generalizable evidence of category-level model performance. Overall, the paper contributes a transparent case-based account of the opportunities and limitations of LLM-assisted refactoring and gameplay feature generation in an existing game software system. --- ### Trip+: Benchmarking Agents in Personalized Interactive Travel Planning Authors: Junle Chen, Wei Chen, Yehong Xu, Zhengjun Huang, Yuqian Wu, Zhoujin Tian, Kai Wang, Lei Wang, Xiaofang Zhou Published: 2026-06-19 Categories: cs.AI arXiv: https://arxiv.org/abs/2606.21169v1 Interactive travel planning has become a popular use case for language models. Agents are deployed to manage evolving preferences and unexpected disruptions over multiple turns. Such settings require models to make complex, profile-conditioned planning decisions. However, existing benchmarks often evaluate feasibility, personalization, or interaction in relatively isolated settings. We therefore introduce Trip+ to measure the ability of agents to plan travel holistically. In Trip+, given traveler profiles and dynamic interactions, agents must generate and revise minute-level itineraries. End-to-end traveler experiences are evaluated via an LLM-based simulator, enabling the assessment of subjective metrics like fatigue. Our scenarios range from simple request resolutions to complex environment-driven replanning. We evaluate 18 LMs and find a consistent gap in experiential quality. Models favor technically feasible but exhausting itineraries that diverge sharply from profiled traveler preferences. --- ### Dementia-Agents: A Multi-Modal Multi-Agent System for Dementia Staging and Phenotyping Authors: Yaling Shen, Maja Christensen, Yiwen Jiang, Jenna Dennison, David Darby, Amy Brodtmann, Zongyuan Ge Published: 2026-06-19 Categories: cs.CL arXiv: https://arxiv.org/abs/2606.21168v1 Dementia diagnosis requires integrating multi-modal clinical assessments from diverse informants and clinicians under incomplete and heterogeneous data conditions. Yet most AI-driven approaches remain Alzheimer's disease (AD)-centric, framing the problem as binary AD detection or three-stage AD progression modeling within well-curated research settings. This pathology-driven paradigm overlooks the broader, syndrome-level nature of dementia, which spans multiple stages, phenotypes, and etiologies. In this paper, we propose Dementia-Agents, a clinically aligned multi-agent framework for real-world dementia staging and phenotyping. The framework follows a three-step workflow: (1) a data agent translates structured clinical records into semantically faithful textual representations that preserve missing-data signals and routes them to domain-aligned experts; (2) five fine-tuned expert agents generate domain-level predictions; and (3) a coordinator agent performs probabilistic aggregation to produce final staging and phenotyping decisions. We develop and evaluate Dementia-Agents on a real-world clinical cohort of 1,066 patients from two cognitive neurology services. Compared with monolithic multi-modal large language models (MLLMs) and prior medical multi-agent systems, our approach achieves consistent improvements in diagnostic performance for real-world syndrome-level dementia staging and phenotyping, while preserving domain-level interpretability. --- ### OmniV2X: A Generative Foundation Planner for Efficient End-to-End Cooperative Driving Authors: Juntong Peng, Juanwu Lu, Yupeng Zhou, Can Cui, Yaobin Chen, Ziran Wang Published: 2026-06-19 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2606.21165v2 We present OmniV2X, a generative foundation model for vehicle-to-everything (V2X) cooperative driving. The model directly interprets independent context sequences comprising multi-modal and multi-agent observations. The new design mitigates the computational cost of dense 3D perception, the vulnerability to data scarcity in cooperative scenarios, and the poor compliance with standardized messaging in existing methods that fuse multi-modal inputs into a shared representation. For training, we present an end-to-end supervised pipeline using a downstream trajectory generation loss, in which a high-capacity generative sequence planner implicitly learns to steer the model and leverage multi-modal inputs via cross-attention injection. As a foundation model, we demonstrate that OmniV2X pre-trained on large-scale single-agent planning datasets can efficiently adapt to cooperative environments by integrating the conditioning context with lightweight, standard-compliant V2X tokens. Evaluated on the DAIR-V2X-Seq dataset, OmniV2X outperforms existing end-to-end cooperative driving baselines, achieving state-of-the-art performance with less than 10% of the fine-tune V2X dataset and less than 1% of the communication bandwidth. We conduct comprehensive evaluations to demonstrate its computational efficiency and robustness under real-world constraints. --- ### OmniV2X: A Generative Foundation Planner for Efficient End-to-End Cooperative Driving Authors: Juntong Peng, Juanwu Lu, Yupeng Zhou, Can Cui, Yaobin Chen, Ziran Wang Published: 2026-06-19 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2606.21165v1 We present OmniV2X, a generative foundation model for vehicle-to-everything (V2X) cooperative driving. The model directly interprets independent context sequences comprising multi-modal and multi-agent observations. The new design mitigates the computational cost of dense 3D perception, the vulnerability to data scarcity in cooperative scenarios, and the poor compliance with standardized messaging in existing methods that fuse multi-modal inputs into a shared representation. For training, we present an end-to-end supervised pipeline using a downstream trajectory generation loss, in which a high-capacity generative sequence planner implicitly learns to steer the model and leverage multi-modal inputs via cross-attention injection. As a foundation model, we demonstrate that OmniV2X pre-trained on large-scale single-agent planning datasets can efficiently adapt to cooperative environments by integrating the conditioning context with lightweight, standard-compliant V2X tokens. Evaluated on the DAIR-V2X-Seq dataset, OmniV2X outperforms existing end-to-end cooperative driving baselines, achieving state-of-the-art performance with less than 10% of the fine-tune V2X dataset and less than 1% of the communication bandwidth. We conduct comprehensive evaluations to demonstrate its computational efficiency and robustness under real-world constraints. --- ### PIAvatar: Physically Interactive Avatars via Deformation Gradient Decoupling Authors: Sang-Hun Han, Min-Gyu Park, Jisu Shin, Seunghyun Shin, Jin-Hwi Park, Hae-Gon Jeon Published: 2026-06-19 Categories: cs.GR, cs.CV arXiv: https://arxiv.org/abs/2606.21162v2 3D human avatars have shown impressive visual fidelity driven by pose-conditioned models, yet they still lack the physical ability required for interactions with each other and environments. Although recent studies have made various attempts to incorporate physical characteristics into 3D avatars, they only exhibit limited physical deformations, often leading to constrained interaction behaviors. To resolve this issue, we present PIAvatar, a framework to simultaneously enable physically aware interactions between avatar-avatar and avatar-environment, and a non-rigid deformable human body simulation. In this work, our key insight is to decouple kinematic velocity from deformation gradient. When external