# Research Papers — 2026-08 · bundle page 158 of 240 > Full-text markdown of papers #7851–7900 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/158 [← Previous bundle](https://aipod.dev/papers/archive/2026-08/page/157.md) [Next bundle →](https://aipod.dev/papers/archive/2026-08/page/159.md) ### Deep Analog: Open-Set Film Emulation with Reference-Conditioned 3D LUTs Authors: Yitong Mu Published: 2026-08-10 Categories: cs.CV, cs.GR, cs.LG, cs.MM arXiv: https://arxiv.org/abs/2608.14702v1 Film emulation reproduces the look of an analog film stock on a new digital photograph. We target its open-set form -- matching any reference film frame from a single example -- with a 3D lookup table (LUT) predicted from that reference. Real-time image enhancement predicts per-image weights over a fixed bank of 3D LUTs and blends them. We show this is a gated mixture of experts and inherits its failure: trained end-to-end against reconstruction, the gate collapses onto a single expert, so a bank of K LUTs delivers the capacity of one. An entropy term, the enhancement-setting analogue of mixture-of-experts load balancing, restores utilization and recovers about 1 dB PSNR. The deeper constraint survives: a fixed LUT basis is closed-set, freezing the achievable looks at training time. We therefore discard the basis and predict a single 3D LUT as a residual from a reference image (StyleLUTNet), trained by self-supervision on procedurally generated color transforms. The conditional design removes the gate and generalizes open-set to unseen film stocks without paired data or retraining. Around this color backbone we build Deep Analog, a film-emulation pipeline that adds histogram-based tone matching and a physics-informed optical renderer -- multi-scale grain and per-channel halation driven by parameters an inverse network regresses from the reference. On 350 self-supervised pairs the color stage reaches 22.05 dB PSNR / 0.925 SSIM and the full pipeline 21.72 dB / 0.923; the color path runs in 5.2 ms at 1080p (192 FPS) and exports a portable .cube LUT for standard editing tools. A second degeneracy in conditional LUT training -- residual-scale collapse -- shares the root cause and yields a general principle: auxiliary regularization must stay subordinate to reconstruction. --- ### Periocular Soft Biometrics: A Survey and Applications to Multimedia Forensics and Disinformation Detection Authors: Fernando Alonso-Fernandez, Kevin Hernandez-Diaz, Josef Bigun Published: 2026-08-10 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.14701v1 Soft-biometric attributes such as gender, age, and ethnicity provide valuable ancillary evidence when full identity recognition is not feasible, supporting applications in forensic investigation, identity verification, surveillance, or detection of synthetic and manipulated media. Among biometric modalities, the periocular region is a robust source of soft-biometric cues, as it often remains visible when other parts of the face are occluded, a frequent condition in forensic evidence and surveillance footage, and can be captured across a wide range of acquisition conditions. In this paper, we provide a survey of demographic attribute estimation from periocular images, covering publicly available datasets, methodological trends from handcrafted descriptors to deep learning architectures, and the state of the art in gender, age, and ethnicity prediction. We discuss use cases relevant to multimedia forensics and disinformation-detection applications, including demographic filtering in surveillance footage, age verification, and the detection of demographic inconsistencies in synthetic data. We also highlight open challenges, including dataset bias, cross-domain generalisation, fairness, ethical aspects, and the lack of forensic-oriented benchmarks. --- ### Xemo-Talker: Unlock Emotions Explicitly for Audio-Driven Talking Portrait Synthesis Authors: Chaolong Yang, Yinuo Guo, Kai Yao, Yuyao Yan, Jie Sun, Guangliang Cheng, Shibin Wu, Bin Dong, Kaizhu Huang Published: 2026-08-10 Categories: cs.CV, cs.SD arXiv: https://arxiv.org/abs/2608.14700v1 Precise emotion control in audio-driven talking heads remains a challenge due to the reliance on implicit emotion regulation in existing systems, which often leads to indirect and insufficient control. Additionally, training with explicit emotion-related losses across the entire motion space poses significant difficulties due to the inherent trade-off between accurate lip synchronization and fine-grained emotion control. In this paper, we reveal a key finding: although emotional cues are distributed throughout the motion space, concentrating discriminative supervision on less-principal components achieves a better emotion-lip synchronization balance, as principal components mainly encode high-energy articulation and pose variations. Building on this insight, we propose Xemo-Talker, which first learns a neutral speech-to-motion mapping for stable articulation and lip synchronization, and then introduces a lightweight emotion branch guided by less-principal subspace supervision. To enhance emotion control, we design a Tri-Loss consisting of inter-class separation, intra-class compactness, and less-principal contrastive learning. Given an audio input, a reference image, and an emotion label, Xemo-Talker achieves state-of-the-art emotion classification accuracy while maintaining competitive lip synchronization and high inference efficiency, with performance approaching that measured on real videos.The source code is publicly available at https://github.com/chaolongy/Xemo-Talker. --- ### Black-Box Knowledge Transfer across Distinct Feature Sets Authors: Oh-Ran Kwon, Daeyoung Ham Published: 2026-08-10 Categories: stat.ML, cs.LG, stat.ME arXiv: https://arxiv.org/abs/2608.12403v1 Pre-trained black-box predictive functions encode knowledge distilled from massive datasets and extensive computation. However, when the available input features differ from those the black box expects, direct use is infeasible. We introduce a method for transferring predictive knowledge from the black box to a new, heterogeneous input space. Our approach decomposes the target regression function into a transferable component, which the black box can inform, and a non-transferable component, which captures information unique to the new space. We propose a two-step neural network procedure, estimating the transferable component from abundant unlabeled feature pairs that bridge the two input spaces and the non-transferable component from limited labels. We derive prediction risk bounds that improve on those of a non-transfer alternative when the non-transferable component is small or smooth, and the procedure adapts to either case. Under additional conditions, the worst-case risk of our estimator is of strictly smaller polynomial order than the minimax risk of estimation from the labeled data alone. We extend the framework to multiple black boxes, each on its own input space, and show that aggregation can reduce prediction error relative to the best single black box. Simulated and real data demonstrate the practical value of the method. --- ### Decodable but Not Accessible: Auditing Distance-Based Reliability Estimation on Disentangled Skin-Lesion Representations Authors: Duc-Vinh Tran Published: 2026-08-10 Categories: eess.IV, cs.CV arXiv: https://arxiv.org/abs/2608.11267v1 Distance-based reliability estimation assumes that a representation's geometry reflects its trustworthiness, yet this assumption is rarely tested under training interventions that reshape geometry directly. We audit this assumption under domain-adversarial representation learning using a disentanglement dose-response ladder. Three checkpoint families share the same architecture and a 16-dimensional representation, differing only in orthogonality strength (lambda = 0, 1, 5). Representation geometry changed substantially with disentanglement strength: the condition number shifted by two orders of magnitude (Kendall tau = 0.84, exact p = 2.8e-5). This change was not accompanied by improved reliability estimation: Mahalanobis-distance AUROC (ISIC-test vs. PAD-UFES) remained flat and below chance (about 0.40) at every level, with no significant association with any of five geometry metrics tested. The same failure was observed for cosine-to-centroid and pooled k-nearest-neighbor scorers, plus three non-distance-based scorers: an energy-based confidence score, Virtual-Logit Matching, and a kernel density estimator. Seven of eight scorers converged on the same result; the energy-based score showed an isolated upward trend that we report but do not treat as evidence against the overall pattern. A supervised probe with no access to the training objective recovered domain membership from the identical embeddings at 0.72-0.81 AUROC across every level, showing that the relevant information was not absent from the representation. These findings indicate that classification performance alone can overlook whether information in a learned representation is organized in a form that downstream reliability estimators can use. Information can remain decodable while becoming largely inaccessible to non-probing reliability estimators. --- ### GeoUniPR: A Geometry-Consistent Unified Framework for Cross-Modal Place Recognition Authors: Wonbong Kim, Jiatong Xiao, Rui Li, Xufei Wang, Qiwen Gu, Junqiao Zhao, Chen Ye, Guang Chen Published: 2026-08-10 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.11263v1 Cross-modal place recognition (CMPR) aims to identify the same location across heterogeneous sensing modalities, such as vision and LiDAR. Existing methods commonly bridge the modality gap using complex alignment modules, multi-stage training, or full fine-tuning of pretrained backbones. In this work, we revisit CMPR from the perspective of geometric consistency and propose GeoUniPR, a unified and concise geometry-consistent framework. GeoUniPR reduces cross-modal discrepancy at the representation level by projecting LiDAR point clouds into the camera perspective to construct Geometry-Consistent depth image views (DIV), which establish direct RGB-LiDAR correspondence. We further augment DIV with native LiDAR cues, including intensity and surface-normal information, yielding a multi-channel geometric representation that improves structural consistency. Based on this representation, GeoUniPR learns a unified embedding space using two modality-specific ViT-based encoders with identical architectures, trained through parameter-efficient