# Research Papers — 2026-08 · bundle page 97 of 240 > Full-text markdown of papers #4801–4850 of 11995 published in 2026-08, newest first. AI-readable mirrors of the full 11995-paper 2026-08 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2026-08/page/97 [← Previous bundle](https://aipod.dev/papers/archive/2026-08/page/96.md) [Next bundle →](https://aipod.dev/papers/archive/2026-08/page/98.md) ### Evaluation of Image Matching Methods for Visual Odometry on UAVs Authors: Gašper Spagnolo, Luka Čehovin Zajc, Matej Dobrevski Published: 2026-08-19 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.18624v1 Unmanned aerial vehicles (UAVs) are becoming a powerful tool for many environmental monitoring and transport applications. Yet, their reliance on Global Navigation Satellite System (GNSS) technology for navigation makes them susceptible to catastrophic failures in scenarios where the positioning signal is unavailable or disrupted. This work explores Visual Odometry (VO) as a crucial navigation component. Recently, numerous deep-learning-based methods for image matching have been proposed that are yet to be implemented in a fully-fledged VO system. In this paper, we evaluate recent state-of-the-art image matching methods for the task of VO for UAV position tracking, with a downwards-facing camera, on our synthetic dataset, and find that while the best results are generated by the recent RoMa matcher, SIFT features can outperform some recent state-of-the-art. --- ### PALATE: Personalized Aesthetic Learning through Adaptive Taste Evolution for Multi-User Portrait Retouching Authors: Jingxuan Wang, Yifan Mei, Yuxia Niu, Chaowan Jiao, Qijin Shen Published: 2026-08-19 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.18622v1 Automatic portrait retouching has advanced rapidly, yet its objective is inherently subjective: the same portrait admits multiple professionally valid results, and users disagree about which one is best. Most existing methods optimize a population-level aesthetic standard and therefore cannot capture individual taste, while fine-tuning a separate editing model for every user incurs prohibitive training, storage, and data costs. We propose PALATE, a shared reward-evolution framework that keeps the image editor fixed and instead personalizes the selection among retouched candidates of the same source portrait. PALATE decomposes the reward for each user into a global backbone shared by all users, category-level residuals shared by aesthetically similar users, and a lightweight user adapter, with anti-collapse regularizers keeping the three levels complementary.A cyclic dual-level distillation scheme first distills user-specific preferences into category rewards and then consolidates the resulting category-level knowledge into the global backbone, which is redistributed to initialize the next evolution round. In this way, the shared initialization improves progressively across rounds, enabling unseen users to be calibrated from only a few rankings. On expert-retouched candidates from PPR10K with held-out users and held-out images, PALATE attains 72.83% pairwise preference-prediction accuracy, surpassing all reward, aesthetic, and image-quality baselines, of which the strongest, PickScore, reaches 58.06%. Each new user costs only 512 bytes of user-specific parameters and millisecond-level scoring. --- ### SPARC: Slice-to-volume Pipeline for Automated Reconstruction of gated 3D+time fetal Cardiac MRI Authors: Arnaud Boutillon, Naomi Clarke, Tomas Woodgate, Daniel West, Alina Schneider, Rachael Franklin, Anthony Price, Jo Hajnal, Kuberan Pushparajah, David Lloyd, Maria Deprez Published: 2026-08-19 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.18616v1 Fetal cardiac MRI (fCMR) provides valuable diagnostic information complementary to echocardiography, particularly for complex congenital heart disease (CHD). Dynamic cine imaging captures cardiac motion essential for assessment of cardiac function; however, the reconstruction of 3D+time cine volumes from 2D+time acquired slices remains challenging due to unpredictable fetal motion and the absence of automated and robust processing tools suitable for clinical deployment. We present the SPARC pipeline (Slice-to-volume Pipeline for Automated Reconstruction of gated 3D+time fetal Cardiac MRI) which combines physics-informed slice-to-volume reconstruction (SVR) of Doppler ultrasound (DUS) gated stacks of slices, assisted by deep learning (DL) models for thoracic segmentation and anatomical reorientation. The proposed SVR algorithm achieves a tenfold reduction in reconstruction time relative to existing frame-wise approaches ($4.8 \pm 1.0$ vs $49.0 \pm 14.1$ min, $p < 0.0001$) while improving the reconstruction quality. Thoracic segmentation performance using ensemble aggregation exceeded inter-rater agreement (Dice $84.7 \pm 3.9\%$ vs $81.4 \pm 7.7\%$, $p<0.05$), while anatomical reorientation achieved a success rate of $90.1\%$. End-to-end evaluation on a large held-out clinical cohort ($n = 121$) demonstrated fully automatic processing in $82.6\%$ of cases with a mean runtime of $7.1 \pm 1.3$ min, compatible with clinical deployment. The complete SPARC pipeline is publicly available as a Docker container https://hub.docker.com/r/aboutill/sparc and is currently deployed at our institution as a clinical research tool. --- ### CDGP: Contrastive Dual Gaussian Processes for Weakly Supervised Anomaly Segmentation Authors: Seungjun Chu, Seokhee Han, Mateusz Nowak, Peter Chin Published: 2026-08-19 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.18614v1 Industrial visual inspection must both decide whether a product is defective and localize the defect, yet pixel-level masks are costly to collect at scale. Most anomaly-segmentation methods learn only from defect-free images and score deviations from normality. A true defect and an unusual-but-normal region, however, can both deviate substantially and receive similarly high scores. We propose Contrastive Dual Gaussian Processes (CDGP), a weakly supervised framework that models normal and anomaly inducing-variable predictive distributions over dense tokens. Its posterior-dominance statistic standardizes their predictive-mean difference by the joint predictive uncertainty, providing both spatial evidence and image-level confidence. This evidence complements hierarchical normal-reconstruction residuals for fine localization. All calibration uses training data only, without human pixel annotations or test-time fitting. Across MVTec AD~2, KSDD2, and VisA, CDGP ranks first among the evaluated methods on all MVTec AD~2 localization metrics and is first-place or competitive on KSDD2 and VisA. Factorized and matched linear-head controls delimit the contribution and scope of the linear-kernel Gaussian process (GP) formulation. --- ### CTIFoundry: An Agent-Native Corpus Scaffold for Cyber Threat Intelligence Authors: Yutong Cheng, Changze Li, Qian Cui, Wei Ding, Lingzhi Wang, Yan Chen, Peng Gao Published: 2026-08-19 Categories: cs.AI, cs.CR arXiv: https://arxiv.org/abs/2608.18613v1 Cyber threat intelligence (CTI) is increasingly consumed not by human analysts but by LLM agents that compose multi-step investigations at query time. The harness side of this shift has matured rapidly (planning loops, tool protocols, context management), but the corpus side has not: threat reports and vulnerability databases are still packaged for retrieval-augmented generation, as opaque chunks behind an embedding index. We argue that this substrate, not model capability, is the bottleneck on agentic CTI investigation, and present CTIFoundry, an agent-native corpus scaffold. At build time, CTIFoundry materializes the latent structure of a CTI corpus: a deterministic ontology graph over four authoritative knowledge bases (CVE, CWE, CAPEC, ATT&CK) whose official cross-references become typed, traversable edges; a span-grounded report layer whose canonical, alias-resolved cross-vendor entities index provenance-carrying chunks; and hybrid dense+lexical retrieval surfaces. At query time this structure is exposed through seven typed tools and three procedural skills mounted on a stock open-source agent harness. On the public CTIConnect benchmark, swapping only the action surface lifts the identically-harnessed agent by +0.19 to +0.28 overall F1 across a four-model, two-provider panel: a small model on CTIFoundry surpasses a flagship on the flat substrate, and the gain is not bought with search effort, since on both Claude models the scaffolded agent is more accurate at roughly half the tool calls. An ablation attributes it: typed structure carries the larger share, procedural skills convert structure into discipline, and the two compose super-additively, because skills bind only to structure that exists. --- ### Scalable Geospatial Machine Learning for Power-Line Asset Risk: Integrating Remote Sensing for Lightning and Vegetation Risk Modelling Authors: Artur Sokolovsky, Bhavik Merai, Moe Jafari, Muen Chen Published: 2026-08-19 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.18611v1 Electric power networks are increasingly exposed to weather-sensitive failure mechanisms that require asset-level, spatially explicit risk modelling for effective intervention planning. This study contributes a modular, robust, and explainable probability-of-failure (PoF) modelling framework for utility asset management. The central contribution is an asset-level architecture that can be scaled to new environmental data sources and additional PoF types without reworking the underlying pipeline. This is particularly relevant for industry settings, where risk models must remain operationally maintainable while adapting to changing data availability, asset-management priorities, and climate-driven hazard conditions. We demonstrate the framework for vegetation-related and lightning-related failure modes using a harmonised geospatial machine-learning pipeline. The implementation integrates multi-source predictors, including topography (SRTM), vegetation condition (MODIS Normalised Difference Vegetation Index - NDVI), lightning climatology (LIS VHRMC), OpenStreetMap-derived proximity features, and utility operational records. The resulting architecture is computationally efficient, operationally extensible, and suitable for utility-scale deployment. It provides actionable asset-level risk stratification for inspection prioritisation, vegetation management, asset hardening, and resilience planning, supporting earlier intervention and more climate-resilient network operations. --- ### Denoising-Aware Inversion: Revealing Privacy Risks in Noise-Protected Text Embeddings Authors: Yubo Wang, Shujie Cui, James Bailey, Hongzhi Yin, Wenyu Liang, Min Tang, Shiyue Qin, Weiqing Wang Published: 2026-08-19 Categories: cs.LG, cs.AI, cs.CR arXiv: https://arxiv.org/abs/2608.18610v1 Dense text