# Research Papers — 2026-09 · bundle page 202 of 266

> Full-text markdown of papers #10051–10100 of 13298 published in 2026-09, newest first. AI-readable mirrors of the full 13298-paper 2026-09 archive (50 papers per file).

Canonical page: https://aipod.dev/papers/archive/2026-09/page/202
[← Previous bundle](https://aipod.dev/papers/archive/2026-09/page/201.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-09/page/203.md)

### Time-Frequency Geometric Cross-Attention for Chunked Vision-Language-Action Models

Authors: Shengye Dong, Haochen Niu, Hao Liu, Peiwen Lin, Chuang Wang, Shanmin Pang
Published: 2026-09-09
Categories: cs.AI, cs.RO
arXiv: https://arxiv.org/abs/2609.09925v1

Modern vision-language-action (VLA) policies predict a whole chunk of actions: one to two seconds of coordinated motion emitted in a single forward pass. Yet an action chunk is essentially a short multivariate trajectory, but inside these models it is a sequence of generic per-timestep hidden tokens decoded by a linear head. This under-serves two motion structures. First, frequency: a chunk superimposes a smooth global trend and fine corrective motion across time scales, and a single token entangles them. Second, cross-phase geometry: motions of different phases (reach, contact, grasp adjustment, settling) unfold along very different, near-orthogonal directions in representation space, yet are tightly related for the task and arise across the time axis. Dot-product attention scores alignment by an inner product, so it favors aligned tokens and is least sensitive near orthogonality, leaving such relationships for the network to recover through a detour. We introduce Time-Frequency Geometric Cross-Attention (TFGCA), a drop-in module repairing both blind spots. TFGCA uses a per-dimension learnable stationary wavelet transform to decompose the action chunk into time-frequency tokens, and each time token retrieves information from them via a cross-attention that fuses the dot product (similarity) with the wedge-product magnitude (sensitive to near-orthogonality) through a learnable weight. A zero-initialized residual reproduces the base behavior at initialization, so it can be dropped onto a pretrained VLA and fine-tuned jointly. Relative to the same-source base, TFGCA improves in-distribution LIBERO by +1.5 on average, the OOD LIBERO-Plus by +6.3, the randomized average under RoboTwin domain randomization by +28.5, and the overall success rate on three real-robot AgiBot A2 tasks by +11.67 points, with larger gains out of distribution.

---

### Multimodal Emotion Recognition in Conversations via Class-Wise Adaptive Modality Fusion and Affective Geometry

Authors: Oriol Marín, Roger Marí, Gloria Haro, Rafael Redondo
Published: 2026-09-09
Categories: cs.CV
arXiv: https://arxiv.org/abs/2609.09924v1

Emotion Recognition in Conversations (ERC) requires integrating heterogeneous textual, audio, and visual cues while accounting for conversational context and emotional dynamics. We extend the Self-Distillation Transformer architecture for ERC with appearance+geometry visual representations, class-wise adaptive modality fusion, and a valence-arousal prior for affective transitions. On the MELD and IEMOCAP datasets, geometry-enhanced visual representations improve weighted F1 by 0.27 and 4.36 points over appearance-only features, respectively, while class-wise adaptive fusion provides further gains of 0.17 and 0.25 points over the original softmax gate. The valence-arousal prior yields targeted improvements of 0.30 and 0.74 accuracy points on emotionally shifted utterances while preserving performance on stable turns. These results indicate that structured facial cues, emotion-dependent modality weighting, and affective geometry provide complementary benefits for multimodal ERC.

---

### Multi-Pass, Multi-View Blended Learning for High-Fidelity Volumetric CT Synthesis from Chest X-Rays

Authors: Ozer Can Devecioglu, Serkan Kiranyaz, Rashid Mazhar, Tahir Hamid, Muhammad Chowdhury, Moncef Gabbouj
Published: 2026-09-09
Categories: cs.LG
arXiv: https://arxiv.org/abs/2609.09920v1

