# Research Papers — 2026-05 · bundle page 29 of 326 > Full-text markdown of papers #1401–1450 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/29 [← Previous bundle](https://aipod.dev/papers/archive/2026-05/page/28.md) [Next bundle →](https://aipod.dev/papers/archive/2026-05/page/30.md) ### FP8 is All You Need (Part 1): Debunking Hardware FP64 as the HPC Holy Grail (June 13th version) Authors: Satoshi Matsuoka Published: 2026-05-28 Categories: cs.AR, cs.AI, cs.DC, cs.PF arXiv: https://arxiv.org/abs/2606.06510v3 Conventional HPC holds that native hardware FP64 is the irreducible foundation of scientific computing. On AI-optimized GPUs of the NVIDIA B300 generation and beyond, native FP64 throughput has collapsed to ~1.3 TFLOPS even as FP8 tensor throughput has grown to multiple PFLOPS. We argue something stronger than that this is survivable: the FP8 tensor-core matrix-multiply is the sole computational primitive on which double-precision scientific computing needs to be built. Every canonical kernel -- dense and sparse linear algebra, spectral transforms, stencils -- and every application composing them reduces, via the Chinese Remainder Theorem-based Ozaki Scheme II, to sequences of FP8 matrix operations; the only non-FP8 arithmetic is a bounded, fixed-width integer accumulation at reconstruction. Native FP64 is thereby demoted from a hardware requirement to a derived accuracy guarantee obtained by composition over the FP8 primitive. We organize the claim as a five-layer hierarchy -- the FP8 op, Ozaki II, the basic kernels or Berkeley "dwarfs", composite solvers, and full applications -- and, because the dwarf taxonomy already spans scientific computing, establish it by exhibiting the reduction for every dwarf rather than a sample. The claim is falsifiable, and we build the instrument that tests it: a Tensor-Memory Equilibrium (TME) model extending the Roofline with emulation parameters (alpha, beta, gamma). We identify register-level fusion as the mechanism that keeps emulation memory-bound, project recovered FP64 performance across B300 and Rubin against an H100 baseline, and close the kernel coverage with a companion FFT analysis and compensated reductions. The model could have returned a negative verdict; instead it passes across the dwarfs and their compositions. This is the analytical half of a two-part program, with a follow-on implementation to validate the thesis on real silicon. --- ### The Score Hamiltonian: Mapping Diffusion Models to Adiabatic Transport Authors: Peter Halmos, Boris Hanin Published: 2026-05-28 Categories: math-ph, cs.AI, cs.LG, physics.data-an arXiv: https://arxiv.org/abs/2606.05217v4 We exhibit an exact correspondence between sampling with score-based diffusion models and adiabatic transport of ground states for a family of Schrödinger operators we call Score Hamiltonians, built from the learned score's quantum potential. We obtain novel density reconstruction bounds and principled annealing schedules via adiabatic theorems for Fokker-Planck equations with time-varying potentials. We find the fundamental limit of sampling is set by the ratio of squared score-matching error to Score Hamiltonian spectral gap - the inverse Poincaré constant of the data density. --- ### Geodesics with Unified Tangent-constrained Priors and Curvature Regularization Authors: Chong Di, Li Liu, Jinglin Zhang, Zhenjiang Li, Da Chen, Laurent D. Cohen Published: 2026-05-28 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2606.00139v1 Curvature-penalized geodesic models have proven their effectiveness in image segmentation by computing globally optimal curves. Unfortunately, these models remain susceptible to shortcuts when delineating objects with complex shapes and image intensity distributions, as they lack mechanisms to enforce shape-aware tangent constraints. To address this limitation, we propose a unified geodesic framework that integrates tangent-constrained priors with curvature penalization. The key idea is to formulate tangent admissibility directly within the orientation-lifted space, where path tangents are restricted to spatially varying angular sectors derived from intrinsic shape representatives (ISR) such as skeletons or interior landmarks. This formulation gives rise to a family of tangent-constrained Finslerian metrics, extending the classical curvature-penalized geodesic models while enforcing mandatory tangent constraints. The resulting Hamilton-Jacobi-Bellman (HJB) partial differential equations (PDEs) admit efficient numerical solutions via variants of the fast marching method, preserving the single-pass computational complexity. Experiments on synthetic, natural, and medical images demonstrate that the proposed geodesic framework indeed improves robustness against weak boundaries and topological shortcuts, yielding segmentation results with enhanced shape fidelity compared to existing geodesic models. --- ### A Multi-AI-agent Framework Enabling End-to-end Finite Element Analysis for Solid Mechanics Problems Authors: Titu Ranjan Sarker, Muhammed Jawaad Zulqernine, Ling Yue, Shaowu Pan, Chenxi Wang, Shiyao Lin Published: 2026-05-28 Categories: cs.AI arXiv: https://arxiv.org/abs/2606.00138v1 Finite element analysis (FEA) is the most important numerical approach for solid mechanics. Challenges of FEA include a steep learning curve for entry-level users and potential false simulations due to incorrect definitions of key simulation components, such as boundary conditions, load cases, and solution variables. Years of engineering experience are usually necessary for real-world problem-solving. To address these issues, we present AbaqusAgent, a multi-agent framework grounded in large language models (LLMs) for solid mechanics analyses. AbaqusAgent is developed to facilitate analysis case generation and execution using Abaqus, one of the most widely used FEA packages, by turning users' natural-language instructions into executed FEA analyses and result visualization. AbaqusAgent is composed of six agents, including interpreter, architect, input writer, runner, reviewer, and visualizer agents, encompassing all the essential pre-processing and post-processing steps of standard FEA analyses. A wide variety of 50 solid mechanics problems have been successfully validated, achieving an overall success rate of 86%. Beyond improving the efficiency of FEA for solid mechanics problems and lowering the barrier to computational mechanics education, AbaqusAgent advances the human-simulation interaction paradigm and enables integration with AI-empowered optimization and material characterization workflows. The code is available at https://github.com/LIRAM-LIN/AbaqusAgent --- ### Advances in Neural 3D Mesh Texturing: A Survey Authors: Sai Raj Kishore Perla, Hao Zhang, Ali Mahdavi-Amiri Published: 2026-05-28 Categories: cs.CV, cs.GR arXiv: https://arxiv.org/abs/2606.00137v1 Texturing 3D meshes plays a vital role in determining the visual realism of digital objects and scenes. Although recent generative 3D approaches based on Neural Radiance Fields and Gaussian Splatting can produce textured assets directly, polygonal meshes remain the core representation across modeling, animation, visual effects, and gaming pipelines. Neural 3D mesh texturing therefore continues to be an essential and active area of research. In this survey, we present a comprehensive review of recent advances in neural 3D mesh texturing, covering methods for texture synthesis, transfer, and completion. We first summarize key foundations in mesh geometry, texture mapping, differentiable rendering, and neural generative models, and then organize the literature into a unified taxonomy spanning early GAN-based methods to modern diffusion-based pipelines. We further analyze common architectures and supervision strategies, review datasets and evaluation protocols, and discuss emerging applications, practical/commercial systems, and open challenges. Together, these insights provide a structured perspective on the current landscape and help guide future developments in learning-based 3D mesh texturing. --- ### Generative AI and Digital Ecosystem Resilience: A Proactive Lifecycle-Based Survey Authors: Jonghyun Chung, Rishabh Chaddha, Sanket Badhe, Debanshu Das, Nathan Huang, Amanpreet Kaur Published: 2026-05-28 Categories: cs.LG, cs.AI, cs.CL, cs.CR, cs.SI arXiv: https://arxiv.org/abs/2606.00136v1 The proliferation of adversarial synthetic content, accelerated by Generative AI (GenAI) is rendering traditional reactive detection methods ineffective. This survey synthesizes emerging research to demonstrate a paradigm shift toward the proactive detection of emerging inauthentic narratives. In this survey, we adopt a unified, lifecycle-based taxonomy to combine socio-technical lifecycle models of adversarial campaigns with advanced computational methodologies for emerging inauthentic narrative detection. By structuring the analysis around the C5 Interaction Model (Context, Causes, Content, Cycle of Amplification, Consequences), we integrate different research streams from machine learning and social science. To differentiate spread patterns of synthetic amplification from authentic baseline traffic, this paper surveys state-of-the-art techniques for modeling the creation, seeding, and propagation of fresh narratives, including the analysis of Coordinated Inauthentic Behavior (CIB), epidemiological modeling, and Hawkes process. This survey also provides a systematic review of proactive detection methods for adversarial threats at different stages in the C5 interaction model, specifically, anomaly detection in high-dimensional embedding spaces, unsupervised coordination detection on multi-layer graphs, and agentic AI systems. Finally, this survey addresses challenges posed by GenAI, including the difficulty of tracking rapidly changing threats and multi-level distributional drift, and it outlines a future research agenda focused on detecting anomalous clusters and building anticipatory and resilient systems. This survey provides a comprehensive, lifecycle-based review of methods for the proactive detection of emerging synthetic threats for more resilient information ecosystems. --- ### On Effectiveness and Efficiency of Agentic Tool-calling and RL Training Authors: Tong Liu, Cheng Qian, Matej Cief, Yuan He, Daniele Dan, Nikolaos Aletras, Gabriella Kazai Published: 2026-05-28 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2606.00135v2 Tool-calling is a central component of modern large language model (LLM) agents, equipping them with skills beyond their parametric knowledge. This paper studies tool-calling along two complementary axes: effectiveness, i.e., how this capability is measured, and efficiency, i.e., how it is learned. On effectiveness, we systematically