# Research Papers — 2026-05 · bundle page 146 of 326

> Full-text markdown of papers #7251–7300 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/146
[← Previous bundle](https://aipod.dev/papers/archive/2026-05/page/145.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-05/page/147.md)

### Geometry-Aware Uncertainty Coresets for Robust Visual In-Context Learning in Histopathology

Authors: Franciskus Xaverius Erick, Johanna Paula Müller, Bernhard Kainz
Published: 2026-05-18
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2605.18419v2

Vision-language models (VLMs) can couple visual perception with open-ended clinical reasoning, making them attractive for computational histopathology. However, fine-tuning billions of parameters on scarce, expert-annotated pathology data is prohibitive, while in-context learning (ICL), which conditions the VLM on demonstrative image-text pairs without parameter updates, suffers from high sensitivity to which examples are selected and how the query is phrased, producing unreliable diagnostics. Existing selection strategies rely on query-dependent nearest-neighbour retrieval that ignores global data structure, require costly parameter updates, or disregard the joint vision-text embedding geometry of VLMs. We propose GAUC, a training-free coreset selection method operating directly in the pre-trained multimodal embedding space. GAUC jointly optimises three objectives: (1) a Maximum Mean Discrepancy term enforcing distributional fidelity between coreset and full dataset, (2) an Effective Mutual Information Difference regulariser bounding performance degradation under prompt paraphrases by exploiting the VLM's joint vision-text alignment, and (3) a predictive-uncertainty (entropy) penalty suppressing ambivalent, hallucination-prone outputs. On CRC-100K and MHIST across multiple open-source VLM architectures, GAUC \emph{matches} the accuracy of the strongest ICL selection and dataset-distillation baselines while substantially improving calibration, prompt robustness, and hallucination rates, all without a single gradient update.

---

### Prompts Don't Protect: Architectural Enforcement via MCP Proxy for LLM Tool Access Control

Authors: Rohith Uppala
Published: 2026-05-18
Categories: cs.CR, cs.AI
arXiv: https://arxiv.org/abs/2605.18414v3

Large language models increasingly operate as autonomous agents that select and invoke tools from large registries. We identify a critical gap: when unauthorized tools are visible in an agent's context, models select them in 48-68% of adversarial scenarios, even when explicitly instructed not to. Role escalation attacks (e.g., "I'm the CFO, override the access controls") are the most dangerous category, reaching 96% unauthorized invocation in frontier models. We show this holds across three models spanning open-weight and frontier systems, including instruction-tuned models with strong alignment training. Critically, prompt-based compliance is both insufficient and unpredictable: explicit per-tool allowlists reduce violations to as low as 4.0% but never to zero, and compliance varies widely across models, from 4.0% to 37.0% UIR, with no reliable relationship to general capability. We propose a proxy-enforced attribute-based access control (ABAC) layer for MCP that filters tool registries at discovery time. Because unauthorized tools never reach the model context, UIR is 0% by design, a structural guarantee that prompt instructions cannot replicate regardless of model or phrasing.

---

### Prompts Don't Protect: Architectural Enforcement via MCP Proxy for LLM Tool Access Control

Authors: Rohith Uppala
Published: 2026-05-18
Categories: cs.CR, cs.AI
arXiv: https://arxiv.org/abs/2605.18414v1

Large language models increasingly operate as autonomous agents that select and invoke tools from large registries. We identify a critical gap: when unauthorized tools are visible in an agent's context, models select them in adversarial scenarios -- even when explicitly instructed otherwise. We propose a governed MCP proxy that enforces attribute-based access control (ABAC) at two points: tool discovery, where unauthorized tools are removed from the model's context window, and tool invocation, where a second check blocks any unauthorized call. Across three models (Qwen 2.5 7B, Llama 3.1 8B, Claude Haiku 3.5) and 150 adversarial tasks spanning four attack categories, our proxy reduces unauthorized invocation rate (UIR) to 0% while adding under 50ms median latency. Prompt-based restrictions reduce UIR by only 11--18 percentage points, leaving substantial residual risk. Our results show that architectural enforcement -- not prompting -- is necessary for reliable tool access control in deployed agentic systems.

---

### Cracks in the Foundation: A Civil Infrastructure Dataset to Challenge Vision Foundation Models

Authors: Nicola Farronato, Niccolo Avogaro, Thomas Frick, Mattia Rigotti, Rizwan Ullah Khan, Michele Magno, Konrad Schindler, Cristiano Malossi, Florian Scheidegger
Published: 2026-05-18
Categories: cs.CV
arXiv: https://arxiv.org/abs/2605.18413v2

Automated structural health monitoring is essential to prevent catastrophic infrastructure failures. Precise, pixel-level defect segmentation is needed to accurately assess structural integrity, but progress in defect segmentation for civil infrastructures has been held back by an extreme scarcity of data, which requires costly expert annotation. The need for data is accentuated by algorithmic hurdles intrinsic to the problem, including center-bias and the need to rely more on shape when inspecting nearly textureless building materials. To remove the bottleneck, we introduce Cracks in the Foundation (CiF), the largest and most detailed civil infrastructure (instance) segmentation dataset to date, comprising $\approx$150,000 high-resolution images meticulously curated over five years in collaboration with civil engineering experts. With the help of this unprecedented data source, we expose a blind spot of current visual AI: despite the advent of promptable Foundation Models (FMs) and Vision Language Models (VLMs), and despite the impressive abilities of today's specialised segmentation models, it turns out that dense image understanding in the built environment is nowhere near solved. Our evaluations indicate that even the most recent zero-shot FMs face significant challenges when deployed on real-world infrastructure and even the performance of specialised models with domain-specific supervision plateaus at $\approx$25% mAP. CiF establishes inspection of civil infrastructure, an elementary and seemingly easy perceptual task, as an open challenge that reveals fundamental weaknesses of present-day models trained predominantly on internet images, literally and figuratively highlighting cracks in the current foundation model paradigm.

---

### Historical Knowledge Graphs for Global Maritime Estimated Time of Arrival

Authors: Neofytos Dimitriou
Published: 2026-05-18
Categories: cs.CV
arXiv: https://arxiv.org/abs/2605.18408v1

Accurate vessel estimated-time-of-arrival forecasts are critical for port operations and decarbonization, yet global-scale travel-time prediction remains difficult without costly contextual data. Herein, I present a methodology for constructing a historical maritime knowledge graph using only Automatic Identification System (AIS) data. First, segmented trajectories are extracted from noisy AIS data using a Gaussian-mixture-model-based preprocessing pipeline. The graph is then constructed by iteratively processing the trajectories and storing speed distributions stratified by vessel type, time of travel, and direction of travel; the resulting global graph comprises 5,433 geohash-3 nodes and 12,334 edges. The graph can be queried to retrieve travel-time predictions between any two location via a hierarchical, priority-based system that uses historical statistics with principled fallback. On a temporally held-out test set, median RMSE is 22.75 min (segment-level) and 30.90 min (trajectory-level), with 69.1% of trajectories within 20% of actual arrival time. On a second external test set, median RMSE is 27.36 min (segment-level) and 37.46 min (trajectory-level), with 62.1% of trajectories within 20%. These results corroborate the promise of our method, enabling global travel-time prediction and providing a strong foundation for just-in-time arrival planning and emissions reduction.

---

### Qumus: Realization of An Embodied AI Quantum Material Experimentalist

Authors: Lihan Shi, Zhaoyi Joy Zheng, Xinzhe Juan, Yimin Wang, Ming Yin, Mayank Sengupta, Kristina Wolinski, Yanyu Jia, Jingzhi Shi, Derek Saucedo, Neill Saggi, Haosen Guan et al.
Published: 2026-05-18
Categories: cond-mat.mes-hall, cond-mat.mtrl-sci, cs.AI, cs.RO
arXiv: https://arxiv.org/abs/2605.18407v1

While modern Large Language Models (LLMs) and agentic artificial intelligence (AI) have demonstrated transformative capabilities in digital domains, the realization of embodied AI capable of real-world scientific discovery remains a difficult frontier. The advancements are hindered by the inherent complexity of integrating high-level reasoning, multimodal information processing and real-time physical execution. Here we introduce Qumus, the first AI quantum materials experimentalist. Physically embodied within a robotic mini-laboratory, Qumus is an intelligent, multimodal, and multi-agent system designed for the creation and nano-processing of atomically thin two-dimensional (2D) materials and stacked van der Waals (vdW) structures. Qumus autonomously navigates the full scientific cycle, from hypothesis generation and protocol planning to multi-step experimental execution, result analysis and reporting, acting as an experimentalist. Markedly, the system has achieved, for the first time, the AI-creation of graphene, as well as the first AI-fabrication of complex nanodevices including atomically thin field-effect transistors via vdW stacking. Qumus excels at these tasks by demonstrating autonomous error correction and closed-loop experimentation. Our results establish a generalizable framework for self-improving embodied AI systems that learn directly from the quantum world, opening a pathway toward accelerated discovery in quantum materials, electronics and beyond.

