# Research Papers — 2026-05 · bundle page 154 of 326 > Full-text markdown of papers #7651–7700 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/154 [← Previous bundle](https://aipod.dev/papers/archive/2026-05/page/153.md) [Next bundle →](https://aipod.dev/papers/archive/2026-05/page/155.md) ### Counterfactual Explanations Under Concept Drift Authors: Marcin Kostrzewa, Jerzy Stefanowski, Maciej Zięba Published: 2026-05-17 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.17651v1 Counterfactual explanations (CFEs) provide actionable recourse, but most methods assume a static framework with fixed data and a trained classifier. This assumption breaks in evolving data environments, such as data streams, where online models are repeatedly updated under concept drift. We identify CFE maintenance in this setting as a previously overlooked problem: explanations that are valid when generated may silently become invalid as the model evolves, including robust CFEs, which are not designed for continuous drift. We propose a lightweight, model-agnostic update scheme that repairs existing CFEs using local sampling to estimate validity and plausibility directions while preserving proximity to the original instance. Experiments on synthetic drifting streams show that initially created CFEs rapidly lose validity, whereas maintained CFEs preserve validity and local plausibility at a lower cost than repeated regeneration. --- ### SAPO: Step-Aligned Policy Optimization for Reasoning-Based Generative Recommendation Authors: Zaiyi Zheng, Liang Wu, Guanghui Min, Yaochen Zhu, Liangjie Hong, Chen Chen, Jundong Li Published: 2026-05-17 Categories: cs.AI arXiv: https://arxiv.org/abs/2605.17648v2 Generative recommendation treats next-item prediction as autoregressive item-identifier generation. Specifically, items are encoded as semantic identifiers (SIDs), which are short coarse-to-fine token sequences whose early tokens capture broad semantics and later tokens refine them. Recent work augments this paradigm with reasoning traces and optimizes them via reinforcement learning with verifiable rewards, typically outcome-reward algorithm with exact-match feedback on the generated SID. However, in large-catalog recommendation, exact-match feedback on the generated SID only reports whether the final item is correct; when a generated SID mismatches, outcome-reward cannot identify which SID-token prediction caused the mismatch and may penalize matched SID-token positions together with the mismatched position. We identify that the natural unit of credit assignment in this setting is a single reasoning step (one thinking block paired with one SID token). We instantiate this idea in SAPO (Step-Aligned Policy Optimization): rather than broadcasting one advantage to the whole response, SAPO computes a separate group-relative advantage for each reasoning step and applies it only to the corresponding thinking block and SID token. Across three real-world recommendation datasets, SAPO stabilizes reinforcement-learning training and consistently improves over existing generative recommendation baselines, with the largest gains where sparse exact-match feedback makes reasoning-step credit assignment important. Our results suggest that reinforcement-learning objectives for structured generation should mirror the decoder's own decomposition of the output. --- ### SAPO: Step-Aligned Policy Optimization for Reasoning-Based Generative Recommendation Authors: Zaiyi Zheng, Guanghui Min, Yaochen Zhu, Liang Wu, Liangjie Hong, Chen Chen, Jundong Li Published: 2026-05-17 Categories: cs.AI arXiv: https://arxiv.org/abs/2605.17648v1 Generative recommendation treats next-item prediction as autoregressive item-identifier generation. Specifically, items are encoded as semantic identifiers (SIDs), which are short coarse-to-fine token sequences whose early tokens capture broad semantics and later tokens refine them. Recent work augments this paradigm with reasoning traces and optimizes them via reinforcement learning with verifiable rewards, typically outcome-reward algorithm with exact-match feedback on the generated SID. However, in large-catalog recommendation, exact-match feedback on the generated SID only reports whether the final item is correct; when a generated SID mismatches, outcome-reward cannot identify which SID-token prediction caused the mismatch and may penalize matched SID-token positions together with the mismatched position. We identify that the natural unit of credit assignment in this setting is a single reasoning step (one thinking block paired with one SID token). We instantiate this idea in SAPO (Step-Aligned Policy Optimization): rather than broadcasting one advantage to the whole response, SAPO computes a separate group-relative advantage for each reasoning step and applies it only to the corresponding thinking block and SID token. Across three real-world recommendation datasets, SAPO stabilizes reinforcement-learning training and consistently improves over existing generative recommendation baselines, with the largest gains where sparse exact-match feedback makes reasoning-step credit assignment important. Our results suggest that reinforcement-learning objectives for structured generation should mirror the decoder's own decomposition of the output. --- ### TabKDE: Simple and Scalable Tabular Data Generation with Kernel Density Estimates Authors: Meysam Alishahi, Yan Zheng, Junpeng Wang, Chin-Chia Michael Yeh, Jeff M. Phillips Published: 2026-05-17 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.17642v1 Tabular data generation considers a large table with multiple columns -- each column comprised of numerical, categorical, or sometimes ordinal values. The goal is to produce new rows for the table that replicate the distribution of rows from the original data -- without just copying those initial rows. The last 4 years have seen enormous progress on this problem, mostly using computational expensive methods that employ one-hot encoding, VAEs, and diffusion. This paper describes a new approach to the problem of tabular data generation. By employing copula transformations and modeling the distribution as a kernel density estimate we can nearly match the accuracy and leakage-avoidance achievements of the previous methods, but with almost no training time. Our method is very scalable, and can be run on data sets orders of magnitude larger than prior state-of-the-art on a simple laptop. Moreover, because we employ kernel density estimates, we can store the model as a coreset of the original data -- we believe the first for generative modeling -- and as a result, require significantly less space as well. Our code is available here: \url{https://github.com/tabkde/tabkde-main} --- ### Causal Intervention-Based Memory Selection for Long-Horizon LLM Agents Authors: Saksham Sahai Srivastava Published: 2026-05-17 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2605.17641v1 Long-horizon LLM agents rely on persistent memory to support interactions across sessions, yet existing memory systems often retrieve context using semantic similarity or broad history inclusion, treating retrieved memories as uniformly useful. This assumption is fragile because memories may be topically related while remaining irrelevant, stale, or misleading. We propose Causal Memory Intervention (CMI), a causal memory-selection technique that estimates how candidate memories affect the model's answer under controlled interventions, selecting memories that improve task performance while suppressing unstable, irrelevant, or harmful ones. To evaluate this setting, we introduce Causal-LoCoMo, a causally annotated benchmark derived from long conversational data, where each example contains a user request, a structured memory bank, useful memories, irrelevant distractors, and synthetic harmful memories. We compare CMI against vector, graph, reflection, summary, full-history, and no-memory baselines. Results show that CMI achieves a stronger balance between answer quality and robustness to misleading memory, suggesting that reliable long-term memory requires selecting context based on causal usefulness rather than relevance alone. The full framework, benchmark construction code, and experimental pipeline are available at https://github.com/Saksham4796/causal-memory-intervention. --- ### MARQUIS: A Three-Stage Pipeline for Video Retrieval-Augmented Generation Authors: Debashish Chakraborty, Dengjia Zhang, Jialiang Jin, Hanting Liu, Katherine Guerrerio, Hanxiang Qin, Tyler Skow, Alexander Martin, Reno Kriz, Benjamin Van Durme Published: 2026-05-17 Categories: cs.IR, cs.CV arXiv: https://arxiv.org/abs/2605.17640v1 Retrieval-augmented generation from videos requires systems to retrieve relevant audiovisual evidence from large corpora and synthesize it into coherent, attributed text. Current approaches struggle at both ends: retrieval methods fail on complex, multi-faceted queries that cannot be captured by a single embedding, while generation methods lack the high-level reasoning needed to synthesize across multiple videos and face memory constraints over long, multi-video contexts. We present MARQUIS: a three-stage pipeline that addresses these limitations through (1) query expansion, fusion, and reranking, (2) calibrated structured evidence extraction, and (3) article generation from extracted evidence, optionally controlled by an RLM. On the MAGMaR2026 shared task, we improve retrieval performance from 0.195 to 0.759 (nDCG@10). For article generation, ITER-QA-BASE improves average human score from 3.09 to 3.83 over the CAG baseline, while MARQUIS-RLM achieves a human score of 3.30 and the strongest citation recall among non-QA systems. --- ### Temporal Decay of Co-Citation Predictability: A 20-Year Statute Retrieval Benchmark from 396M Ukrainian Court Citations Authors: Volodymyr Ovcharov Published: 2026-05-17 Categories: cs.CL, cs.IR arXiv: https://arxiv.org/abs/2605.17639v1 Co-citation structure is widely assumed to provide stable retrieval signal in legal information systems. We test this assumption longitudinally by constructing UA-StatuteRetrieval, a benchmark that measures co-citation predictability across 20 annual snapshots (2007-2026) of 396 million codex citations from 101 million Ukrainian court decisions. Using a leave-one-out protocol over the full bipartite citation graph, we find that Adamic-Adar MRR declines 33% on a fixed set of articles (from 0.43 to 0.29) and 