analyze tool-calling evaluation pipelines and show that results can be highly sensitive to seemingly minor, often undocumented implementation choices including the random seed, system prompt, multi-turn template construction, and how prior interaction/reasoning history is carried forward. These choices can lead to substantial differences in reported performance, especially in multi-turn settings where without rigorous standardization, leaderboard rankings are unreliable. On efficiency, we examine standard reinforcement learning (RL) for tool-calling and identify two sources of computational waste: (i) during rollouts, many prompts produce no learning signal, and (ii) during policy updates, optimization incurs high computational cost. Guided by these findings, we introduce two techniques that accelerate RL-based tool-calling training, achieving substantial wall-clock speedup without degrading performance. --- ### On Effectiveness and Efficiency of Agentic Tool-calling and RL Training Authors: Tong Liu, Cheng Qian, Matej Cief, Yuan He, Daniele Dan, Nikolaos Aletras, Gabriella Kazai Published: 2026-05-28 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2606.00135v1 Tool-calling is a central component of modern large language model (LLM) agents, equipping them with skills beyond their parametric knowledge. This paper studies tool-calling along two complementary axes: effectiveness, i.e., how this capability is measured, and efficiency, i.e., how it is learned. On effectiveness, we systematically analyze tool-calling evaluation pipelines and show that results can be highly sensitive to seemingly minor, often undocumented implementation choices including the random seed, system prompt, multi-turn template construction, and how prior interaction/reasoning history is carried forward. These choices can lead to substantial differences in reported performance, especially in multi-turn settings where without rigorous standardization, leaderboard rankings are unreliable. On efficiency, we examine standard reinforcement learning (RL) for tool-calling and identify two sources of computational waste: (i) during rollouts, many prompts produce no learning signal, and (ii) during policy updates, optimization incurs high computational cost. Guided by these findings, we introduce two techniques that accelerate RL-based tool-calling training, achieving substantial wall-clock speedup without degrading performance. --- ### XAI-SOH-FL: Enhancing SOH-FL with Adaptive Aggregation and Explainable AI for Intrusion Detection in Heterogeneous IoT Authors: Ambreen Aslam, Maaz Hassan, Bibi Zahra, Muhammad Khuram Shahzad Published: 2026-05-28 Categories: cs.CR, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2606.00134v1 Intrusion Detection Systems (IDS) in Internet of Things (IoT) environments face significant challenges due to data heterogeneity, lack of labeled data, and limited model interpretability. Federated Learning (FL) offers a privacy-preserving solution; however, existing approaches such as SOH-FL suffer from two key limitations: reliance on a manually tuned aggregation parameter γ and lack of explainability in model predictions. In this paper, we propose XAI-SOH-FL, an enhanced framework that integrates adaptive aggregation and explainable artificial intelligence into the SOH-FL paradigm. First, we introduce a dynamic γ selection mechanism based on similarity thresholding, enabling the aggregation process to adapt to evolving data distributions. Second, Bayesian Optimization is employed to automatically determine optimal γ values, eliminating the need for manual tuning. Third, SHAP (SHapley Additive exPlanations) is incorporated to provide feature-level interpretability for intrusion detection decisions. Experimental evaluation on the CICIDS2017 dataset demonstrates that the proposed approach achieves an accuracy of 94.12% and an F1-score of 0.92, outperforming the baseline SOH-FL model while converging in fewer communication rounds. Furthermore, SHAP-based analysis reveals that flow-level features such as Flow Duration and Packet Length significantly influence model predictions. These results indicate that XAI-SOH-FL provides an effective balance between accuracy, adaptability, and interpretability in heterogeneous IoT environments. --- ### World Models: A Comprehensive Survey of Architectures, Methodologies, Reasoning Paradigms, and Applications Authors: Arif Hassan Zidan, Yi Pan, Hanqi Jiang, Ruiyu Yan, Wei Ruan, Zihao Wu, Lifeng Chen, Weihang You, Xinliang Li, Bowen Chen, Huawen Hu, Peilong Wang et al. Published: 2026-05-28 Categories: cs.LG, cs.ET arXiv: https://arxiv.org/abs/2606.00133v1 World models, internal simulators that learn the structure and dynamics of an environment, have emerged as a central paradigm in the pursuit of artificial general intelligence, enabling agents to predict, plan, and reason within learned representations. Despite rapid progress across reinforcement learning, robotics, autonomous driving, and video generation, the field lacks a unified framework integrating its diverse architectural choices, training methods, reasoning mechanisms, and application settings. This survey addresses that gap with a multi-axis taxonomy organized along four dimensions: (i) architecture, encompassing representation format, dynamics formulation, input modality, learning paradigm, and downstream application; (ii) methodological family, including state-space and recurrent approaches, transformer-based models, diffusion-based generators, physics-informed networks, and language-augmented multimodal systems; (iii) reasoning strategy, covering imagination-based planning, latent policy learning, counterfactual reasoning, and planning under uncertainty; and (iv) application domain, spanning robotics, autonomous driving, video prediction, multimodal agents, reinforcement learning, scientific modeling, medical imaging, educational measurement, and business and finance. Tracing the field from early cognitive-science foundations to milestone systems such as PlaNet, the Dreamer family, MuZero, Sora, Cosmos, and Genie, we examine how these dimensions interact and highlight the recent convergence of chain-of-thought reasoning with world-model imagination. We review evaluation protocols and benchmarks, identify persistent challenges such as compounding prediction errors, sim-to-real transfer, and fragmented evaluation, and outline future directions toward unified multimodal world models, foundation-scale interactive simulators, and safe deployment in safety-critical domains. --- ### Foundation-Preserving Adaptation via Generalized Rayleigh-Quotient Optimization Authors: Dongjun Kim, Adrian de Wynter, Huancheng Chen, Heasung Kim, Haris Vikalo Published: 2026-05-28 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2606.00132v1 While finetuning effectively adapts foundation models to specialized downstream tasks, it can degrade nontarget capabilities acquired during pretraining. Existing forgetting aware methods typically seek safer updates through specialized initialization or fixed constraints, but do not regulate the adaptation preservation trade-off during training. We propose Foundation Preserving LoRA (FoLoRA), a forgetting aware optimization framework. Guided by a first order preservation condition, FoLoRA defines a forgetting penalty over pretraining-proxy activations and a task utility over downstream task activations. It then scores update directions by task utility per unit forgetting penalty via a generalized Rayleigh quotient. The resulting spectral coordinate system enables direction wise gated Adam updates, attenuating low utility to penalty directions during training. To estimate the forgetting penalty, FoLoRA constructs pretraining proxy calibration data by sampling from the pretrained model rather than relying on a single proxy dataset. Experiments on math, code, and instruction following adaptation show that FoLoRA achieves the strongest preservation adaptation balance over baselines, improving target task performance with best aggregate preservation of non target capabilities. --- ### AI-PROPELLER: Warehouse-Scale Interprocedural Code Layout Optimization with AlphaEvolve Authors: Chaitanya Mamatha Ananda, Rajiv Gupta, Mircea Trofin, Aiden Grossman, Sriraman Tallam, Xinliang David Li, Amir Yazdanbakhsh Published: 2026-05-28 Categories: cs.AI, cs.LG, cs.PL, cs.SE arXiv: https://arxiv.org/abs/2606.00131v1 Post-link optimizers (PLOs) such as Propeller and BOLT have demonstrated that precise, profile-guided code layout can extract significant performance gains from heavily optimized binaries. However, these systems are currently restricted to intraprocedural techniques, leaving the global potential of interprocedural layout largely untapped. Interprocedural code layout is historically difficult due to a combinatorially intractable search space and complex call-return semantics that are challenging to model. Consequently, the performance potential of fine-grained interprocedural layout remains unproven in practice. AI-PROPELLER uses Magellan, an agentic workflow that evolves the compiler heuristic in Propeller into a fine-grained interprocedural optimizer and fine-tunes the resulting policy hyperparameters. To ensure high-fidelity, we move away from approximate static cost models and the agentic workflow generates multiple layout variants that are executed on actual hardware to measure real performance counters, providing a precise reward signal for the evolutionary loop. AI-PROPELLER has been evaluated on several benchmarks including large warehouse-scale applications and experiments show performance improvements of 0.23% to 1.6% optimized with state-of-the-art FDO and PLO which is significant for real-world binaries. This is the first time ever that large warehouse-scale applications in industrial settings have been optimized with fine-grained interprocedural code layout. --- ### Automatically Differentiable Nonlinear Tensor Networks (ADNTNs) for Exponential Parameter Compression of Deep Neural Networks Authors: Andrzej Cichocki, Michal Wietczak Published: 2026-05-28 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2606.00130v2 Large deep neural networks are costly to store and deploy because inference must move and evaluate many parameters. This paper studies \emph{Automatically Differentiable Nonlinear Tensor Networks} (ADNTNs), compact differentiable weight generators for replacing selected dense, convolutional, and attention layers. An ADNTN maps a small set of trainable tensor cores to a full weight tensor through hierarchical contractions and learnable nonlinearities; the generated layer is then used as an ordinary linear or convolutional operator. We investigate three multilayered topologies: Tree Tensor Networks, augmented Tree