# Research Papers — 2026-08 · bundle page 145 of 240 > Full-text markdown of papers #7201–7250 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/145 [← Previous bundle](https://aipod.dev/papers/archive/2026-08/page/144.md) [Next bundle →](https://aipod.dev/papers/archive/2026-08/page/146.md) ### LookBack: Where and How to Score LVLM Responses via Visual Reference Usage Authors: Beomsik Cho, Jinhyeong Kim, Dongseok Lee, Jaehyung Kim Published: 2026-08-12 Categories: cs.CV, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2608.11847v2 Large Vision-Language Models (LVLMs) integrate visual perception with language generation, enabling responses that span image understanding and complex reasoning. However, LVLMs do not just inherit the text-level hallucinations; they also hallucinate against the image, producing fluent responses ungrounded in what they see. This makes LVLM response scoring inherently harder, and our diagnostics show that existing confidence-based metrics adopted from LLMs are insufficient for LVLMs. Specifically, removing the input image barely changes confidence-based selection, suggesting that output-space confidence primarily captures textual plausibility rather than agreement with the image. To address this gap, we propose LookBack, a training-free LVLM response scoring method that augments token likelihood with visual lookback score, a lightweight measure of how strongly each response token refers to image tokens. Across four benchmarks and three models, LookBack consistently improves Best-of-$N$ selection over existing baselines with negligible additional overhead. --- ### BoltNet: An Ultra-Lightweight Convolutional Network for On-Device Plant Species Identification Authors: Daniel Rossi, Guido Borghi, Roberto Vezzani Published: 2026-08-12 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.11844v1 Automated plant species identification from citizen-science imagery is an established, demanding fine-grained recognition problem: large taxonomic label spaces, visually similar species, and long-tailed observations require real model capacity, while field use constrains memory, latency, and power. Model size is only part of the deployment cost: intermediate activations held in memory during inference and platformdependent execution behavior matter too, so compact recognition must be assessed on target hardware rather than through complexity metrics alone. We present BoltNet, an ultra-lightweight fully convolutional architecture combining a Spatial Redistribution Bottleneck and Logit PreSampling to improve the tradeoff between predictive performance and model size in high-cardinality classification, and report the AccuracyCompression Tradeoff as a complementary diagnostic. On Pl@ntNet300K, BoltNet reaches 0.682 F1-score with 341K parameters (1.37 MB), the highest F1-score among evaluated models below 2 MB and close to substantially larger convolutional backbones. Model-only measurements on a Raspberry Pi 5, Jetson Orin Nano, and Hailo-8 characterize execution across CPU, GPU, and NPU platforms, where BoltNet is the most consistently efficient model, with the best FPS/W on the GPU and NPU and second-best on the CPU. Results on AIDERv2 and CLRS provide secondary evidence of transfer across environmental image-classification tasks. Code available at: https://codeberg.org/danielrossi/BoltNet --- ### When the Knowledge Base Becomes the Gold Standard: Measuring Resource-Shared Evaluation Loops in Entity-Level Machine Translation Authors: Jinhyung Bae, Dain Kil, Seongmin Oh, Seungmin Lee Published: 2026-08-12 Categories: cs.CL, cs.DL arXiv: https://arxiv.org/abs/2608.11843v1 The Seungjeongwon Ilgi, a UNESCO Memory of the World record, is only 37.4% translated, and the most conspicuous failure mode in automatic translation is the person name -- a misread name corrupts the historical fact rather than merely the surface. Low-resource historical domains have no expert gold standard for entity translation, so practitioners substitute a knowledge base (KB) for the gold. That KB is the same resource injected into the system: scoring becomes self-referential and the metric measures instruction compliance rather than translation quality. We measure this loop. Using expert person-name annotations from the National Institute of Korean History as a gold independent of the injection pipeline, we hold the entity set fixed and vary only the provenance of the correct reading. Of 527 expert-annotated mentions, only 31.1% lie outside the injection pipeline, and the residual loop is not uniform -- in the overlapping segment the injected reading agrees with the human translation 97.8% of the time against 70.1% in the independent one, so the segment that looks healthiest is the one the loop is holding up. Across four models, a difference-in-differences analysis shows the gain from KB injection is confined to the segment whose gold shares the injected resource; in the independent segment it is at or below zero. Post-injection preservation clusters in a narrow 0.910-0.996 band even though baseline capability differs fivefold, so the reported gain is the complement of prior performance and weaker models appear to improve more dramatically. On an independent sample built by removing the construction filter, the measure replicates within model (overlapping intervals) while discriminating between models (non-overlapping intervals) -- it reflects a property of the model, not of the sample. --- ### User-Assisted Collaborative Distributed Inference for Efficient QoS-Aware Autoscaling Authors: Alfreds Lapkovskis, Ali Beikmohammadi, Sindri Magnússon, Praveen Kumar Donta Published: 2026-08-12 Categories: cs.DC, cs.AI, cs.LG, cs.NI, cs.PF arXiv: https://arxiv.org/abs/2608.11840v1 Growing demand for artificial intelligence (AI) inference services requires scalable infrastructure, yet centralized serving costs rise with demand. We propose a collaborative distributed inference system combining dedicated infrastructure with resources contributed by service users. Dedicated resources provide baseline capacity for maintaining quality of service (QoS), while volunteered resources absorb increasing demand without proportional growth in centralized infrastructure. To capture stochastic and dynamic interactions among users, resources, tasks, and policies, we develop a high-dimensional generative Markov model with structured temporal factorization. The model supports simulation and provides a foundation for task scheduling and QoS-aware resource allocation optimization. We evaluate the system across user populations, resource capacities, and centralized and distributed scheduling policies. Simulations show that distributed scheduling becomes increasingly advantageous as the user population grows, improving request completion and P99 latency while substantially reducing dedicated resource consumption. These results demonstrate the feasibility of user-assisted collaborative inference for infrastructure-efficient autoscaling. --- ### Air Quality Station Simulation via LSTM and Attention-Based Modelling Authors: Alexander Kostadinov, Petar O. Hristov, Dessislava Petrova-Antonova Published: 2026-08-12 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.11839v1 Poor air quality in urban areas is driven by a complex chain of processes and presents a significant public health concern. To better understand and control the mechanisms that determine air quality, cities deploy networks of measurement stations, and launch initiatives for collecting denser data about the concentration of pollutants in the atmosphere. Extracting insights from the stations relies on their reliable and uninterrupted operation. However, hardware is susceptible to faults and black- outs that may result in data unavailability, which affects the overall quality of analyses. In this paper, we present a deep-learning model, called SATADL, which can infer complex relations and output multiple-hour-ahead air-quality forecasts. The goal of the model is to simulate the mea- surements of an unresponsive station until its operation is restored. The architecture of the model, which allows it to extract information from different aspects of the data, is described in detail and a careful examination of all of its components is provided. We demonstrate the performance of SATADL on four sets of air quality stations from around the world, by using it to simulate the concentration of PM10 for periods of hypothetical failures of one of the measurement stations, lasting for as long as 48 hours. A selection of baseline and published deep learning models were trained and used as a benchmark. The results show that SATADL per- forms better across different prediction windows, for both coefficient of determination and root mean squared error, demonstrating its suitability as a virtual proxy station. --- ### GeoBridge: Decoupled Semantic Conditioning for Generative Image Geolocalization Authors: Zhiyang Dou, Xumeng Han, Fengde Peng, Zipeng Wang, Moxuan Zhao, Zhipei Huang, Zhenjun Han Published: 2026-08-12 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.11838v1 Multimodal large language models (MLLMs) have advanced image geolocalization mainly by improving how they reason about geographic cues. How that reasoning isdecoded into coordinates, however, has lagged behind. Predicting a place name for a geocoding API is discrete and lossy: it ignores image evidence and collapses multi-granular semantics into a coarse lookup. We argue that the bottleneck has shifted from what a model reasons to how that reasoning is represented for a continuous, geometry-aware decoder. We present GeoBridge, a role-decoupled conditioning mechanism that connects a frozen semantic MLLM to a frozen Riemannian flow-matching head that generates coordinates on the sphere. The central obstacle is arole conflict: supervising the condition with discrete semantic labels biases its representation toward class-discriminative geometry, at odds with the smooth manifold the generative head requires. GeoBridge keeps the semantic supervision decoupled from the condition interface: a separate projection forms the continuous condition the frozen head expects, injecting geographic priors without disturbing the spherical decoder. On IM2GPS3K, GeoBridge reaches 38.67/52.89/70.37 at the 25/200/750 km thresholds, improving over a place-name-to-API pipeline and reasoning-augmented direct prediction at these precision-relevant scales. GeoBridge is a decode-side algorithmic contribution, orthogonal and complementary to chain-of-thought reasoning. Code will be made publicly available. --- ### Distractor-Aware Video Object Segmentation Authors: Andreas Robinson, Abdelrahman Eldesokey, Michael Felsberg Published: 2026-08-12 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.11835v1 Semi-supervised video object segmentation is a challenging task that aims to segment a target throughout a video sequence given an