# Research Papers — 2026-05 · bundle page 104 of 326 > Full-text markdown of papers #5151–5200 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/104 [← Previous bundle](https://aipod.dev/papers/archive/2026-05/page/103.md) [Next bundle →](https://aipod.dev/papers/archive/2026-05/page/105.md) ### Exploiting Longitudinal Context in Clinician-Verified Interactive Lesion Tracking Authors: Yannick Kirchhoff, Maximilian Rokuss, Daniel Philipp Mertens, David Füller, Benjamin Hamm, Andreas Schreyer, Oliver Ritter, Klaus Maier-Hein Published: 2026-05-22 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2605.23118v1 Tracking tumor lesions across serial CT scans is essential for oncological response assessment. Existing automated methods face a fundamental trade-off: end-to-end trackers achieve high automation but offer no opportunity to correct silent tracking failures, while decoupled registration-segmentation pipelines permit user verification yet discard the lesion's prior appearance, limiting accuracy in ambiguous cases. In this work, we propose a Verified Tracking paradigm: a clinician verifies a registration-proposed prompt, which the model leverages alongside the baseline lesion appearance to resolve segmentation ambiguities. We present a unified framework combining early spatial prompt fusion with latent temporal difference weighting for longitudinally-informed segmentation. To address data scarcity, we leverage large-scale synthetic pretraining, proving essential for exploiting longitudinal context, improving performance by up to 4.5 Dice points over training from scratch. Our approach secured first place in the MICCAI autoPET IV challenge. We further curate and release PanTrack, a new longitudinal pancreatic cancer benchmark, to assess out-of-distribution generalization. Experiments show that our model outperforms prior work in both fully automatic and the proposed verified tracking setting offering a clinically safe middle ground between automation and control. Code, model and dataset will be released at https://github.com/MIC-DKFZ/LongiSeg --- ### CoReVAD: A Contextual Reasoning Framework for Training-Free Video Anomaly Detection Authors: Hyeongmuk Lim, Youngbum Hur Published: 2026-05-22 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2605.23116v1 Existing Video Anomaly Detection (VAD) methods typically rely on task-specific training, leading to strong domain dependency and high training costs. Moreover, most existing methods output only scalar anomaly scores, providing limited insight into why specific events are considered abnormal. Recent advances in Vision-Language Models (VLMs) have enabled both anomaly detection and human-interpretable reasoning. However, many VLM-based approaches still require additional training steps (e.g., instruction tuning or verbalized learning) or external Large Language Models (LLMs), incurring further training costs and inference overhead. To address these challenges, we propose CoReVAD, a contextual reasoning framework for training-free video anomaly detection that operates with a single frozen VLM. CoReVAD directly generates anomaly scores and temporal descriptions from the VLM. To mitigate noise in generative outputs, we introduce a Local Response Cleaning (LRC) module based on local vision-text alignment. Furthermore, global temporal context and progression are incorporated through softmax-based refinement, Gaussian smoothing, and position weighting. Experiments on UCF-Crime and XD-Violence demonstrate that CoReVAD achieves competitive performance among training-free methods while providing reliable and interpretable explanations. Our official code is available at: https://github.com/Muk-00/CoReVAD --- ### Robust OT-Guided Generative Residual Domain Adaptation for Bike-Sharing Demand Prediction under Temporal Domain Shift Authors: Yiming Ma Published: 2026-05-22 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2605.23115v1 Bike-sharing models trained on historical station-hour data may degrade when deployed in later years because travel patterns change over time. This paper studies March Citi Bike demand prediction from 2021 to 2026 as a temporal domain adaptation problem and proposes Gen-ROTDA, a robust optimal transport-guided residual domain adaptation framework. The method fits a target-domain station-time anchor with a small labeled target subset, transfers residual rather than raw demand, applies a deterministic label-preserving residual feature generator, and trims high-cost transport matches before training the final residual predictor. Experiments compare Gen-ROTDA with anchor-only, source-only, target-only, fine-tuning, MMD adaptation, Sinkhorn OTDA, ROTDA, and Gen-OTDA. Gen-ROTDA achieves the lowest MAE on the main 2025 to 2026 task and is the best OT-family method on average across multi-year tasks, although fine-tuning and MMD adaptation remain strong overall baselines. Under abnormal target-unlabeled records, Gen-ROTDA is much more stable than non-robust OT variants, suggesting that robust transport is useful for noisy temporal transfer in bike-sharing demand prediction. --- ### Inconsistency-aware Multimodal Schrödinger Bridge for Deepfake Localization Authors: Jiayu Xiong, Jing Wang, Qi Zhang, Wanlong Wang, Jun Xue Published: 2026-05-22 Categories: cs.CV arXiv: https://arxiv.org/abs/2605.23113v1 Audio-visual deepfake localization demands interval-level outputs that serve as temporal evidence. Despite recent progress, symmetric fusion under single-sided or asynchronous forgeries propagates cross-modal noise, degrading high-precision localization. We present IaMSB, an inconsistency-aware multimodal Schrödinger Bridge (SB) that jointly estimates cross-modal consistency and performs interval-level localization. Unlike diffusion models, SB minimizes path-distribution discrepancy and yields consistency scores without explicit noise injection or denoising. With the Schrödinger Bridge (SB), IaMSB unifies consistency estimation, cross-modal information selection, and bridge-step scheduling in one framework. Specifically, a lightweight coarse bridge first proposes candidate intervals and estimates cross-modal consistency; these statistics select cross-modal witness signals and allocate bridge steps asymmetrically across modalities. A refinement bridge then performs step-tuned fusion and outputs refined, time-aligned intervals. IaMSB anticipates single-sided and asynchronous forgeries and, using bottlenecked cross-modal interaction with step allocation, suppresses noise transfer, avoids unnecessary iterations. Across benchmarks, IaMSB stabilizes strict-IoU boundary precision, raising AP@0.95 by 3%~10%, and yields improved high-precision localization, particularly for single-sided forgeries. --- ### Inductive Deductive Synthesis: Enabling AI to Generate Formally Verified Systems Authors: Shubham Agarwal, Alexander Krentsel, Shu Liu, Mert Cemri, Audrey Cheng, Rui Meng, Tomas Pfister, Chun-Liang Li, Sylvia Ratnasamy, Aditya Parameswaran, Matei Zaharia, Ion Stoica et al. Published: 2026-05-22 Categories: cs.AI, cs.DC, cs.LO, cs.PL arXiv: https://arxiv.org/abs/2605.23109v1 AI agents increasingly excel at generating, testing, and refining code. However, they fall short on tasks requiring formal guarantees of full coverage that testing alone cannot provide. Distributed systems are a prime example: properties such as consistency between reads and writes must hold under every possible interleaving of events. Mechanized formal verification can guarantee such correctness, but typically demands months to years of expert effort. As evidence, even SOTA coding agents (Codex with GPT-5.4 and Claude Code with Opus 4.6) succeed on only 2/7 distributed key-value-store specifications. In this paper, we present the first effective approach to addressing this gap, Inductive Deductive Synthesis (IDS), which jointly and incrementally synthesizes implementation and proof, and learns from failed attempts to systematically try promising strategies. Built as an agentic LLM system, IDS achieves 7/7 in about 6.8 hours and $106 per spec on average, roughly 200x faster than expert effort and 17% cheaper than SOTA agents. IDS further incorporates performance feedback into the same loop, yielding implementations up to 3x faster than published verified systems. --- ### Standalone LLM and a Pre-specified Agentic Pipeline for Explaining ICU Mortality Predictions: a Feasibility Study on the eICU Demo Dataset Authors: Di Zhu, Chen Xie, Haoyun Zhang, Zihan Wei, Ziwei Wang, Jiazhao Shi, Ziyu Wang, Qiyang Xie Published: 2026-05-21 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.26109v1 Machine-learning models can predict ICU mortality accurately, but feature-attribution methods alone rarely provide the clinical narrative needed for bedside use. Large language models (LLMs) may bridge this gap, and multi-step agentic pipelines are a plausible extension because they separate data interpretation, guideline checking, and final explanation. This revised feasibility study preserves the original standalone-versus-agentic comparison while making the main clinical findings more explicit. Using the retained local eICU Demo artifact set (2,353 ICU stays; 8.1\% mortality), XGBoost achieved an AUROC of 0.855 (95\% CI 0.796--0.906) and an AUPRC of 0.332 (95\% CI 0.217--0.494). On a stratified 38-case explanation subset, the standalone LLM produced 1 explanation with explicit outcome leakage, whereas the four-step agentic pipeline produced none. Among the 14 cases that overlapped with the SHAP review subset, the standalone LLM showed higher SHAP alignment (mean Jaccard 0.171 versus 0.077) and higher direction consistency (92.9\% versus 78.6\%), while the agentic pipeline showed higher guideline grounding (0.762 versus 0.143), higher value specificity (0.236 versus 0.143), and slightly higher plausibility (0.700 versus 0.671). Clinically, the results suggest that agentic decomposition may improve safety-relevant grounding and patient-specific detail, but it should be paired with attribution-based checks before use in high-stakes risk explanation. --- ### KVBoost: Chunk-Level Key-Value Cache Reuse with Deviation-Guided Recomputation for Efficient Large Language Model Inference Authors: Srihari Unnikrishnan Published: 2026-05-21 Categories: cs.AI, cs.DC arXiv: https://arxiv.org/abs/2608.21362v1 Transformer-based large language models (LLMs) incur high prefill latency because key-value (KV) tensors must be recomputed for each request. Existing prefix-caching systems reduce this cost but require prompts to share a leading contiguous prefix, limiting effectiveness when shared content appears at arbitrary positions. We present KVBoost, a chunk-level KV cache reuse system for HuggingFace-compatible decoder models that enables reuse regardless of content position. KVBoost introduces a dual-hash keying scheme that separates positional identity (prefix hash) from content identity (content hash), supporting both exact and approximate cache matches. To address attention boundary errors from independently cached chunks, KVBoost employs two repair strategies: SelectiveRecompute, which re-encodes boundary regions, and CacheBlendRecompute, which identifies and recomputes high-deviation tokens after a probe pass. The system further incorporates asymmetric KV quantization (int8/int4), adaptive chunk boundary splitting, and importance-weighted eviction under a fixed memory budget. Evaluated on Qwen/Qwen2.5-3B over 1,000 bug-localization samples, KVBoost achieves a 4.49x reduction in time-to-first-token (142.4 ms vs.