Tensor Networks with boundary disentanglers, and MERA-style multi-scale decoders. Compared with flat brick-wall automatically differentiable tensor networks, these hierarchies provide logarithmic-depth communication between tensorised modes and optional lateral mixing, which can improve long-range structure without large increases in stored parameters. We give a unified forward--adjoint formulation showing how reverse-mode automatic differentiation computes pre-activation adjoints and contracted-environment gradients for all trainable cores. The formulation supports task losses, reconstruction losses, distillation, quantisation-aware terms, batching, and modern optimisers. Proof-of-concept experiments on selected AlexNet and VGG-16 layers on CIFAR-10 datasets achieve per-layer parameter-compression ratios from about $2{,}000\times$ to $430{,}000\times$. Several VGG-16 compressed models match or slightly exceed the dense baseline, whereas AlexNet shows moderate degradation under more restrictive redundancy. These results indicate that nonlinear tensor-network generators are a promising structured route to compact pattern-recognition models, while also showing that contraction schedules and hardware-aware implementations remain essential for practical speedups. --- ### A Shared Valence Axis Across Modern LLMs and Human EEG: The Saturation Regularity Authors: Yousef A. Radwan, Xuhui Liu, Kilichbek Haydarov, Yuqian Fu, Mohamed Elhoseiny Published: 2026-05-28 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2606.00129v1 Large language models (LLMs) have emerged as powerful representation learners whose internal features increasingly align with human cognition. We study whether modern LLMs can serve as a lens for understanding neural representations in the human brain, focusing on emotional valence in EEG. We first build a one-dimensional valence direction, the V-axis, from modern LLMs using only nine emotion-evocative sentences. We validate it through zero-shot transfer to sentiment benchmarks and cross-model consistency across fourteen LLMs. We then show that this LLM-derived direction maps onto human neural activity. On a public EEG cohort of 123 subjects watching affective videos, a single linear projection on EEG features tracks the V-axis position of each stimulus. Moreover, 36 EEG emotion classifiers trained without exposure to the V-axis spontaneously rediscover the same direction in their internal representations, suggesting that the same valence structure emerges in both language models and human electrophysiology. Yet this convergence does not provide an effective training signal. We test twenty-five alignment strategies, including knowledge distillation, representational similarity, contrastive, and topographic losses; none improve decoding, and sixteen significantly reduce accuracy. We formalize this result as the saturation regularity: once task labels alone drive a brain-decoding network onto the target direction, additional supervision mainly distorts an already-saturated basin, while the load-bearing within-class residual receives little useful gradient. This regularity also indicates where improvement should come from: the residual subspace unreachable by supervision. Motivated by this insight, we ensemble across residual diversity rather than supervising the basin, improving balanced accuracy by 10.5% over the prior best on FACED, with the same effect replicated on SEED-V. --- ### Multimodal Music Recommendation System using LLMs Authors: Srikar Prabhas Kandagatla, Sreehitha R. Narayana, Chandana Magapu, Swetha Mohan, Shamanth Kuthpadi, Hongjie Chen, Ryan A. Rossi, Franck Dernoncourt, Nesreen Ahmed Published: 2026-05-28 Categories: cs.IR, cs.AI, cs.LG, cs.MM arXiv: https://arxiv.org/abs/2606.00125v1 Music recommendation systems typically treat songs as opaque tokens, relying on collaborative interaction histories which overlooks semantic or acoustic content. Prior work has explored LLM-augmented, multimodal, and text-enhanced approaches to sequential recommendation, and while some methods partially combine semantic, acoustic, or engagement signals, none jointly model all three within a unified LLM-based sequential reasoning framework that grounds recommendations in actual song content. In this work, we propose a multimodal framework for session-based music recommendation that enriches the LastFM-1K dataset with three complementary signals: (1) audio and lyric embeddings extracted using pretrained music and text representation models, (2) LLM-generated semantic metadata using the MGPHot annotation schema, and (3) listening completion ratios. We adopt the E4SRec framework by extending it with multimodal features and different item ID encoder backbones, including SASRec, BERT4Rec, and GRU4Rec. We further extend the LLM backbone option with LLaMa-2-13B, Qwen2.5-7B-Instruct, and LLaMa-3-70B in both zero-shot and fine-tuned settings. Our experiments show that integrating content-based features improves over ID-only baselines up to 95% in terms of Recall and 79% in terms of NDCG. Moreover, our experiments show that naive multimodal fusion does not always yield additive improvements, highlighting challenges in cross-modal integration. We release a large-scale multimodal benchmark for music recommendation. --- ### Positional Encodings Anchor Spatial Structure in Vision Transformers: A Geometric Perspective on Robustness Authors: Mahmoud Mannes Published: 2026-05-28 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2606.00124v1 Positional embeddings (PEs) in Vision Transformers (ViTs) are known to impact performance and robustness, but their role in shaping internal spatial representations is not well understood. In this work, we study how different forms of PEs influence the representational geometry of ViTs and how these changes relate to robustness under content-disrupting distribution shifts. We introduce a metric, the Spatial Similarity Distance Correlation (SSDC), to quantify spatial structure in token representations. Using this metric, we show that ViTs trained without PEs still develop non-trivial spatial structure, but this structure is driven by visual content and collapses under token permutation. In contrast, we find that all PEs considered (learned absolute, sinusoidal, and rotary) are associated with a consistent shift toward an index-anchored spatial organization. Representations in these models remain stable under perturbations that disrupt content, and exhibit substantially improved robustness to such distributional shifts. We further show that while different PEs produce distinct depth-wise trajectories of spatial structure, their robustness properties are largely similar (with secondary variation across encoding schemes), suggesting that robustness appears to depend on the presence of a stable positional reference frame more than it depends on the specific encoding mechanism. These results offer a geometric account of how positional encodings shape internal representations, with implications for the principled design of future encoding schemes. --- ### CardioLens: Revealing the Clinical Reality Gap of MLLMs via Multi-Sequence Cardiac MRI Evaluations Authors: Zixian Su, Hongkai Zhang, Fan Gao, Encheng Su, Taiping Qu, Jingwei Guo, Nan Zhang, Hui Wang, Zhen Zhou, Kairui Bo, Yan Chen, Yue Ren et al. Published: 2026-05-28 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2606.00123v1 Multimodal Large Language Models (MLLMs) have shown strong performance on public medical benchmarks, yet existing evaluations often remain weak proxies for clinical use, relying on isolated inputs and simplified recognition-style tasks. We introduce CardioLens, a leakage-resistant evaluation testbed for multi-sequence Cardiovascular Magnetic Resonance (CMR), constructed from private hospital archives through a rigorous report-to-QA construction and verification pipeline. CardioLens contains 473,896 slices and 13,494 verified QA pairs across 4D Cine, LGE, perfusion, and T2-weighted imaging, and evaluates three stages of CMR interpretation: image understanding, report generation, and disease diagnosis. Across 24 state-of-the-art MLLMs, CardioLens reveals a substantial clinical reality gap: models perform poorly overall, with performance degrading along the real CMR workflow. Confusion analysis further shows a category-collapse failure mode, where models default to frequent abnormal categories rather than distinguishing clinically distinct findings. To rule out MLLM-compatible input construction as the primary cause, we compare random, clinically motivated, and data-driven slice selection protocols under different slice budgets; performance changes only marginally, typically by about 1%. Explicit reasoning prompts also fail to rescue performance, often making models more conservative rather than improving visual evidence use. These results show that current MLLMs remain far from reliable CMR interpretation, where clinical decisions require integrating distributed evidence across sequences, views, and temporal phases. CardioLens provides a clinically grounded testbed for developing next-generation MLLMs toward real-world clinical deployment. --- ### Versatile Framework with Semantic and Structural guidance for Image Reconstruction from Brain Activity Authors: Yizhuo Lu, Changde Du, Qiongyi Zhou, Liuyun Jiang, Huiguang He Published: 2026-05-28 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2606.00121v1 Reconstructing visual stimuli from brain recordings has been a meaningful and challenging task in brain decoding. Especially, the achievement of precise and controllable image reconstruction bears great significance in propelling the progress and utilization of brain-computer interfaces. Recent methods, leveraging advances in the power of text-to-image generation models, have reconstructed images that closely approximate complex natural stimuli in terms of semantics (e.g., concepts and objects). However, they struggle to maintain consistency with the original stimuli in fine-grained structural information (e.g., position, orientation and size), which undermines both the controllability and interpretability of the models. To address the aforementioned issues, we propose a two-stage image reconstruction framework, termed MindDiffuser. In Stage 1, Contrastive Language-Image Pretraining (CLIP) text embeddings decoded from brain responses are input into Stable Diffusion, generating a preliminary image containing semantic information. In Stage 2, we use decoded shallow CLIP visual features as supervisory signals, iteratively refining the feature vectors from Stage 1 via backpropagation to align structural information. We conducted extensive experiments on brain response datasets across three modalities (fMRI, EEG, MEG) elicited by