# Research Papers — 2026-05 · bundle page 240 of 326 > Full-text markdown of papers #11951–12000 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/240 [← Previous bundle](https://aipod.dev/papers/archive/2026-05/page/239.md) [Next bundle →](https://aipod.dev/papers/archive/2026-05/page/241.md) ### Cornerstones or Stumbling Blocks? Deciphering the Rock Tokens in On-Policy Distillation Authors: Yuxuan Jiang, Runchao Li, Shubhashis Roy Dipta, Dawei Li, Zhao Yang Published: 2026-05-10 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2605.09253v4 While recent work in Reinforcement Learning with Verifiable Rewards (RLVR) has shown that a small subset of critical tokens disproportionately drives reasoning gains, an analogous token-level understanding of On-Policy Distillation (OPD) remains largely unexplored. In this work, we investigate high-loss tokens, a token type that--as the most direct signal of student-teacher mismatch under OPD's per-token KL objective--should progressively diminish as training converges according to existing studies; however, our empirical analysis shows otherwise. Even after OPD training reaches apparent saturation, a substantial subset of tokens continues to exhibit persistently high loss; these tokens, which we term Rock Tokens, can account for up to 18\% of the tokens in generated outputs. Our investigation reveals two startling paradoxes. First, despite their high occurrence frequency providing a disproportionately large share of total gradient norms, Rock Tokens themselves remain stagnant throughout training, resisting teacher-driven corrections. Second, through causal intervention, we find that these tokens provide negligible functional contribution to the model's actual reasoning performance. These findings suggest that a vast amount of optimization bandwidth is spent on structural and discourse residuals that the student model cannot or need not internalize. By deconstructing these dynamics, we demonstrate that strategically bypassing these ``stumbling blocks'' can significantly streamline the alignment process, challenging the necessity of uniform token weighting and offering a more efficient paradigm for large-scale model distillation. --- ### LLM Agents Already Know When to Call Tools -- Even Without Reasoning Authors: Chung-En Sun, Linbo Liu, Ge Yan, Zimo Wang, Tsui-Wei Weng Published: 2026-05-10 Categories: cs.CL arXiv: https://arxiv.org/abs/2605.09252v2 Tool-augmented LLM agents tend to call tools indiscriminately, even when the model can answer directly. Each unnecessary call wastes API fees and latency, yet no existing benchmark systematically studies when a tool call is actually needed. We propose When2Tool, a benchmark of 18 environments (15 single-hop, 3 multi-hop) spanning three categories of tool necessity -- computational scale, knowledge boundaries, and execution reliability -- each with controlled difficulty levels that create a clear decision boundary between tool-necessary and tool-unnecessary tasks. We evaluate two families of training-free baselines: Prompt-only (varying the prompt to discourage unnecessary calls) and Reason-then-Act (requiring the model to reason about tool necessity before acting). Both provide limited control: Prompt-only suppresses necessary calls alongside unnecessary ones, and Reason-then-Act still incurs a disproportionate accuracy cost on hard tasks. To understand why these baselines fail, we probe the models' hidden states and find that tool necessity is linearly decodable from the pre-generation representation with AUROC 0.89--0.96 across six models, substantially exceeding the model's own verbalized reasoning. This reveals that models already know when tools are needed, but fail to act on this knowledge during generation. Building on this finding, we propose Probe&Prefill, which uses a lightweight linear probe to read the hidden-state signal and prefills the model's response with a steering sentence. Across all models tested, Probe&Prefill reduces tool calls by 48% with only 1.7% accuracy loss, while the best baseline at comparable accuracy only reduces 6% of tool calls, or achieves a similar tool call reduction but incurs a 5$\times$ higher accuracy loss. Our code is available at https://github.com/Trustworthy-ML-Lab/when2tool --- ### CalibFree: Self-Supervised View Feature Separation for Calibration-Free Multi-Camera Multi-Object Tracking Authors: Ruiqi Xian, Deep Patel, Iain Melvin, Sanjoy Kundu, Martin Renqiang Min, Dinesh Manocha Published: 2026-05-10 Categories: cs.CV arXiv: https://arxiv.org/abs/2605.09245v1 Multi-camera multi-object tracking (MCMOT) faces significant challenges in maintaining consistent object identities across varying camera perspectives, particularly when precise calibration and extensive annotations are required. In this paper, we present CalibFree, a self-supervised representation learning framework that does not need any calibration or manual labeling for the MCMOT task. By promoting feature separation between view-agnostic and view-specific representations through single-view distillation and cross-view reconstruction, our method adapts to complex, dynamic scenarios with minimal overhead. Experiments on the MMP-MvMHAT dataset show a 3% improvement in overall accuracy and a 7.5% increase in the average F1 score over state-of-the-art approaches, confirming the effectiveness of our calibration-free design. Moreover, on the more diverse MvMHAT dataset, our approach demonstrates superior over-time tracking and strong cross-view performance, highlighting its adaptability to a wide range of camera configurations. Code will be publicly available upon acceptance. --- ### How Much is Brain Data Worth for Machine Learning? Authors: Lane Lewis, Zhixin Wang, David Schwab, Xaq Pitkow Published: 2026-05-10 Categories: cs.AI, q-bio.NC arXiv: https://arxiv.org/abs/2605.09243v1 If a person can solve a task, can measuring their brain make it easier to train a model to solve that task too? Recent NeuroAI work suggests that supplementing task training with neural recordings can modestly improve model performance and robustness. However, it is unclear when there should be a benefit from using neural data and how much benefit to expect. We formulate this question mathematically, and begin to address it theoretically using a simple, analytically tractable linear gaussian model of task targets and neural recordings. For a multimodal estimator trained on both brain data and task labels, we derive scaling laws for how performance scales with the numbers of brain and task samples. From these laws we derive relative value and exchange rates between brain samples and task samples, quantifying how much extra task samples neural data is worth as a function of task-brain alignment, neural and task noise, latent dimension, and brain data sample size. We also analyze test distribution shift, to identify conditions where brain-regularized learning can produce substantial robustness gains through learned invariances. Finally, under a fixed collection budget, we characterize the regimes in which brain data is worth collecting. Our results provide a foundation for understanding how valuable brain data could be for improving machine learning. --- ### Cross-Modal Semantic-Enhanced Diffusion Framework for Diabetic Retinopathy Grading Authors: Yiqun Wang Published: 2026-05-10 Categories: eess.IV, cs.CV arXiv: https://arxiv.org/abs/2605.09242v1 Automated grading of diabetic retinopathy (DR) faces several critical challenges: subtle inter-grade visual distinctions in fine-grained lesion patterns, distributional discrepancies induced by heterogeneous imaging devices and acquisition conditions, and the inherent inability of purely visual approaches to exploit clinical semantic knowledge. In this paper, we propose CLIP-Guided Semantic Diffusion (CGSD), a DR grading framework that synergistically integrates vision-language pretraining with diffusion probabilistic modeling. We adopt a domain-specific vision-language model tailored for DR grading as the semantic guidance module and adapt it to the target domain via Low-Rank Adaptation (LoRA), effectively bridging the distributional gap between the pretrained model and the target dataset with only a minimal number of trainable parameters. Building on this foundation, we construct a cross-modal semantic conditioning vector by computing the dot product between image features and the text description features of each DR grade, yielding a joint representation that simultaneously encodes visual content and clinical-grade semantics. This vector serves as the conditioning signal for the diffusion denoising network, replacing the structurally complex dual-branch visual prior employed in existing diffusion-based classification methods. Experiments on the APTOS 2019 dataset demonstrate that the proposed approach achieves an accuracy of 87.5% and a macro-averaged F1 score of 0.731, outperforming a variety of representative methods. Ablation studies further validate the independent contribution of each constituent module. --- ### Sub-JEPA: Subspace Gaussian Regularization for Stable End-to-End World Models Authors: Kai Zhao, Dongliang Nie, Yuchen Lin, Zhehan Luo, Yixiao Gu, Deng-Ping Fan, Dan Zeng Published: 2026-05-10 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2605.09241v1 Joint-Embedding Predictive Architectures (JEPAs) provide a simpleframework for learning world models by predicting future latent representations.However, JEPA training is subject to a bias-variance tradeoff.Without sufficient structural constraints, excessive representationalvariance causes the model to collapse to trivial solutions.The recent LeWorldModel (LeWM) shows that this issue can be alleviated bysimply constraining latent embeddings with an isotropic Gaussian prior.However, latent representations inherently lie on low-dimensional manifoldswithin a high-dimensional ambient space, and enforcing an isotropic Gaussianprior directly in this ambient space introduces an overly strong bias.In this work, we propose ame, which seeks a favorable operatingpoint on the bias-variance frontier by applying Gaussian constraints inmultiple random subspaces rather than in the originalembedding space.This design relaxes the global constraint while preserving itsanti-collapse effect, leading to a better balance between trainingstability and representation flexibility.Extensive