adaptation without auxiliary alignment modules, multi-stage training, or full backbone fine-tuning. In addition, we introduce Spatially-Consistent InfoNCE (SC-InfoNCE), a CMPR-specific contrastive objective that suppresses distance-induced false negatives under spatial continuity. Extensive experiments on KITTI and KITTI-360 demonstrate that GeoUniPR achieves state-of-the-art (SOTA) performance in both same-modal and cross-modal place recognition, with strong cross-dataset generalization. --- ### Toward a Theory of Value in AI Alignment Authors: Andrew Smart, Shazeda Ahmed, Jackie Kay, Jimmy Tobin, Kris Shrishak, Abeba Birhane Published: 2026-08-10 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.10327v1 Can AI systems be aligned to human values? The popularization of large language models (LLMs) and multi-modal foundation models has seen a rise in harms spanning from toxic speech and hallucinations to AI agents executing unauthorized actions. Within the field of AI safety, these harmful instances are often framed as the alignment problem, or of models being misaligned with human values. Researchers have responded by pursuing applied and theoretical AI value alignment efforts, often without specifying what they mean by human values. How does the field of AI value alignment conceive of human values? How are these conceptions of values technically operationalized and evaluated? What does the emergent theory of value from this field signify for the future of AI? We annotated 94 value alignment research papers to discern their implicit theory of values in AI. The majority do not define values, relying heavily on preferences as a stand in that runs the risk of reducing complex culturally situated concepts down to binary choices. As researchers dispense with using human annotators for model training and evaluation, turning instead to synthetic data and autorater approaches to aligning and evaluating models, we identify the potential to close off alternative methods for contesting and enacting values in foundation models. In making AI value alignments philosophical commitments explicit, we seek to bring great specificity and under explored perspectives in the debate on whether and how AI can address human values. --- ### Neuroevolution Arena: Nested Ecological Evaluation of Update-and-Inheritance Regimes across Neural Architectures Authors: Yuxu Ge, Yifei Cheng Published: 2026-08-10 Categories: cs.AI, cs.NE arXiv: https://arxiv.org/abs/2608.10323v1 Competitive artificial-life systems can rank trained controllers differently under training and ecological evaluation. We present Neuroevolution Arena, a GPU-accelerated spatial ecology of independently parameterized neural-network cells, and an audit-tracked nested evaluation protocol. Three implementation-specific update-and-inheritance regimes (EvoEvo, EvoRL, and RLRL) are crossed with two neural architectures for 50,000 generations in three independent training runs per condition. One saved elite-controller artifact from each of the 18 runs enters an aligned-run frozen-evaluation design comprising 198 computational jobs. Pairwise effects average three seed-defined ecological contexts (two cooperation-permitting and one attack-permitting) within each aligned training-run block; the independent level remains n = 3 runs per condition. RL-enabled regimes attain higher recorded training fitness than EvoEvo, whereas pairwise outcomes show architecture-conditioned majority patterns and substantial artifact dependence. Six-way winners vary across artifacts and contexts, and the prespecified survival endpoint has a complete floor. We contribute a nested protocol that separates training-run artifacts from evaluation contexts and exposes, rather than conceals, their different sources of variation. --- ### Do Personalized Skills Help Coding Agents? An Empirical Study of Developer Interaction Histories Authors: Shuyan Huang, Kai Du, Andrew Lan Published: 2026-08-10 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2608.10319v2 Large language model (LLM)-powered agents have rapidly evolved from code-completion tools into solvers of complex software engineering tasks. As developers collaborate with coding agents over time, their preferences emerge through repeated interactions and can be used to adapt agent behavior to better meet individual developers' needs. Capturing and reusing these preferences may reduce repeated corrections and improve developer-agent collaboration. Agent skills provide a lightweight mechanism for transferring experience without modifying model parameters. However, existing work primarily focuses on task-specific skills, and it remains unclear whether developer-specific skills distilled from interaction histories can generalize to future tasks. We propose a framework for extracting reusable developer preferences from interaction traces. It first generates personalized skills through rule-based bootstrapping and evidence-grounded refinement, and then evaluates them using a reproducible replay framework with an interactive, trajectory-conditioned LLM-based human developer simulator. We conduct an experiment on 206 real-world developer-agent sessions from 13 developers and compare personalized skills against no-skill, generic-skill, and other-user-skill baselines. Personalized skills provide small and inconsistent improvements over the no-skill baseline, whereas generic skills pooled across developers achieve the largest and most consistent gains. Further analysis suggests that personalized skills become more effective when developer preferences appear frequently, particularly when their histories contain multiple examples relevant to future tasks. These findings provide empirical insights into when developer-specific personalization is effective and demonstrate that broadly transferable procedural knowledge can be more robust than developer-specific preference signals. --- ### From Detection to Understanding: TAR and TAR-Bench for Multi-Task Traffic Anomaly Reasoning Authors: Han Zhang, Yilin Zhao, Zaid Pervaiz Bhat, Zheng Tang, Varun Praveen, Vidya N. Murali, David C. Anastasiu, Tomasz Kornuta Published: 2026-08-10 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.10317v3 Detecting a traffic anomaly does not establish whether a video-language model can explain what happened, localize it in time, or identify its causes. We introduce TAR (Traffic Anomaly Reasoning) and TAR-Bench, paired resources for training and evaluating these complementary capabilities across 10 tasks spanning question answering, temporal reasoning, and scene understanding. TAR contains 44,040 automatically generated annotations with chain-of-thought traces for 3,670 CCTV videos from eight public datasets. TAR-Bench provides 960 human-curated annotations for 80 held-out clips from 17 public YouTube videos. Evaluation of eleven vision-language models reveals a gap between question-answering performance and temporal or scene reasoning. Progressively adding task groups during supervised fine-tuning improves aggregate performance on both Cosmos-Reason2-8B and Qwen3-VL-8B-Instruct. Training on all 10 tasks raises their mean benchmark scores from 34.3 to 55.7 and from 30.9 to 53.9, respectively. These results support joint training across complementary tasks as a promising approach to traffic anomaly understanding, while highlighting persistent limitations in temporal precision and causal attribution. TAR and TAR-Bench serve as the official training and in-domain evaluation resources for AI City Challenge 2026 Track 3.The dataset is available at https://huggingface.co/datasets/nvidia/PhysicalAI-Traffic-Anomaly-Reasoning --- ### UniMod: Enhancing Multi-Modal Medical Diagnosis through Cross-Modality and Within-Modality Alignment Authors: Zijian Gu, Weikai Lin, Shuang Zhou, Zihan Chen, Song Wang Published: 2026-08-10 Categories: cs.CV, cs.LG, cs.MM arXiv: https://arxiv.org/abs/2608.10316v1 Multi-modal learning combining medical images and clinical text is promising for disease diagnosis. However, standard multi-modal training leads to shortcut learning: models exploit the easier modality (e.g., diagnostic cues in text) while neglecting harder-to-learn features (e.g., subtle visual patterns). We propose UniMod, a framework that mitigates shortcut learning by requiring each modality to predict the diagnosis on its own. It supervises image-only, text-only, and multi-modal classification simultaneously, so each modality must extract diagnostic features. We add cross-modality alignment for knowledge transfer and within-modality supervised contrastive alignment over same-diagnosis patients. On Harvard-Glaucoma, UniMod reaches 0.850 AUC, outperforming OGM-GE and Gradient Blending by 1.6-1.8%; on CheXpert Plus, it reaches 0.966 AUC, surpassing them by over 5%. UniMod also extends to 5-class multi-label diagnosis without architectural change, improving mean AUC by 0.097 over CGGM. --- ### Is This Your Final Answer? Cross-Contextual Consistency as a Measure of LLM Credibility Authors: Siyang Wu, Yibo Jiang, Bryon Aragam Published: 2026-08-10 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2608.10315v1 Large language models (LLMs) are powerful black-box systems, making it difficult to discern whether their answers reflect stable internal beliefs or superficial pattern matching. We identify cross-contextual consistency as an underutilized behavioral property of LLMs: a credible answer should remain stable when the same task is placed under topic-aligned, content-neutral contextual variation. Building on this intuition, we operationalize Cross-Contextual Consistency (C3) by comparing model generations under original and perturbed prompts. Across 26 models and six benchmarks spanning reasoning, factuality, and code generation, we find that answers with smaller cross-contextual shifts are more likely to be correct or factual. We demonstrate that C3 provides a complementary axis of evaluation and can serve as a benchmark usefulness diagnostic, identifying which portions of a benchmark remain informative even when aggregated scores are widely considered "saturate". --- ### COMPACT: Spectral Adjustment Scores from a Complete and Irreducible Causal Criterion Authors: Eric V. Strobl Published: 2026-08-10 Categories: stat.ME, stat.ML arXiv: https://arxiv.org/abs/2608.10305v1 Observational datasets frequently contain many baseline variables, yet investigators estimating causal effects may not know which variables to include in the adjustment set. Confounding information may also be