\ 639.1 ms) and outperforms prefix caching by 16%, with no loss in accuracy (99.2% vs.\ 99.1%). KVBoost provides a practical, memory-bounded inference acceleration layer compatible with RoPE-based models without architectural modification. --- ### When to Communicate: Belief Distributions and KL Divergence for Principled Gating in Multi-Agent RL Authors: Teoman Kaman Published: 2026-05-21 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2608.14559v1 Effective communication in multi-agent reinforcement learning requires agents to decide not only \textit{what} to communicate, but when? Existing approaches either communicate at every timestep or learn a binary gate through REINFORCE policy gradients \cite{singh2019}, a high-variance signal that produces unstable and uninterpretable gating behavior. I propose a principled alternative: agents communicate only when the KL divergence between their learned belief distributions exceeds a fixed threshold. Each agent maintains a belief distribution over a latent world state computed as a softmax over its LSTM hidden state, and communicates only when belief disagreement is large enough to justify information exchange. I evaluate this approach on the Predator-Prey benchmark from IC3Net \cite{singh2019} across two environment sizes with 5 seeds each, and on MPE simple\_spread \cite{lowe2017}, comparing against IC3Net, CommNet, and an independent controller. On PP 10$\times$10, IC3Net outperforms KL-belief at all thresholds. On the harder PP 20$\times$20, a threshold ablation over $\varepsilon \in \{0.1, 0.3, 0.5, 1.0\}$ reveals an inverted U-shape: $\varepsilon=0.5$ achieves 73.84 average steps and 42\% success rate versus IC3Net's 75.31 steps and 31\%, a gap of 1.47 steps and 11 percentage points with tighter seed variance. On MPE, the belief head improves mean reward by 12 points and reduces variance by 26$\times$ even when gating is inactive, suggesting two orthogonal contributions: principled gating when beliefs can converge, and improved latent representations that benefit coordination regardless. --- ### RIG-RoPE: Relation-Stratified Multimodal Attention with Instance-Local Rotary Geometry and Representation-Aware Traversal Coordinates Authors: Donggen Li Published: 2026-05-21 Categories: cs.CL, cs.CV arXiv: https://arxiv.org/abs/2608.05154v4 Multimodal rotary positional encodings apply temporal, height, and width phases to interleaved text, image, and video tokens. This creates two ambiguities: cross-instance spatial displacement depends on preprocessing chart choices unless registration is declared, and scalar advance across visual blocks is often inherited from coordinate extrema rather than defined at the representation level. We introduce RIG-RoPE, combining instance-local rotary geometry, relation-stratified attention, and representation-aware traversal coordinates. RIG-RoPE normalizes relation-homogeneous scores separately, allocates mass with a common H/W-neutral LogSumExp statistic, and uses traversal extent that is additive over ordered slices and sublinear over parallel spatial scale. Text advances by unit increments, image patches are simultaneous, and video accumulates over tokenizer temporal tokens. In a matched, inference-only Qwen2-VL-2B checkpoint experiment, native and RIG text-only paths were exactly equal. RIG was exactly invariant to a whole-chart single-image translation and to translating only the second instance of an unregistered image pair. Native attention remained sensitive to the latter, while an H/W-collapse control confirmed that RIG retained same-instance spatial effects; visual embeddings and all parameters were unchanged. Across three seeds of a frozen tiny task, RIG also had zero clean-to-Gauge logit change, whereas the raw-H/W baseline changed in every seed. Gauge-accuracy differences were +2/72, 0, and 0, failing the preregistered stability gate. These results support the specified activation and Gauge mechanisms, not stable task improvement, universality, or empirical superiority. --- ### RIG-RoPE: Relation- and Instance-Gated Rotary Positional Encoding with Duration-Aware Temporal Coordinates Authors: Donggen Li Published: 2026-05-21 Categories: cs.CL, cs.CV arXiv: https://arxiv.org/abs/2608.05154v1 Rotary positional encoding (RoPE) is a core component of modern language models and has been extended to multimodal LLMs through multidimensional variants such as multimodal RoPE (M-RoPE), which split positional channels into temporal, height, and width subspaces. This report identifies two limitations of static multidimensional position assignment in interleaved multimodal contexts. First, height/width rotations may be applied to token pairs whose spatial displacement is not a well-defined geometric object, producing cross-modal and inter-instance spatial interference. Second, temporal coordinates are often treated as equal-step counters, so a text token, an image block, and a video segment can advance the temporal phase by comparable amounts despite different information density. We propose RIG-RoPE, a relation- and instance-gated RoPE mechanism with duration-aware temporal coordinates. RIG-RoPE augments each token with a modality indicator, a visual instance identifier, and a scalar information-duration coordinate. It enables H/W rotations only for query-key pairs from the same visual instance; otherwise the unknown spatial displacement is marginalized rather than set to zero. Temporal rotations use interpolated cumulative block durations: text tokens consume unit duration, images use a dimension-aware logarithmic spatial scale, and videos further apply a logarithmic temporal extension over effective frames. We provide a gauge-invariance argument for avoiding ordinary cross-instance spatial rotation, an impossibility result for static IDs under shared H/W subspaces, and a duration-consistency argument against equal-step multimodal time. RIG-RoPE adds no learned parameters and can be implemented inside tiled attention kernels with constant additional metadata per token. This preliminary report establishes the formulation and validation path without claiming empirical superiority. --- ### OncoTriad-QA: A Patient-Level Radiology-Pathology-Genomics Benchmark for Pan-Cancer Reasoning Authors: Ahnaf Munir, Dannong Wang, Michael W. McDonald, Mubarak Shah, Pegah Khosravi, Yu Tian Published: 2026-05-21 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2608.02615v1 Cancer diagnosis and characterization require integrating complementary evidence from radiology, pathology, genomics, and clinical metadata. However, most medical large language model (LLM) and vision-language model (VLM) benchmarks focus on isolated modalities or narrow image-text tasks, leaving patient-level oncology assessment across multiple evidence streams largely untested. We introduce OncoTriad-QA, a patient-level radiology-pathology-genomics benchmark for pan-cancer question answering. OncoTriad-QA contains 86.1k semantic questions across 9,281 TCGA patient cases from 32 cancer cohorts, aligning CT/MRI radiology, whole-slide histopathology, somatic mutations, copy-number alterations, DNA methylation, bulk RNA-seq, and clinical metadata. Case-specific annotations are constructed through a source-grounded LLM-assisted pipeline using curated labels, diagnostic reports, molecular profiles, and modality-derived evidence as primary sources of truth, with automated consistency checks and clinician review. We also introduce OncoVLM, a reference multimodal model that maps modality-native radiology, pathology, DNA methylation, and RNA-seq evidence into an LLM interface through learned projectors. Experiments show that existing general-purpose and medical LLMs remain limited on comprehensive pan-cancer QA, especially when questions require integrating imaging findings, tumor morphology, and molecular evidence. After fine-tuning on OncoTriad-QA, OncoVLM exceeds MedGemma-4B by an average of 10.7 points when using MCQ accuracy and BERTScore-F1, with consistent gains across multiple-choice and open-ended questions under radiology-only, pathology-only, and all-available settings. These results demonstrate the benchmark's value for training and evaluating models for integrated cancer question answering. --- ### VLD-RAG: Agentic Vision-Language Retrieval-Augmented Generation for Long, Visually-Rich Multi-Page Documents Authors: Seonok Kim Published: 2026-05-21 Categories: cs.IR, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2607.24748v1 Visually-rich documents such as reports, slides, and manuals often distribute the evidence needed to answer a question across multiple pages, mixing text with layout cues, tables, charts, and figures. This work studies multimodal retrieval-augmented generation for question answering over such visually-rich long documents, where retrieval must select evidence pages that include both textual and visual signals. We present VLD-RAG, an agentic multimodal RAG framework for multi-page evidence retrieval and cross-page reasoning over long documents. VLD-RAG builds a page-preserving multimodal index that stores parsed text, page-level metadata, and dense visual representations, and uses a hybrid retrieval strategy that combines keyword-based sparse search with dense semantic queries to identify candidate sources and evidence