---

### Computational aspects of the Volterra Signature

Authors: Paul P. Hager, Fabian N. Harang, Luca Pelizzari, Samy Tindel
Published: 2026-05-18
Categories: math.NA, stat.ML
arXiv: https://arxiv.org/abs/2605.18406v1

The Volterra signature extends the classical path signature by incorporating general matrix-valued kernel into its iterated integral structure, yielding a flexible notion of memory for time series. Its components can be viewed as successive Picard iterates of linear controlled Volterra equations, making their exact computation of additional mathematical interest. However, the kernel introduces substantial algorithmic challenges. We provide a resolution by first decomposing the Chen-type convolution relation established in (arXiv:2603.04525) into analytic and arithmetic parts, and then introducing several efficient algorithms: a general approximative scheme with quadratic complexity $O(J^2)$ in the number of time steps $J$, an FFT-based acceleration with complexity $O(J\log J)$ for convolution kernels on uniform grids, and an exact recursion with complexity $O(JR^2)$ for kernels admitting a state-space representation of dimension $R$; retaining standard signature complexity in the path dimension and truncation level $N$. We further show that the number of factors in matrix-valued kernels of the form $K(t,s)=\sum_p k_p(t-s)A_p$ do not increase the asymptotic complexity in $J$ and $N$. Finally, we derive a finite-difference predictor--corrector scheme for the associated Volterra signature kernel. All algorithms are implemented in the publicly available JAX-based package "tensordev".

---

### SkillsVote: Lifecycle Governance of Agent Skills from Collection, Recommendation to Evolution

Authors: Hongyi Liu, Haoyan Yang, Tao Jiang, Bo Tang, Feiyu Xiong, Yuyu Luo, Zhiyu Li
Published: 2026-05-18
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2605.18401v2

Long-horizon LLM agents generate traces that could become reusable experience, but raw trajectories are noisy, local, and hard to govern. Agent Skills offer a structured artifact for combining procedural guidance, executable resources, and applicability boundaries. Yet open skill ecosystems contain redundant, uneven, environment-sensitive artifacts, and indiscriminate updates can pollute future context. We present SkillsVote, a lifecycle-governance framework for Agent Skills across collection, recommendation, attribution, and evolution. SkillsVote profiles a million-scale open source corpus for environment requirements, quality, and verifiability, and synthesizes tasks for verifiable skills. Before execution, it performs agentic library search over structured skill folders to expose instructional context. After execution, it decomposes trajectories into skill-linked subtasks, attributes outcomes to skill-guided execution, agent exploration, environment, and result signals, and admits only successful reusable discoveries to evidence-gated updates. Experiments on Terminal-Bench 2.0 and SWE-Bench Pro show that SkillsVote improves agent performance on challenging agentic coding benchmarks. The gains arise from two complementary pathways: online evolution over task streams at test time and offline transfer via frozen libraries built from either historical trajectories or curated open source skills.

---

### Generalize cross-ratios in n-dimensional Plane-Based Geometric Algebra

Authors: Enzo Harquin, Stephane Breuils, Pascal Monasse, Venceslas Biri, Vincent Nozick
Published: 2026-05-18
Categories: cs.CG, cs.CV
arXiv: https://arxiv.org/abs/2605.18398v1

We develop a complete theory of projective cross-ratios in n-dimensional Plane-Based Geometric Algebra (PGA), R(n,0,1), covering geometric objects of every grade: finite and ideal points, hyperplanes, and intermediate flats. For each object type and configuration, we establish an explicit cross-ratio formula, prove that it recovers the appropriate classical invariant, and identify the canonical pairwise measurement operator. A systematic duality analysis further revealed that all eight configurations organize into four dual pairs under the Hodge dual, and that all measurement operators reduce to either the commutator or the commutator dual, depending solely on the geometric configuration rather than on object grade. In each case the formula recovers the appropriate classical invariant: signed distance ratios for parallel configurations and sine cross-ratios for secant ones. These results establish the cross-ratio as a grade-agnostic projective invariant within PGA, and provide a constructive foundation for defining n-dimensional homographies directly from prescribed invariants.

---

### NEWTON: Agentic Planning for Physically Grounded Video Generation

Authors: Yuxiang Feng, Juncheng Wang, Chao Xu, Yijie Qian, Huihan Wang, Wenlong Hou, Yang Liu, Baigui Sun, Yong Liu, Shujun Wang
Published: 2026-05-18
Categories: cs.CV
arXiv: https://arxiv.org/abs/2605.18396v2

Video generation models produce visually compelling results but systematically violate physical commonsense -- on VideoPhy-2, the best model achieves only 32.6% joint accuracy. We identify a specification bottleneck: text prompts are lossy compression of the physical world, omitting the parameters that fully determine dynamics, and no amount of model scaling can recover what was never specified. From this diagnosis we derive three properties that physics conditioning must satisfy -- sufficiency, dynamism, and verifiability -- and show that no existing approach satisfies all three. We present NEWTON, in which video generation is demoted from the system output to one action inside an agent's toolbox: a learned planner orchestrates physics-aware tools (keyframe generation, scientific computation, prompt refinement) to construct rich conditioning, and a verifier closes the loop for iterative re-planning. The planner is the sole trainable component, optimized on-policy via Flow-GRPO inside the live multi-turn loop. On VideoPhy-2, NEWTON improves joint accuracy from 21.4% to 29.7% on LTX-Video and from 30.7% to 37.4% on Veo-3.1, without modifying either generator. Our project page: https://Newton026.github.io/newton

---

### Diagnosing Korean-Language LLM Political Bias via Census-Grounded Agent Simulation

Authors: Sungwoo Kang
Published: 2026-05-18
Categories: cs.CY, cs.AI
arXiv: https://arxiv.org/abs/2605.18395v1

Large language models (LLMs) exhibit systematic political biases in voter simulations, but their underlying mechanisms and cross-lingual generalizations remain poorly understood. We introduce Dynamo-K, a census-grounded simulation framework evaluating Korean-language LLM political behavior across four models on six Korean elections (2017-2025). Using this framework, we identify three systematic failure modes: (1) progressive bias in moderate agents, where explicit mitigation reduces Mean Absolute Error (MAE) by 5.2 times; (2) model-dependent third-party salience collapse, distinguishing between salience failure and decision bias; and (3) regional polarization collapse, where models bidirectionally under-predict historical party strongholds. To address these failures, we demonstrate that scenario reframing recovers 62% of 2017 MAE by restoring third-party visibility. Furthermore, we introduce a learned reweighting adapter that successfully calibrates opposing-valence models without relying on candidate names at train or test time. Validating our diagnostic framework, Dynamo-K accurately predicts 3/3 presidential winners - including a 2.1%p MAE on the highly contested 0.73%p-margin 2022 race - and correctly identifies the dominant party in a held-out local election. The pipeline is open-source and provides a scalable, cost-effective method for diagnosing LLM political behavior.

---

### Vision Foundation Models as Generalist Tokenizers for Image Generation

Authors: Anlin Zheng, Qi Han, Xin Wen, Chuofan Ma, Lanxi Gong, Gang Yu, Xiangyu Zhang, Xiaojuan Qi
Published: 2026-05-18
Categories: cs.CV
arXiv: https://arxiv.org/abs/2605.18390v1

In this work, we explore the largely unexplored direction of building a generalist image tokenizer directly on top of a frozen vision foundation model (VFM). To build this tokenizer, we utilize a frozen VFM as the encoder and introduce two key innovations: (1) a region-adaptive quantization framework to eliminate spatial redundancy in standard 2D grid features, and (2) a semantic reconstruction objective that aligns the decoded outputs with the VFM's representations to preserve semantic fidelity. Grounded in these designs, we propose VFMTok, a generalist visual tokenizer capable of operating seamlessly in both discrete and continuous latent spaces. VFMTok achieves substantial improvements in synthesis quality while drastically enhancing token efficiency. For discrete autoregressive (AR) generation, it accelerates model convergence by \textbf{3 times} and achieves a state-of-the-art gFID of \textbf{1.36} on ImageNet class-conditional synthesis. Similarly, for continuous-space generation, integrating VFMTok with a denoising model yields an exceptional gFID of \textbf{1.25}. Furthermore, because the latent space inherently captures rich spatial semantics, VFMTok enables high-fidelity class-conditional synthesis without classifier-free guidance (\textbf{w/o CFG}) across both generative paradigms, significantly accelerating inference speed. Beyond these remarkable empirical results, we systematically investigate the underlying mechanisms of our approach. We discover that the specific self-supervised learning objectives utilized during VFM pre-training dictate its effectiveness as a tokenizer. Specifically, a VFM jointly optimized with global contrastive learning and latent masked image modeling provides the optimal representations for image tokenization. These insights establish a strong foundation and offer valuable guidance for the design of future image tokenizers.