visual stimuli, demonstrating that our framework significantly enhances the performance of previous state-of-the-art models, highlighting the effectiveness and versatility of our approach. Spatial and temporal visualization results further support the neurobiological plausibility of our framework, providing guidance for future neural decoding efforts across different brain signal modalities. --- ### SpikeWFM: Spiking-Aided Wireless Foundation Model for Robust Channel Prediction Authors: Liwen Jing, Yisha Lu, Tingting Yang, Li Sun, Yuxuan Shi, Yuwei Wang, Mengfan Zheng, Leiyang Xu Published: 2026-05-28 Categories: eess.SP, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2606.00120v1 This paper proposes SpikeWFM, a novel hybrid architecture that integrates spiking neural networks (SNNs) with conventional artificial neural network (ANN)-based transformers for wireless foundation models (WFMs). Inspired by the noise-robust and energy-efficient information processing in the human brain, SpikeWFM aims to enhance the resilience of WFMs against noise and interference while maintaining strong generalization capabilities across diverse wireless scenarios. Drawing from the success of large language models, WFMs leverage self-supervised pre-training on large-scale datasets spanning various wireless environments to learn a unified embedding that supports a wide range of downstream tasks, including channel prediction, channel estimation, beam predition, positioning and etc. Such models typically outperform task-specific designs and exhibit superior adaptability to unseen conditions. However, existing WFMs remain vulnerable to realistic noise and interference in practical wireless systems. To address this limitation, we incorporate spiking neurons into the transformer-based WFM architecture. We provide a brief theoretical analysis demonstrating how the SNN-ANN hybrid effectively mitigates noise and interference through temporal sparsity and event-driven processing. Experimental results show that SpikeWFM consistently outperforms conventional ANN-based WFMs in both pre-training convergence and channel prediction accuracy. Additional results on communication and sensing tasks will be presented in the full journal version of this work. --- ### V2I Work Zone Geometry Reconstruction with Pose-Conditioned UWB Range Denoising Authors: Jiaxi Liu, Hangyu Li, Yang Cheng, Rui Gana, Junwei You, Weizhe Tang, Peng Zhang, Steven T. Parker, Xiaopeng Li, Bin Ran Published: 2026-05-28 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2606.00119v1 Reliable work zone mapping is important for connected and autonomous vehicles (CAVs) to navigate safely and smoothly through work zone areas. Cone-mounted ultra-wideband (UWB) roadside units (RSU) offer a cost-effective way for work zone layout inference, as roadside anchors and vehicle tags provide direct vehicle-to-infrastructure (V2I) range constraints for work zone geometry reconstruction. However, UWB range estimation is degraded by bursty outliers, non-line-of-sight (NLOS) errors, arbitrary anchor-ordering issues, and vehicle pose uncertainties in practical field deployments. To address these challenges, this study proposes a pose-conditioned, permutation-equivariant predictive denoiser for multi-anchor UWB ranging. The model employs shared anchor-wise temporal prediction to capture range dynamics, symmetric set aggregation to handle unordered and missing anchors, and pose-conditioned residual decoding to incorporate vehicle motion as a geometric prior. A two-stage training strategy first learns prediction from observed ranges, and then fine-tunes the denoiser with NLOS-weighted supervision. The method is evaluated on rare real-world V2I UWB field data collected with a CAV, as well as on controlled large-scale simulation benchmarks for ablative insights. Results show that the proposed method substantially improves range accuracy, cone localization, and work zone geometry reconstruction in challenging NLOS-dominated regimes, remains robust to anchor re-indexing and moderate anchor dropout, and reduces measurement-weighted field MSE by 66.9% relative to the raw input. --- ### Automatically Attacking Software Reverse Engineering AI Agents Authors: Brian Crawford, Justin Phillips, Patrick McClure Published: 2026-05-28 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2605.30667v1 Software tools for reverse engineering executable binary files, such as Ghidra, enable malware analysts to safely conduct robust static analysis without having access to original source code. Coupled with the analytic power of large language models (LLM), agentic systems enabled with tools, such as GhidraMCP, can allow analysts to automate a previously human driven process. Although this automation can increase the productivity of a single malware analyst, it also introduces a new area of vulnerability for malware obfuscation. This paper presents an adversarial technique using genetic algorithm-based prompt generation, a modification of an adversarial attack known as AutoDAN, to demonstrate the ability to deceive LLM-powered disassembly and decompilation systems into misinterpreting binary executables, effectively corrupting their analytical output. This proof-of-concept methodology exploits inherent vulnerabilities in how LLMs process and interpret decompiled machine code via prompt injection by using extraneous string variable assignments to pass surreptitious instructions to the LLM while not impacting the functionality of the executable file. We demonstrate this capability through several concise examples. This approach could enable attackers to bypass automated detection systems that rely on LLM-driven analysis pipelines. By studying and understanding this attack, insights can be gained regarding the security implication of integrating LLMs into cybersecurity toolchains and building more robust agentic code analysis systems. --- ### Structure-Induced Information for Rerooting Levin Tree Search Authors: Jake Tuero, Michael Buro, Laurent Orseau, Levi H. S. Lelis Published: 2026-05-28 Categories: cs.AI arXiv: https://arxiv.org/abs/2605.30664v2 Subgoal-based policy tree search, which uses a policy to guide search, is effective for complex single-agent deterministic problems but often relies on explicit subgoal generation that can incur substantial overhead and hinders scalability. In this paper, we overcome these limitations by using a learned ``rerooter'' through the recently-introduced $\sqrt{\text{LTS}}$ algorithm. A rerooter implicitly decomposes the problem into soft subtasks. While previous work focused on the formal guarantees for given or handcrafted rerooters, in this work we propose three rerooter designs: (i) a clustering-based rerooter that exploits global state-space structure, (ii) a heuristic-based rerooter that leverages learned cost-to-go estimates, and (iii) a hybrid that combines both signals. Our framework avoids having to explicitly reconstruct and reason over generated subgoals, thereby enabling scalable allocation of search effort with significantly lower computational overhead. Empirically, our rerooting-based methods scale to complex environments where subgoal-based policy tree search fails, and achieve state-of-the-art online training efficiency on the domains tested. --- ### Spatio-temporal stochastic graph-based learning for infectious disease forecasting Authors: Luz Stefani Sotomayor Valenzuela, Susanna Cramb, Darren Wraith Published: 2026-05-28 Categories: cs.LG, q-bio.PE arXiv: https://arxiv.org/abs/2605.30662v1 Spatio-temporal graph-based models have typically been used to forecast new cases of infectious diseases such as COVID-19 and chickenpox outbreaks. However, the use of stochastic modelling into their learning process has been surprisingly under-investigated and rarely considered entire data sets of large countries. As a result, it is unknown whether these models would provide accurate forecasts in real-world disease spread scenarios. In this work, we propose a spatio-temporal stochastic graph-based architecture that integrates a stochastic formulation and uncertainty approximation process to forecast new infectious disease cases. We find that our approach can adapt to encode large and small population geographical networks within a single model architecture. Using two real-world data sets, COVID-19 in the US and chickenpox in Hungary, we report an enhanced effect of the proposed architecture across predictions of the 2022 first wave for COVID-19 in the US and comparative results of chickenpox waves during 2012-2014 in Hungary. By benchmarking with four spatio-temporal graph-based models, quantitative results show competitive overall weekly performance of the proposed approach on forecasting new cases for all 3,218 US counties and all 20 Hungary counties. The proposed approach can represent overall epidemic progression relative to baselines, though with a one-step delay; while exhibiting a reduced sensitivity to high-frequency and low-amplitude variability. --- ### BOKBO (Best of K Bad Options): Calibrated Abstention for VLA Policies Authors: Anya Singh, Cabrel Happi, Jai Relan, Varun Nair, Vidyut Baradwaj Published: 2026-05-28 Categories: cs.LG, cs.RO arXiv: https://arxiv.org/abs/2605.30660v1 Test-time scaling for vision-language-action (VLA) policies, methods such as RoboMonkey, SEAL, MG-Select, and V-GPS, samples K candidate action chunks at inference and executes the verifier-best. When all K candidates are unsafe, the system executes a violating action with no warning. We propose BOKBO, the first conformal abstention layer for K-sample VLA inference, providing finite-sample distribution-free guarantees on executed-violation rate. We provide both global and per-task (Mondrian) variants, with the per-task variant closing the conditional gap on the hardest tasks. Our analysis exposes a structural failure of policy-internal nonconformity scores under perturbation-based K-sampling: the base-policy confidence proxy and K-sample disagreement correlate at 0.98 with the action-noise hyperparameter $σ$, while correlating at the noise floor with actual safety violations. We test the failure's scope by replicating the analysis under token-level temperature sampling and find the failure is mechanism-specific and partially mitigated under policy-stochasticity-based sampling. A learned violation predictor conditioned on semantic visual features and task identity supports tight calibration: at $ε$ = 0.05 on libero_object_temp_x0.1 with OpenVLA-OFT, the conditional CRC bound holds on 86% of bootstrap splits with 78% coverage and 70% net task success. Mondrian-BOKBO raises the minimum per-task conditional hold fraction from 0.71 to 0.93. Results are stable across 5 training seeds, replicate within bootstrap noise