47% under a train/test temporal split (from 0.51 to 0.27) confirming genuine temporal decay rather than compositional shift or evaluation artifact. The decay is non-uniform: criminal procedure maintains stable co-citation patterns (MRR ~0.40), while civil law degrades from 0.35 to 0.15, coinciding with the 2017 judicial reform. Hub articles (>100K citations) resist decay, but mid-frequency articles (1K-10K) -- the practical retrieval frontier lose half their predictability. A BM25 text baseline decays even faster (31%), and embedding drift analysis with E5-large reveals a 4.3% semantic shift in how articles are cited, providing a mechanistic explanation for the observed decay. The benchmark is released at https://huggingface.co/datasets/overthelex/ua-statute-retrieval. --- ### TouchMap-OR: Multi-View 3D Mapping of Hand-Surface Contacts Authors: Sophokles Ktistakis, Rui Wang, Bastian Grande, Hugo Sax Published: 2026-05-17 Categories: cs.CV arXiv: https://arxiv.org/abs/2605.17638v1 Hand-surface interactions between clinicians, patients, and medical equipment play a central role in pathogen transmission during medical procedures. However, these interactions remain largely unobserved, as current infection-prevention practices rely on manual observation and cannot reconstruct detailed contact histories. In this work we formulate the problem of identity-resolved hand-surface interaction reconstruction in operating rooms and introduce TouchMap-OR, a multi-view RGB-D vision system that models clinicians, articulated hand geometry, and the semantic structure of the clinical environment to infer when and where contacts occur. The system reconstructs globally consistent multi-person 3D skeleton tracks across cameras while estimating articulated MANO hand meshes from RGB observations aligned to depth data. Multi-view hand reconstructions are fused and associated with tracked clinicians to obtain consistent left and right hand trajectories. A semantic 3D model of the operating room is built from multi-view segmentation and depth fusion, enabling reconstructed hand trajectories to be mapped to specific surfaces, including medical equipment, movable objects, and patient body sites. Temporal hand-surface proximity is used to infer contact episodes describing which clinician touched which surface and when. We evaluate TouchMap-OR on recordings from three real anesthesia inductions with manually annotated contact events. TouchMap-OR achieves 0.75 binary contact F1, outperforming tracking-based baselines while maintaining comparable multi-person tracking accuracy and achieving 0.96 identity attribution accuracy. --- ### WebGameBench: Requirement-to-Application Evaluation for Coding Agents via Browser-Native Games Authors: Wenyu Zhang, Guoliang You, Tianlun, Haotian Zhao, Tianshu Zhu, Haoran Wang, Xiaoxuan Tang, Mingyang Dai, Jingnan Gu, Daxiang Dong, Jianmin Wu Published: 2026-05-17 Categories: cs.AI arXiv: https://arxiv.org/abs/2605.17637v2 Coding agents are increasingly used as application builders, yet many evaluations still focus on source code, repository-level tests, or intermediate traces rather than the delivered application. We introduce WebGameBench, a requirement-to-application benchmark that evaluates whether coding agents can turn a frozen Structured WebGame Specification into a browser-accessible game. Browser-native games provide a compact but behavior-dense testbed: even simple games require coordinated input handling, spatial mapping, rule execution, state transitions, terminal conditions, restart behavior, and visible feedback. In WebGameBench, each generated artifact is built, served, and exposed as a browser-accessible application under a unified deployment protocol. A runtime evaluator then interacts with the delivered game in a real browser and assigns a three-way label: EXCELLENT, USABLE, or UNUSABLE. On a human-reviewed subset, the runtime label is broadly aligned with human gameplay review under the Usable-rate criterion. Across 111 tasks, 12 coding agents, and 14 evaluation configurations, WebGameBench separates current systems: the best configuration reaches a 76.9% usable rate but only a 20.2% excellent rate. This gap shows that crossing the minimum playable-delivery threshold is still far from complete requirement satisfaction. To our knowledge, WebGameBench is the first requirement-to-application benchmark for browser-native game delivery that validates delivered-application runtime labels against independent human gameplay review under the Usable-rate criterion. --- ### ML-based Fast Simulation of FARICH Responses Authors: Foma Shipilov, Alexander Barnyakov, Artem Ivanov, Fedor Ratnikov Published: 2026-05-17 Categories: hep-ex, cs.LG arXiv: https://arxiv.org/abs/2605.17635v2 A fast simulation of the detector response is a vital task in high-energy physics (HEP). Traditional Monte-Carlo methods form the backbone of modern particle physics simulation software but are computationally expensive. We present a machine-learning-based approach to fast simulation of the Focusing Aerogel Ring Imaging Cherenkov (FARICH) detector response. Given a particle track and momentum, the goal is to generate realistic samples of photon hits on the detector matrix. We propose a conditional Generative Adversarial Network (cGAN) with a lightweight convolutional architecture that reproduces the projected detector response conditioned on particle parameters. We compare the cGAN against a linear statistical baseline using metrics applied to probability maps and to the reconstructed velocity distributions. The cGAN produces realistic samples and provides a significant speed-up over Monte-Carlo simulation. --- ### AI Agents May Always Fall for Prompt Injections Authors: Sahar Abdelnabi, Eugene Bagdasarian Published: 2026-05-17 Categories: cs.CR, cs.CL, cs.CY arXiv: https://arxiv.org/abs/2605.17634v1 Prompt injection is the most critical vulnerability in deployed AI agents. Despite recent progress, we show that the prevailing defense paradigm (data-instruction separation) both fails to detect attacks that operate through contextual manipulation and degrades contextually appropriate behavior. We then recast prompt injection via the lens of Contextual Integrity (CI), a privacy theory that judges information flow compliance with contextual norms. This explains types of attacks that current defenses attempt to patch and predict advanced ones future agents will face. We develop unique benign and attack scenarios that force an agent to violate the norms by (1) misrepresenting the flow, (2) manipulating norms, or (3) mixing multiple flows. This reframing suggests an impossibility result: an adversary can always construct a context under which a blocked flow appears legitimate, or a defender who tightens norms will block genuinely legitimate flows. Our findings suggest that current research addresses a shrinking fraction of future attack surfaces. Instead, through CI, we offer a principled framework for evaluating context-sensitive failures, and designing CI-aware alignment for the frontier autonomous agents. --- ### SparseSAM: Structured Sparsification of Activations in Segment Anything Models Authors: Hoai-Chau Tran, Chi H. Nguyen, Duy M. H. Nguyen, Mathias Niepert, Fan Lai, Khoa D. Doan Published: 2026-05-17 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2605.17633v1 The Segment Anything Model (SAM) achieves strong open-vocabulary segmentation, but its ViT-based image encoders dominate inference latency and memory. Existing activation compression methods, such as token merging, reduce the token length to process, yet introduce non-trivial runtime overhead and encounter catastrophic quality drop under high compression. Other methods applying Sparse Attention focus on attention alone, leaving the MLP fully dense and capping achievable speedup. We propose SparseSAM, a (i) training-free structured sparsification framework that jointly accelerates attention and MLP layers while preserving token identity. SparseSAM introduces (ii) Stripe-Sort Attention, which uses a deterministic Z-order permutation to transform dense attention into static hardware-friendly sparse patterns, eliminating dynamic masking overhead. SparseSAM further introduces a (iii) Residual-Consistency MLP that routes only informative tokens through the MLP while propagating remaining tokens through the residual pathway. Across four segmentation benchmarks, SparseSAM loses only 0.004 mIoU at a 0.4 density and 0.021 mIoU at 0.3, a 2.10x reduction in accuracy loss versus token merging advances, while achieving 2x faster inference and 2.8x memory reduction. --- ### SegRAG: Training-Free Retrieval-Augmented Semantic Segmentation Authors: Abderrahmene Boudiaf, Irfan Hussain, Sajid Javed Published: 2026-05-17 Categories: cs.CV arXiv: https://arxiv.org/abs/2605.17630v2 Open-vocabulary segmentation models such as SAM3 perform well across broad categories via text prompting, yet degrade when target classes are visually underrepresented in pretraining or depart from canonical depictions-limitations text prompts cannot resolve spatially. We present SegRAG, a training-free retrieval-augmented segmentation framework that grounds SAM3 with class-specific point prompts derived from a curated DINOv3 feature bank. Offline, dense patch-level descriptors are extracted from annotated references and filtered by Intra-Class Cohesion Distillation (ICCD), retaining only prototypes that reliably retrieve within-class foreground. At inference, Topographic Similarity Grounding (TSG) computes a cosine-similarity landscape against retrieved prototypes, identifies coherent high-confidence regions via connected-component analysis, and extracts peak locations through non-maximum suppression. The resulting point prompts are delivered jointly with class-name text in a single SAM3 forward pass. On four standard benchmarks, SegRAG consistently outperforms the text-only baseline, gaining up to +3.92 mIoU on LVIS. On AgML agricultural benchmarks under zero-shot domain transfer, it raises mean IoU from 25.27 to 59.24 (+33.97) and recovers individual classes from zero to over 95 mIoU. Ablations confirm that ICCD, TSG, and joint prompting each contribute independently and compound when combined. Code is available at (https://github.com/boudiafA/SegRAG). --- ### Verifier-Guided Code Translation via Meta-Step Decoding Authors: Tianyang Zhou, Somesh Jha, Mihai Christodorescu, Kirill Levchenko, Varun