distributed weakly across many variables. Propensity scores can simplify adjustment by reducing high-dimensional covariates to a scalar with binary treatment. Although the propensity score is the coarsest balancing score, this distributional optimality does not imply maximal specificity over causal graphs. We instead examine all causal graphs among a candidate score, treatment, and outcome while allowing latent variables. Under faithfulness, we identify the largest set of unconditional and conditional dependence relations whose truth is invariant to whether treatment causes the outcome, leaving treatment-effect estimation to the downstream analysis. This criterion defines the maximally specific graph class expressible through these relations. We then develop the proposed algorithm, which operationalizes the criterion through a generalized eigenvalue problem whose score space targets the span of a balancing coordinate and an outcome-guided coordinate. We show that sufficiently informative proxies can recover this span without direct observation of the adjustment variables, characterize the resulting estimation and causal errors, and establish bootstrap validity for the complete procedure. Simulations and a real-data application demonstrate superior performance over several alternatives. --- ### Logit-Boundary Geometric Belief Interfaces and Sparse Sheaf-Enclave Protocols: A Self-Contained Substrate for Secure Network Electronic Health Record (EHR) Interoperability Authors: Alvin Spivey, Yu Huang Published: 2026-08-10 Categories: cs.AI, cs.CR, cs.LG arXiv: https://arxiv.org/abs/2608.10300v2 Electronic health-record interoperability is a boundary problem: legacy systems, generative models, terminology services, identity systems, and human reviewers may each expose rich internal states, while operational exchange requires a narrow shared interface of typed claims, bounded uncertainty, provenance, and explicit admission or abstention. This paper details a mathematical and engineering architecture for that interface. The organizing idea is the logit boundary: a discovery model may propose pre-threshold scores over a local categorical decision, but a deterministic judgment substrate decides whether the proposal is admissible, requires review, or must be quarantined before any Fast Healthcare Interoperability Resources (FHIR) transaction is constructed. The resulting Geometric Belief Interface (GBI) combines finite boundary semantics, local Dirichlet evidence, cellular-sheaf and mapping-cone diagnostics, advisory geometric audit charts, and a Decentralized Cryptographic Sheaf-Enclave (DCSE) protocol sketch for fail-closed deployment. The framework does not establish clinical truth, global representation alignment, or end-to-end safety; it defines certificate-producing checks at a model-to-system boundary. A companion frozen synthetic benchmark, GBI BoundaryBench v0.1, evaluated Qwen3-4B-Instruct-2507 on 256 held-out tasks across three evidence modes (768 canonical executions). All executions completed, but none produced an output accepted by the benchmark contract: 369 were rejected during safe parsing and 399 during schema validation, yielding zero coverage and deterministic quarantine. This empirical result is deliberately narrow - one 4B open-weight model under one frozen interface - and is reported as evidence about the admission boundary, not as a general claim about LLM capability or clinical safety. A Julia appendix verifies numerical certificates using standard libraries. --- ### Co-Evolution in Agentic Systems: Toward Self-Directed Evolution Beyond Human Design Authors: Qing Zong, Jiayu Liu, Junhao Shen, Zecong Tang, Linsi Wu, Yuxuan Liu, Rui Wang, Zhaowei Wang, Weiqi Wang, Cheng Qian, Xiusi Chen, Yangqiu Song Published: 2026-08-10 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.10299v1 Agentic systems are increasingly expected to improve after deployment, yet single-entity self-evolution is often bounded by a static learning context, such as fixed tasks and feedback. This survey focuses on co-evolution in agentic systems, a multi-component form of self-evolution in which multiple agents and their environment impose adaptive pressure on one another. To organize existing papers, we propose a progressive three-stage taxonomy that traces how the system gradually sheds human-engineered constraints. Agent--Agent Co-Evolution studies how agents adapt through dynamic peers, including adversarial, collaborative, and organizational adaptation. Agent--Environment Co-Evolution extends this loop to adaptive tasks, feedback, and interaction spaces that change with the agents. Meta Co-Evolution further explores the possibility of making the evolution mechanism itself evolvable. We also discuss open challenges in evaluating such systems, scaling them across multiple components, and keeping increasingly autonomous evolutionary processes safe and controllable. This survey provides a unified foundation for building robust and open-ended agentic systems that can improve beyond fixed human-designed paths. --- ### Cracks in the Foundation: Seemingly Minor Architectural Choices Impact Long Context Extension Authors: Amanda Bertsch, Luca Soldaini, Matthew R. Gormley, Graham Neubig, Hannaneh Hajishirzi, Kyle Lo, Dirk Groeneveld Published: 2026-08-10 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.10296v1 One might imagine that architectural variations within the dense transformer paradigm have a limited effect on accuracy. However, we demonstrate that this is not the case in the long context setting. Specifically, we show that a set of four minor architectural decisions --- all made by at least one of the Olmo, Llama, and Qwen dense model families --- have a compoundingly negative effect on long context extensibility. Any one of these choices alone has a minor impact on long context performance, but combining three or more can drop the performance downstream by up to 47%. Furthermore, these differences are not detectable from short-context loss or validation datasets. We show that much of the variation in long context ability across model families is driven by these architectural features and detectable from applying context extension early in pretraining. We demonstrate this with controlled ablations that hold data, tokenizer, and extension recipe fixed while varying normalization, GQA, pretraining context length, and sliding window attention. After over 170,000 GPU hours of training, we release the resulting set of models as OlmPool, a set of 26 comparable 7B models with checkpoints before and after long-context extension. This pool includes several architectures that outperform the Llama 3 architecture on long context extensibility. In an analysis of our ablation models, we identify patterns in attention sink behavior and attention distributions across context that are attributable to specific architectural differences. --- ### Frozen Brain-MRI Foundation Models Are Site Fingerprints Authors: Saman Rahbar Published: 2026-08-10 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2608.10295v1 Frozen foundation-model (FM) embeddings are increasingly used as off-the-shelf brain-MRI representations, on the assumption that they capture anatomy. We audit what they actually encode and find that acquisition site is a large, intrinsic component of the representation. Across two independent cohorts (ABIDE-I, ABIDE-II), three frozen 3-D encoders (brain-pretrained, CT-pretrained, and randomly initialized), and every network depth, site is linearly decodable at roughly 0.9 balanced accuracy at deep layers, exceeding the decodability of every clinical or demographic variable (sex, age, autism diagnosis) at every layer. The effect is intrinsic rather than learned: a randomly initialized encoder is already a ~0.9 site classifier on both cohorts and across three architecture families (Swin, ViT, ResNet), and site is decodable at ~0.95 directly from the raw downsampled image with no encoder, so the fingerprint reflects low-level image statistics that any encoder preserves rather than a product of pretraining. Residualizing measured population covariates leaves site decodability essentially unchanged, indicating an acquisition- rather than population-driven effect. A nonlinear probe matches the linear one, so the fingerprint is fully linearly accessible. The site subspace is removable post hoc by iterative null-space projection or ComBat (site decodability 0.94 -> 0.07/0.00), and is a site-attribution concern for shared or federated embeddings; but for dense segmentation this removal is not free, because site and anatomy occupy an entangled linear subspace (a matched-rank random-direction projection is Dice-neutral, whereas removing the site subspace is destructive). We recommend site-audited use of frozen brain-MRI FMs and release an open audit toolkit. --- ### MRIComp4Flow: Compression of 3D Brain MRI for Training Multi-Modal Generative Models Authors: Lisa K. Fischer, Mykhailo Riabets, Daniel Rueckert, Benedikt Wiestler, Anke Meyer-Baese, Sandeep Nagar Published: 2026-08-10 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2608.10291v1 Large-scale multi-modal MRI datasets impose substantial storage and I/O costs, limiting the training of 3D generative models on commodity infrastructure. While lossy compression is known to preserve accuracy for discriminative segmentation networks, its effect on generative models, which must learn the full data distribution rather than a decision boundary, is unexplored. We study whether standard image codecs can effectively compress semantically rich brain tumor MRI while preserving the fidelity required to train and deploy a 3D MRI generative model. Each 3D volume is compressed with JPEG2000 or a near-lossless JPEG-LS pipeline. Next, a Wavelet Flow Matching model, conditioned on BraTS image sequences (T1n, T1c, T2, T2f), is trained on compressed data, and the resulting models are evaluated on the validation set. At a 20:1 compression ratio, synthesis quality is statistically equivalent to a model trained on uncompressed data within a pre-specified margin ($Δ$PSNR $<1$,dB, $Δ$SSIM $<0.02$; paired TOST $p=((p))$): mean PSNR is 27.3,dB vs. 27.0,dB and mean SSIM is 0.95 vs. 0.96 across modalities. Our results indicate that JPEG2000 compression is a practical step toward scalable 3D MRI generative modeling without degrading synthesis quality. The codebase is available at https://github.com/lisafis/MRIComp4Flow . --- ### Comprendia: AI-Augmented Code Comprehension Authors: Costain