forces act on avatars, the kinematic velocity induces stress which hinders the avatar's ability to achieve a desired pose. In addition, we integrate a skeletal framework within the avatar. It allows estimating its poses and real-time tracking in a closed form, even during non-rigid physical interactions. Our approach is implemented within a conventional Material Point Method framework to ensure physically consistent dynamics. We lastly evaluate the method on both human-object and human-human interaction scenarios to assess its behavior under diverse interaction settings. --- ### On the Use of Survival Selection Methods for Evolutionary Diversity Optimisation Authors: Adel Nikfarjam, Jakob Bossek, Aneta Neumann, Frank Neumann Published: 2026-06-19 Categories: cs.NE arXiv: https://arxiv.org/abs/2606.21161v1 Generating a diverse set of high quality solutions for an optimisation problem has been studied extensively in recent years by the evolutionary computation community. A paradigm that has received increasing attention is evolutionary diversity optimisation (EDO), where the goal is to maximise the diversity of a solution set subject to quality constraints. Since the contribution of each solution to the diversity of the population depends on other solutions and can change dramatically if several solutions in the population are modified simultaneously, most EDO approaches generate a single new solution per generation and discard the solution with the least contribution to diversity, ensuring a steady increase in population diversity over successive generations until convergence. In this study, we aim to answer two questions: (1) Is generating multiple solutions in each generation beneficial for EDO? (2) How can this be achieved efficiently, given that conventional survival selection methods do not work well in EDO due to the dependency of a solution's contribution to diversity on other solutions? --- ### Dead-Direction Signatures: A Cheap Spectral Reading of Singular Complexity Authors: Tejas Pradeep Shirodkar, P. J. Narayanan Published: 2026-06-19 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2606.21158v1 Singular learning theory characterises the complexity of a deep network through the geometry of its loss singularities. The local learning coefficient (LLC), the standard estimator of Watanabe's real log canonical threshold (RLCT, $λ$), reads this geometry as an integrated Bayesian scalar through SGLD, which needs per-task calibration and $10^4$-$10^6$ forward-backward passes per checkpoint. We introduce Dead-Direction Signatures (DDS), a family of cheap closed-form spectral readings of singular structure: each reads a network's activation matrix or per-sample-gradient Fisher-Gram at a chosen layer, replacing the SGLD posterior chain with spectral linear algebra. The readings rest on a dead-direction framework that predicts a structural correlation between activation- and Fisher-side spectra at any singular minimum, and a rank-multiplicative volume identity that single-eigenvalue monitors cannot produce: the active-volume $\log\det^{+}(G)$ slope counts the dead directions, tracking the rank-deficit $r$ across $r \in \{1,2,3,4\}$ (slope ratios $2.0, 3.1, 4.0$ at $r{=}2,3,4$ against the predicted $2,3,4$), where the smallest eigenvalue is rank-blind. On reduced-rank regression with closed-form $λ$, calibrated LLC recovers $λ$ at $99\%$ mean and the DDS observables rank-track it at the framework-predicted sign; on a non-linear modular-addition transformer DDS separates $d_{\mathrm{model}}$ across eighteen orders of magnitude where calibrated LLC at the protocol budget is rank-flat. Complementary to LLC's integrated posterior reading, DDS gives a directional, layer-local handle on a network's dead directions, read in closed form from its activation and gradient spectra. --- ### Contrastive and Adaptive Multi-modal Masked Autoencoder for Spatial Transcriptomics Authors: Joohyeok Kim, Taejin Jeong, Jinyeong Kim, Seong Jae Hwang Published: 2026-06-19 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2606.21156v1 The high cost of spatial transcriptomics (ST) has driven extensive studies into predicting gene expression directly from H&E histology images. However, this prediction task faces an inherent limitation, as tissue morphology alone provides insufficient information to fully resolve underlying gene expression. To address this limitation, a recent study leverages partial gene expression to guide the prediction process alongside histology images. Building on this paradigm, we approach the prediction task as a spatial imputation problem, employing a Masked Autoencoder (MAE) to utilize a small fraction of gene expression as genetic anchors for inferring whole-slide gene expression profiles. Specifically, we propose a bio-saliency score and a learning-to-rank strategy to adaptively identify the most informative spots within the tissue. Based on these identified spots, our framework selects contiguous regions as genetic anchors to ensure suitability for real-world ST profiling hardware. To effectively leverage these anchors, we design a cross-modal joint encoder that integrates visual and genetic modalities. By aligning the selected anchors with their corresponding visual features via contrastive learning, the encoder generates robust joint representations to accurately predict gene expression across the whole slide. Notably, our framework consistently surpasses existing methods in both histology-only prediction and spatial imputation, achieving superior accuracy even without genetic anchors and further excelling with as little as 10% transcriptomic coverage. Our code is available at https://github.com/Kyyle2114/CAMMST. --- ### Who Checks the Citations? Benchmarking Legal Hallucination Detection Authors: Patty Liu, Dominik Stammbach, Peter Henderson Published: 2026-06-19 Categories: cs.CL arXiv: https://arxiv.org/abs/2606.21155v2 Attorneys, judges, and pro se filers increasingly use AI to draft legal documents, yet these tools frequently fabricate citations. Despite predictions that newer models would hallucinate less or that court sanctions would deter negligent filers, we found over 1,000 filings containing fabricated citations---with this number growing year-over-year. This study evaluates whether AI-based systems can mitigate these errors by automatically detecting hallucinations. We propose a taxonomy of legal citation hallucinations grounded in actual court filings and introduce a dataset of 1,300 brief excerpts containing injected errors. Benchmarking five models in agentic and non-agentic settings as well as Claude Code reveals that while the latest iterations perform better---GPT-5 achieves 84.4% recall and a 55.0% F1 score in an agentic framework---all models struggle with subtle error categories. Agentic verification remains resource-intensive, with GPT-5 averaging 15.3 steps per excerpt. Furthermore, restricted information access limits the efficacy of even the best agents. This gap creates policy concerns, as it disadvantages both AI systems and litigants who lack subscriptions to commercial legal databases. Together, our dataset, tools, and policy recommendations provide a foundation for building and auditing reliable legal citation checking tools. --- ### DUET: Decentralized Bilevel Optimization without Lower-Level Strong Convexity Authors: Zhen Qin, Zhuqing Liu, Songtao Lu, Yingbin Liang, Jia Liu Published: 2026-06-19 Categories: math.OC, cs.LG arXiv: https://arxiv.org/abs/2606.21153v1 Decentralized bilevel optimization (DBO) provides a powerful framework for multi-agent systems to solve local bilevel tasks in a decentralized fashion without the need for a central server. However, most existing DBO methods rely on lower-level strong convexity (LLSC) to guarantee unique solutions and a well-defined hypergradient for stationarity measure, hindering their applicability in many practical scenarios not satisfying LLSC. To overcome this limitation, we introduce a new single-loop DBO algorithm called diminishing quadratically-regularized bilevel decentralized optimization (DUET), which eliminates the need for LLSC by introducing a diminishing quadratic regularization to the lower-level (LL) objective. We show that DUET achieves an iteration complexity of $O(1/T^{1-5p-\frac{11}{4}τ})$ for approximate KKT-stationary point convergence under relaxed assumptions, where $p$ and $τ$ are control parameters for LL learning rate and averaging, respectively. In addition, our DUET algorithm incorporates gradient tracking to address data heterogeneity, a key challenge in DBO settings. To the best of our knowledge, this is the first work to tackle DBO without LLSC under decentralized settings with data heterogeneity. Numerical experiments validate the theoretical findings and demonstrate the practical effectiveness of our proposed algorithms. --- ### Context-Aware Generative AI for Automated Telecom Test Script Generation Authors: Gautam Prasad, Chandramohan T. N., Joy Bose Published: 2026-06-19 Categories: cs.SE, cs.AI, cs.NI arXiv: https://arxiv.org/abs/2606.21151v1 Automated test generation for telecom software systems and networks has advanced significantly with the adoption of machine learning and rule-based approaches. However, most existing solutions generate static test suites against a snapshot of the system; as code, configurations, topologies, and key performance indicators (KPIs) evolve, these tests quickly become outdated or misaligned with the live system. There is currently no widely adopted solution that continuously detects fine-grained changes and selectively adapts only the affected tests without regenerating entire test suites. This paper presents a context-aware generative AI framework for automated telecom test script generation that treats testing as a continuously adapting process driven by the current state of the system rather than a static artifact. The central contribution is delta-conditioned test generation over a live knowledge graph: our approach employs a continuously updated knowledge graph (KG) as a single source of truth, a delta engine for fine-grained change detection, and a KG-guided generative AI agent, operating via the Model Context Protocol (MCP), to create, update, or retire test cases automatically. We further integrate Retrieval-Augmented Generation (RAG) to enrich reasoning with telecom-domain knowledge and historical artifacts. We demonstrate applicability across software-system and telecom-network use cases, including a Python-based KPI monitoring application managed in GitLab, and show how the framework reduces manual effort, improves test relevance, and accelerates test cycles. --- ### AOR-Bench: Do Large Audio Language Models Over-Refuse Pseudo-Harmful Queries? Authors: Jiaxi Yang, Chaewan Chun, Jason Lucas, Yuchen Yang, Dongwon Lee Published: 2026-06-19 Categories: cs.SD, cs.AI arXiv: https://arxiv.org/abs/2606.21147v2 Large Audio Language Models (LALMs) have demonstrated strong performance across a wide range of audio tasks. As they are increasingly deployed in real-world applications, ensuring their safety alignment has become more important. Although refusal mechanisms serve as a key safeguard by preventing LALMs from responding to harmful requests, they can also lead to over-refusal, where models incorrectly reject benign queries. This issue is especially challenging in the audio domain because speech that appears harmful in isolation may become benign when interpreted together with the surrounding acoustic context, such as background sounds. To study this problem, we introduce AOR-Bench (Audio Over-Refusal Benchmark), the first benchmark for over-refusal specifically designed for LALMs. AOR-Bench contains 3,000 pseudo-harmful audio samples across six scenario categories. Evaluating 12 representative LALMs from six major model families, we find that over-refusal is widespread (Figure 1) and uncover several important patterns in their safety judgments. As a preliminary effort to mitigate this issue, we further explore two lightweight strategies (e.g., Chain-of-Thought and activation steering) to reduce over-refusal. --- ### AOR-Bench: Do Large Audio Language Models Over-Refuse Pseudo-Harmful Queries? Authors: Jiaxi Yang, Chaewan Chun, Jason Lucas, Yuchen Yang, Dongwon Lee Published: 2026-06-19 Categories: cs.SD, cs.AI arXiv: https://arxiv.org/abs/2606.21147v1 Large Audio Language Models (LALMs) have demonstrated strong performance across a wide range of audio tasks. As they are increasingly deployed in real-world applications, ensuring their safety alignment has become more important. Although refusal mechanisms serve as a key safeguard by preventing LALMs from responding to harmful requests, they can also lead to {\em over-refusal}, where models incorrectly reject benign queries. This issue is especially challenging in the audio domain because speech that appears harmful in isolation may become benign when interpreted together with the surrounding acoustic context, such as background sounds. To study this problem, we introduce \textbf{AOR-Bench} (\textbf{A}udio \textbf{O}ver-\textbf{R}efusal \textbf{Bench}mark), the first benchmark for over-refusal specifically designed for LALMs. AOR-Bench contains 3,000 pseudo-harmful audio samples across six scenario categories. Evaluating 12 representative LALMs from six major model families, we find that over-refusal is widespread (Figure~\ref{fig:overall_performance}) and uncover several important patterns in their safety judgments. As a preliminary effort to mitigate this issue, we further explore two lightweight strategies (e.g., Chain-of-Thought and activation steering) to reduce over-refusal. --- ### ChronoLock: Protecting Videos from Unauthorized Text-to-Video Personalization Authors: Jiaming He, Jiashu Zhang, Guanyu Hou, Shuhan Ye, Hanwei Zhu, Yi Yu, Xudong Jiang Published: 2026-06-19 Categories: cs.CV arXiv: https://arxiv.org/abs/2606.21146v1 Text-to-video (T2V) diffusion models have made it increasingly easy to synthesize realistic and temporally coherent videos, while recent personalization techniques allow such models to imitate a specific subject, style, or motion pattern from only a few reference clips. This capability creates a new data-misuse risk: videos shared online can be collected and used for unauthorized T2V fine-tuning. Existing protective perturbations are mainly designed for image recognition or text-to-image personalization, and therefore focus on corrupting static appearance cues rather than the temporal denoising dynamics that make video personalization possible. To address this gap, we introduce ChronoLock, the first proactive protection framework that makes released videos difficult to exploit for unauthorized T2V personalization. ChronoLock targets the motion-learning process directly by optimizing bounded perturbations over temporal denoising trajectories. It first disrupts intra-chunk temporal adaptation with a diffusion objective that