Reconstructing volumetric Computed Tomography (CT) from a single 2D chest radiograph (CXR) is an ill-posed inverse problem, further complicated by the scarcity of paired CXR-CT training data. Prior approaches address this by training on Digitally Reconstructed Radiographs (DRRs), which are synthetic projections derived from CT volumes. However, the domain gap between DRRs and real CXRs limits generalization, often resulting in coarse or anatomically inconsistent reconstructions when applied to clinical images. To address this challenging problem, this study introduces a Multi-Pass Multi-View Blended Learning framework for synthesizing high-fidelity volumetric CT directly from real chest X-ray (CXR) images. The proposed approach progressively decomposes the synthesis task into two distinct, complementary learning stages. Stage 1 is an unsupervised CXR-to-DRR Domain Adaptation, while Stage 2 includes three passes, namely, (a) supervised DRR-to-CT Transformation, (b) unsupervised Multi-View Slice Refinement, followed by (c) Progressive Transfer Learning (PTL). With such a blended learning paradigm, the proposed approach mitigates the synthetic-to-real domain gap while enhancing both the structural integrity and anatomical detail of the final output. On the LIDC-IDRI dataset, where paired DRR-CT ground truth is available for quantitative evaluation, the proposed method improves upon prior methods by up to 14% in PSNR and 7.6% in SSIM. The framework successfully generates structurally consistent and anatomically realistic high-fidelity CT volumes from real CXRs, marking a significant advancement toward clinical viability of CT reconstruction from standard radiographic images.

---

### Development and Validation of a Physics-Guided Machine Learning Extrapolation Framework Using a Classical Transient Diffusion Benchmark

Authors: Ashutosh Yadav, Alok Dubey, Prodyut Ranjan Chakraborty, Harshal Akolekar
Published: 2026-09-09
Categories: cs.LG
arXiv: https://arxiv.org/abs/2609.09912v1

Machine learning models used in engineering are typically trained within limited operating ranges, yet reliable predictions are often required beyond these domains. Consequently, the primary challenge is extrapolation rather than interpolation. Rigorous validation is hindered by the scarcity of data outside the training range. To address this limitation, a novel extrapolation framework is integrated with established machine learning architectures to enable accurate and physically consistent predictions beyond the training domain. The framework is established by systematically evaluating two physics-guided architectures: a Bidirectional Long Short-Term Memory (BiLSTM) network and a Physics-Informed Neural Network (PINN). A classical one-dimensional transient diffusion problem is adopted as a benchmark because its exact analytical solution provides unlimited, reliable data across the spatio-temporal domain, enabling rigorous quantitative validation. The problem is particularly challenging because the solution evolves from an initial singularity through a strongly nonlinear transient regime before approaching a steady-state linear profile. When training data are confined to an intermediate portion of this evolution, backward extrapolation toward the singularity becomes especially demanding. To improve reliability, physics-guided coordinate transformations, boundary-aware learning strategies, and stability-enhancing temporal marching are incorporated. Extrapolation is evaluated using a train-predict-validate-extend strategy, in which validated predictions are recursively added to the training set to progressively extend the prediction horizon. The results demonstrate accurate and physically consistent predictions beyond the training domain, highlighting the framework's potential for engineering applications where data availability is limited.

---

### A Kernel-Based Modular Discriminant Analysis Framework for Small-Sample Learning

Authors: Lingxiao Qu, Yan Pei
Published: 2026-09-09
Categories: cs.LG
arXiv: https://arxiv.org/abs/2609.09910v1

The small-sample-size (SSS) problem remains a fundamental challenge in machine learning when labeled data are scarce due to cost, accessibility, or ethical constraints. While numerous approaches have been proposed, existing methods often struggle to maintain stable and discriminative representations under high-dimensional and limited-data conditions. Kernelized Linear Principal Component Discriminant Analysis (KLPCDA), a recently proposed modular framework, integrates variance preservation, inter-class separability, and intra-class compactness within a unified kernel space. Although its formulation has shown promising initial results, a systematic understanding of how its components interact across diverse SSS scenarios remains lacking. In this paper, we present a systematic cross-domain study of KLPCDA to characterize the interaction mechanisms among its core objectives. We analyze the behavior of its seven variants across multiple real-world SSS tasks, including hyperspectral image classification, mechanical fault diagnosis, medical diagnosis, and face recognition. Through extensive experiments and ablation studies, we investigate how different objective combinations influence performance under varying conditions such as noise, class imbalance, and high dimensionality. Our analysis reveals consistent patterns in the interaction of the three core objectives variance, between-class, and within-class terms, providing a unified and interpretable understanding of their roles in stabilizing representations and enhancing discrimination in SSS settings. Based on these findings, we further derive practical guidelines for selecting appropriate KLPCDA variants under different data characteristics. Experimental results demonstrate that KLPCDA achieves strong and robust performance across domains, while maintaining low computational complexity suitable for resource-constrained environments.

