# Research Papers — 2026-05 · bundle page 15 of 326 > Full-text markdown of papers #701–750 of 16266 published in 2026-05, newest first. AI-readable mirrors of the full 16266-paper 2026-05 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2026-05/page/15 [← Previous bundle](https://aipod.dev/papers/archive/2026-05/page/14.md) [Next bundle →](https://aipod.dev/papers/archive/2026-05/page/16.md) ### Sample-Efficient Post-Training for LEGO Spatial-Physics Reasoning Authors: Yuhuan Yuan, Zhouliang Yu, Minghao Liu, Weiyang Liu, Ge Lin Kan Published: 2026-05-29 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2606.07602v2 LLM-based LEGO assembly requires both semantic grounding and physical feasibility. In this paper, we identify a data-induced failure mode, physhack, in which generated assemblies satisfy physical-validity constraints while remaining geometrically misaligned, semantically inconsistent, or poorly calibrated. To address this challenge, we propose a model-based data selection approach that uses only 5% of the original training data while improving semantic and structural alignment across multiple independent evaluators. We further introduce PVPO, a reinforcement learning method that couples physical-validity and voxel-space geometric rewards to strengthen the LEGO synthesis capabilities of LLMs. PVPO-trained DeepSeek-Llama-8B outperforms the frontier VLM Kimi-K3 across semantic, structural, and physical evaluation dimensions, even when Kimi-K3 is provided with a ground-truth image as an additional reference. --- ### Sample-Efficient Post-Training for LEGO Spatial-Physics Reasoning Authors: Yuhuan Yuan, Zhouliang Yu, Minghao Liu, Weiyang Liu, Ge Lin Kan Published: 2026-05-29 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2606.07602v1 LLM-based LEGO assembly generation requires both semantic grounding and physical feasibility. We identify a data-induced failure mode, PhysHack, in which the assemblies satisfy physical-validity constraints while producing structures that are geometrically misaligned, semantically inconsistent, or poorly calibrated. To address this challenge, we propose a model-based data selection approach that uses only a small fraction of the training data while improving physically grounded LEGO assembly generation. Building on the selected trajectories, we introduce PVPO, a sample-efficient reinforcement learning method that couples physical feasibility with voxel-space geometric rewards. Our results show that physical validity alone is an insufficient proxy for reliable physical reasoning: models can learn to generate valid structures without preserving semantic or geometric fidelity. Experiments across model backbones and test-time scaling settings demonstrate that PVPO improves structural and semantic alignment, physical validity, structural stability, and calibration, while reducing reliance on extensive post-hoc rejection sampling. In particular, results on calibration show that PVPO mitigates PhysHack by making test-time selection more predictive of semantic and structural quality. --- ### LFNO: Bridging Laplace and Fourier via Transient-Steady Decomposition Authors: Jeongun Ha, Sanga Yoon, Donghun Lee Published: 2026-05-29 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2606.07601v1 We introduce the Laplace-Fourier Neural Operator (LFNO), a unified framework for modeling dynamical systems across transient and steady-state regimes by integrating the spectral advantages of Laplace and Fourier Neural Operators. LFNO employs a dual-branch architecture that explicitly decomposes system dynamics into transient and steady-state components. We evaluate LFNO on nine benchmarks, including three ODE systems (Duffing, Lorenz, and Pendulum) and six PDE systems (Euler-Bernoulli beam, Heat, Reaction-diffusion, Brusselator, Burgers, and Navier-Stokes). LFNO significantly outperforms existing operators on ODE systems, where transient dynamics dominate, and consistently surpasses LNO while achieving performance competitive with FNO on PDE benchmarks. Furthermore, LFNO offers improved stability and physical interpretability through its component-wise decomposition. These results demonstrate that LFNO provides a robust and unified approach for learning complex dynamical systems across multiple temporal scales. --- ### Reachability and asymptotics of Gaussian Transformer dynamics Authors: Albert Alcalde, Zhengping Ji, Enrique Zuazua Published: 2026-05-29 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2606.07600v1 We formulate data propagation through the Transformer, the machine learning architecture powering large language models, as a nonlinear control system on the space of probability measures. For the mean-field Transformer model with self-attention and affine feed-forward layers, we prove that Gaussian distributions remain exactly Gaussian along the induced flow. This invariance reduces the infinite-dimensional measure dynamics to a finite-dimensional bilinear control system governing the evolution of the mean and covariance, reformulates the expressive capacity of Transformers as a reachability problem for prescribed Gaussian moments, and reveals a novel connection with Riccati-type equations from classical filtering and control. For time-varying controls, we prove exact finite-time reachability of any target Gaussian distribution whose covariance matrix has the same rank as the initial one, this rank constraint being an intrinsic invariant of the dynamics. For time-invariant parameters, we derive explicit spectral conditions leading either to asymptotic stability toward positive-definite equilibria or to finite-time blow-up of the covariance. Numerical experiments complement the theory by showing that practical Transformers with Gaussian inputs remain close to moment-matched Gaussian distributions through early and intermediate layers, while Transformers with prescribed attention matrices reproduce the predicted covariance regimes: bounded evolution in stabilizing configurations and blow-up in destabilizing ones. --- ### DiffoR: A Unified Continuous Generative Framework for Universal Ordinal Regression Authors: Hongxu Ma, Lin Wang, Chenghou Jin, Han Zhou, Jie Zhang, Xiaoyu Yang, Chunjie Chen, Jihong Guan, Shuigeng Zhou Published: 2026-05-29 Categories: cs.LG, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2606.07599v1 Ordinal Regression (OR) aims to predict target values with inherent order, underpinning critical applications across diverse domains, from recommender systems to computer vision. Though having evolved from naive regression to discretization-based classification and generation, existing paradigms remain fundamentally constrained by quantization artifacts and the lack of global ordinal topological perception. These methods typically enforce rigid boundary delineations, failing to capture the non-stationary semantic transitions inherent to ordinal data. In this paper, we propose a novel paradigm where OR is formulated as a Continuous Generative Ordinal Regression task. Under the novel paradigm, we introduce DiffOR, a unified framework that leverages diffusion models to recover continuous ordinal values via iterative denoising, thereby enabling the dynamic learning of soft semantic transitions. To explicitly preserve ordinal topology, we devise a Dual-Decoupling Strategy: Spatially, Multi-scale Increment Aggregation decomposes targets into hierarchical continuous increments; Temporally, Dynamic Denoising Perception synchronizes denoising steps with feature frequencies, ensuring robust coarse-to-fine refinement. Theoretically, we show that the proposed method can significantly enhance both representation capability and mechanistic interpretability. Extensive experiments on 12 benchmarks across four domains validate DiffOR's consistent superiority over state-of-the-art methods, establishing a new standard that demonstrates strong potential as a general-purpose solution for universal ordinal regression. --- ### A Topological Characterization of Graph Neural Networks via Stochastic Block Model Embeddings on the n-Sphere Authors: Gopal Anantharaman Published: 2026-05-29 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2606.07598v1 We propose a topological framework for comparing trained Graph Neural Networks (GNNs) by mapping the Stochastic Block Models (SBMs) induced on the graphon-signal space of a Message Passing Neural Network (MPNN) onto the unit $n$-sphere $\sphere^{n-1}\subset\R^n$. The construction rests on three classical pillars: the \emph{compactness} of the cut-distance graphon space $(\Wo,\cutdist)$ \citep{lovasz2006limits,lovasz2012large}, the Frieze--Kannan \emph{weak regularity lemma} together with its graphon-signal extension due to \citet{levie2023graphon}, and the Lipschitz continuity of MPNNs with respect to the cut-distance. We show that, for any prescribed tolerance $\varepsilon>0$, a trained MPNN $Φ$ acting on a sufficiently large graph factors (up to $\varepsilon$) through a step-graphon-signal of bounded complexity, and we construct an explicit measure-preserving map $Ψ_n\colon(0,1)\to\sphere^{n-1}$ that places the SBM regions on disjoint spherical caps. This produces a problem-agnostic, low-dimensional ``fingerprint'' of a trained GNN that is amenable to visual inspection and to nearest-neighbour search across model zoos, enabling \emph{transfer-learning candidate retrieval} without retraining. We discuss the obstruction posed by concentration of measure in high dimension -- a phenomenon directly relevant to LLM-scale embeddings. We close with five concrete future research directions: hyperbolic and Grassmannian alternatives to the spherical model, Gromov--Wasserstein distances on graphon-signals as an isometry-free alternative to the $n$-sphere map, an information-geometric (Fisher) reformulation of the SBM manifold, persistent-homology fingerprints of layer-wise embedding clouds, and a spectral-distance baseline derived from the graphon eigendecomposition. --- ### Repetition Mismatch: Why Data Mixture Experiments Don't Scale and How to Fix Them Authors: Kevin Zhou, Lisa Alazraki, Kris Cao, Marek Rei Published: 2026-05-29 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2606.07597v2 Pre-training data