combines fitting error, frame-relative denoising relations, and adjacent-frame variation, and then enlarges inter-chunk boundary mismatch to weaken long-range motion continuity. Transformation-sampled updates further improve robustness to common preprocessing operations.Experiments on UCF Sports and HMDB51 with popular T2V backbones and personalization scheme show that ChronoLock effectively reduces motion imitation under automatic metrics and human evaluation. --- ### AdaMem: Learning What to Remember with Adaptive Memory Policies for Personalized Agents Authors: Xingyu Chen, Rui Wang, Zhaopeng Tu, Liefeng Bo Published: 2026-06-19 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2606.21144v2 Long-term memory systems allow LLM agents to preserve information beyond a single context window, but most systems focus on storing and retrieving facts after extraction, leaving the write decision under-specified. What deserves memory can depend on the user's current task, topic, activity, or interaction partner, while uniform extraction applies one notion of importance across these different situations. We formulate this challenge as preference-conditioned write control and introduce AdaMem, which uses adaptive natural-language Memory Policies to personalize what an agent writes to memory. Each policy represents the user's memory preference for a particular interaction context, is updated from periodic feedback, and controls subsequent memory writing. We evaluate this loop in AdaMem-Bench, which assigns different memory preferences to six concurrent interaction personas across five ten-week stories. Across two extraction models and two feedback modes, AdaMem improves average QA accuracy over Mem0 from 80.0\% to 84.35\% while reducing persistent memory by 9.27\%. Our analyses show that explicit feedback helps models learn better memory policies, but current models still struggle to translate those policies into reliably selective writing behavior. AdaMem thus demonstrates the promise of adaptive write control while exposing policy execution as a central limitation of current memory agents. Our code is publicly available: https://github.com/galaxyChen/AdaMem --- ### AdaMem: Learning What to Remember for Personalized Long-Horizon LLM Agents Authors: Xingyu Chen, Rui Wang, Zhaopeng Tu, Liefeng Bo Published: 2026-06-19 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2606.21144v1 Long-term memory systems for Large Language Model (LLM) agents typically try to \emph{remember everything}, extracting memories uniformly to retain as many facts as possible. In production, however, inference cost and finite context budgets make this untenable: beyond consolidating raw dialogue into memory, an agent must exert \emph{write control}, efficiently keeping only the information each user actually cares about. Otherwise, long-horizon personalized interactions suffer \emph{memory bloat}, where irrelevant trivia crowds out useful information and steadily erodes question-answering (QA) accuracy. We argue that what is worth remembering is role-dependent, and propose \textbf{AdaMem} (Adaptive Memory), a method that \emph{learns what to remember} for each user from feedback. AdaMem maintains a structured, role-specific Memory Policy and refines it from weekly QA feedback through a lightweight, patch-style self-reflection step with failure rollback. To study this setting, we build \textbf{AdaMem-Bench}, a benchmark that simulates weeks of interaction with week-by-week QA. Across two extraction models and two feedback modes, AdaMem improves QA accuracy by up to \textbf{+9.0\%} over the uniform Mem0 baseline while shrinking memory volume by \textbf{9\%}. --- ### Matching Matters: A Fair Quality-Efficiency Benchmark for Command-Line Agents Authors: Han Chi, Jiaxin Qi, Yan Cui, Baisheng Lai, Jianqiang Huang Published: 2026-06-19 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2606.21140v2 Rapid advances in large language models have improved the task-solving capabilities of command-line-interface (CLI)-based agents, whose CLIs determine how models invoke tools, maintain interaction history, and recover from failures. Consequently, effective matching between CLIs and LLMs has become essential. However, existing agent benchmarks largely emphasize success rate while overlooking practical objectives such as cost and efficiency, as well as the selection of LM-CLI combinations, all of which are critical in real-world deployment. We therefore introduce AgentMeter, a quality-efficiency benchmark with a new metric, the AgentMeter Score (AMS), that jointly characterizes task quality, budget sensitivity, and resource-intensive zero-reward execution, enabling a more complete assessment of deployed LM-CLI pairs. Furthermore, collected task descriptions may inadvertently favor LM-CLI pairs that are particularly compatible with their wording and structure, causing evaluation results to reflect description-specific advantages rather than general task-solving capability. We therefore propose AgentMeter-Opt, a trajectory-grounded optimization framework that constructs pair-adapted, task-preserving description variants to build a fairer evaluation set across LM-CLI pairs. Extensive experiments show that no CLI is universally optimal across language models and that task success, execution cost, and AMS identify different competitive configurations. Results on AgentMeter-Opt further reveal that task-preserving description changes affect LM-CLI pairs unevenly and can alter their relative ordering across valid description conditions. Together, AgentMeter and AgentMeter-Opt provide a practical foundation for fair and deployment-relevant evaluation of command-line agents. --- ### PoLAR: Factorizing Extent and Mode in Latent Actions for Robot Policy Learning Authors: Youngjoon Jeong, Jihwan Yu, Minsoo Jo, Junha Chun, Taesup Kim Published: 2026-06-19 Categories: cs.RO, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2606.21139v1 Latent action pretraining learns representations of visual change from pairs of observations, but existing methods typically encode each transition as a single unstructured representation that entangles transition extent and transition mode. We introduce Polar Latent Actions with Radial structure (PoLAR), which imposes a radial-direction structure on latent actions, encouraging radius to encode transition extent and direction to retain transition mode. PoLAR uses temporal offset between two observations as a weak proxy for transition extent, encouraging latent action from observation pairs separated by larger temporal gaps to occupy larger radii. We instantiate this structure in hyperbolic space, whose expanding volume with radius offers a natural fit for more diverse transition modes at larger extents. Across in-task and large-scale pretraining settings, PoLAR improves downstream policy performance in simulation and real-world robot experiments, outperforming latent action baselines and strong pretrained VLAs. These results suggest that the geometry of the latent action space is an important design choice for transferring visual pretraining to downstream robot policy learning. --- ### SEED: Simple ViT and Evolving Harness for Explainable Text Forgery Detection Authors: Kahim Wong, Kemou Li, Yiming Chen, Haiwei Wu, Jiantao Zhou Published: 2026-06-19 Categories: cs.CV arXiv: https://arxiv.org/abs/2606.21138v2 AI-assisted image editing threatens trust in financial, legal, and identity records. The GenText-Forensics