embeddings are widely used in data mining, retrieval, and downstream machine learning systems due to their compact and semantically rich representations, but recent embedding inversion attacks have shown that they can expose substantial information about the original text, leading to serious privacy leakage risks. A common defense is to release perturbed embeddings by adding Gaussian noise, which is simple yet effective against standard inversion attacks and does not significantly degrade embedding utility for downstream tasks. However, it remains unclear whether such noise-protected embeddings are sufficiently safe against adaptive attackers that explicitly account for the perturbation process. In this paper, we study text embedding inversion in a noise-protected setting, where the attacker can observe only noisy embeddings and has no access to clean embedding targets. We first analyze why existing generative inversion methods fail under this setting and identify a "Double Noise Trap", which fundamentally prevents standard generative inversion models from achieving high-quality reconstruction. To address this challenge, we propose DAEI, a denoising-aware embedding inversion pipeline that combines a residual denoising autoencoder with generative text inversion where the denoiser is trained in an unsupervised manner using Stein's unbiased risk estimate to enable denoising from noisy observations alone. Extensive experiments show that DAEI achieves approximately 154\% relative improvement in BLEU over the existing generative inversion baseline, while also improving token-level F1 and ROUGE-L by 32--60\%. The promising inversion performance of DAEI challenges the prevailing assumption that simple Gaussian perturbation is sufficient to prevent sensitive information leakage from embedding representations. --- ### VA-Judger: Reward Modeling from Human Preference Feedback for Joint Video-Audio Generation Authors: Yinming Huang, Shuyuan Tu, Xi Yan, Zihan Yang, Jianhua Han, Hang Xu, Kaihang Pan, Yu-Gang Jiang, Zuxuan Wu Published: 2026-08-19 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.18607v4 Using reinforcement learning to post-train joint video-audio generation models requires a reward signal. Existing methods construct this reward by combining metrics for individual quality dimensions, including audio quality, visual fidelity, and synchronization. However, these metrics evaluate perceptual dimensions separately and fail to capture the overall semantic and temporal coherence among the text prompt, video, and audio that shapes human preferences. Optimizing models against these metrics encourages reward hacking, generating video-audio content that achieves high scores on these metrics yet appears incoherent or unfaithful to human viewers. To address this problem, we first construct a large-scale human-preference dataset VAPref-10K for joint video-audio generation, comprising 9K prompts and 10.3K fine-grained paired comparisons from generation models. We also introduce the VA-Judger-Bench benchmark with both in-domain and out-of-domain model comparisons to evaluate whether reward models truly align with human preferences. We further propose VA-Judger, a chain-of-thought omni-reward model for joint video-audio generation. In particular, VA-Judger first learns from pairs with clear quality gaps to establish structured output and coarse preference discrimination, then distills reliable preference explanations for harder near-quality comparisons via rejection sampling verified against human annotations, and finally performs dimension-wise reinforcement learning that decomposes human feedback into individual quality dimensions for denser reward signals than a single binary preference label. Experiments show that VA-Judger outperforms metric baselines in predicting human preferences on both in-domain and out-of-domain evaluations. Using its human-aligned rewards for post-training audio-video generation model also yields significant improvements in generation quality. --- ### Teach a Molmo2Fish: Towards interactive fish tracking with natural language guidance Authors: Kai Van Brunt, Justin Kay, Sara Beery Published: 2026-08-19 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.18602v1 Computer vision is increasingly used to automate recognition tasks in large ecological datasets, but more complex tasks such as multi-object tracking continue to pose challenges. As researchers seek to incorporate vision models in ecology workflows, various lines of research have explored how to make imperfect predictions useful through human-in-the-loop processes. We propose a new approach to working with imperfect tracking predictions through an interactive prediction correction workflow taking place as a conversation with a multimodal large language model, which we tailor to a sonar fish tracking dataset as an initial proof of concept. We investigate the performance of the tool, Molmo2Fish, across guided and unguided tasks, correcting its own predicted tracks and external tracks. We find that Molmo2Fish achieves high performance on fish tracking and track correction tasks, but there is still much room to improve on incorporating natural language guidance. The code and data are publicly available at https://github.com/tidalove/molmo2fish. --- ### Off-Manifold Collapse in Guided Protein Language Models Authors: Shuibai Zhang, Xinchi Liu, Fred Zhangzhi Peng, Zhihan Yang, Shutong Wu, Yingzi Ma, Jiawei Zhang Published: 2026-08-19 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.18597v1 Protein language models are widely used priors for protein sequence design, and a growing body of work controls them at inference time as an alternative to fine-tuning. Such guidance faces a dilemma: mild enough to preserve natural activation statistics, it barely moves the property; strong enough to move it, the generations become progressively harder to fold. We show the failure has a specific and cheaply detectable signature, an off-manifold collapse of the model's own representations. Guided activations fall toward a region statistically indistinguishable from random amino-acid input, and the sequences degenerate to low complexity, yet the property oracle being optimized can still score these generations as a success. The optimized oracle can therefore fail to witness the collapse and, for solubility, can actively reward it, whereas structure and composition expose the failure. Because the failure is already visible in a finished candidate, we detect it at the output rather than modify the generator. We introduce a cheap density prior over natural protein activations and keep only the candidates that remain typical under it, a training-free post-hoc step we call Mahalanobis filtering. At matched guidance settings it improves both the property score and the structural plausibility of the sequences it keeps at negligible cost, without touching the generator, and transfers across different guidance methods. We release the activation statistic at https://huggingface.co/Shuibai12138/off-manifold-collapse-plm --- ### ReX-Shot: Single-Image Rephotography via Geometry- and Camera-Grounded Generation Authors: Ruiqi Zhang, Hao Zhu, Wenhao Zhang, Qi Zhang, Junqi Shi, Ming Lu, Xun Cao, Zhan Ma Published: 2026-08-19 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.18593v1 Single-image rephotography aims to synthesize new shots of a scene from a single reference image with specified viewpoints, focal lengths, and photographic effects, which are intrinsically coupled in imaging. Existing methods typically treat these factors separately and struggle under joint control: novel-view synthesis may introduce geometric distortions under focal-length changes, while super-resolution and instruction-guided editing remain confined to 2D and cannot reliably extend detail restoration or appearance control to novel viewpoints. We attribute these limitations to imperfect single-image 3D reconstruction and the sampling limit of continuous focal-length enlargement. To reduce projection bias from geometric errors, we use implicitly transformed foundation-model features for robust target-view guidance. We further formulate focal-length enlargement as a geometry-guided super-resolution problem and exploit generative detail priors to recover details lost during sparse 3D resampling. Built on this 3D-aware generative backbone, we lift photographic-effect control from 2D filtering to 3D-aware appearance editing, preserving content consistency across viewpoints and focal lengths. These components form ReX-Shot, a geometry- and camera-grounded generative framework for single-image rephotography. To our knowledge, ReX-Shot is the first unified framework to jointly control viewpoint, focal length, and parameterized photographic effects from a single image. Experiments show that ReX-Shot outperforms representative baselines across all three controls while enabling near-real-time interactive rephotography. --- ### Infrared Universality of Collective Dynamics across Transformer and State-Space Architectures Authors: Byung Gyu Chae Published: 2026-08-19 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.18592v1 Whether distinct neural architectures develop common collective dynamics remains an open question. Recent analysis of Transformer language models revealed a nearly flat, weakly infrared-enhanced time-scale density of states (TDOS) associated with near-marginal long-memory dynamics. Here we test whether a closely related organization emerges in Mamba, whose selective state-space dynamics provides a fundamentally different microscopic mechanism. Mamba allows relaxation dynamics to be resolved at three levels: the intrinsic spectrum of the learned state-space generator, its input-conditioned selective rescaling, and the collective TDOS of the complete block measured from its Jacobian. These spectra are not identical: selective dynamics and the remaining block transformations substantially reorganize the microscopic relaxation hierarchy. Nevertheless, the full block develops a reproducible slow-mode continuum whose infrared sector becomes progressively better resolved with increasing sequence length. Cumulative analysis yields $ρ(λ)\simλ^β$, with the long-sequence Mamba exponent stabilizing near $β_{\rm M}\simeq-0.17$. The corresponding memory dynamics follows $K(t)\sim t^{-(1+β)}$, close to the marginal $1/t$ regime. Despite fundamentally different microscopic dynamics, Transformer full-block spectra exhibit closely related infrared organization, with representative exponents of order $β_{\rm Tr}\sim-0.1$. These results separate explicit state-space memory from collective infrared organization and show that distinct sequence architectures can develop closely related near-marginal slow-mode dynamics. They extend infrared collective organization beyond Transformers and provide an independent test of the dynamical structure described by Cognitive Field Theory. --- ### Can a Lightweight Multimodal Model Estimate LLM Reasoning Performance? A Study for Compute-Optimal Document Inference Authors: Zishan Ahmad, Vishal Vaddina Published: 2026-08-19 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2608.18591v1 Uniformly allocating inference reasoning budgets to LLMs is expensive and prone to over-thinking penalties; especially in document tasks where visual layouts drive complexity. To address this, we introduce BudgetDoc, the first multimodal benchmark providing explicit supervision for model-budget-performance trade-offs across three document tasks. Using BudgetDoc, we train DRB (Document-Reasoning Balancer), an approx. 