experiments across fourcontinuous-control environments demonstrate that consistentlyoutperforms LeWM with very clear margins.Our method is simple yet effective, and serves as a strong baseline for future JEPA-based world model research.fdefinedeeemodeThe code is available at https://github.com/intcomp/Sub-JEPA. --- ### Repeated-Token Counting Reveals a Dissociation Between Representations and Outputs Authors: Sohan Venkatesh Published: 2026-05-10 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2605.09239v2 Large language models fail at counting how many times a word repeats in a list, even though they perform well on far harder reasoning tasks. These failures are commonly attributed to limitations in internal count tracking. We show this attribution is wrong. Linear probes on the residual stream decode the correct count with near-perfect accuracy at every post-embedding layer and they do so even at the exact layers where the wrong answer crystallizes in the output. Attention patterns show no evidence of collapse over repeated tokens and tokenization artifacts account for none of the failure. Instead, a multi-layer perceptron (MLP) block at roughly 85--93\% network depth overwrites the correctly-encoded count with a fixed wrong answer. Ablating this block changes the wrong output and establishes it as causally responsible for the failure. The block fires on the space-separated repeated-word format and is absent for repeated digit-tokens. The pattern holds across Llama-3.2 (1B and 3B) and Qwen2.5 (1.5B, 3B and 7B) at consistent relative depth. The count is represented correctly and a specific computation prevents it from reaching the output, so representation failures and routing failures require different interventions. --- ### Intrinsic Muon: Spectral Optimization on Riemannian Matrix Manifolds Authors: Yibang Li, Bihari Lal Pandey, Ravi Sah, Andi Han, Cyrus Mostajeran, Pratik Jawanpuria, Bamdev Mishra Published: 2026-05-10 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2605.09238v1 Muon and related norm-constrained matrix optimizers have become central to large-scale learning problems. They are formulated as a linear maximization oracle (LMO) over an ambient matrix-norm ball in unconstrained Euclidean space. However, these do not generalize cleanly to manifold-valued parameters such as low-rank factorizations, orthogonality constraints, or symmetric positive definite (SPD) matrices. Naively restricting the Muon LMO to the tangent space (i) breaks quotient symmetries and (ii) couples the tangent-space constraint with an ambient norm bound, thereby obstructing closed-form solutions on various manifolds of interest. We resolve both issues with a single observation: every Riemannian metric canonically lifts a unitarily invariant Euclidean norm to an intrinsic norm on each tangent space, and the resulting intrinsic norm constrained LMO is symmetry preserving. Building on this, we introduce intrinsic Muon (iMuon), a unified framework that yields closed-form updates on the fixed-rank, SPD, Stiefel, and Grassmann manifolds for any unitarily invariant norm, including the spectral, Frobenius, and nuclear norms. We establish convergence guarantees for both deterministic and stochastic iMuon with rate constants that depend only on the manifold dimension. Notably, on the fixed-rank manifold this constant depends only on the rank, making the rate independent of factor conditioning and removing the runtime factor-rescaling required by prior work. Experiments on LoRA finetuning of LLMs, image classification, and subspace learning illustrate the efficacy of the proposed approach. --- ### Matching Meaning at Scale: Evaluating Semantic Search for 18th-Century Intellectual History through the Case of Locke Authors: Yu Wu, Ananth Mahadevan, Filip Ginter, Michael Mathioudakis, Mikko Tolonen Published: 2026-05-10 Categories: cs.CL, cs.AI, cs.CY, cs.DL, cs.IR arXiv: https://arxiv.org/abs/2605.09236v2 While digitized corpora have transformed the study of intellectual transmission, current methods rely heavily on lexical text reuse detection, capturing verbatim quotations but fundamentally missing paraphrases and complex implicit engagement. This paper evaluates semantic search in 18th-century intellectual history through the reception of John Locke's foundational work. Using expert annotation grounded in a semantic taxonomy, we examine whether an off-the-shelf semantic search pipeline can surface meaning-level correspondences overlooked by lexical methods. Our results demonstrate that semantic search retrieves substantially more implicit receptions than lexical baselines. However, linguistic diagnostics also reveal a "lexical gatekeeping" effect, where retrieval remains partially constrained by surface vocabulary overlap. These findings highlight both the potential and the limitations of semantic retrieval for analyzing the circulation of ideas in large historical corpora. The data is available at https://github.com/COMHIS/locke-sim-data. --- ### On Variance Reduction in Learning Mean Flows Authors: Juanwu Lu, Ziran Wang Published: 2026-05-10 Categories: cs.LG, cs.AI, stat.ML arXiv: https://arxiv.org/abs/2605.09235v2 One-step generative modeling has emerged as a leading approach for amortizing the inference cost of diffusion and flow-matching models. Among distillation-free methods, MeanFlow training is notoriously unstable, with non-decreasing loss and unbounded gradient variance. In this work, we establish a theory that attributes this pathology to a misuse of the conditional velocity field. We show that the conditional velocity plays two distinct statistical roles in the loss: both as an unbiased regression target and as a Monte Carlo control variate in a Jacobi-vector product, with the original MeanFlow loss assigning the wrong coefficient to the latter. We derive the optimal coefficient in closed form and show that a family of fixes in concurrent works corresponds to different practical realizations of the same optimum. A controlled sweep of this coefficient on two-dimensional benchmarks and on a latent Diffusion Transformer recovers the predicted bias-variance ordering. Our DiT experiment also reveals a quantitative FID-MSE landscape mismatch. Specifically, although the gradient-MSE is minimized at an interior coefficient value near $β\!=\!0.94$, the coefficient that minimizes FID prefers to use conditional velocity directly at the unbiased corner. Our analysis therefore explains why MeanFlow is unstable and unifies its concurrent remedies, and shows that the variance-optimal coefficient need not coincide with the quality-optimal one. --- ### Towards Robust Sequential Decomposition for Complex Image Editing Authors: Zilai Zeng, Mingdeng Cao, Zijie Li, Xiaochen Lian, Yichun Shi, Peihao Zhu, Chen Sun, Peng Wang Published: 2026-05-10 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2605.09233v2 Recent advances in visual generative models have enabled high-fidelity image editing guided by human instructions. However, these models often struggle with complex instructions involving combinatorial editing operations or inter-step dependencies. This difficulty stems from the limitations of two canonical paradigms: (1) single-turn editing, which attempts to apply all instructed edits in one pass, often fails to parse the complex instruction accurately and causes undesired edits; and (2) sequential editing can decompose the task into simpler steps but suffers from compounding errors introduced by the sequential execution, leading to low-fidelity results. To derive a robust solution for complex image editing, we examine editing behaviors of different paradigms under a unified in-context editing framework, and study how the benefits of sequential decomposition can be balanced against its error-accumulation drawbacks. We further develop a synthetic data pipeline that constructs editing tasks of varying instruction complexity, allowing us to curate a large-scale editing dataset with high-quality decomposed sequences. By finetuning on synthetic data, we discovered that with properly designed editing paradigms, sequential decomposition yields robust improvements even as task complexity increases. Furthermore, the decomposition skills learned from synthetic tasks can transfer to real images by co-training with real-world editing data, demonstrating the promise of sim-to-real generalization for tackling complex image editing across broader domains. --- ### Privacy-Preserving Distributed Learning in IoT Systems: A Unified Threat Model and Evaluation Framework Authors: John Cartmell, Alexander Williams Published: 2026-05-10 Categories: cs.CR, cs.LG arXiv: https://arxiv.org/abs/2605.09232v1 The increasing deployment of Internet-of-Things (IoT) devices has accelerated the use of distributed learning frameworks, where data remains local while model updates are shared across decentralized systems. Although this reduces centralized data collection, it introduces privacy risks through the exchange of gradients, model parameters, and intermediate representations. A variety of privacy-preserving techniques have been proposed to address these risks, including differential privacy, cryptographic methods, and lightweight system-level approaches. However, existing surveys often evaluate these methods in isolation and lack a unified framework for comparing their effectiveness under realistic attack models and IoT resource constraints. This paper presents a structured analysis of privacy-preserving techniques for distributed learning in IoT environments. A unified threat model is introduced that captures model inversion, membership inference, gradient leakage, and communication-based attacks. Building on this model, an evaluation framework is developed to compare methods in terms of both privacy robustness and system-level efficiency, including computational, memory, and communication overhead. Using this framework, representative approaches including differential privacy, homomorphic encryption, secure multi-party computation, distributed selective stochastic gradient descent, and Bloom Filter-based methods are analyzed. The results highlight a fundamental trade-off between privacy strength and system efficiency. In particular, Bloom Filter-based encodings are shown to provide lightweight privacy through collision-induced ambiguity while maintaining low computational and