# Research Papers — 2026-08 · bundle page 25 of 240 > Full-text markdown of papers #1201–1250 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/25 [← Previous bundle](https://aipod.dev/papers/archive/2026-08/page/24.md) [Next bundle →](https://aipod.dev/papers/archive/2026-08/page/26.md) ### Pro-Router: Token-Aware Progressive Model Routing with Adaptive Edge-Cloud Collaboration for Efficient Multimodal LLM Inference Authors: Xinyuan Gui, Shaowen Wang, Sheng Sun, Zijian Wang, Zishu Yu, Zheming Yang Published: 2026-08-28 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.28726v1 The remarkable performance of multimodal large language models (MLLMs) comes at the cost of substantial computational overhead, posing significant challenges to real-time deployment and cost effectiveness. Existing model routing approaches either decide from coarse request-level features alone or spend one or several extra language model passes to inspect the generated response, leaving the token-level uncertainty signals that emerge during generation unused. To address these limitations, we propose Pro-Router, a token-aware progressive model routing method with adaptive edge-cloud collaboration for efficient multimodal LLM inference. Pro-Router employs a two-stage progressive decision mechanism. First, a lightweight prompt pre-scorer module performs rapid pre-screening before token generation begins, guiding apparently simple requests to small models. Second, a token-aware verifier reads the sampling probability distribution of each token the small model generates, estimating the model's confidence in its own output to determine, per request, whether the answer ships or escalates to the cloud-based high-precision model. Furthermore, we design an adaptive edge-cloud serving pipeline that sizes every dispatch to each device's measured service rate, so both the edge and the cloud tiers stay fully utilized without manual parameter tuning and are not impacted by the network latency. Extensive experiments on multiple multimodal benchmark datasets and models demonstrate the effectiveness of Pro-Router. Compared to other methods, it achieves the highest routing accuracy and improves routing speed by more than 10x. Its serving pipeline also reaches more than 75% higher end-to-end throughput than the existing model routing pipeline. Our code is available at https://github.com/xinyuangui2/pro-router. --- ### Beyond the Answer Key: Robustness Evaluation of Large Language Models for Step-Level Mathematical Verification Authors: Fateme Mazdarani, Carlos Toxtli Published: 2026-08-28 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.28725v1 Large language models (LLMs) are increasingly used as graders, verifiers, and process auditors, but most mathematical evaluations still emphasize final-answer accuracy. This can obscure whether a model can verify a non-canonical but valid solution trace. We introduce a controlled linear-equation benchmark for evaluating LLMs in the evaluator role. Each instance asks the model to judge final-answer correctness, step-level trace correctness, and the first incorrect step. Our evaluation of state-of-the-art open LLMs reveals a significant robustness gap: models that accurately evaluate canonical solutions often fail when presented with perturbed but logically equivalent variants. Across GPT-OSS 20B, Qwen3-14B, and Phi-4-Reasoning, base models perform well on canonical traces but degrade substantially on perturbed traces, especially for error localization. On valid perturbed traces, base-model false-rejection rates reach 75.6-85.3%, showing strong sensitivity to canonical solution form. Supervised fine-tuning, distillation, and test-time compute improve robustness in some settings, but gains are model dependent and can trade off against canonical performance. The results show that reliable process-level verification remains challenging, and evaluator robustness should be measured separately from solver accuracy, even in a simple algebraic domain with exact ground truth. --- ### MANTLE: A Framework for Adaptive In-Situ Planetary Perception Using a Modular Uplink Principle Authors: Pranav Durai, Gary Doran Published: 2026-08-28 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.28724v1 Planetary surface exploration missions rely increasingly on autonomous robotic platforms capable of interpreting complex terrain to ensure safe navigation, enable targeted science, and improve operational efficiency, as demonstrated across past Mars missions from Viking through Perseverance. Among the key perception capabilities, landform classification provides contextual information for landing site selection and scientific analysis, while boulder segmentation supports hazard assessment and path planning. This paper presents MANTLE, a multi-task adaptive network for terrain and landform extraction. The model uses a shared DINOv2 backbone for high-level feature extraction with task-specific heads: a classification head for large-scale landform classification, and a segmentation head for pixel-wise boulder localization, each trained on curated datasets built respectively from HiRISE orbital imagery and MSL surface-level imagery. The classification head achieved a test accuracy of 92.56% across seven Martian terrain classes, while the segmentation head achieved a validation IoU of 0.753 and showed strong cross-sol generalization on a held-out test set from previously unseen rover traverses. A key advantage of MANTLE is its modular, extensible design, formalized here as the Modular Uplink Principle: only a shared, frozen backbone needs to remain onboard, while subsequent perception capabilities are trained on Earth as lightweight task-specific heads and uplinked without retraining the full model. This work demonstrates two such high-impact capabilities, terrain classification and boulder segmentation, as an initial realization of a framework built to support many more over a mission's lifetime. With this foundation, future explorers need not arrive on Mars fully formed, but can continue to learn, adapt, and grow more capable with every uplink. --- ### RoboPhys-3D: A Comprehensive Embodied World Model Evaluation via 3D Reconstruction Authors: Tianyi Wang, Jiazhou Chen, Yiming Xu, Xiangyu Li, Tianyi Zeng, Chih-Hsien Chou, Ning Lu, Liang Peng, Junfeng Jiao, Christian Claudel Published: 2026-08-28 Categories: cs.RO, cs.AI, cs.CV, cs.ET, eess.SY arXiv: https://arxiv.org/abs/2608.28718v1 Video world models increasingly serve as data engines, action planners, and simulators for embodied AI, but conventional embodied world model (EWM) benchmarks lack a unified 3D-grounded protocol for establishing whether generated rollouts preserve the underlying 3D scene state or translate into executable actions. We introduce RoboPhys-3D, a 3D-grounded EWM benchmark built on RoboTwin 2.0, covering 50 manipulation tasks across four regimes, with 5,000 episodes and 25,000 multi-view ground-truth videos. A defining feature of RoboPhys-3D is that generated and ground-truth videos are processed through the same 3D reconstruction pipeline, enabling reconstruction-induced error to be distinguished from generation-induced error. The RoboPhys-3D benchmark organizes 50 complementary metrics into 18 sub-dimensions across four levels: pixel-level fidelity, 3D geometry consistency, state-level understanding, and task-level completeness. We further introduce Average Full Score, a hierarchical score averaging all 50 metrics for comprehensive evaluation, and RoboPhyscore, a compact task-aligned score averaging the metrics most strongly correlated with task success. Among the four representative video world models, Cosmos 3 achieves the highest RoboPhyscore (0.6330, 92.7% of ground truth), while state- and execution-grounded metrics reveal substantial failures that perceptual and vision-language model-based judgments fail to capture. RoboPhyscore further exhibits strong agreement with human evaluation (Pearson r = 0.9761 and Spearman \r{ho} = 0.8962), demonstrating the importance of grounded, execution-aware evaluation for EWM capability. --- ### Evaluating the Effects of Inter-Observer and Model Variability on Radiological Peritoneal Cancer Index Assessment Authors: Savvas Saragiotis, Pieter C. Gort, Lotte J. S. Fleurkens-Ewals, Anna F. van Herwijnen, Marion Tops-Welten, L. D. Kampmeijer, Joost Nederend, Fons van der Sommen Published: 2026-08-28 Categories: eess.IV, cs.CV arXiv: https://arxiv.org/abs/2608.28716v1 Deep learning segmentation models are often evaluated using geometric metrics such as Dice, HD95, and ASD, yet it remains unclear to what extent improvements in these metrics translate into clinically meaningful changes in downstream decision-making. The metric-to-decision gap is examined using radiological Peritoneal Cancer Index (rPCI) region segmentation on contrast-enhanced CT, where a consensus definition provides anatomically grounded 3D regions and the clinically used PCI 20 threshold enables decision-level evaluation. Inter-observer variability is quantified across four experts on ten abdominal CT scans, and a published nnU-Net based rPCI segmentation model is benchmarked against this human reference using Dice, HD95, and ASD across all 13 regions. To relate geometric differences to clinical impact, a probabilistic peritoneal metastasis simulation is implemented on majority-vote rPCI maps, propagating region-boundary variability into variability of derived (r)PCI scores and classification at the PCI 20 cutoff. Observers showed high agreement (mean Dice $0.87$), while the model matched human performance in most regions but deviated more in regions 4, 8, and the small-bowel regions (9-12). Across simulations, score differences were typically small (mean $Δ$rPCI $\approx 0.3$-$0.6$) for both observers and the model, and decision flips occurred predominantly when the reference score was near 20. These results suggest that rPCI-derived scoring is generally robust to typical segmentation variability, while highlighting borderline cases as the main setting where expert review remains essential. --- ### SCoPE-Reg: Efficient Rigid Ultrasound Slice-to-Volume Registration via State-Space Correlation and Closed-Form Pose Estimation Authors: Niklas Schwarz, Jens Kleesiek, Moritz Rempe Published: 2026-08-28 Categories: eess.IV, cs.CV arXiv: https://arxiv.org/abs/2608.28715v1 Ultrasound-guided interventions can require localization of an untracked 2D frame within a 3D anatomical reference. Rigid slice-to-volume registration (SVR) estimates this six-degree-of-freedom pose but remains challenging because of limited anatomical context, acoustic artifacts, and view-dependent appearance. Existing methods often use dense cross-attention, whose cost scales with the product of slice and volume token counts, or direct pose regression without explicit correspondence constraints. We introduce SCoPE-Reg, combining state-space slice--volume interaction, dense 3D coordinate prediction, and parameter-free weighted Kabsch estimation. On SVR tasks from CAMUS and $μ$-RegPro, SCoPE-Reg yields mean target registration errors of $0.73$ mm and $2.27$ mm against $1.24$ mm and $2.63$ mm for the state of the art (SOTA), reduces peak error on CAMUS by 56% below SOTA ($12.5\!