1B-parameter pre-flight estimator (SigLIP-2 + Qwen3-0.6B) that predicts ordinal model performance across budget levels, achieving a 0.753 weighted F1. When dynamically allocating reasoning budgets across five frontier models and three datasets, DRB matches or improves F1 scores compared to always-maximum-budget baselines in 9 of 15 configurations while drastically reducing cost. Finally, preliminary evaluations demonstrate DRB's potential to generalize to cross-model selection. --- ### FD-CanKD: Frequency-Decoupled Cross-Attention Distillation as a Refinement Prior for Compact Object Detectors Authors: YoungJae Cheong, Jhonghyun An Published: 2026-08-19 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.18590v1 Compact object detectors are suitable for resource-constrained visual perception, but their limited representation capacity creates an accuracy gap relative to large models. Conventional detector distillation often relies on prediction-level supervision or a single feature-alignment target, such as response, distribution, correlation, or frequency-domain matching. Frequency-Decoupled Cross-Attention Knowledge Distillation (FD-CanKD) is presented as a detector-oriented framework that transfers teacher knowledge at three complementary levels: head-level prediction supervision, relation-level non-local context transfer, and frequency-level component-selective alignment. Student features first aggregate teacher-side spatial context through cross-attention-based relation transfer, after which frequency-aware alignment preserves complementary structural and detail-sensitive cues. Under controlled Microsoft Common Objects in Context (COCO) experiments, fixed 50-epoch from-scratch comparisons show that FD-CanKD remains competitive with representative detector knowledge distillation baselines. Post-distillation continued fine-tuning further produces a stronger refinement-ready student than detector-only fine-tuning, reaching 48.87 mean average precision (mAP) at intersection-over-union thresholds from 0.50 to 0.95 (mAP50:95), 65.84 mAP50, and 53.40 mAP75 after 20 additional epochs. All distillation modules are removed after training, leaving the deployed student unchanged at 19.7M parameters. The framework is instantiated and evaluated in a controlled YOLOv12 teacher-student setting as a representative compact-detector case study. --- ### OmniHandwritingOCR: A Diagnostic Benchmark for Evaluating Multimodal LLMs in Handwritten OCR Scenarios Authors: Zinuo Guo, Min Zhang, Bo Jiang Published: 2026-08-19 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2608.18586v1 Multimodal large language models (MLLMs) are increasingly used as OCR systems in document and knowledge-processing pipelines, but their ability to faithfully read real handwriting remains underexplored. Existing OCR benchmarks focus largely on printed text or clean single-line inputs, leaving limited coverage of realistic handwritten OCR scenarios such as multilingual handwriting, writer errors, and structurally complex mathematical expressions. We introduce OmniHandwritingOCR, a diagnostic benchmark for evaluating MLLMs and OCR systems on handwritten OCR. It covers handwritten text recognition and handwritten mathematical expression recognition across six subtasks and twelve subsets, totaling 77.57K labeled images from public datasets and newly collected student writings. A key component is a difficulty-stratified multi-line formula corpus designed to test robustness under increasing structural complexity. We evaluate thirteen open- and closed-source systems with five complementary metrics under a unified protocol. Results show that current systems remain far from faithful transcription: performance drops sharply on complex multi-line formulas, model rankings vary across language and formula settings, and several generative models hallucinate plausible but visually unsupported corrections. OmniHandwritingOCR provides a challenging testbed for diagnosing language, content, structural, and visual-grounding failure modes of multimodal models in handwritten OCR scenarios. --- ### SPARC: Subspace Position-Aware Robust Few-Shot Calibration for Distribution-Shifted Industrial Anomaly Detection Authors: Seokhee Han, Seungjun Chu, Mateusz Nowak, Peter Chin Published: 2026-08-19 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.18585v1 Vision-based industrial anomaly detectors are calibrated on one distribution but may be deployed on another that differs in illumination, fixture placement, or sensor characteristics, sharply degrading an otherwise accurate detector. Adapting to the incoming lot is a natural response, but labeled anomalies are scarce. We therefore consider calibration using only a handful of verified-normal images available before scoring the rest of the lot. Existing fixes require backpropagation, detector-specific tuning, or choices about feature directions that few calibration samples cannot justify. We present SPARC, a few-shot calibration method that intercepts patch features between encoder and detector and removes a closed-form, spatially indexed estimate of deployment-time nuisance through per-cell subspace projection. It needs only $k \le 8$ verified-normal images and uses the algebraic saturation rank $r{=}k{-}1$ on the encoder's native patch grid. The correction requires no gradient or weight updates and works with memory-bank, density, prototype, and mutual detectors. On the shift-prone benchmarks, SPARC improves pooled Image AUROC and AU-PRO$_{0.3}$ for all seven detectors whose image scores depend on corrected patch features by $+13.8$ and $+3.5$ percentage points (pp), respectively; on benchmarks without engineered shift, the changes are small and mixed. Controls that give competing corrections the same calibration images attribute these gains to the per-cell subspace structure rather than the images alone. Further ablations support the saturation-rank choice and characterize sensitivity to backbone and calibration conditions. --- ### From Storage to Access: Verifiable Activation of Parametric Knowledge in LLMs via Explicit Priming and Implicit Reasoning Authors: Zuocheng Ying, Yang Yang, Yumou Wu, Chuanbo Zhu, Jiarui Wang, Ziqi Wu, Jingming Cai, Junqing Yu, Zikai Song Published: 2026-08-19 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2608.18581v1 Although Large Language Models (LLMs) encode rich factual knowledge in their parameters, reliably recalling and verifying such knowledge remains a key bottleneck in factual question answering. Existing end-to-end methods entangle knowledge elicitation with reasoning, making it difficult to determine whether correct answers arise from parametric knowledge or the input context. To address this challenge, we propose VAKE (Verifiable Activation of Parametric KnowledgE), a two-stage reinforcement-learning framework that externalizes latent parametric knowledge through explicit Priming and transfers the acquired elicitation capability to implicit Reasoning. Given a query and an insufficient retrieved subgraph, the Priming policy explicitly inserts bridging triples as verifiable evidence, with supervision provided by rewards derived from answers generated by a separate frozen model over the augmented subgraph. Building on the policy learned during Priming, the Reasoning stage trains the model to answer from the original input, testing whether the capability acquired through explicit knowledge elicitation transfers to implicit reasoning. Experiments across seven benchmarks and models from 3B to 14B show that VAKE consistently outperforms standard baselines, including when transferring directly from HotpotQA to OOD datasets. LLM-based evaluation further shows that over 80% of the inserted triples provide factual bridging knowledge not derivable from the retrieved context, while more than half elicit knowledge inaccessible through direct prompting. These results suggest that VAKE activates latent parametric knowledge rather than copying the input context or memorizing dataset-specific associations. --- ### FACET: Preserving Source Intent and Executable State in Terminal Task Synthesis Authors: Kou Shi, Zun Wang, Qisheng Su, Shiting Huang, Ziao Zhang, Zhen Fang, Qingnan Ren, Jin Liu, Yu Zeng, Yiming Zhao, Lin Chen, Zehui Chen et al. Published: 2026-08-19 Categories: cs.AI, cs.PL arXiv: https://arxiv.org/abs/2608.18580v1 Training terminal agents requires scalable executable supervision, yet synthesizing high-quality terminal tasks remains challenging. Each task couples an instruction, an initialized environment, a reference solution, and an executable verifier; if these artifacts are generated from inconsistent assumptions, the resulting task may be unsolvable or incorrectly evaluated. Meanwhile, multi-stage synthesis can discard the goals, dependencies, state transitions, and procedural constraints encoded in the original sources. We present FACET (Fine-grained Agentic Construction of Executable Tasks), a framework that addresses both information preservation and cross-artifact consistency. FACET reconstructs related agent skills into coherent, information-rich scenarios, then realizes and repairs the execution environment before generating the final task artifacts. The resulting container state serves as shared grounding for the instruction, solution, and verifier, while execution-based validation and targeted repair correct artifact-specific failures without unnecessarily regenerating valid components. FACET produces complex terminal tasks with dense executable checks, and successful trajectories collected from these tasks provide effective, data-efficient supervision. Fine-tuning models across multiple scales consistently improves performance on Terminal-Bench 2.1, while analyses of alternative generation schemes support the importance of environment-grounded construction for task validity and solution-verifier alignment. These results establish source-intent preservation and shared executable-state grounding as key principles for scalable terminal-task synthesis. --- ### MR-IQA-2: Faithful Image Quality Reflection via Fine-Grained Credit Assignment Authors: Yuan li, Youyuan Lin, Chenhui