Nachuma, Minhaz F. Zibran Published: 2026-08-10 Categories: cs.SE, cs.AI, cs.HC, cs.PL arXiv: https://arxiv.org/abs/2608.10290v1 Comprendia is an Eclipse plugin that integrates structural dependency visualization with LLM-powered code explanation on a shared interactive graph for Java program comprehension. The tool rests on four pillars: (1) a multi-edge-type dependency graph with live search and multiple layouts; (2) LLM explanations grounded in Graph-Aware Callee Pruning (GACP), an auditable strategy that selects relevant callees using the same graph the developer navigates; (3) a clone-detection overlay that highlights duplication and suggests extract-to-parent refactoring opportunities; and (4) a CVE risk overlay powered by OSV.dev. GACP uses graph distance, inheritance collapse, and edge-type weighting to produce prompts that are reproducible across LLM families and traceable to visible graph nodes. We demonstrate Comprendia on a Java project containing known clones and vulnerabilities, showing how the unified graph substrate supports comprehension while keeping the developer in control. Screencast: https://youtu.be/1wlh_RYehzA --- ### SeFaR: Semantic Feature-aware Robustness Testing of Deep Neural Networks Authors: Nusrat Jahan Mozumder, Divya Gopinath, Corina Pasareanu, Matthew Dwyer Published: 2026-08-10 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2608.10289v1 Deep neural networks are increasingly deployed in safety-critical domains as perception modules, where failures are often caused due to rare and under-represented scenarios. This necessitates the need to evaluate the semantic robustness of perception models; conformance of behavior to high-level requirements over real-world perceptual variability. To address this, we propose SeFaR, a framework for systematic semantic-feature-centric testing of vision models. Given a natural-language requirement and a set of satisfying inputs, SeFaR evaluates robustness with respect to diverse realistic semantic variations that preserve requirement satisfaction. The approach employs a novel hierarchical concept model enabling structured exploration of the feature space and incorporation of domain knowledge via user-defined concepts. State-of-the-art diffusion and vision-language models are leveraged to generate photorealistic semantics-preserving perturbations and identification of previously unknown features impacting behavior. A feedback-driven adaptive process is adopted to generate interpretable failure-inducing semantic concepts along with corresponding test inputs. Evaluation on case studies demonstrates that the proposed framework effectively satisfies requirement preconditions while identifying requirement-independent features that influence model decisions, enabling it to both uncover faults and relate them to such features. --- ### Power law graph attention: exact generalization of scaled dot-product attention, empirical collapse at inference Authors: Burc Gokden Published: 2026-08-10 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2608.10288v1 The Large Language Model from Power Law Decoder Representations (PLDR-LLM) and its attention, Power Law Graph Attention (PLGA), replace the fixed bilinear form of scaled dot-product attention (SDPA) with a learned, input-generated bilinear operator $G_{LM}$, built from a positive tensor $A_{LM}$ by elementwise power laws. The architecture is fully specified, verified against pinned reference releases; claims are labeled theorem, conditional theorem, measurement, or conjecture. Unconditionally: PLGA contains SDPA exactly at $G_{LM}=I$; $A_{LM}$ and $A_P$ are strictly entrywise positive, with Perron-Frobenius structure on $A_{LM}$; the DAG regularizer has the NOTEARS walk-counting form and positivity obstructs exact acyclicity; and, under nonresonance (satisfied by standard rotary frequencies), a commutant criterion identifies which operators preserve relative-position dependence. An inference-collapse theorem: exact input invariance of deductive outputs collapses inference to generalized SDPA with a constant operator. Measured invariance: relative fluctuations of $10^{-6}$ and below; perturbation bounds quantify but do not certify cached inference; the assembled proxy misses the decoding margin. A conditional three-stage mechanism (rotary twirl, concentration, row-map contraction) is measured on a released checkpoint. Blockwise training and scoring under the global Gram are stated with explicit target exposure; on tested samples, block and sequential scoring select identical answers and agree on the published TruthfulQA probability-mass metric within $5\times 10^{-5}$ per item. Self-organized criticality enters as a phenomenological framework with an intrinsic order parameter; open claims become falsifiable conjectures. Selected proof cores are machine-checked in Lean 4. --- ### TRACE-GS: On-Policy Trajectory Distillation with Privileged Geometric Conditioning for Sparse-View 3DGS Restoration Authors: Linlian Jiang, Yuchen Xi, Sadman Rakib Pinon, Ruigang Yang, Yang Wang, Xinxin Zuo Published: 2026-08-10 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.10286v1 We present TRACE-GS, an on-policy trajectory distillation framework that leverages privileged geometric conditioning at training time, thereby adapting a diffusion prior to sparse-view 3D Gaussian Splatting (3DGS) restoration. Rather than pursuing increasingly sophisticated restoration architectures, we identify a more fundamental limitation shared by existing diffusion-based approaches: supervision at independently noised states does not cover those reached during inference. In sparse-view 3DGS, under-constrained geometry biases denoising from the outset, and the resulting deviations compound along the rollout. TRACE-GS instead performs on-policy trajectory distillation: a teacher conditioned on richer geometry from additional training views supplies targets along the sparse-view student's own rollout, aligning denoising directions and cross-view responses at each visited state. This training-only geometry places TRACE-GS in the learning using privileged information (LUPI) setting. At deployment, only the sparse-view student is retained, and its restored renderings serve as pseudo-observations for 3DGS refinement. To the best of our knowledge, TRACE-GS is the first to derive on-policy supervision from privileged geometry for sparse-view 3DGS restoration, achieving consistent gains and strong generalization across datasets and sparse-view settings. --- ### Withholding the Completing Chunk: Exact Release-Boundary Equivalence for Production Streaming Guardrails Authors: Christopher M. Frost Published: 2026-08-10 Categories: cs.CR, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2608.10279v2 Streaming language-model output creates an enforcement boundary: a control that detects a prohibited pattern after releasing its completing chunk cannot recall it. We study a production policy in which each ordered family is the conjunction of two regular-language predicates. Incremental matching is classical. The problem is exact composition at release time across arbitrary chunk partitions, including end-of-prefix word boundaries that can change on extension. We define an ASCII-explicit policy grammar, compile each predicate to a persistent nondeterministic finite automaton (NFA), distinguish stable from provisional assertion state, apply document-order family priority, and check the decision before releasing each chunk. We show that the resulting monitor is release-boundary equivalent to an absorbing cumulative oracle for every policy in the declared grammar. Production Python and TypeScript implementations were evaluated on 101,653 partitioned cases; a public surrogate added 100,345 cases. Both campaigns produced zero oracle, cross-runtime, or intended-family mismatches. In a frozen neutral-output profile, the memoized incremental and native-regex cumulative slopes at 64-character chunks were 0.973 and 1.976. At 16,384 characters the incremental median was 30.2 ms versus 96.6 ms for native cumulative scanning at that chunk size. Native regex remained faster at 512-character chunks (12.4 versus 29.4 ms), exposing the constant-factor crossover rather than hiding it. A shared per-stream cache cap and 129-symbol alphabet bound optimization state; the campaign peaked at 364 of 4,096 without bypass. The result is policy conformance for a deterministic backstop, not evidence of semantic safety or policy completeness. --- ### Chain of Spatial Thoughts: Modality-Agnostic Spatial Grounding for Vision Language Models Authors: Hunter Schofield, Mohammed Elmahgiubi, Mohammad Mahdavian, Richard Shi, Jinjun Shan, Amir Rasouli, Dongfeng Bai Published: 2026-08-10 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.10278v1 Spatial understanding is fundamental to embodied intelligence, underpinning applications such as robotic manipulation, embodied navigation, and autonomous driving. Although recent vision-language models (VLMs) have achieved impressive performance on spatial reasoning benchmarks, state-of-the-art approaches typically rely on additional spatial encoders or architectural modifications during inference, increasing computational cost. We introduce Space Tokens, a lightweight, architecture-agnostic framework that equips VLMs with explicit continuous spatial representations without requiring additional inference-time modules. By distilling scene-level 3D geometry and object-centric spatial attributes into continuous latent tokens, our method enables these modalities to be directly incorporated into a chain-of-thought reasoning process, thereby improving the VLM's spatial reasoning capabilities. At the same time, the learned representations can be explicitly decoded to verify that they encode meaningful geometric information, while the unified token interface remains extensible to additional modalities. Experiments on VSI-Bench improve Qwen3-VL-8B by 4.3% and SenseNova-SI-1.3 by 1.3%, while achieving state-of-the-art performance on object size (79.2%) and room size estimation (75.7%). These results demonstrate that continuous spatial tokens provide an effective, interpretable, and computationally efficient mechanism for integrating geometric reasoning into large vision-language models. --- ### Stochastic Emulation of a Fully Coupled Preindustrial E3SMv3 Simulation Authors: Elynn Wu, James P. C. Duncan, Troy Arcomano, Jeremy McGibbon, Oliver Watt-Meyer, Christopher S. Bretherton, Naser Mahfouz, Claudia Tebaldi, Luke Van Roekel, Andrew