\to\!5.5$ mm), and registers $100\%$ and $80\%$ of frames within $3$ mm. On CAMUS at $128^2$ it retains the lowest error at increasing pose-perturbation magnitude. It holds $6.49$ M parameters independent of resolution, sustaining $51$ FPS at $512^2$. SCoPE-Reg establishes a SOTA in rigid ultrasound SVR: by coupling correspondence-based accuracy with bounded worst-case error and resolution-independent cost, it becomes viable at native acquisition resolution during intervention, where prior methods trade accuracy, reliability, or frame rate against one another. Supplementary code provided and will be open-sourced upon acceptance. --- ### Evaluating the Safety of Deep Learning-Based Brain MRI Reconstruction Authors: Dat Tat Mai, Thai Viet Pham, Thu Nguyen Thi Dang, James Jin Kang Published: 2026-08-28 Categories: eess.IV, cs.CV arXiv: https://arxiv.org/abs/2608.28714v1 Objective: Deep learning accelerates brain MRI four- to tenfold, but models can erase lesions or synthesize false tissue - failures pixel-averaged metrics like PSNR and SSIM miss. We review whether current evaluation practices detect this blind spot. Methods: Following PRISMA 2020, we searched seven databases without date limits, including 263 studies (1995-2026), appraised them using QUADAS-2 and matched instruments, and synthesized narratively. Categories were derived from titles, abstracts, and controlled vocabulary; reported prevalence figures represent floors. Duplicate screening achieved high agreement (Fleiss kappa = 0.877), as did appraisal (0.788; 0.390 where observable). Extraction is unaudited. Results: Only 18 of 263 studies (6.8%) recorded both a fidelity metric and reader assessment on identical data, leaving the central surrogate unmeasured. Reader studies mostly measured inter-reader agreement, which was weak: fastMRI 2020 concordance reached 0.457 and 0.386 (Kendall W), improving only where SSIM diverged. Erasing a 100 mm3 lacunar infarct shifts global PSNR by 0.03 dB under the stated error model. As the corpus grew fivefold, reader assessments dropped from 32% to 18%, recovering to 21%. Generative models - most associated with hallucination (39%) - were among the least reader-evaluated (11.3%), while self-supervised models reached 47% with zero reader evaluation. Only 5% released code and ran reader studies; none evaluated a model observer; no named dataset covered acute stroke or hemorrhage. Conclusions: On these floors, current evaluation practices cannot certify diagnostic safety. We derive five requirements safety-oriented evaluations must meet. --- ### Coronary Mask Guided Registration for Continuous Time 4D Cardiac CT Dataset Construction Authors: Yuang Wang, Shuo Wang, Changyu Chen, Dufan Wu, Pengfei Jin, Yunqiang An, Yang Gao, Bin Lu, Dongrui Dai, Muge Du, Yan Yan, Dong Li et al. Published: 2026-08-28 Categories: eess.IV, cs.CV arXiv: https://arxiv.org/abs/2608.28712v1 Objective: Clinical cardiac CT multiphase reconstructions generally provide acceptable image quality in end-diastole (ED) or end-systole (ES) phases, but in other phases may exhibit motion artifacts, especially in the right coronary artery (RCA). This limits ground-truth availability in 4D cardiac CT imaging research. We aim to construct a 4D cardiac CT dataset that is generally suitable to serve as pseudo ground truth. Methods: We propose Coronary Mask Guided Registration (CMGR) to produce a motion-preserved, artifact-reduced, and continuous-time 4D cardiac CT sequence from the clinical multiphase reconstruction of each patient. For artifact reduction, CMGR uses the ED or ES phase as the reference phase and warps the reference volume with deformation fields to produce the sequence. For motion preservation, CMGR registers the reference phase to each non-reference phase of the multiphase reconstruction. To capture the motion of both the RCA and other cardiac structures in each registration, CMGR regularizes RCA masks and incorporates them into image-domain registration. Time-continuity is achieved by interpolating the deformation fields for non-reference phases to arbitrary times. Results: CMGR outperformed representative image-domain registration methods in capturing RCA motion and providing reasonable RCA shape, and showed competitive performance in capturing whole-heart motion. Additionally, CMGR reduced motion artifacts from clinical multiphase reconstructions, and intermediate CMGR frames generally provided plausible transitions between discrete cardiac phases. Conclusion: CMGR provides an effective approach for constructing continuous-time 4D cardiac CT datasets. Significance: The dataset can be used in system design simulations and in reconstruction algorithm development, thereby facilitating advances in cardiac CT imaging. --- ### QGPINNs: A Physics-Informed Neural Network Framework for Nonlocal Differential Equations on Quantum Graphs Authors: Vaibhav Mehandiratta, Saket Ramchandra Published: 2026-08-28 Categories: cs.LG, math.NA arXiv: https://arxiv.org/abs/2608.28589v1 We propose QGPINNs, a physics-informed neural network framework developed in PyTorch for the numerical solution of nonlocal differential equations on quantum graphs. The framework is designed as a general computational implementation in which the solution on each edge of the graph is approximated by a neural network, while a unified graph-based loss function enforces the governing equations together with initial, boundary, and vertex transmission conditions. In particular, the formulation incorporates standard continuity and Kirchhoff-Neumann vertex conditions and Dirichlet boundary conditions into the learning process to couple the local edge-wise neural approximations into a global solution on the graph. The framework is developed for two representative classes of nonlinear models: multi-order fractional elliptic problems and time-fractional evolution equations on quantum graphs. To improve accuracy and training stability, QGPINNs integrates several graph-adapted learning strategies, including soft and hard constraint enforcement, dynamic loss balancing, Fourier feature embeddings, and a learnable singularity-capturing feature for weakly singular solutions arising in the considered problems. The framework also extends naturally to inverse problems, including the identification of the orders of fractional operators and physical parameters from noisy observational data. We validate the accuracy, computational efficiency, and physical consistency of the proposed framework through numerical experiments on benchmark graph structures and real-world networks, including the IEEE 14-bus system and an open-channel agricultural drainage network. --- ### Aero Hand Open: A Simulation-Ready Tendon-Driven Hand for Dexterous Manipulation Learning Authors: Nan Wang, Mohit Yadav, Jonathan Wulff, Aidan Rosenbaum, Kezhou Chen, Yuvan Sharma, Xu Dong, Yiwei Tao Published: 2026-08-28 Categories: cs.RO, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2608.28578v2 Tendon-driven hands are anthropomorphic, and moving the actuators off the joints is what makes a hand of this capability affordable to build. Two effects produce that saving. Routing force through a cable removes the requirement that a motor fit inside the joint it drives, so smaller and cheaper motors suffice, and one motor can drive several joints through a single cable, so fewer motors are needed. They are also harder to learn on than a direct-drive hand. The underactuated transmission that produces the saving is itself difficult to represent in a simulator, and the joints one cable drives are not independently commandable. We present Aero Hand Open, a tendon-driven anthropomorphic hand that is released simulation-ready. Three things ship with it. A simulation model reproduces the cable transmission itself. An identified actuation map connects that model to the motor commands in both directions, including the three-way coupling of the thumb. A reinforcement learning package trains policies for the hand. Together they let a policy be trained entirely in simulation and run on the hand with no fine-tuning and no state estimation. We release the mechanical design, the simulation model, the identified mapping, the training environment and the deployment stack. --- ### Aero Hand Open: A Simulation-Ready Tendon-Driven Hand for Dexterous Manipulation Learning Authors: Nan Wang, Mohit Yadav, Jonathan Wulff, Aidan Rosenbaum, Kezhou Chen, Yuvan Sharma, Xu Dong, Yiwei Tao Published: 2026-08-28 Categories: cs.RO, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2608.28578v1 Tendon-driven hands are anthropomorphic, and moving the actuators off the joints is what makes a hand of this capability affordable to build. Two effects produce that saving. Routing force through a cable removes the requirement that a motor fit inside the joint it drives, so smaller and cheaper motors suffice, and one motor can drive several joints through a single cable, so fewer motors are needed. They are also harder to learn on than a direct-drive hand. The underactuated transmission that produces the saving is itself difficult to represent in a simulator, and the joints one cable drives are not independently commandable. We present Aero Hand Open, a tendon-driven anthropomorphic hand that is released simulation-ready. Three things ship with it. A simulation model reproduces the cable transmission itself. An identified actuation map connects that model to the motor commands in both directions, including