on $π_0$-FAST, hold on libero_spatial_temp_x0.1 as a co-equal benchmark, and survive four within-suite distribution shifts. We additionally identify and correct a methodological pitfall: globally-set force thresholds well below expert-typical manipulation forces conflate unsafe behavior with normal manipulation, inflating violation rates by $5\times$. --- ### Learning to Perceive the World Through Control: Empowerment-Based Representation Learning Authors: Mahsa Bastankhah, Sophie Broderick, Benjamin Eysenbach Published: 2026-05-28 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.30656v1 In many practical reinforcement learning environments, observations are far higher-dimensional than the variables that matter for control. In this work, we ask: can we learn representations that capture only control-relevant features of the environment? We study this question through the empowerment objective, which maximizes an agent's influence over the environment and is widely used for unsupervised skill learning. We show that empowerment agents induce two distinct representations -- forward and backward -- that capture complementary aspects of the state, and both of which are invariant to control-irrelevant features. Thus, empowerment maximization leads agents to learn an implicit, control-centric model of the world. Our analysis highlights the importance of learning representations through interaction rather than from passive datasets: interaction aimed at maximizing control is essential for learning useful invariance properties, a perspective that aligns closely with the causal learning literature. --- ### EUDAIMONIA: Evaluating Undesirable Dynamics in AI Authors: Jun Rui Huang, Wang Bill Zhu, Ziyi Liu, Nathanael Fast, Ravi Iyer, Robin Jia Published: 2026-05-28 Categories: cs.CL, cs.AI, cs.HC arXiv: https://arxiv.org/abs/2605.30654v1 Large language models (LLMs) are increasingly used as conversational partners for companionship, emotional disclosure, and interpersonal advice, but the social dynamics of these interactions can create harms that are not captured by capability-oriented or traditional safety evaluations. We introduce the Social AI Design Code, a framework for evaluating whether LLMs align with user welfare in social interactions, including whether they encourage harmful intimacy, dependence, or prolonged engagement. To evaluate these risks in natural and diverse user-LLM interactions, we operationalize the code with EUDAIMONIA, a benchmark of 969 user inputs and 3,147 design-requirement violation checks built from WildChat through weak-to-strong filtration, multi-model relabeling, and controlled rewriting. Evaluating 22 recent LLMs, we find that even the strongest models, Claude-Opus-4.7 and GPT-5.5, violate 30.7% and 27.2% of checks, respectively. Extended thinking does not reduce violation rates, suggesting that these failures are persistent social-alignment problems rather than deficits solvable through test-time reasoning alone. --- ### Counterfactual Graph for Multi-Agent LLM Calibration Authors: Jiatan Huang, Mingchen Li, Ziming Li, Sunjae Kwon, Hong Yu, Chuxu Zhang Published: 2026-05-28 Categories: cs.CL arXiv: https://arxiv.org/abs/2605.30653v1 Multi-agent LLM systems often treat agreement as evidence: when many agents in a panel give the same answer, that answer is assumed to be more reliable. We show that this assumption can fail after agents communicate. Communication can induce correlated failures and false consensus, so the same vote share may reflect reliable agreement in one topology but over-confidence in another. We propose CAGE-CAL, a counterfactual agent-graph calibration framework for multi-agent LLMs. For each query, CAGE-CAL compares an observed post-communication agent graph with a matched counterfactual no-communication graph, capturing both pairwise failure correlations and group-level dependencies. Rather than simply counting how many agents agree, CAGE-CAL estimates the counterfactual shift between observed and no-communication dependence, and calibrates confidence accordingly. Across five benchmarks, CAGE-CAL improves reliability discrimination with competitive ECE, and its calibrated confidence further improves topology selection over the best fixed-topology strategy. --- ### Bridging the Gap Between Natural Language and Market Dynamics via High-Dimensional Representation Learning Authors: Yujin Jeong, Noelle Jung, Brian Y. C. Leung Published: 2026-05-28 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.30652v1 Traditional multi-modal financial forecasting often relies on scalar sentiment scores, which fail to capture the nuances of financial news. To address this information loss, this paper explores high-dimensional representation learning by replacing discrete polarity ratings with dense FinBERT embeddings within a Transformer-based forecasting architecture. We benchmarked various embedding strategies on the FNSPID dataset, including raw embeddings, attention-weighted aggregation, and a custom Siamese network. While the attention-based mechanism struggled with the low signal-to-noise ratio typical of financial data, the integration of Siamese-optimized embeddings outperformed both the scalar baseline and raw embedding approaches, demonstrating that preserving high-dimensional narrative context yields improved predictive accuracy for short-term stock price movements. --- ### LARK: Learnability-Grounded Trajectory Selection for Efficient Reasoning Distillation Authors: Tianrun Yu, Kaixiang Zhao, Chih-Chun Chen, Amanda Hughes, Taylor W. Killian, Fenglong Ma, Weitong Zhang, Porter Jenkins Published: 2026-05-28 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2605.30651v1 We study trajectory selection for reasoning distillation, where teacher-generated reasoning trajectories are selectively used as supervision for a student model. Existing methods rely on heuristics such as trajectory quality or model confidence, but they often overlook whether a trajectory is learnable by the student. In this paper, we present LARK, a learnability-grounded method for reasoning trajectory selection. LARK selects trajectories that the student can learn efficiently while preserving the generalization of the full training distribution. At the core of LARK is a learnability factor $ρ$, which characterizes the rate at which the student's training loss decreases. To estimate this rate efficiently and maintain generalization, we introduce a learnability proxy and a $χ^2$-regularized selection policy that balances learnability and distributional coverage, both with strong theoretical guarantees on their estimation error. Empirically, LARK consistently outperforms data selection baselines across multiple base models and reasoning tasks. Diagnostic analyses show that the LARK score predicts downstream training utility and that LARK-selected trajectories induce faster supervised fine-tuning loss reduction. Our code is available at https://github.com/Tianrun-Yu/LARK. --- ### Convergence of Steepest Descent and Adam under Non-Uniform Smoothness Authors: Sharan Vaswani, Yifan Sun, Reza Babanezhad Published: 2026-05-28 Categories: cs.LG, math.OC arXiv: https://arxiv.org/abs/2605.30648v1 Recent work has analyzed the convergence of first-order methods under non-uniform smoothness assumptions that better model the loss landscape in machine learning tasks. We generalize this assumption to objectives whose curvature is an affine function of the objective value. This property is satisfied by a broad class of problems, including logistic regression, generalized linear models with a logistic link function, softmax policy gradient in reinforcement learning, and a class of neural networks. Under this assumption and gradient domination conditions, we establish a general convergence rate for the steepest descent method, and deterministic, diagonal variants of RMSProp and Adam. Our results imply that for logistic regression on separable data and the softmax policy gradient objective, sign GD converges linearly and is provably faster than GD. Furthermore, we show that for a class of two-layer neural networks on separable data, RMSProp and Adam can converge at a linear rate with a constant step-size and momentum parameter. Finally, we present a lower bound demonstrating that, under our assumption, RMSProp and Adam are provably faster than AdaGrad, AMSGrad, gradient descent, and heavy-ball momentum. --- ### Same Patient, Different Words, Different Diagnosis? Evaluating Semantic Stability in Clinical LLMs Authors: Mahdi Alkaeed, Adnan Qayyum, Nabeel Abo Kashreef, Muhammad Bilal, Junaid Qadir Published: 2026-05-28 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2605.30646v1 Large Language Models (LLMs) are increasingly used in clinical applications. However, their behavior remains highly sensitive to subtle linguistic variations, such as rephrasing or syntactic variation. This sensitivity poses risks in safety-critical healthcare settings, where semantically equivalent inputs should produce consistent predictions. However, a key challenge is to ensure that prompt variations truly preserve clinical meaning, as embedding-based similarity metrics often fail to capture distinctions involving negation, temporality, or severity. To address this limitation, we propose a semantic verification framework based on Natural Language Inference (NLI) to filter meaning-preserving prompt variations, which are further refined using an LLM-as-a-judge and audited by a clinical expert. In addition, we introduce three metrics to quantify model sensitivity: MeaningPreserving Variation Sensitivity (MVS), confidence variation (ΔC), and Worst-Case Instability (WCI). We evaluate 16 open-source general-purpose (GP) and medical LLMs within the same model families and parameter scales, using reformulated prompts derived from the DiagnosisQA and MedQA datasets. Our results demonstrate that robustness differences between domain-specific (DS) models are mixed and highly model-dependent, i.e., domain specialization does not consistently improve or reduce robustness to meaning-preserving prompt reformulations. Several DS models rank among the most robust (when compared with GP counterparts), and strong GP baselines remain competitive as well. --- ### Diffusion Models Preferentially Memorize Prototypical Examples or: Why Does My Diffusion Model Love Slop? Authors: Marta Aparicio Rodriguez, Anastasia Borovykh, Grigorios A. Pavliotis, Daniel J. Korchinski Published: 2026-05-28 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.30642v1 Generative models have a persistent limitation: their tendency to memorize training data can create legal liabilities and erode creative diversity. Understanding which samples are memorized in whole or in part, and under what conditions, therefore