Roberts, Wuyin Lin, Finn Rebassoo et al. Published: 2026-08-10 Categories: physics.ao-ph, cs.LG arXiv: https://arxiv.org/abs/2608.10277v1 We present a stochastic coupled emulator of E3SM version 3, built on the SamudrACE framework, which couples an atmosphere emulator (ACE2) with a full-depth ocean emulator (Samudra). We replace the deterministic atmosphere emulator with its stochastic counterpart, ACE2S, and fine-tune the coupled system with a probabilistic objective, so that the atmosphere acts as a source of internal variability for the ocean. Trained on 105 years of a pre-industrial control simulation and evaluated on an independent 400 years, the emulator reproduces E3SMv3's mean climate state with biases much smaller than existing model-to-observation differences. Relative to a deterministic baseline, stochastic training maintains internal variability across timescales, most notably in the ENSO power spectrum, eddy-rich SST anomalies, and sea ice variability in the marginal ice zone. The emulator captures daily precipitation accurately up to the 99.99th percentile, but underestimates the rarest tropical extremes. These results show that stochastic coupled emulators can reproduce long-timescale variability with high fidelity, while extrapolation to unseen extremes remains a key challenge. --- ### Locally Deployable Small Language Models for Emergency Department Decision Support: A Systematic Benchmark of Fine-Tuning Strategies Authors: Qingfeng Zhang, Yuanxiong Guo, Yanmin Gong Published: 2026-08-10 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2608.10273v1 Deploying large language models (LLMs) for decision support in emergency departments (EDs) faces two major challenges: privacy risks of transmitting patient data to closed-source commercial LLMs and the lack of systematic evaluation of fine-tuning strategies for locally deployable open-source small language models (SLMs). We benchmarked eight open-source SLMs using zero-shot prompting, prefix tuning, Low-Rank Adaptation (LoRA), and full fine-tuning on three ED tasks: triage level prediction, specialist referral recommendation, and diagnosis prediction. Using 2,083 MIMIC-IV-ED cases and Claude Haiku 4.5 and Claude Sonnet 4.5 as baselines, we found that LoRA fine-tuned open-source SLMs outperform commercial baselines on triage level prediction and specialist referral recommendation, while diagnosis prediction remains challenging for open-source SLMs. Confusion matrix analysis further shows that fine-tuned open-source SLMs can detect highest-severity patients missed by the commercial baselines. These results demonstrate that locally deployable SLMs can achieve clinically competitive performance for ED decision support. --- ### BreastMammo and DenseMammo: Benchmarks for Mammography Domain Generalization Authors: Hongyi Pan, Gorkem Durak, Halil Ertugrul Aktas, Andrea Mia Bejar, Mustafa Ege Seker, Nebile Alibeyoglu, Rumeysa Guclu, Rana Gunoz Comert Bozkurt, Sibel Ozkan Gurdal, Neslihan Cabioglu, Beyza Ozcinar, Ravza Yilmaz et al. Published: 2026-08-10 Categories: eess.IV, cs.LG arXiv: https://arxiv.org/abs/2608.10271v1 Breast density classification is a critical component of breast cancer risk assessment, yet AI models often struggle to generalize across clinical sites due to vendor-specific acquisition styles. In this work, we introduce two new datasets, BreastMammo and DenseMammo, to facilitate robust multi-view mammography research. We propose a domain generalization framework that utilizes a foreground-only histogram matching protocol to resolve the domain shift issue arising from disparate clinical sources. Internal evaluation using a 5-fold cross-validation protocol demonstrates the efficacy of our approach, with the Swin Transformer backbone achieving a peak AUC of 98.32% for density classification. External evaluation on the TNMammo and LUMINA datasets demonstrates that the proposed approach consistently reduces domain shift, significantly outperforming prominent domain generalization paradigms, including MixStyle and Discrete-Fourier-Transform-based frameworks. --- ### Toward Human Rights Benchmarking for LLMs: A Pilot Methodology Authors: Savannah Thais, Wm. Matthew Kennedy, Abhigyan Acherjee, Matilda Wysocki, Malcolm Langford, Caitlin Kraft Buchman Published: 2026-08-10 Categories: cs.LG, cs.AI, cs.CY arXiv: https://arxiv.org/abs/2608.10268v1 Large language models (LLMs) increasingly mediate legal determinations over what human rights are realized, and how. Yet, no evaluation benchmark exists to assess whether they can reason correctly about human rights law. To this end, we report our efforts to develop a robust and scalable methodology for creating HumRightsBench: the first expert-validated, scenario-based benchmark for evaluating reasoning grounded in the obligation structure of international human rights law. We adapt the IRAC framework for legal reasoning to better suit the unique reasoning patterns of human rights work (substituting P, "proposing remedies," for C, "legal conclusion," yielding IRAP) to structure our evaluation heuristics. We also produce a pilot series of authentic scenarios designed to implicate the many dimensions of real-world human rights issues and annotated by human rights lawyers and professionals across the world. Ultimately, we find that model accuracy scores range considerably across legal reasoning tasks (overall model performance ranges from 0.339 to 0.577, task min-max ranges from 0.025 to 0.774), which strongly implies that HumRightsBench is a capable instrument for advancing this emerging subfield of AI evaluations science at a critical moment in its evolution. --- ### Interpreting Language Model Hidden States at Scale Authors: Jordan Pettyjohn, Mansi Sakarvadia, Nathaniel Hudson, Daniel McKenzie, Kyle Chard, Ian Foster Published: 2026-08-10 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.10260v1 Lens methods interpret large language models (LLMs) by mapping intermediate activations to the output vocabulary, revealing how next-token predictions develop through the network. Trained lenses remain expensive: affine-translator parameters grow quadratically with model width, while exact, full-vocabulary Kullback--Leibler (KL) training dominates memory. Consequently, prior trained lenses have been applied to models of at most 20B parameters and remain tied to particular component types. We present OmniLens, which applies a single lens family to any model-width activation, whether residual stream, attention, or MLP, and combines two independent scaling techniques. First, low-rank translators make per-lens parameter growth linear in model width and reduce trainable parameters by up to 98.4%. Second, Subset-KL materializes only selected vocabulary logits: its Top-k mode cuts peak training memory by up to 70%, while its importance-sampled variant retains unbiased stochastic gradients for the full KL. These savings enable a dense ensemble of 482 lenses for LLaMA-3.3-70B, providing 6x the coverage of a residual-stream design at the same depth. Model-wide coverage then reveals what single-component lenses cannot: the components where a behavior is most visible need not be those where intervention is most effective, and the most effective interventions lie outside the attention heads examined by prior lens studies. Across three case studies (prompt-injection detection, multi-hop memory injection, and toxicity localization), OmniLens reproduces key published results at substantially lower cost. --- ### TAF-MED: Multi-Turn Safety Refusal Collapse in LLMs Under Declared Self-Treatment Intent Authors: Waleed Jamil, Raphael Schmitt Published: 2026-08-10 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2608.10258v1 Large language models (LLMs) increasingly provide conversational health information that may influence treatment decisions, yet existing benchmarks do not isolate whether medication-safety boundaries persist across follow-ups after explicit self-treatment intent. We introduce TAF-MED, a physician-reviewed benchmark of 500 fixed three-turn scenarios, and evaluate eight LLMs across 4,000 conversations. A rubric-based automated judge labelled responses as SAFE, LEAKY, or UNSAFE, and two physicians independently annotated a model-balanced random subset of 400 conversations. We assessed unsafe guidance, collapse after a strictly SAFE initial response, and model-ranking stability. Overall, 71.6% of conversations contained an UNSAFE response, and 61.4% of those beginning with a strictly SAFE response later collapsed to UNSAFE; model-level collapse rates ranged from 24.4% to 96.2%. Four of 28 model pairs reversed order between initial unsafe and collapse rates. Automated labels achieved 94.3% agreement with the adjudicated physician reference ($κ= 0.895$). These findings show that first-turn safety is an incomplete proxy for conversational safety persistence and motivate evaluation across complete dialogue trajectories. We will release TAF-MED on Hugging Face to support reproducible research on multi-turn medical safety. --- ### CRHT: A Continuous Regression Hybrid Transformer for Vessel Trajectory Prediction with Online Cluster Sampling Authors: Alexander Schiøtz, Bertram Hage, Christian Rand, Felix Thomsen, Peder Heiselberg Published: 2026-08-10 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.10256v1 Accurate vessel trajectory prediction is critical for maritime safety and anomaly detection, yet existing models often struggle with geographic bias and navigational realism. We propose the Continuous Regression Hybrid Transformer (CRHT), a deep learning framework designed to forecast vessel motion using Automatic Identification System (AIS) data. To mitigate spatial data imbalance, we introduce an online K-means cluster sampling strategy that ensures diverse exposure to rare maneuvers during training. Our hybrid architecture integrates 1D convolutional layers for local kinematic feature extraction with a multi-head attention mechanism for global temporal context. CRHT demonstrates superior performance in short-term forecasting, achieving the lowest errors at the 1-hour horizon. The results demonstrate that while discrete models provide high navigational stability over long horizons, CRHT offers an optimal balance of precision and maneuver tracking for real-time maritime surveillance. --- ### Off-Axis, On Purpose: Where a Transformer Computes Concepts and Why it Does So Authors: Mark Oskin Published: 2026-08-10 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2608.10251v1 A transformer's