pages. A verifier-guided agent workflow coordinates a Retrieval Agent, Answer Agent, and Validation Agent to broaden evidence coverage, detect missing citations, and refine retrieval requests when needed. We evaluate retrieval with Top-1 and Top-5 evidence-page accuracy and generation with generalized accuracy, and show that VLD-RAG improves both evidence-page retrieval and end-task question answering on visually-rich long-document benchmarks, including LongDocURL and MMLongBench-Doc, outperforming previous vision-based retrieval baselines. These findings highlight that coordinated agent verification and multimodal hybrid retrieval are crucial for reliable grounding when correct answers depend on evidence scattered across pages. --- ### DecodeShare: Tracing the Shared Subspace of LLM Decode-Time Decisions Authors: Zishan Shao, Lixun Zhang, Kangning Cui, Yixiao Wang, Ting Jiang, Hancheng Ye, Qinsi Wang, Zhixu Du, Yuzhe Fu, Fan Yang, Danyang Zhuo, Yiran Chen et al. Published: 2026-05-21 Categories: cs.AI arXiv: https://arxiv.org/abs/2607.20469v1 Large language models (LLMs) handle many tasks with one set of parameters, but under KV-cached inference it is unclear what task-general structure, if any, is used at decode time rather than during prefill. We propose DecodeShare, a protocol that identifies a low-dimensional subspace consistently shared across tasks in decode-time hidden states, and then tests its causal role by removing that subspace only during decoding. In our experiments, disturbing the discovered shared subspace degrades decision performance far more than disturbing either a prefill-derived or random subspace under the same intervention budget. We further show this decode-shared subspace has practical consequences for activation steering: common steering directions can overlap the task-general decode channel. Projecting out this shared subspace directly separates the functional roles of the two components, while evaluating steering vectors at decode-time yields more reliable signal for downstream deployment than prefill-based proxies. Despite its compactness, the shared subspace can serve as a high-leverage causal channel at decode time. Code is available at: https://github.com/Zishan-Shao/decodeshare.git. --- ### FormulaSPIN: Self-Play Fine-Tuning for Natural Language to Spreadsheet Formula Generation Authors: Cy Xie Published: 2026-05-21 Categories: cs.AI arXiv: https://arxiv.org/abs/2607.19354v1 Spreadsheet applications are used by hundreds of millions worldwide, yet writing formulas remains a significant barrier. Existing approaches rely on static supervised data, which quickly saturates on limited annotations. In this paper, we introduce FORMULASPIN, a self-play framework that breaks the ceiling of supervised fine-tuning by enabling iterative self-improvement without any additional data. Vanilla SPIN fails on this task: it uniformly penalizes every non-matching output, so execution-equivalent alternatives are punished as negatives in one example while serving as ground truth in another, producing contradictory gradients. Our framework resolves this by exploiting formula generation's unique advantage: binary executability provides implicit supervision that separates semantic errors from valid stylistic variants. We frame training as a two-player game in which the main player learns to prefer ground-truth formulas over those from its previous version, while execution feedback sorts outputs into distinct granularities-enabling an adaptive curriculum that shifts from semantic correctness to stylistic refinement. To further increase accuracy, we incorporate ExecVote, a semantic-level voting mechanism that naturally handles multiple valid formulations. Experiments on multiple benchmarks demonstrate that FORMULASPIN achieves state-of-the-art performance, with 74.9% exact match and 87.1% execution accuracy on NL2FORMULA, matching models trained with additional preference annotations while outperforming both traditional SFT and frontier proprietary models. These findings underscore self-play's potential to tackle scarce data tasks and open the door to extending it beyond executable domains. --- ### Structured Synthetic Reasoning Data for Arithmetic Fine-Tuning of Small Language Models Authors: Jake O'Grady, Effirul Ramlan Published: 2026-05-21 Categories: cs.AI arXiv: https://arxiv.org/abs/2607.18266v1 Small language models are attractive for local deployment, but they often struggle with multi-step arithmetic reasoning. We study whether structured synthetic reasoning data can improve this behaviour under consumer-hardware constraints. Starting from GSM8K, we generated a 21,250-example corpus of grade-school arithmetic word-problem variants using GPT-5-mini, combining natural-language solution traces, light Socratic-style cues, structural variation, and irrelevant distractor context. We then fine-tuned Qwen3-0.6B and Qwen3-1.7B with LoRA on consumer hardware (Apple M4, 16 GB RAM). Exact-match accuracy on GSM8K improved from 36.5% to 49.1% for Qwen3-0.6B and from 53.5% to 66.5% for Qwen3-1.7B. For Qwen3-1.7B, transfer to related arithmetic benchmarks was stronger, reaching 98.9% on MultiArith and 73.0% on SVAMP, compared with 54.4% and 45.3% for the base model. Qualitative analysis suggests that fine-tuned models produce shorter reasoning traces, make fewer arithmetic and distractor-use errors, and benefit more consistently from self-consistency sampling. These results show that low-cost synthetic data design can materially improve arithmetic adaptation in small language models. Because the intervention combines Socratic-style cues with other data-design choices, we interpret the gains as evidence for structured synthetic reasoning data rather than as a causal test of Socratic guidance alone. --- ### Dream machine -- the next creative economy Authors: Peter Woodbridge, John J. O'Hare Published: 2026-05-21 Categories: cs.CY, cs.AI arXiv: https://arxiv.org/abs/2606.26114v1 We examine the structural transformation of creative industries under generative artificial intelligence, drawing on 374 primary sources spanning policy documents, industry data, creator surveys, and platform analytics. Beginning with the December 2024 release of OpenAI's Sora video model as a watershed event, we trace the historical pattern of creative resistance to technological disruption, then develop an analytical framework -- the Human-AI Agency Continuum for mapping the spectrum of human and machine collaboration in creative work. We present evidence for the "slop ceiling," an audience-imposed quality threshold that constrains AI-generated content to approximately 1--3% of platform streams despite comprising 44% of uploads. Analysis of the UK Government's 2025 consultation on AI and copyright (over 11,500 responses, 88% opposing expanded AI training rights) reveals deep structural tensions between technology firms and creative workers. We investigate how major studios, from Disney's $1 billion OpenAI investment to Netflix's AI-native animation unit, are positioning for an AI-augmented production pipeline. The work covers coordination collapse in creative supply chains, the emergence of new professional roles such as prompt engineers and AI orchestrators, and proposes four principles for navigating the transition: transparency, consent, compensation, and human-centred design. Eight appendices provide quantitative analysis, a glossary, topical bibliography, and deep dives into shadow AI adoption, AI stigma, and algorithmic intent. --- ### From Lexicon to AI: A Structured-Data Pipeline for Specialized Conversational Systems in Low-Resource Languages Authors: Siddhant Hitesh Mantri, Dhara Gorasiya, Malhar Kulkarni, Pushpak Bhattacharya Published: 2026-05-21 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2606.26112v1 Low-resource languages face a critical challenge in AI development: creating specialized conversational systems without access to massive training corpora. We present a systematic methodology for transforming structured linguistic resources into specialized AI systems, demonstrating that expert-curated lexical databases can serve as effective foundations for conversational AI development. Our approach converts Hindi WordNet into 1.25 million diverse instruction-response pairs, fine-tunes a 12B-parameter language model using resource-efficient LoRA with 4-bit quantization. Evaluation through a Hindi language learning chatbot demonstrates that structured-knowledge-based systems achieve superior pedagogical effectiveness (91.0 vs. 79.4-83.6 for general-purpose models) while maintaining competitive semantic performance and exceptional consistency. The complete pipeline demonstrates a proof-of-concept methodology using Hindi for developing specialized AI systems for any languages with WordNet resources. This work addresses the critical gap in AI accessibility for low-resource languages, offering a practical alternative to corpus-intensive approaches and potentially enabling specialized AI development for the hundreds of languages with existing WordNet resources. --- ### Distributed Quantum Learning over Near-term Devices: Convergence Analysis and Security Design Authors: Atit Pokharel, Shaba Shaon, Thomas Morris, Dinh C. Nguyen Published: 2026-05-21 Categories: quant-ph, cs.AI, cs.CE arXiv: https://arxiv.org/abs/2606.20606v1 Distributed quantum learning (DQL) has emerged as a promising paradigm to scale quantum-enhanced machine learning by interconnecting multiple quantum devices. However, for efficient real-world deployment, it is essential to characterize how DQL converges under practical scenarios while simultaneously safeguarding multi-device quantum infrastructures from evolving security threats. Addressing these aspects in an integrated manner is key to ensuring both performance and resilience in large-scale DQL systems. Therefore, this paper presents a new DQL study where our innovation lies in: (i) conducting a holistic convergence analysis for DQL under practical settings, i.e., partial device participation, non-convex loss functions, and heterogeneous data distributions, (ii) developing a novel multi-layered post-quantum cryptographic architecture with a quantum neural network-powered adaptive mechanism that monitors conditions, evaluates threats, and adjusts parameters across three National Institute of Standards and Technology (NIST)-compliant levels. Our theoretical framework and empirical