Chu, Shin'ya Nishida Published: 2026-08-19 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2608.18579v1 Multimodal large language models (MLLMs) have shown strong potential for image quality assessment (IQA) by improving consistency between quality ratings and their underlying reasoning. However, most approaches supervise reasoning through human-provided ratings and rarely examine whether it faithfully reflects image quality. Rating accuracy alone does not ensure faithful reasoning; a shared reward also obscures supervision sources and may reinforce unfaithful reasoning when a correct rating occurs by chance. To improve the faithfulness and reliability of blind IQA, we aim to (1) decouple credit assignment for reasoning and rating and (2) provide verifiable supervision for faithful reasoning. We introduce MR-IQA-2, an actor-editor-judge framework that operationalizes reasoning-editing-reflection. The actor generates quality reasoning for an input image, and the editor revises the image according to the identified quality factors. A frozen judge compares the original and edited images and provides reflective supervision for the actor's reasoning. MR-IQA-2 further uses fine-grained credit assignment to decouple reasoning and rating supervision. Judge feedback supervises reasoning, whereas human ratings supervise the predicted rating. Masked token-specific updates distinguish these signals while preserving the causal relation from reasoning to rating. Across IQA benchmarks, MR-IQA-2 achieves competitive rating alignment with humans. Visual reflection also enables richer and more faithful visual understanding beyond rating, which may inform image-quality optimization and related downstream tasks. Code is available at https://github.com/RobinY99/MR-IQA-2. --- ### Compress and Forget: bitsandbytes Quantization Amplifies Proactive Interference in LLMs Authors: Shayan Shahrabi-Farahani, Dara Rahmati Published: 2026-08-19 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2608.18578v2 Proactive interference (PI) is a documented failure mode in large language models in which retrieval of a repeatedly overwritten value degrades as prior overwrites accumulate, mirroring a classical phenomenon in human working memory. Post-training quantization (PTQ) is now the default deployment path for open-weight models, yet its effect on this failure mode has not been tested. We evaluate three precision levels (FP16, INT8, INT4/NF4, via bitsandbytes) across three architecturally distinct instruction-tuned models (Qwen2.5-7B-Instruct, Mistral-7B-Instruct-v0.3, Phi-3.5-mini-instruct), holding the retrieval task fixed. INT4 quantization significantly reduces accuracy under high interference in every model (e.g., from 81.0% to 68.3% for Qwen), confirmed by paired McNemar's tests ($p \le 2.6 \times 10^{-6}$) and a mixed-effects regression spanning all interference levels; INT8, often assumed safe, also carries a smaller but real penalty in two of three models. The effect is specific to semantically similar (word-type) distractors and reverses sign under a numeric control condition, and is mechanistically linked to a rise in same-key intrusion errors under INT4 (from 21.5% to 24.6% of trials, $p = 4.8 \times 10^{-7}$). A follow-up ablation shows the effect originates in the quantized transformer backbone rather than the output projection layer. These results suggest that bitsandbytes 4-bit quantization can impose an additional cost on applications relying on long, updatable, semantically dense contexts, even when aggregate benchmark accuracy appears largely unaffected. We release our code and tokenizer-verified vocabulary construction method at https://github.com/ShayanShahrabi/compress-and-forget --- ### Beyond receptive fields: sequence-pooled normalization can supply most of a sequence labeler's context Authors: Qing Tian Published: 2026-08-19 Categories: cs.LG, cs.NE arXiv: https://arxiv.org/abs/2608.18576v1 A convolutional sequence labeler's receptive field is routinely treated as the extent of the model's usable context: it sets dilation schedules, bounds streaming horizons, and underwrites locality claims. However, we show that this can be false: when a normalization layer computes statistics from the current input along the sequence at inference, those statistics open a sequence-spanning path that bypasses the convolutional receptive field to provide global context. We derive this from the layer's Jacobian (the criterion needs no experiment), and what the path carries has a closed form. On a synthetic labeling process with computable optima, the global summary that a sequence-spanning normalization encodes already supplies almost all of what a larger receptive field would buy where labels come in long runs: a network reaching 9 positions comes within 0.009 of the whole-sequence optimum, against a near-chance bound for its reach. Closing the path, by taking the same statistics per position, multiplies what enlarging the receptive field is worth by up to an order of magnitude on simulated genomes at every difficulty level tested and on real 1000 Genomes haplotypes. The same path also confounds attribution: ablating a trained network's receptive-field-enlarging blocks severs part of the path, overstating their contribution 8.3-16.1-fold relative to retraining from scratch. The substitution of normalization for receptive field fades as labels switch more often. Where labels run long, neither the receptive-field justification nor the ablation is wrong about its numbers, but both credit the wrong component. --- ### Beyond LLM-Based Reasoning: Lightweight GNNs for Agent Failure Attribution Authors: Ting-Wei Li, Yuanchen Bei, Xiao Lin, Hanghang Tong Published: 2026-08-19 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.18575v1 Large language model (LLM)-based multi-agent systems (MAS) often exhibit complex failure modes, which frequently cause agents to produce incorrect outcomes. This motivates the task of Agent Failure Attribution: given a failed multi-agent trajectory, identify the faulty agents and their corresponding error types. Existing approaches predominantly rely on LLMs to perform failure attribution, either through direct prompting, fine-tuning on synthetic data or complex agentic pipelines. While effective, these methods incur substantial computational overhead due to long-context processing, expensive post-training and handcrafted workflows. Moreover, empirical evidence shows that even state-of-the-art models achieve limited accuracy on existing benchmarks, suggesting that scaling model size alone is insufficient. In this work, we revisit this task and question the necessity of such expensive generative solutions. We introduce AFANet, a lightweight graph-based framework that models interaction trajectories through step-level semantic signals and agent-level relationships. We show that with significantly fewer parameters and near-zero inference cost, AFANet (i) matches or outperforms LLM-based baselines, including fine-tuned models on in-domain benchmarks, (ii) maintains robust performance across different GNN architectures and (iii) can be further improved with inexpensive test-time adaptation on the OOD benchmark. Our results suggest that effective agent failure attribution does not require heavy LLM reasoning and a lightweight, structured approach can achieve strong performance. --- ### Beyond Forgetting: Diagnosing and Harnessing Shared Reasoning in Continual RLVR Authors: Lirui Luo, Guoxi Zhang, Hongming Xu, Rongqing Li, Cong Fang, Lifeng Fan Published: 2026-08-19 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.18574v3 Reinforcement learning with verifiable rewards (RLVR) commonly post-trains reasoning models on multiple tasks, while rerunning multitask RLVR (MTRL) as new tasks are added makes capability expansion costly. We therefore study continual RLVR, which updates the existing model as each task arrives. The central question is whether a model updated this way can perform as well as a jointly trained model. To answer this question, we introduce Continual Reasoning Gym, a continual-RLVR environment that organizes text and visual reasoning tasks into five task sequences. In this setting, we identify two key observations: Sequential RLVR exhibits modest forgetting, yet its final performance remains below that of MTRL. To understand the latter, we decompose final performance and show that forgetting accounts for only part of the gap. To explain the former, we identify shared reasoning: transferable reasoning structure allows training on one task to support others on average. We therefore introduce Continual Prompt Replay (CPR), which harnesses shared reasoning to improve learning on the arriving and future tasks by replaying previous-task prompts and regenerating their responses with the current policy. On average, only CPR reaches MTRL-level performance. --- ### PATE-Forensics: Perception-as-Tool for Explainable Deepfake Forensics with General-Purpose MLLMs Authors: Yaqi Li, Jielun Peng, Yabin Wang, Jincheng Liu, Xiaopeng Hong Published: 2026-08-19 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.18573v1 Existing explainable deepfake forensic methods typically rely on task-adapted MLLM to jointly address detection, localization, and explanation. Inspired by agent-style tool use, we instead introduce a Perception-as-Tool paradigm and instantiate it as PATE-Forensics, which architecturally decouples detection and localization from explanation generation while coupling detection and localization as tightly as possible within a forensic perception tool. The DINOv3-based tool couples a multi-granularity detection module that integrates global, patch-level, and segment-level evidence with a cue-guided localization module by spatializing the patch-level and segment-level evidence into forgery score maps that guide dense mask prediction. The original image and forensic perception outputs produced by the tool form structured forensic context for a general-purpose MLLM, which is guided by prompt constraints to generate explanations without task-specific fine-tuning. On DDL-X Track 3, PATE-Forensics achieves the best official score of 0.89, outperforming the second-ranked team by 0.19 points. Our code is available at https://github.com/yqli00000/PATE-Forensics. --- ### VQC-ZTI: Variational Quantum Control for Zero Trust Protection of the Tactile Internet Authors: Mubassir Serneabat Sudipto, Shakil Ahmed, Ashfaq Khokhar Published: 2026-08-19 Categories: cs.CR, cs.LG, cs.NI arXiv: https://arxiv.org/abs/2608.18572v2 Tactile Internet services couple cyber events directly to physical actuation, so security decisions must improve risk discrimination without perturbing the control path. This paper presents VQC-ZTI, a split-plane Variational Quantum Classifier framework for zero-trust protection of Tactile Internet services, in which an off-path