Chandrasekaran Published: 2026-05-17 Categories: cs.LG, cs.SE arXiv: https://arxiv.org/abs/2605.17626v1 Test-time scaling is an important mechanism for improving large language models, especially on tasks with deterministic verifiers. Code translation is a canonical example: the source program constrains valid outputs, while compilers, type check- ers, and behavioral checks provide exact pass/fail feedback. Existing approaches typically apply these verifiers only after generation, which is inefficient because early errors corrupt the autoregressive context and are rarely corrected later. We introduce Decoding Time Verification (DTV), a framework that treats structural boundaries as meta steps for verifier-guided decoding. DTV interleaves generation with verifier calls under a state-machine controller that enforces valid prefixes, using structural-boundary checks and structure-aware rollback to prevent error propagation while reducing wasted tokens. We evaluate DTV on C-to-Rust and JavaScript-to-TypeScript translation. Using Qwen3-4B as the primary generator under matched token budgets, DTV improves pass rates from 72.3% to 82.0% on C-to-Rust and from 33.3% to 46.0% on JavaScript-to-TypeScript relative to matched self-refinement baselines, while using fewer tokens per case; the same trend largely transfers to Gemma-4-E4B. In the evaluated cost-matched grid, DTV achieves a more favorable pass-rate-cost tradeoff than post-hoc verification or sampling-based scaling. These results show that verifier-guided decoding is an effective use of inference-time compute for code translation. --- ### Episodic-Semantic Memory Architecture for Long-Horizon Scientific Agents Authors: Nikola Milosevic Published: 2026-05-17 Categories: cs.AI arXiv: https://arxiv.org/abs/2605.17625v1 As Large Language Models (LLMs) evolve into persistent scientific collaborators, context window saturation has emerged as a critical bottleneck. Scientific workflows involving iterative data analysis and hypothesis refinement rapidly saturate even extended contexts with dense technical content, while monolithic approaches suffer from quadratic cost scaling and cognitive degradation. We evaluate a Dual Process Memory Architecture that decouples immediate episodic needs (constant 10-message window) from long-term consolidated knowledge (growing at approximately 3 tokens/message). Unlike prior social agent memory systems, our domain-specific consolidation addresses contradictory parameter evolution, multi-hop reasoning across experimental phases, and precise technical fact retention. Through large-scale evaluation spanning 15,000 messages with cross-model validation across six LLMs from three families (OpenAI, Anthropic, Google), totaling 1,440 queries, we establish three key findings. First, while full-context models fail at 10,000 messages due to context overflow, our system maintains 70-85% accuracy with 1-2 second latency using 62% fewer tokens (45,434 vs 120,000+ limit). Second, cross-model validation reveals architecture-level trade-offs independent of specific LLMs: Dual Process excels at numeric/temporal queries (65-90% accuracy) while RAG excels at historical retrieval (60-85%), suggesting complementary deployment strategies. Third, we identify a "Sim-to-Real" gap where synthetic tests maintain constant memory but realistic workflows exhibit linear growth (about 3 tokens/message), with consolidation quality emerging as the primary scalability bottleneck. The architecture successfully manages profiles with 14,000+ scientific facts (125k tokens), demonstrating that domain-specific memory consolidation enables sustained operation beyond full-context limits. --- ### Multi-task learning on partially labeled datasets via invariant/equivariant semi-supervised learning Authors: Miquel Martí i Rabadán, Alessandro Pieropan, Hossein Azizpour, Atsuto Maki Published: 2026-05-17 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2605.17624v1 We investigate the potential of invariant and equivariant semi-supervised learning for addressing the challenges of training multi-task models on partially labeled datasets with differently structured output tasks. Specifically, we use the popular FixMatch method for invariant semi-supervised learning and its equivariant extension Dense FixMatch. We evaluate their performance on the Cityscapes and BDD100K datasets in the context of the prevalent object detection and semantic segmentation tasks in computer vision. We consider varying sizes of the subsets annotated for each task and different overlaps among them. Our results for both invariant and equivariant semi-supervised learning outperform supervised baselines in most situations, with the most significant improvements observed when fewer labeled samples are available for a task and generally better results for the latter approach. Our study suggests that invariant/equivariant learning is a promising general direction for multi-task learning from limited labeled data. --- ### Prediction of Challenging Behaviors Associated with Profound Autism in a Classroom Setting Using Wearable Sensors Authors: Yadhu Kartha, Conor Anderson, Jenny Foster, Theresa Hamlin, Johanna Lantz, Ryan Lay, Juergen Hahn, Gari D. Clifford, Hyeokhyen Kwon Published: 2026-05-17 Categories: cs.AI arXiv: https://arxiv.org/abs/2605.17618v2 Autism Spectrum Disorder (ASD) is characterized by challenges with social interaction and communication and by restricted or repetitive patterns of thought and behavior, with significant variability in presentation. Approximately a quarter of children with ASD are classified as having profound autism, who often exhibit challenging behaviors, such as self-injurious behavior, aggression, elopement, or pica, that pose serious safety risks and disrupt learning in educational settings. Prior work has applied wearable sensors and machine learning to detect challenging behaviors, but has been largely confined to controlled laboratory environments. This work demonstrates that predicting challenging behavior episodes is feasible in a real-world special education classroom. We collected approximately 110.7 hours of labeled multimodal wearable data comprising accelerometry, electrodermal activity (EDA), and skin temperature from 9 children and young adults aged 10 to 21 years across standard classroom sessions. We fine-tuned state-of-the-art foundation models for multimodal wearable time-series analysis and show that challenging behavior episodes can be predicted up to 10 minutes in advance with an AUC-ROC of 0.78. These results establish a concrete foundation for developing proactive in-class intervention systems that enable teachers to minimize the safety risks of challenging behaviors in special education classrooms --- ### GraphMind: From Operational Traces to Self-Evolving Workflow Automation Authors: Yiwen Zhu, Joyce Cahoon, Anna Pavlenko, Qiushi Bai, Nima Shahbazi, Divya Vermareddy, Meina Wang, Mathieu Demarne, Swati Bararia, Wenjing Wang, Hemkesh Vijaya Kumar, Hannah Lerner et al. Published: 2026-05-17 Categories: cs.AI arXiv: https://arxiv.org/abs/2605.17617v2 Complex operational workflows coordinating personnel, tools, and information are central to system operations, yet end-to-end automation remains challenging due to extensive human input requirements and limited ability to adapt over time. We present GraphMind, a system that constructs, executes, and evolves action-centric workflow graphs with minimal human effort. The system operates in three phases. First, a scalable offline pipeline extracts structured workflow graphs from large volumes of human resolution traces, capturing problems, actions, and their causal relationships. Second, an online multi-agent traversal engine navigates the graph to dynamically construct and execute workflows, combining graph-guided retrieval with LLM-driven reasoning at each step. Third, Adaptive Traversal Reinforcement (ATR) reinforces successful traversal paths, enabling execution-informed graph adaptation. GraphMind has been deployed across four production cloud database services for incident investigation. Evaluated on 93 held-out incidents and validated via blind expert review, the system outperforms an Agentic Summary-RAG baseline in mitigation reach, hallucination rate, and diagnostic throughput while requiring 8x less retrieval context. The ATR layer reduces hallucination rate by 26%, demonstrating that workflow graphs can learn from execution feedback. A 12-week field study confirms practical value: 97% of scored conversations yield actionable results within interactive latency. --- ### VeriCache: Turning Lossy KV Cache into Lossless LLM Inference Authors: Jiayi Yao, Samuel Shen, Kuntai Du, Shaoting Feng, Dongjoo Seo, Rui Zhang, Yuyang Huang, Yuhan Liu, Shan Lu, Junchen Jiang Published: 2026-05-17 Categories: cs.AR, cs.LG arXiv: https://arxiv.org/abs/2605.17613v1 The large size of the KV cache has become a major bottleneck for serving LLMs with increasing context lengths. In response, many KV cache compression methods, such as token dropping and quantization, have been proposed. However, almost all of these methods are inherently lossy-despite minimal accuracy degradation for short outputs, their outputs increasingly diverge from full-KV-cache outputs as more tokens are decoded, which leads to catastrophic failures in code generation and tool calling. We present VeriCache, the first inference framework that ensures the same output as full-KV-cache decoding but largely preserves the high decoding throughput of a range of KV cache compression algorithms. VeriCache uses the compressed KV cache to draft tokens, then verifies them against the full KV cache. While it may seem like just speculative decoding, VeriCache requires addressing a key system challenge to work-keeping the full KV cache out of GPU memory and minimizing the overhead of swapping it in for verification. The insight is two-fold: (1) compressed-KV decoding can be parallelized with full-KV swap, because one is HBM-bandwidth-bound and the other is PCIe/network-bound, and (2) the compressed KV cache often produces output similar to the full KV cache, allowing a long drafting horizon to amortize each full-KV swap. VeriCache applies to both long-context decoding and remote prefix caching, supports a broad family of token-dropping and quantization methods through a uniform compressor interface, and composes with traditional speculative decoding. Experimental results show