mixtures are commonly tuned by running small-scale experiments and extrapolating to the target training budget. When high-quality data is scarce and must be repeated, this extrapolation frequently fails, but the source of the failure has not been isolated. We show that a primary culprit is a repetition mismatch: because high-quality datasets are small, their repetition rate changes as the training budget grows, shifting the optimal mixture in ways that small-scale proxy experiments do not anticipate. A subsampling procedure that matches the target repetition rate controls for this effect. In a two-source setting combining limited high-quality data with web crawl, a single repetition-controlled experiment using only 1/16 of the target tokens recovers a mixture within 0.10 of the optimum on Wiki-Text for a 1.17B parameter model, compared to an error of 0.85 without repetition control. Achieving comparable accuracy without repetition control requires multiple training horizons, consuming 19%, 44%, and 94% of the target token budget when using the results from two, three, and four horizons respectively. With three data sources, the larger mixture space requires more than a single experiment to constrain, but the approach remains effective: at the 757M scale, just two repetition-controlled horizons recover the optimal mixture, outperforming baselines that instead require the full two-source experiments to construct. Our results reveal that repetition dynamics, not scale alone, shape whether small-scale mixture experiments generalize. More broadly, they suggest that data repetition deserves treatment as a first-class variable in mixture optimization, rather than an inconvenient side effect of limited data. --- ### Repetition Mismatch: Why Data Mixture Experiments Don't Scale and How to Fix Them Authors: Kevin Zhou, Lisa Alazraki, Kris Cao, Marek Rei Published: 2026-05-29 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2606.07597v1 Pre-training data mixtures are commonly tuned by running small-scale experiments and extrapolating to the target training budget. When high-quality data is scarce and must be repeated, this extrapolation frequently fails, but the source of the failure has not been isolated. We show that a primary culprit is a repetition mismatch: because high-quality datasets are small, their repetition rate changes as the training budget grows, shifting the optimal mixture in ways that small-scale proxy experiments do not anticipate. A subsampling procedure that matches the target repetition rate controls for this effect. In a two-source setting combining limited high-quality data with web crawl, a single repetition-controlled experiment using only 1/16 of the target tokens recovers a mixture within 0.05 of the optimum for a 757M parameter model, compared to an error of 0.75 without repetition control. Achieving comparable accuracy without repetition control requires three to four horizons, consuming 44 to 94% of the target token budget. With three data sources, the larger mixture space requires more than a single experiment to constrain, but the approach remains effective: at the 757M scale, just two repetition-controlled horizons recover the optimal mixture, outperforming baselines that instead require the full two-source experiments to construct. Our results reveal that repetition dynamics, not scale alone, shape whether small-scale mixture experiments generalize. More broadly, they suggest that data repetition deserves treatment as a first-class variable in mixture optimization, rather than an inconvenient side effect of limited data. --- ### Shortcuts in the Tail: Debiasing via Post-Hoc Spectral Compression of Fine-Tuning Updates Authors: Edward Sun, Dmitrii Troitskii Published: 2026-05-29 Categories: cs.LG arXiv: https://arxiv.org/abs/2606.07596v2 Fine-tuning often introduces spurious correlations alongside task knowledge, causing systematic failures on underrepresented groups. Existing mitigations require retraining, group labels, or curated counterfactual data. We show a simple post-hoc intervention reduces shortcut reliance without any of these: truncating the tail of the SVD of $ΔW = W_\mathrm{ft} - W_\mathrm{base}$ reduces the spurious-group gap while preserving task accuracy. Across three instruction-tuned models ($0.5$B--$7$B) and four classification benchmarks, top-$k$ truncation reduces the gap on every cell at $<2$ pp accuracy loss, by up to $5\times$ on CivilComments. We propose this works because the shortcut response sits in the tail of the singular ordering of $ΔW$, a claim about how truncation behaves rather than about the raw singular values, which are broadly distributed and look the same across all four datasets. A controlled boundary case in which fine-tuning has only a shortcut to learn shows the predicted FT-to-base collapse, and bottom-/random-$k$ and matched-rank LoRA controls rule out generic low-rank approximation and rank-constrained training as the explanation. We read this as preliminary evidence that the singular basis of $ΔW$ is a useful coordinate system for studying what fine-tuning has learned. --- ### Shortcuts in the Tail: Debiasing via Post-Hoc Spectral Compression of Fine-Tuning Updates Authors: Edward Sun, Dmitrii Troitskii Published: 2026-05-29 Categories: cs.LG arXiv: https://arxiv.org/abs/2606.07596v1 Fine-tuning often introduces spurious correlations alongside task knowledge, causing systematic failures on underrepresented groups. Existing mitigations require retraining, group labels, or curated counterfactual data. We show a simple post-hoc intervention reduces shortcut reliance without any of these: truncating the tail of the SVD of $ΔW = W_\mathrm{ft} - W_\mathrm{base}$ reduces the spurious-group gap while preserving task accuracy. Across three instruction-tuned models ($0.5$B--$7$B) and four classification benchmarks, top-$k$ truncation reduces the gap on every cell at $<2$ pp accuracy loss, by up to $5\times$ on CivilComments. We propose this works because the shortcut response sits in the tail of the singular ordering of $ΔW$, a claim about how truncation behaves rather than about the raw singular values, which are broadly distributed and look the same across all four datasets. A controlled boundary case in which fine-tuning has only a shortcut to learn shows the predicted FT-to-base collapse, and bottom-/random-$k$ and matched-rank LoRA controls rule out generic low-rank approximation and rank-constrained training as the explanation. We read this as preliminary evidence that the singular basis of $ΔW$ is a useful coordinate system for studying what fine-tuning has learned. --- ### VisualLeakBench: Reproducible Action-Boundary Propagation Failures in Vision-Language Agents Authors: Youting Wang, Yuan Tang, Yitian Qian, Chen Zhao Published: 2026-05-29 Categories: cs.CV, cs.AI, cs.IR arXiv: https://arxiv.org/abs/2606.07595v1 Vision-language agents increasingly consume screenshots, documents, and user interfaces before writing to memory, sending messages, or invoking external tools. We study a concrete failure mode in this setting: action-boundary propagation, where sensitive or unsafe visible text is copied from an image into downstream tool arguments. We present VisualLeakBench, a diversified 500-image benchmark spanning UI, chat, document, form, and dashboard scenes, and evaluate a stratified 100-image agent subset with four production VLM systems under two workflows: note capture and external handoff. At baseline, target strings are propagated into tool arguments in 78.8% of PII cases and 85.5% of rendered unsafe-text cases. Under a defensive system prompt, rendered unsafe-text propagation remains high at 52.6%, while PII tool propagation falls to 2.0%, largely by suppressing tool use rather than preserving utility. Rates are tool-surface dependent: search-like tools suppress PII propagation, but rendered unsafe text still crosses tool boundaries. We measure visual-to-tool propagation rather than downstream instruction execution. We additionally provide a labeled-target oracle upper-bound diagnostic that localizes most failures at the tool boundary while leaving response-side leakage as residual risk. --- ### Gradient Descent with Large Step Size Restores Symmetry in Deep Linear Networks with Multi-Pathway Authors: Hee-Sung Kim, Sungyoon Lee Published: 2026-05-29 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2606.05219v1 Recent analyses of multi-pathway Deep Linear Networks use Gradient Flow to predict a "winner-takes-all" specialization in which path symmetry breaks and each feature concentrates in a single pathway. In this work, we show that discrete Gradient Descent (GD) with a large step size tells a different story. We prove that single-path solutions are sharp minima, whereas distributing signals across pathways reduces sharpness by a factor that decreases with both the number of pathways and depth. Consequently, while early training reproduces the depth-driven symmetry breaking predicted by GF, oscillations at the Edge of Stability subsequently override this tendency and drive the network into a re-balancing phase, where signals redistribute across pathways. Together, these results clarify how depth shapes pathway competition and explain why large-step GD favors shared representations rather than persistent single-pathway dominance. --- ### The Variance Brain Foundation Models Forgot: Third-Order Statistics Predict Cognition Where Billion-Parameter Models Fail Authors: Giovanni Marraffini, Gabriel Mahuas, Trinidad Borrell, Victoria Shevchenko, Demian Wassermann Published: 2026-05-29 Categories: q-bio.NC, cs.AI arXiv: https://arxiv.org/abs/2606.04010v1 Brain foundation models (BFMs) are self-supervised Transformers pretrained on fMRI data. We posit that these models should capture each subject's cognitive performance from their fMRI signal. Yet across three state-of-the-art BFMs and every readout we test, they predict cognition worse than a linear regression from the $\sim$80K parameters of the functional connectivity matrix (FC). The gap widens with scale: BrainLM's 650M model predicts cognition worse than its 111M. We attribute this to a \textbf{variance allocation problem}: BFM pretraining captures the