VQC analyzes encrypted-flow telemetry while an on-path policy engine applies cached deterministic grant, restrict, step-up, and deny actions. By decoupling anomaly scoring from enforcement, VQC-ZTI preserves predictable control behavior and allows detector sensitivity and policy aggressiveness to be tuned independently. We evaluate the framework on CESNET-derived aggregated traffic using random, entity-group, and temporal holdouts with a hybrid PyTorch-PennyLane implementation. The full-hybrid Quantum Neural Network achieves mean areas under the receiver operating characteristic curve of 0.9981, 0.9974, and 0.9941 and reduces the false-positive rate relative to ExtraTrees by 44.6%, 49.6%, and 67.9%, respectively. A representative component-timing decomposition further illustrates that batched VQC scoring remains in the asynchronous evidence path rather than the immediate enforcement path. --- ### NanoSleep: A Parameter-Efficient Hybrid Temporal Convolutional Network for Single-Channel Sleep Stage Classification Authors: S M Asif Hossain, Shruti Kshirsagar Published: 2026-08-19 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.18571v1 Sleep stage classification from single-channel electroencephalography (EEG) is essential for wearable and home-based sleep monitoring. However, many deep learning models achieve high accuracy at the cost of large model sizes, which limits their deployment on resource-constrained devices. In this work, we present NanoSleep, a compact hybrid temporal convolutional network for automatic sleep stage classification. NanoSleep combines a learnable Sinc-convolutional front end, a dual-branch feature extractor that fuses multi-scale temporal and spectral representations, a gated dilated temporal convolutional backbone with channel recalibration, and a conditional random field for sequence-level decoding. We further employ a weighted calibrated focal loss to address class imbalance. We evaluate NanoSleep on the Sleep-EDF and Sleep-EDF-Expanded datasets using subject-wise cross-validation. The proposed model consistently outperforms six representative baseline methods, and an ablation study confirms the contribution of each major component. These results demonstrate that NanoSleep provides an effective balance between accuracy and efficiency, making it well suited for wearable devices, home-based sleep monitoring, and resource-constrained clinical applications. --- ### Learning Topological Features of $\widehat Z$-invariants Authors: Brandon Robinson, Shimal Harichurn, Fabian Ruehle, Sergei Gukov, Rak-Kyeong Seong, Miranda C. N. Cheng Published: 2026-08-19 Categories: hep-th, cs.LG, math.GT arXiv: https://arxiv.org/abs/2608.18570v1 Machine learning and data analysis techniques have recently emerged as powerful tools for identifying patterns and formulating conjectures in mathematical research, most notably in the field of low-dimensional topology. In this paper, we initiate a systematic approach to handling mathematical data structured as (truncated) infinite $q$-series, or equivalently, infinite series of integers. To apply this data analysis pipeline, we construct a comprehensive dataset of $\widehat{Z}$-invariants (homological blocks) for plumbed 3-manifolds. We demonstrate that neural networks can reliably extract essential topological information, such as homology class and underlying graph structure, directly from the $q$-series coefficients. A central feature of our methodology is a focus on interpretability; by contrasting local gradient sensitivity with global feature relevance, we reveal that the networks learn to bypass complex topological rules in favor of specific spectral and geometric proxies. Finally, we apply this pipeline to probe homology cobordism, discovering a high-accuracy predictive relationship between the $\widehat{Z}$-invariant exponents and the Heegaard Floer $d$-invariant (correction term). These results suggest that $\widehat{Z}$-invariants capture subtle geometric information regarding cobordism equivalences, warranting a new direction for the study of quantum invariants. --- ### The Role of Grid Cells in Reducing Spatial Aliasing in Hippocampal Place Representations Authors: Alexander Johnson, Obadah Ghizawi, Ali A. Minai Published: 2026-08-19 Categories: cs.NE, cs.AI, cs.RO, eess.SY, q-bio.NC arXiv: https://arxiv.org/abs/2608.18569v1 Spatial aliasing occurs when two or more distinct locations produce highly similar place-cell representations, primarily due to environmental symmetry or repetitive structures. This issue is most pronounced when place representations are constructed solely from boundary vector cell (BVC) inputs, because symmetric or repetitive structures can yield indistinguishable sensory patterns across multiple locations in an environment. This work introduces grid cell signals to mitigate spatial aliasing in such settings. Because grid cells contribute periodic, internally generated spatial signals that vary independently of environmental geometry, they play a key role in disambiguating perceptually identical locations. We integrate multiple modules of analytically constructed grid cells with BVC-driven place cells and show that this leads to a 94--99% reduction in spatial aliasing relative to a BVC-only baseline across three environments: an open environment without obstacles; an environment with a cross-shaped central obstacle creating high visual symmetry; and a maze environment. The greatest improvement occurs in the environment with the highest visual symmetry. These results indicate that grid cells provide information complementary to boundary-based inputs, yielding more reliable place representations in geometrically ambiguous environments. --- ### SemanticSlider3D: Training-Free Continuous Semantic Editing for 3D Objects Authors: Ru Wang, Rahul Jain, Koichiro Niinuma, Aakar Gupta Published: 2026-08-19 Categories: cs.HC, cs.CV arXiv: https://arxiv.org/abs/2608.18560v2 Fine-grained control over continuous semantic attributes of 3D objects is essential for 3D content creation, but is not well supported by conventional 3D modeling workflows or prompt-based interaction with existing generative AI tools. While slider-based methods have proven effective for fine-grained semantic control in 2D image generation, no equivalent approach exists for 3D. Extending these 2D methods to 3D is non-trivial due to challenges unique to 3D, including geometric integrity and cross-view coherence. We present SemanticSlider3D, a technique for continuous semantic attribute editing of 3D objects that requires no per-attribute training. Given a user-specified attribute, our pipeline constructs a semantic editing direction in the latent space of a state-of-the-art 3D generation model, presenting a diverse and coherent spectrum of 3D variations. A technical validation on a dataset of 50 3D object-attribute pairs shows our method was preferred by all five human assessors across variation range, consistency, 3D object quality, and attribute disentanglement, over a baseline combining a 2D slider with an image-to-3D model. An exploratory study with six participants demonstrates that SemanticSlider3D supported decision-making in 3D prototyping and was perceived as a valuable addition to existing workflows. --- ### MorphoGP: A Nonparametric Framework for Predicting Equilibrium Beach Profiles Under Tidal Influence Authors: Xi Wu, Yanqing Wei, Hang Yin, Pengze Li, Hongshuai Qi, Xi Chen Published: 2026-08-19 Categories: cs.LG, cs.AI, physics.geo-ph arXiv: https://arxiv.org/abs/2608.18558v1 The prediction of equilibrium beach profiles under tidal influence is of fundamental importance for sustainable coastal development, informing shoreline protection strategies and managing coastal ecosystems under changing environmental conditions. However, it remains challenging due to the highly nonlinear interactions among wave, tide, and sedimentary processes. Traditional empirical and numerical models often exhibit limited adaptability across diverse coastal environments, with especially pronounced limitations in beach systems where tidal processes are important . To improve data-driven prediction under these conditions, this study proposes MorphoGP, a unified category-specific Gaussian process framework for predicting equilibrium beach profiles (EBPs) under tidal influence. The framework first introduces a ContourCluster model based on contrastive learning to classify tide-influenced beach morphologies automatically. Within each morphological category, a specialized Gaussian process expert learns statistical associations between environmental descriptors including waves, tides, and sediments and the beach profile's shape. A Gating Net then integrates the outputs of all experts through a probabilistic weighting mechanism to produce the final prediction. Evaluated on data from over 180 beach profiles from tide-influenced coasts along the Chinese coast, MorphoGP achieves improved predictive performance compared with conventional and deep learning models, reducing the test RMSE by about 59.3\% compared with the best baseline and achieving a final RMSE of 0.297 m. The proposed framework provides a physically informed, data-driven tool for equilibrium beach-profile prediction under tidal influence and coastal management, while stronger process-level physical coupling remains an important direction for future development. --- ### Performance Drift Detection in Machine Learning as a Service (MLaaS) for IoT Environments Authors: Deepak Kanneganti, Sajib Mistry, Sheik Mohammad Mostakim Fattah, Erik Elmroth, Aneesh Krishna, Monowar Bhuyan Published: 2026-08-19 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2608.18555v1 Machine Learning as a Service (MLaaS) is a powerful cloud paradigm enabling data-driven intelligent applications in Internet of Things (IoT) environments, widely adopted across healthcare, smart homes, and industry due to its cost-effectiveness. However, the dynamic nature of IoT frequently alters data distributions, affecting MLaaS stability, while periodic MLaaS updates further introduce performance drift. Unlike traditional ML systems, MLaaS clients operate as black-box users without access to internal data or parameters, making drift detection particularly challenging. To address this, we propose a novel MLaaS Performance Drift Detection framework for IoT environments. The framework first employs an MLaaS extraction model that learns service behavior from input-output pairs and identifies prediction-influenced features. Building on this, the proposed MLaaS Performance Drift Detection (MPDD) model jointly captures variations in input data and MLaaS behavior. We further design an Adaptive-Temporal Performance Drift Detection Mechanism (APDDM) that dynamically adjusts monitoring frequency based on behavioral and data variations, enabling timely drift detection for effective service