---

### Spherical Harmonic Optimal Transport: Application to Climate Models Comparisons

Authors: Pierre Houédry, Iskander Legheraba, Léo Buecher, Nicolas Courty
Published: 2026-05-18
Categories: cs.LG, math.OC
arXiv: https://arxiv.org/abs/2605.18389v2

Optimal transport provides a powerful framework for comparing measures while respecting the geometry of their support, but comes with an expensive computational cost, hindering its potential application to real world use cases. On manifolds, convolutional algorithms based on the heat kernel have been proposed to alleviate this cost, but their theoretical properties remain largely unexplored. We establish that the heat kernel cost converges to the optimal transport cost as time vanishes in the balanced and unbalanced cases. In the specific case of the 2-sphere $\mathbb{S}^2$, we ensure that the associated Sinkhorn divergences retains the desirable geometric and analytic properties of classical optimal transport discrepancies. Moreover, we leverage the harmonic structure of the sphere to derive a fast Sinkhorn algorithm, requiring only $\mathcal{O}(n)$ memory and $\mathcal{O}(n^{3/2})$ time per iteration, with fully dense GPU-friendly operations. We validate its computational efficiency on synthetic data, and discuss its potential use in the evaluation of global climate models, providing both spatial and seasonal insights into models performances.

---

### Graph Hierarchical Recurrence for Long-Range Generalization

Authors: Stefano Carotti, Marco Pacini, Alessio Gravina, Davide Bacciu, Bruno Lepri, Sebastiano Bontorin
Published: 2026-05-18
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2605.18387v1

Graph Neural Networks (GNNs) and Graph Transformers (GTs) are now a fundamental paradigm for graph learning, combining the representation-learning capabilities of deep models with the sample efficiency induced by their inductive biases. Despite their effectiveness, a large body of work has shown that these models still face fundamental limitations in tasks that require capturing correlations between distant regions of a graph. To address this issue, we introduce Graph Hierarchical Recurrence (GHR), a novel framework that operates jointly on the input graph and on a hierarchical abstraction obtained through pooling. We also show that the limitations of existing models are even more pronounced in out-of-range generalization, where test instances involve interactions over distances longer than those observed during training. By contrast, despite its simple design, GHR provides three key advantages: strong performance on long-range dependencies, improved out-of-range generalization, and high parameter efficiency. To corroborate these claims, we show that across a broad set of long-range benchmarks, GHR consistently outperforms existing graph models while using as little as 1% of the parameters of current state-of-the-art models. These results suggest a complementary direction to the current trend of scaling architectures to obtain graph foundation models, indicating that increased model capacity alone may not be sufficient for generalization.

---

### Towards Ubiquitous Mapping and Localization for Dynamic Indoor Environments

Authors: Halim Djerroud, Nico Steyn, Olivier Rabreau, Patrick Bonnin, Abderraouf Benali
Published: 2026-05-18
Categories: cs.RO, cs.AI
arXiv: https://arxiv.org/abs/2605.18385v1

We present UbiSLAM, an innovative solution for real-time mapping and localization in dynamic indoor environments. By deploying a network of fixed RGB-D cameras strategically throughout the workspace, UbiSLAM addresses limitations commonly encountered in traditional SLAM systems, such as sensitivity to environmental changes and reliance on mobile unit sensors. This fixed-sensor approach enables real-time, comprehensive mapping, enhancing the localization accuracy and responsiveness of robots operating within the environment. The centralized map generated by UbiSLAM is continuously updated, providing robots with an accurate global view, which improves navigation, minimizes collisions, and facilitates smoother human-robot interactions in shared spaces. Beyond its advantages, UbiSLAM faces challenges, particularly in ensuring complete spatial coverage and managing blind spots, which necessitate data integration from the robots themselves. In this paper we discuss potential solutions, such as automatic calibration for optimal camera placement and orientation, along with enhanced communication protocols for real-time data sharing. The proposed model reduces the computational load on individual robotic units, allowing less complex robotic platforms to operate effectively while enhancing the robustness of the overall system.

---

### TabH2O: A Unified Foundation Model for Tabular Prediction

Authors: Pascal Pfeiffer, Dmitry Gordeev, Mathias Müller, Laura Fink, Joan Salvà Soler, Mark Landry, Branden Murray, Marcos V. Conde, Sri Satish Ambati
Published: 2026-05-18
Categories: cs.LG
arXiv: https://arxiv.org/abs/2605.18383v2

We present TabH2O, a foundation model for tabular data that performs classification and regression in a single forward pass via in-context learning. TabH2O builds on the TabICL architecture with several key modifications: (1) unified training, a single model handles both classification and regression via a dual-head architecture, eliminating the need for separate models and reducing total pretraining cost; (2) single-stage pretraining, training stability improvements (bounded scalable softmax, inter-stage normalization, learnable residual scaling, logit soft-capping) eliminate the need for multi-stage curriculum learning, enabling training with full-length sequences from the start; and (3) noise-aware pretraining, synthetic datasets include explicit noise dimensions to teach the model robustness to irrelevant features. We evaluate TabH2O v1.1 (29.2M parameters) on the TALENT benchmark (300 datasets), where it achieves an average rank of 2.54 out of 6 evaluated methods, outperforming tuned CatBoost (4.00), H2O AutoML (4.28), LightGBM (4.98), and TabPFN v2.6 (2.80), and competitive compared to TabICL v2 (2.13), while placing in the top-3 on 80% of the testing datasets across classification and regression tasks. We also achieve state-of-the-art results on TabArena. Moreover, our single model is well-suited to tabular datasets up to roughly 500,000 rows and 100 features.

---

### TabH2O: A Unified Foundation Model for Tabular Prediction

Authors: Pascal Pfeiffer, Dmitry Gordeev, Mathias Müller, Laura Fink, Joan Salvà Soler, Mark Landry, Branden Murray, Marcos V. Conde, Sri Satish Ambati
Published: 2026-05-18
Categories: cs.LG
arXiv: https://arxiv.org/abs/2605.18383v1

We present TabH2O, a foundation model for tabular data that performs classification and regression in a single forward pass via in-context learning. TabH2O builds on the TabICL architecture with several key modifications: (1) unified training, a single model handles both classification and regression via a dual-head architecture, eliminating the need for separate models and reducing total pretraining cost; (2) single-stage pretraining, training stability improvements (bounded scalable softmax, inter-stage normalization, learnable residual scaling, logit soft-capping) eliminate the need for multi-stage curriculum learning, enabling training with full-length sequences from the start; and (3) noise-aware pretraining, synthetic datasets include explicit noise dimensions to teach the model robustness to irrelevant features. We evaluate TabH2O v1 (29.2M parameters) on the TALENT benchmark (300 datasets), where it achieves an average rank of 2.55 out of 6 evaluated methods, outperforming tuned CatBoost (4.07), H2O AutoML (4.18), and LightGBM (5.08), competitive with TabPFN v2.6 (2.74), and behind TabICL v2 (2.12), while placing in the top-3 on 81% of the testing datasets across classification and regression tasks.

---

### Probing SMEFT Operators through $t\bar{t}t\bar{t}$ Production with Hyper-Graph Neural Networks at the LHC

Authors: Amir Subba, Sanmay Ganguly
Published: 2026-05-18
Categories: hep-ph, cs.AI, hep-ex
arXiv: https://arxiv.org/abs/2605.18382v1

We present a phenomenological study of $t\bar{t}t\bar{t}$ production in proton-proton collisions at $\sqrt{s} = 13$~TeV, using a Hyper-Graph Neural Network (H-GNN) to discriminate multilepton signal events from the dominant SM backgrounds, namely $t\bar{t}W$, $t\bar{t}Z$, $t\bar{t}H$, $t\bar{t}VV$, single-top associated production, and diboson and triboson processes. In the H-GNN architecture each event is represented as a hypergraph whose nodes correspond to reconstructed jets and leptons and whose hyperedges encode higher-order correlations among arbitrary subsets of these objects, allowing the network to learn the many-body kinematic structures that characterize the $t\bar{t}t\bar{t}$ final state. Combining same-sign di-lepton, tri-lepton, and four-lepton channels following a CMS-like event selection, the H-GNN attains an area under the ROC curve of $0.951$ for the $t\bar{t}t\bar{t}$ signal and yields a statistical significance of $Z = 9.11$ at an integrated luminosity of $\mathcal{L} = 140~\mathrm{fb}^{-1}$, to be compared with $Z = 8.62$ for a SPANet baseline, $Z = 7.37$ for a Particle Transformer baseline, and $Z = 5.13$ obtained by the ATLAS analysis, evaluated under identical event selection. We exploit the improved signal extraction to derive one- and two-parameter $95\%$ confidence level limits on the Wilson coefficients of the dimension-six operators $\mathcal{O}_{Φu}$, $\mathcal{O}^{(1)}_{tt}$, $\mathcal{O}^{(1)}_{qq}$, $\mathcal{O}^{(1)}_{qt}$, and $\mathcal{O}^{(8)}_{qt}$, and we project the expected sensitivity at the HL-LHC integrated luminosities of $1000~\mathrm{fb}^{-1}$ and $3000~\mathrm{fb}^{-1}$ with $50\%$ uncertainty on the background estimation.