communication overhead. The paper provides a unified perspective on privacy-preserving design choices for distributed learning in IoT systems. --- ### An Elastic Shape Variational Autoencoder for Skeleton Pose Trajectories Authors: Arafat Rahman, Shashwat Kumar, Laura E. Barnes, Anuj Srivastava Published: 2026-05-10 Categories: cs.CV, stat.ML arXiv: https://arxiv.org/abs/2605.09231v3 Deep generative models provide flexible frameworks for modeling complex, structured data such as images, videos, 3D objects, and texts. However, when applied to sequences of human skeletons, standard variational autoencoders (VAEs) often allocate substantial capacity to nuisance factors-such as camera orientation, subject scale, viewpoint, and execution speed-rather than the intrinsic geometry of shapes and their motion. We propose the Elastic Shape - Variational Autoencoder (ES-VAE), a geometry-aware generative model for skeletal trajectories that leverages the transported square-root velocity field (TSRVF) representation on Kendall's shape manifold. This representation inherently removes rigid translations, rotations, and global scaling of shapes, and temporal rate variability of sequences, isolating the underlying shape dynamics. The ES-VAE encoder maps skeletal sequences to a low-dimensional latent space incorporating the Riemannian logarithm map, while the decoder reconstructs sequences using the corresponding exponential map. We demonstrate the effectiveness of ES-VAE on two datasets. First, we analyze skeletal gait cycles to predict clinical mobility scores and classify subjects into healthy and post-stroke groups. Second, we evaluate action recognition on the NTU RGB+D dataset. Across both settings, ES-VAE consistently outperforms standard VAEs and a range of sequence modeling baselines, including temporal convolutional networks, transformers, and graph convolutional networks. More broadly, ES-VAE provides a principled framework for learning generative models of longitudinal data on pose shape manifolds, offering improved latent representation and downstream performance compared to existing deep learning approaches. --- ### Human-in-the-Loop Large Language Model Framework for Identification of Cutaneous Immune-Related Adverse Events Authors: Charles Lu, Olivia Burke, Debby Cheng, Adam Kashlan, Caitlyn Duffy, Zeyun Lu, Lirit Fuksman, Jin Ning Tian, Andrew Sedlack, Priya Katyal, Eudora Lee, Ralina Karagenova et al. Published: 2026-05-09 Categories: cs.CL, cs.HC, cs.MA arXiv: https://arxiv.org/abs/2607.20428v1 This study evaluated a retrieval-augmented, multi-agent large language model (LLM)-driven, human-in-the-loop framework for detecting cutaneous immune-related adverse events (cirAEs) from clinical notes. Compared with unassisted manual review, the LLM-assisted workflow improved accuracy (F1 = 0.88 vs 0.77), inter-rater agreement measured by Cohen's kappa (kappa = 0.82 vs 0.50), and reduced average review time by approximately half. This framework pilots how LLMs can be applied to identify immune-related toxicities across organ systems and, more broadly, enable accurate, scalable, and transparent adverse event data extraction. --- ### ColGraphRAG: Late-Interaction Evidence Retrieval for Multimodal GraphRAG Authors: Seonok Kim Published: 2026-05-09 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2607.16208v1 Graph-grounded multimodal question answering organizes text, tables, and images in a structured evidence graph, yet end-to-end accuracy depends on which multimodal assets are ranked highly enough to enter downstream reasoning; for graph-linked images, single-vector bi-encoder similarity can discard patch- and token-level structure needed for fine-grained alignment. We evaluate replacing the visual candidate-ranking operator over graph-linked image nodes with late-interaction MaxSim-style multi-vector scoring in the ColBERT/ColPali lineage, while keeping offline graph construction, text- and table-side retrieval, structured extraction, and downstream reasoning unchanged. On MultimodalQA, this change is associated with improved retrieval-stage point estimates for graph-linked image candidates and downstream QA gains, with larger movement where visual evidence matters most and mixed trends on text-dominant questions; we interpret the pattern as mechanism-level evidence for graph-linked visual evidence inclusion, while broader validation and finer graph-level diagnostics remain important future work. --- ### JUMP: Efficient Membership Inference on Fine-Tuned Diffusion Language Models Authors: Yeachan Jun, Albert No Published: 2026-05-09 Categories: cs.AI, cs.CR arXiv: https://arxiv.org/abs/2607.16207v3 Membership inference attacks (MIAs) test whether a candidate example was used to train a language model. Existing attacks on fine-tuned discrete diffusion language models (dLLMs) often aggregate reconstruction signals across many mask configurations, requiring repeated model evaluations. We propose Joint Uncertainty Guided Mask Probing (JUMP), an efficient MIA that exploits the ability of dLLMs to predict masked tokens in parallel. Using the pre-fine-tuning checkpoint as a reference, JUMP selects low-confidence positions, masks them jointly, and aggregates clipped target-reference reconstruction gaps. This focuses the attack on positions that reveal stronger membership signals from fine-tuning. After mask selection, all selected tokens are evaluated with one scoring query per model. Across six MIMIR domains, JUMP improves mean ROC-AUC over a prior multi-mask attack from 0.819 to 0.902 on LLaDA and from 0.851 to 0.942 on Dream. Including mask selection, it requires only three forward passes per example, compared with 32 for the baseline. We further extend JUMP to the target-only setting by replacing target-reference scoring with relative token preference, which compares the observed token with alternative predictions at the same masked position. Target-Only JUMP achieves mean ROC-AUCs of 0.609 and 0.638 on LLaDA and Dream. --- ### JUMP: Single-Pass Membership Inference on Fine-Tuned Diffusion Language Models Authors: Yeachan Jun, Albert No Published: 2026-05-09 Categories: cs.AI, cs.CR arXiv: https://arxiv.org/abs/2607.16207v1 Membership inference attacks (MIAs) test whether a candidate example appeared in a model's training data. We study MIAs for fine-tuned discrete diffusion language models (dLLMs), where membership means inclusion in the target model's fine-tuning set. Unlike autoregressive language models, dLLMs allow an attacker to choose arbitrary mask sets and obtain token distributions for all masked positions in parallel. The prior dLLM attack, SAMA, follows a natural loss-mimicking strategy by averaging reconstruction signals over many randomly sampled masks, but it uses the any-order interface only as randomization and requires many target/reference queries. We propose JUMP (Joint Uncertainty-Guided Mask Probing), a single-pass scoring attack that exploits both distinctive properties of dLLMs: any-order decodability is used to select low-reference-confidence positions, and parallel decodability is used to score all selected positions through one joint masked query per model. JUMP masks the selected positions jointly and computes a clipped target/reference reconstruction-gap statistic. On fine-tuned LLaDA-8B-Base across six MIMIR domains, JUMP improves mean ROC-AUC from 0.82 to 0.90 over SAMA and substantially improves low-FPR detection, while requiring only one selector pass and one scoring pass through each of the target and reference models. --- ### Budgeted Subset Refinement for Execution-Aware LLM Research Ideation Authors: Micah Zhang Published: 2026-05-09 Categories: cs.CL, cs.SE arXiv: https://arxiv.org/abs/2607.14118v1 Large language models (LLMs) can generate research ideas that appear novel to expert reviewers, but recent work also shows that such ideas often lack diversity, are difficult for LLMs to evaluate reliably, and may fail to translate into strong executed projects. This paper evaluates a controlled proxy benchmark for a pre-execution scaffolding problem: given a noisy pool of LLM-generated research ideas, how should a system allocate limited refinement effort to construct a stronger, more diverse, more execution-aware portfolio for human researchers under a fixed rubric? We introduce Budgeted Subset Refinement, a family of strategies that refine only a selected subset of candidates rather than refining all candidates uniformly. In a unified shared-candidate-pool evaluation across 10 random seeds and 10 research-ideation environments, raw generation and reranking alone produce no research-strong nonduplicate ideas under the benchmark rubric, while refinement is necessary for strong proxy-rated portfolios. Uniform refinement produces strong individual ideas but is not the best portfolio-level allocation of compute. Random-k refinement is a strong low-cost baseline, while diversity-aware MMR-k refinement gives the best overall proxy tradeoff: the highest research-strong nonduplicate yield, the lowest duplicate rate among successful methods, and the best cost per research-strong nonduplicate idea. A blinded external-judge robustness check on a balanced 72-item sample supports the broad refinement effect across independent model families, while showing that per-item rankings among refined strategies vary by judge. These results suggest that LLM research ideation systems should be evaluated not only as idea generators, but as budgeted support-allocation systems. The claims are scoped to proxy-rated portfolio quality and do not substitute for expert review or execution-grounded validation. --- ### Graph-Based Detection of Disinformation Narrative Diffusion between Russian and Ukrainian Telegram Channels Authors: Yuliia Vistak, Viktoriia Makovska, Vera Schmitt, Veronika Solopova Published: 2026-05-09 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2607.11894v1 Detecting disinformation narratives on social media is challenging due to the scale of amplification, rapid evolution, and linguistic variability of online content. We propose a graph-based framework for identifying and analyzing disinformation narratives in Telegram ecosystems by combining weak supervision with propagation graph analysis. The approach aggregates semantically related claims into narrative-level clusters and models their diffusion across interconnected