that VeriCache achieves up to 4X higher throughput than full-KV inference while producing identical outputs. --- ### A Feature-Driven Framework for Software Fault Prediction Authors: Ahmad Nauman Ghazi, Nagajyothi Devarapalli, Ashir Javeed, Sadi Alawadi, Fahed Alkhabbas, Khalid AlKharabsheh Published: 2026-05-17 Categories: cs.SE, cs.LG arXiv: https://arxiv.org/abs/2605.17611v1 Software fault prediction (SFP) is a critical task in software engineering, enabling early identification of faults in modules to improve software quality and reduce maintenance costs. This research investigates the combined effects of feature selection and parameter tuning on the performance of machine learning (ML) models for SFP. This study evaluates the interaction between feature selection methods, including correlation-based feature selection (CFS), recursive feature elimination (RFE), mutual information (MI), and L1 regularization, where hyperparameter tuning techniques such as grid search, randomized search, and genetic algorithm (GA) are used for optimization of ML algorithms, including random forest (RF), logistic regression (LR), and support vector machines (SVM) for optimized fault prediction performance. The combined application of CFS and GA yielded the highest accuracy, achieving 88.40% with RF, representing an improvement of 18% over baseline models without feature selection or tuning. Feature selection reduced dimensionality and identified critical attributes such as weighted methods per Class (WMC) and coupling between objects (CBO), while iterative parameter tuning optimized model alignment to these feature sets. Notably, the proposed methods demonstrated robustness, with minimal cross-validation variability (+-1.0%), and efficiency, reducing training times in univariate methods such as L1 regularization. --- ### SafeLens: Deliberate and Efficient Video Guardrails with Fast-and-Slow Screening Authors: Shahriar Kabir Nahin, Hadi Askari, Muhao Chen, Anshuman Chhabra Published: 2026-05-17 Categories: cs.CV, cs.CL arXiv: https://arxiv.org/abs/2605.17610v3 The rapid growth of online video platforms and AI-generated content has made reliable video guardrails a key challenge for safety and real-world deployment. While most videos can be screened through fast pattern recognition, a small subset requires deeper reasoning over temporally complex content and nuanced policy constraints. Existing approaches typically rely on large vision-language models applied uniformly across all inputs, resulting in high inference costs and inefficient allocation of computation. We propose SafeLens, a video guardrail framework that introduces a fast-and-slow inference architecture for efficient and accurate content moderation with variable computational cost across inputs. Additionally, we construct a high-quality dataset by applying influence-guided filtering to the SafeWatch Dataset, retaining only 2.4% of the original data. To further address limitations of training-time scaling, we enable test-time reasoning by augmenting the filtered data with structured Chain-of-Thought traces. Across real-world and AI-generated video benchmarks, SafeLens achieves state-of-the-art performance, outperforming strong open-source video guardrails (e.g., SafeWatch-8B, OmniGuard-7B) and closed-source models (e.g., GPT-5.4, Gemini-3.1-pro) while significantly reducing inference cost, demonstrating that efficient design serves to be more effective than scaling data or model size alone. --- ### SafeLens: Deliberate and Efficient Video Guardrails with Fast-and-Slow Screening Authors: Shahriar Kabir Nahin, Hadi Askari, Muhao Chen, Anshuman Chhabra Published: 2026-05-17 Categories: cs.CV, cs.CL arXiv: https://arxiv.org/abs/2605.17610v1 The rapid growth of online video platforms and AI-generated content has made reliable video guardrails a key challenge for safety and real-world deployment. While most videos can be screened through fast pattern recognition, a small subset requires deeper reasoning over temporally complex content and nuanced policy constraints. Existing approaches typically rely on large vision-language models applied uniformly across all inputs, resulting in high inference costs and inefficient allocation of computation. We propose SafeLens, a video guardrail framework that introduces a fast-and-slow inference architecture for efficient and accurate content moderation with variable computational cost across inputs. Additionally, we construct a high-quality dataset by applying influence-guided filtering to the SafeWatch Dataset, retaining only 2.4% of the original data. To further address limitations of training-time scaling, we enable test-time reasoning by augmenting the filtered data with structured Chain-of-Thought traces. Across real-world and AI-generated video benchmarks, SafeLens achieves state-of-the-art performance, outperforming strong open-source video guardrails (e.g., SafeWatch-8B, OmniGuard-7B) and closed-source models (e.g., GPT-5.4, Gemini-3.1-pro) while significantly reducing inference cost, demonstrating that efficient design serves to be more effective than scaling data or model size alone. --- ### Adaptive Generate-Rank-Verify: Inference-Time Search with Costly Verification Authors: Shaddin Dughmi, Mahdi Haghifam, Yusuf Hakan Kalayci Published: 2026-05-17 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.17609v2 Many inference-time language-model pipelines combine a cheap reward signal with an expensive verifier, such as exact answer checking in mathematical reasoning or hidden-test execution in code generation. We formalize this setting using a learning-theoretic lens as generative active search: a cost-sensitive first-positive search problem in which a policy adaptively samples candidates from an unknown distribution, observes cheap scores, and pays for verifier labels until it finds a positive example. For a fixed prompt, the generator and reward model induce two unknown objects: a distribution over reward scores and a score-conditioned success function. When these quantities are known, we characterize the distribution-aware optimal policy using a dynamic programming approach. In the realistic and practical setting where both the score distribution and success function are unknown, we propose ADAP, a shellwise adaptive generate-rank-verify algorithm that progressively increases the number of sampled responses and top-ranked verifications. Under the monotonicity assumption that higher reward scores are no less likely to pass verification, we show that ADAP achieves expected cost within a constant factor of the distribution-aware optimum. We complement this result with learning-theoretic lower bounds, based on a centered star number, showing that structural assumptions on the score--label relationship are necessary. Experiments on mathematical reasoning and competitive programming validate the predicted advantage over both fixed non-adaptive policies and difficulty-adaptive baselines. --- ### Bayesian-Monte Carlo Schedule Updating for Construction Digital Twins: A Probabilistic Framework for Dynamic Project Forecasting Authors: Atena Khoshkonesh, Mohsen Mohammadagha, Vinayak Kaushal, Navid Ebrahimi Published: 2026-05-17 Categories: cs.CE, cs.AI arXiv: https://arxiv.org/abs/2605.17608v1 Construction projects frequently experience schedule delays and forecasting uncertainty due to variability in labor productivity, material availability, weather conditions, and project coordination. Conventional deterministic scheduling methods such as the Critical Path Method (CPM) assume fixed activity durations and therefore cannot adequately represent dynamic project uncertainty. This study presents a Bayesian-Monte Carlo probabilistic schedule updating framework for construction digital twin environments. The proposed methodology integrates stochastic activity-duration modeling, Bayesian recursive updating, Monte Carlo simulation, and uncertainty propagation within a unified computational framework for adaptive schedule forecasting. Activity durations are modeled using lognormal probability distributions and continuously updated through Bayesian inference as new project observations become available. Monte Carlo simulation is then used to propagate updated uncertainty throughout project networks and generate probabilistic completion-time forecasts, delay-risk estimates, and activity criticality measures. Simulation experiments using PSPLIB benchmark project networks demonstrate that the proposed framework improves forecasting accuracy and uncertainty representation compared with deterministic CPM and static probabilistic scheduling approaches. The framework further supports adaptive project forecasting through integration of BIM reports, drone observations, IoT telemetry, productivity logs, and site monitoring data. --- ### The Neural Tangent Kernel for Classification Authors: Jonathan Plenk, Sergio Calvo-Ordonez, Alvaro Cartea, Yarin Gal, Mark van der Wilk, Kamil Ciosek Published: 2026-05-17 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.17606v2 In wide neural networks, the Neural Tangent Kernel (NTK) remains approximately constant during training, providing a powerful theoretical tool for studying training dynamics, generalization, and connections to kernel methods. However, this theory is largely restricted to regression losses. It was previously thought that training on a classification loss, or more generally losses involving nonlinear output transformations, breaks this property, leading to divergent logits and a breakdown of the linearization. In this paper, we extend NTK theory to classification by identifying conditions under which wide neural networks remain in the lazy training regime. We show that parameter-space regularization ensures a constant NTK during training for cross-entropy loss, while in the absence of regularization the regime is recovered when targets are non-degenerate, i.e. when all classes have strictly positive probability. Under these conditions, training is well-approximated by the linearized model, yielding an explicit characterization of the solution in terms of the NTK. We further analyze the distribution of trained predictors induced by random initialization and relate this notion of model uncertainty to Bayesian methods. --- ### Venom: A PyTorch Generative Modeling Toolkit Authors: Liang Yan Published: 2026-05-17 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.17605v1 Modern generative