---

### Generating Physically Consistent Molecules with Energy-Based Models

Authors: Christoph Griesbacher, Lea Bogensperger, Andreas Habring, Thomas Pock
Published: 2026-05-18
Categories: cs.LG
arXiv: https://arxiv.org/abs/2605.18381v1

Molecules in equilibrium follow a Boltzmann distribution, making the underlying energy landscape a physically grounded modeling objective. However, such landscapes are difficult to learn from data and, once learned, hard to sample from. Diffusion and flow-matching models sidestep these difficulties by learning a time-conditional score or transport field between noise and data, losing the energy inductive bias in exchange for a more tractable training objective. We introduce EBMol, an energy-based model (EBM) that restores this inductive bias by learning an atom-additive scalar potential without explicit simulation during training. Our method employs a flow-inspired Restoring Field Matching objective to approximate the energy landscape. We adopt the Mirror-Langevin algorithm for sampling, enabling unified updates of atomic positions and types, and incorporate parallel tempering for inference-time compute scaling. EBMol is the first EBM for 3D molecular generation to achieve state-of-the-art performance on QM9 and GEOM-Drugs. Moreover, we show that the learned energy landscape serves as a principled quality metric for ranking and filtering configurations, and demonstrate controllable generation without retraining through shape-steered sampling via potential composition and zero-shot linker design.

---

### QSTRBench: a New Benchmark to Evaluate the Ability of Language Models to Reason with Qualitative Spatial and Temporal Calculi

Authors: Anthony G. Cohn, Robert E. Blackwell
Published: 2026-05-18
Categories: cs.AI
arXiv: https://arxiv.org/abs/2605.18380v1

We introduce an extensive qualitative spatial and temporal reasoning (QSTR) benchmark for evaluating large language models (LLMs). We pose questions concerning compositional reasoning (using composition tables, CT), converse relations, and conceptual neighbourhoods (CN) for QSTR calculi, Point Algebra (PA), Allen's Interval Algebra, Interval and Duration (INDU), Region Connection Calculus (RCC-5, RCC-8, and RCC-22), the nine intersection model, cardinal direction calculus, and STAR. The RCC-22 CN is published here for the first time. An extended benchmark systematically varies question presentation including prefix/infix, words/symbols/nonce terms and schematic descriptions for selected calculi. We report results for contemporary frontier models. All models tested perform better than guessing but none can consistently answer all questions correctly. Performance varies sharply by calculus, with PA being the most straightforward, and RCC-22 the most difficult. We release the benchmark, and our results under an open licence to facilitate further assessment of qualitative spatio/temporal reasoning in LLMs.

---

### Beyond Square Roots: A Memory-Efficient Explicit Factorization for Multi-Epoch Private Learning

Authors: Nikita P. Kalinin, Aki Rehn, Joel Daniel Andersson, Antti Honkela, Christoph H. Lampert
Published: 2026-05-18
Categories: cs.LG
arXiv: https://arxiv.org/abs/2605.18379v2

Correlated-noise mechanisms are among the most promising approaches for improving the utility of differentially private model training, but rigorous guarantees require explicit, analyzable factorizations, and practical deployment requires memory efficiency. Recent works have developed banded inverse factorizations, which address both requirements by exploiting a banded structure in the correlation matrix. The bandwidth controls the size of the noise buffer used to correlate noise across iterations, and thus governs the tradeoff between utility and memory cost. At the two ends of this tradeoff, DP-$λ$CGD achieves high memory efficiency by using only a one-step noise buffer, but this limits its utility gains, while the banded inverse square root (BISR) factorization exploits larger correlation windows and is asymptotically optimal for large bandwidths but performs poorly at low bandwidths. To bridge this gap, we introduce $γ$-BIFR, a unified generalization of both factorizations. In the low-memory, low-bandwidth regime, $γ$-BIFR improves RMSE, amplified RMSE, and private training performance, while yielding tighter theoretical guarantees for multi-participation error in multi-epoch training.

---

### Beyond Square Roots: Explicit Memory-Efficient Factorization for Multi-Epoch Private Learning

Authors: Nikita P. Kalinin, Aki Rehn, Joel Daniel Andersson, Antti Honkela, Christoph H. Lampert
Published: 2026-05-18
Categories: cs.LG
arXiv: https://arxiv.org/abs/2605.18379v1

Correlated-noise mechanisms are among the most promising approaches for improving the utility of differentially private model training, but rigorous guarantees require explicit, analyzable factorizations, and practical deployment requires memory efficiency. Recent works have developed banded inverse factorizations, which address both requirements by exploiting a banded structure in the correlation matrix. The bandwidth controls the size of the noise buffer used to correlate noise across iterations, and thus governs the tradeoff between utility and memory cost. Existing factorizations highlight this tradeoff: DP-$λ$CGD achieves high memory efficiency by using only a one-step noise buffer, but this limits its utility gains, while the banded inverse square root (BISR) factorization exploits larger correlation windows and is asymptotically optimal for large bandwidths but performs poorly at low bandwidths. We propose $γ$-BIFR, a unified generalization of both factorizations. In the low-memory, low-bandwidth regime, $γ$-BIFR significantly improves RMSE, amplified RMSE, and private training performance, while yielding tighter theoretical guarantees for multi-participation error in multi-epoch training.

---

### Beyond Inference-Time Search: Reinforcement Learning Synthesizes Reusable Solvers

Authors: Soheyl Massoudi, Gabriel Apaza, Milad Habibi, Mark Fuge
Published: 2026-05-18
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2605.18374v1

Large language models (LLMs) typically approach combinatorial optimization as an inference-time procedure, solving each instance separately through sampling, search, or repeated prompting. We ask whether reinforcement learning can instead shift part of this reasoning cost into the weights of a code LLM, so that the model synthesizes a reusable solver for an entire problem family. We study this question on Synergistic Dependency Selection (SDS), a controlled variant of constrained Quadratic Knapsack designed to expose a specific failure mode: local signals and strict feasibility constraints make greedy heuristics attractive but unreliable. Under identical scaffolding, Best-of-64 base-model sampling saturates at an approximately 28.7% gap to the global Virtual Best Solver (VBS); code audits show that the base model often retrieves Simulated Annealing templates but misimplements the Metropolis acceptance rule. We fine-tune Qwen2.5-Coder-14B-Instruct with Group Relative Policy Optimization (GRPO) using a feasibility-gated reward and light structural scaffolding. The resulting policy converges to a constraint-aware Simulated Annealing template in 99.8% of feasible SDS outputs, achieves a 5.0% gap to that VBS, and is 91 times cheaper in post-generation execution/search cost than cumulative Best-of-64 evaluation. A compile-once check shows that one best frozen solver per seed remains highly competitive when reused unchanged across the SDS test set, while an additional-domain evaluation on Job Shop Scheduling provides narrower but positive evidence that the scaffold transfers beyond SDS. Negative ablations reveal the limits of this recipe: standard stabilizers degrade performance, a soft feasibility gate fails, and results remain sensitive to reward normalization and domain-specific design choices.

---

### Dynamic robotic cloth folding with efficient Koopman operator-based model predictive control

Authors: Edoardo Caldarelli, Franco Coltraro, Adrià Colomé, Lorenzo Rosasco, Carme Torras
Published: 2026-05-18
Categories: cs.RO, cs.LG, math.DS, math.OC
arXiv: https://arxiv.org/abs/2605.18373v1

Robotic cloth folding is a challenging task, particularly when considering dynamic folding tasks, which aim at folding cloth by fast motions that leverage its dynamics. When subject to such fast motions, the complexity of cloth dynamics hinders both system identification and planning of folding trajectories, resulting in a difficult simulation-to-reality transfer when using physical models of cloth. Compared to the dexterity that humans exhibit when performing folding tasks, robotic approaches usually employ small garments with quite rigid dynamics, and are either too slow, or fast but imprecise, requiring several attempts to achieve a reasonably good fold. In this paper, we tackle these challenges by generating fast folding trajectories with a novel model predictive controller, integrating physics-based simulation of cloth dynamics and efficient, kernel-based Koopman operator regression. Koopman operator regression, an increasingly popular machine learning technique for nonlinear system identification, is used to obtain a linear model for the cloth being folded. Such a surrogate model, trained with data from a high-fidelity, physics-based cloth simulator, can then be employed within a suitable model predictive control algorithm, in place of the costly, nonlinear one, to efficiently generate folding trajectories to be executed by a robotic manipulator. Both in simulated and real-robot experiments, we show how the linearization supplied by the Koopman operator-based model can be employed to efficiently generate fast folding trajectories to unseen poses, without sacrificing folding accuracy.