validation reveal two key insights: (i) the derived convergence bound uncovers a fundamental trade-off between convergence rate, measurement shots, and the size of the participating device subset; and (ii) findings from our evaluations on a physical testbed modeling quantum control architectures expose the performance limitations of static post-quantum security, while confirming that our adaptive framework effectively mitigates these overheads to preserve overall system efficiency. Specifically, the hardware experiments demonstrate that our dynamic security mechanism reduces total security execution time by approximately 49% relative to static high-security baselines, while maintaining a threat detection accuracy of over 91%. Furthermore, extensive simulations validate our theoretical analysis..... --- ### Trust in Generative AI for Health Information Consumption and the Effect of Learned Dependency: An Experimental Investigation Authors: Arif Ahmed, Gondy Leroy, Agrim Sachdeva, Philip Harber, Stephen A. Rains, Seokjun Youn, Prosanta Barai Published: 2026-05-21 Categories: cs.CY, cs.AI arXiv: https://arxiv.org/abs/2606.20605v3 Background: Generative artificial intelligence (GenAI) is increasingly used for health information, yet its influence on users' trust calibration remains unclear. Objective: This study examines whether learned dependency on GenAI influences trust in AI-generated health information and whether text highlighting reduces overreliance on incorrect outputs. Methods: Two randomized controlled experiments were conducted with 338 college students and 563 Amazon Mechanical Turk participants. Both experiments used a 2 by 2 between-subjects design manipulating information accuracy (correct versus incorrect) and text highlighting (highlight versus no highlight). Trust and learned dependency were measured using validated scales, and linear regression models tested main and interaction effects. Results: In both experiments, information accuracy significantly increased trust (p < 0.001), while learned dependency was positively associated with trust (p < 0.05). The interaction between accuracy and dependency was significant (p < 0.001), indicating that highly dependent users were more likely to trust incorrect AI-generated information. Text highlighting had no significant effect on trust and did not moderate the relationship between dependency and trust. Conclusions: Learned dependency weakens trust calibration, increasing susceptibility to inaccurate AI-generated health information. Text highlighting alone is insufficient to reduce overreliance, highlighting the need for more effective interface designs that encourage critical evaluation of GenAI outputs. --- ### Simulating Hate Speech Cascades with Multi-LLM Agents: Empirical Grounding, Modeling Fidelity, and Intervention Strategies Authors: Fan Huang Published: 2026-05-21 Categories: cs.SI, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2606.18264v1 Faithful modeling of hateful content propagation on online platforms remains an open problem for moderation research. Classical cascade models that do not explicitly represent the profile, community, and content factors associated with hateful-content propagation may yield moderation strategies that behave less effectively when deployed in real-world scenarios. Multi-agent large language model (LLM) systems can, in principle, make each reshare decision depend on the user's profile, the surrounding community, and the post's content, but it remains unclear whether this added flexibility actually reproduces real hateful cascades more faithfully than classical baselines. We study three hateful Bluesky cascades and a size-matched benign control. In the empirical Bluesky data, we found that: 97.4--99.7\% of reposters take a hostile stance; toxicity-engagement homophily is higher on the diffusion tree than on the follower graph for hateful cascades; topology is star-like for the hateful cascades (most reposts come directly from the root) versus tree-like for the benign cascade (reposts propagate through multi-hop chains). In simulation, a multi-LLM-agent simulator reproduces the stance monoculture and the toxicity-delta direction. A structured ablation identifies agent heterogeneity as the leading fidelity factor, and amplifier targeting on dense networks yields 7.5--12.9\% reduction at 5.7\% benign collateral. --- ### Tracking Urban Atmospheric Pollutants using Sentinel-5P Satellite Data Authors: Alice Gomez-Cantos, Henry O. Velesaca Published: 2026-05-21 Categories: stat.AP, cs.AI arXiv: https://arxiv.org/abs/2606.02592v1 Urban nitrogen dioxide ($NO_2$) is a key indicator of combustion-related air pollution and exhibits strong spatial and temporal variability in cities. This study presents a satellite-based framework for tracking urban $NO_2$ pollution using tropospheric column observations from Sentinel-5P/TROPOMI over Guayas Province, Ecuador. Rather than estimating surface concentrations, the methodology emphasizes robust distributional metrics, including the median and upper-tail percentiles ($P_{90}$, $P_{95}$, and $P_{99}$), to characterize background conditions and localized pollution extremes at the canton scale. Multi-year satellite observations are aggregated annually and analyzed using unsupervised K-means clustering to identify characteristic pollution regimes without predefined thresholds. Results show that highly urbanized cantons consistently exhibit elevated extreme $NO_2$ values and greater variability, while less urbanized areas display lower and more homogeneous patterns. The proposed approach provides an interpretable and scalable tool for urban air-quality assessment in data-scarce regions using satellite observations alone. The implementation is publicly available on GitHub https://hvelesaca.github.io/sentinel-5P-clustering/. --- ### Rashomon-Seeded Annealing for Robust Bayesian Inference in Factorial Designs Authors: Yiyang Fan, Soumyakanti Pan, Tyler H. McCormick Published: 2026-05-21 Categories: stat.ME, stat.ML arXiv: https://arxiv.org/abs/2606.02589v1 Integrating over model uncertainty in factorial designs via Bayesian model averaging is hindered by the combinatorial explosion of interpretable interaction effects, often yielding a multimodal posterior, where standard Markov chain Monte Carlo algorithms encounter significant convergence issues. We propose a general computational framework that repurposes Rashomon sets, collections of high-performing models traditionally valued for prediction and interpretability, as a strategic "warm start" for estimating the full posterior. Our method, Rashomon-seeded annealing, initializes annealed importance sampling (AIS) by anchoring the starting density within these pre-identified, high-evidence regions while preserving global support over the entire model space. Rather than restricting inference to the Rashomon set and understating uncertainty, the AIS correction restores full posterior inference, turning the Rashomon certificate from an inferential truncation into a proposal mechanism. We demonstrate this approach using Rashomon Partition Sets (RPS) as a rigorous, certified seed constructor for factorial designs. The resulting algorithm yields consistent self-normalized posterior summaries, such as model-averaged cell means, credible intervals, and uncertainty summaries without exhaustive enumeration of the complete model space. This bridges the gap between high-evidence model discovery and rigorous Bayesian inference, and outlines a general strategy in which any high-posterior seed set can provide computational leverage for AIS-based model averaging. --- ### CLSP-REQA: A Real-Time Quality-Aware Closed-Loop Seizure Prediction Framework with Mamba-BiLSTM and Confidence-Gated Intervention Authors: Mufeng Chen, Qi Wu, Bingchao Huang, Xiwen Lai, Zekai Chen, Xinge Ouyang, Quansheng Ren Published: 2026-05-21 Categories: eess.SP, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2606.00074v2 Reliable seizure prediction is a prerequisite for closed-loop neurostimulation therapy, yet existing methods rarely account for the variability in EEG signal quality encountered in real-world deployment, and the overwhelming majority adopt non-strict evaluation protocols that overestimate generalisation performance. We propose CLSP-REQA (Closed-Loop Seizure Prediction with Real-time EEG Quality Assessment), a unified framework that embeds a lightweight signal quality estimator directly within the prediction pipeline. A Real-time EEG Quality Assessment (REQA) module runs in parallel with a Mamba-BiLSTM backbone, producing a scalar quality score q in (0,1) that modulates output confidence through a tiered non-linear fusion function (ECLO). Under strict cross-patient evaluation on the CHB-MIT Scalp EEG Database (n = 23 subjects, 198 seizures), CLSP-REQA achieves an AUC-ROC of 0.7426 +- 0.0199, outperforming the unadapted cross-patient baseline of 0.69 reported by Jemal et al., using only 16 EEG channels compared to 23 in prior work, and without requiring any target-patient data or domain adaptation. On the SIENA Scalp EEG Database (n = 14 subjects, 47 seizures), CLSP-REQA achieves AUC 0.7012 +- 0.0249, substantially surpassing the best domain-adapted cross-patient result of 0.61 on the same dataset, demonstrating strong cross-dataset generalisation. The framework outputs a structured four-tuple (p, q, c, Phi_SHAP) directly compatible with closed-loop neurostimulator interfaces. --- ### CLSP-REQA: A Real-Time Quality-Aware Closed-Loop Seizure Prediction Framework with Mamba-BiLSTM and Confidence-Gated Intervention Authors: Mufeng Chen, Qi Wu, Bingchao Huang, Xiwen Lai, Zekai Chen, Xinge Ouyang, Quansheng Ren Published: 2026-05-21 Categories: eess.SP, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2606.00074v1 Reliable seizure prediction is a prerequisite for closed-loop neurostimulation therapy, yet existing methods rarely account for the variability in EEG signal quality encountered in real-world deployment, and the overwhelming majority adopt non-strict evaluation protocols that overestimate generalisation performance. We propose CLSP-REQA (Closed-Loop Seizure Prediction with Real-time EEG Quality Assessment), a unified framework that embeds a lightweight signal quality estimator directly within the prediction pipeline. A Real-time EEG Quality Assessment (REQA) module runs in parallel with a Mamba-BiLSTM backbone, producing a scalar