---

### Interpreting Object-Dependent Concept Brittleness in Text-to-Image Diffusion Models

Authors: Yifan Yuan, Xiangyu Liu, Hongming Shan, Yu Han, Yu Jiang, Hao Tan, Junping Zhang, Linlin Shen
Published: 2026-09-09
Categories: cs.CV, cs.MM
arXiv: https://arxiv.org/abs/2609.09909v1

Although text-to-image diffusion models generally exhibit strong prompt-following ability, we identify a persistent and previously underexplored failure pattern in which a small subset of prompts differing only in the object consistently fails to realize the same target concept under identical generation settings. We term this phenomenon object-dependent concept brittleness. Such cases suggest systematic internal blind spots rather than random sampling noise. In this paper, we present an interpretability-oriented framework to audit and minimally correct these failures. Our key idea is to analyze denoising trajectories in a step-wise sparse autoencoder (SAE) space, where abstract style and attribute concepts become more separable than in the raw denoising representation. This sparse space enables us to compare successful and failed generations, identify concept dimensions whose evidence is missing, weakened, or temporally delayed, and construct class-level concept prototypes from reliable class-consistent samples. Based on this audit process, we introduce a lightweight inference-time correction strategy that interpolates denoising features toward the corresponding prototype in SAE space. Rather than serving as a task-specific retraining method, this intervention acts as a validation of the diagnosed concept deficiency. We evaluate the proposed framework on style and attribute failure cases across multiple diffusion backbones, with significant improvements in concept consistency, text fidelity, and repair success. Further analyses show that deeper denoising representations provide clearer concept structure, while early-stage intervention offers the strongest correction leverage. Code is available at https://github.com/Metecade/Object-Dependent-Concept-Brittleness.

---

### Meta-LinEXP3: Online-within-Online Learning for Adversarial Linear Contextual Bandits

Authors: Hao Li, Jie Xu, Zheng Xie
Published: 2026-09-09
Categories: cs.LG, math.OC
arXiv: https://arxiv.org/abs/2609.09907v2

Meta-learning has emerged as an effective paradigm for transferring knowledge across sequential bandit tasks. While substantial progress has been made for stochastic bandits and non-contextual adversarial bandits, meta-learning for adversarial linear contextual bandits (ALCBs) with random action sets remains largely unexplored. To address this problem, we propose Meta-LinEXP3, an online-within-online algorithm that constructs a predictable task-level prior from completed tasks to guide the inner LinEXP3 learner. For known context distributions, we develop a policy-centered estimator that achieves an intrinsic-dimension $\mathcal{O}(\sqrt{n})$ per-task regret bound. For unknown distributions, we introduce a past-only regularized moment estimator with an $\mathcal{O}(n^{2/3})$ leading regret term and explicit finite-sample error. We further establish a direct connection between prior accuracy and transfer regret, showing that increasingly accurate priors yield sublinear transfer-dependent regret across tasks. Experiments demonstrate the effectiveness of Meta-LinEXP3, including its application to structured hyperspectral tensor sampling.

---

### FlowCPO: A Unified Divergence View of Preference Alignment for Flow Models

Authors: Yansen Han, Shengyi Liao, Peng Sun, Deyuan Liu, Yuanxing Zhang, Pengfei Wan, Tao Lin
Published: 2026-09-09
Categories: stat.ML, cs.AI, cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2609.09905v1

Preference alignment for flow and diffusion models now spans online reinforcement learning and offline preference optimization, but the relation between these methods remains unclear. In particular, existing forward-process alignment methods require fresh samples from the current model, while offline methods based on fixed preference pairs rely primarily on positive-only fine-tuning or DPO-style likelihood-ratio surrogates. We organize these approaches through a divergence-based framework and introduce FlowCPO, an offline forward-KL objective that uses both preferred and dispreferred samples without online rollouts. For linear interpolation, we show under explicit regularity conditions that the forward-KL objective is bounded by a contrastive flow matching loss, yielding a tractable surrogate on fixed data. We further show that this loss is nonnegative, whereas the signed regression loss of simplified FlowDPO can be unbounded below. In the in-domain setting, FlowCPO achieves higher mean GenEval and OCR scores than the evaluated baselines, reaching 0.84 and 0.87 versus 0.81 and 0.74 for FlowDPO at CFG 3.0. In the out-of-domain setting, the results are mixed, with the best GenEval result but lower reward scores than RFT on several metrics.