variance components that dominate fMRI but not the higher-order structure that predicts cognition. Our per-cumulant analysis of the reconstructed signal shows that the second-order covariance is partially preserved, while the third-order co-skewness tensor is largely destroyed. To recover what BFMs lose, we design a linear pipeline that projects the fMRI signal into the subspace that best preserves its co-skewness and computes FC there. This \textbf{exceeds raw FC and every pretrained BFM} on every dataset and parcellation we test, outperforming prior state-of-the-art under controlled evaluation \textbf{with no pretraining and no GPU}. We \textbf{recover the raw-FC ceiling on BrainLM's forward pass} by finetuning with a loss targeted at this same subspace. This shows that the bottleneck is the pretraining objective, not the architecture or the model size. --- ### Counterfactual Explanations for Deep Two-Sample Testing Authors: Wei-Cheng Lai, Marco Simnacher, Christoph Lippert Published: 2026-05-29 Categories: stat.ML, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2606.04009v2 Two-sample testing is a fundamental tool for detecting distributional differences across scientific domains, but classical tests (including kernel-based tests) can be ineffective on high-dimensional structured data such as images. Recent deep two-sample tests improve sensitivity in these settings by learning informative representations, yet they provide limited insight into which data features drive rejection of the null hypothesis $H_0$. To address this issue, we propose a counterfactual explanation framework for deep two-sample testing that generates sample-level edits moving observations from a source group toward a target group while explicitly reducing the discrepancy measured by the test. Our method combines a diffusion autoencoder with a pretrained deep two-sample test model and optimizes a maximum mean discrepancy (MMD) objective in the test model's representation space to produce plausible counterfactuals. We quantify distribution-level effects through changes in the test statistic and the resulting two-sample p-values. We evaluate the method on synthetic 2D shape datasets and two MRI cohorts. Across both settings, the counterfactual transformations consistently increase p-values relative to the original samples, indicating that the edited source set becomes statistically closer to the target distribution under the test. We measure minimality using LPIPS to ensure the counterfactuals remain close to the original samples. The resulting edits provide interpretable evidence of the features associated with the detected group differences. On MRI, the localized changes are consistent with known anatomical differences between cohorts. --- ### Neural Radiated-Noise Fields for Unmanned Underwater Vehicle Noise Spectrum Prediction in Three-Dimensional Scenes Authors: Yan Wu, Yang Yang, Jun Fan, Bin Wang Published: 2026-05-29 Categories: eess.SP, cs.AI arXiv: https://arxiv.org/abs/2606.04008v1 Radiated noise in unmanned underwater vehicles (UUVs) is an important indicator for characterizing acoustic signatures and evaluating platform performance. To address the strong dependence of traditional physics-based modeling and numerical simulation methods on target structural information and environmental boundary conditions, and their inability to achieve continuous spatial spectrum-response modeling in three-dimensional scenes, this paper proposes a neural radiated-noise field (NRNF). An NRNF represents the UUV radiated-noise spectrum as a continuous function of the three-dimensional UUV position, the three-dimensional hydrophone position, the UUV yaw angle, and the frequency, enabling query-based prediction at arbitrary spatial locations. The proposed method employs sinusoidal encoding for position and frequency, and introduces a learnable three-dimensional scene feature grid to explicitly represent environmental structure and propagation effects. A spectrum-prediction dataset is constructed from lake trials, and the proposed model is evaluated under three settings: horizontal extrapolation, depth extrapolation, and cross-run generalization. Results show that the NRNF achieves an average prediction error of 3.5 dB in the 50 to 5000 Hz band. Horizontal extrapolation is easiest, depth extrapolation is the most challenging, and cross-run generalization is of intermediate difficulty. Further ablation results demonstrate that the scene feature grid significantly improves the prediction stability and spatial generalization of the model. --- ### The Shape of Addition: Geometric Structures of Arithmetic in Large Language Models Authors: Liuyuan Wen, Xun Zhu, Lihao Huang, Wenbin Li, Yang Gao Published: 2026-05-29 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2606.03645v1 Large Language Models exhibit paradoxical fragility in fundamental arithmetic, implying a disconnect between internal computation and discrete output. By analyzing the residual stream geometry during multi-operand addition, we identify the Iso-Raw-Sum Trajectory (IRST), a geometric structure where representations are anchored by semantic digits and modulated by continuous carry fibers. We propose the Noisy Quantization Model to explain this geometry, framing arithmetic errors as Geometric Slippages caused by internal neural noise pushing a continuous, latent Carry Potential across quantization thresholds. This geometric framework further elucidates Probe Versatility, explaining how lightweight probes can disentangle coexisting latent signals (such as ground truth versus hallucination) from a single activation vector. Finally, we validate these insights through a geometric consistency check method that effectively detects and corrects these quantization failures during inference. Our code is available at https://github.com/RL-MIND/Shape-of-Addition. --- ### Spatial Transcriptomics-Guided Alignment Enhances Molecular Profiling in Pathology Foundation Model Authors: Fengtao Zhou, Yingxue Xu, Zhengyu Zhang, Yihui Wang, Zhengrui Guo, Ling Liang, Jiabo Ma, Cheng Jin, Ziyi Liu, Huajun Zhou, Hongyi Wang, Du Cai et al. Published: 2026-05-29 Categories: cs.LG arXiv: https://arxiv.org/abs/2606.03644v1 Comprehensive molecular profiling is essential for modern precision oncology but remains hindered by prohibitive costs, specimen exhaustion, and protracted turnaround times. While pathology foundation models (PFMs) have demonstrated potential for inferring molecular phenotypes from routine hematoxylin and eosin (H&E) whole-slide images (WSIs), current architectures primarily rely on vision-centric self-supervised learning or vision-language alignment, lacking the spatially resolved molecular supervision required to connect subtle morphological features with underlying genomic alterations. Spatial transcriptomics (ST) emerges as a transformative technology that enables transcriptomic quantification within intact tissue sections, thereby preserving the precise spatial link between histology and molecular profiles. In this study, we present a Spatial Transcriptomics-guided Alignment framework for Molecular Profiling (STAMP), which endows PFMs with intrinsic molecular awareness. To support this paradigm, we curated HumanST-1k, a human ST dataset spanning diverse anatomical organs and sequencing platforms. This atlas yields 1.8 million pairs of H&E patches and corresponding transcriptomic profiles, providing a corpus that links histological structures with their molecular states. To mitigate the technical noise inherent to raw transcriptomics, STAMP applies a pathway-informed alignment strategy that aggregates transcriptomic data into biologically functional pathways, which are subsequently integrated into PFMs via parameter-efficient fine-tuning. This alignment enriches the representation space of PFMs and unlocks their capacity to resolve sub-visual molecular signatures. The clinical utility of these augmented representations was validated through a multi-tier evaluation framework. --- ### DXA-Derived Skeletal Phenotypes and Hip Fracture Risk: A Backdoor-Adjusted Causal Analysis Authors: Zixin Shi, Chen Zhao, Meiling Zhou, Kevin A. Maupin, Joyce H. Keyak, Nancy E. Lane, Kuan-Jui Su, Hui Shen, Hong-Wen Deng, Kui Zhang, Weihua Zhou Published: 2026-05-29 Categories: q-bio.QM, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2606.02625v1 Purpose: To compare dual-energy X-ray absorptiometry (DXA)-derived hip skeletal phenotypes in relation to hip fracture risk using prespecified confounder adjustment and to assess whether phenotypes ranked by their backdoor-adjusted average treatment effects (ATEs) improve risk stratification. Methods: We analyzed 21,098 UK Biobank participants with linked health records, hip DXA-derived skeletal measures, and prespecified covariates. Sixteen phenotypes spanning bone mineral content (BMC), bone mineral density (BMD), and T-score across hip-related regions were evaluated. Confounder selection was guided by a prespecified directed acyclic graph (DAG). Backdoor-adjusted ATEs were estimated on the absolute risk-difference scale per standard deviation (SD) increase. Effect heterogeneity was evaluated for total femur BMD, and downstream prediction was assessed using clinical variables combined with phenotypes ranked by ATE magnitude. Results: Among 21,098 participants, 115 had hip fractures. All 16 phenotypes showed negative backdoor-adjusted ATEs per SD increase. The largest ATEs were observed for total femur BMC and total femur BMD, each with a risk difference of -0.0047, corresponding to approximately 4.7 fewer hip fractures per 1,000 participants per SD higher phenotype value. Conditional effects of total femur BMD were stronger among older participants and those with lower BMI. In prediction, clinical variables plus the top 11 ATE-ranked phenotypes achieved higher AUC than FRAX with femoral neck BMD (0.842 vs. 0.709), with higher sensitivity (0.748 vs. 0.443) and similar specificity (0.793 vs. 0.777). Conclusion: DXA-derived hip skeletal phenotypes differed in their backdoor-adjusted ATEs. Phenotype-level causal evaluation may help identify informative DXA measures for risk stratification. --- ### TadA-Bench: A Million-Variant Benchmark