quality score q in (0,1) that modulates output confidence through a tiered non-linear fusion function (ECLO). Under strict cross-patient evaluation on the CHB-MIT Scalp EEG Database (n = 23 subjects, 198 seizures), CLSP-REQA achieves an AUC-ROC of 0.7426 +- 0.0199, outperforming the unadapted cross-patient baseline of 0.69 reported by Jemal et al., using only 16 EEG channels compared to 23 in prior work, and without requiring any target-patient data or domain adaptation. On the SIENA Scalp EEG Database (n = 14 subjects, 47 seizures), CLSP-REQA achieves AUC 0.7012 +- 0.0249, substantially surpassing the best domain-adapted cross-patient result of 0.61 on the same dataset, demonstrating strong cross-dataset generalisation. The framework outputs a structured four-tuple (p, q, c, Phi_SHAP) directly compatible with closed-loop neurostimulator interfaces. --- ### Rare Events, Real Signals: Functional Ensembles as Units of Computation in Deep Spiking Networks Authors: Aditi Aravind, Konstantinos Ladakis, Mario Alexios Savaglio, Stelios M. Smirnakis, Maria Papadopouli Published: 2026-05-21 Categories: cs.NE, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2606.00073v1 We investigate how internal representations emerge across hierarchical processing systems by introducing a neuroscience-inspired framework for analyzing deep spiking neural networks (SNN) through the lens of functional connectivity. Drawing on concepts from systems neuroscience and information theory, we form the first-order functionally-connected (1FC) group of a neuron based on its statistically significant pairwise correlations with neurons from the previous layer of a trained SNN architecture. We then track its response properties during inference under various conditions. Our analysis shows that several principles of functional connectivity previously observed in biological cortex are preserved in spiking ResNet architectures. These 1FC ensembles display interesting properties: their aggregate cofiring reliably predicts downstream neuronal responses through a robust, ReLU-like input-output relationship, whose gain scales systematically with ensemble size. Reliable encoding of the presented class emerges only during high 1FC cofiring events, which themselves occur infrequently, indicating that informative representations are concentrated in rare but highly coordinated activity patterns. Under uniform random noise or adversarial perturbations, these response profiles are disrupted, particularly in early and intermediate layers. This enables a targeted high-resolution interrogation at specific nodes and pathways. We showed that the functional connectivity structure is shaped by learning and this structure breaks under weight permutation. These establish 1FC ensembles as a functionally meaningful substrate for input encoding and information transfer, with potential implications in designing targeted fine-grained diagnostics on the information flow. --- ### Self-Play Reinforcement Learning under Imperfect Information in Big 2 Authors: Aalok Patwa Published: 2026-05-21 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2605.28863v2 Imperfect-information multiplayer games test whether agents can act under hidden information, sparse rewards, and non-stationary opponents. We study these challenges in Big 2, a four-player imperfect-information card game. We develop a self-play RL framework for Big 2 that enables controlled comparisons between policy-gradient and value-approximating agents. Under a common environment, input representation, training budget, and evaluation protocol, PPO outperforms Monte Carlo Q approximation, SARSA, and Q-learning against random, greedy, and heuristic Big 2 opponents. We further find that moderate entropy regularization improves PPO by preventing the policy from becoming overly deterministic, and that current-policy self-play provides a stronger finite-budget curriculum than checkpoint self-play or fixed-opponent training. Together, these results show that Big 2 is a useful controlled setting for studying deep RL under imperfect information, multiplayer interaction, delayed rewards, and variable action sets. --- ### Molecular Lead Optimization via Agentic Tool Planning Authors: Lingxiao Li, Haobo Zhang, Ruohao Fan, Bin Chen, Jiayu Zhou Published: 2026-05-21 Categories: cs.LG, q-bio.QM arXiv: https://arxiv.org/abs/2605.28862v1 Drug discovery is a lengthy and resource-intensive process composed of multiple stages. Among these stages, lead optimization plays a critical role in transforming early hit compounds into viable drug candidates. This stage requires improving ADMET-related properties through subtle structural refinement while preserving key molecular substructures responsible for binding affinity to disease targets. Recent advances in artificial intelligence have shown promise in accelerating various aspects of drug discovery; however, most existing approaches to lead optimization rely on one-step molecular optimization, which fail to account for the long-term consequences of sequential design decisions. To address this limitation, we propose TRACE, a trajectory-aware, LLM-reasoning agent for molecular lead optimization that formulates tool selection as a sequential decision-making problem over action trajectories. Given a lead molecule and an optimization objective, TRACE makes trajectory-aware decisions over molecular optimization tools, enabling forward-looking refinement under structural constraints. Experiments on multiple ADMET optimization tasks show that our agent achieves higher optimization success, larger property improvements, and higher validity, while preserving molecular similarity compared to baseline models. --- ### Comment on "Spin-1/2 Kagome Heisenberg Antiferromagnet: Machine Learning Discovery of the Spinon Pair-Density-Wave Ground State" Authors: Helia Kamal, Dominik Kufel, DinhDuy Vu, Chris R. Laumann, Norman Y. Yao Published: 2026-05-21 Categories: cond-mat.str-el, cond-mat.dis-nn, cs.LG arXiv: https://arxiv.org/abs/2605.28861v1 A recent article (Phys. Rev. X 15, 011047 (2025)) utilizes group-equivariant convolutional neural networks to study the ground state of the kagome Heisenberg antiferromagnet. On the largest finite-size cluster studied to date ($N=108$), the authors report variational energies significantly lower than other numerical methods, including state-of-the-art density matrix renormalization group (DMRG) calculations. In contrast to previous results suggesting a possible spin-liquid ground state, the authors observe a spinon pair-density-wave ground state. We find that: (i) the reported low energies are artifacts of broken ergodicity in the Metropolis--Hastings sampling, since the single-spin-flip update rule utilized by the authors effectively freezes the Markov chains; and (ii) when ergodic sampling is enforced via spin-exchange updates, the neural network converges to energies significantly higher than existing DMRG results, calling the paper's claims into question. --- ### Mechanistic origins of catastrophic forgetting: why RL preserves circuits better than SFT? Authors: Jeanmely Rojas Nunez, Viraj Sawant, Nathan Allen, Nomgondalai Amgalanbaatar, Yannis Zongo, Vasu Sharma, Maheep Chaudhary Published: 2026-05-21 Categories: cs.LG, cs.AI, cs.CL, cs.CR arXiv: https://arxiv.org/abs/2605.28860v2 Fine-tuning large language models (LLMs) frequently induces catastrophic forgetting of prior capabilities. Recent work has shown that reinforcement learning (RL) retains prior capabilities more effectively than supervised fine-tuning (SFT), attributing this to policy-gradient updates remaining closer to the base policy \cite{shenfeld2025rl}. We extend this behavioral account to the mechanistic level and ask whether RL's advantage is mirrored by stronger preservation of internal computational circuits. We introduce differential circuit vulnerability, a head-level measure of how much a circuit degrades under fine-tuning, and use it to compare RL and SFT on Qwen2.5-3B-Instruct adapted to scientific question-answering. We find a clear mechanistic trade-off: SFT adapts more rapidly to the target task but produces substantially greater circuit disruption and forgetting of prior capabilities, whereas RL preserves a larger fraction of the base circuit at the cost of slower task adaptation. These findings suggest that circuit preservation may help explain why RL is more robust to catastrophic forgetting. We released our code here: https://github.com/rl-sft-circuit-research/differential-circuit-vulnerability. --- ### $E^3$-Agent: An Executable and Evolving Agent for Resource Management of Edge Generative Inference Authors: Rui Bao, Yaping Sun, Zhiyong Chen, Feng Yang, Meixia Tao, Nan Li, Wenjun Zhang Published: 2026-05-21 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.27428v1 Edge deployments of generative inference increasingly face two practical realities: per-device per-model performance is often unknown at deployment time, and it is non-stationary due to user-driven semantic events, background load, and device churn. Consequently, a resource manager that is tuned offline under a fixed regime can become brittle and expensive to maintain. This paper presents $E^3$-Agent, an executable and evolving agent for edge artificial intelligence generated content (AIGC) resource management. $E^3$-Agent separates a fast-path router that makes millisecond-level dispatch decisions from a slow-path, event-driven large language model (LLM) meta-controller that mitigates regime shifts through a small, explicit control surface exposed via a tool interface, including risk gating, router configuration, and rapid performance calibration. The agent learns online from execution feedback and continuously adapts to unknown and time-varying service-time mappings. We evaluate $E^3$-Agent in a discrete-event simulator driven by MLPerf-derived device-model measurement priors, covering cold-start warmup and three dynamic regimes: semantic dynamics, device churn, and hidden drift. Across the dynamic scenarios, $E^3$-Agent reduces average latency by 65%-73% compared to the best static baseline, stays within 7%-10% of an online full-information Oracle used for evaluation, and effectively suppresses stutter rate under semantic degradation. --- ### Eroding Trust in Real Speech: A Large-Scale Study of Human Audio Deepfake Perception Authors: Nicolas M. Müller, Wei Herng Choong Published: 2026-05-21 Categories: cs.SD, cs.AI arXiv: https://arxiv.org/abs/2605.26136v1 Audio deepfakes have improved rapidly recently, yet their effect on human trust in real speech remains unstudied. We present the largest listening study on audio deepfake perception to date, collecting 35,532 judgments from 1,768 participants across 138 text-to-speech and voice conversion systems. Our central finding is a skepticism shift: compared to a 2021 baseline, human accuracy on fake samples barely changed (72.9% to 71.2%), but accuracy on real samples dropped from 72.7% to 64.1%. Participants are not worse at detecting synthesis artifacts; rather, they increasingly distrust authentic speech. Samples generated by commercial and autoregressive language model systems proved hardest to detect (61.3 - 65.9%), while those from traditional seq2seq and flow-matching models remain easier to spot (75.4 - 76.8%). An ML detector that served as a reference point maintained over 94.5% accuracy across all conditions. Our results suggest that the primary threat posed by modern deepfakes may not be mere deception, but the erosion of trust in genuine audio. --- ### SilIF: Silhouette-Augmented Isolation Forest for Unsupervised Transaction Fraud Detection Authors: Venkatakrishnan Gopalakrishnan Published: 2026-05-21 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.26135v1 Unsupervised anomaly detection is widely used in transaction fraud detection where labels are scarce. Isolation Forest (IF) is among the most popular classical methods due to its scalability and ease of deployment. We propose SilIF, an augmentation of Isolation Forest that adds a silhouette-based scoring layer computed in a representation space induced by the trees of the forest. For each point, we extract a vector of per-tree path lengths, cluster these "fingerprints" into structural groups, and compute a silhouette score that measures how well the point fits its assigned group versus the nearest alternative. The silhouette signal is combined with the base IF score via a single hyperparameter alpha. On the IEEE-CIS Fraud Detection benchmark (~590K transactions, 3.5% fraud), SilIF with alpha=1.0 improves over plain Isolation Forest by +0.0080 AUC-PR on average across five seeds, with SilIF winning on all five seeds (paired t-test p=0.046). We also report results on a synthetic credit-card dataset (Sparkov) where the silhouette augmentation does not improve over plain IF, and we characterize the conditions that distinguish the two outcomes. The paper presents SilIF as a tunable, easy-to-deploy enhancement to Isolation Forest with honest reporting of when it helps and when it does not. Code at https://github.com/venkat15vk/silif-anomaly-detection. --- ### Pretraining Data Exposure in Large Language Models: A Survey of Membership Inference, Data Contamination, and Security Implications Authors: Ziyi Tong, Feifei Sun, Le Minh Nguyen Published: 2026-05-21 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2605.26133v1 Large Language Models (LLMs) have become the predominant paradigm in NLP, advancing both research and industry. As model sizes and pretraining data grow, concerns about Pretraining Data Exposure (PDE) increase due to the scale and opacity of training datasets. PDE refers to determining whether specific data appeared in an LLM's pretraining corpus. It is critical for ensuring evaluation integrity and protecting privacy, intersecting two key areas: data contamination and membership inference. Though conceptually related, these areas have often been studied in isolation. This paper offers the first unified survey of both under the PDE framework. We formalize PDE across exposure levels, review attack and defense methods, synthesize empirical findings, and highlight open challenges and future research directions. --- ### More Skills, Worse Agents? Skill Shadowing Degrades Performance When Expanding Skill Libraries Authors: Hongwen Song, Song Wei Published: 2026-05-21 Categories: cs.SE, cs.AI, stat.AP arXiv: https://arxiv.org/abs/2605.24050v2 Skill libraries allow LLM agents to load task-specific instructions on demand, letting non-expert users solve domain-specific tasks through natural language without knowing which skills exist or how they work. However, performance degrades as libraries grow -- by up to 21\% when scaling from a small set of helpful skills to a 202-skill library. In this work, we formulate this performance degradation as the pass rate drop between loading a library of known-helpful skills and the full library. Moreover, we propose to decompose the pass rate drop by conditioning on the skill(s) invocation -- which skills the agent selects during a trajectory -- into two effects: \emph{skill shadowing}, where the agent selects wrong skills more often as the library expands, and \emph{context overhead}, where the enlarged context degrades execution even when selection is correct. We derive upper bounds on both effects to characterize their magnitudes of impacts to the pass rate drop. Our empirical estimates of the effects and their upper bounds both show that the \emph{skill shadowing} effect grows with library size and significantly contributes to the performance degradation, whereas the \emph{context overhead} effect remains small and indistinguishable from zero. This observed asymmetry establishes that the skill selection failure, not the enlarged context, is the primary bottleneck when expanding the skill libraries. --- ### Mixture of Complementary Agents for Robust LLM Ensemble Authors: Yichi Zhang, Kevin Lu, Yuang Zhang, Jie Gao, Lirong Xia, Fang-Yi Yu Published: 2026-05-21 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2605.24048v1 Multi-AI collaboration, such as ensembling or debating large language models (LLMs), is a promising paradigm for aggregating information and boosting performance. A foundational step in these pipelines is to feed the responses of several proposer LLMs into a summarizer LLM, which synthesizes a better answer. However, choosing which proposers to include is non-trivial. Existing approaches primarily focus either on accuracy (picking the strongest models) or diversity (ensuring variety), and often overlook the interactions among proposers and with the summarizer. We reframe proposer selection as a combinatorial selection problem akin to feature selection, where the value of an LLM lies in its complementarity with others. However, directly applying standard feature-selection algorithms is impractical in the LLM setting due to prohibitive time complexity. Motivated by this limitation, we explore an extensive range of computationally feasible, greedy-style selection algorithms that assess complementarity using a small labeled set. Our experiments validate complementarity as a guiding principle for proposer selection and identify methods that achieve the best performance-cost trade-offs in practice. --- ### EMMA: Extracting Multiple physical parameters from Multimodal Data Authors: Farhat Shaikh, Ayan Banerjee, Sandeep Gupta Published: 2026-05-21 Categories: cs.CV arXiv: https://arxiv.org/abs/2605.24047v1 We introduce EMMA, a physics-informed multimodal framework that recovers all identifiable dynamical parameters of a system directly from raw video, audio, and image-based time-series observations. Unlike prior video-only approaches that struggle with occluded states, hidden actuation inputs, or assumptions about known initial conditions and coordinate frames, EMMA performs joint inference of explicit parameters, implicit dynamical components, and calibration invariants within a unified continuous-time model. EMMA leverages a Liquid Time-Constant (LTC) network to learn latent dynamics from heterogeneous modalities while a physics-constrained loss enforces consistency with the governing differential equations. A unified feature pipeline enables consistent alignment across video trajectories, acoustic signatures, and chart-derived measurements, allowing EMMA to estimate parameters under forced, implicit, and multivariate dynamics without requiring segmentation masks, differentiable rendering, or specialized sensors. Across 100+ scenarios including five standard dynamical benchmarks (75 Delfys videos), real-world rover and quadrotor systems with hidden inputs, and simulation-chart case studies spanning biological and chaotic systems, EMMA delivers robust multi-parameter recovery and significantly outperforms existing single-modality and equation-discovery baselines. Our results establish EMMA as a general, scalable solution for physics-consistent model extraction from opportunistic multimodal data. Code and data are available at: https://github.com/ImpactLabASU/EMMA-CVPR2026 --- ### A Large-Scale Dataset and Benchmark: Do Protein-Ligand Models Learn Binding Sites or Just Binding Likelihood? Authors: Zhaohan Meng, Zhen Bai, Ke Yuan, Iadh Ounis, Zaiqiao Meng, Hao Xu, Joseph Loscalzo Published: 2026-05-21 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2605.24045v1 Protein-ligand modeling underpins computational drug discovery and molecular design. Existing protein-ligand benchmarks typically evaluate whether a protein and ligand interact and how strongly they bind, through tasks such as binary binding prediction and affinity regression. However, these evaluations provide limited evidence of whether models can localize binding sites or identify the non-covalent interactions underlying molecular recognition. To address this gap, we introduce InteractBind, a large-scale protein-ligand dataset comprising approximately 100k protein-ligand pairs, together with a benchmark for fine-grained evaluation. The core fine-grained task is that of binding-site localization, which uses protein-residue and ligand-atom interaction maps spanning six major types of non-covalent interactions to assess whether model-derived interaction maps localize binding sites. InteractBind further includes binding affinity and protein similarity-controlled splits to support realistic generalization assessment. Using InteractBind, we evaluate eight existing sequence-based and interaction-aware models, assessing binary binding prediction and binding-site localization. Results reveal limited binding-site localization despite strong binary binding prediction, with marked variation across non-covalent interaction types. Overall, InteractBind establishes a benchmark paradigm that encourages the development of more interpretable and physically grounded