management. Extensive experiments on real-world datasets demonstrate that MPDD achieves up to 22-25% accuracy improvement over baseline drift detection methods. APDDM provides an average accuracy gain of approximately 4% and reduces the miss detection rate by around 9% compared to fixed-interval monitoring. --- ### CentaurBench: Benchmarking LLM Capabilities on Augmenting vs. Automating Real-World Work Tasks Authors: Pattaraphon Kenny Wongchamcharoen, Kris Gulati, Min Min Fong, Abhishek Nagaraj Published: 2026-08-19 Categories: cs.CY, cs.AI, cs.MA, econ.GN arXiv: https://arxiv.org/abs/2608.18554v1 Most LLM benchmarks rank models on their ability to automate work tasks. In practice, however, models are often used to assist other (human or LLM) agents. The question that drives model selection is therefore not only which model produces the best output, but which model most improves the work of another (weaker) agent. We introduce a unified framework that evaluates the capability of models to automate and augment another agent's performance. Across seven economically grounded real-world tasks, an assistant model writes assistance text for a standardized lower-capacity worker model, which produces the deliverable. In automation mode, the assistant produces the output directly. Outputs are scored through blind pairwise comparisons by an LLM judge panel with task-specific rubrics, replicated across ten runs. Rankings across the two regimes are only modestly correlated, and the automation winner loses augmentation on five of seven tasks. Assistance is not reliably positive. The unaided worker outranks every assisted condition on three tasks, and only one model's guidance beats no guidance on average. These results suggest that automation ability is an incomplete proxy for assistance quality, motivating benchmarks that evaluate models according to the roles they play in human-AI and multi-agent systems. --- ### MARCUS: Missing-Aware Region Representation with Contextual Urban Signals for Rent Prediction Authors: Chenya Huang, Bin Liang, Zhidong Li, Yuxi Lu, Kunqi Li, Justin Wang, Fang Chen Published: 2026-08-19 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.18546v1 Multimodal urban data has expanded the applications of urban region representation learning, such as functional zone identification and real estate appraisal, but also introduces challenges caused by data incompleteness. Existing studies usually handle missing data through imputation, treating missingness as noise while ignoring its potential semantic value. To address this issue, we propose MARCUS, a missing-aware region representation model that treats missingness as a contextual urban signal. MARCUS models missingness in three stages: Intra Learning jointly encodes observed features and missing patterns, Inter Learning estimates modality reliability to guide cross-modal interaction, and Fusion uses missing-aware and time-aware gating to generate the final region embedding. We apply MARCUS to rent prediction, a task with long-term trends and seasonal fluctuations, using real-world datasets from Sydney and New York. Experimental results show that MARCUS achieves state-of-the-art performance, reducing MAE by 51.35% on Sydney and 12.62% on New York compared with the best baselines. Additional experiments, including an imputation-based ablation study and randomized additional-missingness analysis, further demonstrate the effectiveness of the proposed method. --- ### Shared Circuits for Shared Grammar: Tracing Subject-Verb Agreement Across Languages Authors: Isabella Gidi, Antonio Almudévar, Core Francisco Park, Naomi Saphra, Ricard Marxer Published: 2026-08-19 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.18545v1 Multilingual large language models often generalize across languages, and prior work suggests that their internal mechanisms can overlap cross-lingually. It remains unclear, however, when such sharing emerges and whether it varies with the overt realization of the same grammatical operation. We investigate this question for present-tense subject-verb agreement, a morphosyntactic process that varies substantially across languages and is only weakly expressed in English. Using activation patching and attention analysis across 29 languages and five open-source model families, we identify the attention heads causally implicated in agreement and compare these head-level signatures across languages. We find that languages with overt person/number inflection exhibit more similar agreement circuitry than non-conjugating languages, with the strongest sharing appearing when the analysis isolates recovery of the inflectional contrast itself. English provides an informative bridge case, becoming more similar to conjugating languages precisely in contexts where overt agreement is required. Finally, many implicated heads display similar attention patterns across languages, suggesting that cross-lingual overlap reflects shared functional roles as well as shared localization. Together, these results indicate that multilingual LLMs reuse partially shared computational structure for morphosyntactic agreement rather than relying on fully separate language-specific solutions. --- ### Zero-Shot SAM2 Segmentation and Vision Transformer-Based Recognition of Elamite Cuneiform Symbols from Degraded Tablet Images Authors: Utsav Poudel, Rasik Bhattarai, Siddhartha Pathak, Raghavendra Ramacharna, Gaurav Jaswal Published: 2026-08-19 Categories: cs.CV, cs.HC arXiv: https://arxiv.org/abs/2608.18544v1 Automated recognition of ancient cuneiform script poses a compound signal-degradation problem: the three-dimensional relief of clay tablets creates spatially varying illumination and cast shadows, surface erosion introduces structured noise that overlaps with genuine sign impressions, and severe class imbalance across 141 sign categories undermines classifier reliability. We introduce EpigraphNet, a segmentation-guided transformer pipeline evaluated on the Persepolis Fortification Archive. From 1,239 annotated tablet images, brightness-adaptive morphological preprocessing and zero-shot SAM2-Large segmentation generate clean binary symbol masks, which a fine-tuned Vision Transformer (ViT-B/16) with inverse-frequency class weighting then classifies. EpigraphNet reaches 86.41% top-1 accuracy on a 132-class benchmark, a 17.21 percentage-point gain over the strongest CNN baseline (ResNet-101, 69.20%) and 5.31-12.91% over four modern backbones (DeiT-B/16, Swin-B, ConvNeXt-B, EfficientNet-B4) under identical conditions. The full pipeline runs at approximately 18 ms per sign on an NVIDIA A100 GPU. A lower Spearman correlation between sign frequency and per-class performance indicates more balanced recognition across frequent and rare classes. Implementation is available at: github.com/r11up/sam-guided-vit --- ### Bridging Search and CRM: Productionizing AI Product Research Agents for Customer Re-Engagement Authors: Mandar Kulkarni, Pooja A., Samir Shah Published: 2026-08-19 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.18543v1 Modern e-commerce platforms often operate search, recommendation, personalization, and CRM systems independently, limiting opportunities for proactive customer re-engagement. This is particularly challenging for exploratory intents such as best smartphones or latest 5G phones, where users may leave the platform for external research before purchasing. We present a scalable, production-deployed framework that bridges search and CRM workflows through AI-powered Product Research Agents. The system identifies users with exploratory purchase intent and low engagement, conducts grounded multi-agent product research using behavioral signals, external knowledge, and enterprise catalog data, and delivers personalized recommendations through WhatsApp. We evaluate the framework in a 23-day production deployment involving approximately 15K WhatsApp notifications for mobile product discovery. The campaign achieved substantial CTR improvements over traditional WhatsApp recommendation campaigns, with evidence of secondary engagement through message forwarding and sharing. The deployment also generated downstream purchases and GMV impact, demonstrating the practical effectiveness of AI Product Research Agents for proactive customer re-engagement and end-to-end customer journey optimization. --- ### Evaluating and Explaining Prompt Sensitivity of LLMs Using Interactions Authors: Ruiyang Qin, Qingzhuo Wang, Tian Wang, Zhihua Wei, Wen Shen Published: 2026-08-19 Categories: cs.LG, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2608.18539v1 The remarkable capabilities of large language models (LLMs) are often undermined by their instability. Even subtle and semantically irrelevant changes in prompts can cause dramatic fluctuations in performance, a phenomenon known as prompt sensitivity. Previous studies typically evaluate prompt sensitivity by comparing the LLM's final outputs when prompts change. However, such coarse-grained metrics fail to explain the internal reasons for prompt sensitivity. In this paper, we introduce interactions as a fine-grained tool to analyze prompt sensitivity of LLMs. Specifically, we decompose the output score of the LLM into a set of interactions. Each interaction represents a nonlinear relationship involving a set of input variables. We discover that subtle changes to prompts can trigger severe instability in interactions, even when the outputs of the LLM remain the same. To this end, we propose an Interaction-based Prompt Sensitivity (IPS) metric by quantifying changes in interactions when we introduce subtle changes to prompts. We apply the IPS metric to 50 open-source LLMs and uncover four factors that reduce the prompt sensitivity of LLMs, including supervised fine-tuning, increased model scales, dense architectures, and few-shot learning. More crucially, we discover a common mechanism by which these four factors reduce prompt sensitivity: all four factors tend to reduce the prompt sensitivity of low-order interactions (i.e., interactions involving few input variables). --- ### FinRCA-Bench: Benchmarking Evidence Retrieval and Reasoning for Financial AI Systems Authors: Pratik Ghawate Published: 2026-08-19 Categories: cs.AI, cs.IR arXiv: https://arxiv.org/abs/2608.18534v1 Large language models are increasingly used to support financial operations, but their apparent reasoning performance can depend on whether they receive the right evidence. In financial reconciliation, the evidence needed for diagnosis is distributed across invoices, purchase orders, approvals, allocations, payments, ledger entries, and bank activity, linked by transactional relationships rather than textual similarity. End-to-end accuracy can therefore conflate evidence access with reasoning quality. We introduce FinRCA-Bench, a deterministic synthetic benchmark of 2,250 accounts-payable-to-bank