remains an important open problem. Here we answer the question "Are atypical or rare samples memorized first?" in the negative. We train diffusion models on strings generated according to the production rules of the Random Hierarchy Model (RHM), and find that samples composed of common substrings are preferentially memorized. This holds true even if the training data consists of entirely unique samples, indicating that deduplication at the data point level does not provide a meaningful privacy guarantee. Correspondingly we predict, then observe, delayed memorization for fat-tailed datasets (i.e., those with more atypical samples). This effect is amplified when fat-tails are introduced into high-level production rules. These together suggest that dataset diversity, particularly at higher levels of abstraction, plays an important role in staving off memorization. Finally, we identify an intermediate regime of partial memorization in which common substrings are learned first and subsequently overproduced during generation. If training is stopped in this regime, models will exhibit the reversion-to-the-mean blandness often derided as "slop". --- ### COFT: Counterfactual-Conformal Decoding for Fair Chain-of-Thought Reasoning in Large Language Models Authors: Arya Fayyazi, Mehdi Kamal, Massoud Pedram Published: 2026-05-28 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2605.30641v1 Large language models (LLMs) can reveal and amplify societal biases during chain-of-thought (CoT) generation. We present COFT (Chain of Fair Thought), a training-free decoding method that applies token-level fairness control at decode time, with distribution-free marginal validity guarantees (under exchangeability) for any frozen causal language model. COFT operates in three stages. First, it creates a masked counterfactual prompt by replacing sensitive spans with neutral tokens. Second, it compares the factual and masked logit distributions through lightweight logit fusion to attenuate attribute-driven biases. Third, it uses dual-branch split-conformal calibration to certify per-step candidate token sets at a user-chosen risk level. We evaluate COFT across six models and multiple bias benchmarks. Our method reduces standard bias metrics by 30-55% (median 38%) while preserving task utility and language quality. Reasoning accuracies remain unchanged within run-to-run noise margins. The computational overhead is modest, equivalent to one additional cached forward pass (<=11%). COFT offers a clear, auditable path to safer CoT generation with significant bias reduction, negligible utility loss, and no requirement for retraining, auxiliary classifiers, or weight access. --- ### CSULoRA: Closest Safe Update Low-Rank Adaptation Authors: Oleksandr Marchenko Breneur, Adelaide Danilov, Aria Nourbakhsh, Salima Lamsiyah Published: 2026-05-28 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2605.30640v1 Low-rank adaptation has become a standard method for parameter-efficient fine-tuning of large language models, but even small amounts of unsafe or adversarial fine-tuning data can substantially weaken the safety behavior of aligned models. Existing safety-preserving LoRA methods often rely on hard interventions such as projection, pruning, thresholding, or additional training objectives. While these methods can suppress unsafe update directions, they may also remove task-relevant information or require extra tuning. We introduce CSULoRA, a post-hoc method for correcting trained LoRA adapters through closest safe update estimation. CSULoRA estimates a safety-aligned subspace from the weight displacement between a safety-aligned model and its corresponding base checkpoint. It then decomposes each LoRA update into fully aligned, partially aligned, and off-subspace components. Instead of discarding components outside the estimated safety subspace, CSULoRA solves a closed-form penalized minimum-change problem that preserves the fully aligned component while smoothly attenuating potentially unsafe directions according to their relative energy. In adversarial fine-tuning experiments, CSULoRA substantially reduces attack success rate while preserving most of the utility gains obtained from standard LoRA fine-tuning. --- ### PInVerify: An Offline Embodied Benchmark for Active Instance Verification Authors: Yuhang Jiang Published: 2026-05-28 Categories: cs.CV, cs.AI, cs.RO arXiv: https://arxiv.org/abs/2605.30639v1 Embodied agents have made strong progress in navigating to target objects, but reaching the goal vicinity does not guarantee that the agent has found the correct instance: subtle attribute differences (e.g., "white floral" vs. "white striped") often require close-range, multi-view inspection. We address this gap with Active Instance Verification (AIV), a task in which an agent actively selects viewpoints around a candidate object to decide whether it matches a fine-grained natural-language description. We formalize AIV as a finite-horizon decision process and introduce PInVerify, an offline embodied benchmark for AIV: 3,000 evaluation episodes across 18 object categories, delivered as multi-view captures with a 6-sector navigation topology that exposes trap views (navigable but uninformative) and unreachable sectors. As reference baselines we build a training-free pipeline and a LoRA-fine-tuned end-to-end agent around open-source multimodal large language models (MLLMs) at on-device scale ($\leq$8B parameters), with attribute decomposition, a visibility-weighted multi-view tracker, and three next-best-view (NBV) strategies. In our evaluation across Qwen3-VL (4B/8B), SenseNova-SI-1.2-InternVL3-8B, CLIP, and SigLIP2, the best MLLM-based baseline exceeds the best embedding baseline by 4.9 pp; GT-box ablations show a +3.1 pp detection gap; and we do not observe reliable gains from active viewpoint selection within the tested NBV strategies. A LoRA-fine-tuned agent (SFT+GSPO) reaches 85.6%. PInVerify aims to support further work on active, fine-grained semantic verification in embodied AI. Code: https://github.com/Avalon-S/PInVerify. --- ### Score Broadcast and Decorrelation: A General Framework for Broadcast-Based Credit Assignment Authors: Mustafa Uzun, Mete Erdogan, Cengiz Pehlevan, Alper T. Erdogan Published: 2026-05-28 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2605.30638v1 We introduce Score Broadcast and Decorrelation (SBD), a principled framework for broadcast-based credit assignment for general families of differentiable losses. Error broadcast is a biologically plausible alternative to backpropagation that sends output information to hidden layers without weight transport. The Error Broadcast and Decorrelation (EBD) framework, recently introduced for the mean-squared-error (MSE) setting, grounded this mechanism in the stochastic orthogonality of optimal estimators, under which the optimal residual is orthogonal to functions of the input. We generalize that foundation by introducing an orthogonality principle between the output score (the gradient of loss with respect to the final-layer output) and hidden-layer activations, which holds whenever the optimal score has conditional mean zero. This single principle unifies broadcast-based credit assignment across the standard differentiable-loss families, including cross-entropy, Bregman divergences, proper scoring rules, and exponential-family negative log-likelihoods. The framework supplies a theoretical grounding for the three-factor learning rule under general losses, with the neuromodulatory factor derived as the broadcast loss score. We derive the cross-entropy case explicitly, characterize the admissible loss class, and introduce a score vector expansion technique that enriches the broadcast signal while preserving the orthogonality framework. Experiments on CIFAR-10 and Tiny ImageNet show that SBD substantially improves over existing broadcast approaches, with score vector expansion delivering further gains. Overall, this work identifies the loss score as the signal to broadcast, supplies the orthogonality theory and theoretical grounding for the three-factor learning rule from neuroscience, and shows how score vector expansion enriches the decorrelation directions of the resulting objective. --- ### EHRBench: An Automated and Reliable EHR-based Benchmark for Clinical Decision Making with LLMs Authors: Yuzhang Xie, Keqi Han, Yunpeng Xiao, Hejie Cui, Guanchen Wu, Ziyang Zhang, Kai Shu, Jiaying Lu, Xiao Hu, Carl Yang Published: 2026-05-28 Categories: cs.AI arXiv: https://arxiv.org/abs/2605.30637v1 Clinical decision-making (CDM) is central to real-world clinical workflows, where clinicians infer diagnoses, select treatments, or anticipate future health outcomes under incomplete evidence. LLMs are increasingly used to support these decisions due to strong language capabilities, broad biomedical knowledge, and efficiency, yet the reliability of LLMs on real-world clinical decision tasks remains insufficiently understood. To evaluate CDM models, especially LLM-based models, an ideal and practical medical decision benchmark should be constructed via an automated yet reliable pipeline to ensure both scale and quality. Moreover, the grounding of a CDM benchmark in real patient EHRs can better support evaluation on practical CDM tasks that require substantive biomedical knowledge and clinical inference. To fill the gaps, we introduce EHRBench, an automated and reliable EHR-grounded benchmark for evaluating LLM-based clinical decision-making at scale. To ensure scalability and reliability, EHRBench is constructed through an EHR-LLM-KB(knowledge-base) interaction pipeline. For efficiency, we use a specialized LLM to automatically convert encounter-level EHR trajectories into structured templates and deterministically instantiate the templates into QA items. In parallel, we apply systematic KB-based verification and enrichment to filter hallucinated or ambiguous relations and to improve reliability. Using this pipeline, we construct nearly 1M (960,067) QA items spanning three core inference-required clinical decision tasks: diagnosis, treatment, and prognosis. We benchmark more than 30 representative LLMs on EHRBench and provide detailed analyses of performance and robustness. The results show consistent capability trends across settings, further validating the reliability of EHRBench and highlighting actionable gaps toward clinically reliable LLM systems. --- ### CellBRIDGE: Learning Cellular Trajectories via Interaction-Aware Alignment Authors: Silas Ruhrberg Estévez, Nicolas Huynh, Tennison Liu, Roderik M. Kortlever, Gerard I. Evan, David L. Bentley, Mihaela van der Schaar Published: 2026-05-28 Categories: cs.LG, q-bio.GN arXiv: https://arxiv.org/abs/2605.30635v1 Inferring dynamics from population