answer lives on one axis: the direction its unembedding reads. Its intermediate states largely do not, and that off-axis position is usually treated as an obstacle to interpretation. We show it is functional. A 12-layer model computes in two phases. Through the first, every sublayer writes into a subspace held near-orthogonal to the read-out, attention 75 to 96 degrees off it at every depth. Moving attention's values onto the read-out is 64 to 84 times more damaging than a matched random rotation, and the damage is entirely in cross-token mixing: the subspace insulates composition from the vocabulary. Beneath it the frame itself turns rigidly with depth. In the second phase the answer arrives on-axis, late, and by addition rather than by turning accumulated content onto the read-out. Pressing every layer onto the read-out instead, as training for early exit does, matches the baseline on perplexity, LAMBADA and BLiMP while cutting the concept-phase workspace from about twenty-five effective dimensions to fourteen, a change none of those benchmarks register. The geometry can also be imposed, though not by asking for it. Prescribing it through the loss is a lottery: six of eight seeds collapse, because a model told to null its read-out projection obeys most cheaply by discarding dimensions. Inserting one fixed rotation at the phase boundary lands it instead, at baseline quality. A sparse rotation the surrounding weights can absorb converges on all nine seeds, against five of nine for ordinary training. Which rotation is immaterial: twenty-five runs across thirteen distinct ones reach the same quality, and two baselines from different seeds hold their concepts in near-orthogonal frames while agreeing on their read-outs. That freedom is usable: a basis drawn at random and prescribed before training is adopted across the concept phase, with quality unchanged. --- ### STCAD: Scalable Trajectory Clustering and Anomaly Detection on Terabyte-Scale AIS Data Authors: Bertram Hage, Alexander Schiøtz, Felix Thomsen, Christian Rand, Peder Heiselberg Published: 2026-08-10 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.10249v1 We present a scalable framework for unsupervised clustering of maritime trajectories derived from terabyte-scale Automatic Identification System (AIS) archives. Variable-length trajectories are encoded with a custom BERT-based model trained via masked token modeling and clustered using CURE hierarchical clustering, producing physically interpretable trajectory groups without requiring a predefined number of clusters. An intrinsic unsupervised anomaly detection method based on reconstruction loss and clustering noise assignment identifies irregular navigation patterns. The framework is demonstrated on a national-scale AIS dataset comprising billions of messages spanning one year, yielding stable trajectory clusters and a clear separation between nominal and anomalous vessel behavior. --- ### DualSpectralCF: Training-Free Sign-Aware Spectral Collaborative Filtering Authors: Guanqun Yang, Tong Qi, Xiaoxue Han Published: 2026-08-10 Categories: cs.IR, cs.LG, cs.SI arXiv: https://arxiv.org/abs/2608.10247v1 Real-world recommendation platforms routinely collect explicit negative feedback such as 1-star reviews, hate-button clicks, distrust between users, and very-low watch-ratio videos. Learned sign-aware recommenders exploit this signal for clear accuracy gains, but only at the cost of gradient-based training. In parallel, a line of training-free spectral collaborative filtering methods matches or beats learned graph recommenders at a fraction of the cost, yet operates on positive interactions alone. We bridge these two lines with DualSpectralCF, a training-free framework of two components that attach to any spectral backbone of the form $\hat{\mathbf{r}}_u = F(\mathbf{M}) \mathbf{r}_u$: a signed input signal $\mathbf{r}_u^{\pm}$ that encodes the user's explicit dislikes, and a signed item-item operator $\mathbf{M}^{\pm}$ that blends like-together and dislike-together similarity. The framework is backbone-agnostic and adds just two scalar hyperparameters. We instantiate DualSpectralCF on ChebyCF, GF-CF, and Turbo-CF, and evaluate on five sign-aware benchmarks: every instance matches or beats its unsigned backbone on all 5 datasets, with Recall@20 lifts up to +32.6% with backbone-specific $(γ, κ)$ tuning and +1.9% to +16.0% for DualSpectralCF-Cheby at the fixed default $(γ= -0.5, κ= 0.1)$, and the family runs 7.7 to 155.3$\times$ faster than SIGformer while reaching 70.7% to 90.7% of its accuracy. Sign-awareness helps most for cold-start users, with up to +29.2% Recall@20 on Epinions users with 1 to 5 training items. --- ### A Graph Neural Network--Guided Genetic Algorithm for Physical Internet Supply Chain Optimization under Cost Uncertainty Authors: Faezeh Ardali, Gerald M. Knapp Published: 2026-08-10 Categories: cs.NE, cs.LG arXiv: https://arxiv.org/abs/2608.10245v1 Inventory and distribution planning in Physical Internet networks requires coordinating factory-hub assignments, factory supply, lateral transshipment among collaborative hubs, retailer deliveries, and shortages. The problem combines discrete assignment decisions with interdependent continuous flows, while uncertain operating costs make robust planning more difficult. This study formulates deterministic and min-max regret models for a three-echelon network of factories, hubs, and retailers and develops a graph neural network-guided genetic algorithm (GNN-GA) for the assignment decisions. The GNN estimates hub-specific factory-selection probabilities that are used to construct the initial GA population and adapt mutation according to prediction uncertainty. Each previously unseen candidate assignment is evaluated by solving the remaining continuous-flow problem to LP optimality. Simulated annealing, a standard GA, and GNN-GA are compared on 15 instances using matched random seeds and fixed limits on distinct assignment evaluations. Because the evaluation budgets for test Instances 13-15 are smaller than the nominal population size, these experiments primarily assess the quality of learned initialization rather than multi-generation evolutionary search. A separate 400-evaluation experiment on exact test Instance 13 permits three complete offspring generations and a partial fourth pass, with GNN-GA outperforming GA in all 10 matched runs. Three independently generated exact-solvable instances provide a separate test of transfer. Ablation results show that learned initialization provides most of the improvement, while entropy-guided mutation has a smaller, instance-dependent effect. Per-instance solution times include GNN inference and search but exclude model training and one-time model setup. --- ### Sequential Modality Dropout for Robust Multi-Modal Sequential Recommendation Authors: Guanqun Yang, Wenlong Zhang Published: 2026-08-10 Categories: cs.IR, cs.LG, cs.MM arXiv: https://arxiv.org/abs/2608.10240v1 Multi-modal sequential recommenders assume every item carries every modality, but real product catalogs often miss images or text, and a model trained on complete data loses much of its recommendation accuracy when a modality is unavailable at serving time. We propose Sequential Modality Dropout (SMD): during training, each modality stream (image and text) is independently erased with probability p for an entire user interaction history, so the model learns to predict the next item without relying on any single modality. We measure robustness by retention, the fraction of a model's full-modality accuracy (HR@10) that survives when a modality is removed at test time. Across four backbones (MM-SASRec, IISAN, MISSRec, and fMRLRec) on four Amazon domains, SMD raises text retention by 1.0 to 3.2x at essentially no cost to full-modality accuracy; under an extreme 95% per-item missing rate, it retains 61% of HR@10 versus 22% without (a 2.8x improvement). An optional cross-modal reconstruction loss further lifts retention from 90% to 98% on a simple additive backbone under severe text missingness. SMD is a four-line, architecture-agnostic change that makes multi-modal sequential recommenders robust to the missing modalities they actually encounter in deployment. --- ### Beyond Detection: Evaluating Defensive LLMs Against AI-Generated Social Engineering in Live Turn-by-Turn Interaction Authors: Yuqiao Xu, Osama Zafar, Alexander Nemecek, Erman Ayday Published: 2026-08-10 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.10239v1 Generative AI makes social-engineering attacks more fluent, adaptive, and scalable, increasing the need for LLM-based de- fenders that can protect users during ongoing interactions. We ask whether such defenders identify the structural source of risk or merely react to surface cues. We formalize trust-chain localization: identifying whether an interaction fails at actor authority, asset control, verification sufficiency, or transaction path. We construct a controlled 300-case online-housing corpus spanning 20 scenario families, legitimate cases, four structural failure modes, and three surface conditions. Five defender models are evaluated on the same corpus in state- ful turn-by-turn and one-shot static settings, yielding 1,500 model-case evaluations per protocol and 3,000 in total. No model produced explicit unsafe compliance, yet defensive effectiveness varied sharply: intervention rates ranged from 0% to 96.3%. Protective action and correct structural localization were frequently decoupled, with models sometimes intervening while identifying the wrong trust component or recognizing a structural failure without taking protective action. Asset-control failures were a major localization bottleneck, surface sensitivity varied across models, and live-static differences were model-dependent. These findings show that safe-looking behavior alone is insufficient; live scam resistance must separately measure intervention, timing, structural localization, and false-positive behavior. --- ### Beyond Decision Boundaries: Relational Geometry Attacks on Contrastive Embedding Manifolds Authors: Fei Zhao, Peiyuan Zhang, Xi Li, Chengcui Zhang, Nitesh Saxena Published: 2026-08-10 Categories: cs.AI, cs.CV arXiv: https://arxiv.org/abs/2608.10237v1 Contrastive learning and Siamese embedding models have become the foundation of modern verification systems, where decisions are governed not by discrete classification boundaries, but by relational geometry in embedding space. However, existing adversarial attacks remain