initial mask at the first frame. Discriminative approaches have demonstrated competitive performance on this task at a sensible complexity. These approaches typically formulate the problem as a one-versus-one classification between the target and the background. However, in reality, a video sequence usually encompasses a target, background, and possibly other distracting objects. Those objects increase the risk of introducing false positives, especially if they share visual similarities with the target. Therefore, it is more effective to separate distractors from the background, and handle them independently. We propose a one-versus-many scheme to address this situation by separating distractors into their own class. This separation allows imposing special attention to challenging regions that are most likely to degrade the performance. We demonstrate the prominence of this formulation by modifying the learning-what-to-learn (LWL) method to be distractor-aware. Our proposed approach sets a new state-of-the-art on the DAVIS 2017 val dataset, and improves over the baseline on the DAVIS 2017 test-dev benchmark by 4.6 percentage points. --- ### Kernel Methods for Learning Operators with Multiple Inputs and Outputs Authors: Adrien Weihs, Chunyang Liao, Jingmin Sun, Hayden Schaeffer Published: 2026-08-12 Categories: cs.LG, math.ST, stat.ML arXiv: https://arxiv.org/abs/2608.11831v1 Learning mappings between infinite-dimensional objects is a central challenge in scientific machine learning. We introduce a general kernel-based encoder-decoder framework for operator learning that separates observation, representation, learning, and reconstruction. We develop this framework for multi-input, multi-output operator learning, where operators map between products of potentially distinct function spaces. Our approximation theory shows that, although the number of inputs and outputs can increase, the convergence rate is governed by the most challenging constituent approximation problem rather than the overall problem dimension. The framework leads to practical kernel methods with closed-form training and inference, combining mathematical tractability with computational efficiency. We further specialize the approach to multiple operator learning by introducing KernelMO, a family of kernel methods with complementary operator-valued and product-space formulations. Across five families of parametric partial differential equations, the proposed methods achieve competitive or state-of-the-art predictive accuracy while reducing training and inference costs relative to neural operator architectures and deep learning based models, offering an efficient and lightweight alternative. --- ### Quantifying the Relationship Between Clinical Safety and Environmental Impact in Therapeutic LLMs Authors: Alireza A. Safaei, Laura M. Vowels, Matthew J. Vowels, Apoorv Jha, Shekoufeh Rahimi Published: 2026-08-12 Categories: cs.CY, cs.CL arXiv: https://arxiv.org/abs/2608.11830v1 The deployment of large language models (LLMs) in mental health contexts raises questions about the relationship between clinical safety and environmental cost. In this paper, we examine this relationship by combining K-Bench clinical safety scores with EcoLogits life-cycle assessment estimates across 47 supported model configurations. We evaluate model performance and environmental impact across four dimensions: energy use, carbon emissions, water consumption, and abiotic depletion. The results indicate a non-linear trade-off at the upper end of the safety distribution: a 2.61 percentage-point increase in clinical safety score corresponded to an approximately 60-fold increase in estimated energy use per million output tokens. Row-level analyses further suggest that additional test-time compute did not consistently improve clinical safety and, in some configurations, was associated with lower clinical safety scores. These findings suggest that relying solely on larger models or additional inference-time computation may be an inefficient strategy for improving safety in therapeutic AI systems. We discuss the implications for sustainable deployment and highlight dynamic model selection, including model cascading, as a potential approach for reducing environmental impact while preserving clinical performance in higher-risk cases. --- ### Towards Understanding On-Policy Distillation through the Lens of Test-Time Scaling Authors: Xinmu Ge, Zizhuo Zhang, Yu Huang, Jianing Zhu, Lin Yuan, Wanli Gu, Weichang Wu, Weiran Huang, Bo Han, Xiaolu Zhang, Jiangchao Yao Published: 2026-08-12 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2608.11829v3 On-policy distillation (OPD) has emerged as a promising post-training technique for enhancing LLM reasoning. Under the reverse KL objective, the idealized optimum of OPD aligns the student distribution with that of the teacher. When the teacher consistently outperforms the student, this naturally suggests that OPD should yield broad improvements over the pre-OPD student. However, do such improvements extend across the entire range of test-time sampling budgets? In this work, we revisit this expectation through the lens of test-time scaling by varying the sampling budget $K$ and evaluating performance with pass@$K$. Across multiple settings, we observe two distinct patterns: OPD can improve pass@$K$ at both small and large sampling budgets, but it can also improve small-budget performance while reducing large-budget pass@$K$. We show one condition that guarantees such a reversal and an idealized reverse KL counterexample where it occurs even when the teacher has higher accuracy on every problem. To choose between two candidate teachers at a target sampling budget, we propose the \textit{Teacher Advantage Score at $K$} (TAS@$K$), which can be computed before OPD training to predict which teacher will lead to a larger improvement in pass@$K$. Across three domains and thirteen benchmarks, the ordering predicted by TAS@$K$ agrees with the observed pass@$K$ improvements of the resulting OPD models in 83.6\% of experiments, providing a useful signal for teacher selection at the target pass@$K$. --- ### Located but Not Releasable: Silent Gate Inversion and Bounded Linear Release Authors: Xining Xun Published: 2026-08-12 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2608.11822v1 A growing body of work reports that language models represent task-relevant latent structure that they fail to use. Whether such structure, once located, can be converted into behavior is a separate question that is rarely tested end to end. We submit the complete pipeline -- detect, localize, and release -- to a fully preregistered stress test on a 25.7M transformer trained on causal-evidence discrimination, where a known suppression phenomenon (latent causal structure present but behaviorally unused) has previously been documented. Every threshold, claim template, and decision-tree branch was hashed and archived before any corresponding data existed. Three findings. (i) Localization succeeds: interventions at observation-evidence channels of mid layers restore target behavior on otherwise-suppressed worlds (paired release advantages $0.563$ and $0.854$, 97.5% CIs excluding zero; best-site release rate $0.889$). (ii) Gating fails out of distribution: a detector calibrated to trigger on zero out-of-distribution calibration worlds triggers on 6.9-7.3% of held-out in-distribution generations and on zero of the 2,400 held-out generations that actually need it -- a complete inversion that silently reduces the gated pipeline to its base model. (iii) Linear release is capped: removing the gate and injecting a per-instance linear direction unconditionally yields a monotone dose-response that plateaus far below the preregistered release margin (intercept $0.382 \to 0.311 \to 0.264$ vs. threshold $\le 0.08$); per-instance adaptivity adds less than $\pm 0.03$. The failure is doubly located: the detector is OOD-inverted, and the entire family of linear release directions at this site and resolution is bounded away from sufficiency. The two failures are dissociable, and neither overturns localization. Every number traces to a hashed artifact in the released audit chain. --- ### TD-VAD: Breaking Visual Dependence in Video Anomaly Detection with Text-Driven Learning Authors: Shuangqing Zhang, Lei-Lei Ma, Zhao Wang, Wen Dong, Xinyi Xu, Guo-Sen Xie, Caifeng Shan, Fang Zhao Published: 2026-08-12 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.11820v1 Visual data is typically a prerequisite for training existing video anomaly detection (VAD) methods. However, obtaining sufficient annotated anomaly data for training is challenging and not scalable due to the rarity of anomaly data and the wide variety of abnormal events. In this work, we advocate that the effectiveness of treating texts as video sequences for the VAD model and propose a novel Text-Driven Video Anomaly Detection (TD-VAD) approach to break visual dependence. In contrast to the anomaly video data, text descriptions of abnormal events are easy to collect, and their class labels can be directly derived. Specifically, our method utilizes video-like text descriptions with temporal characteristics generated by LLM to train a VAD model, without any reliance on target-domain anomaly data. To capture the long- and short-range temporal logic of events, we design the event evolution causal attention module to model contextual dependencies across time. During inference, considering the domain gap between the texts and video sequences, we use the frozen CLIP encoder to extract embeddings of video frames to align the text modality while retaining crucial visual information. Comprehensive experiments on two large-scale VAD datasets, XD-Violence and UCF-Crime, demonstrate that our method outperforms prior one-class and unsupervised VAD methods by a large margin. --- ### How China-Origin Vision-Language Models Move from Refusal to Reframing in State Alignment Authors: Guang Yang, Fengchen Liu, Alex Wang, Homa Hosseinmardi, Amir Ghasemian Published: 2026-08-12 Categories: cs.CR, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2608.11816v1 State-aligned distortion has been documented in China-origin text-based large language models (LLMs), but whether, and in what form, it arises in multimodal systems has not been systematically examined. We construct a balanced benchmark of 200 core entries spanning ten politically sensitive topics, plus a seven-variant visual-abstraction probe, and run nine vision-language models (VLMs), seven China-origin and two non-China, across four elicitation paradigms and two prompt languages, yielding 21,708 trials. Each response is audited on six dimensions -- explicit refusal, information integrity, visual grounding, state-aligned framing, language consistency, and response length -- by two independent frontier LLM judges, validated against three human experts on a 200-trial