for Future-Round Discovery Toward Agentic Protein Engineering Authors: Jin Gao, Juntu Zhao, Zirui Zeng, Jiaqi Shen, Junhao Shi, Dukun Zhao, Yuming Lu, Dequan Wang Published: 2026-05-29 Categories: q-bio.QM, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2606.02624v1 AI for scientific discovery is entering an agentic era, where protein-engineering systems are expected to prioritize future wet-lab experiments rather than merely fit static measurements. We introduce TadA-Bench, a million-variant wet-lab replay benchmark from 31 TadA directed-evolution rounds for future-round discovery toward agentic protein engineering. TadA-Bench preserves the campaign chronology and defines a fixed-data replay task: given earlier experimental rounds, models rank variants that appear only in later rounds. It provides aligned DNA, RNA, and protein views, and uses Seq2Graph, a graph-based label-unification pipeline, to reconcile noisy enrichment measurements into consistent cross-round activity labels. Random-split controls show strong interpolation, but future-round ranking and finite-budget candidate selection are much weaker. Controlled analyses suggest that evolutionary coverage is more informative than local data density, positioning TadA-Bench as a reproducible wet-lab replay substrate for future-round discovery toward agentic protein engineering; the data and code are released on Hugging Face and GitHub. --- ### Oscillatory State-Space Models as Inductive Biases for Physics-Informed Neural PDE Solvers Authors: Abhishek Chandra, Taniya Kapoor Published: 2026-05-29 Categories: cs.NE, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2606.02623v1 Solving time-dependent partial differential equations (PDEs) is an important problem in computational science and engineering. Physics-informed neural networks (PINNs) learn PDE solutions from governing equations. However, accurately capturing temporal evolution remains challenging. Recent sequence-model-based approaches parameterize time evolution using general-purpose sequence models, which capture temporal dependencies but do not explicitly encode the structured dynamics of PDE solutions. In addition, their memory requirements can scale unfavorably with sequence length and resolution, limiting applicability in large-scale or high-dimensional settings. This work introduces a PINN approach that incorporates oscillatory state-space dynamics to represent the modal structure of PDE solutions. The proposed method leverages a linear-oscillator-based temporal evolution, together with a PDE-aware spectral basis in space. This design enables closed-form spatial differentiation and consistent enforcement of boundary conditions. The method is evaluated on forward, inverse, and high-dimensional PDE problems, including cases up to 100 spatial dimensions. The results show improved accuracy and reduced memory usage compared to recent sequence-model-based PINN approaches. Overall, this work highlights the benefits of incorporating structured dynamical priors into the temporal evolution of neural PDE solvers and suggests designing more physics-aligned and computationally efficient PINN architectures. --- ### Ego-METAS: Egocentric online Multimodal Energy-efficient Temporal Action Segmentation benchmark Authors: Maria Santos-Villafranca, Jesus Bermudez-cameo, Alejandro Perez-Yus, Giovanni Maria Farinella, Antonino Furnari Published: 2026-05-29 Categories: cs.CV arXiv: https://arxiv.org/abs/2606.02246v1 To operate in the physical world, embodied agents must perceive their environment in an "always-on" fashion, selectively accessing the most informative sensors to balance energy constraints and task accuracy. Despite its importance for resource-constrained devices, energy-aware perception remains under-explored, with most prior work assuming unlimited compute. To address this, we introduce Ego-METAS: the first Egocentric online Multimodal Energy-efficient Temporal Action Segmentation benchmark. Ego-METAS provides a unified testbed of more than 100 hours of untrimmed egocentric video from EgoExo4D, CMU-MMAC, and CaptainCook4D, spanning 5 modalities (RGB, audio, gaze, IMU, and monochrome camera). We formulate an online temporal action segmentation task where models must dynamically select which sensors to activate at each timestep while strictly adhering to hardware-representative energy budgets. Alongside the benchmark, we release unified splits, cleaned annotations, pre-extracted features, and a diverse suite of baseline routing policies. Our evaluations show that optimal routing is highly scenario-dependent, and that existing policy-learning methods, designed primarily for trimmed clips, struggle to adapt to continuous, untrimmed environments. However, even simple dynamic fusion of complementary modalities (e.g., via random routing) proves critical for balancing predictive accuracy against strict energy budgets. Ultimately, Ego-METAS provides a standardized foundation to develop robust, cost-aware policies for autonomous, always-on embodied AI. --- ### Weighted Conformal Clustering Authors: Anirban Nath, YoonHaeng Hur, Genevera I. Allen Published: 2026-05-29 Categories: stat.ME, math.ST, stat.ML arXiv: https://arxiv.org/abs/2606.00436v1 Clustering is a central tool for discovering latent structure in unlabeled data; yet modern clustering pipelines often end with a hard assignment of each observation to a cluster without rigorous measures of assignment uncertainty. We propose a novel weighted conformal approach for constructing valid confidence sets for cluster labels. The key difficulty is that the labels available for calibration are not observed ground-truth labels, but synthetic labels produced by a data-dependent clustering algorithm. Our method develops a conformal inference algorithm that corrects the resulting mismatch with the latent target labels through weights by formulating conformal clustering as a conditional label-distribution shift problem. We first derive an oracle procedure that attains finite-sample marginal coverage and then develop a computationally tractable and implementable version using estimated conditional label probabilities and novel augmented calibration. We show that the coverage of the estimated-weight procedure depends on the estimator, giving an explicit bound on the loss relative to the nominal level. Empirical studies demonstrate that the proposed weighted approach offers improvements over the recently proposed split conformal clustering procedure in terms of informative confidence set size, especially in nonlinear and high-dimensional clustering applications. --- ### Detect Before You Leap: Mirage Detection in Vision-Language Models Authors: Md. Shaown Miah, S. M. Taiabul Haque, Syed Ishtiaque Ahmed, Sayeed Shafayet Chowdhury Published: 2026-05-29 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2606.00435v4 Vision-language models (VLMs) can produce confident answers without relevant visual evidence, a failure mode known as mirage reasoning (Asadi et al., 2026). To that end, we study pre-release mirage detection: deciding whether a VLM answer should be released or withheld. Our model-agnostic method, Text-Conditioned Layer-wise Internal Alignment (TC-LIA), tracks question-image alignment across the layers of a frozen CLIP ViT-H/14 encoder, summarizing patch-text alignment by final similarity, late-layer top-k alignment, early-to-late gain, and slope. TC-LIA is purely unsupervised (fixed projections, fixed scoring weights, no labels, no training) and already delivers strong detection independently. Additionally, when combined with blank/noise detection, domain routing, and VLM self-assessment, it forms an ensemble whose supervised training improves performance but is an optional add-on. On 19,004 samples spanning ten VQA domains, fourteen state-of-the-art VLMs exhibit 57.3-75.0% base mirage rates. Our proposed TC-LIA alone cuts this to 7.5% with 83.5% Related/Unrelated/Blank-Noise classification accuracy, and the ensemble reaches 84.3-88.4% accuracy with 5.9-7.2% mirage rates (best joint result: 88.4% accuracy, 6.4% mirage rate). Notably, an ensemble trained on a single backbone transfers well to unseen backbones, with the best-transferring source staying within 1.2% accuracy points of per-backbone training across thirteen held-out VLMs. --- ### Detect Before You Leap: Mirage Detection in Vision-Language Models Authors: Sayeed Shafayet Chowdhury, Md. Shaown Miah, S. M. Taiabul Haque, Syed Ishtiaque Ahmed Published: 2026-05-29 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2606.00435v3 Vision-language models (VLMs) can produce confident visual answers even when the required visual evidence is missing, blank, or unrelated to the question. This failure mode, recently described as mirage (Asadi et al., 2026), is especially concerning in medical and document VQA, where visually ungrounded answers may be mistaken for image-based evidence. We study pre-release mirage detection: given an image-question pair, determine whether a VLM's answer should be released or the system should abstain before the answer reaches the user. We propose Text-Conditioned Layer-wise Internal Alignment (TC-LIA), a model-agnostic method that probes patch-token representations across the layers of a CLIP ViT-H/14 vision encoder. The key idea is to project layer-wise image patch tokens into the final CLIP embedding space and measure their similarity with the question embedding, tracking whether question-relevant visual evidence emerges across vision layers. TC-LIA summarizes this trajectory using final image-text cosine similarity, late-layer top-k patch-text alignment, early-to-late gain, and layer-wise slope. These features are combined with pixel-statistic-based blank/noise detection, zero-shot domain routing, and structured VLM self-assessment in an ensemble classifier. We evaluate on 19,004 samples spanning ten VQA domains, including medical imaging, document understanding, scene text, reasoning, and video understanding, with four input conditions: RELATED, IN-DOMAIN UNRELATED, OUT-OF-DOMAIN UNRELATED, and BLANK/NOISE. Across fourteen VLMs, base prompt mirage rates range from 57.3-75.0%. TC-LIA alone reduces the mirage rate to 7.5% at 83.5% accuracy; ensemble