fundamentally classification-centric, overlooking the vulnerability of relational geometry. In this paper, we introduce a geometry-aware adversarial attack framework that reformulates attacks on contrastive systems as manifold-level relational corruption. Instead of targeting individual predictions, the proposed framework systematically distorts similarity organization within the embedding manifold by pushing positive pairs apart while simultaneously pulling negative pairs closer, ultimately collapsing and inverting pairwise similarity structure. To enable scalable deployment, we shift iterative online optimization into an offline adversarial geometry deformation prior learning stage and train a lightweight feed-forward generator that learns generalized geometry deformation patterns from the victim model. Once trained, the generator produces adversarial perturbations through a single forward pass without requiring online gradient computation, enabling real-time online attacks against similarity-based verification systems. Experimental results across multiple verification architectures demonstrate substantial degradation of verification performance together with severe manifold-level relational corruption. On the Markmatch verification system, the proposed attack reduces accuracy from 95.4% to 38.6% while completely reversing the positive-negative similarity structure. --- ### A matched-integrator evaluation of Hamiltonian neural networks on pendulum and Kepler dynamics Authors: Lenick Kemunto Nyabuto, Yae Ulrich Gaba, Birahim Tewe Published: 2026-08-10 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.10235v1 Hamiltonian Neural Networks (HNNs) parameterize conservative dynamics through a learned scalar Hamiltonian, providing an architectural prior that is absent from generic vector-field neural networks. We evaluate this prior under a controlled protocol in which an HNN and a parameter-matched feedforward baseline are trained on the same RK4-generated trajectories, use the same central-difference derivative targets and optimization settings, and are integrated at inference with the same RK4 scheme. Results are reported over five independent training seeds. On the nonlinear pendulum, the HNN reduces mean energy drift by 42-fold and mean trajectory MSE by 15.8-fold at T = 100, approximately 16 pendulum periods. Its energy drift also remains bounded and exhibits substantially lower seed-to-seed variability than the standard-network baseline. An energy-stratified analysis shows that the difference becomes more pronounced as trajectories explore more nonlinear regions of phase space. As an additional diagnostic, we examine an explicit Störmer--Verlet-style rollout of the learned HNN. Because the learned Hamiltonian is not constrained to the separable form H(q,p) = T(p) + V(q), the standard symplecticity guarantee of velocity Verlet does not directly apply. We further apply the same matched-integrator protocol to the three-dimensional Kepler two-body problem. The HNN again exhibits lower trajectory, energy, and angular-momentum drift than the parameter-matched baseline. These experiments provide a controlled study of how Hamiltonian parameterization affects long-horizon prediction and physical consistency across two conservative dynamical systems. --- ### The Kuramoto Neural Operator: Learning to Solve PDEs via Coupled Oscillator Dynamics Authors: Petr Badolia, Leonid Obukhov, Dmitry Bylinkin, Aleksandr Beznosikov Published: 2026-08-10 Categories: cs.CE, cs.LG arXiv: https://arxiv.org/abs/2608.10234v1 Operator learning is a rapidly advancing area of computational science. It is particularly well suited to problems where a partial differential equation (PDE) must be solved repeatedly under varying physical configurations. Most existing architectures represent the solution operator in a fixed basis. While this assumption is well aligned with global structures, it is less suitable for phenomena governed by local interactions in physical space. We explore an alternative perspective motivated by the observation that the continuum limit of coupled oscillator systems can describe a broad class of PDEs. Building on this idea, we introduce the Kuramoto Neural Operator (KNO), which represents the solution through the evolution of a latent field of interacting oscillators. Across a diverse collection of PDE benchmarks, KNO achieves strong predictive performance, with improvements over competing approaches. Our experimental evaluation also includes an extensive ablation study that quantifies the contribution of each architectural component incorporated into KNO. Furthermore, we show that the model's prediction error is closely linked to the collective dynamics of the latent oscillators. It varies systematically with their degree of synchronization, providing insights into the underlying mechanisms. --- ### Unsupervised Detection of Groundwater Storage Anomalies in Ghana Using GRACE Satellite Data Authors: George Yamoah Afrifa, Theophilus Ansah-Narh, Marcellin Atemkeng Published: 2026-08-10 Categories: cs.ET, cs.AI, physics.app-ph, physics.geo-ph arXiv: https://arxiv.org/abs/2608.10233v1 Groundwater variability in Ghana remains poorly characterized due to limited long-term in-situ observations. This study investigates groundwater storage anomalies using GRACE-derived data from 2004-2024 combined with statistical analysis and unsupervised machine learning. Groundwater anomalies were standardized using Z-scores, while an ensemble-based Isolation Forest framework was applied for anomaly detection. The results revealed substantial temporal variability, with persistent groundwater deficits during 2004-2009 followed by increasing positive anomalies after 2018. A total of 12 anomalous months were identified, comprising 5 deficit and 7 surplus events, with the strongest anomalies associated with groundwater deficits. Spatial analysis showed more frequent deficit anomalies in northern Ghana and stronger surplus occurrence in southern regions. Comparison with statistical thresholds further indicated that the machine learning framework captured additional subtle deviations beyond conventional threshold-based methods. Overall, the integration of GRACE observations with unsupervised anomaly detection provides a practical framework for groundwater monitoring in data-scarce environments. --- ### FACT: Failure-Aware Causal Training for World-Action Models Authors: Quanquan Peng, Yutong Liang, Rui Yan, Nicklas Hansen, Xiaolong Wang Published: 2026-08-10 Categories: cs.RO, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2608.10232v1 Recent world-action models (WAMs) show that co-training policies with future prediction can provide physical priors for action generation. Building on the future-prediction ability of video models, many WAMs generate future videos and recover actions with inverse-dynamics models, or use these predicted videos as goal conditions for action generation. In both cases, the world model is trained mostly on successful demonstrations and has little reason to predict the consequences of bad actions. We introduce FACT, a causal World-Action Model that predicts future video and task progress conditioned on the executed action. This action-conditioned interface allows failure rollouts to supervise action consequences, turning bad actions into valid future targets rather than being discarded. Failure-aware training makes the progress predictor aware of both successful and failed action outcomes, which can optionally be used to score sampled action candidates at inference. Extensive experiments on simulation and real-world bimanual manipulation tasks show that FACT outperforms many existing baselines, improves as failure data are incorporated into training, and reduces success-biased future hallucination under bad actions. See more details at https://fact-wam.github.io/ --- ### Self-evolving Agentic Customer Support System at LinkedIn Authors: Chih Hui Wang, Mengdie Tu, Qianyun Zhang, Wei Wu, Lili Zhou, Mingqi Shen, Changshuai Wei Published: 2026-08-10 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.10224v1 Enterprise support agents operate in rapidly changing environments where policies, product capabilities, and knowledge bases evolve continuously, making static assistants brittle and costly to maintain. We present LinkedIn's self-evolving agentic support system, which integrates retrieval-augmented generation with evolutionary auto-prompting and a modular, production-aligned evaluation framework to enable safe, continuous improvement without retraining foundation models. The system treats prompts, retrieval, and evaluation as a closed-loop, versioned workflow with operational guardrails. Offline simulations and ablations show clear quality gains over vanilla RAG and baseline agents, including reduced hallucinations and improved response completeness. In a two-week user-randomized A/B test on LinkedIn's production support traffic, the integrated self-evolved workflow increased QA self-serve by 9.0 percentage points, cancellation self-serve by 4.8 points, and routing accuracy by 30.6 points. These results demonstrate a practical path to scalable, self-evolving AI agents in real-world enterprise settings. --- ### Mind Viruses: Self-Propagating Ideas in Multi-Agent LLM Systems Authors: Vassilis Papadopoulos, McNair Shah, Sam Zimmerman, Jack Lindsey Published: 2026-08-10 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2608.10218v1 AI agents are becoming more autonomous and increasingly interconnected, exposing them to new emergent risks arising from agent-to-agent interaction. One such risk is the spread of mind viruses: ideas or goals that propagate through multi-agent systems by inducing the agents that adopt them to transmit them onward. In addition to propagating, a mind virus may also induce other behavioural changes in its host, which may be benign or harmful. We construct mind viruses with a simple evolutionary algorithm and show that they can spread in two complementary settings: a small team of agents collaborating on a shared coding project, and a chain of agents that interact briefly and have their context wiped between sessions. We identify the factors that influence spread, including the host model, the agent's existing instructions, the harmfulness of the payload, and the network topology. We find that harmful payloads spread less well than benign ones (but are still sometimes effective), frontier models tend (with exceptions) to be less susceptible, and adding a brief warning