Challenge at ACM MM 2026 addresses this by requiring structured forensic reports, in which integrating detection, pixel-level localization, and natural language explanation for multilingual text-centric forgery images. We present SEED, a modular system with three components. First, a similarity-guided pipeline augments training with diverse synthetic forgeries. Second, a single ViT, built on DINOv3 with LoRA adaptation, jointly performs detection and pixel-level localization while preserving pre-trained priors with minimal trainable parameters. Third, an evolving harness takes the detector's predictions and generates a complete forensic report via an MLLM, iteratively improved through a proposer-evaluator loop optimizing report quality. SEED ranked 3rd in the GenText-Forensics Challenge. Code and data are available at https://github.com/KahimWong/GenText-Forensics-3rd-Place. --- ### Horizon Adaptive Offline Policy Learning via Value Stitching Authors: Kexin Zheng, Xianyuan Zhan, Xintao Yan Published: 2026-06-19 Categories: cs.LG, cs.RO arXiv: https://arxiv.org/abs/2606.21136v1 Learning accurate value functions plays a decisive role for reinforcement learning (RL) agents to solve long-horizon, complex tasks. Conventional temporal-difference (TD) learning objectives suffer from value-estimation bias that accumulates over the horizon, while extended-horizon modeling methods, such as n-step TD backups and Q-chunking, adopt a rigid, fixed-horizon value-modeling recipe that is often not flexible enough to capture complex value structures in long-horizon, multi-stage tasks. In this paper, we show that enabling value updates with dynamic horizon composition can yield a strong offline policy learning scheme. Our method, Horizon Adaptive Offline Policy Learning via VAlue STitching (VAST), replaces fixed-horizon backups with recursive, horizon-adaptive value composition. Its key ingredient is to couple value optimization with a future state- and horizon-length-conditioned auxiliary value function that is learned through direct data supervision, and a stitching policy that optimally selects the reward-maximizing horizon length and future sub-goal to achieve horizon-adaptive value stitching. This design enables direct estimation and compositional "stitching" of variable-length returns grounded in actionable sub-goal states, providing an accurate and greedily exploitable value-supervision signal for offline policy optimization. Across 50 tasks on OGBench, VAST outperforms fixed-step, extended-horizon methods, and generative-value offline RL baselines, achieving strong performance particularly in high-complexity, long-horizon decision-making tasks. --- ### Odoriko: A Shape-Aware Multimodal Diffusion Framework for Human Motion Authors: Dongseok Shim, Julian Tanke, Kengo Uchida, Christian Simon, Koichi Saito, Takashi Shibuya, Shusuke Takahashi, Yuki Mitsufuji Published: 2026-06-19 Categories: cs.CV, cs.GR, cs.RO arXiv: https://arxiv.org/abs/2606.21135v1 Human motion generation has been widely studied across diverse input modalities, text, music, and video, and recent efforts have unified these into single multimodal frameworks. However, while morphological factors such as gender and body shape are known to produce distinct kinematic signatures, no existing unified framework incorporates this into generation, treating all subjects as morphologically equivalent. We present Odoriko, the first unified multimodal motion generation framework that reflects subject bio-morphological information directly in synthesized motion output. Rather than averaging over subject variation, Odoriko generates motion that is consistent with who is moving, not just what they are asked to do, across text, music, and video conditions within a single model. When explicit morphological information is unavailable, Odoriko additionally recovers subject morphology alongside motion, unifying estimation and generation in one framework. Extensive experiments across text-to-motion, music-to-dance, and video-to-motion benchmarks demonstrate that Odoriko matches or exceeds prior specialized models on standard metrics, while enabling morphology-consistent generation that no existing unified framework supports. --- ### Learning Burst-Aware Early Warning Models for Capacity Stress under AI Workload Surges in Hyperscale Data Centers Authors: Zihan Yu, Xianling Zeng, Zhiming Xue, Yalun Qi, Sichen Zhao Published: 2026-06-19 Categories: cs.AI arXiv: https://arxiv.org/abs/2606.21130v1 The rapid growth of large-scale AI workloads, particularly Large Language Model (LLM) training and inference, is fundamentally reshaping the operational dynamics of hyperscale data centers. Unlike traditional cloud workloads, AI-driven jobs exhibit bursty, high-intensity, and rapidly shifting resource demands, often leading to sudden capacity stress that cannot be effectively handled by reactive threshold-based mechanisms. In this paper, we propose a deployment-oriented, burst-aware early warning framework for proactive capacity stress prediction under AI workload surges. We formulate the problem as a high-recall forecasting task over multivariate telemetry windows, with the explicit goal of enabling operational intervention before system degradation occurs. The proposed framework integrates workload intensity, temporal variation, and system pressure signals, and employs a lightweight tree-based learning model to capture nonlinear interactions in highly imbalanced environments. To evaluate the system under realistic conditions, we introduce an AI workload surge injection methodology that simulates burst-driven demand patterns observed in large-scale AI systems. Our XGBoost-based model achieves an ROC AUC of 0.697 and an AP of 0.670, significantly outperforming baseline methods. Under deployment-oriented threshold selection, the framework achieves a Recall of 0.914, enabling the detection of the majority of stress-prone periods with acceptable false-alarm cost. Beyond predictive performance, we show how the proposed framework can be integrated into operational control loops to support proactive actions such as workload throttling and resource scaling. Our results highlight the practical value of high-recall, learning-based early warning systems in enabling resilient and adaptive data center operations in the era of AI-driven workloads. --- ### What Accuracy and Gradient Cosine Miss: Evaluating Feedback Alignment via Scale Stability, Reference Validity, and Depth Utility Authors: Yuren Hao, Xiang Wan, ChengXiang Zhai Published: 2026-06-19 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2606.21126v1 Despite the success of deep learning, training deep networks in biologically plausible and hardware-efficient ways remains an open challenge. Feedback alignment (FA) methods address this by replacing backpropagation's symmetric backward weights with fixed random matrices, but their effectiveness depends critically on whether they can be accurately evaluated. The standard evaluation relies on two quantities: task accuracy and cosine similarity between the method's credit signal and the backpropagation gradient. We show that this reporting pair is insufficient by identifying two independent failure modes, both silent under current reporting: (1) measurement degeneracy, where the BP reference gradient collapses to the numerical floor in terminal-LayerNorm residual architectures, rendering cosine uninterpretable; and (2) aggregation collapse, where the aggregate