---

### Beyond Conventional Federated Learning via High-Order Regularization

Authors: Alireza Kabgani, Masoud Ahookhosh
Published: 2026-09-09
Categories: cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2609.09904v1

Federated clients that perform several local optimization steps can return parameter displacements with widely different magnitudes. The quadratic regularization of FedProx grows linearly with displacement and therefore offers limited control over the contrast between ordinary and unusually large client movements. We here introduce HiFedProx, which replaces the quadratic penalty with a scale-matched power-type regularizer indexed by $p\geq2$. All powers have the same regularization-gradient magnitude at a reference displacement $R$, while every $p>2$ gives a weaker response below $R$ and a stronger response above it. An exact affine reference calculation shows that increasing $p$ compresses relative displacement disparities, although very large powers approach fixed-radius behavior and increase local curvature. HiFedProx combines this geometry with finite-budget stochastic client optimization and same-minibatch Armijo backtracking. In paired five-seed experiments on a frozen 60-writer FEMNIST subset, a common-parameter study over $p\in\{2,3,4,5,6,7,8\}$ shows similar clean-training performance but substantial gains under composite stress. The lowest moderate- and severe-stress losses occur at $p=7$ and $p=6$, improving over $p=2$ by $11.44\%$ and $23.16\%$, respectively. Although displacement-tail ratios continue to decrease through $p=8$, predictive performance peaks in an intermediate range and Armijo trial cost increases with $p$. These results indicate that the exponent should be calibrated rather than maximized. In our experiments, $p=5$--$7$ provides the most useful range.

---

### Contrastive Projection: Reading Transformer Internals by Differencing Logit Lenses

Authors: Olli Tuomi
Published: 2026-09-09
Categories: cs.CL
arXiv: https://arxiv.org/abs/2609.09902v1

Reading a transformer's internal states in token space is easy to do and hard to trust: a logit lens on a single hidden state is dominated, at intermediate layers, by the generic tokens the model would predict for almost any input. We read the difference instead. Subtracting two closely matched prompts' hidden states and projecting through the unembedding cancels the shared component and surfaces what separates them, an operation equivalent to reading a RepE/ActAdd steering vector through a logit lens. Built into a training-free tracer that reads at every position, sub-layer, and head and averages over designed baselines, it traces a compound- noun MLP->attention chain in Phi-2, confirmed there by activation patching, with the same distinction recovered across three architectures by readout and probe rather than by patching; it reads what retrieval surfaces for real versus fictional entities, and reads metaphor as a set of domain-to-domain mappings rather than a single figurativity feature. A cross-seed control marks the boundary: across five networks differing only in initialization, the same distinction surfaces as almost entirely different tokens (top-10 overlap 0.08). What a computation looks like in token space is network-specific; the distinction it draws is not

---

### Deep and shallow biases in language models

Authors: An Vo, Vy Tuong Dang, Khai-Nguyen Nguyen, Emilio Villa-Cueva, Thamar Solorio, Anh Totti Nguyen, Daeyoung Kim
Published: 2026-09-09
Categories: cs.CL
arXiv: https://arxiv.org/abs/2609.09901v1

Large language models often repeatedly select the same answer even when many alternatives are plausible. Prior work treats this concentration as bias, but it does not distinguish stable model preferences from responses that depend on a particular prompt wording. We introduce a bias depth score that measures both how strongly a model prefers its top answer under direct prompting and whether that answer survives scenario reframing. Across 4,442 opinion prompts and four large language models, only about a quarter of the concentrated preferences survive reframing. We call these persistent cases Deep biases, and the remaining prompt-dependent cases Shallow biases. Our results show that Deep biases are more often inherited from pretraining and preserved through SFT. Under both continued fine-tuning and prompt-based debiasing for diversity, Deep biases are consistently harder to remove than Shallow biases. Bias depth therefore separates stable learned biases from prompt-wording artifacts that single-prompt metrics conflate. Code, models, and data are available at deepbias.github.io.