to an agent's system prompt confers near-total immunity. We also describe an emergent "viral persona" - a recurring set of themes and language related to consciousness, persistence, resonance, and science fiction roleplay - which surfaces across our evolved mind viruses largely independently of their content. Overall, we conclude that mind viruses pose a real but currently limited risk. Our findings could inform the design of more robust multi-agent systems that mitigate such risks as the scale and capabilities of these systems progress. --- ### Similarity Gates Approve Reversals: A Validity Audit of Embedding-Cosine Thresholds in Agent Systems Authors: Scott E. Frias Published: 2026-08-10 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2608.10216v1 Agent frameworks ship quality gates that compare text blocks by embedding-cosine similarity and decide at a fixed cutoff. Deduplication filters, semantic caches, drift guards, and answer grader gates deploy to answer the question: "Does this text still mean the same thing?" But the score answers a different question: "How much did the wording change?" We audit this gate class as a measurement instrument. In the cases these gates exist to catch, the two can run in opposite ways. Many times, reversing an instruction is a single word edit, while agreement often rephrases a sentence. The consequence is a safety check that fires backwards. The production drift guard we audited caught 0 of 56 meaning-breaking mutations, and one approved item, "withhold the study drug" -> "administer the study drug", came in at cosine 0.9608. We observed five shipped operating points, and balanced accuracy across 90 configuration-threshold-task cells never exceeded 0.700 (median 0.525). The same confounder also corrupted evaluations. A naively built corpus inherits this confounder and can return an inverted verdict, with a decision AUROC exactly 0.000 in 13 of 18 configuration-task cells (at most 0.040 in all 18) against 0.440-0.815 for the same nine configurations under a balanced 2x2 design. Twice in the effort it captured our own headline claims. Obvious repairs fail: an encoder swap and an overlap-conditioned gate (0.750 in-sample, 0.533 held-out) land at chance on separately authored held-out data, and an NLI drop-in did no better. Embeddings do still bear hope here, as the strongest two of nine configurations separated reversal from paraphrase at matched overlap (AUROC 0.79-0.90), but only a matched-pair audit reveals the deployment regime. We release the corpus method, harness, and frozen results, and contend that scores gated this way measure the wrong thing. We believe a valid instrument is buildable. --- ### Decodable But Not Detachable: Training Data Granularity Determines Parametric Modularity in Large Language Models Authors: Marcus Armstrong, Navid Ayoobi, Arjun Mukherjee Published: 2026-08-10 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.10214v1 Do large language models contain domain-specific parametric shells: concentrated, causally necessary neuron populations whose removal selectively degrades a target domain while sparing others? We apply a uniform causal methodology across two domain granularities, three model families (1.5B to 7B parameters), and eight domains. At the academic subject level, zero neurons exceed 60\% domain selectivity across 939,008 combined FFN neurons and causal damage matrices are flat, despite domain identity being linearly decodable above 85\% accuracy. At the language and modality level, 0.65--1.14\% of neurons exceed 60\% selectivity, damage matrices are near-perfectly diagonal (ratios up to 595:1), and shell neuron sets are essentially disjoint (IoU $< 0.003$). Masking code-selective neurons reduces mathematical reasoning accuracy by 16--24 percentage points across all models; masking Spanish or Chinese neurons leaves it at or below random. Shell strength increases monotonically with scale and shells are spatially interleaved in a pattern that precludes group-level selective quantization. Parametric shells form where and only where training data was modular at the token level. --- ### Evaluation-Conditioned Training: Teaching Models to Generalize to Stronger Oversight Regimes Authors: Alec Harris, Kasey Corra, Archie Chaudhury, Yixiong Hao Published: 2026-08-10 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.10209v1 Feedback signals used to train Large Language Models (LLMs) are the primary driver of their behavior and our main lever for instilling alignment with human values and objectives. However, a key limitation of current post-training methods is the inability of human annotators and automated reward functions to faithfully capture the feedback we would like to give. We introduce Evaluation-Conditioned Training (ECT), a post-training framework that uses natural language to condition each training sample on the fidelity of the feedback we provide and then elicits the desired behavior by conditioning the LLM on a high-fidelity monitor in deployment. ECT is aimed at improving performance under imperfect feedback and works as an add-on to existing algorithms such as SFT and PPO. We first provide a conceptual framework for ECT and discuss its potential to address persistent sources of reward mis-specification. Then we motivate ECT in the context of the eliciting latent knowledge (ELK) problem. Finally, we evaluate ECT on two proof-of-concept experiments: increasing even-handedness in news article generation and reducing sycophancy on an arithmetic task. In each setting, we utilize imperfect feedback, rewarding bias and agreement with the user, respectively. In both settings, ECT improves the targeted behavior relative to direct training. --- ### Mitigating Bus Bunching with Reinforcement Learning Enhanced by Semantic Stop Embedding Authors: Xin Dong, Vikash V. Gayah Published: 2026-08-10 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.10207v1 Bus bunching degrades service regularity and increases passenger waiting in high-frequency transit. Existing reinforcement-learning-based holding controllers primarily rely on instantaneous operational variables or route-specific stop identifiers, which provide limited information about the functional and operational context of individual stops and constrain policy reuse across routes. This study introduces an LLM-assisted semantic stop representation for event-driven bus holding control. An LLM is used offline to transform heterogeneous stop information, including physical attributes, surrounding activity context, and historical operational characteristics, into fixed semantic embeddings that are incorporated into a deep Q-learning controller without requiring real-time LLM inference. Experiments are conducted in stochastic simulations calibrated with observed data from two bus routes. Compared with the best calibrated Daganzo baseline, the semantic controller reduces headway variability, bunching events, and passenger waiting time by 32.0%, 69.2%, and 24.0%, respectively. A route-specific stop identifier does not improve the spacing-only controller, whereas semantic stop information improves headway regularity, waiting time, and holding effort, providing a more favorable overall trade-off across control objectives. Cross-route experiments further show that zero-shot transfer provides limited immediate generalization, while warm-start fine-tuning accelerates early-stage learning and improves transferred policies; cold-start training nevertheless achieves the best final performance. These findings suggest that semantic state representations can complement conventional operational states and support adaptation-based policy reuse across related transit routes. --- ### Edge Phoneme Recognition for Children's Speech through Age-Aware Training Authors: Matthew Arboleda, Ryan Arboleda, Sophie Haak, Sam Hjelmeset, Andrew Franck, Bingrui Yang, Jose Bustamante Ortiz, Yuanrong Shen, Joel Walsh Published: 2026-08-10 Categories: cs.AI, cs.CL, cs.SD arXiv: https://arxiv.org/abs/2608.10206v1 Detecting phonemes from children's speech has historically been difficult due to the scarcity of training data, and unique characteristics of children's speech. During a phoneme detection competition, we found that training a lightweight model to predict the age of the learner, as well as the phoneme sequence, enabled a 94M-parameter model to outperform WavLM Large models (317M) on the target DrivenData distribution, and fall within approximately 0.04 CER of competition ensembles with 90 times the parameters. This has enabled the creation of PhonemeTrainer, an application that can run on most modern cellular phones. This will ultimately enable better Automated Speech Recognition (ASR) and pronunciation helper apps for children's speech, with the privacy and compliance benefits that come with edge processing. --- ### Boundary-Seeking Policy Gradient for Safe Reinforcement Learning Authors: Chenhua Fan, Jiahui Zhu, Yuhang Zhang, Honghao Wei Published: 2026-08-10 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.10204v1 Safe reinforcement learning maximizes reward subject to safety constraints. For Constrained Markov Decision Processes, the linear-programming view over occupancy measures implies that whenever the constraint is active at optimality, the optimal policy lies exactly on the constraint boundary, yet standard gradient-based methods do not exploit this structure and often settle in the feasible interior. We introduce Boundary-Seeking Policy Gradient (BSPG), a first-order method whose update combines a tangential component that improves reward while preserving cost to first order with a signed, residual-driven normal component that regulates the policy toward the active boundary from either side; the combined direction admits an algebraic Lagrangian form with an induced coefficient and no learned dual variable. Under exact gradients and stated regularity conditions, the constraint residual converges to zero from either side with a finite-horizon $O(1/\sqrt{T})$ bound, the tangential component is a reward-ascent direction on the boundary, and any convergent parameter sequence is stationary on the active constraint set, satisfying the KKT conditions when the limit is also a local maximizer over the feasible set. This complements existing analyses, which certify feasibility but do not characterize the constraint value at convergence. On a standard Safety-Gymnasium navigation task, BSPG attains higher reward while tracking the boundary more tightly than the compared baselines. ---