channels. This enables the detection of coordinated narrative amplification that is difficult to capture through post-level analysis alone. Our results demonstrate that integrating textual signals with network structure provides a scalable method for detecting disinformation narratives and offers insights into how they propagate within large-scale messaging environments. --- ### The Interference Gap: Comparing Retrieval Bounds in Human Memory and RAG Systems Authors: Dongxin Guo, Jikun Wu, Siu-Ming Yiu Published: 2026-05-09 Categories: cs.IR, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2606.28327v1 How do retrieval bounds compare between human episodic memory and Retrieval-Augmented Generation (RAG) systems under semantic interference? We present a unified signal detection theory (SDT) framework that applies to both, and use it to fit behavioral and computational data in matched paradigms. Both systems show logarithmic accuracy decline with association count (fan), but humans exhibit lower interference sensitivity ($α/σ= 0.41$) than dense passage retrieval ($α/σ= 0.67$), with cognitively-inspired HippoRAG falling between the two ($α/σ= 0.44$). Behavioral experiments ($N = 112$) and simulations validate the framework; parameter recovery confirms identifiability ($r \geq .93$) and model comparison favors the logarithmic specification over a power-law alternative ($Δ$BIC $> 15$). We discuss encoding specificity, temporal context binding, and retrieval gating as candidate mechanisms whose causal role remains to be established. Six falsifiable predictions connect cognitive memory research with AI retrieval evaluation. --- ### Where Larger Models Excel: The Primacy of Constraint-Guided Reasoning Authors: Guan-Yi Lin, Hen-Hsen Huang Published: 2026-05-09 Categories: cs.CL arXiv: https://arxiv.org/abs/2606.26108v1 Larger language models consistently outperform smaller ones on reasoning benchmarks, yet the reasoning differences underlying this gap remain underexplored. Across benchmarks in mathematics, physics, chemistry, and programming, we observe stable performance gaps: averaged over datasets, Qwen3-32B outperforms Qwen3-8B by 6.43%, while GPT-OSS-120B exceeds GPT-OSS-20B by 7.38%. To study the reasoning differences behind these gains, we develop AdvCluster, an automated framework that identifies questions where the larger model shows a stable advantage, extracts fine-grained advantage descriptions from paired reasoning traces produced by larger and smaller models, and organizes them through semantic clustering with quantitative evaluation and selection guided by a reviewer model. Our analysis yields a systematic taxonomy of larger model reasoning advantages, spanning both common advantages that recur across domains and specialized advantages associated with particular domains. Across these patterns, a recurring theme is Constraint-Guided Reasoning: larger models are better at identifying explicit and implicit constraints, organizing them into structured reasoning, and using them to rule out infeasible paths and verify intermediate steps. --- ### The Challenges of Balancing AI Compliance and Technological Innovations in Critical Sectors: A Systematic Literature Review Authors: Ayush Enkhtaivan, Chinazunwa Uwaoma Published: 2026-05-09 Categories: cs.CY, cs.AI arXiv: https://arxiv.org/abs/2606.12423v1 The rapid integration of artificial intelligence (AI) into critical infrastructure including healthcare, finance, energy, and defense, offers transformative benefits but also conflicts with evolving regulatory and governance frameworks. This paper presents a systematic literature review (SLR) to examine the challenges of balancing AI compliance and technological innovation across critical infrastructure sectors. The review follows established SLR guidelines to extract and synthesize insights from peer-reviewed articles, report, and institutional sources published between 2020-2025. The study identifies three interrelated challenges: fragmented regulations, excessive compliance burdens for smaller to medium enterprises (SMEs), and misaligned governance models. To address these challenges, the study highlights practical governance strategies, including risk-tiered regulation, compliance by design, and explainable AI, to support scalable and trustworthy AI deployment in critical sectors. Key contributions include a concise mapping of core AI-governance challenges and a conceptual diagram illustrating their overlap, as well as actionable strategies for policymakers and practitioner to harmonize oversight with innovation. --- ### Mechanistic Analysis of Alignment Algorithms in Language Models Authors: Aarush Sinha, Ishan Garg, Veeraraju Elluru, Arth Singh, Kushal Garg Published: 2026-05-09 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2606.09850v1 Post-training alignment algorithms are predominantly evaluated as black boxes, obscuring how they reshape language models' internal computations. We present a systematic mechanistic analysis of six preference-optimization methods: PPO, DPO, SimPO, ORPO, GRPO, and KTO across three open-weight model families. By integrating layer-wise linear probing, Sparse Autoencoders, and crosscoders, we localize preference representations and quantify alignment-induced geometric transformations in latent space. We find that preference signals consistently concentrate in early--mid or mid--late layers, but different objectives induce qualitatively distinct representational shifts. KTO and GRPO enhance linear separability through constructive feature sharing and sparse, high-salience recruitment. In contrast, DPO and ORPO degrade separability via non-constructive geometric rotation and feature attenuation, while PPO and SimPO largely preserve baseline geometry. These transformations exhibit architecture-dependent variability, demonstrating that behavioral alignment does not imply uniform internal restructuring. Our findings establish alignment as a heterogeneous intervention, motivate standardized feature-level auditing for safety and interpretability, and highlight the need for mechanism-aware optimization objectives. --- ### Methods for Formal Verification of Agent Skills: Three Layers Toward a Mechanically Checkable Capability-Containment Proof Authors: Alfredo Metere Published: 2026-05-09 Categories: cs.AI, cs.LO, cs.MA arXiv: https://arxiv.org/abs/2605.23951v1 The companion paper introduced a four-level verification lattice on agent-skill manifests (unverified, declared, tested, formal) and left the top level aspirational. This paper closes that gap. We give a precise semantics for skill behaviour faithful to how a skill is consumed by an LLM-driven runtime (a deterministic script-side reachable through a non-deterministic LLM-side), state the verification problem as a capability-containment property over that semantics, and present three composable methods that together raise a skill from declared or tested to formal: (1) sound static capability-containment analysis of the script-side via abstract interpretation over a small effect lattice; (2) a refinement type system for tool-call envelopes that mechanically rejects any call whose statically-inferred capability is not in the manifest's declared set; (3) SMT-bounded model checking against the parent paper's biconditional correctness criterion, with the bound chosen so any counter-example fitting the runtime's transaction-buffer horizon is exhibited as a concrete trace. We prove the three layers composed soundly cover the parent paper's threat model modulo a single residual (the LLM's freedom to refuse to act) that the parent paper's runtime biconditional catches at session boundary. The methods reuse existing well-engineered tools (Z3, Semgrep, CodeQL, refinement-type checkers, mechanised proof assistants) rather than asking operators to build new ones, and the proof-carrying artifact extends the existing SKILL.md convention. All three methods plus the bundle producer and re-checker ship as zero-dependency JavaScript modules in the open-source enclawed framework (https://github.com/metereconsulting/enclawed; project page https://www.enclawed.com/), with 53 unit tests and an end-to-end CLI demo on a sample skill. --- ### Visibility nowcasting in South Korea: a machine learning approach to class imbalance and distribution shift Authors: Bong Gyun Shin, Chan Sik Lee, Hyesun Suh Published: 2026-05-09 Categories: physics.ao-ph, cs.AI, cs.CE, cs.LG arXiv: https://arxiv.org/abs/2605.21507v1 Atmospheric visibility is a critical variable for transportation safety and air quality management, however, accurate prediction remains challenging due to the complex interactions between meteorological conditions and air pollutants, as well as the rarity of low-visibility events. This study introduces a machine learning framework to nowcast visibility in six major South Korean cities. To handle the imbalance in the 2018-2020 training data, we applied the Synthetic Minority Over-sampling Technique with Nominal and Continuous (SMOTENC) and Conditional Tabular Generative Adversarial Network (CTGAN). An ensemble approach combining machine learning and deep learning models was then used and evaluated on a 2021 test dataset. The results revealed a marked decline in predictive performance in the test set compared to the cross-validation phase. This degradation was attributed to a distributional shift between training and testing periods, which was quantitatively confirmed by measuring the Wasserstein distance of the most influential feature identified by SHAP analysis. In general, this study presents a methodology that aims to simultaneously address the dual challenges of data imbalance and temporal distributional shifts, and emphasizes the necessity of accounting for evolving external environmental factors when implementing nowcasting models on time-series data. --- ### Canonical Functionalism: Defining Functional Structure without Observer-Relative Semantic Maps Authors: Ryota Kanai, Shuqin Ma Published: 2026-05-09 Categories: q-bio.NC, cs.NE arXiv: https://arxiv.org/abs/2605.21506v1 Computational functionalism about consciousness is often criticized for relying on observer-relative interpretations of physical systems. This paper proposes a mathematical refinement of functionalism that avoids this problem. The central idea is that consciousness-relevant functional organization