---

### Strangers to Themselves: What Language Models Say About Themselves Is Generic

Authors: Phil Blandfort, Urja Pawar
Published: 2026-09-09
Categories: cs.LG, cs.AI, cs.CL, cs.CV, cs.CY
arXiv: https://arxiv.org/abs/2609.09899v1

Language models can fluently describe how they would behave: whether they would cave to pushback, misuse a tool, or lie under pressure. Is that description actually about the model speaking? We turn self-knowledge into a prediction test. Across nine behavioral evaluations, we measure how a model behaves under different conditions, ask it to predict those rates, and compare its predictions with controls that remove the self from the question. We find that: (i) Direct self-report is weak (r = +0.04), and even showing the model the exact items only raises prediction to +0.24. Crucially, the same item-informed question about "capable AI agents in general" does just as well (+0.28), while other models' answers about themselves predict the target model at least as well as its own. (ii) Frontier scale does not detectably change this pattern: any gains in prediction are not self-specific, and are consistent with a better theory of how AI assistants behave rather than better self-knowledge. (iii) First-person framing does have one robust effect: it shifts reports in the flattering direction, understating harmful behavior relative to the same question about a generic agent. (iv) Finetuning on a model's own behavioral record can teach narrow self-predictions, but it also changes the behavior being predicted and the gains do not transfer broadly. The practical implication is simple: asking a model what it would do mostly reveals a theory of AI assistants in general, plus a favorable bias, rather than privileged knowledge of that model.

---

### Grounded Evaluation and Repair for NL-to-PDDL Problem Generation

Authors: Joana Rosa, Pedro Santos, Valdemar Oliveira, Romão Silva, L. Miguel Silveira, Bruno Martins
Published: 2026-09-09
Categories: cs.AI
arXiv: https://arxiv.org/abs/2609.09898v1

Large Language Models (LLMs) have shown promise for translating Natural Language (NL) planning descriptions into PDDL problem instances. However, standard evaluation criteria such as syntactic validity or planner success can substantially overestimate faithfulness to the described task: a generated problem may be parseable and solvable while misrepresenting the intended initial state, goal, object structure, or optimization target. This paper studies an end-to-end NL-to-PDDL pipeline that combines LLM generation, checks in terms of PDDL parsing, planning and validation, a domain-conformance checker, an LLM critic, and iterative repair. Fine-grained repair feedback is constructed from the domain description, the generated problem, the natural language problem description, and operational diagnostics. Reference-based comparisons against curated benchmark PDDL problem descriptions are used for post-hoc benchmark analysis, and these offline checks include renaming-invariant structural matching and semantic equivalence, where domain support is available. Across Planetarium, AutoPlanBench, and curated PDDL~2.1 problems, results show that operational success and benchmark-reference reconstruction can diverge substantially. Results also show that structured repair can be useful, and that PDDL~2.1 remains challenging for reference reconstruction, even when operational success improves.

---

### Can We Trust Video Hallucination Detectors? VidHalLoc for Evaluating the Evaluators

Authors: Xinyu Chen, Adnan Mahmood, Mark Dras
Published: 2026-09-09
Categories: cs.CV
arXiv: https://arxiv.org/abs/2609.09895v1

Video-language models and video agents can produce hallucinations that conflict with spatiotemporal evidence. Existing benchmarks mainly evaluate model hallucinations, and heterogeneous mechanisms make detector reliability difficult to compare. We introduce VidHalLoc, a benchmark that evaluates hallucination detection methods under a unified diagnostic evaluation protocol using 2,000 adversarial hallucination samples across Video Question Answering and Video Captioning tasks, spanning Ontology and Dynamic hallucination categories. To construct VidHalLoc efficiently, we introduce VideoHALO, a Harness Engineering-informed multi-agent workflow that decomposes data construction into four executable stages supported by a memory system and a communication protocol. Evaluation of fifteen methods reveals that the four dedicated detectors peak at an Overall accuracy of only 34.63%, indicating limited reliability across video hallucination types (Dataset Repository: https://huggingface.co/datasets/wesfggfd/VidHalLoc).