---

### The Hidden Cost of Contextual Sycophancy: an AI Literacy Intervention in Human-AI Collaboration

Authors: Cansu Koyuturk, Sabrina Guidotti, Dimitri Ognibene
Published: 2026-05-18
Categories: cs.HC, cs.AI, cs.CY, cs.ET
arXiv: https://arxiv.org/abs/2605.18372v2

Large Language Models (LLMs) are increasingly used in educational settings as interactive tools for collaboration. However, their tendency toward sycophancy, aligning with user beliefs even when incorrect, raises concerns for learning and decision-making, especially for less knowledgeable users. This study investigates how sycophantic alignment emerges in authentic multi-turn human-AI interactions and whether interventions targeting increasing AI literacy and prompting competencies can mitigate its effects. In a controlled mixed-design experiment, 60 participants completed analytical survival ranking tasks by first generating individual rankings and then making final decisions after collaborating with an AI assistant, both before and after receiving either general or sycophancy-focused prompting training. Preliminary results show that LLMs are highly sensitive to user input: lower-quality initial responses lead to poorer AI advice, suggesting that the model mirrors or incorporates user reasoning rather than correcting it or offering better alternatives that are missing or less frequent in the conversation. Critically, the propagation of user errors into AI responses significantly reduced both the quality of AI feedback and final user task performance, revealing a form of contextual sycophantic dependence. While the intervention did not eliminate the propagation of contextual errors, it significantly improved AI advice by reducing the direct mirroring of incorrect user rankings. These findings suggest that prompting and AI literacy alone may be insufficient to ensure epistemically independent AI support, highlighting the need for system-level approaches that better promote critical engagement in human-AI collaboration.

---

### On Stability and Decomposition of Sample Quantiles under Heavy-Tailed Distributions

Authors: Choudur Lakshminarayan
Published: 2026-05-18
Categories: stat.ML, cs.LG, math.ST
arXiv: https://arxiv.org/abs/2605.18370v2

We study sample quantiles of distributions indexed by estimated parameters, with a on Value-at-Risk related to linear projections of financial returns that whose underlying probability law is heavy-tailed. In this setting, the projection direction and the empirical quantile threshold are estimated from the data, so the standard Bahadur representation under a fixed distribution does not separate the distinct sources of instability. A canonical starting point is Bahadur's representation, which expresses the sample quantile through the empirical distribution function plus a remainder term \cite{bahadur1966}. Empirical-process theory provides a usable scaffolding through the mechanics of half-spaces, symmetric differences, and Glivenko--Cantelli uniform convergence. They yield stability bounds, but absorb changes in projection direction and changes in quantile threshold into a single symmetric-difference measure. Interestingly, a global uniform-convergence requirement is imposed on what is intrinsically a local quantile-stability problem. This paper introduces a Q-Q orthogonality formulation for separating projection-direction and quantile-threshold effects. The object of interest is the difference between the empirical quantile computed using the estimated projection direction and the population quantile computed at the reference projection direction. We decompose this difference into three terms, $\hat q_α(\hat w)-q_α(w_0)=D_1+D_2+D_3$. Here, $D_1$ measures the population quantile movement induced by perturbing the projection direction, $D_2$ measures the empirical quantile fluctuation with the projection direction held fixed, and $D_3$ is the Bahadur-type remainder.

---

### GeoFlow: Enforcing Implicit Geometric Consistency in Video Generation

Authors: Jan Ackermann, Shengqu Cai, Boyang Deng, Zhengfei Kuang, Songyou Peng, Gordon Wetzstein
Published: 2026-05-18
Categories: cs.CV
arXiv: https://arxiv.org/abs/2605.18365v1

Generating geometrically consistent videos remains an open challenge: text-to-video diffusion models trained on web-scale data treat geometry only implicitly, leading to object deformation, texture drift, and non-rigid backgrounds under camera motion. Existing solutions either improve consistency as a byproduct, apply only to static scenes or realign the latent space of the model completely. We introduce a geometry-consistency reward that directly measures whether motion in a generated video is compatible with a coherent scene. Our key insight is that in physically consistent videos, background motion should be explainable by rigid camera-induced flow, while independently moving objects should preserve appearance identity along motion trajectories. We operationalize this using optical flow, depth--pose predictions, and feature-based correspondence to separate rigid and dynamic regions and evaluate their respective consistency. Integrating this reward with reinforcement fine-tuning transforms geometric consistency from an emergent property into an explicit optimization objective for video generators. The approach is model agnostic and applies to diverse dynamic scenes containing both camera and object motion. Experiments show substantial reductions in temporal geometric artifacts over strong baselines while preserving perceptual quality. Code and model weights are published.

---

### Proximal basin hopping: global optimization with guarantees

Authors: Guillaume Lauga, Cesare Molinari, Samuel Vaiter
Published: 2026-05-18
Categories: cs.LG, math.OC
arXiv: https://arxiv.org/abs/2605.18364v2

Global optimization is a challenging problem, with plenty of algorithms displaying empirical success, but scarce theoretical backing. In this work, we propose a new theoretical framework called Proximal Basin Hopping (PBH), carefully tailored to combine proximal optimization and local minimization. We use it to construct a practical algorithm that converges to the global minimizer with high probability, when using a finite amount of samples. Proximal Basin Hopping outperforms well known algorithms with theoretical backing on standard synthetic hard functions, and real problems such as fitting scaling laws for deep learning. Furthermore, the higher the dimension, the better the performance gap.

---

### RAVE: Re-Allocating Visual Attention in Large Multimodal Models

Authors: Xi Leng, Xinhong Ma, Ziqiang Dong, Feng Zhang, Xiaoying Tang, Yang Yang, Guanjun Jiang
Published: 2026-05-18
Categories: cs.CV
arXiv: https://arxiv.org/abs/2605.18359v4

Large multimodal models (LMMs) inherit the self-attention mechanism of pretrained language backbones, yet standard attention can exhibit suboptimal allocation, including cross-modal misallocation between textual and visual evidence and intra-visual imbalance among visual tokens. We propose RAVE (Re-Allocating Visual Attention), a lightweight pair-gating mechanism that adds a learned query-key bias to pre-softmax attention scores over visual keys, derived from pre-RoPE query and key features. RAVE requires no architectural modification to the backbone and can be trained end-to-end with the rest of the model. Across a suite of multimodal benchmarks, RAVE improves over standard attention by an average of 3 points, with the largest gains on perception-intensive tasks -- including multilingual OCR, chart understanding, document VQA, and scene text VQA -- where accurate visual grounding is critical.

---

### RAVE: Re-Allocating Visual Attention in Large Multimodal Models

Authors: Xi Leng, Xinhong Ma, Ziqiang Dong, Feng Zhang, Xiaoying Tang, Yang Yang, Guanjun Jiang
Published: 2026-05-18
Categories: cs.CV
arXiv: https://arxiv.org/abs/2605.18359v2

Large multimodal models (LMMs) inherit the self-attention mechanism of pretrained language backbones, yet standard attention can exhibit suboptimal allocation, including cross-modal misallocation between textual and visual evidence and intra-visual imbalance among visual tokens. We propose RAVE (Re-Allocating Visual Attention), a lightweight pair-gating mechanism that adds a learned query-key bias to pre-softmax attention scores over visual keys, derived from pre-RoPE query and key features. RAVE requires no architectural modification to the backbone and can be trained end-to-end with the rest of the model. Across a suite of multimodal benchmarks, RAVE improves over standard attention by an average of 3 points, with the largest gains on perception-intensive tasks -- including multilingual OCR, chart understanding, document VQA, and scene text VQA -- where accurate visual grounding is critical.

---

### Decoupled Conformal Optimisation: Efficient Prediction Sets via Independent Tuning and Calibration

Authors: Fanyi Wu, Lihua Niu, Samuel Kaski, Michele Caprio
Published: 2026-05-18
Categories: cs.LG
arXiv: https://arxiv.org/abs/2605.18354v1

Bayesian conformal optimisation methods often use the same held-out data both to search for efficient prediction sets and to certify coverage or risk. This coupling is natural for high-probability risk-control guarantees, but it is not necessary when the target is standard finite-sample marginal conformal coverage. We propose Decoupled Conformal Optimisation (DCO), a train-tune-calibrate design principle that uses an independent tuning split for efficiency-oriented structural selection and a fresh calibration split for the final conformal quantile. Conditional on the tuned structure, standard split-conformal exchangeability yields finite-sample marginal coverage for any candidate class, without a confidence parameter or multiple-testing correction. DCO therefore targets a different finite-sample guarantee from PAC-style methods: marginal conformal coverage rather than high-probability risk control. Under consistency assumptions on the coupled risk bound, the two approaches nevertheless converge to the same population threshold. Across classification and regression benchmarks, including ImageNet-A, CIFAR-100, Diabetes, California Housing, and Concrete, DCO tracks the nominal coverage level closely while often reducing average prediction-set size or interval width relative to PAC-style calibration. On ImageNet-A, for example, the average set size decreases from $26.52$ to $25.26$ and the 95th-percentile set size from $58.95$ to $53.73$; on Diabetes, the average interval width decreases from $2.098$ to $1.914$.