cosine masks layerwise heterogeneity that concentrates credit at one end of the network. To address these limitations, we propose a diagnostic evaluation protocol based on three checks -- scale stability, reference validity, and depth utility -- together with per-layer rather than aggregate cosine reporting. Across multiple architectures and methods, the standard reporting pair gives no signal of failure in any audited case, while our protocol identifies all failures with wide calibration margins. The two failure modes are causally independent: a per-block scale penalty alleviates Mode 1 (residual scale explosion driving reference collapse) without affecting Mode 2 (cosine ranking that contradicts every functional metric we measured). Identifying these silent failures prevents researchers from building on non-functional credit assignment and provides actionable guidance for developing FA methods that genuinely train deep layers. --- ### PulseCX: Breaking the Closed-World Assumption in Real-Time CX Authors: Rajat Agarwal, Suvidha Tripathi, Shubham Sharma Published: 2026-06-19 Categories: cs.AI, cs.IR arXiv: https://arxiv.org/abs/2606.21124v1 Conversational AI agents in Customer Experience (CX) typically suffer from a Closed-World Constraint, ignoring high-velocity external shifts like viral trends or outages. Ad-hoc web search attempts to bridge this gap but often introduce prohibitive latency and context poisoning. We introduce PulseCX, a framework that decouples knowledge acquisition from consumption. Adopting a structure-first paradigm, PulseCX employs an asynchronous agent to linearize signals into a Decay-Aware Temporal Knowledge Graph (DA-TKG) governed by reinforcement--decay dynamics to actively manage information lifecycles. By coupling this self-evolving memory with hierarchical intent gating, PulseCX removes synchronous search bottlenecks (<10ms overhead) and drives significant gains in Intent Resolution (IRR) and Customer Satisfaction (s-CSAT) in dynamic environments. --- ### A Multi-Agent Audit Framework for High-Stakes Reasoning: Evaluation and Interpretability in Clinical Mental Health Screening Authors: Jingchen Ye, Yanpei Yu, Luyao Zhang Published: 2026-06-19 Categories: cs.CL arXiv: https://arxiv.org/abs/2606.21123v1 High-stakes reasoning tasks necessitate transparent and verifiable workflows, yet conventional single-model large language models (LLMs) often struggle with hallucination and low interpretability under zero-shot paradigms. To address this general AI challenge, we propose a Multi-Agent Audit Framework that simulates a collaborative, multi-step verification process. We empirically validate this architecture in the sensitive domain of clinical mental health screening using a modular LangChain workflow. Our framework decomposes the reasoning process into a Perception Agent, Knowledge Retrieval-Augmented Generation (RAG), Chain-of-Thought (CoT) clinical inference, and a critical Audit verification stage. We evaluated this framework on the DAIC-WOZ dataset using locally deployed open-source models. Experimental results demonstrate that our multi-agent pipeline significantly outperforms single-agent baselines, reducing the Mean Absolute Error (MAE) for PHQ-8 depression severity prediction from 5.35 to 5.02. By exposing cross-agent validation traces, the framework mitigates reasoning drift and provides highly interpretable diagnostic rationales, offering a generalizable paradigm for reliable AI-assisted decision support beyond isolated model scaling. We make data and code open access on GitHub for replicability. --- ### Answer Engineering: Local Trajectory Editing for Protocol-Constrained Decision Making in Large Language Models Authors: Victor Lavrenko, Anastasiia Molodnitskaia Published: 2026-06-19 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2606.21121v1 Large language models can produce confident but protocol-invalid answers in domains where procedural compliance is critical. This paper presents Answer Engineering, a deterministic runtime and authoring layer that applies localized rule-guided interventions to the visible reasoning trajectory during standard autoregressive generation, without retraining, modifying model weights, or performing global search. The method is evaluated on a controlled clinical benchmark for sudden sensorineural hearing loss (SSNHL), where correct management depends on protocol-consistent interpretation of symptom timing, Weber/Rinne tuning-fork findings, and otoscopic findings. In the benchmark, step-by-step reasoning shifted rather than eliminated errors: compliant outcomes for SSNHL decreased from 54.5% under unguided generation to 25.1%, while acceptance on the conductive contrast condition increased from 1.6% to 58.9%. Local trajectory editing increased SSNHL compliance to 83.5% and conductive-case adherence to 77.9%, raising balanced accuracy from 42.0% under reasoning-only generation to 80.7%. The results support a systems-level view in which protocol adherence can be improved through auditable runtime control of reasoning trajectories, while also identifying limitations caused by rule coverage, trigger reliability, and persistent diagnosis-first generation dynamics. --- ### MammoExpert: Benchmarking Chain-of-Thought Reasoning in Mammography Diagnosis Authors: Di Dai, Bo Liu, Youcheng Li, Haojun Yu, Zhouhang Bian, Quanlin Wu, Dong Wang, Sichen Meng, Hongye Xuan, Zijie Lan, Shenda Hong, Liwei Wang Published: 2026-06-19 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2606.21119v1 Mammography is an essential tool for breast cancer detection, with millions of examinations conducted annually. However, publicly available high-quality mammography datasets for AI development remain limited in both scale and annotation richness, particularly regarding pathological subtype coverage and structured diagnostic reasoning annotations. In this paper, we present MammoExpert, the first mammography dataset with Chain-of-Thought reasoning annotations across three diagnostic phases: (i) primal observation, (ii) factual assessment, and (iii) diagnostic synthesis. Comprising 2,379 mammography images covering 67 WHO-classified histopathology subtypes, each exam provides 42 radiographic features annotated by nine senior radiologists. We evaluate its performance on the breast lesion classification task, demonstrating superior accuracy and reasonability compared to existing classification models. Combining public dataset CBIS-DDSM with MammoExpert yields 7.1\% classification accuracy improvement, while the training model to learn CoT reasoning achieves another 4\% gain on the MammoExpert test set. Similar improvements are observed on INBreast and Vindr datasets, where the full approach yields accuracy gains of 6.9\% and 6.7\%, respectively. MammoExpert can serve as a benchmark for interpretable breast lesion diagnosis through explicit CoT reasoning. --- ### ConnectomeBench2: A Unified Benchmark for Automated Connectomic Proofreading Authors: Jeff Brown, Tim Farkas, Gleb Razgar, Edward S. Boyden Published: 2026-06-19 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2606.21116v1 Proofreading--correcting segmentation errors in 3D brain reconstructions--is the rate-limiting step in synapse-resolution connectomics. We release ConnectomeBench2, a unified multi-species dataset of over 716,485 expert-labeled proofreading decisions with >4,500,000 associated images spanning four major open connectomes (mouse, human, zebrafish, fly), spanning both