the three-way coupling of the thumb. A reinforcement learning package trains policies for the hand. Together they let a policy be trained entirely in simulation and run on the hand with no fine-tuning and no state estimation. We release the mechanical design, the simulation model, the identified mapping, the training environment and the deployment stack. --- ### Learning a Size-Weight Frontier for Synthetic-Augmented Inference Authors: Chengpiao Huang, Kaizheng Wang Published: 2026-08-28 Categories: stat.ME, cs.AI, cs.LG, stat.ML arXiv: https://arxiv.org/abs/2608.28576v1 Synthetic data can improve statistical inference when real data are scarce, but naively treating synthetic samples as real data can introduce bias and lead to unreliable inference. We develop a general framework for synthetic-augmented inference across a population of related tasks. It characterizes synthetic augmentation by the number of synthetic observations and their weight. Central to our framework is a size-weight frontier that specifies, for each weight, the largest synthetic sample size for which all smaller sizes attain the target task-marginal coverage. We estimate this frontier from historical tasks, and establish a finite-sample coverage guarantee simultaneously for all size-weight configurations on or below the estimated frontier. In experiments using large language model responses to augment opinion survey data, our procedure achieves target coverage and substantially narrows confidence intervals. --- ### SignRR: Retrieve and Refine Real Motion for Sign Language Production Authors: Fidel Omar Tito Cruz, Angie Sanchez Marquina, Summy Farfan, Gissella Bejarano Published: 2026-08-28 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.28568v2 Sign language production (SLP) aims to generate continuous signing motion from spoken language, often through gloss-to-pose generation. Prior work mainly follows two paradigms. Generative models synthesize motion from a learned prior or from noise, without reference to an observed signing instance, making rare hand configurations and signer-specific articulation difficult to preserve. Retrieval-based methods reuse real, well-articulated motion segments, but concatenating segments from different signers and co-articulation contexts can introduce rhythm and style inconsistencies across the full sequence, not only at segment boundaries. These limitations suggest a complementary solution: use retrieval to provide realistic articulation, and use learned refinement to impose the global coherence that retrieval alone lacks. We therefore propose retrieve-and-refine, a paradigm that starts from real retrieved motion and refines it into a globally coherent signing sequence rather than generating motion from scratch. Our framework, SignRR, initializes motion from a dictionary of real sign segments and refines the full sequence with a part-aware Residual VQ-VAE, where residual quantization preserves fine hand articulation and temporal length differences are handled in the latent space. Experiments on PHOENIX14T and CSL-Daily show that SignRR achieves state-of-the-art back-translation performance while maintaining competitive pose quality. --- ### SignRR: Retrieve and Refine Real Motion for Sign Language Production Authors: Fidel Omar Tito Cruz, Angie Sanchez Marquina, Summy Farfan, Gissella Bejarano Published: 2026-08-28 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.28568v1 Sign language production (SLP) aims to generate continuous signing motion from spoken language, often through gloss-to-pose generation. Prior work mainly follows two paradigms. Generative models synthesize motion from a learned prior or from noise, without reference to an observed signing instance, making rare hand configurations and signer-specific articulation difficult to preserve. Retrieval-based methods reuse real, well-articulated motion segments, but concatenating segments from different signers and co-articulation contexts can introduce rhythm and style inconsistencies across the full sequence, not only at segment boundaries. These limitations suggest a complementary solution: use retrieval to provide realistic articulation, and use learned refinement to impose the global coherence that retrieval alone lacks. We therefore propose retrieve-and-refine, a paradigm that starts from real retrieved motion and refines it into a globally coherent signing sequence rather than generating motion from scratch. Our framework, SignRR, initializes motion from a dictionary of real sign segments and refines the full sequence with a part-aware Residual VQ-VAE, where residual quantization preserves fine hand articulation and temporal length differences are handled in the latent space. Experiments on PHOENIX14T and CSL-Daily show that SignRR achieves state-of-the-art back-translation performance while maintaining competitive pose quality. --- ### GeBDA: Building Damage Assessment as Text-Based Sequence Prediction Authors: Olivier Dietrich, Krishna Sapkota, Konrad Schindler, Genady Beryozkin Published: 2026-08-28 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.28567v1 Conventionally, Building Damage Assessment (BDA) is tackled either with dedicated network architectures or by fine-tuning geospatial image foundation models. In this work, we ask whether a general-purpose Vision-Language Model (VLM) can localize buildings and grade their damage through autoregressive sequence generation alone. We cast BDA as predicting a variable-length set of bounding boxes, each specified by its coordinates and a damage label. Our preliminary implementation, based on the open Gemma model, achieves promising damage mapping results from only bi-temporal satellite images and a suitable text prompt. --- ### On two proofs of $d^2$ mixing of weighted Dikin walks Authors: Yuansi Chen, Yunbum Kook Published: 2026-08-28 Categories: cs.DS, cs.LG, math.OC, math.PR, stat.CO arXiv: https://arxiv.org/abs/2608.28566v1 We study the mixing time of weighted Dikin walks for sampling from exponential distributions on polytopes and truncated positive-semidefinite (PSD) cones. Our first result gives a general total-variation mixing bound under strong self-concordance, $\barν$-symmetry, and mixed-trace regularity on the local metric. The key idea is to control the Metropolis--Hastings acceptance probability on a high-probability region rather than at every point. Applying this framework to the Lee--Sidford, Lewis-weight, and John metrics yields an $\widetilde O(d^2)$ mixing bound for sampling from polytopes, while applying it to a hybrid barrier yields an $\widetilde O(d^4)$ mixing bound for sampling from truncated PSD cones. Our second result establishes stronger $χ^2$-divergence guarantees and pointwise acceptance control using a new fourth-order bootstrap condition. For a suitably scaled Lee--Sidford metric, this yields an $\widetilde O(d^2)$ mixing bound in $χ^2$-divergence, improving on the previous $\widetilde O(d^{9/4})$ bound. --- ### Learning between the peaks: sharp asymptotics for kernel ridge regression under power-law anisotropy Authors: Lorenzo Rizzi, Arie Wortsman Zurich, Bruno Loureiro Published: 2026-08-28 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2608.28564v1 We study kernel ridge regression under anisotropic Gaussian data, where the input covariance decays as a power law with exponent $α\geq 0$ for polynomial inner-product kernels. We derive asymptotically sharp expressions for the kernel spectrum and the generalization error in the polynomial high-dimensional regime $n=Θ(d^κ)$, revealing how anisotropy reshapes the learning curves. For weak anisotropy ($0<α<1$), the problem remains effectively high-dimensional and retains some features of the isotropic case, while departing from it in others: the variance still peaks at integer sample complexities $κ\in\mathbb{N}$, but these peaks are progressively damped as $α$ grows; meanwhile, for targets strongly aligned with the data's principal directions, the bias drops at fractional sample complexities, decoupling the bias transitions from the interpolation peaks. For strong anisotropy ($α> 1$), the effective dimension of the problem is constant, and the variance stops depending on sample size altogether, plateauing under ridgeless interpolation or vanishing at an explicit rate under fixed ridge penalty. The bias undergoes a sharp transition governed by the target's decay rate: below a threshold, learning is abrupt rather than gradual; above it, the bias decays as a power law that recovers the classical source and capacity rates. We finally specialize these results to single-index targets, showing how the alignment of the index with the data's principal directions determines the effect of anisotropy on learning. Together, our results clarify how the input geometry shapes the kernel features and fundamentally impacts its generalization properties. --- ### A Formal Limitation on Learning Human Language From Textual Corpora Authors: Emily Cheng, Ryan Cotterell Published: 2026-08-28 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.28560v2 Can a listener recover what a speaker means from the form of an utterance alone? We answer this question information-theoretically, and for a listener given by any featurizer of text, including the hidden states of contemporary large language models. Modeling language use as a joint distribution over meanings, contexts, and utterances, we derive upper bounds on the probability that a decoder recovers a speaker's intended meaning from a representation of the utterance. The bounds are governed by the uncertainty that form leaves about meaning, which splits into an irreducible part and a part that only (extralinguistic) context, but never the utterance alone, can resolve. Because these quantities are intrinsic to language, no representation, however much text or supervision produced it, can surpass them. The bounds apply, moreover, to meaning spaces that are discrete or continuous. We provide empirical evidence in support of the theory through experiments on artificial languages, Mandarin zero-pronoun resolution, and color reference. --- ### A Formal Limitation on Learning Human Language From Textual Corpora Authors: Emily Cheng, Ryan Cotterell Published: 2026-08-28 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.28560v1 Can a listener recover what a speaker means