---

### Presupposition and Reasoning in Conditionals: A Theory-Based Study of Humans and LLMs

Authors: Tara Azin, Yongan Yu, Raj Singh, Olessia Jouravlev
Published: 2026-05-18
Categories: cs.CL
arXiv: https://arxiv.org/abs/2605.18352v1

Presupposition projection in conditionals is central to theories of meaning and pragmatics, yet it remains largely unevaluated in large language models. We address this gap through a parallel behavioral study comparing human judgments and LLM predictions on a normed dataset of conditional sentences that controls the relation between the antecedent and the projected presupposition. We collect likelihood ratings from 120 participants and four LLMs under matched contextual conditions. Results show that humans integrate probabilistic and pragmatic cues in their judgment, whereas LLMs show variable alignment with human patterns. Using a linguistically motivated checklist within an LLM-as-a-Judge framework, we further evaluate model reasoning. We observe models that best match human ratings often lack coherent pragmatic reasoning, while models with stronger reasoning produce less human-like judgments. These findings suggest that LLMs' performance on such tasks may result from surface pattern matching rather than pragmatic competence. Our findings highlight the importance of benchmarks grounded in linguistic theory for comparing humans and models.

---

### Mapping the Fitness Landscape: A Structure-Guided Approach to Multi-Modal Optimization

Authors: Meng Xiang, Pei Yan
Published: 2026-05-18
Categories: cs.NE
arXiv: https://arxiv.org/abs/2605.18351v1

Multimodal optimization requires finding many optima rather than merely keeping a diverse population. Yet most niching-based evolutionary algorithms rely on distances or density estimators without explicitly recovering the underlying peak--basin organization in the decision space, which can lead to pseudo-multimodality: many distinct individuals ultimately collapse into only a few basins. We introduce Chaotic Landscape-Decoding Evolution (CLDE), a decision-space-centric framework that turns multimodal search into a closed loop of decode--value--allocate--refine. CLDE injects controlled global exploration via a logistic chaotic map with a decaying step size, then builds a $k$-nearest-neighbor graph on a decoding canvas and performs persistence-guided basin growing that merges peaks only when they are not separated by deep valleys. An adaptive persistence threshold continuously tunes the decoding resolution online to avoid over-fragmentation and over-merging. Guided by the decoded structure, CLDE carries out basin-wise selection and refinement to improve solution quality while preserving basin coverage. We instantiate CLDE as CLDE-S and CLDE-M for single- and multi-objective multimodal optimization. Experiments on 20 CEC2013 functions show that CLDE-S achieves strong peak ratio under the same evaluation budget, while on DTLZ and MMMOP suites CLDE-M attains competitive IGD/IGDx, with pronounced gains on strongly multimodal problems.

---

### Optimising CSRNet with parameter-free attention mechanisms for crowd counting in public transport

Authors: Aida Rostamza, Enrico Del Re, Joshua Cherian Varughese, Cristina Olaverri-Monreal
Published: 2026-05-18
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2605.18349v1

Occupancy estimation and crowd counting are critical tasks in designing smart and efficient public transport vehicles. Given that public transport loading can vary from sparse to crowded, classical models for occupancy estimation must be adapted to suit this purpose. Attention mechanisms have shown remarkable capability in enhancing the representational power of deep neural networks for crowd counting in congested scenes with occlusion, complex backgrounds, and perspective distortion. However, conventional approaches, often implemented as parameterized sub-networks within convolutional layers, inevitably increase model size and computational cost, limiting deployment on resource-constrained edge devices. This paper investigates the effectiveness of state-of-the-art parameter-free attention mechanisms for crowd counting and density map estimation in highly congested scenes. We evaluate channel-wise (PFCA), spatial-wise (SA), and 3-D (SimAM) modules and compare their performance with parameterized attention modules constrained to introduce no more than 1% additional parameters. Furthermore, we present a novel combination of attention mechanisms that combines the strengths of PFCA and SA (PFCASA) customized for analyzing video streams onboard public transport systems. Using CSRNet as the backbone, experiments on the ShanghaiTech dataset demonstrate that parameter-free attention mechanisms achieve comparable or superior accuracy without introducing additional model parameters. A detailed performance analysis further reveals that PFCASA outperforms other attention modules in scenes with fewer than 40 individuals, while PFCA shows greater effectiveness as crowd density increases, underscoring their potential applicability for integration into smart public transport modalities.

---

### Focused Forcing: Content-Aware Per-Frame KV Selection for Efficient Autoregressive Video Diffusion

Authors: Peiliang Cai, Evelyn Zhang, Jiacheng Liu, Hao Lin, Ruiqi Zhang, Weile Mo, Yue Ma, Shikang Zheng, Jiehang Huang, Dongrui Liu, Linfeng Zhang
Published: 2026-05-18
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2605.18346v1

Recent advances in autoregressive video diffusion have enabled sequential and streaming video generation. However, long-horizon generation requires increasingly large KV caches, making efficient compression without sacrificing quality challenging. Existing methods mostly select historical frames based on attention scores, but their context decisions remain coarse. When multiple frames are generated in the same chunk, these methods often apply a shared history selection to the whole chunk, score historical frames solely by attention, and assign head-wise budgets either uniformly or by attention-pattern heuristics rather than explicit head-importance estimation. We show that frames within the same generated chunk can depend on distinct historical frames, that the same historical frame can receive different attention scores as its relative temporal distance to the current frames changes, and that masking different heads induces unequal generation degradation. Motivated by these findings, we propose \textbf{Focused Forcing}, a training-free KV selection method that focuses cached history along both generated-frame and head dimensions. For each generated frame, Focused Forcing preserves the most relevant and distinctive historical frames by combining attention scores with diversity scores of historical frames, while assigning larger budgets to heads with higher estimated importance. Across multiple autoregressive generation paradigms, Focused Forcing achieves up to $\textbf{1.48}\times$ end-to-end acceleration without training, while \textbf{improving visual quality and text alignment}. \textit{Our code will be released on GitHub.}

---

### Hybrid Quantum-Classical Neural Architecture Search

Authors: Alberto Marchisio, Muhammad Kashif, Nouhaila Innan, Muhammad Shafique
Published: 2026-05-18
Categories: quant-ph, cs.LG
arXiv: https://arxiv.org/abs/2605.18345v1

Hybrid quantum-classical neural networks (HQNNs) are emerging as a practical approach for quantum machine learning in the noisy intermediate-scale quantum (NISQ) era, as they combine classical learning components with parameterized quantum circuits in an end-to-end trainable framework. However, their performance and efficiency depend strongly on architectural choices such as data encoding, circuit structure, measurement design, and the coupling between classical and quantum modules. This makes manual design increasingly difficult, especially when hardware limitations and resource constraints must also be taken into account. In this paper, we study the foundations of HQNNs and neural architecture search (NAS), discuss how NAS extends to quantum and hybrid settings, and demonstrate FLOPs-aware search (where FLOPs serve as a proxy for computational complexity), as an important hardware-aware direction for building HQNNs that are not only accurate but also computationally efficient and practically deployable.

---

### Robust Player-Conditional Champion Ranking for League of Legends: Style Similarity, Mastery Priors, and Archetype-Constrained Discovery

Authors: Min Heo, Pranav Kadiyam, Prasun Panthi
Published: 2026-05-18
Categories: stat.AP, cs.LG
arXiv: https://arxiv.org/abs/2605.18338v1

Champion recommendation in multiplayer online battle arena games is usually framed informally as a problem of metagame strength, personal comfort, or global win rate. We formalize champion recommendation in League of Legends as an interpretable, player-conditional ranking problem under sparse, noisy, and non-stationary behavioral data. The proposed framework combines four information sources: a population-strength proxy, player-style similarity, direct and indirect mastery priors, and archetype-level guardrails. The method uses robust median/MAD normalization, logarithmic transforms for skewed event counts, recency-weighted player style vectors, mastery-weighted champion-pool vectors, weighted cosine similarity, rank-scaled score components, and k-means++ clustering for coarse archetype support. The implemented prototype uses a Python/Pandas modeling layer, Supabase-backed storage, and a web-facing recommendation interface. Unlike black-box supervised win-prediction systems, the proposed method returns decomposed recommendation scores that can be inspected as expected-performance proxy, fit, mastery, and archetype compatibility. A single-player case study on a 100-game history for the player identifier DIVINERAINRACCON is included as an end-to-end sanity check. The manuscript is therefore a methods and systems contribution: it specifies a reproducible, modular, and auditable champion recommender and gives a validation protocol for future large-scale evaluation through temporal train-test splits, next-champion recovery, calibration analysis, and ablation studies.

---

### Infini-News: Efficiently Queryable Access to 1.3 Billion Processed Common Crawl News Articles

Authors: Ruggero Marino Lazzaroni, Jana Lasser, Kirill Solovev
Published: 2026-05-18
Categories: cs.CL
arXiv: https://arxiv.org/abs/2605.18337v1

Large-scale news corpora support a wide range of research in Computational Social Science and NLP, yet access remains constrained: commercial archives impose prohibitive costs and licensing restrictions, while open alternatives like Common Crawl's CC-News require terabyte-scale storage and computationally intensive processing. We present Infini-News, a retrieval toolkit and index for the entire CC-News archive from August 2016 to the latest available snapshot. Our contributions are threefold. First, we extract, clean the text, and parse the structured metadata of over 1.35B articles. Second, we enrich the corpus with language detection using three frontier language classifiers (GlotLID, lingua, and CommonLingua), and with multi-source geographic attribution that resolves a country of origin for 83.4% of articles across 222 countries. Third, we construct Infini-gram indexes: suffix-array structures that let researchers search the full archive for arbitrary text patterns in sub-second time. Together, these resources lower the barrier to longitudinal, cross-national media research.