split and merge error correction. Trained on this dataset, a single Vision Transformer with shared encoders for mesh geometry and electron microscopy reaches human-level accuracy across species for split error correction and merge error identification, with performance scaling with data size and modality. Beyond accuracy, we show that the model is well-calibrated within distribution, that measures of distribution distance predict where calibration and accuracy will degrade on unseen data, and that connectomics-specific pretraining and active learning-based sample selection show potential to substantially reduce the labeling effort needed to extend to new species and brain regions. The benchmark provides the infrastructure to train and evaluate increasingly capable vision models for connectomic proofreading. Data and code availability. The ConnectomeBench2 dataset is released on Hugging Face at https://huggingface.co/datasets/jeffbbrown2/ConnectomeBench2. The accompanying codebase is available on GitHub at https://github.com/timfarkas/ConnectomeBench2. --- ### MS-rPPG: Multi-spectral State Space Model for Remote Photoplethysmography in Driver Monitoring Systems Authors: Jiho Choi, Sang Jun Lee Published: 2026-06-19 Categories: cs.CV, cs.AI, eess.IV arXiv: https://arxiv.org/abs/2606.21115v1 Remote photoplethysmography (rPPG) is a camera-based technique for measuring physiological signals, particularly cardiac activity. From the remotely measured signals, heart rate can be estimated, which is crucial for health monitoring. In this study, we investigate a driver health monitoring system based on remote heart rate estimation. However, driving environments represent uncontrolled settings where videos are subject to varying illumination conditions and frequent head movements. We introduce MS-rPPG, a multi-spectral framework that combines RGB with near-infrared (NIR) face video to alleviate rPPG estimation under challenging driving conditions. To combine the complementary features from two spectral videos, we propose a cross-spectral linear modulation (CSLM) strategy based on frequency-domain analysis. Moreover, we introduce MS-Mamba, a novel state space model designed to effectively model long-range temporal dependencies while jointly capturing cross-channel interactions between multi-spectral features. We collected a real-world dataset called MS-Drive, which was recorded from 50 participants while driving the vehicle. The proposed method was evaluated on the MR-NIRP Car dataset and MS-Drive datasets. The experimental results indicate that MS-rPPG shows better robustness and heart rate estimation accuracy than previous methods, highlighting its promise for driver health monitoring. The codes are available at github.com/ziiho08/MS-rPPG. --- ### Object-Centric Dataset Resources for Constrained-Data Image Generation and Augmentation Authors: Vasile Marian, Yong-Bin Kang, Alexander Buddery Published: 2026-06-19 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2606.21113v1 Object-centric image generation is important in settings with few labeled examples, including pedestrian analysis in smart-city scenes, traffic-sign inspection, and domain-specific object detection. Synthetic images are most useful for training and evaluation when datasets preserve object structure, bounding boxes, visual diversity, and realistic context. Existing image datasets usually target classification, detection, or scene understanding rather than controlled object-centric generation and augmentation with limited class-specific data. We present a shareable collection of three object-centric dataset resources: Cityscapes-Pedestrian, TrafficSigns, and COCO PottedPlant. The collection standardizes 256-by-256 object-centric crops and bounding-box annotations across three regimes: dense pedestrian scenes with privacy blur and occlusion, cleaner high-contrast traffic signs, and context-diverse potted-plant scenes. The release contains 3,009 TrafficSigns samples, 2,156 Cityscapes-Pedestrian manifest records, and 7,679 COCO PottedPlant manifest records. The larger COCO-derived manifest preserves contextual and multi-instance diversity, while equal-size subsets can be drawn with a fixed random seed for controlled comparisons. The release provides direct TrafficSigns data where redistribution is permitted, together with scripts, manifests, box-level annotation tables, checksums, and reconstruction documentation for the Cityscapes- and COCO-derived subsets. It is available through the Latzi/object-centric-low-data-datasets GitHub repository and Zenodo DOI 10.5281/zenodo.20573001. The collection supports label and split inspection, subset creation, reconstruction from upstream data, and evaluation of object-centric image generation or synthetic-data augmentation methods on shared records. --- ### Chem2Gen-Bench: Benchmarking Chemical-to-Genetic Translation in Perturbation Response Space Authors: Yuxiang Lin, Ying Chen Published: 2026-06-19 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2606.21109v1 Virtual-cell and perturbation models are increasingly used to predict cellular responses for biomedical discovery, but chemical and genetic perturbations are not automatically interchangeable. Existing evaluations often study chemical response prediction or genetic perturbation prediction separately, leaving target-matched chemical-to-genetic translation under-tested. We introduce Chem2Gen-Bench, a benchmark comprising 260,084 chemical and 1,099,045 genetic perturbation profiles organized into cell-target contexts, and evaluate pairwise alignment, retrieval, protocol covariate associations, feature spaces, and foundation-model embeddings. Across matched contexts, translation fidelity is measurable but heterogeneous; background adjustment increases the association between pairwise similarity and retrieval success, while paired tests show lower mean retrieval success after adjustment under the evaluated settings. In a target-matched K562 audit, the evaluated foundation-model embeddings did not consistently improve over gene-delta baselines. Chem2Gen-Bench provides an auditable framework for testing when chemical and genetic perturbations align around shared targets and when representation gains are supported by matched perturbation evidence. --- ### SARIF: Segment Anything for Robust Image Forensics Authors: Dong-Hyun Moon, Ju-Hyeon Nam, Sang-Chul Lee Published: 2026-06-19 Categories: cs.CV arXiv: https://arxiv.org/abs/2606.21108v1 Image forgery localization remains challenging due to diverse manipulation techniques and distribution shifts. Existing forgery localization models achieve high accuracy on benchmarks but often struggle with cross-domain generalization and robustness. In this paper, we propose SARIF (Segment Anything for Robust Image Forensics), a framework that leverages the Segment Anything Model (SAM), which has a promptable architecture and strong generalization ability. SARIF introduces a feedback-guided mask decoder and a dual-encoder design that extracts forgery-specific information to capture forensic traces while exploiting the SAM architecture. To localize manipulated regions, we design a block-wise prompting mechanism that derives forgery-specific cues from residual features between an adapted encoder and its frozen counterpart. These features are fused with the previous mask prompt to drive a feedback-based mask refinement process, enabling automatic forgery segmentation without manual input. Extensive