from the form of an utterance alone? We answer this question information-theoretically, and for a listener given by any featurizer of text, including the hidden states of contemporary large language models. Modeling language use as a joint distribution over meanings, contexts, and utterances, we derive upper bounds on the probability that a decoder recovers a speaker's intended meaning from a representation of the utterance. The bounds are governed by the uncertainty that form leaves about meaning, which splits into an irreducible part and a part that only (extralinguistic) context, but never the utterance alone, can resolve. Because these quantities are intrinsic to language, no representation, however much text or supervision produced it, can surpass them; the bounds hold whether the space of meanings is discrete or continuous. Experiments on artificial languages, Mandarin zero-pronoun resolution, and color reference provide empirical evidence in support of the theory. --- ### Blog: Survey of Optimizers Authors: Ruoran Xu Published: 2026-08-28 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2608.28557v1 Neural-network optimization in 2025-2026 is no longer well described as a succession of new Adam variants. The design space has expanded from coordinates to matrices and layers, from fixed training horizons to policies over time, and from mathematical update rules to state representations that must survive sharding and low-precision computation. This survey organizes recent optimizers and training optimization methods along four largely independent axes: temporal estimation, update geometry, horizon management, and representation and systems. It connects the spectral normalization of Muon, the historical matrix statistics of Shampoo and SOAP, adaptive and hybrid matrix methods, memory-efficient optimizers, schedule-free training, small-batch corrections, and quantized optimizer states. The central empirical conclusion is deliberately non-triumphal: matrix-aware methods represent a genuine advance, but there is no context-independent replacement for AdamW. Rankings change with model scale, data-to-parameter ratio, batch size, schedule, parameter partition, tuning budget, and whether the target metric is tokens, FLOPs, wall-clock time, or memory. The practical consequence is a compositional view of optimizer design and a stricter protocol for evaluating optimizer claims. --- ### Logos: An Agent Harness on a Cross-Process Bus Authors: Hanzhang Jia, Liheng Zeng, Hao Cheng, Yi Gao, Bo Ma Published: 2026-08-28 Categories: cs.AI, cs.MA arXiv: https://arxiv.org/abs/2608.28553v3 Plugin-based agents assemble capabilities at runtime, and the spatiotemporal-composability calculus proves a reversibility guarantee for this assembly. However, the guarantee is carried by a single process, which confines all components, sessions, and recovery records to one failure domain, where a fault spreads past the plugin boundary, and process death interrupts every session the process hosts. Resting only on the hypotheses the calculus already states and the stateless interface of the model call, this paper relaxes the single-process restriction of the calculus to an arbitrary assignment of components and records to processes, gives four sufficient conditions, and proves with Theorem 1, derived from the four lemmas, that the reversibility guarantee holds across processes when these conditions are met. Based on Theorem 1, this paper constructs Logos, a cross-process plugin-based agent in the peer-process and name-routed form of ROS, where a plugin is a process, the router holds only a rebuildable routing table, and the session state needed for recovery lives in an append-only transcript owned by no process. Under one fault on two hundred benchmark tasks across three configurations, the single-process reference lost every session and scored 1.5 percent on the official validator, the MCP configuration kept its sessions while spending 1099 calls on a dead endpoint, and Logos kept every session alive, wasted zero calls, and succeeded on 120 tasks against 102 for both configurations combined. At the mechanism level, eighty sessions terminated at four points of the tool-call cycle all resumed with no repeated action, 3,500 concurrent calls paired with zero violations, and one bus hop cost 1 in 823 of the model's first token. The results show that the reversibility guarantee holds across processes and that assembly itself can leave the host process. --- ### Logos: An Agent Harness on a Cross-Process Bus Authors: Hanzhang Jia, Liheng Zeng, Hao Cheng, Yi Gao, Bo Ma Published: 2026-08-28 Categories: cs.AI, cs.MA arXiv: https://arxiv.org/abs/2608.28553v1 Modern agent systems assemble capabilities at runtime, and this dynamic composition has recently received a complete formal treat ment in the spatiotemporal-composability calculus, in which a capability is a component carrying a tracked inverse, and agents are assembled as plugins. This plugin form is carried by a single process sharing one context, a carrier that places all components in one physical failure domain, a fault suspends every component at once, and process death interrupts every session the process hosts. This paper shows that neither the modeling nor the calculus binds an agent to one process, the statelessness of the language model keeps all cross-step state outside the model, and the soundness invariant is defined on the state space alone. These observations condense into four lemmas whose premises are the hypotheses of the calculus and the statelessness of language-model inference. On these lemmas this paper constructs Logos, a ROS-like cross process agent harness in which a plugin is a process and the only shared state is an append-only transcript. Eighty sessions resume with no repeated effect after kills placed at the four boundaries of the tool-call cycle, and a same-fault comparison with a single process reference configuration shows one fault interrupting every co-resident session while under the peer-process construction one fault ends at one node. --- ### Advancing Interaction-Sensitive Feature Selection: Novel Relief-Based Algorithms, Expanded Comparisons, and Recommendations for Biomedical Data Mining Authors: Kia Kazemi-Nia, Harsh Bandhey, Philip J. Freda, Ryan J. Urbanowicz Published: 2026-08-28 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.28552v1 As a precursor to high-dimensional biomedical data modeling, reliable feature selection can reduce computational expense, improve modeling performance, and yield simpler, more interpretable models. However, most filter-based feature selection methods struggle to detect feature interactions, while wrapper or embedded feature selection methods are computationally expensive. Relief-based algorithms (RBAs) are filter methods that are sensitive to feature interactions while mitigating these other limitations. This study (1) refactors, optimizes, and expands the scikit-rebate Python package with existing and newly proposed RBA variants and (2) conducts rigorous RBA benchmark comparisons across diverse genomic simulations. We expand scikit-rebate to include SWRF*, mu-Relief, and 5 novel RBA variants implementing alternative strategies for neighbor selection and feature scoring. All RBAs were evaluated to compare predictive feature ranking and runtime across simulated genomic datasets varying in sample size, number of features, heritability, and underlying association type (e.g. main effects and interactions). All RBAs, except mu-Relief, were proficient in detecting 2-way interactions in noisy data. RBAs utilizing 'far' scoring were best at detecting 2-way interactions - with MultiSWRFDB* top-performing - but were far less sensitive to main effects. SWRF, MultiSWRF, MultiSURF, and MultiSWRFDB yielded top performance across main effect and 2-way interaction datasets with MultiSWRFDB performing best when also considering 3-way interactions. Refactoring of scikit-rebate resulted in 10 to 35-fold reductions in RBA runtimes. The newly introduced RBAs were among the strongest performing, and by robustly retaining both main effects and 2-way epistatic interactions, these algorithms preserve predictive signals for downstream modeling. --- ### Video Generative Models as Geometry Learner Authors: Haosen Yang, Jifei Song, Zhensong Zhang, Xiatian Zhu, Jiankang Deng Published: 2026-08-28 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2608.28549v1 Recent generative approaches to geometry estimation adapt pretrained image diffusion models and treat the task as image-conditioned generation. Leveraging off-the-shelf image diffusion models, they either (i) train task-specific geometry models (for depth and surface normal estimation) independently, losing the opportunity of exploring the intrinsic correlation of these geometric targets, or (ii) jointly fine-tune modified image diffusion backbones (e.g., altered self-attention), which typically demands substantial labeled data. To overcome these limitations in a principled fashion, we repurpose pretrained video generative models as a unified and data-efficient framework for geometry estimation, formulated innovatively as a next-frames prediction task. Our method, GeoNeXt, inherits naturally structured knowledge and richer priors from the video model, while further adapting them for joint modeling of images and geometry targets (image <-> geometry), enabling more data efficient and effective learning of geometry. Extensive experiments validate our method for zero-shot monocular depth and surface normal estimation across diverse datasets, outperforming both previous task-specific and unified generative competitors while using substantially less training data. Notably, our method rivals discriminative state-of-the-art approaches trained on over 100x more data and even standouts on several benchmarks. --- ### DARTS: Decoder-Aware Representation Tuning via Surgery for Model Merging Authors: Aaryan Ajay Sharma, Sai Nishanth Padala, Seganrasan Subramanian Published: 2026-08-28 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.28547v1 Model merging combines multiple task-specific fine-tuned LLMs into a single multi-task model without additional training. However, merged models are known to suffer from representation bias: systematic drift between the merged model's hidden states and those