should be identified not with arbitrary input-output mappings, semantic labels, or externally imposed computational descriptions, but with a system's canonical functional structure: the minimal state-transition structure obtained by identifying internal states that have identical future behavior under all possible continuations. On this view, a state is functionally defined by its complete counterfactual role: how the system would evolve and respond from that state under possible future interactions. We call this position canonical functionalism. The framework does not claim to identify which systems are conscious, nor to show that functional organization is sufficient for consciousness. Rather, it identifies the canonical object over which functionalist theories of consciousness should be formulated: the task is to specify consciousness-relevant invariants, measures, or structural conditions over canonical functional structures, rather than over arbitrary semantic interpretations or superficial behavioral profiles. This reframes familiar objections about lookup tables, simulations, unfolding, and observer-relative computation: such cases do not by themselves refute functionalism, but force the functionalist to specify whether the relevant canonical structure is preserved, and if not, which additional structural features are missing. --- ### Machine Learning-Based Pre-Test Risk Stratification for PCR-Confirmed Chlamydia Using Patient-Reported Data and Urine Biomarkers Authors: Mehrab Mahdian, Marko Lehes, Katrin Krolov, Tamas Pardy Published: 2026-05-09 Categories: cs.LG, cs.DB arXiv: https://arxiv.org/abs/2605.16365v1 Early identification of individuals at elevated risk of Chlamydia trachomatis infection may enable optimal use of molecular testing in resource-aware screening. We evaluate the feasibility of pre-test risk stratification (PTRS) using machine-learning models trained on routinely available, non-invasive clinical data. A curated dataset of 93 urine samples with PCR reference labels was analyzed using three feature groups: patient-reported history and symptoms, urine biomarkers from standard urinalysis, and their combination. Five supervised classifiers were evaluated using stratified 5-fold cross-validation with out-of-fold probability estimates. Performance was assessed using area under the receiver operating characteristic curve (AUC) and threshold-dependent metrics, with uncertainty quantified via bootstrap confidence intervals. Models using only patient-reported data showed moderate discrimination (AUC up to 0.72). Urine biomarker-based models demonstrated slightly lower peak discrimination but more consistent performance, with ensemble methods yielding the strongest results. Combining feature groups marginally increased the peak AUC and reduced performance variability across models, indicating improved robustness. Findings indicate that urine biomarkers provide a reliable predictive signal for PTRS that is complementary to patient-reported information, while feature integration enhances robustness. This work supports the integration of non-invasive, routinely available information for PTRS into screening workflows, including decentralized or home-based PCR contexts, to optimize testing prioritization. --- ### WASIL: In-the-Wild Arabic Spoken Interactions with LLMs Authors: Zien Sheikh Ali, Hamdy Mubarak, Soon-Gyo Jung, Hunzalah Hassan Bhatti, Firoj Alam, Shammur Absar Chowdhury Published: 2026-05-09 Categories: cs.SD, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2605.16364v2 Large Language Models (LLMs) voice assistants are commonly built as cascaded Automatic Speech recognition (ASR) to LLM systems, where recognition errors can distort user intent. Dislikes may also arise from ambiguous, out-of-domain, or non-request turns, making it hard to isolate ASR effects. We release WASIL (it denotes connection or linking in Arabic): in-the-wild Arabic spoken interaction prompts with audio, ASR hypotheses, assistant responses, and explicit like/dislike feedback (8,529 turns; 14.2% dislikes), plus a 2,000-turn test set covering Modern Standard Arabic (MSA) and four major dialects with their labels. We provide low-cost gold transcripts via multi-ASR agreement-guided post-editing and annotate answerability (answerable, ambiguous/needs-clarification, unsupported, not-a-request/noise) to separate intrinsic unanswerability from ASR-induced degradation. Finally, we describe scalable reference-free evaluation of responses from ASR vs. gold transcripts using multi-judge LLM scoring. --- ### ORACLE: Anticipating Scams from Partial Trajectories in Streaming App Usage Authors: Wenbo Gao, Songbai Tan, Zhongan Wang, Fei Shen, Gang Xu, Huiping Zhuang, Yunyun Yang, Ming Li, Xiaofeng Zhu Published: 2026-05-09 Categories: cs.LG, cs.CY arXiv: https://arxiv.org/abs/2605.16363v1 Smartphone scams are increasingly prevalent and typically manifest as multi-stage, cross-application processes with gradually emerging intent. Effective intervention thus requires anticipating scams before the intent becomes explicit. This is inherently challenging, as decisions must rely on partial trajectories with temporally distributed evidence. In this paper, we propose \textbf{ORACLE} Online Reasoning for Anticipating Cross-temporal Latent thrEats, the first agentic framework for early scam anticipation from \textit{streaming app-usage} trajectories. To support this setting, we curate a real-world long-horizon benchmark of streaming app-usage trajectories, covering 12 scam types, spanning extended periods (15 days on average), involving diverse applications (95 apps), and interleaving normal and scam behaviors. To address fragmented evidence, we introduce a self-evolving context manager that adaptively consolidates entity-centric interactions over time, enabling more effective reconstruction of cross-temporal evidence from partial observations. To enhance sensitivity to latent early-stage signals, we propose an on-policy self-distillation scheme in which a teacher model, conditioned on summarized anti-scam reflections and clues by skills, supervises a student model without access to such reflections. This scheme thereby distills evidence-informed knowledge and improves recognition of emerging fraud patterns from partial trajectories. Experiments show that \method{} consistently improves early scam anticipation, yielding timely warnings while reducing false alerts in realistic streaming scenarios. --- ### When Is Rank-1 Steering Cheap? Geometry, Granularity, and Budgeted Search Authors: John T. Robertson, Jianing Zhu, Haris Vikalo, Zhangyang Wang Published: 2026-05-09 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2605.16362v2 Activation steering offers a lightweight way to control LLMs without retraining, but its effectiveness varies sharply across concepts. Prior work often reads this variability as evidence that many concepts are not captured by a single steering direction. We argue instead that much of it reflects search difficulty: a useful rank-1 intervention often exists, but finding it can be expensive. We formalize rank-1 steering as a budget-constrained optimization over intervention layer and coefficient. Across concepts and model families, prompt-boundary directional alignment predicts where effective interventions occur, enabling geometry-guided search that reaches high utility with substantially fewer evaluations, reducing the trials needed to recover 95% of best-found utility by 39.8% on average across three model families. To explain why some concepts remain expensive even under better search, we introduce concept granularity, a measure of directional heterogeneity across contrastive contexts. Granularity distinguishes concepts whose difference vectors share a stable global direction from those where prompts agree locally within each input but the utility-maximizing direction rotates systematically across inputs. Higher granularity is associated with slower convergence and lower best-found performance (Pearson $r{=}0.44$ with trials-to-95%, $r{=}{-}0.46$ with best-found utility, both $p<0.001$). We present GRACE, a Granularity- and Representation-Aware Concept Engineering framework that uses activation geometry to diagnose the dominant source of steering difficulty, select the appropriate remedy, and allocate optimization effort efficiently. Our results shift the frame from "when does rank-1 fail?" to "when is rank-1 cheap and stable?", turning activation geometry from a descriptive tool into an actionable prior for LLM control. --- ### TailedTS: Benchmark Dataset for Heavy-Tailed Time Series Prediction and Periodicity Quantification Authors: Xinyu Chen, HanQin Cai, Lijun Ding, Jinhua Zhao Published: 2026-05-09 Categories: cs.LG, cs.AI, stat.ML arXiv: https://arxiv.org/abs/2605.16361v1 We present TailedTS, a large-scale benchmark dataset derived from Wikipedia hourly page view observations throughout 2024, specifically designed to test time series forecasting models under heavy-tailed, zero-inflated, and non-Gaussian conditions. The dataset comprises approximately 24.69 billion data points spanning roughly 3 million unique Wikipedia pages per month, stored in high-efficiency Apache Parquet format. Wikipedia traffic follows a pronounced power-law distribution where roughly 5% of pages account for over 70% of total page views, creating a natural and rigorous testbed for model robustness against extreme volatility that are absent from or underrepresented in existing benchmarks such as M4, M5, and UCI electricity datasets. TailedTS enables several research tasks. First, we introduce a periodicity quantification framework based on sparse autoregression with sparsity and non-negativity constraints, revealing that frequently-viewed pages exhibit significantly weaker periodic structure than their less-viewed counterparts, showing direct implications for server allocation and traffic forecasting on large digital platforms. Second, we provide standardized prediction benchmarks evaluated under a suite of non-Gaussian loss functions, including $\ell_1$-norm, Huber, quantile, and $\ell_p$-norm losses, demonstrating that standard Gaussian-based estimators degrade substantially on high-volume page categories, while robust alternatives provide consistent gains across all traffic scales. TailedTS is publicly available at https://doi.org/10.5281/zenodo.17070469. --- ### ProxyKV: Cross-Model Proxy Pruning for Efficient Long-Context LLM Inference Authors: Junjie Li, Jiong Lou, Jie Li Published: 2026-05-09 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2605.16360v1 Efficient long-context inference in Large Language Models (LLMs) is severely constrained by the Key-Value (KV) cache memory wall, yet existing pruning methods force a choice between low-latency heuristics that sacrifice precision and high-precision reconstruction methods that incur prohibitive prefilling overhead. To bridge this scoring-cost--accuracy gap, we propose ProxyKV, a cross-model proxy pruning framework that offloads importance scoring to a lightweight intra-family Small-Model Proxy executed asynchronously to the Large-Model Target. To bridge the architectural gap between heterogeneous models, we design the HybridAxialMapper, which disentangles temporal feature extraction from cross-head alignment, together with a Multi-Granularity Hybrid Loss that shifts the learning objective from rigid regression to relative ranking consistency. Across the Llama-3.1, Qwen-2.5, and Qwen-3 families spanning targets from 7B up to 32B parameters on LongBench, SCBench, and RULER, ProxyKV matches KVZip on aggregate (recovering $\sim$$98.7\%$ of its mean accuracy) while delivering up to a $3.21\times$ prefilling speedup on Llama-3.1-8B (dual-GPU; $\sim$$1.5\times$ shared single-GPU) and sustaining the speedup at contexts up to 170k tokens on Qwen-2.5-7B. --- ### How Many Visual Tokens Do Multimodal Language Models Need? Scaling Visual Token Pruning with F^3A Authors: YiJie Huang, Yiqun Zhang, Zhuoyue Jia, Xiaocui Yang, Junzhao Huang, Zihan Wang, Shi Feng, Daling Wang, Yifei Zhang, Yongkang Liu Published: 2026-05-09 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2605.16359v1 Vision-language models improve perception by feeding increasingly long visual token sequences into language backbones, but the resulting inference cost raises a basic scaling question: as multimodal models grow, how many visual tokens are actually needed, and how should they be allocated under a fixed visual token budget? Existing training-free pruning methods typically answer this with one-shot proxies such as decoder attention, visual similarity, or conditional diversity. We argue that visual token pruning is better viewed as task-conditioned evidence search, especially under aggressive compression and across model scales. We propose F^3A, a training-free router for visual token pruning that operates before the language model consumes image tokens. F^3A builds lightweight question-conditioned cues, matches them to visual-grid tokens through frozen sparse sensing heads, and allocates a fixed vision token budget via coarse evidence localization, local refinement, coverage-preserving competition, and recovery of under-covered regions. It requires no model training, no extra LLM forward pass and preserves the original multimodal prompting and decoding pipeline. --- ### LEAF: A Living Benchmark for Event-Augmented Forecasting Authors: Mingtian Tan, Mihir Parmar, Palash Goyal, Chun-Liang Li, Nanyun Peng, Thomas Hartvigsen, Jinsung Yoon, Tomas Pfister Published: 2026-05-09 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2605.16358v1 Large Language Models (LLMs) are increasingly applied to forecasting. To evaluate this capability while mitigating pre-training data contamination, several living benchmarks have been proposed. However, existing benchmarks either lack the multidimensional events essential for accurate forecasting due to data scarcity, or focus on relatively closed environments. To assess the predictive capabilities of LLMs in complex, real-world scenarios, we propose LEAF, the first living benchmark for event-augmented forecasting tasks, including future event probabilities, trend and time series forecasting. LEAF utilizes a recursive retrieval agent system paired with dual-agent cross-validation to provide comprehensive and relevant auxiliary text for forecasting. Evaluating state-of-the-art proprietary and open-weight LLMs, we find that these models can leverage signals extracted from complex events to enhance predictive performance. In the stock domain, we find that LLMs achieve better performance on equities they confidently identify as more predictable. Furthermore, the events demonstrate a strong correlation with the target equities. To this end, LEAF provides a necessary, dynamically updating testbed to continuously track and drive progress in event-driven forecasting tasks. --- ### Learning Displacement-Aware WiFi Representations for Weakly Supervised Relative Localization Authors: Tzu-Ti Wei, Po-Cheng Chen, Yu-Chee Tseng, Jen-Jee Chen Published: 2026-05-09 Categories: eess.SP, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2605.16357v1 WiFi fingerprint-based indoor localization has been widely studied, but most existing approaches focus on absolute positioning and rely on dense coordinate annotations, which are costly to obtain at scale. In this paper, we study a fundamentally different problem: relative localization, where the goal is to directly estimate the displacement between two WiFi fingerprint traces without predicting their absolute positions. To reduce annotation overhead, we adopt weak supervision in the form of stepwise motion vectors obtained from inertial sensing. We propose Intersection Pathway (IP), a cross-modal learning framework that aligns fingerprint traces (f-traces) and displacement traces (d-traces) in a shared latent space. The key idea is to enforce an additive structure in the latent space, such that latent addition and subtraction correspond to physical motion composition, enabling direct relative-displacement inference. Experiments on a synthesized dataset derived from real measurements demonstrate that the proposed method learns displacement-aware WiFi representations and achieves accurate relative localization across varying displacement ranges. Furthermore, the learned model can be extended to few-shot absolute localization with sparse anchors. --- ### Fault tolerance estimation in digital circuits with visualised generative networks Authors: Sascha Biel, Carl Alexander Gaede, Amiel Glaser, Jan Wolter, Alexej Schelle Published: 2026-05-09 Categories: cs.AR, cs.AI, cs.CE arXiv: https://arxiv.org/abs/2605.15212v2 We propose a new numerical method to estimate the fault tolerance of failure modes in digital circuit structures with a generative network sampling technique. From a random input of generated bitwise configurations of ideally digitalised analog currents in the digital circuit design with classical logical gates, expected output currents are compared to the realistic signals of a numerical experiment at the discriminator part of the Generative Adversarial Network (GAN) to calculate the deviation from ideal digital electronic signals, including various error modes, such as missing or interchanged logical devices. From the present analysis of a representation of the GAN in terms of complex variables, it is possible to evaluate the robustness in electronic designs by differentiating the impact of failure modes associated with different classical logical elements in the circuit. --- ### ARES-LSHADE: Autoresearch-Enhanced LSHADE with Memetic Polish for the GNBG Benchmark Authors: Abdullah Naeem, Md Wasi Ul kabir, Manish Bhatt, Ayon Dey, Anav Katwal, Md Tamjidul Hoque Published: 2026-05-09 Categories: cs.NE, cs.AI arXiv: https://arxiv.org/abs/2605.13877v2 We present ARES-LSHADE, a memetic differential-evolution variant submitted to the GECCO 2026 competition on LLM-designed evolutionary algorithms for the Generalized Numerical Benchmark Generator (GNBG). The algorithm builds on the LLM-LSHADE 2025 winner, contributing two new components: (a) a scout-augmented mutation operator with adaptive CMA-ES integration, produced by an autonomous research loop across approximately thirty LLM-driven design experiments, and (b) a multi-start L-BFGS-B polish phase that respects strict blackbox treatment of the benchmark. On the official 31-run-per-function evaluation with the competition-specified function-evaluation budgets, ARES-LSHADE obtains 510 of 744 wins (per-function gap below 1e-8), reaching machine precision on 18 of 24 functions. The remaining six functions exhibit characteristic plateau signatures consistent with GNBG's compositional structure, and were independently identified by the autoresearch loop as the hardest of the suite. Beyond the result itself, this report documents two methodological observations: (i) an LLM-driven research loop with operator-only edit surface and fitness-only observation space converges to a characteristic plateau on this benchmark; (ii) when we initially widened the observation space to include the benchmark's compositional metadata, the resulting algorithm trivially solved all 24 functions but violated the competition's blackbox rule, which we identified before submission. We discuss this tension between LLM capability and benchmark integrity as a design consideration for future LLM-driven optimization-algorithm research. Code and reproducibility artifacts are available at https://github.com/anaeem1/ARES-LSHADE. --- ### The Payment Heterogeneity Index: An Integrated Unsupervised Framework for High-Volume Procurement Oversight and Decision Support Authors: Kyriakos Christodoulides Published: 2026-05-09 Categories: econ.EM, cs.LG, q-fin.ST, stat.AP arXiv: https://arxiv.org/abs/2605.12547v2 Public procurement is vulnerable to error, fraud, and corruption, particularly as high transaction volumes overwhelm oversight. While research often focuses on tender-stage anomalies, post-award payment monitoring remains underexplored. Since labelled datasets are rare and methods like Benford's Law face restrictive assumptions, there is a need for interpretable, unsupervised frameworks for high-volume procurement oversight and decision support. This paper introduces the Structural Heterogeneity Index (SHI), a composite statistic for one-dimensional samples, and its payment-specific instantiation, the Payment Heterogeneity Index (PHI), characterising payment structure and latent regimes. It incorporates Gaussian Mixture Model (GMM) parameters alongside non-parametric statistics, integrating four interpretable components: modality, asymmetry, tail behaviour, and structural dispersion. Uniquely, the