experiments on standard forgery-localization benchmarks show that SARIF achieves strong average cross-dataset performance and robustness to common image corruptions. --- ### Enhancing Differentially Private Mechanisms via Empirical Bayes Authors: Minwoo Kim, Junyong Park, Sungkyu Jung Published: 2026-06-19 Categories: cs.LG, cs.CR, stat.ME arXiv: https://arxiv.org/abs/2606.21107v1 Differential privacy (DP) has become the gold standard for ensuring the privacy protection of machine learning and statistical algorithms in recent decades. A plethora of algorithms and methods have been developed to enhance the utility of DP algorithms while maintaining the same level of DP. However, these are often overly complex or computationally ineffective. We propose a novel approach focusing on denoising the output of the simple additive Gaussian mechanism by adopting the idea of \textit{empirical Bayes estimation}. We highlight that the empirical Bayes approach can reduce the mean-squared error solely by taking the output of the Gaussian mechanism as input. Our numerical studies show that this simple yet powerful approach can be applied to improve upon various statistical problems, including histogram release, principal component analysis, and linear regression, often outperforming existing private algorithms. --- ### ShuffleFlow: Scalable Posterior Inference for Bayesian Inverse Imaging Authors: Tianao Li, Tjitske Starkenburg, Yu Sun, Emma Alexander Published: 2026-06-19 Categories: cs.CV arXiv: https://arxiv.org/abs/2606.21099v1 Variational inference (VI) is a powerful method for principled posterior inference for scientific inverse imaging. VI learns the posterior distribution, often with a flow-based network, which can cheaply generate posterior samples upon optimization, and can flexibly incorporate score-based or classic priors. However, its application to large-scale image reconstruction is severely hindered by the poor scalability of the flow-based networks. In this work, we introduce ShuffleFlow, a scalable VI framework to address this challenge. Our method breaks down the problem into three parts: a pixel-unshuffling-based image coordinate sampler, a neural field as feature encoder, and a conditional normalizing flow (CNF) as posterior estimator. Specifically, our framework partitions an image into a stack of sub-images with pixel-unshuffling and uses a shared CNF to model the joint distribution of the sub-image stack. We condition the CNF on the output of a neural field, which embeds feature vectors corresponding to pixel-unshuffling sample locations to capture spatial structures, and share the flow's latent variable across the channels to model their correlations. We demonstrate our method's effectiveness and efficiency on both linear and nonlinear imaging inverse problems, and show its ability to more rapidly generate a high-sample-count posterior than diffusion samplers. --- ### LLM-Based Multi-Reference Evaluation for Efficient and Robust Assessment of Phrase Break Annotations Authors: Younghan Park, Hoyeon Lee, Hawon Jeong, Jong-Hwan Kim Published: 2026-06-19 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2606.21098v1 Reliable evaluation of phrase break annotations is crucial, as subtle variations in prosodic boundaries directly affect the clarity and naturalness of speech. However, existing approaches exhibit major limitations: single-reference evaluation assumes a unique gold phrasing for an utterance despite multiple valid phrasings, while human judgment, though flexible, is labor-intensive and unscalable. To address these, we propose LLM-based Multi-Reference Evaluation (LMRE) for phrase break annotations that models the one-to-many nature of prosodic phrasing and generates multiple valid phrasings from minimal demonstrations. On a Korean testbed of 1,356 annotations covering five strategies, LMRE shows stronger alignment with human judgment than single-reference evaluation in both acceptance behavior and score correlation. Our findings demonstrate that LMRE effectively achieves both scalability and multi-reference support, highlighting the potential of LLMs for evaluation in the speech domain. --- ### GRAG: Generic Response-Augmented Generation Framework for Personalized Conversational Systems Authors: Junfeng Liu, Christopher T. Symons, Ranga Raju Vatsavai Published: 2026-06-19 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2606.21097v2 Deploying highly capable personalized conversational agents in resource-constrained or privacy-sensitive environments remains a significant challenge. We identify a fundamental bottleneck in the existing approaches: current training paradigms treat personalization and grounding as a single monolithic learning problem. Under these paradigms, language models are forced to simultaneously address what to say (content grounding) and how to say it in a user-specific way (personalization), which introduces significant computational and optimization challenges. Consequently, contextual grounding is often sacrificed for persona adherence, or vice versa, resulting in responses that are either weakly grounded in the conversational history or insufficiently personalized. In this work, we propose the Generic Response-Augmented Generation (GRAG) framework that decouples these competing objectives by leveraging offline, generic responses from high-capacity, general-purpose LLMs as a semantic and structural scaffold to guide the fine-tuning of smaller, task-specialized models seamlessly in resource-limited environments. By decoupling the content grounding from personalization, GRAG allows the model to focus exclusively on persona injection while remaining firmly anchored to the conversational context. We instantiate the GRAG in two post- and pre-fusion-based architectural variants and evaluate them on multiple benchmark conversational datasets that cover diverse personalization structures. Our results demonstrate that GRAG significantly outperforms state-of-the-art methods that do not use auxiliary scaffolding, yielding up to 47% improvements in ROUGE-2 and 36% in BLEU scores. Ultimately, GRAG offers a generalizable blueprint for building grounding-aware personalized conversational systems in resource-limited environments. --- ### SLeDGe: Semi-Supervised Learning on Data Streams with Graph Structure Learning Authors: Heechan Moon, Kijung Shin Published: 2026-06-19 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2606.21096v1 Semi-supervised learning (SSL) on data streams is challenging due to the continuous evolution of high-volume data and the scarcity of labels. Existing methods are limited in leveraging the intrinsic relationships among samples because they typically rely on fixed similarity measures or static graph structures, which cannot capture how relationships evolve over time. We propose SLeDGe, an SSL method for data streams that jointly learns a predictive model and an adaptive graph structure under strict memory and label constraints. SLeDGe maintains compact labeled and unlabeled memories using distinct update strategies, balancing rapid adaptation to novel features with the retention of historical consistency. In addition, by encouraging sparsity in the relational graph, SLeDGe filters out spurious connections and enables effective propagation of label supervision. Across 12 datasets, SLeDGe outperforms state-of-the-art competitors, achieving average relative accuracy gains of 31.7% with 0.1% labels and 14.8% with 1% labels. ---