of each individual source model. Prior work (Yang et al., 2024a) study and mitigate this bias for encoder-based vision models using a lightweight correction module trained with L1 loss. However, such bias is not studied for decoder models due to their autoregressive nature. We analyze the problem of representation bias in decoder models, and show two challenges absent in encoders: (1) the causal attention mask causes bias to accumulate across token positions, requiring position-dependent correction; and (2) not all token positions are equally important, i.e., high-entropy (decision-critical) positions matter far more than low-entropy ones. To address these challenges, we propose Decoder-Aware Representation Tuning via Surgery (DARTS). DARTS employs a novel entropy-weighted L1 loss to upweight correction at high-entropy positions where errors most affect generation quality, and a per-position additive bias that captures position-dependent error without overparameterization. We perform extensive evaluation on three domains: code generation (HumanEval), mathematical reasoning (GSM8K), and instruction following (AlpacaEval) on Llama-2-7B models, and show DARTS achieves significant improvement over the standard surgery approach while adding negligible parameters ($0.1\%$ of total parameters). --- ### An Enclosed Mode Is a Gauge Choice: Topology Relative to Reach in Certified Code World Models Authors: Javier Aguilar Martín Published: 2026-08-28 Categories: cs.LG, cs.AI, eess.SY arXiv: https://arxiv.org/abs/2608.28541v1 A code world model accepted by a sampling gate can be exactly right on everything the gate can see and arbitrarily wrong beyond it. We characterize what a certified model can know, and what its errors can cost, when the omission is an annular freeze mode enclosing an unreachable interior. The gate quotient makes the question precise: acceptance-with-certainty determines the model exactly on the reachable query set; beyond reach is gauge. On a minimal ring instrument we prove the extreme case (a wrong-topology filled-disc artifact unfalsifiable by any sampling gate and bitwise harmless at play) and measure, with LLM synthesis across three model families, how one knob (a channel of width gamma) walks the same artifact through three regimes: unfalsifiable-and-harmless, falsifiable-and-costly, and instantly falsified. Three principles organize the empirics. First, danger is topology relative to reach: a channel the planner can use collapses the blind model's exploitation (play cost 1.09 to ~0 over a knee at gamma ~ 0.1), while a hidden channel with the same first Betti number keeps it at full strength (1.12). Second, repair is parameter-bound and sensor-bound: no family recovers the region from outside evidence; from inside, models pose the right topology but cannot pin its parameters, and the posed topology tracks the guiding persistent-homology summary's wrong beta_1 (a sensor with a measured geometric resolution limit), not the truth. Third, mitigation must match the error's dimension and direction: point fences fail against the one-dimensional boundary, a dimension-matched persisted fence collapses exploitation to a two-lesson transient (0.999 to 0.058), and the dual freedom certificate collapses the invented-mode failure symmetrically (1.769 to 0.029). In n dimensions the shell makes misidentification near-certain while the danger stays fully exploitable: the two axes are independent. --- ### InstructMesh: Selective Refinement of Generative 3D Models for Fabrication Authors: Faraz Faruqi, Ahmed Katary, Demircan Tas, Theresa Hradilak, Ning Zhang, Jiaji Li, Fabian Manhardt, Martin Nisser, Vrushank Phadnis, Ruofei Du, Federico Tombari, Megan Hofmann et al. Published: 2026-08-28 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.28534v1 Recent advances in generative AI allow users to create 3D models from text or images. However, these models prioritize visual plausibility over geometric accuracy, often generating results with flaws that compromise their intended use post-fabrication. We present InstructMesh, an interactive post-generation refinement tool that enables selective repair of generative 3D models through region selection and targeted operations, such as opening or sealing voids, or adjusting local thickness. Users can invoke edit operations via natural language prompts or slider controls. By operating directly on the intermediate latent representation, InstructMesh allows users to apply robust geometric corrections without requiring expert modeling skills. To inform our design, we first analyze common fabrication-related failure modes in outputs from state-of-the-art generative tools. We then conduct two user studies, demonstrating that novices can identify and perform fabrication-relevant repairs on generative outputs using InstructMesh, and revealing user preference for hybrid interfaces that combine slider controls with natural language input. --- ### Texture Image Classification Using DWT AlexNet Feature Fusion and Deep Neural Networks Authors: Arun D. Kulkarni Published: 2026-08-28 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2608.28524v1 Texture image classification plays a significant role in computer vision applications, including industrial inspection, medical image analysis, remote sensing, and object recognition. Handcrafted features can capture local texture characteristics but may have limited capability to represent complex visual patterns. In contrast, deep learning models automatically learn discriminative representations but may not fully exploit the multiscale spatial-frequency information inherent in texture images. This paper proposes a hybrid feature fusion framework, termed DWT_AlexNet_DNN, which combines Discrete Wavelet Transform (DWT) features with deep features extracted using AlexNet for texture image classification. --- ### When Robots Mishear Us: Mapping the Safety Risks of Voice-Controlled Embodied AI Authors: Sihan Jia, Oliver Lemon Published: 2026-08-28 Categories: cs.AI, cs.CL, cs.RO arXiv: https://arxiv.org/abs/2608.28518v1 We investigate whether automatic speech recognition (ASR) errors in user input can lead to unsafe outputs from Embodied AI (EAI) models. We find that ASR errors can lead to harmful instructions being accepted and executed by EAI models, thereby reducing safety. We simulate ASR errors and combine them with existing safety benchmarks (SafeAgentBench and POEX) to evaluate how different errors affect embodied AI safety. We find that some of them preserve semantic structure but increase harmful ambiguity, while others weaken the model refusal behaviour and allow unsafe plans to be generated and executed. We show that in some cases automatic correction of ASR errors can reduce the risk, but this is not always effective. Overall, we show that ASR errors lead to significant safety risks for embodied AI. --- ### Learning the Target Priors Before Image Translation: A Decoupled Training Paradigm for Cross-Modal Image Translation in Remote Sensing Authors: Keyan Hu, Mingtao Wang, Ziyu Zhou, Tiandong Shi, Haifeng Li, Ji Qi, Chao Tao Published: 2026-08-28 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.28517v1 Cross-modal image translation in remote sensing must preserve source-observed content while matching the target-domain distribution. Existing methods jointly learn the target prior and cross-modal dependence from scarce paired data, overlooking a key asymmetry: only the latter intrinsically requires cross-modal correspondence. We formalize this distinction through conditional-score and denoising-risk analyses and propose Learning the Target Priors Before Image Translation (LTP-BIT), a prior-first paradigm that decouples the two learning tasks. LTP-BIT first learns a target-domain generative prior from large-scale unpaired imagery, then retains the pretrained backbone weights and learns source-conditioned control through P-DART, a parameter-efficient dual-stream architecture. Controlled experiments show that prior matching and scaling primarily improve target-domain realism, whereas instance fidelity relies more strongly on conditional adaptation. LTP-BIT achieves state-of-the-art performance across SAR-to-RGB and NIR-to-RGB benchmarks using only 9.81% task-specific parameters. On QXS-SAROPT, it retains near-full-data instance fidelity with only 25% of the paired samples. --- ### Conformal Uncertainty Quantification Guarantees for Neural Operators Authors: Tom Stent, Nicolas Boullé Published: 2026-08-28 Categories: math.NA, cs.AI, math.PR arXiv: https://arxiv.org/abs/2608.28515v1 Neural operators provide fast surrogate models for approximating operators between function spaces, but their predictions often lack uncertainty quantification. We develop a split conformal framework to guarantee that a calibrated pointwise band around the neural operator output contains the true solution on at least a $1-γ$ fraction of the evaluation domain, with probability at least $1-α$ over test and calibration inputs, where $α,γ\in(0,1)$. Our method reduces a normalized residual field to its spatial $(1-γ)$-quantile and computes a scaling factor using a held-out calibration dataset. We prove marginal coverage guarantees for measurable residual fields defined on arbitrary probability spaces, covering both continuum domains and fixed discretizations. Under mild assumptions on the data distribution, we show that the coverage conditional on the calibration set follows a Beta distribution, which we verify with numerical experiments on Darcy flow and Navier--Stokes equations, where our calibration yields bands consistently tighter than existing corrections while retaining the target coverage. --- ### Training Communication-Efficient Mixture-of-Experts Language Models with Layer Re-Configuration Authors: Simeng Sun, Roger Waleffe Published: 2026-08-28 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.28511v1 When training Mixture-of-Experts (MoE) language models with expert parallelism, all-to-all token dispatch and combine collectives can consume a substantial fraction of end-to-end training time. In this work, we study communication-efficient MoE models (CE-MoE), in which we adopt a heterogeneous layer pattern that decouples token-mixing and channel-mixing depth. Compared to conventional models which interleave MoE layers after each token-mixing layer (e.g., attention, Mamba-2), CE-MoE models concentrate expert capacity in a select few routed MoE layers, while maintaining depth by adding additional token-mixing and dense-FFN layers. Across a scaling ladder from 2B to 31.5B total parameters, under matched total and activated parameters, CE-MoE models consistently reduce training cost while matching validation loss and downstream benchmarks with full-MoE baselines. At the 31.5B scale, CE-MoE uses 33.3\% fewer GPU-hours while improving average downstream score and inference throughput. --- ### Phoneme- and Word-Level Metrics Using Self-Supervised Speech Representations for Forced Alignment Evaluation Authors: V. S. D. S. Mahesh Akavarapu, Michael Daniel, Gerhard Jäger Published: 2026-08-28 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.28508v1 Forced alignment evaluation typically requires manually annotated timestamps, limiting large-scale and multilingual analysis. We introduce two corpus-level metrics based on self-supervised (SSL) speech representations for reference-free forced alignment evaluation: Phoneme-Cluster Mutual Information (PCMI) and Word Acoustic Consistency Score (WACS). PCMI measures agreement between aligned phoneme labels and clusters induced from SSL-speech representations, while WACS measures consistency of repeated word realizations using dynamic time warping similarity between word representation sequences. Using both random and systematic perturbations, we show that PCMI and WACS degrade consistently under alignment perturbations. We further analyze the metrics across multiple alignment systems on 85 languages from FLEURS, validate them against manually annotated alignments from 45 languages in DoReCo, and evaluate them on two phonologically complex low-resource languages. The metrics effectively separate high- and low-quality alignments and correlate strongly with timestamp-based alignment quality measures. Our results demonstrate that SSL-speech representations enable scalable, reference-free forced alignment evaluation. The metrics are available as an open-source Python package at https://github.com/mahesh-ak/forced-aligner-metrics. --- ### REPLICANT: Learning Policies for Evading and Hardening Malware Detectors Authors: Shae McFadden, Ilias Tsingenopoulos, Mario D'Onghia, Alexander Herzog, Myles Foley, Chris Hicks, Lorenzo Cavallaro, Fabio Pierazzi Published: 2026-08-28 Categories: cs.LG, cs.CR arXiv: https://arxiv.org/abs/2608.28499v1 To determine the real-world effectiveness of machine learning based malware detection, it is vital to evaluate its robustness against highly capable adversaries. However, state-of-the-art attacks do not effectively model realistic adversaries, as they often assume access to privileged information such as the training data, feature space, or confidence scores of the target. In this work, we present Replicant, a deep reinforcement learning framework that learns the realistic task of evasion under a strict label-only black-box threat model. Replicant learns a reusable policy on how to modify a malware sample and when to query the target, which transfers across samples, detectors, and feature spaces. Across seven Android malware detectors and three feature spaces, Replicant is the strongest and most query-efficient approach achieving a mean attack success rate of 78.8%, a relative improvement of 20.9%-39.2% over the state-of-the-art. Furthermore, when used for adversarial training, Replicant also outperforms the state-of-the art by producing detectors with more generalizable robustness. With Replicant we demonstrate that learning the task of evasion not only results in stronger attack performance but, crucially, provides a better signal for hardening malware detectors. --- ### On the Maintenance and Co-evolution of Agent Plugins: An Empirical Study of Claude Code Plugin Marketplaces Authors: Ahmed Hereiz, Yingzhe Lyu, Hao Li, Bram Adams, Ahmed E. Hassan Published: 2026-08-28 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2608.28497v1 AI coding agents, software tools that automate development tasks through reasoning and tool use, are increasingly extended through plugin marketplaces, yet the structure, maintenance, and co-evolution dynamics of these emerging repositories remain empirically unexplored. Unlike traditional software packages that deliver functionality through source code, agent plugins deliver functionality through a combination of natural-language instruction files, scripts, and configuration files, raising the question of whether these plugins are maintained artifacts that co-evolve across components, or one-off artifacts that developers write once and do not need to revisit. To study the maintenance and co-evolution of agent plugins, we conduct an empirical study of 1,926 repositories hosting Claude Code plugin marketplaces, analyzing 8,351 plugins and 77,773 commits across 2,018 marketplaces. We find that the marketplace is expanding rapidly, plugin-touching commit activity growing 8.8x over six months after the October 2025 launch, and plugins targeting Software Engineering tasks accounting for 61.3% of all plugins. Plugin development is predominantly feature-driven, with feature commits occurring at more than twice the rate of conventional open-source software (OSS) (39.6% vs. 17.2%). Claude co-authors 34.9% of all commits, and four commit types (docs, perf, style, and refactor) carry substantially different meanings in plugin repositories than in traditional software. Most component types evolve independently, but within skills directories, natural-language instruction files and implementation scripts co-evolve at above-chance rates, with 78% of co-changes being functionally coupled, representing a new class of maintenance dependency not observed in traditional software engineering. --- ### Ladders in Chaos: When, How, (and Perhaps Why) Does Test-Time Scaling Improve LLM Machine Translation Authors: Di Wu, Sergey Troshin, Christof Monz, Antske Fokkens, Vlad Niculae Published: 2026-08-28 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.28496v2 Two forms of test-time scaling for Large Language Models (LLMs) have emerged as effective and widely adopted paradigms: sequential, in which later answer attempts depend on earlier ones, and parallel, such as i.i.d. sampling with reranking. In this study, we investigate their properties in translation. First, our study shows that sequential sampling has a higher performance ceiling, providing a more diverse and effective pool of samples, particularly under smaller sampling budgets. Second, we interrogate the nature of test-time scaling through a multidimensional manual analysis. Human analysis of the Best-of-N translations demonstrates that sequential sampling substantially improves translation fluency and naturalness, but can degrade accuracy when inference budgets are large. Finally, we suggest an explanation of the mechanism through which sequential scaling improves machine translation. Our controlled analysis partially attributes the success of sequential self-improvement to the model's access to a larger target-side context. Ablation experiments on sequential sampling demonstrate its robustness across different sampling temperatures, while also revealing sensitivity to context construction, suggesting directions for future improvement. --- ### Ladders in Chaos: When, How, (and Perhaps Why) Does Test-Time Scaling Improve LLM Machine Translation Authors: Di Wu, Sergey Troshin, Christof Monz, Antske Fokkens, Vlad Niculae Published: 2026-08-28 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.28496v1 Two forms of test-time scaling for Large Language Models (LLMs) have emerged as effective and widely adopted paradigms: sequential, in which later answer attempts depend on earlier ones, and parallel, such as i.i.d. sampling with reranking. In this study, we investigate their properties in translation. First, our study shows that sequential sampling has a higher performance ceiling, providing a more diverse and effective pool of samples, particularly under smaller sampling budgets. Second, we interrogate the nature of test-time scaling through a multidimensional manual analysis. Human analysis of the Best-of-$N$ translations demonstrates that sequential sampling substantially improves translation fluency and naturalness, but can degrade accuracy when inference budgets are large. Finally, we suggest an explanation of the mechanism through which sequential scaling improves machine translation. Our controlled analysis partially attributes the success of sequential self-improvement to the model's access to a larger target-side context. Ablation experiments on sequential sampling demonstrate its robustness across different sampling temperatures, while also revealing sensitivity to context construction, suggesting directions for future improvement. --- ### Low-Power End-to-End Cochlear Implant Speech Denoising with Spiking Neural Networks Authors: Ludovic Boulanger, Sean U. N. Wood Published: 2026-08-28 Categories: cs.SD, cs.NE, eess.AS arXiv: https://arxiv.org/abs/2608.28493v1 Cochlear implants (CI) restore hearing for individuals with severe to profound hearing loss. However, CI users often struggle to understand speech in noisy environments. Deep neural networks (DNN) have shown promise in enhancing speech for CI users, yet their high energy demands make them non-ideal for low-power CI processors. Spiking neural networks (SNN), on the other hand, offer comparable performance with significantly lower energy consumption. Hence, we propose a novel SNN inspired by the Deep ACE architecture that simultaneously performs speech enhancement and CI coding. Our model achieves competitive vocoded short-time objective intelligibility (VSTOI) and signal-to-noise ratio improvement (SNRi) scores compared to Deep ACE, while achieving more than a sixfold reduction in energy consumption. --- ### AcrossVAM1.0: Particle World Modeling for Text-Assisted Robot Video Prediction Authors: Yafei Zhang, Nan Wu Published: 2026-08-28 Categories: cs.AI, cs.RO arXiv: https://arxiv.org/abs/2608.28491v1 Predicting robot videos requires both precise motion reasoning and preservation of high-frequency appearance, yet monolithic pixel models entangle these objectives and often conceal their progress behind a strong last-frame baseline. We present AcrossVAM1.0, a