modeling has grown into a broad collection of related but often separately implemented paradigms, including denoising diffusion models, score-based stochastic differential equations, flow matching, variational autoencoders, normalizing flows, adversarial models, and energy-based models. For newcomers, this fragmentation makes it difficult to compare training objectives, inference procedures, sampling algorithms, and conditioning mechanisms within a single coherent codebase. We introduce V ENOM, an educational PyTorch toolkit that implements representative generative modeling families under a unified, MNIST-first interface. V ENOM emphasizes breadth, readability, reproducible entry points, and consistent training and sampling APIs rather than large-scale performance engineering. The package currently includes diffusion and score-based models, flow matching and one-step generators, variational autoencoders, normalizing flows, generative adversarial networks, and energy-based models. It provides separate training and sampling scripts, classifier and classifier-free guidance examples, bilingual tutorial notebooks, and a model-family organization that supports teaching, prototyping, and lightweight benchmarking. --- ### Longwang: Zero-Shot Global Spatiotemporal Precipitation Downscaling with a Latent Generative Prior Authors: Yue Wang, Daniele Visioni Published: 2026-05-17 Categories: physics.ao-ph, cs.LG arXiv: https://arxiv.org/abs/2605.17603v1 High-resolution precipitation information is essential for climate impact assessment, yet global climate models remain too coarse to resolve key small-scale processes. Existing machine learning downscaling methods often require paired low- and high-resolution data for supervised learning, are tied to fixed regions or scale factors during inference, and can be computationally expensive to train and run in physical space. Here we introduce Longwang, a zero-shot latent generative framework for global spatiotemporal precipitation downscaling. Longwang learns a context-conditioned latent generative prior and combines it with a physically informed observation operator through posterior sampling, enabling daily O(10 km) precipitation fields to be generated from monthly O(100 km) inputs. On ERA5 reanalysis, Longwang outperforms standard posterior sampling with an unconditional generative prior in reconstructing fine-scale spatial patterns, preserving temporal coherence, and recovering extreme precipitation intensities. The framework further generalizes to historical climate simulations and future climate projections under substantial distribution shift. --- ### AutoRubric-T2I: Robust Rule-Based Reward Model for Text-to-Image Alignment Authors: Kuei-Chun Kao, Daixuan Huo, Yuanhao Ban, Cho-Jui Hsieh Published: 2026-05-17 Categories: cs.AI, cs.CV, cs.LG arXiv: https://arxiv.org/abs/2605.17602v2 Aligning Text-to-Image (T2I) generation models with human preferences increasingly relies on image reward models that score or rank generated images according to prompt alignment and perceptual quality. Existing reward models are commonly trained as Bradley-Terry (BT) preference models on large-scale human preference corpora, making them costly to train, difficult to adapt, and opaque in their evaluation criteria. Meanwhile, Vision-Language Model (VLM) judges can provide more fine-grained assessments through textual rubrics, but their manually designed or heuristically generated scoring rules may fail to reliably reflect human preferences. In this paper, we propose AutoRubric-T2I, the first rubric learning framework in T2I that automatically synthesizes and selects explicit rubrics for guiding VLM judges. AutoRubric-T2I first synthesizes reasoning traces from preference pairs into candidate rubrics, then uses a VLM judge to score paired images under each rubric, producing pairwise rubric-score differences for preference learning. To remove noisy and redundant rules, we further employ a $\ell_1$-Regularized Logistic Regression Refiner, which selects the Top-$N$ most discriminative rubrics. Extensive evaluations show that AutoRubric-T2I produces high-quality, interpretable reward signals using less than 0.01% of the annotated preference data, substantially reducing the need for large-scale reward-model training. On image reward benchmarks such as MMRB2, AutoRubric-T2I outperforms strong reward model baselines. We further validate AutoRubric-T2I as an RL reward on downstream T2I tasks, including TIIF and UniGenBench++, where it improves generation quality over scalar reward models using the Flow-GRPO pipeline on diffusion models. --- ### Mixture of Experts for Low-Resource LLMs Authors: Ori Bar Joseph, Smadar Arvatz, Noam Kayzer, Dan Revital, Sarel Weinberger Published: 2026-05-17 Categories: cs.CL arXiv: https://arxiv.org/abs/2605.17598v1 Mixture-of-Experts (MoE) architectures enable efficient model scaling, yet expert routing behavior across underrepresented languages remains poorly understood. We analyze routing dynamics in two architecturally distinct MoE models -- a pure Transformer (Qwen3-30B-A3B) and a hybrid Mamba-Transformer (Nemotron-3-Nano-30B-A3B) -- using Hebrew as a morphologically rich, low-resource testbed. Both pre-trained models exhibit \emph{deep-layer routing collapse}: usage entropy drops sharply in final layers and tokens concentrate on a narrow expert subset, a pattern largely absent for English. Continual pre-training (CPT) on balanced bilingual data substantially corrects this imbalance, increasing entropy and shifting routing toward shared, language-agnostic experts; supervised fine-tuning (SFT) alone achieves less complete correction. Extending the analysis to Japanese reveals quantitatively consistent collapse signatures, providing cross-linguistic evidence that the phenomenon is a systematic consequence of pre-training underrepresentation rather than any language-intrinsic property. Routing improvements correlate with consistent downstream benchmark gains, positioning routing entropy and expert specialization as principled diagnostics for multilingual capacity in MoE systems. --- ### NeuSymMS: A Hybrid Neuro-Symbolic Memory System for Persistent, Self-Curating LLM Agents Authors: Mujahid Sultan, Sri Thuraisamy, Daya Rajaratnam Published: 2026-05-17 Categories: cs.AI arXiv: https://arxiv.org/abs/2605.17596v2 We present NeuSymMS, an adaptive memory system that enables large language model (LLM) agents to learn, remember, and reason about users across sessions via a hybrid neuro-symbolic architecture. NeuSymMS couples neural fact extraction from unstructured dialogue using LLMs and a CLIPS-based expert system that classifies, deduplicates, and reconciles facts under explicit lifecycle rules. The system represents knowledge as subject-relation-value triples stored in relational database management system. It supports user/agents/agent-to-agent scoping, and implements a dual-horizon (short-term and long-term) memory model. IT leverages access-based promotion and time-based pruning of the memory on both horizpons. NeuSymMS maintains continuity of memory while avoiding context-window bloat and cross-entity contamination. We argue that this architecture offers a practical path to trustworthy, auditable memory for production agentic systems and discuss its novelty relative to log retrieval, summarization, and key-value approaches. --- ### Error-Decomposed Class-Conditional Fusion for Statistically Guaranteed Hard-Category Robust Perception Authors: Guowei Luo, Ziqi Shi, Zhao Xie Published: 2026-05-17 Categories: cs.CV arXiv: https://arxiv.org/abs/2605.17591v1 Aggregate object detection metrics inherently mask catastrophic and repeatable failures in operationally critical, long-tail minority classes. This paper formally defines this pervasive vulnerability as the Hard-Category Reliability Problem (HCRP): the fundamental architectural challenge of strictly rectifying vulnerable categories without compromising the performance boundaries of stable classes under stringent protocols. To systematically dismantle this limitation, we propose Error-Decomposed Class-Conditional Fusion (ED-CCF), an elegant decision-layer inference framework. Diverging from heuristic global post-processing, ED-CCF projects predictions into a sophisticated quad-state error taxonomy, dynamically activating calibration pathways exclusively upon rigorous empirical justification. On a highly constrained 600-image validation benchmark, isolating cz as the critical vulnerability (HCEC=0.86, BSR=0.14), our framework achieves a targeted breakthrough: it elevates cz mAP50 from 0.089343 to 0.109353 (a massive +22.4% relative surge) while flawlessly preserving the Pareto optimality of global stability (raising all mAP50 from 0.581925 to 0.584864). Backed by exhaustive validation across 50 paired subset trials demonstrating an overwhelming 96% win rate and strict Bonferroni-corrected Wilcoxon significance (p<0.05), this work fundamentally redefines output-level fusion as an auditable, statistically guaranteed paradigm for safety-critical visual perception. --- ### Form and Function: Machine Unlearning as a Problem of Misaligned States Authors: Kennon Stewart Published: 2026-05-17 Categories: cs.LG, math.OC arXiv: https://arxiv.org/abs/2605.17590v1 We formulate machine unlearning for online L-BFGS as a counterfactual state-alignment problem. Given an actual event stream and a deletion-edited counterfactual stream, the target of unlearning is the optimizer state that would have arisen had the deleted samples never been processed. We introduce state-aware metrics that separately measure parameter error, memory-operator error, combined state error, and update-direction error. The memory metric compares the inverse-Hessian actions induced by the o-L-BFGS memory, rather than treating curvature pairs as of finite influence. Under convexity assumptions, we derive a recursive bound on counterfactual state deviation. We then evaluate a state-aware benchmark of deletion interventions, including memory-only and parameter-only corrections, against an counterfactual oracle model. These results show that unlearning for online L-BFGS is not merely a parameter-correction problem: it requires alignment with a realizable counterfactual optimizer state. --- ### MSIQ: Moment-based Scale-Invariant Quality Measure for Single Image Super-Resolution Authors: Leonid Bedratyuk Published: 2026-05-17 Categories: cs.CV arXiv: https://arxiv.org/abs/2605.17588v1 