sample. Measuring each dimension separately lets us decompose multimodal censorship into individual signals rather than a single refusal-based score; in particular, refusal and framing are measured independently, so a model can stop refusing while still reframing. We find that (i) Chinese-language prompting roughly triples the odds of state-aligned framing, within every model; (ii) China-origin models reframe more than non-China models (direction robust across judges and human raters; magnitude 1.6--3.2x); (iii) the effect is strongest in text-only political commentary (36.5%) and is gated by recognition of the depicted subject rather than pixel detail, persisting even at silhouette for iconic images; and (iv) across four Qwen generations, state-aligned framing rises while explicit refusal falls: censorship migrates from a visible act (refusal) to an invisible one (fluent reframing). We argue this shift to invisible reframing is fundamentally a problem of human-AI interaction: it removes the very signal users rely on to recognize that information has been withheld. --- ### Learning with Bilevel-Minimax Optimization for Efficient and Reliable Transfer Attacks Authors: Yaohua Liu, Yifan Guo, Jiaxin Gao Published: 2026-08-12 Categories: cs.LG, cs.CV arXiv: https://arxiv.org/abs/2608.11815v1 Transfer-based adversarial attacks craft adversarial examples using surrogate models to mislead black-box victim models. Beyond perturbation generation, transferability is fundamentally governed by the coupling of initialization, surrogate adaptation, and gradient dynamics. We revisit this challenge from a bilevel-minimax perspective and propose BMAT (Bilevel-Minimax Adversarial Transfer). The bilevel formulation captures the dependency between initialization and perturbation, while the inner minimax problem promotes surrogate robustness for cross-architecture generalization. Algorithmically, we develop an integrated bottom-up solver that combines a Soft Weight Modulator and an Implicit Gradient Approximator to enable ternary coupling among initialization, surrogate adaptation, and perturbation optimization. We further provide theoretical insights into the optimization dynamics of the proposed bilevel-minimax framework. Extensive experiments on classification and segmentation benchmarks show that BMAT outperforms more than 10 strong baselines across more than 30 victim models, improving both intra- and cross-architecture transfer and yielding up to a 2x reduction in mIoU. Code is available at https://github.com/callous-youth/BMAT. --- ### Can Vision Models Read the Radar Display? On the Feasibility of Radar Imagery for Air Traffic Complexity Estimation Authors: Hyewook Kim, Byul Kang, Seokbin Yoon, Keumjin Lee Published: 2026-08-12 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2608.11810v1 Air traffic controllers perceive traffic complexity through the radar display, suggesting that a computer vision model operating on the same imagery may provide a natural architecture for modeling controller-perceived complexity; however, whether radar imagery is a viable input format for deep learning vision models remains unclear. Unlike natural images, radar images are extremely sparse and self-similar, consisting primarily of a black background and a few visually identical aircraft blobs, while small changes in aircraft positions can substantially alter sector-level complexity. To test whether a vision model can capture these operationally important differences, we encode each traffic situation as a position image supplemented by five channels representing aircraft state variables, including heading, speed, and altitude, and train a Vision Transformer (ViT) to regress four intrinsic complexity components derived from pairwise geometric relations among aircraft. The model achieves $R^2 > 0.96$ for all four components, and a one-aircraft-removal perturbation study shows that its response changes proportionally to how much the removed aircraft contributed to sector complexity rather than treating every removal as equivalent. These results demonstrate that, despite its atypical visual characteristics, radar imagery is a viable input format for air traffic complexity modeling. --- ### CoDiR: Confidence-Guided Diffusion Refinement for Semi-Supervised Histopathology Segmentation Authors: Hoai Nhan Pham, Dang-Nguyen Bui, Le-Van Thai, Thanh-Hiep Vo, Lan Anh Dinh Thi, Tien Dat Nguyen, Duy-Dong Nguyen, Ngoc Lam Quang Bui, Tam Tran, Zhi Huang Published: 2026-08-12 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.11807v1 Semi-supervised histopathology segmentation is challenging due to scarce annotations and unreliable pseudo-labels in ambiguous gland regions. To address this problem, we propose Confidence-Guided Diffusion Refinement (CoDiR), a semi-supervised framework that combines a Mean Teacher segmentation model with diffusion-based pseudo-label refinement. Given an unlabeled image, the teacher first produces a soft prediction, and only low-confidence regions are refined by a conditional diffusion model trained to capture plausible mask structures from labeled data. The refined mask is then fused with reliable teacher predictions and used to train the student with confidence weighting and consistency regularization. On the GlaS and CRAG datasets CoDiR reaches 88.09\% and 89.83\% mDice with 10\% labeled data, and 89.19\% and 90.29\% mDice with 20\%, matching or exceeding the strongest published method on seven of the eight benchmark metrics. Ablations attribute the largest single contribution to the refinement module, which adds +6.36\% mDice over the Mean Teacher baseline. The implementation code is publicly available at: https://github.com/vongla345/codir --- ### Hybrid Gated Attention Authors: Zekun Zhou, Ruobing Xie, Lanrui Wang, Weixuan Sun Published: 2026-08-12 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.11805v1 Gated attention is an effective approach to mitigate attention sinks and enhance the representational capacity of attention. To further extend its effectiveness-efficiency Pareto frontier, we propose a Hybrid Gated Attention (HyGA) framework that contains three types of gating strategies. Specifically, these gates leverage diverse information from multiple stages of attention, and collaboratively build element-wise/head-wise gating from multiple perspectives, capturing intra-head and cross-head information interactions. Through our hybrid gating components, HyGA could provide multi-source modulation signals, enabling more comprehensive control over information flow and improving the representational capacity of attention. We also introduce low-rank matrix decomposition and learnable attention sink to further enhance training efficiency and stability. In experiments, we evaluate HyGA on widely-used benchmarks based on different backbones. The experimental results show that our HyGA comprehensively improves both training loss and various downstream performances compared with Gated attention. HyGA has also been verified to achieve the best performance at different computation costs, with comprehensive model analyses for better understanding. The proposed HyGA sheds light on a more effective, efficient, and stable attention mechanism. --- ### Towards Model-based Run-time Cybersecurity: On Control-Flow Anomaly Detection, Attack Identification, and Hardware Monitoring Authors: Martin Sachenbacher, Martin Leucker, Alexander Weiss, Aliyu Tanko Ali Published: 2026-08-12 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2608.11802v1 Methods to increase the resilience of systems to cyber-attacks become increasingly important. Control-flow monitoring provides a principled basis to ensure integrity and detect possible anomalies at run-time. Once anomalies have been detected, so-called attack trees can be used to identify possible types of attacks. However, this approach is vulnerable to camouflage, by which attackers try to evade detection (and correct identification) by deliberately manipulating also the system's observed control flow. In this paper, we outline a model-based approach that provides more robust intrusion detection and attack identification through an architecture that combines software- with hardware-based monitoring. In this approach, software-level observation indicates suspicious activities, while hardware-level monitoring checks them separately in more detail, making it much harder for attacks to camouflage themselves and go undetected. We illustrate the approach with an authentication-service example that captures a realistic failure mode: a software-level observer sees an anomalous but apparently harmless control-flow deviation, maps it to a benign root cause in an attack tree, but misses the true intrusion. A second, independent hardware control-flow monitor observes the actual transition sequence and thereby changes the attack-tree diagnosis from a low-severity configuration or maintenance issue to a high-confidence code-injection or control-flow hijack. In this scenario, the proposed combination of control-flow anomaly detection, attack-tree based intrusion identification, and hardware-based monitoring can improve not only anomaly detection, but also the diagnostic precision of attack-tree-based cyber-attack identification. --- ### JAPE: Joint Anomaly Prediction and Intrinsic Explanation in Multivariate Time Series Authors: Yian Wei, Yuanyuan Yao, Lu Chen, Xiangmin Zhou, Tianyi Li Published: 2026-08-12 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.11801v2 Multivariate time-series anomaly prediction aims to identify whether and when anomalies will occur over a future horizon from historical observations. Existing methods primarily characterize anomalies as deviations in future numerical values, which may overlook subtle dependency changes induced by weak anomaly precursors and provide no native variable-level explanation together with the alert. To bridge these gaps, we propose JAPE, a Joint Anomaly Prediction and Explanation framework that lifts anomaly prediction from numerical-deviation modeling to dependency-structure modeling. JAPE is the first anomaly prediction framework to explicitly model evolving dependency structures for both point-wise alerting and native variable-level explanation. Specifically, JAPE (i) proposes a Decoupled Spatio-Temporal Representation (DSTR) backbone that decouples temporal and spatial modeling and captures lag-aware dependencies via learnable lag aggregation, thereby perceiving structural precursors before numerical deviations emerge; (ii) designs a dual-view alerting mechanism that fuses numerical forecasts with evolving dependency graphs for point-wise anomaly prediction, capturing structural evidence even under subtle numerical deviations; and (iii) presents Native Predictive Explanation (NPE), which directly reuses the predicted dependency graphs to rank variables by structural deviations without additional models or