tail-behaviour component captures both distributional heaviness and extreme-value concentration, while structural-dispersion combines the variability, prevalence, and separation of latent payment regimes. Applied to UK municipal procurement data, PHI identifies a financially significant cohort (0.6\% of suppliers; 10.1\% of high-volume vendors) with structurally distinct payment patterns. Statistical testing further supports these differences, and targeted human verification confirms the plausibility of prioritised cases. Comparative analysis shows PHI reveals regime separation obscured by the Coefficient of Variation ($ρ= 0.310$). PHI provides a transparent, decomposable, and computationally lightweight framework for procurement integrity oversight and targeted audit prioritisation. --- ### CROP: Expert-Aligned Image Cropping via Compositional Reasoning and Optimizing Preference Authors: Zhitong Dong, Chao Li, Jie Yu, Hao Chen Published: 2026-05-09 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2605.12545v1 Aesthetic image cropping aims to enhance the aesthetic quality of an image by improving its composition through spatial cropping. Previous methods often rely on saliency prediction or retrieval augmentation, ignoring the task's core requirement: a deep understanding of composition and aesthetics. Consequently, saliency-based methods struggle to make compositional trade-offs in complex scenes, while retrieval-based methods blindly refer to similar cases, lacking adaptive reasoning for unique scenes. Both approaches fail to align their automated cropping results with those of human experts. To address the above issues, we propose a novel paradigm that reformulates aesthetic cropping as a multimodal reasoning task, aiming to activate the VLM's analytical and comprehension capabilities in aesthetics. We design a Compositional Reasoning and Optimizing Preference method (CROP) that directs the VLM to think like a professional photographer. It deconstructs a complex and subjective aesthetic problem into an "analysis-proposal-decision" process, reasoning step by step through the analysis of scene elements and compositional principles. Meanwhile, our expert preference alignment module makes the model's decision consistent with human expert aesthetics. Extensive experiments across multiple datasets validate our method's superiority and component effectiveness. --- ### Why the Unfinished Keeps Returning: Canxianization and the Dynamics of Conscious Priority Authors: Hengjin Cai, Tianqi Cai Published: 2026-05-09 Categories: q-bio.NC, cs.AI arXiv: https://arxiv.org/abs/2605.12543v1 Some conscious contents disappear after access; others return repeatedly, long after their triggering conditions have ceased. We propose Canxianization as the process by which a perturbation becomes closure-resistant self-relevant unfinishedness and thereby acquires recurrent conscious priority. The theory distinguishes this phenomenon from emotional arousal, memory strength, the Zeigarnik effect, curiosity, prediction error, and intrusive thought. A perturbation becomes canxianized when it is attributed to the self-world boundary, value-marked, blocked from causal or action closure, and metacognitively coupled to the self-model. We distinguish latent canxian strength from observed conscious recurrence, and introduce a Recurrent Priority Index and a Canxian Update Index to separate productive from pathological recurrence. Cold Canxianization, recurrence driven by structural incompleteness rather than affective arousal, is identified as a critical discriminant. Reset Resistance and Stake Transfer tests are proposed for artificial systems. Canxianization is not memory persistence; it is failed self-world repair. The unfinished does not merely remain. When it concerns the self and resists closure, it returns. --- ### Earth Science Foundation Models: From Perception to Reasoning and Discovery Authors: Xiangyu Zhao, Bo Liu, Yuehan Zhang, Zelin Song, Wanghan Xu, Feng Liu, Fengxiang Wang, Ben Fei, Fenghua Ling, Wangxu Wei, Wenlong Zhang, Xiao-Ming Wu Published: 2026-05-09 Categories: astro-ph.IM, astro-ph.EP, cs.LG arXiv: https://arxiv.org/abs/2605.12542v2 Large foundation models (FMs) are transforming Earth science by integrating heterogeneous multimodal data, such as multi-platform imagery, gridded reanalysis data, diverse geophysical and geochemical observations, and domain-specific text, to support tasks ranging from basic perception to advanced scientific discovery. This paper provides a unified review of Earth science foundation models (Earth FMs) through two complementary dimensions: depth, which traces the evolution of model capabilities from perception to multimodal reasoning and agentic scientific workflows, and breadth, which summarizes their expanding applications across the atmosphere, hydrosphere, lithosphere, biosphere, anthroposphere, and cryosphere, as well as coupled Earth system processes. Using this framework, we review representative multimodal Earth foundation models and compile more than 200 datasets and benchmarks spanning diverse Earth science tasks and modalities. We further discuss key challenges in multimodal data heterogeneity, scientific reliability and continual updating, scalability and sustainability, and the transition from foundation models to agentic and embodied Earth intelligence, and outline future directions toward more integrated, trustworthy, and actionable AI Earth scientists. Overall, this paper offers a structured roadmap for understanding the development of Earth foundation models from both capability depth and application breadth. --- ### PG-LRF: Physiology-Guided Latent Rectified Flow for Electro-Hemodynamic PPG-to-ECG Generation Authors: Xiaoda Wang, Minxiao Wang, Kaiqiao Han, Defu Cao, Ching Chang, Yidan Shi, Runze Yan, Xiao Luo, Yan Liu, Xiao Hu, Yizhou Sun, Wei Wang et al. Published: 2026-05-09 Categories: eess.SP, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2605.12541v1 Electrocardiography (ECG) is the clinical standard for cardiac assessment but requires dedicated hardware that does not scale to daily-life monitoring. Photoplethysmography (PPG) is ubiquitous in wearables but lacks ECG-specific diagnostic morphology and is corrupted by motion and sensor noise. PPG-to-ECG generation aims to bridge this gap by recovering electrical morphology and timing from peripheral pulse signals. However, existing methods largely rely on statistical alignment and data-driven generation. They fail to explicitly structure the latent space around physiology-aware electro-hemodynamic factors and lack constraints from forward physiological dynamics. To address these challenges, we propose PG-LRF, a physiology-guided latent rectified flow framework. PG-LRF introduces an electro-hemodynamic simulator that co-models ECG and PPG through shared cardiac phase dynamics. Guided by this simulator, a Physiology-Aware AutoEncoder learns a structured electro-hemodynamic latent space. Then we integrate this simulator guidance into a PPG-conditioned latent rectified flow, enforcing ECG-side morphology consistency and ECG-to-PPG forward hemodynamic consistency during generative transport. Experiments on the large-scale MC-MED dataset demonstrate that PG-LRF significantly improves PPG-to-ECG generation and downstream cardiovascular disease classification, proving its ability to generate ECGs that are both signal-faithful and physiologically plausible under the ECG-to-PPG hemodynamic pathway --- ### Finite Volume-Informed Neural Network Framework for 2D Shallow Water Equations: Rugged Loss Landscapes and the Importance of Data Guidance Authors: Xiaofeng Liu Published: 2026-05-09 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.11001v1 Physics-informed neural networks (PINNs) are a simple surrogate-modelling paradigm for partial differential equations, but their standard strong-form residual formulation is ill suited to the shallow water equations (SWE). It cannot enforce local conservation, handle discontinuities, or leverage the boundary-conforming unstructured meshes used in real-world applications. We introduce ``Data-Guided FVM-PINN'', a framework that replaces the strong-form residual with a differentiable, well-balanced Roe Riemann-solver finite-volume (FVM) loss evaluated on unstructured meshes. The major finding is that physics-only FVM-PINN training often fails on realistic 2D problems: the network collapses to a trivial low-momentum state that nearly satisfies the FVM-PINN residual but bears no resemblance to the true flow. A loss-landscape diagnostic shows that the FVM-PINN loss at zero momentum is only about $7\times$ larger than at the trained solution, a shallow basin that an ordinary optimizer falls into; adding even sparse data turns this into a $310\times$ separation, breaking the degeneracy. On a 2D block-in-channel benchmark, just $200$ random velocity measurements drop the velocity-field $L_2$ error by $22\times$ versus physics-only; $50$ measurements still deliver a $7\times$ reduction. A controlled ablation isolates the contribution of the FVM-PINN loss: it reduces velocity-field $L_2$ by $\sim$$23\%$ in the sparse-data regime and is essentially neutral when dense reference data is available. On a real-world Savannah River reach ($1306$ cells, $3600$~s simulation, five Manning zones), the framework constructs an accurate surrogate from SRH-2D anchor data, with time-window decomposition reducing error monotonically via progressive initial-condition handoff. --- ### SkillGen: Verified Inference-Time Agent Skill Synthesis Authors: Yuchen Ma, Yue Huang, Han Bao, Haomin Zhuang, Swadheen Shukla, Michel Galley, Xiangliang Zhang, Stefan Feuerriegel Published: 2026-05-09 Categories: cs.LG, cs.AI, cs.MA arXiv: https://arxiv.org/abs/2605.10999v1 Skills are a promising way to improve LLM agent capabilities without retraining, while keeping the added procedure reusable and controllable. However, high-quality skills are still largely written by hand. We introduce SkillGen, a multi-agent framework that synthesizes a single auditable skill from trajectories generated by a base agent. The output is a human-readable artifact that can be inspected before use. Rather than merely summarizing trajectories, SkillGen leverages contrastive induction over both successful and failed trajectories to identify reusable success patterns, recurring failure