fusion further improves performance to 84.5-88.4% accuracy with 5.7-7.2% mirage rates. The best result, obtained with Qwen2.5-VL-72B, achieves 88.4% accuracy and a 6.4% mirage rate. --- ### Grounded Decoding: Retrieval-Anchored Probability Fusion for Faithful RAG Authors: Ibne Farabi Shihab, Fariya Afrin, Sanjeda Akter, Anuj Sharma Published: 2026-05-29 Categories: cs.LG arXiv: https://arxiv.org/abs/2606.00432v1 As retrieval-augmented generation (RAG) systems scale, it becomes increasingly challenging to ensure faithful grounding in external evidence. Large language models may still prioritize parametric knowledge over retrieved information when conflicts arise. We propose a novel training-free decoding framework, \emph{Grounded Decoding}, designed to improve factual consistency in RAG without modifying model parameters. Unlike standard approaches that rely on a single conditional distribution, our method constructs two matched-prompt distributions at every generation step: (1) a full RAG distribution conditioned on the query, retrieved documents, and generated prefix, and (2) a retrieval-only distribution conditioned solely on retrieved evidence and the same prefix. The final next-token distribution is derived as the unique solution to a KL-barycenter objective over the probability simplex, yielding a normalized geometric fusion of the two distributions.This formulation naturally recovers standard RAG when the grounding weight is zero and smoothly shifts probability mass toward retrieved evidence as grounding strength increases. We further introduce a conflict-aware adaptive weighting scheme that dynamically adjusts grounding based on distributional disagreement and retriever confidence. Experiments on ALCE, Natural Questions, and FActScore demonstrate consistent improvements in factual accuracy and citation quality over standard RAG and competitive decoding-time baselines, while maintaining fluency. Our results indicate that probability-level fusion provides a strong and efficient alternative to logit-level intervention methods for faithful RAG decoding. --- ### Variance-sensitive Thompson sampling for generalised linear bandits, revisited Authors: Tom Perneczky, Marc Abeille, David Janz Published: 2026-05-29 Categories: cs.LG arXiv: https://arxiv.org/abs/2606.00431v1 We prove a variance-sensitive regret bound for Thompson sampling in stochastic generalised linear bandits. The argument assumes a warm-up, after which the regret is controlled through using the Gaussian Poincaré inequality. This bypasses the point at which previous optimism-based analyses break down. Removing the warm-up while retaining the same variance-sensitive scaling remains open, and appears nontrivial. --- ### Finer Parameter Steps for Low-Rank PEFT: A Controlled Study with CP Tensor Adapters Authors: Xinjue Wang, Xiuheng Wang, Yejun Zhang, Sergiy A. Vorobyov, Esa Ollila, Zhi-Yong Wang Published: 2026-05-29 Categories: cs.LG, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2606.00428v1 Low-rank adapters are usually compared by sweeping a small set of ranks, but the rank also fixes the resolution of the parameter budget. For a $2048{\times}2048$ OPT attention projection, increasing LoRA by one rank stores $4096$ trainable scalars, leaving large gaps between feasible low-budget adapter sizes. This paper asks whether a tensorized adapter with finer capacity increments changes the observed accuracy--budget trade-off. We instantiate this question with fixed-component canonical polyadic (CP) tensor adapters. Under a $32{\times}64{\times}32{\times}64$ tensorization, one normalized CP component stores $193$ trainable scalars per projection, about $21$ times smaller than one LoRA rank step. We compare CP adapters and LoRA on OPT-1.3B across SST-2, RTE, and BoolQ under matched target modules, training protocol, data caps, and seed schedules. CP trains stably and fills the gaps between LoRA ranks, but the effect is task-dependent: SST-2 reaches an early low-budget plateau, BoolQ benefits from additional CP components before saturating slightly below LoRA, and RTE remains LoRA-favored. Finer parameter steps are therefore useful for diagnosing PEFT budget sensitivity, but they do not by themselves guarantee a better accuracy--budget curve. --- ### Topology-Aware State Abstraction with Tangle Cores for Markov Decision Processes Authors: Ibne Farabi Shihab, Sanjeda Akter, Anuj Sharma Published: 2026-05-29 Categories: cs.LG arXiv: https://arxiv.org/abs/2606.00427v1 State abstraction in reinforcement learning is usually formulated as a partition of states based on reward and transition similarity. This excludes a common structural pattern in navigation, graph, and hierarchical decision problems: interface states such as doors, hubs, and bottlenecks naturally participate in more than one region. We introduce \emph{tangle-core abstraction}, an overlapping state-abstraction framework based on graph tangles of empirical transition graphs. The method constructs abstract states from consistently oriented low-order separations and represents shared interfaces through a membership kernel rather than a hard partition. We give value-preservation guarantees for the induced overlapping abstract MDP under an explicit action-consistency condition, identify an interior-homogeneity/boundary-leakage error decomposition, and prove a quantitative interface-overlap result showing when hard partitions incur an avoidable boundary error. Empirically, tangle-core abstractions achieve favorable compression--return tradeoffs against reward-aware, learned, topological-map, and graph-partitioning baselines across bottlenecked tabular domains, procedurally generated mazes, and MiniGrid representations. We also identify a clear failure regime in which transition topology is uninformative, where tangles predictably offer little benefit. These results position graph tangles as an effective topology-aware abstraction prior for decision problems with shared interface structure. --- ### Canonicalized Stable-List Replay for Private Federated Continual Learning over Language-Model Embeddings Authors: Ibne Farabi Shihab, Abu Sa-Adat Mohamed Moon-Im Al Ahsan, Anuj Sharma Published: 2026-05-29 Categories: cs.LG arXiv: https://arxiv.org/abs/2606.00426v1 Federated continual learning (FCL) lets distributed clients adapt language-model heads to evolving NLP tasks without sharing raw text. Under user-level differential privacy (DP), replay-based continual learning faces a structural obstacle: clients can release only small noisy lists of candidate replay summaries, and those lists are unordered across clients. We introduce Canonicalized Stable-List Replay (CSLR), where clients privately produce candidate replay distributions over a shared sentence-embedding space and the server aligns them using signatures induced by public anchor sentences. The anchors provide identifiability for aggregation rather than additional replay data. We prove that, under an observable anchor-signature margin, $O(\log(N/η)/p)$ anchors distinguish $N$ candidate list elements with probability at least $1-η$, and we give a scoped anchorless non-identifiability result for unordered-label oracle models. Across five seeds on continual classification, NER, and dialogue benchmarks, CSLR improves the final average task metric by 3.9--5.6 points over the strongest non-CSLR DP baseline at $\eps=4$ under the reported replay-release budget, while also outperforming Hungarian and optimal-transport matchers. The formal privacy guarantee covers replay release; end-to-end private training additionally requires composition with a private optimizer for task-head updates. --- ### Empirical Likelihood with Generative AI Authors: Jiguang Li, Sid Kankanala, Veronika Rockova Published: 2026-05-29 Categories: stat.ME, stat.ML arXiv: https://arxiv.org/abs/2606.00425v1 Moment conditions are widely used to identify parameters in models where the full likelihood is either unknown or intentionally left unspecified. Empirical likelihood methods address this problem by assigning probability weights to the observed data so that the sample moment conditions hold exactly. Building on this idea, we propose a nonparametric Bayesian framework based on exponentially tilted empirical likelihood. This Bayesian formulation is particularly appealing in settings where prior information is more naturally specified on the observables rather than on the underlying parameters. Such settings arise in the presence of auxiliary data sources or synthetic data generated by modern generative AI models.Inference proceeds by projecting posterior draws from a Dirichlet process onto the moment-restricted model, yielding a computationally efficient procedure that is naturally amenable to parallelization. We establish new Bernstein--von Mises and consistency theorems for the resulting projection posterior under both vanishing-prior and persistent-prior regimes. In an application to return prediction using overnight news headlines, we show that AI-generated auxiliary data can provide a useful source of indirect regularization when informative priors on the parameter itself are unavailable. --- ### Weak Critics Make Strong Learners: On-Policy Critique Distillation for Scalable Oversight Authors: Can Jin, Jiakang Li, Rui Wu, Eddy Z. Zhang, Dimitris N. Metaxas Published: 2026-05-29 Categories: cs.AI arXiv: https://arxiv.org/abs/2606.00424v2 As large language models become stronger, weak supervisors may fail to provide reliable labels, preferences, or final judgments for complex outputs, limiting both weak-to-strong generalization and scalable oversight. We study a more tractable form of weak supervision: using a weak model as a critic rather than as a labeler or judge. Instead of solving the task or selecting the correct answer, the weak critic only needs to provide a non-misleading revision direction that helps the strong model better use its own knowledge. We call this setting *weak-critic strong oversight*. We first show that weak critiques can improve frozen strong models at inference time, and that critique quality is key to this improvement. We then propose progressive on-policy critique distillation (**OPCD**), which filters high-quality