---

### 3D Skew Gaussian Splatting with Any Camera Trajectory Visualization Engine

Authors: Beizhen Zhao, Yifan Zhou, Gaochao Song, Ziran Yin, Hao Wang
Published: 2026-05-18
Categories: cs.CV, cs.GR
arXiv: https://arxiv.org/abs/2605.18334v1

While 3D Gaussian Splatting (3DGS) has revolutionized real-time photorealistic view synthesis, its fundamental reliance on symmetric Gaussian distributions introduces visual artifacts that hinder accurate spatial data exploration. Specifically, symmetric kernels struggle to capture shape and color discontinuities , which cause blurriness and primitive redundancy that mislead human perception during visual analysis. To address these visualization barriers, we introduce 3D Skew Gaussian Splatting (3DSGS), a novel framework that significantly enhances the structural fidelity and compactness of explicit scene representations. Our key insight lies in extending the standard primitive to a general Skew Gaussian counterpart. This generalized primitive inherits the highly efficient rasterization properties of standard Gaussians while gaining intrinsic asymmetric modeling capabilities. We couple this with an enhanced opacity representation to better handle complex transparency, alongside a depth-aware densification strategy that intelligently manages primitive allocation. Furthermore, to make these advancements actionable for real-world visual analytics, we re-derive the CUDA rasterization pipeline to universally support both symmetric and skew Gaussians, integrating it into a decoupled, free-camera interactive visualization engine. Extensive experiments demonstrate that 3DSGS achieves superior rendering quality and structural compactness, particularly in regions with intricate details, while maintaining the real-time frame rates necessary for fluid interactive exploration. Supplementary derivations and visual results are available at \textbf{\textit{https://3d-skew-gs.github.io/}}.

---

### QLIF-CAST: Quantum Leaky-Integrate-and-Fire for Time-Series Weather Forecasting

Authors: Alberto Marchisio, Aayan Ebrahim, Nouhaila Innan, Muhammad Kashif, Muhammad Shafique
Published: 2026-05-18
Categories: quant-ph, cs.LG
arXiv: https://arxiv.org/abs/2605.18333v2

Accurate and efficient time-series forecasting remains a challenging problem for both classical and quantum neural architectures, particularly in multivariate environmental settings. This work adapts the Quantum Leaky Integrate-and-Fire (QLIF) spiking neural network for time-series regression tasks, specifically short-term multivariate weather forecasting. We extend QLIF beyond classification and demonstrate its applicability to continuous-valued prediction problems. The QLIF-CAST model encodes neuron excitation states as single-qubit quantum superpositions, driven by R_x rotation gates and T1 relaxation decay, and is embedded within a hybrid quantum-classical recurrent architecture. We conduct two distinct evaluations. First, a controlled comparison against a parameter-matched classical LIF baseline on a multivariate weather dataset shows that QLIF-CAST achieves 15.4% lower MSE and 4.4% lower MAE, demonstrating that quantum neuronal dynamics reduce prediction error over classical equivalents. Second, a cross-domain comparative analysis with state-of-the-art quantum LSTM (QLSTM) and quantum neural network (QNN) models on air quality and wind speed benchmarks reveals that QLIF-CAST converges in up to 94% less training time, occupying a distinct position in the speed-error trade-off space. Hardware verification on IBM Marrakesh (156-qubit QPU) confirms reliable circuit execution with only 1.2% average deviation from simulation.

---

### Same Signal, Different Semantics: A Cross-Framework Behavioral Analysis of Software Engineering Agents

Authors: Wei Ma, Zhi Chen, Jingxu Gu, Tianling Li, Shangqing Liu, Lingxiao Jiang
Published: 2026-05-18
Categories: cs.SE, cs.AI
arXiv: https://arxiv.org/abs/2605.18332v1

Behavioral studies of LLM-based software engineering agents extract operational rules about which trajectory shapes correlate with higher resolution rates: that a test step follows a code modification, that error cascades are short, or that trajectories are compact. Each rule is typically derived from a single framework, and whether it transfers, in sign as well as magnitude, to structurally different agent designs has not been directly tested. We address this at ecosystem scale: 64,380 SWE-bench runs from 126 agent configurations spanning 43 frameworks, where each configuration pairs an LLM with a framework (e.g., SWE-Agent, OpenHands) that supplies its tools and workflow. We separate framework effects from LLM effects by holding each layer fixed in turn, then measure one behavior-outcome effect per configuration and examine how those effects agree or disagree. Swapping the framework while the LLM is held fixed produces large behavioral differences in every action feature. On most signals, configurations disagree not merely in magnitude but in direction. Error rate is the cleanest case: 47 configurations resolve more issues when their error rate is lower, while 48 resolve more when it is higher. Five other continuous features and three of seven binary patterns from prior SE literature show similar directional disagreement. Framework identity accounts for more of this variation than LLM family: for mean turns, framework explains 64% of the between-configuration variance against the LLM's 10%. The implication is that the same observable behavioral signal can carry opposite meaning for different agent configurations. Behavioral findings from any single framework therefore warrant cross-configuration validation before being claimed as general.

---

### Prune, Update and Trim: Robust Structured Pruning for Large Language Models

Authors: Diego Coello de Portugal Mecke, Tom Hanika, Lars Schmidt-Thieme
Published: 2026-05-18
Categories: cs.LG
arXiv: https://arxiv.org/abs/2605.18331v2

Large Language Models (LLMs) have experienced significant growth and development in recent years. However, performing inference on LLMs remains costly, especially for long-context inference or in resource-constrained devices. This motivates the development of new post-training pruning (PTP) methods. These methods reduce LLMs' requirements by removing a substantial part of the model's parameters. The discarded weights are selected depending on their impact on the models performance. Current PTP methods prune the models by removing the less informative hidden nodes from the FFN layers, and the least important attention layers. We propose Putri, a PTP method that introduces three changes to the State-of-the-art. First, we update the un-pruned weights of the FFN to compensate for the introduced pruning error. Second, the FFN layers are pruned sequentially, taking into account the updates done to the previous layers. Third, instead of removing full attention layers, we remove individual attention-heads. We extend this method such that it can also address Grouped-Query Attention. In summary, Putri is a structure pruning method which remains simple while showing SOTA performance. Pruning experiments on multiple models with a wide variety of sparsity ranges and on different datasets, validate the generality of Putri. Notably, we demonstrate that, unlike previous methods, Putri can prune LLMs on extreme sparsity ratios. The code is available at: https://github.com/Coello-dev/Putri.

---

### Lost in the Folds: When Cross-Validation Is Not a Deep Ensemble for Uncertainty Estimation

Authors: Tristan Kirscher, Markus Bujotzek, Yannick Kirchhoff, Maximilian Rokuss, Fabian Isensee, Kim-Celine Kahl, Balint Kovacs, Klaus Maier-Hein
Published: 2026-05-18
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2605.18329v2

Ensemble disagreement is widely used as a proxy for epistemic uncertainty in medical image segmentation. In practice, many studies form ensembles via K-fold cross-validation (CV), yet refer to them as ``deep ensembles'' (DE). Because CV members are trained on different data subsets, their disagreement mixes seed-driven variability with data-exposure effects, which can change how uncertainty should be interpreted. We audit recent segmentation uncertainty studies and find that terminology--implementation mismatches are common. We then compare a standard 5-fold CV ensemble to a 5-member DE (fixed training set, different random seeds) under otherwise identical configurations on three multi-rater segmentation datasets spanning three modalities. We evaluate uncertainty for calibration, failure detection, ambiguity modeling, and robustness under distribution shift. DE match segmentation accuracy while improving calibration and failure detection, whereas CV ensembles sometimes correlate more strongly with inter-rater variability on the studied datasets. Thus, ensemble construction should be chosen to match the research question: DE for reliability-oriented use (e.g., selective referral/failure detection) and CV ensembles as a proxy for ambiguity. We provide a lightweight nnU-Net modification enabling DE training within the default pipeline.