reconciliation cases spanning 14 operational tables, including 1,500 injected failures across 15 causal categories and 750 legitimate or hard-negative cases. Root-cause labels and record-level evidence contracts are hidden from the model, allowing retrieval to be evaluated independently of answer correctness. We compare Rules/SQL, classical machine learning, dense semantic retrieval, deterministic relational expansion, and Typed Provenance Graph Retrieval (TPGR), a typed traversal restricted to persisted transaction relationships. Rules/SQL reaches 84.97% held-out exact accuracy and classical ML reaches 95.44%. Holding the reasoning model, prompt, and generation settings fixed while changing only retrieval increases macro required-record recall from 0.83% to 77.70% and exact 16-class accuracy from 2.05% to 72.44%. Structural retrieval failures outnumber reasoning failures with sufficient retrieval by 95 to 15; 254 correct predictions occur despite incomplete retrieval, and strict returned-evidence contract accuracy is only 5.72%. On FinRCA-Bench, retrieval architecture strongly shapes observed AI-system performance, and a correct root-cause label is a weak proxy for an auditable diagnosis. --- ### StateTrace: An Object-Centric Framework for Hidden-State Spatiotemporal Reasoning in Long Videos Authors: Yu Han, Wenhao Li, Yichao Cao, Hongyan Xu, Shuo Yang, Shan You, Xiu Su Published: 2026-08-19 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.18532v1 Existing VLMs have achieved strong performance in video understanding, yet they struggle with long-video spatiotemporal reasoning when target objects become invisible, often mistaking "invisible" for "unknown". We define this challenge as hidden-state spatiotemporal reasoning: inferring object states during prolonged invisible intervals from context interactions. To address this, we propose StateTrace, a novel object-centric framework that endows VideoLLMs with an explicit mechanism for hidden state reasoning in long videos. StateTrace builds a reusable spatiotemporal state memory that organizes object trajectories, inter-object relations, and state-transition events into a structured reasoning substrate. At inference time, it retrieves question-relevant state-evolution trajectories and converts them into compact reasoning cues, enabling the model to explicitly reason about why an object disappears, how its state evolves while invisible, and whether that state should persist at query time. We further build HSR-Bench, a diagnostic benchmark for hidden-state reasoning, containing 1,427 video-QA samples from 1,384 unique videos. Extensive experiments across multiple VideoLLMs show that StateTrace consistently improves performance on both public benchmarks and HSR-Bench (e.g., improving VideoLLaMA3 from 39.6 to 64.2 on HSR-Bench). --- ### Pairwise Ranking Outperforms Single-Action RL for Offline Explanation Selection: A Practical Lesson Authors: Tanay Chowdhury, Saeideh Shahrokh Esfahani Published: 2026-08-19 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2608.18531v2 Industrial explainable-recommendation systems built on LLMs incur a substantial serving cost: each request triggers an LLM generation, with latency in the hundreds of milliseconds and cost that scales linearly with traffic. We separate generation from selection: explanations are produced ahead of time as a frozen candidate pool (six prompt styles, two commodity LLMs), and a small CPU-resident selector picks one at request time. The stack needs no GPU and returns in under 100 ms. Our primary benchmark is a 2,958-pair XRec Google Local subset, evaluating six offline-pool selectors (LambdaRank, PPO, GRPO, DPO, teacher-student distillation) and three KG-path selectors (random walks, edge-disjoint enumeration, MMR-reranked paths). A 300-pair MovieLens-1M split with Claude-Sonnet-4.5 references serves as an internal cross-dataset check, since no public benchmark exists for this setting. All variants use the same BERTScore-F1 protocol as XRec and G-Refer, averaged across five seeds. LambdaRank reaches F1 = 0.500 on Google Local, exceeding both G-Refer and XRec, and F1 = 0.329 on the MovieLens-1M check. With seed variance below 0.003 F1, the ordering is reliable: pairwise learning-to-rank outperforms single-action RL (PPO, GRPO, DPO), which use only one labelled candidate per rollout, leaving K-1 labels unused. The KG-path family targets a different objective: all three variants reach USR = 1.000 on Google Local and 0.997-1.000 on MovieLens-1M, since per-request path grounding yields a unique output per query, avoiding template-collapse failures affecting cached-LLM outputs. A generator-pool study comparing Claude 3 Haiku and Claude Haiku 4.5 shows small F1 shifts (0.001-0.006) while preserving selector ranking: selector and generator can be evaluated independently, though absolute F1 depends on the generator. End-to-end build cost is near $15 on commodity hardware. --- ### DART-SD: Diamond-topology Aware Retrieval and Tuning for Self-Distillation of Multi-Turn Tool-Calling Agents Authors: Hangrui Xu, Jiarui Wang, Yang Yang, Chuanbo Zhu, Fangda Chen, Ziqi Wu, Jingming Cai, Yan Song Published: 2026-08-19 Categories: cs.CL, cs.AI, cs.LG, cs.MA arXiv: https://arxiv.org/abs/2608.18524v1 Equipping Large Language Models (LLMs) with multi-turn tool-calling capabilities is essential for building autonomous agents. However, progress is fundamentally limited by the reliance on full-length trajectory imitation. For tasks involving multiple order-independent sub-goals, the optimal solution space forms a vast combinatorial diamond lattice. Forcing this rich topology into monolithic trajectories causes a severe topological collapse, indiscriminately penalizing valid alternative explorations and severely degrading policy diversity. To address this, we propose DART-SD (Diamond-topology Aware Retrieval and Tuning for Self-Distillation), a novel framework that shifts the paradigm from global forcing to topology-guided localized correction. DART-SD first models the execution process as a converging Interaction-State Transition Graph (ISTG), faithfully capturing the inherent diamond topology of successful and failed exploratory paths. During autonomous rollouts, the framework identifies the Critical Topological Breakpoint (CTB) and retrieves success-supported recovery references. Finally, we introduce a progressive self-distillation paradigm through CTB-guided localized supervision, ensuring that the training loss is calculated exclusively on the generated recovery steps while strictly protecting the valid reasoning prefix from destructive gradient updates. Experiments on complex multi-turn tool-calling benchmarks demonstrate that DART-SD significantly outperforms traditional full-trajectory baselines. --- ### Prior-Conditioned Gaussian Discriminants for Generalizable AI-generated Image Detection Authors: Shashank Kotyan, Makoto Shing, Yuki Imajuku, Rujikorn Charakorn, Tarin Clanuwat Published: 2026-08-19 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2608.18523v1 Diffusion-based generators have made synthetic images ubiquitous, but detectors often fail under simultaneous shifts in generator, prompt/style, and source-domain. We study AI-generated image detection as a transfer system described by training prior, frozen encoder feature space, and decision rule, and ask when classifier head training adds value beyond what is already separable in modern features. As a controlled diagnostic, we fit a prior-conditioned Gaussian discriminant ladder: closed-form heads built from first- and second-order feature statistics under nested covariance assumptions. On Percept-Lens, a unified protocol over 39 public datasets (7.1 million images), the best rung is frequently competitive with, and sometimes exceeds, released AI-generated image detector heads when matched on both prior and encoder. We further quantify strong sensitivity to the training prior, data-efficiency of moment-based heads, and representation dependence of Gaussian shift metrics, motivating (prior, encoder, head)-level reporting and stronger analytical baselines for AIGI transfer. --- ### GCNO: Gramian Chebyshev Neural Operator for Physics-Based Compression of Wireless Channels Authors: Rafid Umayer Murshed, Shahab Hamidi-Rad, Elahe Soltanaghai, Akshay Malhotra Published: 2026-08-19 Categories: cs.IT, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2608.18522v1 Large antenna arrays allow wireless systems to serve more users and achieve higher data rates, but they also make channel feedback expensive: the receiving device must repeatedly report a large complex-valued channel matrix to the base station. Most neural compressors treat this matrix like an image and replace it with a fixed-length code that only a matched neural decoder can interpret. The message therefore does not adapt to channel complexity, and changing the antenna count typically requires retraining. We ask whether a device can instead report only the few dominant propagation paths underlying each channel. We introduce the Gramian Chebyshev Neural Operator (GCNO), a physics-based, variable-rate compressor that identifies a sample-dependent set of path directions. GCNO uses receive-transmit channel structure to locate paths, a first-order Taylor correction to refine directions that fall between grid points, and least squares to recover their complex strengths. It is trained without path labels, and the base station reconstructs the channel analytically from the transmitted path tuples rather than through a learned decoder. Across three ray-traced environments, GCNO achieves better reconstruction accuracy at the same payload - or lower payload at the same accuracy - than neural feedback baselines, and transfers to unseen antenna counts without retraining. --- ### Which Negatives Matter? Ask Your Text Encoder: Adaptive Similarity Margins for Dense-Caption Retrieval Authors: Haoyue Liu, Ye Chen, Zhichao Wang, Xiaoying Tang Published: 2026-08-19 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2608.18521v2 Dense-caption retrieval has recently been improved by introducing segmentation, edge maps, LLM-filtered captions, and cross-modal modules into contrastive fine-tuning. However, these methods largely inherit the same InfoNCE objective, whose optimization can prematurely saturate under a strong pre-trained initialization: on dense captions, the loss falls below 10^-3 on 80% of batches within the first epoch, while its gradient becomes numerically zero in 47% of measurements. We find that this behavior is closely related to the large number of near-duplicate captions in dense-caption benchmarks, where a few highly similar negatives remain unresolved after the easy majority has already been separated. As a remedy, we introduce HN-CLIP, which uses the text encoder's own text-text geometry to construct per-negative adaptive