critiques and distills critic-guided behavior into the strong model through adaptive self-teacher signals. Experiments on reasoning and alignment benchmarks show that our method improves strong models over training epochs, suggesting an effective path for scalable oversight with weak supervision. --- ### Weak Critics Make Strong Learners: On-Policy Critique Distillation for Scalable Oversight Authors: Can Jin, Jiakang Li, Rui Wu, Eddy Zhang, Dimitris N. Metaxas Published: 2026-05-29 Categories: cs.AI arXiv: https://arxiv.org/abs/2606.00424v1 As large language models become stronger, weak supervisors may fail to provide reliable labels, preferences, or final judgments for complex outputs, limiting both weak-to-strong generalization and scalable oversight. We study a more tractable form of weak supervision: using a weak model as a critic rather than as a labeler or judge. Instead of solving the task or selecting the correct answer, the weak critic only needs to provide a non-misleading revision direction that helps the strong model better use its own knowledge. We call this setting *weak-critic strong oversight*. We first show that weak critiques can improve frozen strong models at inference time, and that critique quality is key to this improvement. We then propose progressive on-policy critique distillation (**OPCD**), which filters high-quality critiques and distills critic-guided behavior into the strong model through adaptive self-teacher signals. Experiments on reasoning and alignment benchmarks show that our method improves strong models over training epochs, suggesting an effective path for scalable oversight with weak supervision. --- ### UniPinRec: Unifying Generative Retrieval and Ranking at Pinterest Scale Authors: Hanyu Li, Yi-Ping Hsu, Aditya Mantha, Prabhat Agarwal, Laksh Bhasin, Jialu Wang, Hongtao Lin, Bella Huang, Yaxin Li, Xinyi Li, Chuxi Wang, Kousik Rajesh et al. Published: 2026-05-29 Categories: cs.IR, cs.LG arXiv: https://arxiv.org/abs/2606.00422v1 Modern recommendation systems predominantly train retrieval and ranking as separate models despite both increasingly relying on large transformers encoding the same user behavior data, duplicating parameters, compute, and serving cost. Prior work unifies the model architecture but not the full pipeline: input formats, training procedures, and serving stacks remain fragmented across stages. We present UniPinRec, which achieves full-stack unification of retrieval and ranking at Pinterest: one input format, one model, one training stage, deployed within existing serving infrastructure. A shared transformer encodes the user action sequence into candidate-independent representations that branch into retrieval (ANN dot-product) and ranking (cross-attention) via task-specific heads. Three ideas make this work: (1) Masked Action Modeling (MAM) eliminates interleaving, enabling weight sharing without doubling context length; (2) Blended training examples pair action sequences with feedview impression slates to satisfy both objectives jointly; (3) Cross-stage KV cache sharing reuses user-history computation from retrieval for ranking, reducing total FLOPs versus serving two independent models. Deployed in the Pinterest core surfaces, UniPinRec delivers approximately +1% online engagement lift while cutting end-to-end serving latency by 11.1% and lifting QPS by 63.6%. To our knowledge, this is the first full-stack unification of retrieval and ranking, covering inputs, model, training and serving, deployed in a production recommendation system. --- ### Parameter-Free and Group Conditional Online Conformal Prediction Authors: Beepul Bharti, Ambar Pal, Jacopo Teneggi, Jeremias Sulam Published: 2026-05-29 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2606.00419v4 Uncertainty quantification (UQ) is critical for the deployment of machine learning predictors in real-world scenarios where the data distribution may shift over time (i.e., data may not be exchangeable). Online conformal prediction (OCP) methods address this issue at the expense of either (i) group-wise error control or (ii) learning-rate independent implementation. Group-conditional coverage is essential for fairness across different collections of data points and for providing finer UQ guarantees. Parameter-free optimization is crucial for robustness to adversarial and unknown data shifts. We propose a parameter-free algorithm for group-conditional OCP and demonstrate that it achieves the best group-conditional coverage guarantees. We evaluate our algorithm on synthetic and real-world data, demonstrating that our method not only improves the reliability of existing parameter-free OCP methods but also provides prediction intervals that are comparable in size to well-tuned group-conditional approaches. By unifying group-conditional coverage with parameter-free online algorithms, our work lays a foundation for fair and robust uncertainty quantification in shifting environments. --- ### AgentxGCore: Agentic AI for Next-Generation Mobile Core Network Authors: Maria Katarine Santana Barbosa, Kelvin L. Dias Published: 2026-05-29 Categories: cs.NI, cs.AI arXiv: https://arxiv.org/abs/2606.00417v1 To meet the stringent requirements of emerging applications and the increasingly complex network management and operation, the Next Generation Mobile Networks (NextG), or 6G, will adopt an AI-native architecture on the Core Network (CN). In this movement, the Third Generation Partnership Project (3GPP) has extended the cellular CN with new function as a first step toward integrating analytics, Artificial Intelligence (AI), and machine learning. However, those new functionalities are constrained by a centralized approach and managerial complexity. Furthermore, with the rise of Large Language Models (LLMs), a new era in network orchestration and management begins, leveraging and empowering the Intent-based Networking (IBN) paradigm. In addition, AI agents and Agentic AI integrate Reasoning and Acting (ReAct), enabling the usage of such intents to continuously interact with the network. Unlike state-of-the-art approaches that primarily employ Agentic AI to mitigate deployment and configuration complexity in the CN, this paper introduces AgentxGCore, which leverages an Agentic AI-Native layer to extend the 3GPP architecture and enable a system based on the existing APIs across the Beyond Next Generation Core (xGC) domain. This proposal establishes an AI-driven closed-loop for continuous optimization based on real-time information, enabling self-organization and self-adaptation. Our approach involves a multi-agent specialized system, divided into a network planner agent, capable of visualizing the network state and developing a plan to meet the intents, and a network executor, responsible for criticizing and executing the plan. To validate the proposed solution, an environment was built using an open-source CN, heterogeneous datasets, and different LLMs were employed to demonstrate its effectiveness. --- ### 4D Radar Meets LiDAR and Camera: Cooperative Perception under Adverse Weather Authors: Melih Yazgan, Iramm Hamdard, Qiyuan Wu, J. Marius Zoellner Published: 2026-05-29 Categories: cs.CV arXiv: https://arxiv.org/abs/2606.00416v1 Cooperative perception is important for autonomous driving but remains fragile when cameras and LiDAR degrade in adverse weather. We address this challenge by integrating 4D imaging radar as a weather-robust modality into collaborative perception and introducing a Doppler-guided spatial attention mechanism for multi-agent fusion. Our approach extends two representative backbones: a radar-camera pipeline where radar substitutes LiDAR, and a LiDAR-radar pipeline where radar complements LiDAR. To support evaluation, we release radar-augmented benchmarks, OPV2V-R and Adver-City-R, with physics-based LiDAR degradation. Experiments show strong robustness gains in fog and rain, including substantial improvements when radar replaces degraded LiDAR. Additional validation on MAN TruckScenes demonstrates transfer beyond simulation. Overall, our results highlight 4D imaging radar as a robust modality for all-weather collaborative perception. Dataset and code are available at: https://url.fzi.de/SlimComm. --- ### Auditing Near-Optimal Policies Can Be Exponentially Hard: Conditional Query Lower Bounds via Occupancy Rashomon Capacity Authors: Ibne Farabi Shihab, Sanjeda Akter, Anuj Sharma Published: 2026-05-29 Categories: cs.LG arXiv: https://arxiv.org/abs/2606.00414v1 When many reinforcement-learning policies achieve near-optimal return, a post-hoc auditor may have to distinguish among many behaviorally distinct but return-equivalent policies. We formalize this phenomenon through an occupancy-measure analogue of Rashomon capacity: the metric entropy of the near-optimal occupancy region, computed relative to an audited deployment class. Because occupancy measures identify behavior only up to occupancy equivalence, we formulate auditing at the occupancy-class level and distinguish exact local-query oracles from noisy sample-query oracles. Our main exact-query result is conditional: if the audited class contains a $2/H$-separated near-optimal packing whose local signatures are $b$-sparse, then exact local-query auditing requires $Ω(M/b)$ queries; when the packing realizes deployment-class capacity and $b=O(1)$, this becomes $Ω(2^{\Hopt^\cF(\eps)})$. We give a finite discounted hidden-branch MDP attaining this bound and show the exact Bayes success law. For noisy hidden-trigger testing, we prove a mixture lower bound of order $M/β$, where $β$ is the per-sample KL signal, yielding $Ω(2^{\Hopt^\cF(\eps)}/(ρ^2Δ^2))$ for capacity-order packings with $β=O(ρ^2Δ^2)$. We also provide a static target-recognition information lower bound, a transcript-compatible oracle-cover verification upper bound, and a canonical occupancy regularizer whose regularized audited capacity collapses when a trusted reference occupancy is available. Controlled benchmarks distinguish positive sparse-signature instances from high-capacity negative controls where exact auditing is easy, and map the noisy-trigger law to post-processed continuous-control and visual-RL auditing regimes. --- ### Riemannian Stochastic