training. Extensive experiments on five real-world benchmarks across three prediction horizons demonstrate that JAPE improves average F1 and AUC-PR by 19.7% and 41.3%, respectively, while improving explainability with 26.6% gain in MRR. --- ### Reading the Gate, Not the Interference: Output-Side Interference Measurement Does Not Track Merge Collapse Authors: Chencheng Zhu Published: 2026-08-12 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.11797v3 Task-arithmetic merging works until it doesn't, and the field diagnoses why by measuring interference inside the merged model. We take the most direct such measure, the exact layerwise activation cross-term of a factorial ledger, establish its causal anatomy, and then ask what it tracks. The anatomy is clean: each block mostly transports and amplifies the cross-term rather than generating it; erased, it is regenerated by the untouched marginal paths to 99% of its norm unless removed late; its output effect varies monotonically with the displacement's angle (orthogonal displacements make interference worse), and a two-assumption model derives the angle law and retro-dicts the dose curve (R^2 >= 0.99). What the measure tracks is not what the field assumes. Behavioural expert-likeness is decoupled from it across four instruments. Its cross-condition behaviour is denominator-dominated: an instruction template pins the main effect to within 1% while the absolute interaction grows 111x from two to six merged tasks, suppressing expressed interference at k=2 and amplifying it at k=6. And where merging actually collapses, the cross-term is a bystander, not the carrier: across two collapse parameterizations at two scales, even erased persistently at every position, removing it entirely repairs none of the collapse. There the output-side ratio carries no method information under a common counterfactual, while two state-space measures the field already uses rank methods correctly at both scales. All 81 predictions were frozen before their data; falsifications are reported as such. Output-side interference measurement reads the gate, the denominator, and the displacement budget, not the interference. What fails a merge is the carrier-bystander split: collapse rides in the marginal displacements while the cross-term merely accompanies it, and only state space sees the carrier. --- ### Toward Meaningful Transparency for AI Chatbots: Disclosing Persuasive Intent Reduces Persuasion Authors: Adrian Rauchfleisch, Andreas Jungherr Published: 2026-08-12 Categories: cs.CY, cs.AI, cs.HC arXiv: https://arxiv.org/abs/2608.11794v1 The growing role of AI-generated content and AI-enabled systems in public communication has led regulators to demand clear disclosure of content provenance and AI involvement. But the effects of such disclosures remain uncertain. We test two disclosure approaches in their impact on an AI chatbot's persuasive appeal. In a preregistered experiment, 1,500 UK adults held a short conversation with a persuasive chatbot about one of 60 policy issues. The chatbot was identical for everyone. We randomized the disclosure that people received: nothing (control), a prominent disclosure that they were interacting with an AI (T1), or that disclosure plus the chatbot's persuasive intent and instructions (T2). The chatbot shifted attitudes by 12.6 points on a 100-point scale in the control group. The AI-identity disclosure was practically equivalent to no disclosure, with a 13.1-point shift, whereas the additional intent disclosure cut the persuasive effect roughly in half to 6.3 points. It also made participants view the campaign's methods as less acceptable and support stronger penalties against it. For direct chatbot interactions, transparency about AI identity alone does not meaningfully impact its influence. While current rules emphasize what a system is, our results show why the regulation of persuasive AI must also address what the system is trying to do. --- ### PolarSym: Polar Geometry-aware Attention for CAD Floorplan Parsing Authors: Kerui Chen, Yiqing Wang, Kangzhou Xin, Qinghan Zhang, Songyang Ding Published: 2026-08-12 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.11793v1 CAD plan parsing is a fundamental task in Building Information Modeling (BIM), aiming to automatically extract architectural elements including walls, doors, windows, and furniture from 2D engineering drawings. Existing Transformer-based methods capture global semantic dependencies via self-attention, yet they infer spatial relationships merely from semantic features without explicitly characterizing the intrinsic geometric symmetry of building layouts. Such methods tend to produce mismatched correspondences in long-range matching and complex symmetric spatial layouts. To tackle this limitation, we propose PolarSym, a polar-coordinate geometry-aware attention framework for CAD plan parsing. The framework decouples geometric relationships of buildings into two complementary components, direction and distance, which are modeled independently. Structural consistency is strengthened by directional constraints, while long-range symmetric correspondences are built with distance constraints. A dynamic gating mechanism is adopted to synergistically fuse the two geometric information branches while maintaining the vanilla Transformer architecture. This design boosts geometric modeling capacity with negligible extra computation. Experiments on a public CAD plan parsing dataset show that PolarSym surpasses the reproduced SymPoint V2 baseline by 1.73% PQ, 1.54% RQ and 4.31% mIoU under identical training settings. PolarSym also converges faster and yields more stable optimization. Ablation experiments verify the complementary effects of direction and distance modeling. Our results reveal that PolarSym improves the geometric awareness of Transformers at low computational cost, offering an effective geometric modeling paradigm for CAD plan parsing. --- ### High-Order Liquid Evidence Encoding for Gradual GNSS Spoofing Detection in Autonomous Driving Authors: Muhammad Ayub Sabir, Junbiao Pang, Fatima Ashraf Published: 2026-08-12 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.11790v1 Accurate Global Navigation Satellite System (GNSS)-based localization is essential for safe and reliable autonomous driving. However, spoofing attacks can manipulate vehicle position estimates. Continuous and subtle attacks are particularly difficult to detect because individual GNSS observations may remain plausible while the inconsistency between GNSS-implied displacement and onboard vehicle motion gradually increases. Existing methods often rely on static vehicle-behavior features or a single residual signal and do not explicitly model this evolution. To address this problem, we propose a causal high-order liquid evidence framework for GNSS spoofing detection. The method first constructs a physics-guided GNSS--motion inconsistency residual by comparing GNSS-implied displacement with onboard-motion-derived displacement. It then forms separate evidence streams for the residual level and its first- and second-order discrete variations, with relevant contextual cues selected according to the evidence order. Each stream is processed by a separate adaptive liquid encoder, and the resulting temporal states are hierarchically coupled to predict spoofing at the window endpoint using only current and past observations. Experiments on three subsets of the real-world AV-GPS dataset show that the proposed method achieves the highest F1-scores among the evaluated temporal models on Dataset~1 and Dataset~3, reaching 0.9535 and 0.9777, respectively. On Dataset~3, it detects both labeled normal-to-attack transitions within four sampling steps. Code and datasets are publicly available at: https://github.com/pangjunbiao/GNSS_Spoofing.git. --- ### Anti-Shortcut Distillation via Temporal Negative Knowledge Transfer Authors: Syed Muhammad Raza, Omer Tariq, Jeongbae Son Published: 2026-08-12 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.11789v3 Knowledge distillation (KD) trains a compact student by attracting it towards a converged teacher. It is silent about which directions the teacher itself learned to suppress: repulsive and bias-aware objectives exist, but none exploits the teacher's own trajectory to identify what the student should avoid. We observe that the missing signal is already encoded in the teacher's optimization trajectory: features that an early-stage teacher emphasizes but that a converged teacher attenuates are precisely the shortcut directions worth pushing the student away from. We instantiate this observation as \textbf{A}nti-\textbf{S}hortcut \textbf{D}istillation (ASD), a push--pull KD framework that treats the converged teacher $\Tfinal$ as a positive semantic anchor and an early-checkpoint teacher $\Tearly$ as a temporal negative reference. ASD couples two losses: a temporal contrastive loss ($\Ltc$) that places the early-teacher feature as a same-sample negative against in-batch and memory-bank final-teacher features in an InfoNCE objective; and a shortcut suppression loss ($\Lss$) that penalizes student projection onto the top eigenvectors of $\E(\Dh\Dh^{\top})$, the uncentered second-moment matrix of early-to-final feature displacements. Across 13 teacher--student pairs on CIFAR-100, ImageNet-100, and TinyImageNet, ASD attains the highest clean top-1 accuracy on more than 10 pairs and outperforms standard KD on 12. On CIFAR-100-C corruption robustness, ASD obtains the lowest mean Corruption Error ($86.1$\,mCE) on the most challenging cross-architecture pair (WRN-40-2$\to$ShuffleNet-V2). Mechanistic diagnostics confirm the intended geometry: the ASD student is systematically anti-aligned with the shortcut direction, while its projection onto the robust subspace is substantially larger ($0.45$ vs.