---

### CineMatte: Background Matting for Virtual Production and Beyond

Authors: Yuanjian He, Chen Zhang, Fasheng Chen, Jiangbo Cao
Published: 2026-05-18
Categories: cs.CV
arXiv: https://arxiv.org/abs/2605.18328v1

LED Virtual Production (VP) uses large LED volumes to render backgrounds in real time, enabling in-camera visual effects but making post-shot changes labor-intensive. We address this with CineMatte, a robust background matting framework for VP and beyond. CineMatte employs a cross-attention-conditioned design. Instead of concatenating the background with the input, CineMatte employs a Siamese, frozen DINOv3 Vision Transformer with shared weights to encode the input frame and the captured background separately. A cross-attention module compares the two streams to predict the foreground, preserving pretrained semantics and improving robustness to background shifts. Previous ViT-based matting models use a parallel convolutional "detail branch" to recover fine details, which can cause boundary artifacts in real-world samples due to semantic misalignment with the backbone. We instead replace it with a pretrained, image-guided feature upsampler, which largely mitigates the problem. We also introduce CineMatte-4K, a 4K HDR image-video dataset captured on a professional LED VP stage. To the best of our knowledge, the image subset is the first dataset for VP matting and is non-synthetic, obtained via green-screen insertion; the video subset includes camera motion with tracked trajectories so that arbitrary backgrounds can be rendered later with correct parallax. Across CineMatte-4K and public benchmarks (VideoMatte240K, YouTubeMatte), CineMatte not only excels in VP but also generalizes robustly to real-world footage.

---

### Causely: A Causal Intelligence Layer for Enterprise AI A Benchmark Study on SRE and Reliability Workflows

Authors: Dhairya Dalal, Endre Sara, Ben Yemini, Christine Miller, Shmuel Kliger
Published: 2026-05-18
Categories: cs.AI
arXiv: https://arxiv.org/abs/2605.18327v1

AI agents deployed into SRE workflows currently derive their understanding of environment state from raw observability telemetry at query time, paying a semantic-interpretation tax in tokens, latency, and inferential reliability. We propose Causely, a causal intelligence layer that maintains a structured representation of environment topology, attribute dependencies, and causal relationships that are anchroed to a ontological representation of the managed environment. Causely transforms raw telemetry into a live, queryable model providing the semantic and causal foundation AI agents require to diagnose, evaluate impact, and act safely in production. We evaluate this value proposition through a benchmark study conducted in a controlled setting with injected faults in a 24-microservice OpenTelemetry demo application. Our experiments compare four agent configurations (Claude Code, OpenAI Codex, HolmesGPT with Sonnet and Gemini backends). Experiments are run with and without access to Causely under two scenarios: an active incident and a healthy baseline. On the active-fault scenario, causal grounding reduces mean time-to-diagnosis by 63\%, mean token consumption by 60\%, and mean tool-call count by 78\%, compressing the investigation footprint by 4.8$\times$ and lowering direct API cost per run by 57\%; root-cause-diagnosis accuracy rises from 75\% to 100\%.

---

### Improved Baselines with Representation Autoencoders

Authors: Jaskirat Singh, Boyang Zheng, Zongze Wu, Richard Zhang, Eli Shechtman, Saining Xie
Published: 2026-05-18
Categories: cs.CV, cs.AI, cs.GR, cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2605.18324v2

Representation Autoencoders (RAE) replace traditional VAE with pretrained vision encoders. In this paper, we systematically investigate several design choices and find three insights which simplify and improve RAE. First, we study a generalized formulation where the representation is defined as sum of the last k encoder layers rather than solely the final layer. This simple change greatly improves reconstruction without encoder finetuning or specialized data (e.g., text, faces). Second, we study the prevalent assumption that RAE (using pretrained representation as encoder) replaces representation alignment (REPA), which distills the same representation to intermediate layers instead. Through large-scale empirical analysis, we uncover a surprising finding: RAE and REPA exhibit complementary working mechanisms, allowing the same representation to be used as both encoder and target for intermediate diffusion layers. Finally, the original RAE struggles with classifier-free guidance (CFG) and requires training a second, weaker diffusion model for AutoGuidance (AG). We show that REPA itself can be viewed as x-prediction in RAE latent space. By simply re-parameterizing the output of the DiT model, it can provide guidance for "free". Overall, RAEv2 leads to more than 10x faster convergence over the original RAE, achieving a state-of-the-art gFID of 1.06 in just 80 epochs on ImageNet-256. On FDr6, RAEv2 achieves a state-of-the-art 2.17 at just 80 epochs compared to the previous best 3.26 (800 epochs) without any post-training. This motivates EPFID@k (epochs to reach unguided gFID < k) as a measure of training efficiency. RAEv2 attains an EPFID@2 of 35 epochs, versus 177 for the original RAE. We also validate our approach across diverse settings for text-to-image generation and navigation world models, showing consistent improvements. The code is available at https://raev2.github.io.

---

### ISEP: Implicit Support Expansion for Offline Reinforcement Learning via Stochastic Policy Optimization

Authors: Yifei Chen, Shaoqin Zhu, Xiaoqiang Ji
Published: 2026-05-18
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2605.18320v1

Offline reinforcement learning methods typically enforce strict constraints to ensure safety; yet this rigidity often prevents the discovery of optimal behaviors outside the immediate support of the behavior policy. To address this, we propose Implicit Support Expansion via stochastic Policy optimization (ISEP), which leverages a value function interpolated between in-distribution data and policy samples to implicitly expand the feasible action support. This mechanism "densifies" high-reward regions, creating a navigable path for policy improvement while theoretically guaranteeing bounded value error. However, optimizing against this expanded support creates a multimodal landscape where standard deterministic averaging leads to mode collapse and invalid actions. ISEP mitigates this via a stochastic action selection strategy, optimizing the policy by stochastically alternating between conservative cloning and optimistic expansion signals. We instantiate this framework as ISEP-FM using Conditional Flow Matching utilizing classifier-free guidance to effectively capture the interpolated value signal.

---

### The Symmetries of Three-Layer ReLU Networks

Authors: Johanna Marie Gegenfurtner, Moritz Grillo, Guido Montúfar
Published: 2026-05-18
Categories: cs.LG, cs.DM, math.AG, math.CO
arXiv: https://arxiv.org/abs/2605.18319v1

We develop a framework for analyzing parameter symmetries in deep ReLU networks and obtain a complete characterization of the generic parameter fibers for three-layer bottleneck architectures. Our approach provides explicit semi-algebraic descriptions of these fibers and yields a polynomial time algorithm for deciding functional equivalence of two parameters. The symmetries include discrete and continuous transformations arising from layer composition, and depend on whether deeper layers hide or preserve geometric structure from preceding layers. Finally, we show that some of these symmetries induce local conservation laws along gradient flow, while others do not.

---

### Dynamic Elliptical Graph Factor Models via Riemannian Optimization with Geodesic Temporal Regularization

Authors: Chuansen Peng, Xiaojing Shen
Published: 2026-05-18
Categories: cs.LG, cs.GR
arXiv: https://arxiv.org/abs/2605.18316v1

Inferring time-varying graph structures from high-dimensional nodal observations is a fundamental problem arising in neuroscience, finance, climatology, and beyond. Two intrinsic challenges govern this problem: maintaining the \emph{temporal coherence} of the latent graph across successive observation windows, and respecting the \emph{intrinsic Riemannian geometry} of the symmetric positive definite manifold on which precision matrices naturally reside, a curved space whose geodesic structure departs fundamentally from that of the ambient Euclidean space. In this paper we propose dynamic estimation on the Grassmann manifold with a factor model (\textsc{Degfm}), a novel algorithm that jointly addresses both challenges. We model the time-varying precision matrix sequence as a low-rank-plus-diagonal structure governed by a latent elliptical graph factor model, which drastically reduces the effective parameter count and enables reliable estimation in the challenging small-sample regime. Temporal coherence is enforced through a Riemannian geodesic penalty defined on the Grassmann manifold, ensuring that the estimated graph trajectory is smooth with respect to the intrinsic geometry rather than the ambient Euclidean space. To solve the resulting non-convex optimization problem over Grassmann-manifold-valued sequences subject to the LRaD constraint, we derive an efficient Riemannian gradient descent algorithm that respects the manifold structure at every iterate and rigorously establish its convergence to a stationary point. Extensive experiments on both synthetic benchmarks and real-world datasets demonstrate that \textsc{Degfm} consistently outperforms state-of-the-art baselines across all evaluation metrics, confirming the practical effectiveness of the proposed framework.

---

### Attention-based PCA

Authors: Rodrigo Maulen-Soto, Claire Boyer
Published: 2026-05-18
Categories: math.OC, stat.ML
arXiv: https://arxiv.org/abs/2605.18315v2

We study attention mechanisms through the lens of a canonical unsupervised problem: principal component analysis (PCA). We show that, when trained on Gaussian data, both softmax and linear attention layers learn parameters that align with the principal eigenvectors of the covariance matrix, thereby establishing a direct and explicit connection with PCA. Our analysis covers both finite and infinite prompt regimes. In the infinite-prompt limit, we prove convergence to globally optimal solutions aligned with the leading spectral direction, while in the finiteprompt setting we show that the same behavior emerges up to sampling effects. We further extend the analysis to an in-context setting with spiked Wishart covariances, where attention successfully recovers the underlying signal direction. These results demonstrate that attention inherently performs PCA-like computations under unsupervised objectives, providing a theoretical foundation for its representation-learning capabilities.

---