lightweight, text-assisted video action model that factorizes future prediction into object-centric motion and dense appearance. A frozen SAM3-DLP codec decomposes four context frames into semantic particles for the robot, arm, and gripper, together with a background latent. A 0.28M-parameter spatio-temporal Transformer aligns particle identities, rolls their states forward, and is modulated by a frozen OpenCLIP instruction embedding through FiLM. A causal dual-stream decoder combines particle-rendered motion with appearance encoded exclusively from the last observed frame; a residual refiner and learned delivery mask produce five future frames without access to future appearance. On our VRS benchmark constructed from diverse real-robot trajectories, particle dynamics reduce trajectory error by 21.0\% over persistence. Across three delivery-mask seeds, AcrossVAM1.0 improves future-frame PSNR/SSIM from 19.97/0.796 to 20.573/0.8004, while raw particle generation improves motion-region PSNR from 11.89 to 13.23. The delivered model does not yet beat persistence in LPIPS, and correct-versus- shuffled language changes trajectory error by only 2.8--3.1%. We report these limitations alongside oracle, negative-control, multi-seed, and per-robot analyses. The results show that explicit particle dynamics are a promising low-dimensional interface for robot video prediction, while robust language grounding and appearance delivery remain the principal open challenges. --- ### LLM-Based Agents for Software and Systems Security: Approaches, Applications, and Assessment Authors: Jingjing Nie, Jiawei Guo, Krishna Meda, Haipeng Cai Published: 2026-08-28 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2608.28490v1 Software and systems security workflows are typically procedural: analysts inspect heterogeneous artifacts, form hypotheses, invoke tools, interpret outputs, and revise plans. Large language model (LLM)-based agents, which can plan, use tools, retain state, and revise actions across multi-step workflows, are being rapidly adopted to automate this work. Given the consequences of delegating security decisions to autonomous systems, understanding how such agents are built, used, and assessed is crucial. Yet to this date, there remains a lack of systematic understanding of what has been done and how far we are in this field: the term "agent" is applied inconsistently, applications differ sharply in risk, and assessment protocols are often incomparable. To gain a comprehensive and coherent view of this area hence inform relevant future research, this paper provides a systematic literature review of the (1) technical approaches, including agent architecture, perception, memory, reasoning and planning, action space, orchestration, and self-improvement, (2) applications, with respect to the security tasks served, and (3) assessment, including the datasets, outcome and trajectory metrics, safety measures, and baselines considered, over the peer-reviewed literature spanning the emergence of this area (2023--2026). Our synthesis reveals a field that has built agents able to act but not yet agents whose authority is bounded or whose behavior is auditable. In addition to knowledge systematization, we also extend our insights into the limitations of and challenges faced by current approach, application, and assessment designs, which shed light on potentially promising future research directions. --- ### How Proper Scoring Rules Shape LLM Forecasting Authors: Benjamin Turtel, Paul Wilczewski, Kris Skotheim, Ville A. Satopää, Philip E. Tetlock Published: 2026-08-28 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2608.28482v2 This paper evaluates how reward function choice shapes the performance and behavior of LLM forecasters. We compare five proper scoring rules as training objectives for binary forecasts of resolved real-world events. Although the rules share the same theoretical incentive for truthful probability reporting, the resulting models differ in calibration, probability use, and estimated profiles of bias, information, and noise, with smaller differences in aggregate accuracy and discrimination. The Brier-trained model has the lowest observed Brier score and highest AUC-ROC, while the log-trained model has the highest observed log score and lowest calibration error. Models with similar aggregate performance also reach that performance through different combinations of bias, information, and noise. Proper scoring rules therefore need not behave interchangeably as training objectives. Reward choice may shape not only how well an LLM forecasts, but how its forecasting errors are structured. --- ### How Proper Scoring Rules Shape LLM Forecasting Authors: Benjamin Turtel, Paul Wilczewski, Kris Skotheim, Ville A. Satopää, Philip E. Tetlock Published: 2026-08-28 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2608.28482v1 This paper evaluates how reward function choice shapes the performance and behavior of LLM forecasters. We compare five proper scoring rules as training objectives for binary forecasts of resolved real-world events. Although the rules share the same theoretical incentive for truthful probability reporting, the resulting models differ in calibration, probability use, and estimated profiles of bias, information, and noise, with smaller differences in aggregate accuracy and discrimination. The Brier-trained model has the lowest observed Brier score and highest AUC-ROC, while the log-trained model has the highest observed log score and lowest calibration error. Models with similar aggregate performance also reach that performance through different combinations of bias, information, and noise. Proper scoring rules therefore need not behave interchangeably as training objectives. Reward choice may shape not only how well an LLM forecasts, but how its forecasting errors are structured. Each condition uses a single seed, so some differences may reflect training stochasticity. --- ### NL2AGBench: Benchmarking LLM Auto-Formalization for AlphaGeometry Authors: Samuel Xiao, Judy Song, Rory Hu, Ziliang Zong Published: 2026-08-28 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2608.28481v1 Recent advances in large language models (LLMs) have demonstrated strong capabilities in natural language understanding and mathematical reasoning. However, their ability to translate informal mathematical problems into formal representations remains underexplored. This limitation is particularly important for neuro-symbolic geometry systems such as AlphaGeometry, whose theorem-proving engine requires inputs in a specialized domain-specific language (DSL). Although AlphaGeometry achieves near-IMO gold-medalist performance, manually converting natural-language problems into its formal syntax remains a significant usability bottleneck. To address this challenge, we introduce the Natural Language to AlphaGeometry Benchmark (NL2AGBench), which evaluates LLMs in translating English geometry problems into AlphaGeometry-compatible formal representations. NL2AGBench uses execution-based verification within AlphaGeometry to assess translation quality rather than relying solely on textual similarity. We evaluate ten state-of-the-art open- and closed-source LLMs across multiple parameter scales and analyze executable translation accuracy, syntactic correctness, and error characteristics. Our experiments reveal a substantial performance gap between closed- and open-source models: leading closed-source models achieve executable translation rates above 80%, while even the largest open-source models struggle to consistently preserve geometric constraints and produce valid formalizations. We introduce an error taxonomy distinguishing syntax and logic errors and investigate mitigation strategies, including few-shot prompting, fine-tuning, and human-guided hinting, which yield measurable improvements across multiple model families. --- ### Blind Men and the Elephant: Probing the Epistemic Myopia of LLMs under Long-Tail Divergent Knowledge Authors: Zhuoshi Pan, Junru Lu, Yan Qian, H. Vicky Zhao, Di Yin, Xing Sun Published: 2026-08-28 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.28478v1 Factual question answering (QA) typically assumes a single canonical answer, obscuring whether large language models (LLMs) retain divergent accounts of long-tail facts. To address this gap, we introduce ElephantBench, a closed-book knowledge probe comprising 1,094 questions generated through an auditable graph-based pipeline. The pipeline retrieves related documents from a low-exposure web corpus, identifies naturally occurring disagreements, and converts them into multi-account QA records. Each answer is verified against the originating documents and authoritative public web sources and is then reviewed by human annotators. Across 32 models, even the strongest model recovers both accounts on only 52.4% of questions, while on nearly all remaining questions it recalls one account but omits the other. Scaling model size and inference-time reasoning improve recall but do not eliminate this incompleteness. Corpus analysis further shows that exposure imbalance favors the dominant account, whereas greater minority-side exposure is associated with more complete recall. These findings establish ElephantBench as a reproducible knowledge probe for diagnosing epistemic myopia in parametric memory. More broadly, our graph-based benchmark construction pipeline provides an efficient and scalable way to turn long-tail corpora into source-traceable knowledge probes, supporting efforts to evaluate and advance the epistemic rigour of next-generation LLMs. Code is available at https://github.com/Tencent/ElephantBench. --- ### ContextPilot: Teaching Agents for Proactive Context Management via Fine-grained RL Authors: Zhuoshi Pan, Qizhi Pei, Junru Lu, Honglin Lin, H. Vicky Zhao, Di Yin, Xing Sun Published: 2026-08-28 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.28476v1 Long-horizon agentic tasks require large language models (LLMs) to iteratively retrieve, integrate, and maintain dispersed information across multi-turn interactions, but preserving all interaction histories leads to a continuously growing working context. Recent proactive context management methods allow models to edit their own working context with specialized tools, yet they still face three key limitations: (1) a limited toolset restricted to search, deletion, and summarization, with no support for global planning, long-term memory, and adaptive compression; (2) inefficient exploration that treats context management actions uniformly despite their heterogeneous impacts on final outcomes; and (3) coarse-grained credit assignment that assigns the final trajectory-level reward to all intermediate context editing actions during RL. To bridge these gaps, we introduce ContextPilot, a proactive context management framework for long-horizon agentic reasoning. Our approach systematically augments the toolset with planning, long-term memory, and soft context offloading tools. We further propose an RL method tailored for context management, which uses context and entropy variation to identify critical editing decisions for branch sampling and estimates action-level advantages from all branched trajectories that pass through the corresponding context editing action. Experiments on long-context QA and deep search tasks show that ContextPilot achieves stronger performance with a more compact working context, consistently outperforming existing baselines across various base models and benchmarks. Code is available at https://github.com/Tencent/ContextPilot. --- ### COVER: Identifiable Evaluation of Coalition Routing Authors: Raghul Sugumar, Amrit Gopinath Published: 2026-08-28 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.28475v1 When a multi-agent system changes its team, it also changes the messages and final answer it produces, so an end-to-end accuracy gap does not by itself identify a routing effect. We introduce method, an evaluation contract that fixes a public information boundary, downstream stack G, and finite legal team family before outcomes are generated. Complete coverage identifies exact finite-benchmark oracle regret conditional on that stack. For any finite collection of frozen policies, executing the union of their distinct selected teams is the minimal assumption-free support for every pairwise policy contrast, though not for absolute oracle regret. Two controlled tables with source-ID-disjoint splits test the instrument. On MuSiQue-12, a pre-specified privileged positive control improves regret from 0.532 to 0.402; a later public-interface control reaches 0.424 versus 0.554 but is retrospective. On HotpotQA-4, a pre-specified public direct scorer improves regret from 0.313 to 0.110. In fixed-stack Llama execution, verified route regret improves by 0.190, while the raw-answer gain is 0.010 with an interval crossing zero. A five-family ToolSandbox variant-shift validation exhaustively evaluates 16 declared teams on 14 untouched task variants (224/224 valid rows): the declared-family oracle reaches 0.768 safe-evidence completion, while the prospectively frozen router gets 0.637 (regret 0.131), failing the predeclared 0.10 criterion. A later retrospective comparator reaches 0.655, matching all-workers with 4.57 versus 5.00 workers on average. Thus COVER exposes selection headroom without manufacturing a routing win. A crossed-stack diagnostic shows absolute scores depend on G but finds no detectable router-by-finalizer interaction. COVER is an auditable measurement methodology, not a claim of stack-invariant or universal agent-routing superiority. --- ### Real-time virtual circuits for plasma shape control via neural network emulators: experimental demonstration on MAST Upgrade Authors: Nicola C. Amorisco, Kamran Pentland, Adriano Agnello, George K. Holt, Alasdair Ross, Matthew J. Marshall, Edward Jones, Graham J. McArdle, Charles Vincent, Timothy Nunn, Martin Kochan, Pedro Cavestany et al. Published: 2026-08-28 Categories: physics.plasm-ph, cs.AI arXiv: https://arxiv.org/abs/2608.28468v1 Conventional plasma shape control in tokamaks relies on virtual circuits (VCs) that are computed offline from linearisations around a small, tailored number of reference equilibria, and deployed as expertly prepared schedules during the discharge. Here, we report on the first experimental deployment of real-time VCs. We replace pre-set look up tables with VCs updated in real time using surrogates of the plasma response. Both the existing control architecture and the interpretability of VC-based control are retained. Previous work showed that neural network emulators can produce accurate VCs, and validated their performance in closed-loop shape control simulations. Here, we report their first experimental validation on MAST Upgrade (MAST-U). Dedicated experiments spanning different scenarios, including prescribed shape perturbations, feedback-driven divertor-leg motion, and strongly evolving plasma configurations, show that real-time VCs can realise plasma shape control tasks within the MAST-U plasma control system. These results establish the experimental feasibility of real-time linearisations as a practical extension of conventional plasma shape control in tokamaks. The present implementation demonstrates a central step towards a simpler control workflow, in which manually constructed, phased VC schedules are replaced by VCs generated automatically online from a trained surrogate model, without scenario-specific retraining. --- ### Stranger, Fan, or Peer? A Systematic Study on the Role of Interlocutor in Persona-Based Dialogue Generation Authors: Daniela Occhipinti, Malvina Nissim, Marco Guerini Published: 2026-08-28 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.28467v1 Persona-based dialogue systems are usually conditioned on speaker biography, but dialogues involve at least two participants, and who has access to whose biography can vary across training, inference, and evaluation. Prior work often neglected these aspects, obscuring mechanisms that only appear when biography visibility is toggled separately across training, inference, and evaluation, a three-stage factorisation that prior work has largely treated as a single factor. We study this factorisation on a dataset of dialogues paired with speaker's biographies, varying whether the target and interlocutor speakers see each other's biographies during training and inference, and using an LLM as a judge to perform author identification. We find that (i) training-time visibility, more than inference-time visibility, determines whether models express persona traits through dialogue or fall back on copying biographical text (a known problem/phenomenon in persona-based generation); (ii) models trained with interlocutor-biography visibility copy less target-biographical text than models trained without it, while changing visibility only at inference time has a less consistent effect; and (iii) under asymmetric disclosure, where only the interlocutor sees the target biography, target content leaks into interlocutor turns more often, and dialogues containing such traces are easier for the judge to identify, especially when interlocutor turns are visible. These results suggest that biography leakage into generated turns is an artefact of how interlocutor visibility is configured across training and inference, and separating the three stages is necessary. --- ### Anatomy-Aware Promptable Segmentation with Online Interactive Training for AUTOPET V Authors: Pablo Lozano-Jimenez, Sergio Romero-Tapiador, Ruben Tolosana Published: 2026-08-28 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2608.28461v1 We present an anatomy-aware, promptable model for whole-body lesion segmentation in FDG and PSMA PET/CT, developed for the AUTOPET V challenge. The proposed method is built as family of nnU-Net-based models and trained in two stages: i) a pre-training stage that produces a strong initial segmentation, and ii) an online interactive stage that learns to exploit scribble prompts, refining the prediction over successive interactions. Anatomical context is incorporated through organ supervision using a single shared head that predicts lesions and organs from the same features, which reduces false positives arising from physiological uptake. Also as the tracer (i.e., FDG/PSMA) is not provided at inference, we add a tracer classifier based on image processing and a random forest over coronal MIP features, routing each study to a combined FDG+PSMA model or to a PSMA-specific model. Across four-fold cross-validation the organ-supervised model achieves the best and most stable performance, the interactive stage improves the Dice score monotonically with each prompt, and PSMA-specific training yields the strongest tracer-wise results. --- ### LayerRecall: A State-Conditioned Memory Router for Long-Horizon Consistency in Video Generation Authors: Yixuan Ding, Jiahao Kong, Wei Huang, Ruijie Quan, Yi Yang Published: 2026-08-28 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.28460v1 Autoregressive video diffusion enables scalable long-video generation by producing chunks from a bounded recent context. While recency-based caching preserves local continuity, it evicts historical cues needed when subjects, objects, scenes, or attributes reappear. Existing memory mechanisms expose models to nonlocal history, but access alone does not ensure effective use. Our analysis reveals that video DiT layers exhibit distinct preferences for current, recent, and distant context, suggesting that long-range memory requires deciding both what to retrieve and where to use it. We introduce LayerRecall, a current-conditioned, layer-selective memory router that retrieves relevant historical K/V states and injects them only into backbone-specific memory-sensitive layers while preserving local attention elsewhere. To reduce reliance on scarce high-quality long-horizon videos and explicit memory-allocation labels, we further propose Cross-Horizon Prediction Matching (CHPM), which uses a privileged long-context reference to supervise the bounded-memory router in prediction space. Across 100 multi-shot evaluation prompts, LayerRecall achieves the best overall results on MemoBench and MovieBench while matching its backbone on VBench-Long, demonstrating stronger long-range recovery without sacrificing local continuity. Qualitative analyses further reveal memory-guided self-correction, whereby initially mismatched local attributes return to their historical appearance without resetting ongoing motion or scene structure. Additional analyses show cross-backbone portability and negligible inference overhead. ---