snapshots is a fundamental challenge in machine learning and biology. In scRNA-sequencing (scRNA-seq), destructive measurements preclude direct tracking of individual cells across time, making trajectory inference underdetermined. Optimal Transport (OT) provides a principled framework for snapshot alignment, but a long-standing modeling question is which cost functions yield biologically meaningful couplings. Standard OT approaches rely on gene-expression distances, implicitly treating cells as independent points and neglecting structured cell-cell communication mediated by ligand-receptor signaling. We introduce CellBRIDGE (Cell-Based Regularized Interaction-Driven Gene Expression), which augments feature-based OT with a directed, typed interaction cost derived from ligand-receptor activity. By explicitly modeling cell-cell communication, CellBRIDGE improves cross-snapshot couplings and downstream trajectory estimates across synthetic and real scRNA-seq datasets relative to feature-only baselines. Notably, CellBRIDGE enables mechanistically interpretable in silico perturbations: on lung cancer data, silencing specific ligand-receptor pairs induces trajectory shifts that recapitulate expected effects of targeted pathway inhibition. --- ### Rationalize: Shared Semantic Reasoning for Human-AI Alignment Authors: Aritra Dasgupta, Naga Datha Saikiran Battula, Avina Nakarmi, Sohom Sen, Subhodeep Ghosh, Xun Song Published: 2026-05-28 Categories: cs.HC, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2605.30632v1 We introduce Rationalize, a role-pair framework for shared semantic reasoning between humans and AI models in data-driven sensemaking. Building on ideas in human-machine teaming and critical thinking, we conceptualize human-AI interaction as a series of complementary role pairs (Explorer-Guide, Investigator-Informant, Teacher-Student, Judge-Advocate) operating in a shared reasoning space. In this space, human analysts and AI models (such as LLMs) make purposes, questions, assumptions, evidence, inferences, and implications explicit, facilitating alignment not only at the output level but at the level of rationalization of intent and action by each side. We relate these role pairs to the bidirectional human-AI alignment framework, illustrating how "aligning AI to humans" and "aligning humans to AI" differ by role, and sketch a collaborative research agenda for alignment design and assessment using element-level and role-specific approaches. --- ### Controllable Lung Nodule Synthesis via Histogram-Regularized Latent Diffusion Models Authors: Arunkumar Kannan, Yanbo Zhang, Han Liu, Michael Baumgartner, Jianing Wang, Alexander Hertel, Bogdan Georgescu, Sasa Grbic Published: 2026-05-28 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2605.30631v1 While automated diagnosis systems have achieved remarkable success in computed tomography (CT)-based lung cancer screening, their development remains limited by the scarcity of diverse, annotated pulmonary nodule datasets. Diffusion-based generative models offer a promising strategy for data synthesis; however, many existing conditional approaches primarily optimize spatial reconstruction losses, which encourage voxel-wise similarity but may inadequately constrain lesion-level intensity distributions. As a result, these methods may produce over-smoothed texture profiles and underrepresent the distinct attenuation characteristics of different nodule subtypes, including solid, part-solid, and ground-glass nodules. To address this challenge, we propose a controllable latent diffusion model that synthesizes pulmonary nodules within full 3D CT volumes while accurately modeling nodule-specific intensity distributions. Specifically, rather than relying solely on spatial losses, we introduce a histogram-based regularization term that constrains voxel intensity distributions during the generative process. The model combines subtype, spatial mask, and Hounsfield unit (HU) histogram conditioning with the differentiable feature-space histogram regularization term to better align lesion-level intensity distributions, improving the visual plausibility and subtype consistency of synthesized nodules. Extensive experiments on lung CT data demonstrate that our framework achieves strong visual realism, validated through both quantitative metrics and a visual Turing test. Furthermore, when used for data augmentation, the generated nodules improve performance in downstream clinical tasks, particularly for underrepresented nodule subtypes, and show a potential benefit for subtype-informed malignancy classification. --- ### The Architecture of Errors: From Universal Impossibility to Patch-Local LLM Reliability Authors: Mikhail L. Arbuzov, Lee Mosbacker, Sisong Bei, Ziwei Dong, Dmitri Kalaev, Alexey Shvets Published: 2026-05-28 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2605.30628v1 Universal LLM reliability is not a finite-library problem: across all possible tasks, tools, schemas, knowledge sources, and evaluator expectations, new intervention-distinguishable failure modes can appear without bound, so no finite intervention dictionary can guarantee bounded residual error for every such mode. But deployed systems do not operate over the whole universe. They operate inside operationally bounded patches (legal review, medical RAG, code repair, customer-support agents, contract extraction) with recurring tasks, schemas, tools, and evaluator expectations. Within such patches, empirical evidence suggests failures are sparse, repetitive, and concentrated in a small recurring catalogue, so reliability becomes a local catalogue-discovery and intervention-coverage problem rather than an exponential token-length problem. We formalize this transition with two propositions and one corollary. Proposition 1 is the worst-case-mode-wise negative result: no finite intervention dictionary covers every distinguishable failure mode of an unbounded domain. Corollary 1 is the inverse-discovery implication: the logarithmic upper bound on mode discovery cannot accommodate linearly more distinct tail modes without exponentially more observed hard-failure events. Proposition 2 is the positive patch-local result: under log active-mode exposure and head-heavy coverage, a sufficient per-hard-decision intervention budget grows polylogarithmically in sequence length and becomes domain-constant once the patch catalogue saturates. The framework relocates rather than dissolves long-context difficulty: where the number of hard decisions itself grows with task length, reliability remains hard; the contribution is to identify the on-axis intervention rather than to make those regimes easy. --- ### Active Timepoint Selection for Learning Measure-Valued Trajectories Authors: Nicolas Huynh, Mihaela van der Schaar Published: 2026-05-28 Categories: cs.LG, cs.AI, stat.ML arXiv: https://arxiv.org/abs/2605.30625v1 Inferring continuous probability paths from sparse snapshots is a fundamental challenge in domains like single-cell biology, where high-fidelity data acquisition is often destructive and constrained by prohibitive sequencing costs. This motivates the need for active learning strategies to strategically select optimal measurement times. However, designing active learning policies for this setting remains an open problem: the target objects reside on the infinite dimensional Wasserstein space where standard Euclidean metrics are ill-defined, and current interpolation methods lack epistemic uncertainty quantification. We introduce a framework which extends active experimentation to the space of measures. By leveraging Linearized Optimal Transport (LOT), we map distributional snapshots into a tangent space amenable to Gaussian Process modeling, allowing us to construct a tractable probabilistic surrogate for the underlying probability path. This yields an acquisition policy that iteratively selects measurement times to minimize uncertainty. Empirical results demonstrate that our strategy outperforms uncertainty-agnostic baselines on both synthetic and real-world datasets. --- ### Jamming-Resilient PRB Reservation for Latency-Critical O-RAN Network Slicing Authors: Elahe Delavari, Junaid Farooq Published: 2026-05-28 Categories: cs.NI, cs.LG arXiv: https://arxiv.org/abs/2605.30622v1 Open radio access network (O-RAN) architectures enable near real-time, software-driven control of network slicing through programmable xApps deployed on the near-real-time RAN Intelligent Controller (near-RT RIC). In industrial 5G downlink systems, adversarial jamming can abruptly reduce the effective physical resource block (PRB) capacity, triggering queue buildup and persistent latency violations, particularly in the presence of low spectral efficiency cell edge user equipments. This paper proposes a reserve-based resilience framework for PRB allocation in sliced O-RAN deployments. A finite pool of reserved PRBs is controlled by a near-RT RIC xApp that provides hybrid mitigation by proactively clearing backlog to build latency margin and reactively allocating reserve capacity during jammer active intervals. We formulate reserve activation as a constrained sequential decision problem and design a masked Deep Q-Network to learn effective control policies under non-stationary jamming. Simulation results show substantial reductions in URLLC latency violations and improved reserve efficiency compared to reactive baselines. --- ### Harness Updating Is Not Harness Benefit: Disentangling Evolution Capabilities in Self-Evolving LLM Agents Authors: Minhua Lin, Juncheng Wu, Zijun Wang, Zhan Shi, Yisi Sang, Bing He, Zewen Liu, Tianxin Wei, Zongyu Wu, Zhiwei Zhang, Dakuo Wang, Xiang Zhang et al. Published: 2026-05-28 Categories: cs.AI arXiv: https://arxiv.org/abs/2605.30621v1 LLM agents are increasingly deployed as systems built around editable external harnesses, including prompts, skills, memories and tools, that shape task execution without changing model parameters. Harness self-evolution adapts such agents by updating these harnesses from execution evidence. Yet it remains unclear whether a model's base capability in task-solving predicts its capabilities in harness self-evolution: which models produce useful harness updates, and which actually benefit from them? We analyze two harness self-evolution capabilities: (i) harness-updating, the capability to produce useful persistent harness updates from execution evidence; (ii) harness-benefit, the capability to benefit from updated harnesses during task solving. Our analysis reveals two findings. First, harness-updating is flat in base capability: models from different capability tiers produce harness updates that lead to surprisingly similar gains; even Qwen3.5-9B's updates yield gains comparable to those of Claude