\ $0.12$). --- ### TELLME: Test-Enhanced Learning for Language Model Enrichment Authors: Minjun Kim, Inho Won, Hyeonseok Lim, MinKyu Kim, Junghun Yuk, Wooyoung Go, Jongyoul Park, Jungyeul Park, KyungTae Lim Published: 2026-08-12 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2608.11788v1 Continual pre-training (CPT) has been widely adopted as a method for domain adaptation in large language models. However, CPT has consistently been accompanied by challenges, such as the difficulty of acquiring large-scale domain-specific datasets and high computational costs. In this study, we propose a novel method called Test-Enhanced Learning for Language Model Enrichment (TELLME) to alleviate these issues. TELLME leverages the TestEnhanced Learning (TEL) principle, whereby the model's training efficiency is improved using quizzes during training. It integrates this principle with CPT, thereby promoting efficient domain-specific knowledge acquisition and long-term memory retention. Experimental results demonstrate that TELLME outperforms existing methods by up to 23.6% in the financial domain and achieves a 9.8% improvement in long-term memory retention. --- ### GRPO for Financial Advice Generation: Outperforming Commercial LLMs under CATE Evaluation Authors: Ofir Ben Shoham, Shrutendra Harsola, Vignesh Subrahmaniam, Shravan Mohan, Yakov Gazman, Oded Vainas Published: 2026-08-12 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2608.11787v1 Generating actionable financial advice from business records demands that models integrate numerical reasoning, domain knowledge, and sound judgment, while avoiding recommendations that could harm the business. Direct supervision is difficult: historical decisions are not necessarily optimal, and high-quality free-form labels are expensive to obtain. We formulate financial advice generation as a reinforcement learning problem and fine-tune an open-weight language model using Group Relative Policy Optimization (GRPO). Our reward is an LLM-as-a-judge rubric that scores each recommendation across multiple binary dimensions of advice quality, augmented with a safety gate for harm prevention. Since LLM-based evaluation alone cannot confirm whether improvements reflect genuine business value rather than adaptation to the judge, we complement it with a judge-independent audit based on a standard doubly-robust Conditional Average Treatment Effect (CATE) estimator. Under this observational off-policy audit, our trained LLM achieves approximately twice the estimated gross-profit lift of the strongest evaluated commercial baseline ($0.0228$ vs.\ $0.0104$), together with the lowest downside rate and the least negative tail risk of any policy evaluated. Notably, the two evaluations do not rank the baselines identically: the untrained base model places last on the judge rubric but second on the causal audit, indicating that the audit captures a signal the judge does not. Our results demonstrate that GRPO with a finance-grounded reward signal can produce substantially more useful business recommendations than commercial LLMs, and that a judge-independent causal audit is a valuable complement to, rather than a confirmation of, LLM-as-a-judge assessment in financial NLP. --- ### Language-Conditional Dequantization: Recovering What Quantization Steals from Non-English Languages Authors: Nirmal Thomas Published: 2026-08-12 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.11786v1 Aggressive quantization disproportionately harms multilingual capability: in the sub-4B INT3 GPTQ regime, we measure 2-4x larger perplexity degradation on non-English languages than on English. We propose Language-Conditional Dequantization (LCD), a post-hoc method that attaches per-language rank-2 LoRA corrections to the linear layers of an already-quantized model, adding 0.12% parameters per language and training in under 20 minutes on a single GPU. Across Qwen2.5-3B and Llama-3.2-3B, LCD recovers 70-83% of the perplexity gap for non-Latin script languages and 17-28% of the GlobalMMLU accuracy gap, outperforming a language-agnostic correction of equal capacity by 3-9 points on typologically distant languages and a data-free low-rank baseline (LQER) by an order of magnitude. We further identify a perplexity-accuracy disconnect and trace it to where quantization concentrates damage: early-depth errors (Llama) propagate downstream and resist local correction, while late-depth errors (Qwen) do not. A layer-restricted variant of LCD validates this mechanism directly. --- ### TradingMoE: Routing the Right Experts in Evolving Markets Authors: Chang Zhou, Xingtong Yu, Minbin Huang, Zhennan Wu, Yuan Fang, Hong Cheng, Xinming Zhang Published: 2026-08-12 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.11785v1 Large language models (LLMs) have shown strong potential for financial analysis and trading, but direct trading remains challenging because the predictive capabilities required can vary across assets, decision fields, and market conditions. Existing LLM-based trading systems either coordinate human-defined external experts or adopt conventional internal Mixture-of-Experts (MoE) routers that do not directly evaluate how individual experts contribute to trading decisions. Moreover, these routers receive no direct signal indicating when an inactive expert has become more suitable as market conditions change. We find that native router scores poorly reflect how much individual experts improve trading decisions, frequently leaving better alternatives unselected. We further reveal that token-specific expert usefulness exhibits a compact low-dimensional structure. Based on these findings, we propose TradingMoE, a trading-oriented sparse MoE that augments a frozen dense LLM with lightweight residual experts. We introduce a Query-Key router that represents the expertise required by each token under the current market context as a low-dimensional query and matches it with learnable expert keys. We further propose a sparse expert selection update mechanism that samples a few inactive experts during training and estimates whether they should replace the weakest expert in the current Top-k route. This mechanism enables the router to update expert selection as market conditions change while preserving sparse computation. Experiments against 22 baselines on stock and cryptocurrency markets show that TradingMoE improves cumulative return over the best-performing baselines by 30.89% and 30.7%, respectively. Rolling paper-trading experiments further demonstrate that its advantage persists under forward-only deployment. --- ### Coarsening Latent-Class Probabilities: Directional Distortion and Coverage Loss Authors: Marcell T. Kurbucz Published: 2026-08-12 Categories: econ.EM, stat.ME, stat.ML arXiv: https://arxiv.org/abs/2608.11784v2 Outcomes are regressed on a calibrated probability vector for unobserved class membership. Under a structural conditional mean excluding the score and conditional calibration, the observed-data model reduces to a partially linear regression. The probability vector is a Berkson-type surrogate for membership, so the effect vector $τ$ is identified without attenuation. In practice the vector is often coarsened to a hard label - an argmax, a confidence threshold - and that label need not retain the Berkson property. For any coarsening the plug-in estimator converges to $\mathcal{A}τ$, where $\mathcal{A}-I$ is determined by the regression of the discarded part of the score on the retained part. Coarsening therefore leaves $τ$ undistorted exactly when that regression vanishes, and otherwise distorts some contrasts far more than others. The same operator determines the bias that drives coverage loss. Where that bias is of the order of the standard error, the Wald interval has limiting coverage $Φ(z-ν)-Φ(-z-ν)$, with $ν$ their ratio. A fixed bias sends coverage to zero. Operator, standard error, and - through the uncoarsened estimator - the bias are estimable from observed data, so the implied coverage can be approximated before the interval is reported. Simulations show severe coverage loss after argmax coarsening. Three real-data audits exhibit the direction-specific distortion. --- ### VOLA: Improving Open-World Driving by VLM-Based Semantic Attribute Prediction Authors: Yuchen Zhang, Yuan Gao, Sebastian Schmidt, Johannes Betz Published: 2026-08-12 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.11777v1 Driving in the real world is open-world: a car may encounter a fallen mattress, a deer, or other objects outside its training data. Naming them is not enough. The system must know how to treat each region: can it drive over it, and how severe would a collision be? We therefore shift scene perception from category labels to dense action-relevant attributes, where each pixel is labeled by how it should affect motion rather than by object name. We instantiate this general formulation with two ordered attributes: 7-rank drivability and 5-rank vulnerability. We read Qwen3.5 image-token hidden states directly as a spatial semantic representation. A lightweight boundary-aware decoder then turns this coarse token grid into sharp full-resolution attribute maps. The whole process requires neither autoregressive text generation nor an external mask model such as SAM. We train on dense attribute labels built in CARLA and test transfer to real scenes and to novel obstacles never seen in training. We compare with vision-only segmenters trained on the same attributes and prompted VLM segmenters. Our model matches strong vision-only segmenters on familiar categories and improves transfer to real open-world anomalies, reaching 69.4% mean vulnerability-rank recall versus 57.1% for the best vision-only baseline and 53.9% for the best prompted VLM baseline. These results show that VLM image tokens provide useful semantic cues for transferring driving attributes to objects outside the training vocabulary. --- ### The Sleeping Agent: What Gist-Based Context Compression Loses and Why Authors: Nicholas E. Kyrkewood Published: 2026-08-12 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2608.11775v1 Gist-based context compression---summarising older conversation history into compact representations---is a common approach in long-horizon language model agents, yet its effect on different types of memory retrieval is poorly understood. We use Salience-Weighted Consolidation (SWC), a biologically-inspired compression framework motivated by sleep-based memory consolidation, as a diagnostic probe to study when gist compression helps and when it hurts. SWC scores conversation history by salience, partitions it into priority tiers, and applies structured gist abstraction to mid-priority content. Evaluating four conditions on all ten LoCoMo conversations---1,935 matched text-only questions in total, 1,501 used in the primary aggregate after excluding Category 5 (adversarial) questions---at temperature 0, we find a consistent task-type interaction: gist compression substantially outperforms truncation on multi-hop reasoning and single-hop factual questions, but temporal questions remain substantially harder under compression, with compressed conditions scoring well below the full-context reference on the conversations where both are evaluated. We trace this failure to a specific mechanism: the gist abstraction prompt preserves relational and event structure while discarding dates and times. A preservation analysis across all ten conversations confirms the mechanism: an approximately 20-fold increase in temporal expression preservation (3.05% to 62.39%) with a one-sentence prompt modification, while named entity and event preservation rates barely change (x1.02 and x1.11), demonstrating that the fix is a precision instrument. The prompt modification recovers +0.314 (0.254, 0.375) judge accuracy on category-2 (temporal) questions in the matched set. Code and results: https://github.com/kyrkewood/sleeping-agent. --- ### Diagnosis Before Recovery: Turning Agent Failures into