Assessing the quality of single image super-resolution (SISR) results remains an open methodological problem. Common full-reference metrics (PSNR, SSIM, LPIPS) do not explicitly evaluate the preservation of the geometric structure of images, which is critical for the correctness of scale-based reconstruction. In addition, they require the forced alignment of images to the same size (\textit{forced resizing}), which introduces an external interpolation error into the evaluation process. This paper proposes a diagnostic scale-invariant quality measure, MSIQ (\textit{Moment-based Scale-Invariant Quality}), based on the comparison of normalized central geometric moments of two images. MSIQ enables direct comparison of images with different spatial resolutions without resizing, is mathematically deterministic (\textit{model-free}), and has an analytical form. To provide a theoretical basis for the approach, we introduce a conceptual distinction between the ability of metrics to monotonically track degradation (\textit{tracking ability}) and their geometric selectivity (\textit{geometric specificity}). The experimental validation confirmed the stability of MSIQ under uniform scaling and, at the same time, revealed the high sensitivity of traditional metrics to the choice of interpolation method. The results show that MSIQ has pronounced geometric selectivity: the proposed measure effectively separates geometric deformations from non-geometric artifacts, in particular JPEG compression, unlike pixel-based and perceptual metrics. It is also shown that the response of MSIQ to structural perturbations remains stable across different classes of SR algorithms, including DNN models with different architectures. The proposed measure is a complementary diagnostic tool for domains where geometric fidelity has priority, in particular medical imaging and remote sensing. --- ### Scale-Equivariant Generative Forecasting: Weight-Tied Dilated Convolutions, Wavelet Scattering Inputs, and Spectral-Consistency Training for Self-Similar Time Series Authors: Andrea Morandi Published: 2026-05-17 Categories: cs.LG, cs.CE arXiv: https://arxiv.org/abs/2605.17582v1 Many natural and engineered time series -- equity returns, climate anomalies, turbulent velocities, neural recordings, packet-level network traffic -- are approximately self-similar: their horizon-$T$ distribution is tied to the horizon-$1$ distribution by one scaling exponent $H$. Standard deep generative sequence models (transformers, dilated TCNs, the WaveNet family) ignore this. Their receptive fields are wide, but kernel parameters live independently at every dilation level, yielding a multi-scale architecture, not a scale-equivariant one. We make three contributions. First, we give a precise definition of discrete scale equivariance for 1D causal networks and prove that dyadic dilation commutes (up to boundary effects) with any dilated-convolution stack whose kernel weights are shared across levels. Tying the kernel shrinks the convolutional parameter budget by an $L$-fold factor (where $L$ is depth) and hard-wires self-similarity in as an inductive bias. Second, we wrap this Scale-Equivariant WaveNet (SE-WaveNet) backbone in three components that carry the same prior: a one-level Daubechies-4 wavelet input, a Hurst-FiLM block exposing the local scaling exponent, and a spectral-consistency training term targeting the $|f|^{-(2H+1)}$ power-law spectrum. The head is a conditional normalising flow, chosen to preserve equivariance. Third, on 30 years of S&P 500 daily log-returns, SE-WaveNet samples reproduce the empirical scaling-collapse diagnostic on the Allan-Variance top-25 universe (median $\mathcal{C}^\star = 0.020$), while a vanilla WaveNet at matched capacity does not ($\geq 0.06$). NLL, KS-calibration, and tail energy distance tie or beat the baseline, with $L\times$ fewer convolutional parameters. --- ### Topological Data Analysis combined with Machine Learning for Predicting Permeability of Porous Media Authors: Ebru Dagdelen, Catherin Neena Lalu, Aakash Karlekar, Manav Arora, Matthew Illingworth, Jonathan Jaquette, Linda Cummings, Lou Kondic Published: 2026-05-17 Categories: cond-mat.soft, cs.LG arXiv: https://arxiv.org/abs/2605.17581v2 Flow in porous media is difficult to address using standard analytical or numerical methods due to its complexity. However, since synthetic representations of porous media are easy to produce and data from physical experiments are becoming more widely available, the problem is well-suited to studies that include machine learning (ML) techniques. We discuss a number of features that can be extracted from such data, and their utility as input variables into a standard ML algorithm. These features include structural measures describing the geometry of the porous media, topological measures describing the connectivity, and network measures obtained by modeling the porous media as simplified pore networks. These features enable the prediction of the permeability of the considered (synthetic) porous materials using ML techniques that also leverage the separately computed exact permeability (ground truth). Comparing results obtained using different input variables helps develop a better understanding of the utility of various measures for predicting permeability based on the porous media structure. We show, in particular, that topological data analysis (TDA) provides a useful set of features that can be easily combined with ML to yield meaningful results. --- ### ECG-WM: A Physiology-Informed ECG World Model for Clinical Intervention Simulation Authors: Zhikang Chen, Yue Wang, Sen Cui, Yu Zhang, Changshui Zhang, Tianling Ren, Tingting Zhu Published: 2026-05-17 Categories: cs.AI arXiv: https://arxiv.org/abs/2605.17580v1 Electrocardiogram (ECG)-based models have achieved strong performance in diagnostic tasks, yet they remain limited in modeling how cardiac dynamics evolve under external interventions. In particular, existing approaches focus primarily on static prediction and lack mechanisms to capture ECG variations under different pharmacological conditions. In this work, we propose an ECG World Model for action-conditioned predictive simulation of cardiac electrophysiology. Moving beyond disjoint pipelines, our framework features a principled integration of physiological ordinary differential equation (ODE) priors into latent diffusion dynamics via energy regularization. This structural constraint enables the synthesis of physiologically plausible post-intervention ECG trajectories while effectively mitigating generative hallucinations. Building on this simulation process, we introduce an uncertainty-aware evaluation strategy that leverages the stochasticity of diffusion sampling to characterize both the expected clinical risk and its variability, allowing a more reliable comparative assessment of candidate interventions. We evaluate our method across diverse settings, including controlled drug-response scenarios and real-world clinical records. Beyond standard waveform metrics, experimental results demonstrate improved risk calibration and strong alignment with expert-informed treatment preferences. These results establish our approach as a robust foundation for safe and intervention-aware clinical decision support. --- ### TAME: Test-Time Adversarial Prompt Tuning via Mixture-of-Experts for Vision-Language Models Authors: Xin Wang, Yixu Wang, Jiaming Zhang, Ruofan Wang, Jiaqi Yu, Kai Chen, Jingjing Chen, Xingjun Ma, Yu-Gang Jiang Published: 2026-05-17 Categories: cs.CV arXiv: https://arxiv.org/abs/2605.17577v1 Large-scale pre-trained Vision-Language models (VLMs), such as CLIP, exhibit strong zero-shot generalization, yet remain highly vulnerable to imperceptible adversarial perturbations, raising serious safety concerns for open-world deployment. To enhance robustness without requiring downstream task-specific retraining, we propose TAME, a novel test-time defense. Building upon our prior Test-Time Adversarial Prompt Tuning (TAPT), TAME introduces an architectural reformulation by replacing TAPT's single adaptive prompt with an input-conditioned Mixture-of-Experts (MoE) framework, enabling more expressive and adaptive defense. Specifically, TAME maintains a bank of learnable expert prompts and employs an input-dependent routing mechanism to aggregate a customized prompt mixture for each unlabeled test sample at inference time. This test-time defense mechanism is driven by three unsupervised objectives: (1) multi-view prediction entropy minimization, (2) layer-wise alignment of visual token statistics to precomputed clean and adversarial reference distributions, and (3) MoE regularization for balanced expert utilization and prompt diversity. We evaluated TAME on 11 benchmark datasets, including ImageNet and 10 additional zero-shot datasets. The results show that TAME improves the zero-shot adversarial robustness of the original CLIP by at least 49.1% under AutoAttack while largely preserving generalization on clean samples. TAME also consistently outperforms existing adversarial prompt tuning methods across multiple prompt designs, yielding an average robustness gain of at least 30.2%. --- ### UniAlign: A Model-Agnostic Framework for Robust Network Traffic Classification under Distribution Shifts Authors: Tongze Wang, Xiaohui Xie, Wenduo Wang, Chuyi Wang, Yong Cui Published: 2026-05-17 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2605.17575v1 Network traffic classification (NTC) models often suffer severe performance degradation when deployed in real-world environments due to distribution shifts caused by changing network conditions. Existing robustness-enhancing approaches are commonly coupled to specific model architectures or data settings, fail to generalize to state-of-the-art raw-byte-based NTC models, or incur significant training overhead. In this paper, we propose UniAlign, a novel model-agnostic framework that improves the robustness of deep learning-based NTC models under distribution shifts. UniAlign combines \emph{domain alignment fine-tuning}, which encourages the learning of domain-invariant traffic representations across heterogeneous network conditions, with \emph{stable model ensembling}, which enhances inference robustness by aggregating checkpoints within a flat loss region. The framework can be seamlessly integrated into existing supervised NTC models without requiring specific feature