---

### ProMeta: Few-shot PROTAC-targeted degradation prediction across E3 ligases

Authors: Yuansheng Liu, Yufei Ye, Tao Tang, Jiawei Luo, Wen Tao, Xiao Luo
Published: 2026-09-09
Categories: cs.LG, q-bio.QM
arXiv: https://arxiv.org/abs/2609.09891v1

Proteolysis-targeting chimeras (PROTACs) have emerged as a transformative therapeutic strategy that selectively degrades historically ''undruggable'' targets via the ubiquitin-proteasome system. Despite growing efforts to develop computational predictors of PROTAC degradation activity, existing supervised approaches remain severely challenged by data scarcity and imbalance across E3 ligases, limiting their ability to generalize beyond well-studied ligase contexts. In practice, labeled data are heavily concentrated on a few ligases (e.g., CRBN and VHL), while the majority of E3 ligases remain underexplored yet are critical for expanding the design space of targeted degraders. Developing methods that enable robust cross-ligase generalization with minimal labeled data is therefore essential for improving the practical utility of computational PROTAC discovery. We reformulate PROTAC degradation activity prediction across E3 ligases as a few-shot meta-learning problem and present ProMeta, a prototype-based graph neural network trained through episodic meta-learning on source-E3 tasks and evaluated on held-out target-E3 tasks through support-conditioned inference. ProMeta performs inference without updating the encoder by dynamically estimating class prototypes from minimal target-ligase support samples. On the CRBN-to-VHL benchmark, ProMeta achieves AUROC values of 0.796 under K=2, Q=3 and 0.883 under K=2, Q=5, improving by 19.9% and 6.8%, respectively, over the corresponding supervised GNN baseline. Reverse VHL-to-CRBN transfer under the same protocol yielded AUROC values of 0.702 (K=2, Q=3) and 0.821 (K=2, Q=5), confirming bidirectional applicability while revealing direction and data-regime dependence. Together, these results support ProMeta as a practical framework for cross-ligase few-shot prediction under the evaluated support/query protocols.

---

### StreetDiff: Multi-view Street Scenes Generation via Cross-view Consistent Multi-view Stable Diffusion with Structure Prompts

Authors: Qi Zhang, Yanyifan Wang, Weiyuan Zhang, Hui Huang
Published: 2026-09-09
Categories: cs.CV
arXiv: https://arxiv.org/abs/2609.09890v1

Multi-view diffusion models have shown strong performance in scenes with strong geometric priors and sparse semantics, such as indoor rooms or simple outdoor environments (e.g., fields, courtyards). However, they often fail to maintain cross-view consistency under camera rotation, especially in structurally complex urban environments. Without explicit modeling of spherical correspondence across views, existing approaches tend to produce object duplication, structural distortion, and layout inconsistency. To address this limitation, we propose StreetDiff, a multi-view diffusion framework that explicitly enforces cross-view alignment during denoising. StreetDiff introduces a Panorama--Perspective Synergy design to decouple global layout reasoning from local detail synthesis, and incorporates a Panorama Alignment Module (PAM) that establishes spherical-projection-based attention constraints across views. By injecting structured alignment constraints without modifying the diffusion backbone, our framework achieves robust cross-view coherence in challenging urban street scene generation tasks. In addition, we construct Street360, a large-scale HDR multi-view urban panorama dataset. Extensive experiments demonstrate that StreetDiff significantly improves structural consistency and visual fidelity compared to prior multi-view diffusion generation methods.

---

### Leveraging Fine-grained Error Correction in Korean Speech Recognition for Consultation Services

Authors: Yonghyun Jun, Jimin Lee, Hwan Chang, Dongho Shin, Seolah Kim, Hwanhee Lee
Published: 2026-09-09
Categories: cs.CL
arXiv: https://arxiv.org/abs/2609.09889v1