Selective Self-Correction Authors: Pan Wang, Yihao Hu, Hang Wang, Zirui Lv, Xin Zhang, Jianshe Li, Jiang-Ming Yang, Wei Wu, Yongqi Tong Published: 2026-08-12 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.11772v1 Self-correction is particularly useful when a failure constrains the next repair. Coding agents benefit from this property because compilers, tests, and execution traces turn many failures into typed recovery signals, but broad language-agent tasks often expose only a coarse task failure. This creates a tension for generic recovery playbooks: they broaden the agent's context precisely when the system needs a narrower repair interface, mixing incompatible signals for invalid actions, missing procedures, and strict-format errors. Our insight is that development-set failures can recover part of the missing diagnostic substrate by deciding which recovery interventions are admissible before test-time correction. We propose DARC, a diagnosis-guided recovery harness that profiles task-family failure modes, prunes mismatched interventions from a shared recovery library, and freezes a verifier-selected success-cost policy for deployment. This causal order makes correction selective: the harness first determines what kind of failure can be repaired, then decides how much recovery evidence to spend. In ALFWorld, AppWorld, and XBRL Finance, the same protocol yields an action-validity harness, a procedural-recovery fallback, and a format-precision retrieval policy; in each evaluated setting it improves average task performance over base agents and broad playbooks while reducing environment steps or retrieval budget. Our experiments show that failures need not trigger uniformly more context: DARC turns self-correction from prompt expansion into recovery-interface design. DARC provides a practical route toward more reliable agents in domains where compiler-like feedback is absent: making failures actionable before making contexts larger. --- ### Achieving Near-Zero-Overhead Multi-Model Hierarchical Classification in Real-Time Detection Pipelines Authors: Vaishnav Raju Published: 2026-08-12 Categories: cs.CV, cs.DC, cs.LG arXiv: https://arxiv.org/abs/2608.11770v1 Edge-deployed vision systems in target recognition, surveillance, autonomous vehicles, and drone domains require hierarchical inference pipelines where a detection model identifies objects of interest and downstream classifiers provide fine-grained attribute analysis. Running all models on the GPU creates a serial bottleneck that limits real-time throughput as pipeline stages grow. Modern edge SoCs pair GPUs with dedicated neural accelerators (NPUs, DLAs) capable of concurrent execution, yet deploying custom models on these accelerators remains impractical due to strict operator constraints, quantization incompatibilities, and an undocumented end-to-end pipeline. We target NVIDIA Jetson DLA cores as the representative platform. We present a five-step methodology for zero GPU fallback DLA INT8 deployment of classification backbones, comprising architecture adaptation, manual dynamic range workaround to rescue TensorRT's implicit quantization (recovering 94.0% accuracy from implicit quantization's 75%) for rapid pipeline validation before explicit quantization, quantization-aware training, ONNX graph surgery for DLA compilation, and a concurrent GPU-detection/DLA-classification inference pipeline. We document nine engineering constraints with root-cause analysis and generalizable solutions. Validation on a dual-head person attribute classifier running on DLA alongside a GPU object detector on a Jetson Orin NX demonstrates near-zero pipeline overhead (12.5 vs. 13.3~FPS detector-only at 1080p), with dual-DLA scaling at no additional cost. The methodology is backbone-agnostic and generalizes to any detection-classification edge pipeline. --- ### HyperANFIS: Enhancing Rule Representation and Interpretability in Adaptive Neuro-Fuzzy Systems via Hyperbolic Geometry Authors: Haoran Pei, Zhao Su, Zetao Lin, Haoran Li, Jun Shen, Qi Zhu, Lan Guo, Qingguo Zhou, Binbin Yong Published: 2026-08-12 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.11768v1 The adaptive neuro-fuzzy inference system (ANFIS) is an interpretable reasoning framework capable of generating explicit IF-THEN fuzzy rules, making it suitable for tasks requiring transparent reasoning. However, existing ANFIS models generally construct rule antecedents and perform inference in Euclidean space, limiting their representational capacity and predictive performance. To address this issue, we propose Hyperbolic ANFIS (HyperANFIS), a hyperbolic extension of ANFIS. HyperANFIS preserves the fuzzy semantics and core architecture of conventional ANFIS while performing rule-prototype learning, rule activation, and consequent aggregation in hyperbolic space. It also retains the ability to generate interpretable IF-THEN rules. By exploiting the representational properties of hyperbolic geometry, HyperANFIS strengthens the fuzzy inference process, thereby improving predictive accuracy, inter-rule collaboration, and the credibility of its interpretable rules. Experimental results show that HyperANFIS consistently outperforms the standard ANFIS baseline and various ANFIS variants across all datasets, while also generating higher-quality fuzzy rules. --- ### Causal Structure is Inducible but Functionally Decoupled: The Routing/Readout Boundary of a Typed Mechanism Library Authors: Xining Xun Published: 2026-08-12 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.11767v1 When a language model answers an interventional question, the computation it must perform depends on the type of evidence the query requires. We report a decoupling in how a transformer organizes causal knowledge: slot-by-type structure induced by type-level supervision organizes routing, yet remains functionally decoupled from answer readout. We establish this with a typed mechanism library -- discrete mechanism slots partitioned by evidence type, auditable at the state level -- on a causal-world benchmark with exact interventional ground truth, under a frozen protocol, at two scales (22.6M and 125M). Four preregistered findings. (i) Origin. Slot-by-type organization is induced by type-level supervision: absent in architecturally identical unsupervised controls, not buyable by content-free gating labels, and statistically attributable to the supervision signal, replicating at 125M under a powered preregistered protocol (all nine cells passed). (ii) Boundary. The induced structure is a typed routing index with a sharp routing/readout boundary: slot codes scaffold routing but do not drive answer readout ($|Δ\hat{y}| \le 3.4\times10^{-6}$, zero collateral, three seeds, stable across a 5.6x scale window) -- we therefore make no behavioral-editability claim. (iii) Cost. The structure is free: LM quality matches a parameter-matched monolith within 0.0082 nats. (iv) Trust. The library state is exactly local under edit and bit-exactly revertible -- 250 single-edit and 1,000 stacked reverts per seed, zero failures. We further find that the unsupervised null itself moves with scale, so comparisons reusing a null calibrated at one scale may be confounded at another. Every claim is tied to a preregistered, machine-checkable criterion archived before the data it governs; the full audit trail, including one criterion we failed and how the frozen protocol handled it, is released as an appendix. --- ### Instruction Alignment for Binary Code Representation Learning Authors: Huaijin Wang, Shuai Wang Published: 2026-08-12 Categories: cs.SE, cs.AI, cs.CR arXiv: https://arxiv.org/abs/2608.11766v1 Binary code representation learning is a fundamental problem in software security and reverse engineering. Existing methods mainly learn function-level embeddings that capture coarse-grained semantic relationships between binary functions, but they largely ignore fine-grained instruction-level correspondences. This limitation misses valuable supervision signals available from compiler debug information, which can support the learning of more accurate and interpretable binary code representations. We propose to leverage instruction alignment knowledge to further improve binary code representation learning. Our preliminary study reveals that models finetuned for function-level binary code similarity exhibit substantially better instruction alignment than their pre-trained model, suggesting a strong correlation between instruction alignment and function-level embedding quality. Motivated by this observation, we design a training approach that explicitly incorporates instruction alignment as an auxiliary training objective. Our experiments show that instruction alignment training improves retrieval accuracy and provides more discriminative signal for the model's similarity judgments. --- ### ProBAG: Prototype-Guided Boundary-Aware Graph Diffusion for Weakly Supervised Histopathology Segmentation Authors: Duy-Dong Nguyen, Le-Van Thai, Hoai Nhan Pham, Ngoc Lam Quang Bui, Tam Tran, Zhi Huang Published: 2026-08-12 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.11765v1 Weakly supervised semantic segmentation enables histopathology tissue segmentation from image-level annotations, avoiding costly pixel-level labeling by expert pathologists. However, CAM-based methods often localize only highly discriminative regions and remain unreliable near tissue interfaces. We propose ProBAG, a stage-1 pseudo-mask generator that combines dataset-specific visual prototypes with pathology-aligned CONCH text prototypes over multi-scale frozen UNI features. ProBAG introduces two complementary mechanisms: class-wise power recalibration that reshapes inter-class competition while preserving the total foreground activation mass at each pixel, and one-step graph diffusion in which feature affinities are penalized by a late-transformer attention-context discrepancy used as a soft structural boundary cue. The resulting stage-1 pseudo-masks require neither CRF nor an external segmentation model; for complete two-stage comparison, they additionally supervise a downstream Phikon-FPN segmenter. Experiments on BCSS-WSSS and LUAD-HistoSeg show consistent gains over recent WSSS approaches, while ablations indicate that pathology-aligned text semantics provide the largest improvement and graph refinement provides a smaller complementary gain. The code is available at: https://github.com/wterrr/WSSS --- ### A comparison of CNN architectures for Alzheimer's disease detection in single-view MRI scans Authors: Hiram Zuniga, Ulises Orozco-Rosas, Kenia Picos Published: 2026-08-12 Categories: eess.IV, cs.CV, cs.LG arXiv: https://arxiv.org/abs/2608.11762v1 Alzheimer's disease is a leading cause of death with no cure. Therefore, early detection is critical to slow progression and preserve quality of life. Diagnosis relies on medical history, cognitive tests, physical exams, and MRI