modalities or introducing non-constant additional training costs. We evaluate UniAlign on three public datasets covering diverse distribution shifts, including encryption schemes, data collection devices, and attack behaviors. Experimental results on two representative NTC models demonstrate that, compared with standard training, UniAlign improves average classification accuracy by 2.51\% and average F1 score by 2.71\%, outperforming the strongest baseline by 1.45\% in accuracy and 1.69\% in F1 score, while requiring only 12.4\%--53.9\% of the training time of all NTC-specific baselines. --- ### Deepfake Detection in Social Media: A Temporal Artifact Analysis Using 3D Convolutional Neural Networks Authors: Mohammadreza Rashidi, Raja Hashim Ali, Sami Ur Rahman Published: 2026-05-17 Categories: cs.CV, cs.CR arXiv: https://arxiv.org/abs/2605.17573v1 Synthetic facial videos have proliferated across social media faster than platform moderation can respond, raising the cost of disinformation and identity-based attacks. Frame-level deepfake detectors degrade sharply as generator quality increases; high-quality 128x128 GAN output cuts spatial-only accuracy by five percentage points while leaving temporal inconsistencies largely intact. We address this gap with a 3D Convolutional Neural Network detector based on R3D-18, trained with a composite loss that combines binary cross-entropy with a temporal-consistency regularizer. The model processes 16-frame clips from the DeepfakeTIMIT dataset and is initialized from Kinetics-400 action-recognition weights. We report 92.8% accuracy on intra-dataset evaluation at 128x128 resolution; cross-dataset transfer to FaceForensics++ without fine-tuning reaches 76.4%, rising after minimal fine-tuning. Ablation studies show that transfer learning contributes 7.2 percentage points and face tracking adds 3.5 points, while temporal consistency regularization provides additional gains on high-quality fakes. The results establish that temporal artifacts generalize more broadly than spatial ones, providing a detection signal that survives social-media re-encoding. --- ### Stable Routing for Mixture-of-Experts in Class-Incremental Learning Authors: Zirui Guo, Quan Cheng, Da-Wei Zhou, Lijun Zhang Published: 2026-05-17 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2605.17571v1 Class-incremental learning (CIL) requires models to learn new classes sequentially while preserving prior knowledge. Recently, approaches that combine pre-trained models with mixture-of-experts (MoE) have received increasing attention in CIL: they typically expand experts during learning and employ a router to assign weights across experts. However, existing MoE methods often overlook routing drift induced by expert expansion. Once new experts are introduced, the router may reassign samples from earlier classes to newly added experts, thereby perturbing previously established expert compositions and causing interference even when old experts remain frozen. We argue that expandable MoE in CIL requires two complementary properties: stable old-class routing for knowledge preservation and sufficient capacity utilization for new-class adaptation. To this end, we propose Stable Routing for MoE (StaR-MoE), a routing-level framework for expandable MoE in CIL. By incorporating sensitivity-aware routing alignment, StaR-MoE aligns current old-class routing behavior with historical routing distributions through sensitivity-guided constraints. Complementarily, StaR-MoE introduces asymmetric capacity regularization to encourage effective utilization of the expanded expert pool without compromising class-specific routing specialization. Extensive experiments across four standard CIL benchmarks demonstrate that StaR-MoE consistently improves both average and last accuracy over state-of-the-art methods, highlighting the importance of stable routing. --- ### How Off-Policy Can GRPO Be? Mu-GRPO for Efficient LLM Reinforcement Learning Authors: Minghao Tian, Yunfei Xie, Chen Wei Published: 2026-05-17 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2605.17570v1 Group Relative Policy Optimization (GRPO) has been a key driver of recent progress in reinforcement learning with verifiable rewards (RLVR) for large language models, but it is typically trained in a low-staleness, near-on-policy regime that incurs substantial system overhead. We ask a simple question: How off-policy can GRPO be? We show that GRPO-style algorithms can tolerate substantially larger rollout staleness than previously assumed, and propose Mu-GRPO, an RL training framework that organizes training into a small number (e.g., four) of large sequential generation-optimization stages. This design induces high rollout staleness while greatly reducing rollout-optimization switching overhead. To stabilize learning under stale data, Mu-GRPO combines relaxed clipping, which preserves useful stale-rollout gradients, with negative-advantage veto, which removes destabilizing post-trigger suffix updates in negative-advantage responses. Across five language models and multiple math reasoning benchmarks, Mu-GRPO matches or exceeds the performance of standard GRPO while achieving around 2x speedup in wall-clock training time, establishing a substantially improved performance-efficiency trade-off for LLM reinforcement learning. --- ### Structured Neural Marked Point Processes for Interpretable Event Interaction Modeling Authors: Zhitong Xu, Qiwei Yuan, Yinghao Chen, Shandian Zhe, Bin Shen Published: 2026-05-17 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.17568v2 Multi-class event streams arise in numerous real-world applications, where uncovering structured, interpretable inter-event relationships, together with accurate prediction, remains a central challenge. Existing neural point process models are highly expressive but encode event interactions in a black-box manner, preventing explicit discovery of structured dependencies. In this paper, we propose a structured neural marked point process (SNMPP) that achieves high modeling flexibility while enabling explicit event-wise and class-wise relationship discovery from data. Our model constructs a product-form neural influence kernel composed of a signed interaction network over event types and a delay-aware monotonic temporal network. This design enables explicit characterization of inter-class influence topology -- including excitation, inhibition, and neutrality -- while flexibly capturing diverse temporal decay patterns and potential influence delays. For efficient learning, we develop a stratified Monte Carlo estimator for stochastic training. Extensive experiments on synthetic and real-world benchmark datasets validate the ability of our approach to uncover structured relationships and deliver strong predictive performance. --- ### Rethinking Point Clouds as Sequences: A Causal Next-Token Predictive Learning Framework Authors: Yumeng Yao, Jingzhi Dong, Haowen Gu, Tao Chen, Zonghan Wu, Xiaoshui Huang, Yazhou Yao Published: 2026-05-17 Categories: cs.CV arXiv: https://arxiv.org/abs/2605.17566v1 With the rapid progress of multimodal foundation models and predictive pre-training, an important open question is how to equip 3D point clouds with a pre-training paradigm that is better aligned with next-token and next-embedding learning. Existing point-cloud self-supervised methods are largely built on masked reconstruction or explicit geometric generation, and thus remain tied to input recovery rather than predictive dependency modeling. In this paper, we introduce PointNTP, which reformulates point cloud pre-training as a fully causal, decoder-free latent Next-Token Prediction problem. Specifically, each point cloud is first partitioned into local patches and serialized into a structured 3D token sequence according to patch-center geometry. The resulting sequence is then modeled by a causal Transformer under prefix-only conditioning, and trained with a shift-based prediction objective stabilized by stop-gradient targets. This design enables the model to learn structural dependencies directly in latent space, without reconstruction decoders or explicit geometric recovery. Extensive experiments demonstrate that the proposed PointNTP is highly competitive across multiple downstream tasks: it achieves 93.8%(+0.5%), 92.6%(+0.3%), and 89.3%(+1.1%) on OBJ_BG, OBJ_ONLY, and PB_T50_RS of ScanObjectNN, respectively; obtains 85.0%(+0.1%) in Cls.mIoU on ShapeNetPart; and reaches 71.1% mAcc on S3DIS Area 5. Overall, decoder-free causal latent prediction provides a simple, scalable, and potentially modality-agnostic paradigm for point-cloud self-supervised learning, offering a new 3D perspective on foundation-style predictive learning for 3D data. --- ### Generalization or Memorization? Brittleness Testing for Chess-Trained Language Models Authors: Ethan Tang Published: 2026-05-17 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2605.17565v1 Recent work has fine-tuned language models on chess data and reported high benchmark scores as evidence that the resulting models can understand the rules of chess, play full chess games at a professional level, or generate human-readable explanations grounded in expert knowledge. We train KinGPT, a 25M-parameter character-level language model trained only on (position, best-move) pairs, who exceeds 3B-parameter ChessGPT on a 600-puzzle mate-in-N suite and 4B-parameter C1-4B over a 20-theme puzzle benchmark. We examine several claims made in existing literature regarding chess-trained language models and assert that their impressive benchmark performance is largely explained by pattern-matching. We also demonstrate how LLM-Modulo, a verifier-in-the-loop framework, raises RedPajama 3B's best move accuracy from 1.2% to 21.2% and move generation validity from 19.3% to 95.3% on mate-in-N chess puzzles, comparable to gains achieved from ChessGPT's fine-tuning on chess-specific web corpora at a fraction of the cost. Our results illustrate how pairing a general LLM with an external verifier offers a more flexible alternative to directly training on synthetic data for well-defined domains. We open source all training/evaluation code, datasets, puzzle samples, and KinGPT model checkpoints for reproducibility. --- ### A Conditional U-Net Pipeline with Pre- and Post-Processing for Aerial RGB-to-Thermal Image Translation Authors: Tseten Sherpa, Sikandar Ali, Shubham Parab, Haoyun Feng, Matthew Dennis, Keenan