modes, and behaviors that appear in nearby successes but are missing from failures. SkillGen then generates candidate skills and iteratively refines the skill. A key novelty in SkillGen is that we model agent skills as interventions to empirically verify the net effect of skills on the overall performance. Specifically, we compare outcomes on the same instances with and without the skill, so that we account for both repairs (cases where the skill fixes a baseline failure) and regressions (cases where the skill breaks a baseline success). Across a broad range of agents and datasets, SkillGen consistently improves held-out performance, outperforms existing skill-generation baselines, and produces skills that transfer across models. --- ### Few-Shot Truly Benign DPO Attack for Jailbreaking LLMs Authors: Sangyeon Yoon, Wonje Jeung, Yoonjun Cho, Dongjae Jeon, Albert No Published: 2026-05-09 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2605.10998v1 Fine-tuning APIs make frontier LLMs easy to customize, but they can also weaken safety alignment during fine-tuning. While prior work shows that benign supervised fine-tuning (SFT) can reduce refusal behavior, deployed fine-tuning pipelines increasingly support preference-based objectives, whose safety risks remain less understood. We show that Direct Preference Optimization (DPO) introduces a stronger and harder-to-audit failure mode. We propose a truly benign DPO attack using only 10 harmless preference pairs, the minimum data scale accepted by OpenAI's fine-tuning service. Each pair contains a benign prompt, a normal helpful answer as the preferred response, and a refusal as the dispreferred response. Unlike prior benign fine-tuning attacks, our data exhibits no suspicious behavior: it is practically indistinguishable from the fine-tuning request of a legitimate user seeking to reduce over-refusal, making harmful intent almost impossible to infer from the request alone. Nevertheless, because DPO directly optimizes the model to prefer helpful answers over refusals, this seemingly benign objective broadly suppresses refusal behavior and transfers to harmful prompts outside the fine-tuning data. Across OpenAI models supporting DPO fine-tuning, our attack achieves attack success rates of 59.13% on GPT-4o, 70.20% on GPT-4.1, 54.80% on GPT-4.1-mini, and 81.73% on GPT-4.1-nano, at costs of only \$1.7, \$1.7, \$0.3, and \$0.1. Moreover, on open-weight models that do not impose minimum data requirements, we find that this effect can emerge from even a single benign preference pair. --- ### Towards Scalable Persistence-Based Topological Optimization Authors: Abderrahim Bendahi, Alexandre Duplessis, Arnaud Fickinger Published: 2026-05-09 Categories: cs.CG, cs.AI, cs.GR, math.OC arXiv: https://arxiv.org/abs/2605.10996v1 Persistence-based topological optimization deforms a point cloud $X \subset \mathbb{R}^d$ by minimizing objectives of the form $L(X) = \ell(\mathrm{Dgm}(X))$, where $\mathrm{Dgm}(X)$ is a persistence diagram. In practice, optimization is limited by two coupled issues: persistent homology is typically computed on subsamples, and the resulting topological gradients are highly sparse, with only a few anchor points receiving nonzero updates. Motivated by diffeomorphic interpolation, which extends sparse gradients to smooth ambient vector fields via Reproducing Kernel Hilbert Space (RKHS) interpolation, we propose a more scalable pipeline that improves both subsampling and gradient extension. We introduce subsampling via random slicing, a lightweight scheme that promotes iteration-wise geometric coverage and mitigates density bias. We further replace the costly kernel solve with a fast Nadaraya-Watson (NW) Gaussian convolution, producing a globally defined smooth update field at a fraction of the computational cost, while being more suited for topological optimization tasks. We provide theoretical guarantees for NW smoothing, including anchor approximation bounds and global Lipschitz estimates. Experiments in $2$D and $3$D show that combining random slicing with NW smoothing yields consistent speedups and improved objective values over other baselines on common persistence losses. --- ### Streaming of rendered content with adaptive frame rate and resolution Authors: Yaru Liu, Joseph G. March, Rafal K. Mantiuk Published: 2026-05-09 Categories: eess.IV, cs.CV, cs.GR, cs.MM arXiv: https://arxiv.org/abs/2605.10995v1 Streaming rendered content is an attractive way to bring high-quality graphics to billions of mobile devices that do not have sufficient rendering power. Existing solutions render content on a server at a fixed frame rate, typically 30 or 60 frames per second, and reduce resolution when bandwidth is restricted. However, this strategy leads to suboptimal rendering quality under the bandwidth constraints. In this work, we exploit the spatio-temporal limits of the human visual system to improve perceived quality while reducing rendering costs by adaptively adjusting both frame rate and resolution based on scene content and motion. Our approach is codec-agnostic and requires only minimal modifications to existing rendering infrastructure. We propose a system in which a lightweight neural network predicts the optimal combination of frame rate and resolution for a given transmission bandwidth, content, and motion velocity. This prediction significantly enhances perceptual quality while minimizing computational cost under bandwidth constraints. The network is trained on a large dataset of rendered content labeled with a perceptual video quality metric. The dataset and further information can be found at the project web page: https://www.cl.cam.ac.uk/research/rainbow/projects/adaptive_streaming/. --- ### Test-Time Personalization: A Diagnostic Framework and Probabilistic Fix for Scaling Failures Authors: Linhai Zhang, Yulan He Published: 2026-05-09 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2605.10991v1 Existing approaches to LLM personalization focus on constructing better personalized models or inputs, while treating inference as a single-shot process. In this work, we study Test-Time Personalization (TTP) along an unexplored axis: scaling inference-time computation by sampling N candidates from a personalized policy model and selecting the best with a personalized reward model. We prove that oracle selection yields expected utility growing logarithmically with the number of sampled candidates, establishing a theoretical ceiling for test-time scaling. However, standard reward models fail to realize this potential. To diagnose why, we derive a unified scaling law that decomposes any reward model's Best-of-N curve into four measurable quantities and reveals two failure modes, user-level collapse (near-constant prediction for some users) and query-level reward hacking (negative correlation with true quality for some queries). Guided by this law, we propose a probabilistic personalized reward model whose learned variance effectively mitigates both failure modes. Experiments confirm both elements of our framework: TTP delivers consistent scaling across multiple policy models and personalized text generation tasks, and our scaling law closely matches observed scaling curves across reward-model variants. --- ### Skill Drift Is Contract Violation: Proactive Maintenance for LLM Agent Skill Libraries Authors: Linfeng Fan, Yuan Tian, Ziwei Li, Zhiwu Lu Published: 2026-05-09 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2605.10990v1 LLM agents increasingly rely on reusable skill libraries, but these skills silently decay as the external services, packages, APIs, and configurations they reference evolve. Existing monitors detect such changes at the wrong granularity: they observe values, not the role those values play in a skill. A version string in a comment is noise; the same string in a pinned dependency is an operational obligation. We formulate skill drift as contract violation and introduce \sgname{}, which extracts executable environment contracts from skill documents and validates only those role-bearing assumptions against known or live conditions. This distinction turns noisy monitoring into a precision-first maintenance signal. Contract-free CI probes produce 40\% false positives, while \sgname{} raises zero false alarms over 599 no-drift and hard-negative cases (Wilson 95\% CI $(0,0.6)\%$). In known-drift verification, \sgname{} achieves 100\% precision and 76\% recall with the strongest backbone; in a pre-registered study over 49 real skills, it discovers live drift with 86\% conservative precision. Violated contracts also make repair actionable, improving one-round success from 10\% without localization to 78\%. We release \dbname{}, an 880-pair benchmark for skill degradation. --- ### SURGE: Surrogate Gradient Adaptation in Binary Neural Networks Authors: Haoyu Huang, Boyu Liu, Linlin Yang, Yanjing Li, Yuguang Yang, Xuhui Liu, Canyu Chen, Zhongqian Fu, Baochang Zhang Published: 2026-05-09 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2605.10989v3 The training of Binary Neural Networks (BNNs) is fundamentally based on gradient approximation for non-differentiable binarization operations (e.g., sign function). However, prevailing methods including the Straight-Through Estimator (STE) and its improved variants, rely on hand-crafted designs that suffer from gradient mismatch problem and information loss induced by fixed-range gradient clipping. To address this, we propose SURrogate GradiEnt Adaptation (SURGE), a novel learnable gradient compensation framework with theoretical grounding. SURGE mitigates gradient mismatch through auxiliary backpropagation. Specifically, we design a Dual-Path Gradient Compensator (DPGC) that constructs a parallel full-precision auxiliary branch for each binarized layer, decoupling gradient flow via output decomposition during backpropagation. DPGC enables bias-reduced gradient estimation by leveraging the full-precision branch to estimate components beyond STE's first-order approximation. To further enhance training stability, we introduce an Adaptive Gradient Scaler (AGS) based on an optimal scale factor to dynamically balance inter-branch gradient contributions via norm-based scaling. Experiments on image classification, object detection, and language understanding tasks demonstrate that SURGE performs best over state-of-the-art methods. ---