Opus~4.6. Second, harness-benefit is non-monotonic in base capability: weak-tier models benefit little from updated harnesses, mid-tier models benefit most, and strong-tier models benefit less than mid-tier. We trace low gains at the weak tier to two failure modes: weak-tier models may fail to activate relevant harness artifacts, or activate them but fail to follow them faithfully. These findings suggest investing capability budget in the task-solving agent rather than the evolver, and targeting harness invocation and long-horizon instruction following in agent training. Our source code is publicly available at https://github.com/A-EVO-Lab/a-evolve/tree/release/harness-evolution. --- ### Reward Learning from Best-of-$N$ Preference Data: Targets, Tradeoffs, and Design Principles Authors: Rattana Pukdee, Maria-Florina Balcan, Pradeep Ravikumar Published: 2026-05-28 Categories: stat.ML, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2605.30619v1 Best-of-$N$ sampling is widely used to construct pairwise preference data: $N$ candidates are drawn from a base distribution, and the best is paired with a rejected response. Despite its widespread use, what Bradley--Terry (BT) reward learning extracts from such data, and how to choose $N$ and the base distribution, remain unclear. We specialize a recent analysis of preference data via its induced conditional distribution to Best-of-$N$. For independent-reference variants, we derive closed-form reward targets as explicit functions of $N$ and the base distribution, and show that they preserve the latent reward ranking. For the practical Best-vs-Random and Best-vs-Worst variants, chosen and rejected responses are coupled through the same candidate set, so exact BT representability generally fails; nevertheless, bounded-class minimizers approach the reference targets as $N$ grows. Although margin and connectivity are known to govern sample efficiency in pairwise preference learning, Best-of-$N$ couples them through $N$ in opposing directions: larger $N$ widens pairwise margins but reduces connectivity. This trade-off yields two design principles: use larger $N$ when preference labels are the bottleneck, smaller $N$ when generation is the bottleneck; and shape the base distribution to place mass between the responses whose comparison matters most at test time. Experiments on synthetic and real preference data support the predicted dependence on sample size and base-distribution shape. --- ### Improving Selective Classification with Pairwise Queries for Binary Classification Authors: Harsh Vardhan, Sunav Choudhary, Natwar Modani, Arya Mazumdar Published: 2026-05-28 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.30615v1 In selective classification, a model predicts the labels of data samples where it is confident, and abstains from predicting labels for samples on which it is not confident. The rejected samples are often labeled by an expert, which is expensive. The budget for the expert is best utilized when the model has low error on non-rejected samples. However, the estimate of a model's confidence might be inconsistent with the model's predictions, which can lead to high error on non-rejected points. Such situations can readily occur in in-context binary classification by LLMs. To remedy this, we propose making additional pairwise queries to the same model. These pairwise queries can detect high-error samples and be incorporated into selective classification techniques to reduce the error on non-rejected samples. Theoretically, we establish the conditions under which a simple algorithm using pairwise queries outperforms an inconsistent confidence estimate. We support this insight through extensive experiments for $1$ synthetic and $4$ in-context learning-based real binary classification datasets. In all these cases, we show that our algorithms, using pairwise queries, obtain a better accuracy-cost tradeoff than using only the raw confidence estimates, for instance, the LLM's next-token logits. --- ### CacheProbe: Auditing Prompt Cache Isolation in Gateway APIs Authors: Ryan Fahey Published: 2026-05-28 Categories: cs.CR, cs.LG arXiv: https://arxiv.org/abs/2605.30613v1 Over the past year, prompt caching in Large Language Models (LLMs) has become increasingly more popular across inference APIs. Prompt caching helps save precious compute resources and speeds up response times by reusing parts of the KV cache of a specific prompt for another request. However, many implementations of prompt caching are not secure against timing attacks or even basic metadata disclosure. Gu et al. (ICML 2025) develop a method to audit prompt caching in LLMs. This paper investigates whether OpenRouter's API gateway architecture introduces prompt caching vulnerabilities that bypass provider-level prompt cache isolation guarantees. Most LLM inference providers implement per-account or per-organization prompt caching to prevent data leaks, but does routing through OpenRouter with shared organizational credentials inadvertently create global cache sharing across all OpenRouter users? --- ### ZAPS-DA: Zero-Phase Action Policy Smoothing with Decoupled Actor for Continuous Control in Reinforcement Learning Authors: Faiq Shamass Published: 2026-05-28 Categories: cs.RO, cs.LG, eess.SY arXiv: https://arxiv.org/abs/2605.30612v2 Continuous control policies trained with off-policy reinforcement learning frequently exhibit high-frequency action jitter, impractical for direct deployment on physical actuators. Post-hoc filtering attenuates jitter but adds phase lag; embedding smoothness penalties in the actor's loss couples them with the RL gradient and conflates reward regression with over-aggressive smoothing. We present ZAPS-DA, which reduces action jitter at deployment with negligible phase lag and no post-processing. ZAPS-DA pairs an unmodified main actor (trained by the base RL loss) with a separate decoupled actor trained via supervised imitation of zero-phase filtered targets stored in the replay buffer. The deployed policy is the decoupled actor: a feed-forward map from observation to smooth action, with no inference-time filter and no action-history input -- causal distillation of a non-causal filter. A magnitude-matched MSE loss gives zero-hyperparameter portability across optimizer classes. Validated with Soft Actor-Critic and a Savitzky-Golay filter in two driving simulators (paired n=150): on MetaDrive (anchor protocol), ZAPS-DA cuts steering jitter 14-21x and throttle jitter 3-5x (all $p<10^{-4}$, Bonferroni) while matching task-completion (p=0.28 success, p=0.31 crash) at 6.3% reward cost; on a custom Webots adaptive cruise control task, the same configuration yields a Pareto improvement -- reward parity (p=0.121), 8-45x steering-jitter reduction, task-failure rate 2.0% to 0.7%. Against CAPS, the standard penalty-based baseline -- at both its auto-entropy and native fixed-entropy operating points, with penalty weight, spatial noise, and entropy coefficient re-tuned per environment -- ZAPS-DA reaches 14.7x steering-jitter reduction versus CAPS's best 3.2x at matched seeds, a ~4.6x gap, with no per-environment tuning of the smoothness signal and post-hoc applicability to trained policies. --- ### Crafter: A Multi-Agent Harness for Editable Scientific Figure Generation from Diverse Inputs Authors: Haozhe Zhao, Shuzheng Si, Zhenhailong Wang, Zheng Wang, Liang Chen, Xiaotong Li, Zhixiang Liang, Maosong Sun, Minjia Zhang Published: 2026-05-28 Categories: cs.CV, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2605.30611v1 Scientific figures are among the most effective means of communicating complex research ideas, yet producing publication-quality illustrations remains one of the most labor-intensive parts of paper preparation. Existing automated systems each target a single figure type under text-only input, leaving the diversity of types and conditions researchers actually use unaddressed; their raster outputs further cannot be locally revised. Because scientific figures are structured compositions of discrete semantic components, the localized errors generators produce on such layouts demand not a stronger backbone but a harness. We instantiate this harness in two complementary systems: Crafter, a multi-agent harness for figure generation that generalizes across figure types and input conditions without architectural changes, and CraftEditor, which applies the same pattern to convert raster outputs into editable SVGs. Moreover, we introduce CraftBench, a benchmark spanning three figure types and four input conditions with human quality annotation. Experiments show that Crafter substantially outperforms both standalone generators and the agentic baseline on PaperBanana-Bench and CraftBench, with ablations confirming each component's independent contribution; CraftEditor faithfully converts outputs into editable SVGs that surpass all baselines. Our code and benchmark are available at https://github.com/HaozheZhao/Crafter. --- ### Constrained Flow Optimization via Sequential Fine Tuning for Molecular Design Authors: Sven Gutjahr, Riccardo De Santi, Luca Schaufelberger, Kjell Jorner, Andreas Krause Published: 2026-05-28 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.30610v1 Adapting generative foundation models, in particular diffusion and flow models, to optimize given reward functions (e.g., binding affinity) while satisfying constraints (e.g., molecular synthesizability) is fundamental for their adoption in real-world scientific discovery applications such as molecular design or protein engineering. While recent works have introduced scalable methods for reward-guided fine-tuning of such models via reinforcement learning and control schemes, it remains an open problem how to algorithmically trade-off reward maximization and constraint satisfaction in a reliable and predictable manner. Motivated by this challenge, we first present a rigorous framework for Constrained Generative Optimization, which brings an optimization viewpoint to the introduced adaptation problem and retrieves the relevant task of constrained generation as a sub-case. Then, we introduce Constrained Flow Optimization (CFO), an algorithm that automatically and provably balances reward maximization and constraint satisfaction by reducing the original problem to sequential fine-tuning via established, scalable methods. We provide convergence guarantees for constrained generative optimization and constrained generation via CFO. Ultimately, we present an experimental evaluation of CFO on both synthetic, yet illustrative, settings, and a molecular design task. Across these evaluations, CFO achieves consistent increases in reward while ensuring high constraint satisfaction, showcasing its practical utility for constrained generative optimization. ---