Gibbons, Verrah Otiende, Geoffrey H. Siwo Published: 2026-05-17 Categories: cs.CV arXiv: https://arxiv.org/abs/2605.17564v1 Paired RGB-thermal data has shown significant utility across a range of applications, including image fusion, object tracking, and anomaly detection; however, its broader adoption is constrained by the limited availability of aligned RGB-thermal image pairs. RGB-to-thermal (and vice versa) image translation has emerged as a practical solution to this challenge. Prior approaches including conditional generative adversarial networks (cGANs) such as ThermalGAN and Scalable Interpolant Transformer (SiT)-based architectures such as ThermalGen have demonstrated strong potential for aerial-to-thermal image translation. In this work, we explore alternative architectures that prioritize simplicity while maintaining performance. Specifically, we propose a conditional U-Net that incorporates weather data at the bottleneck layer, complemented by targeted preprocessing and post-processing techniques applied within the Pix2Pix GAN architecture. We utilize a training set of 612 paired RGB and thermal images, and evaluate over 5-fold cross-validation, ultimately testing on a held-out test set. Our conditional U-Net model performed best, with a peak signal-to-noise ratio (PSNR) of 14.5485, structural similarity index measure (SSIM) of 0.8095, and learned perceptual image patch similarity (LPIPS) of 0.1666. These results outperformed the base ThermalGen model, which attained PSNR, SSIM, and LPIPS scores of 7.56, 0.2444, and 0.6317 respectively. We find that while saturation boost and contrast enhancement for preprocessing and Gaussian blur for post-processing provide observable improvements, the incorporation of conditioning data was most effective. Our findings cement the potential of integrating auxiliary metadata into thermal image generation, suggesting that such information can serve as a proxy for environmental conditions critical to accurate thermal reconstruction. --- ### Beyond Accuracy: Robustness, Interpretability and Expressiveness of EEG Foundation Models Authors: Urban Širca, Maryam Alimardani, Stefanos Zafeiriou, Konstantinos Barmpas Published: 2026-05-17 Categories: cs.LG, cs.AI, cs.HC arXiv: https://arxiv.org/abs/2605.17562v1 EEG foundation models (EEG-FMs) have been evaluated predominantly on clean, in-distribution accuracy, leaving their robustness, interpretability and representational quality largely unexamined. This study addresses these gaps by benchmarking six EEG-FMs against a baseline deep learning model across eight datasets. Beyond clean accuracy, we conduct three layers of analysis: (i) Robustness: we apply test-time perturbations including additive noise, random and region-based channel dropout and region-specific noise injection. Our analyses show that no single model dominates all failure modes. The most noise-robust model is among the most fragile under channel dropout and much of the dropout fragility disappears when channels are removed rather than zero-padded. (ii) Interpretability: we present the first application of Attention-Aware Layer-Wise Relevance Propagation (AttnLRP) to EEG-FMs and show that models broadly concentrate relevance on task-appropriate brain regions consistent with known neurophysiology. However, attribution maps remain spatially stable under perturbation while predictions degrade, suggesting that the models attend to the correct brain regions but decode corrupted content. (iii) Expressiveness: With block-wise probing we show that late blocks are repurposed during fine-tuning, while early blocks already hold task-related information. Furthermore, we demonstrate that the poor head-only performance previously attributed to low-quality pre-trained representations is largely explained by pooling and that EEG-FMs possess sufficient representational capacity when their token-level embeddings are preserved. Together, these findings provide the first systematic assessment of robustness, interpretability and expressiveness for EEG-FMs and highlight critical considerations for their development. --- ### Automated Root-Cause Subclassification and No-Code Fix Generation for Invalid Bug Reports Authors: Mahmut Furkan Gon, Emre Dinc, Tevfik Emre Sungur, Eray Tuzun Published: 2026-05-17 Categories: cs.SE, cs.AI, cs.MA arXiv: https://arxiv.org/abs/2605.17561v2 Issues faced when using software are reported in the form of bug reports. However, many bug reports are invalid, meaning they do not require code changes, and are resolved with a no-code fix. Manually determining the root cause of the invalid bug reports and providing actionable resolutions by the customer support causes a serious waste of resources. Our goal is to introduce a standardized taxonomy for root-cause oriented invalid bug report subclassification, and perform experiments to test the accuracy of various approaches on invalid subclassification and no-code fix generation. We study how different configurations perform on a gold-standard benchmark we have created. Using a manually curated benchmark for higher quality analysis, we experimented with vanilla LLMs, Retrieval Augmented Generation, and agentic web search to identify invalid subclasses and generate no-code fixes. We evaluated the results against manually labeled ground truth data that includes the invalid subclass and no-code fixes from the original bug reports. We measured subclass detection performance with weighted F1-Score, and assessed no-code fix suggestions using BERTScore and Judge LLM success rates. For subclassification, retrieval augmented generation achieves the highest overall performance with 0.66 weighted F1, slightly outperforming vanilla LLMs at 0.65 and agentic web search at 0.64. At the subclass level, performance peaks at 0.85 F1 for Non-reproducibility and 0.79 for Feature Request and Question, while Wrong Version remains the most challenging with scores between 0.00 and 0.29. For no-code fix generation, agentic web search achieves the highest overall Judge LLM success rate at 68.9%, compared to 64.4% for RAG applications and 64.9% for vanilla LLMs, with subclass-level peaks of 87.4% for Working as Designed and 72.2% for Question. --- ### Controlling False Discovery in Arbitrarily Structured Hypothesis Spaces via Reproducing Kernels Authors: Binyamin Perets, Shie Mannor Published: 2026-05-17 Categories: stat.ME, cs.AI, q-bio.QM, stat.ML arXiv: https://arxiv.org/abs/2605.17559v1 Large-scale hypothesis testing is central to modern science, where controlling the False Discovery Rate (FDR) has become the standard approach to managing false positives across many simultaneous tests. Hypotheses rarely exist in isolation; they often exhibit structure through proximity, connectivity, or hierarchy. This structure represents both a challenge and an opportunity: while classical methods treat these dependencies as obstacles requiring conservative correction, leveraging them can substantially increase discovery power. Here, we reframe structured FDR control as a regularized learning problem. By optimizing within a suitable Reproducing Kernel Hilbert Space (RKHS), we introduce a framework that unifies continuous domains, graphs, and hierarchies under a single algorithm through kernel choice alone. This formulation enables smooth solutions in place of the piecewise-constant fits of prior methods, principled likelihood-based hyperparameter selection rather than heuristic tuning, and inference at unobserved locations which in turn supports sample-efficient experimental design. Building on this estimator, we provide two decision rules which we prove to control the FDR. We validate our method on two sources: spatial locations derived from high-dimensional real-world datasets, and a differential gene expression task utilizing protein-protein interaction graphs. --- ### Firefly: Illuminating Large-Scale Verified Tool-Call Data Generation from Real APIs Authors: Yuxuan Lu, Ziyi Wang, Yingzhou Lu, Yisi Sang, Jiri Gesi, Xianfeng Tang, Yimeng Zhang, Zhenwei Dai, Hui Liu, Hanqing Lu, Chen Luo, Qi He et al. Published: 2026-05-17 Categories: cs.SE, cs.CL arXiv: https://arxiv.org/abs/2605.17558v1 Training tool-calling agents requires large-scale trajectory data with verifiable labels, yet existing approaches either synthesize environments that diverge from real API behavior or generate tasks without ground-truth outcomes for verification. We present FireFly, a pipeline for generating verified tool-call data from real-world MCP servers. Our key insight is to invert the standard synthesis pipeline: rather than generating tasks and hoping they are solvable, we first let a strong LLM explore real APIs along graph-guided DAG structures, then synthesize tasks backward from observed outcomes, guaranteeing label correctness by construction. To handle the scale of real-world tool spaces (${\sim}$1,000 tools), we build a pairwise tool graph and sample sub-DAGs to focus exploration on semantically coherent workflows. To address environment drift in live APIs, we construct a retrieval-augmented simulator that caches all exploration results and replays them during training and evaluation, enabling fully offline and reproducible RL. Applying this pipeline yields 5,144 verified tasks spanning 240 servers and 993 tools. A 4B-parameter model trained with GRPO on FireFly matches Claude Sonnet 4.6 on our held-out test set and shows improvements on multiple tool-calling benchmarks including Tau2-Bench, MCPMark, and MCP-Atlas. --- ### Real-Time Neural Hair G-Buffer Anti-Aliasing Authors: Chenghao Wu, Yuefan Shen, Tao Huang, Kai Yan, Zahra Montazeri, Kui Wu Published: 2026-05-17 Categories: cs.GR, cs.CV arXiv: https://arxiv.org/abs/2605.17557v3 We propose a lightweight real-time method for reconstructing strand-based hair G-Buffers from severely undersampled rasterized inputs. Our pipeline first applies neural spatial reconstruction and temporal accumulation to recover hair coverage, i.e., fractional hair visibility within a pixel, and tangent. It then uses a tangent-guided reconstruction step to complete the position, which is subsequently used for physically based deferred hair shading. We evaluate our method across a diverse set of hairstyles, including straight, wavy, afro, and ponytail styles, under both static and dynamic scenarios. Our method achieves higher hair reconstruction quality than general industrial neural reconstruction solutions such as DLSS and FSR. ---