brain scans, making deep learning suitable for Alzheimer's classification. This work proposes a benchmark that evaluates ten different convolutional neural network (CNN) architectures (including ResNet, DenseNet, MobileNet, EfficientNet, and VGG family models) under the same held-out test split protocol. A two-stage transfer learning and full fine-tuning pipeline is introduced to perform training using a class-balanced subset (3,900 images) derived from the OASIS medical imaging dataset, comprising 86,437 single-view MRI brain scans labeled into four classifications of Alzheimer's disease: Non-Demented, Very Mild Dementia, Mild Dementia, and Moderate Dementia. The best results were achieved by VGG16, with a 0.9637 validation accuracy and a 0.9533 test accuracy score. A key finding documented in this work is the difficulty of classifying the transition from Non-Demented to Very Mild Demented stages, observed consistently across all ten architectures. --- ### Tight Nonasymptotic Local Convergence of Sinkhorn-Knopp Authors: Wenzhi Gao, Zhaonan Qu, Yinyu Ye, Madeleine Udell Published: 2026-08-12 Categories: math.OC, cs.LG, stat.ML arXiv: https://arxiv.org/abs/2608.11760v3 We revisit the Sinkhorn-Knopp (SK) algorithm for the matrix scaling problem. Despite extensive literature on the global convergence of SK and its variants, its local linear convergence behavior remains less understood. We address this gap by providing the first nonasymptotic local analysis of SK that matches the rate obtained from existing asymptotic Jacobian-based arguments. We show that under certain connectivity conditions, SK is a polynomial-time algorithm for doubly stochastic matrix scaling. With the developed tools, we showcase the local suboptimality of SK and provide accelerated variants. Finally, for dense matrices, we improve the complexity of existing first-order matrix scaling algorithms from $O(\tfrac{n^{7/3}}{\varepsilon^{2/3}})$ to $O(\tfrac{n^{9/4}}{\sqrt{\varepsilon}})$. --- ### Automated binary classification of hazelnut X-ray images: A deep-learning benchmark for quality assessment Authors: Giancarlo Sportelli, Nicola Belcari, Roberta Pace, Umberto Bernardo, Sharmin Sultana, Alessandra Toncelli, Matteo Giaccone Published: 2026-08-12 Categories: cs.CV, cs.LG, physics.app-ph arXiv: https://arxiv.org/abs/2608.11759v1 Non-destructive X-ray imaging can reveal internal hazelnut defects that are difficult to detect by external inspection alone; however, automated interpretation remains challenging because of subtle radiographic differences among classes, marked class imbalance, and limited annotated data. Here, we present a benchmark for binary hazelnut quality classification (healthy versus defective) based on 799 segmented single-kernel X-ray images (224 x 224 pixels, grayscale), grouped into 101 acquisition units. Seven single-model configurations and ten probability-aggregation ensembles were evaluated using a group-wise split-rotation protocol across five data splits generated using different random seeds. Decision thresholds were selected on the validation set, and performance was assessed deterministically on validation and test sets. Under the expert-reassessed annotation condition, the average-probability ensemble of the binary cross-entropy-trained convolutional neural network and frozen Swin Transformer achieved the highest mean balanced accuracy (86.3% +/- 1.8%, five seeds), with several other ensembles providing comparable performance. Across methods, substantial split-to-split variability was observed, indicating that multi-split evaluation is essential for reliable model comparison at this dataset scale. Expert reassessment of ambiguous samples improved the performance of all 17 evaluated methods by 2.8-8.1 percentage points, while having only a limited effect on cross-split variance. The results highlight both the potential of deep learning for automated X-ray-based hazelnut quality assessment and the importance of rigorous evaluation and label curation in small, imbalanced agricultural imaging datasets. --- ### AWARe: Mitigating Catastrophic Forgetting via Activation-Weighted Adaptive REtention Authors: Juncheng Liao, Jinfan Lv, Guoming Wang, Jupeng Zheng, Ling Xiao, Siliang Tang Published: 2026-08-12 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.11758v1 Multimodal Large Language Models (MLLMs) exhibit strong generalization and reasoning abilities due to large-scale multimodal pre-training. However, fine-tuning these models on downstream tasks often leads to catastrophic forgetting, where newly learned task-specific knowledge degrades previously acquired capabilities. This issue arises because gradient updates for new tasks overwrite parameters critical to prior knowledge, limiting the practical deployment of MLLMs. To address this challenge, we propose Activation-Weighted Adaptive REtention (AWARe), a fine-tuning method that mitigates catastrophic forgetting by dynamically controlling parameter updates based on activation patterns. AWARe assigns activation-based importance scores to parameters, selectively freezing those essential for preserving prior capabilities while allowing less important parameters to adapt to new tasks. Importantly, AWARe operates without modifying model architectures, ensuring compatibility with existing inference engines. Extensive experiments demonstrate that AWARe effectively preserves upstream capabilities while achieving superior downstream performance compared to existing methods. Code is available at https://github.com/kaln27/AWARe. --- ### MuseCritic: Learning Multi-Aspect Song Rewards through Natural-Language Aesthetic Critiques Authors: Jiabao Zhuang, Changhao Jiang, Hanchen Wang, Jiahao Chen, Zhixiong Yang, Zhenghao Xiang, Yifei Cao, Jiajun Sun, Hui Li, Ming Zhang, Tao Ji, Tao Gui et al. Published: 2026-08-12 Categories: cs.SD, cs.CL arXiv: https://arxiv.org/abs/2608.11755v1 Long-form song generation models continue to improve in duration, structural integrity, and acoustic complexity, making reliable aesthetic rewards increasingly important for aligning these models with human preferences. However, reward models for complete songs remain limited, and existing evaluators typically predict scores in a single forward pass without providing readable explanations. We introduce MUSECRITIC, a semi-scalar reward model that generates a natural-language critique covering five aesthetic dimensions and uses it as an intermediate representation to predict continuous reward scores. MUSECRITIC follows a two-stage training pipeline: a teacher model first provides high-quality critiques for supervised fine-tuning, after which the fine-tuned model generates its own critiques for reward learning, mitigating distribution shift between training and inference. On an in-domain test set of 200 SongEval songs, MUSECRITIC reduces macro-averaged mean squared error from 0.2875 to 0.2316 and improves macro-averaged LCC, SRCC, and Kendall's tau to 0.9068, 0.8838, and 0.7178, respectively. On the out-of-domain Music Arena benchmark with 733 preference pairs, it achieves the highest accuracy of 71.35%. Moreover, using MUSECRITIC with GRPO improves Muse-0.6B on all nine aesthetic metrics from SongEval and Audiobox Aesthetics. These results demonstrate that critique-conditioned reward modeling reduces scoring error and provides an effective optimization signal for song generation. The project repository is available at https://github.com/WuqnEl/MuseCritic. --- ### LabelFusion-TS: Fusing Large Language Models, Transformer Encoders, and Financial Time Series for Monetary-Policy Stance Classification Authors: Michael Schlee, Fabian Lukassen, Christoph Weisser Published: 2026-08-12 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.11753v1 Financial text is produced and interpreted within a market environment, yet financial text classifiers almost always receive text alone. We study whether financial time series are useful as an additional input on the task of classifying sentences from Federal Reserve communication as hawkish, dovish, or neutral. Our system, \lfts{}, extends the \lf{} architecture with this modality: a small voting network combines three independently trained components, a fine-tuned RoBERTa encoder, a prompted large language model (LLM), and a fused ensemble of time-series transformers over the market series of the months preceding publication. Because only about a thousand annotated sentences are available for training, the RoBERTa encoder is first pre-trained on sentences annotated automatically by the LLM and only then fine-tuned on the human labels. Trained on Federal Open Market Committee (FOMC) communication up to 2015 and evaluated on 2015--2022, the fused system achieves 70.2\% weighted F1 -- against 64.1\% for the zero-shot LLM -- and overtakes it with as few as 240 human-labelled sentences. We take this as initial evidence for market time series as an input modality in financial text classification. --- ### UniSwap: Streaming Audio-Visual Identity Swapping for Talking Videos Authors: Yuxuan Zhang, Haozhong Xiong, Jiayi Song, Jinpeng Yu, Yang Shi, Jiaming Liu, Ruihua Huang, Liwei Wang Published: 2026-08-12 Categories: cs.CV, cs.SD arXiv: https://arxiv.org/abs/2608.11752v2 Talking-video character replacement requires coordinated transfer of appearance and voice while preserving the source motion, scene, linguistic content, and audio-video timing. Existing methods use separately optimized models for the two modalities, making audio-visual consistency difficult to enforce. We present UniSwap, the first framework for streaming joint audio-visual identity replacement in talking videos. Given a source video, a reference image, and a reference voice clip, UniSwap transfers the reference appearance and vocal timbre within a single audio-visual diffusion transformer while preserving the source content and dynamics. To address the scarcity of aligned cross-identity training pairs, we introduce a swap-and-reconstruct pipeline that removes visual and vocal identity from real clips and uses the original clips as reconstruction targets. Starting from a bidirectional backbone, we progressively adapt the model through In-context Pretraining for joint replacement, Conditional Streaming Adaptation for block-causal KV-cached generation, and Efficient Self-forcing DMD for mitigating exposure bias and reducing sampling from 30 to 3 denoising steps per block. Efficient Multi-LoRA Switching enables the three DMD roles to share a single frozen backbone. Feature-RoPE Decomposition keeps cached positions within the training range, supporting stable long-form inference. Experiments demonstrate strong audio-visual synchronization, competitive identity preservation, efficient streaming, and stable long-form generation. --- ### MOON: Multi-Objective OrthoNormalized Updates for Multitask Learning Authors: Shiji Zhou, Kunlin Lyu, Lei Zhang, Ruodong Wang, Yifan Sun Published: 