protein-ligand models. --- ### LLM-AutoSciLab: Closed-Loop Scientific Discovery via Active Experimentation with LLMs Authors: Sanchit Kabra, Nikhil Abhyankar, Saaketh Desai, Prasad Iyer, Chandan K Reddy Published: 2026-05-21 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2605.24043v1 Scientific discovery is a closed-loop process in which hypotheses guide data acquisition and observations refine the hypothesis space. Yet most approaches reduce discovery to supervised learning over fixed datasets, where limited observations can support multiple plausible mechanisms that fit locally but fail to generalize. Thus, the key challenge is selecting informative observations to resolve uncertainty, shifting the focus from static inference to adaptive data acquisition. To address this, we propose LLM-AutoSciLab, a closed-loop framework that couples hypothesis generation with hypothesis-conditioned experiment selection and mechanism refinement. Rather than fitting models to passively collected data, LLM-AutoSciLab iteratively proposes plausible hypotheses, selects informative experiments to distinguish or refine them, and updates its state using the resulting evidence. To evaluate dynamic, closed-loop scientific discovery with active data acquisition, we introduce ActiveSciBench, comprising two datasets: ActiveSciBench-Chem with 57 enzyme-kinetics tasks and ActiveSciBench-GRN with 45 gene-regulatory-network tasks. These datasets model discovery as a budget-constrained process requiring adaptive experiment design, variable selection, and recovery of true mechanisms. Across NewtonBench, ActiveSciBench-Chem, and ActiveSciBench-GRN, LLM-AutoSciLab outperforms prior methods, achieving 67.6% and 35.1% symbolic accuracy on NewtonBench and ActiveSciBench-Chem, respectively, and 31.1% exact graph recovery on ActiveSciBench-GRN. Moreover, hypothesis-guided experimentation is 2-5x more sample-efficient than the strongest competing baselines. Code and data are available at: https://github.com/scientific-discovery/LLM-AutoSciLab --- ### Hidden-State Privacy Has an Empty Middle Authors: Alexander Okezue Bell Published: 2026-05-21 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2605.24042v3 Of $1{,}536$ Gaussian release covariances we tested for single-layer hidden-state privacy, zero achieve both moderate utility and moderate privacy against an adaptive retrieval attacker. We prove a complementary Fisher-ball lower bound: every full-rank Gaussian release at $O(1)$ Fisher utility admits a direction whose Mahalanobis signal grows linearly in hidden width, ruling out uniform Gaussian safety in the class and matching the empirical empty middle. The diagonal inverse-Fisher release $Σ^\star_{\mathrm{diag}}(\mathcal{K}) = (2\mathcal{K}/d)\,\mathrm{diag}(1/F_{ii})$ is the unique minimax-optimal diagonal mechanism at first-order KL budget $\mathcal{K}$ and the only release with worst-attacker top-1 $\le 0.001$ at every point of a 32 model-layer grid, but it sits on a privacy/utility edge rather than filling the middle. A generalized-eigen mechanism reaching $13\times$ Pareto reduction under Euclidean retrieval collapses to $100\%$ top-1 under the adaptive Mahalanobis attacker, and a full-trajectory sequence inverter recovers $94\%$ of clean GPT-2 prefixes but $0\%$ under $Σ_{\mathrm{diag}}$. A split-memory transformer trained from scratch reaches $G_{\mathrm{Mah}} \in (20, 33)$ at 90M and maintains a $6$--$24\times$ advantage over same-budget GPT baselines from 30M to 1B at a fixed-token language-modeling loss penalty; pretrained models top out at 9.3. These results reframe hidden-state release from mechanism-design within the Gaussian class to architecture or release co-design. --- ### Iterative Refinement Neural Operators are Learned Fixed-Point Solvers: A Principled Approach to Spectral Bias Mitigation Authors: Xiaotian Liu, Shuyuan Shang, Xiaopeng Wang, Pu Ren, Yaoqing Yang Published: 2026-05-21 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2605.24041v2 Neural operators serve as fast, data-driven surrogates for scientific modeling but typically rely on a monolithic, single-pass inference procedure that struggles to resolve high-frequency details, a limitation known as spectral bias. We introduce the Iterative Refinement Neural Operator (IRNO), which augments pre-trained operators with a learned refinement module iteratively applied via fixed-point iteration. IRNO decomposes the prediction into a coarse initialization followed by successive residual corrections, paralleling classical numerical solvers. Under local assumptions, we establish contraction of the induced operator, ensuring convergence to a unique fixed point. To explicitly target high-frequency errors, we propose a progressive spectral loss that adaptively increases penalty on high-frequency components over refinement steps during training. Across physical systems, IRNO consistently lowers error, with up to 56.05% improvement on turbulent flow. On Active Matter, spectral analysis reveals that, relative to base operator, the normalized error ratios decrease to 27.72-36.10% in low-, 5.07-6.68% in mid-, and 1.48-2.04% in high-frequencies, remaining stable beyond the trained iteration count. Code is available at https://github.com/xiaotianliu-dartmouth/Iterative_Refinement_Neural_Operator --- ### Learning to See Like Humans: Gaze-Aligned Cycling Safety Prediction Authors: Luís Maria Perdigão, Miguel Costa, Carlos Santiago, Manuel Marques Published: 2026-05-21 Categories: cs.CV arXiv: https://arxiv.org/abs/2605.24040v1 Cycling delivers significant public-health and environmental benefits, yet its uptake in cities is often limited by perceived safety. When street environments appear unsafe, individuals are less likely to cycle, making perception a key barrier to adoption. Recent work has shown that pairwise comparisons of street-view images provide a scalable way to learn subjective safety judgments. However, existing approaches do not explicitly model human visual attention, which plays a central role in how humans perceive safety. We propose an Eye-Tracking-Guided Perceived Cycling Safety framework (EG-PCS) that integrates gaze data into a pairwise learning pipeline based on vision transformers. By supervising the model's attention mechanism with eye-tracking signals, we encourage alignment between learned attention maps and human fixation patterns. Experiments show that gaze-guided models achieve similar ranking performance compared to state-of-the-art approaches while producing attention maps that more accurately reflect human visual attention behavior. Our results demonstrate that incorporating eye-tracking information enhances both predictive accuracy and interpretability in perception-based urban analytics. --- ### Aurora Hunter: A Two-Stage Framework for Probabilistic Visibility Forecasting Authors: Zongyuan Ge, Chenwaner Zhang, Haoyang Li, Hantai Zhang, Wei Zhou, Wenxin Gu, Zhaoming Wang Published: 2026-05-21 Categories: physics.space-ph, astro-ph.EP, astro-ph.IM, cs.LG arXiv: https://arxiv.org/abs/2605.24038v3 Aurora visibility at a given location requires two physically distinct conditions to hold at once: aurora occurring overhead, governed by solar wind-magnetosphere coupling, and observing conditions that permit detection, governed by cloud cover and moonlight. Approaches that conflate the two weaken the space-weather signal and limit cross-site generalizability. We develop Aurora Hunter, a two-stage cascade that separates occurrence prediction from observing-condition assessment. Stage 1 uses 43 physics-driven features to predict P(aurora identifiable in all-sky images) via gradient-boosted trees trained on joint Tromso+Kiruna data (about 16,600 hours, 2015-2023). Stage 2 models P(unobscured image class | identifiable) with logistic regression on 15 observing-condition features, trained on hours with identifiable aurora. The cascade P(visible) = P(identifiable) x P(unobscured | identifiable) achieves retrospective ROC-AUC of 0.958 (Tromso test, 2019-2020) and 0.933 (independent Kiruna, 2024), improving on the occurrence stage used alone by +0.095 and +0.097. Transfer to Skibotn, the one station withheld entirely (2022-2025), is limited. SHAP analysis identifies magnetic local time, the Kp x nightside interaction and the three-hour mean Kp as the dominant features (44% of attribution), consistent with auroral oval physics. Hemisphere-wide occurrence maps combine the Stage 1 amplitude, on a clear-sky basis, with the Feldstein oval parameterization. By providing location-specific visibility probabilities with measured reliability rather than coarse geomagnetic indices, the framework links space weather research to practical observation planning. An operational proof of concept is available at https://aurora-hunter.onrender.com --- ### Aurora Hunter: A Two-Stage Framework for Probabilistic Visibility Forecasting Authors: Zongyuan Ge, Chenwaner Zhang, Haoyang Li, Hantai Zhang, Wei Zhou, Wenxin Gu, Zhaoming Wang Published: 2026-05-21 Categories: physics.space-ph, astro-ph.EP, astro-ph.IM, cs.LG arXiv: https://arxiv.org/abs/2605.24038v2 Forecasting aurora borealis visibility matters for space weather research and aurora tourism. Visibility at a site and night depends on two distinct factors: (1) whether aurora is physically occurring, driven by solar wind-magnetosphere coupling, and (2) whether observing conditions allow naked-eye detection, mainly cloud cover and lunar illumination. We present Aurora Hunter, a two-stage cascade that decouples these factors. Stage 1 predicts P(occurring) with XGBoost using 51 physics-driven features trained on joint Tromso+Kiruna data (about 16,600 hourly samples, 2015-2023) with labels from the Tromso AI all-sky image classifier. Stage 2 predicts P(clear observation given occurring) with logistic regression using 21 cloud-cover and lunar-illumination features trained only on aurora-occurring hours. The cascade P(visible)=P(occurring)*P(clear|occurring) reaches ROC-AUC 0.937 (Tromso test, 2019-2020) and 0.905 (independent Kiruna, 2024), improving a single-stage baseline by +0.087. Held-out Skibotn data (2022-2025) confirm cross-site generalization. SHAP identifies the Kp x nightside interaction, MLT position, and auroral oval distance as dominant predictors (39% combined). Prototype: https://aurora-hunter.onrender.com. --- ### Mode-as-Sequence: Translating Multimodal Motion Prediction into Unified Sequential Mode