similarity margins. Specifically, a detached caption-similarity matrix is added to the negative logits, assigning larger margins to more similar captions without mining, synthesizing, or resampling negatives. The resulting objective requires only one caption-similarity matrix and a masked logit addition during training, with no auxiliary data, additional parameters, offline preprocessing, or inference-time overhead. Extensive experiments on four dense-caption retrieval benchmarks show that HN-CLIP improves over the strongest competitors by +2.5 to +4.0 R@1 while training 2.4x faster than GOAL and 5.4x faster than StructXLIP. Moreover, the proposed objective improves all six tested fine-tuning frameworks on the in-domain benchmarks and reaches the strongest full-data baseline with only 20% of the training data. --- ### OptiModNet: A UNet-Transformer Hybrid with Grouped-Query and Channel Attention for Optic Disc and Cup Segmentation Authors: Soumili Ghosh, Debapriya Roy, Aryan Das, Bikash Santra Published: 2026-08-19 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2608.18516v1 Precise segmentation of the optic disc and cup is critical for the early detection and diagnosis of glaucoma. However, achieving consistently high performance across datasets while maintaining low computational requirements remains a significant challenge. In glaucoma detection, low-computation methods are crucial for enabling rapid, large-scale screening and facilitating deployment in resource-limited clinical environments. While deep learning models such as UNets, Vision Transformers (ViTs), and Diffusion models have demonstrated strong segmentation performance but these methods often come with substantial computational overhead. UNets are efficient at capturing local features but are limited in modeling global contextual information. Conversely, ViTs excel at long-range dependency modeling but are computationally intensive. Hybrid architectures, such as UNetR, which combine transformer-based encoders with UNet-style decoders, have shown improved performance but while incurring additional complexity. Considering these, in this work, we propose OptiModNet, a light weight novel hybrid architecture tailored for optic disc and cup segmentation. The model integrates diverse attention mechanisms at multiple stages of the network to enhance both local and global feature representation. We include an Aggregated Pyramid Loss that supervises predictions at multiple decoder depths, to promote better gradient flow and structural consistency. We evaluate OptiModNet on the REFUGE2 dataset for both optic disc and cup segmentation tasks. Our method achieves state-of-the-art performance, exceeding existing approaches by over 2.5\%, while maintaining high efficiency with only 3.73 GFLOPs and 1.93M parameters. The code is available at https://github.com/SG1947/OptiModNet. --- ### Cross-Modal MRI Ovary Segmentation in Endometriosis Using Unpaired TVUS Prototype Priors Authors: Xingjian Kang, Lina Felsner, Dominik Perrin, Daiqi Liu, Jasmin Arjomandi, Franziska Mathis-Ullrich, Alexandra Stoll, Katharina Breininger Published: 2026-08-19 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.18515v1 Transvaginal ultrasound (TVUS) and magnetic resonance imaging (MRI) provide complementary information for endometriosis image analysis, yet existing studies mainly focus on single-modality analysis or disease classification, leaving cross-modal ovarian segmentation largely unexplored. In this work, to tackle the increased difficulty of ovary segmentation in MRI due to ovaries' small target size and ambiguous boundaries with surrounding pelvic structures, we propose a dual branch framework for ovary segmentation across TVUS and MRI. More specifically, by adapting MedSAM3 with TVUS-derived prototype bank, we aim to align anatomically consistent feature representations across both modalities. Extensive experiments are conducted on endometriosis-related TVUS and MRI datasets. We observe quantitative and qualitative improvements of over 5 percentage points for the proposed dual-branch approach compared with multiple state-of-the-art methods. Furthermore, our ablation study shows the contribution of individual components such as the prototype bank and the importance of warm-up pretraining in the source TVUS domain. --- ### Science Done on a Machine by a Machine: AI Agents in Computational Chemistry Authors: Pavlo O. Dral, Hassan Nawaz, Arif Ullah Published: 2026-08-19 Categories: physics.chem-ph, cs.AI, physics.comp-ph arXiv: https://arxiv.org/abs/2608.18508v1 We are witnessing an explosion of agentic systems for computational chemistry simulations: from half a dozen in 2024 to a dozen in 2025, and the current number approaches fifty, surveyed in this Perspective as of 8 August 2026. The capabilities of these agentic systems are shifting from assisting in performing a selection of computational tasks to autonomous design and execution of \textit{in silico} experiments, their analysis, and even manuscript writing. The ultimate destination is a fully autonomous AI scientist, where the entirety of computational chemistry is performed on a machine by a machine, without human supervision. While we are not there yet, and all reported systems currently involve a human in the loop, the trend is unmistakable. Even building specialized agentic systems for computational chemistry is increasingly commoditized by generalist agents, which may in the end replace the need for the specialized ones altogether, since adding a new capability will be as easy as asking AI to do it for you. Both the explosion in their number and the very limited adoption beyond their own developers point that way, and we close this Perspective on what it leaves us to do. The speed and scale of disruption agentic systems are bringing to computational chemistry leave many of us dumbfounded about the field's future and what we should spend our efforts on, as already established specialists, teachers, and students, and we have no answer. --- ### UMER: Unifying Embedding and Ranking via Pair-Aware Discriminative Reasoning for Universal Multimodal Retrieval Authors: Libiao Chen, Xiyang Liu, Yanheng Wei, Tao Wang, Zhenyu Tang Published: 2026-08-19 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.18504v2 Universal multimodal retrieval aims to support diverse instruction-aware retrieval tasks, demanding both efficient corpus-scale matching and fine-grained semantic reasoning. Recent MLLM-based embedding methods typically derive representations from hidden states, while Chain-of-Thought (CoT) reasoning is emerging as a promising strategy for embedding enhancement by encoding intermediate semantic evidence into the representation space. However, existing CoT methods typically use item-wise reasoning over queries and candidates in isolation, providing no explicit evidence to distinguish a positive from a semantically confusable hard negative. Moreover, contrastive embeddings capture global similarity but struggle with meta-tasks requiring answer verification, category judgment or fine-grained reasoning. In this paper, we propose UMER, a Unified Multimodal Embedding and Ranking framework for universal multimodal retrieval. UMER replaces item-wise reflection with Pair-Aware Discriminative Reasoning, which compares query--candidate pairs to identify instruction-relevant matching and discrepancy evidence. UMER jointly learns contrastive embeddings for efficient global matching and discriminative ranking for explicit pairwise relevance judgment within a single MLLM. A complementary mutual distillation strategy further transfers reliable pairwise preferences between the embedding and ranking functions. On the MMEB-V2 benchmark, UMER achieves state-of-the-art performance under comparable experimental settings while supporting budget-adjustable inference. --- ### LLM-Powered Predictive Decision-Making for Sustainable Data Center Operations Authors: Hanzhao Wang, Jingxuan Wu, Yumeng Li, Yu Pan, Guanting Chen Published: 2026-08-19 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.18503v1 The growing demand for AI-driven workloads, particularly from Large Language Models (LLMs), has raised concerns about the significant energy and resource consumption in data centers. This work introduces a novel LLM-based predictive scheduling system designed to enhance operational efficiency while reducing the environmental impact of data centers. Our system utilizes an LLM to predict key metrics such as execution time and energy consumption from source code, and it has the potential to extend to other sustainability-focused metrics like water usage for cooling and carbon emissions, provided the data center can track such data. The predictive model is followed by a real-time scheduling algorithm that allocates GPU resources, aiming to improve sustainability by optimizing both energy consumption and queuing delays. With fast inference times, the ability to generalize across diverse task types, and minimal data requirements for training, our approach offers a practical solution for data center scheduling. This framework demonstrates strong potential for advancing sustainability objectives in AI-driven infrastructure. Through our collaboration with a data center, we achieved a 32% reduction in energy consumption and a 30% decrease in waiting time. --- ### Tianmu-TC: Physics-constraints Generative Artificial Intelligence for Global Tropical Cyclone Forecasting Authors: Shiqi Zhang, Pan Mu, Cheng Huang, Hanting Yan, Yuchao Zhu, Jinglin Zhang, Shengyong Chen, Shoujuan Shu, Cong Bai Published: 2026-08-19 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.18500v1 Tropical cyclones (TCs) pose severe risks from strong winds and heavy rainfall. However, forecasting their track and intensity remains challenging due to chaotic atmosphere and the rapid amplification of initial condition errors, leading to growing forecast uncertainty. While numerical weather prediction (NWP) and deep learning models have made progress, they remain computationally demanding and often fail under complex meteorological scenarios. Here, we present Tianmu-TC, a physics-constraints generative framework for global TC forecasting. Trained on Western North Pacific data, Tianmu-TC leverages physics-constraints to generate controllable outputs with reduced uncertainty thus improving forecast reliability. Experiments show Tianmu-TC outperforms deterministic and ensemble meteorological artificial intelligence models and authoritative NWP systems such as ECMWF in global ocean basins, with significantly lower computational cost. We further show Tianmu-TC performs well in challenging scenarios such as data sparsity, anomaly tracks, rapid intensification and weakening. These findings suggest physics-constraints generative AI offers a promising approach for reliable, efficient global TC forecasting. ---