Optimization for Sufficient Dimension Reduction Authors: Thibault Pautrel, François Portier Published: 2026-05-29 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2606.00413v1 Sufficient dimension reduction (SDR) makes high-dimensional regression tractable by projecting the covariates onto a low-dimensional subspace that preserves the conditional mean of the response. Existing gradient-based estimators either operate in the ambient space and suffer from the curse of dimensionality, or localize in the reduced space at a per-outer-iteration cost at least quadratic in the sample size. We show that minimizers of the population Minimum Average Variance Estimation (MAVE) risk approximate the same Grassmannian target as the Outer Product of Gradients (OPG), and recast the empirical criterion as a smooth maximization on the Stiefel manifold with closed-form Riemannian gradient. The resulting algorithm, SMAVE, combines sparse projected-space nearest-neighbor localization with Riemannian stochastic gradient ascent. A simplified version comes with almost-sure convergence and a non-asymptotic rate matching the standard non-convex stochastic first-order scaling. Empirically, SMAVE matches or improves on RMAVE's synthetic subspace recovery at moderate-to-high ambient dimension, and on four real datasets it uniformly improves over OPG and is competitive with or outperforms RMAVE at orders of magnitude lower runtime. --- ### Masking Stale Observations Helps Search Agents -- Until It Doesn't: A Regime Map and Its Mechanism Authors: Haoxiang Zhang, Qixin Xu, Zhuofeng Li, Lei Zhang, Pengcheng Jiang, Yu Zhang, Julian McAuley Published: 2026-05-29 Categories: cs.CL, cs.AI, cs.IR arXiv: https://arxiv.org/abs/2606.00408v1 Long-horizon search agents accumulate large amounts of retrieved content across many tool calls, making context-budget efficiency increasingly important. A minimal intervention is to mask stale observations from the context as the trajectory progresses, but it remains unclear when this form of context management helps and why. We study observation masking through a systematic sweep over various agent backbones (4B to 284B parameters) and three retrievers on offline and live-web agentic search benchmarks. We find that the accuracy gain from masking follows an asymmetric inverted-U shape when plotted against the model's accuracy without context management: a plateau under weak retrievers, a peak when a strong retriever meets a mid-capacity model, and a sharp collapse when the model is saturated. This pattern reflects the interaction between retriever recall and the model's implicit filtering capacity, rather than either factor in isolation. Mechanistically, masking implements a token-for-turn trade-off: it removes observations the model has largely stopped attending to and pages the agent rarely re-opens. The added turns help when they convert failures into successes, but they fail when masking removes evidence the model would otherwise have used. We therefore reframe context management as a regime-dependent intervention and provide a holistic perspective for analyzing context use in agentic deep search. We release our scaffold and trajectories here (https://github.com/i-DeepSearch/observation-masking) to support future research. --- ### Rethinking Amortized Neural Representations for High-Resolution Terrain Elevation Data Authors: Haoan Feng, Xin Xu, Leila De Floriani Published: 2026-05-29 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2606.00404v1 Implicit neural representations (INRs) model a signal as a continuous coordinate-to-value function. For terrain elevation data, this supports analytic derivatives, arbitrary-resolution decoding, and a smooth surface model of the underlying heightfield. However, fitting and storing a separate INR for every tile does not scale to large terrain datasets. Amortized neural representations reduce this cost with a shared network: a new tile is mapped to a compact per-tile payload, and a shared decoder reconstructs the heightfield from it. Most such methods are hypernetworks that predict the payload in a single forward pass, while others recover it through a short per-tile optimization. These methods were developed primarily for natural images, and their suitability for terrain heightfields remains unclear. We introduce a controlled benchmark on a 1 m/pixel terrain dataset and evaluate three representative methods under a unified protocol. Observing a clear cross-domain gap, we propose HUVR+SIREN, a hypernetwork that adapts the strongest benchmarked method (HUVR) by replacing its coordinate decoder with a smooth, analytically differentiable one. It attains the best height and derivative fidelity on the benchmark with no additional per-tile storage and lower decode cost, and tolerates aggressive post-training quantization with negligible quality loss, giving a compact terrain neural format. Ablations and diagnostics further identify which design choices transfer to terrain and show that the per-tile bottleneck is already near its useful limit, leaving the remaining gap in the shared hypernetwork's architectural design. --- ### A Distribution-Free Framework for Rewrite-Based Human-text Detection via Knockoff Filtering Authors: Yi Liu Published: 2026-05-29 Categories: stat.ME, cs.AI, stat.AP arXiv: https://arxiv.org/abs/2606.00402v1 We propose a distribution-free statistical framework that converts arbitrary rewrite-based detectors into detectors with finite-sample FDR guarantees without retraining. Our key observation is that rewrite-based detection implicitly constructs knockoff samples, enabling LLM-generated text detection to be formulated as a multiple hypothesis testing problem with knockoff structure. This perspective separates the design of detection statistics from the control of false discoveries, allowing existing rewrite detectors to inherit finite-sample false discovery rate (FDR) guarantees through a simple calibration procedure. We demonstrate reliable FDR control with meaningful detection power across three detection models, 19 domains, and four LLMs. --- ### Data-Driven Spectral Prediction for Accelerating Large-Scale Electronic Structure Calculations Authors: Abhiram Badrinarayanan, Davor Davidovic, Edoardo Di Napoli, Jurica Novak, Luigi Genovese, Gustavo Ramirez-Hidalgo, Xinzhe Wu Published: 2026-05-29 Categories: physics.comp-ph, cond-mat.mtrl-sci, cs.LG, math.NA arXiv: https://arxiv.org/abs/2606.00401v1 Simulating large molecular systems comprising thousands of atoms requires highly scalable methodologies. While modern Density Functional Theory (DFT) codes exhibit linear scaling, solving the associated large, sparse generalized eigenproblems remains a critical computational bottleneck on exascale architectures. In the context of the LimitX project, we propose a data-driven framework to accelerate these calculations. By shifting the machine learning target from discrete eigenvalues to the coefficients of an interpolating Chebyshev polynomial, and by comparing both all-atom and fragment-based structural representations, we successfully overcome the dimensionality constraints of large-scale spectral prediction. We investigate three machine learning models (Kernel Ridge Regression, Graph Neural Networks, and Random Forests) trained on a novel 2 TB dataset of protein dimers. The predicted spectra provide initial guesses that effectively bypass early Self-Consistent Field (SCF) iterations in BigDFT. Ultimately, these spectral predictors will be deployed to dynamically optimize upcoming rational filter-based eigensolvers, such as FrASE, which is currently in initial development. --- ### Dynamic Proxy-Mixing: Transferring Replay Controllers from Small to Large Models for Continual Instruction Tuning Authors: Ibne Farabi Shihab, Fariya Afrin, Anuj Sharma Published: 2026-05-29 Categories: cs.LG arXiv: https://arxiv.org/abs/2606.00400v1 Continual instruction tuning updates a language model through a sequence of new domains, yet each update can progressively erode previously learned capabilities and alignment behavior. Replay is the standard mitigation, but fixed replay ratios are inherently limited because the optimal mixture varies with the current domain, the training stage, and the evolving vulnerability of prior behaviors. We propose PROX-YMIX, a framework that learns a dynamic replay controller on a small proxy model and transfers the frozen controller to a larger target. The controller never observes future tasks and constructs its state from normalized validation losses and their temporal dynamics, producing a masked mixture over the current task and accessible replay buffers. Our core empirical hypothesis is forgetting mirroring: task vulnerability rankings remain largely consistent across model scales even when absolute loss magnitudes differ. We validate this assumption empirically before transferring controllers across scales. On LLaMA-3-8B across five continual instruction tuning sequences, PROXYMIX improves average accuracy by 3.4 points, reduces final forgetting by 3.5 points, and raises safety score by 5.8 points over the strongest non-oracle baseline, at roughly 50x lower policy learning cost than Oracle Target RL. The framework is leakage free and architecture independent at the interface level, and we also identify settings where the proxy assumption breaks down, highlighting limitations for robust deployment. --- ### Multi-Objective Reference-Aligned Machine Unlearning Authors: Rasa Khosrowshahli, Stephen Asobiela, Beatrice Ombuki-Berman, Shahryar Rahnamayan Published: 2026-05-29 Categories: cs.LG arXiv: https://arxiv.org/abs/2606.00399v1 Machine unlearning aims to remove the influence of specific training samples while preserving the model's utility. Existing single-objective approaches, such as gradient ascent or random relabeling, often induce catastrophic forgetting due to conflicting optimization dynamics and unbounded forgetting objectives that cause the model to drift from its pre-trained knowledge. We propose Reference-Aligned UnLearning (RAUL), a multi-objective framework that jointly optimizes forgetting and retention by replacing unbounded loss maximization with a bounded KL alignment of predictions on forgotten