Modeling Authors: Zikang Zhou, Haibo Hu, Xinhong Chen, Yifan Zhang, Nan Guan, Yung-Hui Li, Chun Jason Xue, Jianping Wang Published: 2026-05-21 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2605.24037v1 Multimodal motion forecasting is inherently under-supervised: each training scene provides only one realized future, yet multiple plausible futures exist. This sparse supervision often leads to mode collapse (redundant hypotheses and insufficient mode coverage) and unreliable confidence ranking when predicting a small set of trajectories. We propose Mode-as-Sequence, a unified decoding framework that translates an unordered mode set into an ordered mode sequence and explicitly models mode-to-mode dependency. Under this framework, we develop two complementary instantiations. ModeSeq performs recurrent mode decoding, where each mode is generated conditioned on the previously generated modes, encouraging diverse, non-redundant hypotheses with calibrated confidence ordering. To remove the mode-by-mode autoregressive bottleneck, we further propose Parallel ModeSeq, which preserves the same causal dependency using masked mode-to-mode self-attention while decoding all modes in a single forward pass, enabling efficient large-$K$ inference and scalable joint-scene prediction. To learn representative modes and calibrated confidence under sparse labels, we introduce Early-Match-Take-All (EMTA) and its joint-scene extension MA-EMTA, together with a lightweight ranking regularizer that reduces confidence inversions. Extensive experiments on large-scale benchmarks demonstrate consistent improvements in both ranking-oriented metrics and best-of-K accuracy across datasets, horizons, and object types. In the Waymo Open Dataset challenges, ModeSeq achieves 1st place in the 2024 LiDAR-free motion prediction track, and Parallel ModeSeq achieves 1st place in the 2025 Interaction Prediction Challenge, validating the effectiveness of Mode-as-Sequence for both accuracy and efficiency. --- ### WTKO-CNN: Deep Learning Reveals Sequence Motifs Distinguishing Wild-Type and Knockout ATAC-seq Peaks Authors: Lopamudra Dey Published: 2026-05-21 Categories: q-bio.GN, cs.AI arXiv: https://arxiv.org/abs/2605.24034v1 Chromatin regulators can alter transcriptional programs by modifying the accessibility of regulatory DNA elements. Understanding how regulatory sequences differ between wild-type (WT) and knockout (KO) conditions is crucial for deciphering transcriptional control. Here, we applied a convolutional neural network, \textbf{WTKO-CNN} with an attention mechanism to classify DNA sequences as WT or KO, achieving high predictive performance. To interpret the model, we generated saliency maps to identify nucleotide positions most influential for the classification decision. From these high-saliency regions, we extracted and clustered k-mers, enabling de novo motif discovery. Sequence logos and consensus motifs derived from the CNN filters revealed biologically meaningful patterns, which are further validated using MEME, TOMTOM, and HOMER against known transcription factor binding sites. Our analysis identified motifs associated with transcription factor families that discriminate WT from KO sequences, demonstrating that CNN-guided saliency mapping is a powerful approach for uncovering functional sequence features. --- ### Towards Verifiable Transformers: Solver-Checkable Circuit Explanations Authors: Neel Somani Published: 2026-05-21 Categories: cs.LG, cs.LO arXiv: https://arxiv.org/abs/2605.24033v2 Mechanistic interpretability typically discovers circuits and then argues what they do from examples and ablations. We introduce Verifiable Transformers, a framework for turning task-localized circuits into bounded, solver-checkable claims: projected functional equivalence, task-relevant invariance, edge necessity, and robustness to continuous final-residual perturbations. At small scale, we directly verify all four properties for quote-closing and bracket-type circuits, including program-mediated circuits whose attention selection is entirely symbolic. At GPT-2 scale, we remove LayerNorm from a sparsemax/LeakyReLU model after training with a +0.0087 OpenWebText loss increase, replace retained attention heads with synthesized restricted-DSL programs, and calibrate only program-local readouts while freezing and hashing every other parameter. The resulting three-edge quote circuit (embedding $\to$ MLP 0 $\to$ program head $\to$ logits) verifies all four properties over a hash-pinned 1,280-prompt domain in linear real arithmetic: 1,280/1,280 equivalence and invariance, 640 edge-necessity witnesses per edge, and robustness at $ε= 0.01$ with minimum certified radius 0.01515. For two alphabet variants of the same opener-detection/copy-type task, untouched gates expose a localization frontier: bracket-type extraction is exact only with all 144 heads, while the constructed quote artifact verifies with three edges. Naive discovery-based verification failed for measured reasons; at scale, we find we must build the object we can verify. The verified object is a calibrated artifact, not the unmodified model, and all claims are bounded to declared domains. --- ### Is a Document Educational or Just Wikipedia-Style? -- Pitfalls of Classifier-Based Quality Filtering Authors: Mateusz Klimaszewski, Piotr Andruszkiewicz Published: 2026-05-21 Categories: cs.CL arXiv: https://arxiv.org/abs/2605.23721v1 Classifier-based Quality Filtering has recently emerged as a fundamental technique in constructing pre-training corpora. The ability to deploy a single model that can replace or supplement a set of heuristics has proven effective across numerous Large Language Models. In this work, we expose a critical vulnerability in this approach by demonstrating how a straightforward Wikipedia-style reformatting operation can substantially alter a model's quality assessment and enable low-quality content to surpass filtering thresholds. Our analysis reveals that the FineWeb-Edu CQF model would reverse its filtering decision for approximately 7% of evaluated documents, thereby admitting content into the pre-training corpus that would otherwise have been excluded. --- ### Philosophical Dispositions as Behavioral Constraints for AI-Assisted Code Review: An Empirical Study Authors: Kaushal Bansal Published: 2026-05-21 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2605.23108v1 AI-assisted code review tools typically operate as generic "expert reviewer" agents, producing homogeneous findings regardless of the analysis type needed. We present a system that constrains AI reviewer behavior through philosophical dispositions -- coherent personality lenses grounded in specific epistemological traditions (Pyrrhonist Skepticism, Navya-Ny=aya logic, Diogenes' Cynicism, Confucian relational ethics) that direct attention to structurally different types of issues. Each disposition is defined apophatically (by what it refuses to do), equipped with a self-monitoring failure mode (hamartia), and orchestrated in sequence by role protocols. We evaluate this system on 50 merged pull requests across 7 repositories spanning 5 programming languages (Python, Go, C++, Java, Terraform), 5 organizations (2 enterprise, 3 open-source), and 2 temporal eras (pre-AI 2020, post-AI 2024--2026). The disposition system achieves 46% convergence with human reviewers (validating signal quality), identifies unique findings at a 75% rate, and produces no findings judged false-positive by the author across 601 total findings (inter-rater agreement was not assessed and remains a limitation). A controlled baseline comparison demonstrates that 51% of disposition findings are not produced by the same model using generic "expert reviewer" prompting, and these unique findings target structural, operational, and logical concerns rather than standard code-level issues. Preliminary cross-model validation (Claude Opus vs.\ GPT Codex 5.3-xhigh) on 3 PRs shows 100% framework-structure adherence with 39% finding-level agreement, suggesting the framework provides real behavioral constraint while preserving model-specific analytical perspective. --- ### A Fine-Tuned BERT Classifier for Personal-Letter Titles in Late-Ming and Early-Qing Collected Works Authors: Queenie Luo Published: 2026-05-21 Categories: cs.CL, cs.AI, cs.CY, cs.DB arXiv: https://arxiv.org/abs/2605.23103v1 I present Lepton (Letter Prediction), a fine-tuned BERT classifier that predicts whether a title in a Classical Chinese wenji table of contents is a personal letter or a closely confusable preface (particularly the farewell-preface). Lepton fine-tunes bert-base-chinese on 5438 hand-labeled wenji titles from thirty-three late-Ming and early-Qing literati. I've deployed the model on Hugging Face and has been used at the China Biographical Database (CBDB) to identify approximately fifty-five thousand letters across mid-Ming through early-Qing wenji, populating the Ming Letter Platform. --- ### LLM Sparsity Prior for Robust Feature Selection Authors: Caleb Skinner, Yihan Guo, Meng Li Published: 2026-05-21 Categories: stat.ML, cs.LG, stat.ME arXiv: https://arxiv.org/abs/2605.23102v1 Large language models (LLMs) offer a scalable mechanism to elicit domain-informed prior information for high-dimensional variable selection. However, existing methods such as LLM-Lasso are sensitive to weight quality, with performance degrading substantially when LLM-generated weights are inaccurate. To address this challenge, we first introduce a framework for quantifying the quality of LLM-generated weights, enabling rigorous evaluation of LLM-informed methods across varying weight regimes. We then propose the LLM Sparsity Prior (LSP), which integrates LLM-generated weights into the prior inclusion probabilities of Spike-and-Slab and Spike-and-Slab Lasso models via two interpretable hyperparameters governing global sparsity and weight concentration. Hierarchical hyperpriors on these parameters allow the model to dynamically discount uninformative or misleading weights, improving robustness without sacrificing gains when weights are accurate. Finally, we develop principled prompt engineering strategies and validate the method on a private medical dataset studying Acute Kidney Injury. LSP improves prediction accuracy and identifies clinically relevant features missed by the baselines, with robustness to prompt variation and particular effectiveness in low-data regimes. ---