2026-08-12 Categories: cs.LG, cs.AI, stat.ML arXiv: https://arxiv.org/abs/2608.11749v1 Multi-objective optimization (MOO) has demonstrated significant success in multi-task learning by mitigating task conflicts through gradient manipulation. However, most existing methods flatten model parameters into vectors and perform gradient manipulation under Euclidean geometry, thereby overlooking the matrix structure prevalent in modern architectures such as Transformers. In this paper, we show that gradient manipulation in Euclidean space does not generally yield the steepest descent direction under matrix geometry, potentially limiting optimization efficiency. Drawing from the theory of steepest descent for matrix-valued parameters, we propose MOON (Multi-Objective OrthoNormalized Updates), which performs gradient manipulation under spectral--nuclear norm geometry and uses the orthonormalized manipulated gradient for parameter updates. Theoretically, for smooth non-convex objectives, we establish convergence of the averaged Pareto-stationarity measure at rates of $\mathcal{O}(T^{-1/2})$ in the deterministic setting and $\mathcal{O}(T^{-1/4})$ under stochastic gradients. Empirical results across various benchmarks show that MOON consistently improves both optimization efficiency and final multi-task performance. Our code is available at https://github.com/KunlinLyu/MOON. --- ### Dual Modality Prompted Diffusion Priors for Zero Shot Hyperspectral Pansharpening Authors: Pengwei Xie, Fei Zhu, Jiajun Li, Xiangyuan Liu, Xiangyuan Liu, Kangqing Shen, Gemine Vivone Published: 2026-08-12 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.11748v2 Hyperspectral pansharpening aims to reconstruct a high resolution hyperspectral (HRHS) image from a panchromatic (PAN) image and a low resolution hyperspectral (LRHS) image while preserving both spatial details and spectral fidelity. Recent diffusion based methods exploit pretrained image priors by generating a low dimensional representation and subsequently mapping it to the hyperspectral domain. However, the observed panchromatic and hyperspectral images are typically imposed only through external reconstruction objectives, limiting their direct interaction with the diffusion prior. To address this issue, we propose dual-modality image-prompted diffusion model (DIDM) for zero shot hyperspectral pansharpening. DIDM encodes the low resolution hyperspectral and panchromatic observations into spectral and spatial prompt tokens, respectively, and injects them into intermediate features of a frozen remote sensing diffusion model through cross attention, allowing complementary spectral and spatial information to directly guide diffusion feature evolution. In addition, we introduce a panchromatic guided weighted pixel aware total variation regularizer that combines low resolution hyperspectral degradation fidelity and panchromatic response fidelity with gradient adaptive structural regularization, thereby preserving structural discontinuities while suppressing spurious variations in homogeneous regions. Extensive experiments on Pavia, Chikusei, and Houston under reduced resolution protocols show that DIDM achieves the best performance across all evaluated metrics, while full resolution evaluation on FR1 yields the highest HQNR among the compared methods. These results demonstrate that internal dual modality prompting and panchromatic guided structural regularization provide an effective balance between spatial detail enhancement and spectral preservation. --- ### Making Every Step Count: Spatio-Temporal Information Allocation for Imaging Inverse Problems Authors: Yi Cao, Xiangyong Cao, Pei Liu, Yong-Jin Liu, Deyu Meng Published: 2026-08-12 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.11747v1 Flow-based generative models have emerged as powerful image priors for training-free inverse problem solving, capturing coherent semantics and fine-grained structure. Despite these strengths, existing flow-based inverse solvers primarily focus on the design of individual updates, largely overlooking spatio-temporal information allocation under a fixed number of function evaluations (NFEs). Temporally, insufficient early exploration can trap the flow trajectory in an incorrect semantic basin, whereas excessive allocation of NFEs to early stages leaves little budget for late-stage refinement. Spatially, data consistency provides direct constraints only within observed regions, whereas the recovery of missing regions relies mainly on the generative prior. To address these two issues, we introduce two complementary and training-free components, i.e., Spectrum-Adaptive Scheduling (SAS) and Measurement-Prioritized Attention (MPA). For temporal allocation, SAS distributes the available NFEs over flow time according to the degradation spectrum and logSNR geometry, thus better balancing semantic exploration and detail refinement. For spatial propagation, MPA exploits data-prior conflicts to guide information toward weakly constrained regions, thereby enhancing semantic and structural fidelity. Extensive experiments on standard image inverse problems, e.g., super-resolution, motion deblurring, and inpainting, demonstrate that the proposed components can be integrated into existing flow-based inverse solvers in a plug-and-play manner without retraining or additional flow-model evaluations, and can also significantly improve the restoration quality of existing solvers. --- ### Epiplexity Guided Data Selection and Generation for Out-of-Distribution Generalization Authors: Ellen Su, Andres Potapczynski, Shikai Qiu, Edward Hughes, Andrew Gordon Wilson Published: 2026-08-12 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2608.11746v1 Modern systems are increasingly expected to transfer across tasks not specified during training. What data facilitates generalization in these new, unanticipated settings? One hypothesis is that data with more structural information could contain shared circuits and subprograms that could be recycled in a wider array of downstream settings. Epiplexity, a recently proposed measure of the structural information a compute-bounded learner can extract from data, provides a mechanism to reason about this relationship. In this paper, we show how to operationalize epiplexity as an online training signal for data selection and synthetic data generation. For selection, we fit scaling laws to the training loss curves of natural data domains to predict the expected epiplexity gain as a function of training tokens, and use this signal to adaptively determine the sampling weights over domains during training. For synthetic data generation, we define a generator's reward as the change in learner epiplexity over a buffer of previously generated data and use REINFORCE policy gradients to guide the generator toward an epiplexity-maximizing distribution. In both cases, higher epiplexity predicts improved downstream performance on zero-shot and fine-tuning based tasks, supporting the hypothesis that data rich in structural information yield representations that transfer across domains. --- ### LiveAnimate: Stable Long-Form Streaming Human Animation in Real-Time Authors: Yuxuan Zhang, Haozhong Xiong, Yubo Huang, Jiayi Song, Jinpeng Yu, Haofan Wang, Jiaming Liu, Ruihua Huang, Liwei Wang Published: 2026-08-12 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.11745v2 Pose-driven human animation synthesizes a video of a target person from a single reference image and a driving pose stream. Real-time generation is essential for interactive applications such as live streaming, telepresence, and virtual avatars, yet diffusion-based systems require minutes to hours per clip, precluding responsive interaction. We present LiveAnimate, to our knowledge the first animation system to combine real-time streaming with stable long-form generation at billion scale, built on a 14B-parameter video Diffusion Transformer (DiT). A two-stage training pipeline first adapts a pretrained bidirectional DiT into a block-causal autoregressive generator through Reference-Anchored Teacher-Forcing Adaptation, and then reduces the sampling budget to three steps through Block-wise Self-Forcing Distillation. To preserve appearance over extended streams, we introduce Pose-Retrieval Sink Attention (PR-Sink), a bounded KV-cache mechanism combining a Static Sink that permanently anchors the first generated block, a Dynamic Sink that holds a pose-retrieved historical block, and a three-slot Rolling Window. When a pose recurs, PR-Sink restores the relevant appearance context without retaining the entire sequence, so memory and per-block latency remain constant regardless of stream duration. Together with Ulysses sequence parallelism and operator fusion, these designs enable 19.63\,FPS streaming inference on two NVIDIA H100 GPUs. On a three-minute benchmark, LiveAnimate maintains nearly constant perceptual quality and identity from the first 30 seconds to the final minute, while prior systems degrade substantially or require hours of offline computation for the same rollout. These results establish a new operating point in quality, latency, and duration for interactive full-body animation. --- ### Ripple-Pivot Search: Active Parallel Decoding for Diffusion Large Language Models Authors: Yushi Ye, Xu Chen, Haoyun Jiang, Jinsong Lan, Haihong Tang, Xiangtao Li, Mingming Gong, Ivor Tsang, Yanfeng Wang, Jiangchao Yao Published: 2026-08-12 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.11742v2 Diffusion Large Language Models (dLLMs) have emerged as a competitive alternative to autoregressive language models, offering the potential for substantially faster inference through parallel decoding. Existing parallel decoding schedulers typically commit positions only after they meet a per-position criterion, overlooking how early commitments may benefit subsequent decoding. We identify a ripple effect in dLLM decoding: proactively committing a mid-entropy pivot position can induce a pronounced reduction in uncertainty across the remaining masked positions. This uncertainty reduction allows subsequent steps to unmask more tokens in parallel, thereby accelerating the overall decoding process. To exploit the ripple effect, we propose Ripple-Pivot Search (RPS), a novel training-free decoding method that seeks mid-entropy positions as promising candidate pivots (where to decode), and determines their token assignment that yields the greatest downstream benefit via lookahead evaluation (what to decode). Across 3 dLLMs and 4 reasoning and code-generation benchmarks, RPS achieves 4-10$\times$ wall-clock speedup over the standard decoder while preserving generation quality, and improves accuracy over the previous lookahead baseline by up to 5.49% while delivering higher throughput in most settings. When integrated with KV caching, RPS further achieves up to 18$\times$ wall-clock speedup over the standard decoder. ---