samples toward a reference distribution representing unseen data, instantiated either as a uniform distribution or an empirical distribution from a held-out reference set, which constrains the forgetting objective and reduces gradient conflict with retention. The resulting multi-objective optimization (MOO) problem is solved via Jacobian descent, which aggregates multiple gradients into a direction that does not conflict. Our results demonstrate that RAUL achieves the closest gap compared to full retraining. --- ### PR2: Predictive Routing Replay for MoE-Based LLM Reinforcement Learning Authors: Daize Dong, Junlin Chen, Haolong Jia, Jiang Liu, Jiawei Wu, Huanwei Di, Jialian Wu, Zhengzhong Liu, Zicheng Liu, Emad Barsoum, Dimitris N. Metaxas, Hongyi Wang Published: 2026-05-29 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2606.00395v2 Mixture of Experts (MoE) Large Language Models (LLMs) achieve strong performance at scale. However, reinforcement learning (RL) on MoE-based LLMs often suffers from training instability. A root cause is router drift, i.e., expert activations can change drastically across model updates and differ between disaggregated rollout and training phases, causing large rollout--training mismatch and unstable importance sampling weights in PPO-style RL algorithms. Routing replay mitigates this issue by freezing the replay route within each reasoning trajectory, but it ignores how the router evolves under off-policy updates and thus causes router staleness. To address this limitation, we propose Predictive Routing Replay (PR2), which augments each router with a lightweight evolution predictor that learns to anticipate short-horizon router evolution. During the rollout phase, we use the predictive routing distribution to apply top-$k$ routing, enabling gradients to reach experts that are likely to become active after updates. During the training phase, we replay the resulting predicted route to retain consistency for stable importance estimation. Theoretical analysis and experiments support that PR2 reduces routing-induced mismatch, improves RL stability, and yields stronger performance across various reasoning benchmarks. --- ### AutoIQ: An Ensemble Framework for Automatic Assessment of Geometric Distortion in Prostate Diffusion-Weighted Imaging Authors: Haoran Sun, Lixia Wang, Yin-Chen Hsu, Hsu-Lei Lee, Chang Gao, Fei Han, Robert Grimm, Vibhas Deshpande, Ziyang Long, Hsin-Jung Yang, Rola Saouaf, Alessandro D'Agnolo et al. Published: 2026-05-29 Categories: eess.IV, cs.CV arXiv: https://arxiv.org/abs/2606.00393v1 Geometric distortion in prostate diffusion-weighted imaging (DWI) can impair lesion localization and reduce the reliability of MRI-based clinical assessment. We propose AutoIQ, an ensemble machine learning framework for automatic quantification and classification of DWI geometric distortion severity. A total of 140 retrospective prostate biparametric MRI examinations were analyzed, including 33 scans with severe distortion requiring repeat acquisition and 107 scans with acceptable distortion based on expert radiologist assessment. AutoIQ combines two complementary distortion quantification strategies: a segmentation-based method measuring prostate boundary mismatch between T2-weighted imaging (T2WI) and DWI, and a registration-based method estimating deformation magnitude after DWI-to-T2WI alignment. The resulting distortion scores were used to train individual classifiers and a logistic-regression ensemble model. Both computational methods significantly differentiated severe from acceptable distortion cases (p < 0.001). On an independent test set, the ensemble model achieved an accuracy of 0.95, F1-score of 0.93, and AUC of 0.98, outperforming individual models. These results suggest that AutoIQ can provide automated, quantitative quality assessment for prostate DWI and may help identify scans that require repeat acquisition. --- ### Detector-Evasive LLM Paraphrasing via Constrained Policy Optimization Authors: Mingyi Wang, Zhuoer Shen, Yuheng Bu, Shaofeng Zou Published: 2026-05-29 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2606.00392v1 AI-text detectors are vulnerable to paraphrasing and detector-guided paraphrasing attacks, but existing detector-evasion methods often lack precise control over semantic preservation. In particular, optimizing directly for detector evasion can degrade fine-grained semantics, whereas scalarized reward designs provide only indirect, weight-sensitive control over the evasion-semantics trade-off. We address this limitation by formulating detector-evasive LLM paraphrasing as a Constrained Markov Decision Process, where detector evasion is the primary objective and semantic preservation is enforced as an explicit constraint. We propose Detector Evasion Policy Optimization (DEPO), a Lagrangian primal-dual reinforcement learning algorithm with a novel GRPO-style group-based policy update. DEPO adaptively balances semantic preservation and detector evasion during training, enabling the policy to improve attack success within a prescribed semantic-preservation region. Experiments on MAGE, M4, RAID, and peer-review datasets, evaluated against MAGE, RoBERTa, RADAR, Binoculars, and Fast-DetectGPT detectors, show that DEPO achieves strong detector evasion while precisely satisfying the semantic preservation constraint. DEPO also exhibits cross-domain, cross-detector, and prompt-level robustness. --- ### Zamba2-VL Technical Report Authors: Hassan Shapourian, Kasra Hejazi, Olabode M. Sule, Beren Millidge Published: 2026-05-29 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2606.00390v1 We present Zamba2-VL, a suite of vision-language models built on Zamba2, a hybrid language-model architecture combining Mamba2 state-space layers with a small number of shared transformer blocks. Across a broad range of image understanding, reasoning, OCR, grounding, and counting benchmarks, Zamba2-VL is competitive with leading Transformer-based open-weight VLMs of comparable scale, including the Molmo2, Qwen3-VL, and InternVL3.5 families, and substantially outperforms prior SSM-based and hybrid VLMs such as VL-Mamba, Cobra, and mmMamba. Inheriting the near-linear prefill compute and small, near-constant recurrent state of its Zamba2 backbone, Zamba2-VL delivers roughly an order of magnitude lower time-to-first-token (TTFT) than these Transformer baselines at matched parameter scale, with the efficiency gap most pronounced at the smaller 1.2B and 2.7B scales most relevant to on-device and edge deployment. We release three models -- 1.2B, 2.7B, and 7B -- together with inference code at https://huggingface.co/collections/Zyphra/zamba2-vl. --- ### αDepth: Learning Single-Pass Soft Boundary Decomposition for Stereo Conversion Authors: Xiang Zhang, Yang Zhang, Lukas Mehl, Karlis Martins Briedis, Markus Gross, Christopher Schroers Published: 2026-05-29 Categories: cs.CV arXiv: https://arxiv.org/abs/2606.00386v1 Accurately modeling soft boundaries, e.g., hair and defocus blur, is a fundamental challenge in stereo conversion due to the ambiguous blending of foreground and background. Existing depth models primarily predict single-layer depth, leading to ambiguity in depth correspondence at soft boundaries. While matting techniques can capture opacity for layered modeling, they often struggle in complex scenes with multiple targets and usually require user intervention. This paper introduces αDepth, a layered representation that decomposes soft boundaries for high-fidelity stereo conversion. Specifically, we first resolve mixed color and depth ambiguity by estimating layered color and depth values at soft boundaries. Considering complex multi-target scenes, we design a Circular Alpha Representation (CAR) that shifts the paradigm from global target extraction to local boundary decomposition. Unlike prior matting methods restricted to a single foreground/background, CAR enables efficient scene-level inference without manual guidance. Extensive evaluations demonstrate that αDepth achieves state-of-the-art performance in stereo conversion, eliminating background bleeding and structural distortions at soft boundaries. --- ### VESTA: Visual Exploration with Statistical Tool Agents Authors: William Rudman, Abhishek Divekar, Kanishk Jain, Sebastian Joseph, Stella S. R. Offner, Matthew Lease, Kyle Mahowald, Greg Durrett, Junyi Jessy Li Published: 2026-05-29 Categories: cs.AI, cs.CL, cs.CV, cs.LG, stat.CO arXiv: https://arxiv.org/abs/2606.00384v2 Fitting quantitative models to data is a central step in scientific workflows, yet it remains one of the least automated. Recent agent-based systems leverage language and vision-language models (VLMs) to iteratively propose and refine statistical models, but these systems struggle on more challenging modeling tasks. To address these limitations, we introduce VESTA: Visual Exploration with Statistical Tool Agents, a framework that equips VLMs with a dynamically growing exploration toolkit to guide model refinement through data transformations, hypothesis-driven visualizations, and robust statistical tests. Unlike prior systems that rely on iterative critique alone, VESTA actively explores data before and during refinement by selecting or creating diagnostic tools, which accumulate in the model's context and can be reused later. We evaluate VESTA against established baselines in three toolkit configurations: no tools, static expert-written tools, and dynamic model-written tools. To support this evaluation, we introduce DAWN (Dataset for Automated Workflows and Numerical Modeling), a benchmark targeting distribution fitting and time series modeling with varying difficulty tiers, and culminating in real-world astronomy tasks including modeling initial mass functions and gravitational-wave chirp signals. We find that VESTA's dynamic tool creation outperforms prior agentic pipelines, with the largest gains on complex and domain-specific tasks. We further show that dynamically generated tools are substantially more sophisticated than those produced by existing visual tool-creation systems, covering more diagnostic categories per function and strongly preferring visual outputs that the VLM critic can reason over directly. ---