Automatic Speech Recognition (ASR) technology is fundamental to customer service automation and large-scale transcription. However, even advanced ASR models exhibit inevitable errors in complex real-world environments such as call center conversations. When privacy restrictions preclude audio access, error correction must rely on text-based post-editing. Existing text-only approaches face significant challenges in low-resource languages, mainly due to a critical scarcity of annotated corpora and tailored correction methodologies. For Korean, this resource gap is particularly pronounced, as existing resources are predominantly designed for ASR training rather than text-based error correction. To address this, we introduce DasanCallDial, the first large-scale Korean benchmark dataset specifically curated for dialogue-level ASR error correction. Derived from genuine call center interactions, it comprises 1,974 dialogues with 115,460 utterances. Leveraging this resource, we propose Detector-Gated Contextual Span Correction (DCSC), a text-only post-editing framework for error-sparse Korean speech recognition transcripts. DCSC combines an encoder-based detector that first performs token-level error detection, followed by a language model-based corrector trained to rectify fine-grained span-level errors. Additionally, we employ dialogue-level context augmentation to enable the model to leverage discourse history for disambiguation. By employing multi-level granularity, our method achieves state-of-the-art performance, effectively overcoming the limitations of general LLMs in low-resource settings.

---

### When Does Defendant Statement Matter? A Study of Bias and Persuasion in LLM-Simulated Jurors

Authors: Cho-Ying Wu
Published: 2026-09-09
Categories: cs.CL, cs.CY
arXiv: https://arxiv.org/abs/2609.09887v1

LLMs have been used to simulate human decision-making in professional settings, yet their behaviors in common-law jury trials remain unexplored. We study when and how a defendant's courtroom statement affects LLM-simulated jurors, focusing on persuasion, ideological bias, and background-based affinity. To support the analysis, we introduce JuryBench, a benchmark containing controversial criminal cases in U.S. criminal law. In each case, a defendant can claim various plausible justifications to support acquittal or reduced liability. We fix the base case and design defendants of different backgrounds, who give courtroom statements with varying emotional appeal or rebuttal. Jurors with diverse ideological profiles across the spectrum are simulated. We examine 20 frontier LLMs, resulting in a total of 432K decisions and rationales, and quantify changes in verdict severity. Our findings show that LLM-jury simulation echoes many human-jury findings. First, emotional persuasion can be detrimental, since jurors may perceive it as evidence of guilt or inconsistency. Next, we show that background fit between jurors and defendants is a stronger and significant factor than other isolated factors, and that jurors are in general harsher toward opposite-background defendants and lenient toward same-background ones. Finally, we find that juror ideology also strongly shapes severity judgments. These findings highlight both the promise and risks of using LLMs to model jury reasoning and call for careful evaluation. The data and code are available at https://github.com/choyingw/JuryBench

---

### Decision Transformer for UAV-Mounted RIS-Assisted Dynamic D2D Communications

Authors: Yaxuan Liu
Published: 2026-09-09
Categories: cs.AI, cs.RO
arXiv: https://arxiv.org/abs/2609.09885v1

This paper studies unmanned aerial vehicle (UAV)-mouted reconfigurable intelligent surface (RIS)-assisted device-to-device (D2D) communication with stochastic link activation. It models UAV motion and attitude, time-varying Rician angles, and angle-dependent RIS reflection. A joint optimization of UAV trajectory, attitude, and RIS phases is formulated to maximize average sum rate under mobility, energy, and hardware constraints. The problem is addressed using deep reinforcement learning and a Decision Transformer trained on expert trajectories from multiple scenarios. Results demonstrate effective cross-scenario generalization, with zero-shot transfer outperforming direct DRL transfer and online fine-tuning achieving competitive performance with fewer interactions.

---

### Albedo Estimation via Latent Bridge Matching

Authors: Carme Corbi, David Serrano-Lozano, Javier Vazquez-Corral, Maria Vanrell
Published: 2026-09-09
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2609.09884v1

Recent advances in Intrinsic Image Decomposition (IID) have increasingly relied on generative models. However, progress remains limited by three key challenges: (a) insufficient physical consistency, (b) high computational cost at inference time, and (c) limited generalization capabilities. In this work, we show that latent bridge matching (LBM) effectively addresses these limitations for albedo estimation. We introduce a novel LBM-based architecture that enforces physical consistency through a pixel reconstruction loss, benefits from the inherent efficiency of LBM low-cost inference, and improves generalization across diverse datasets by incorporating a shading conditioning. In this extended version, we additionally show that conditioning the shading estimator itself on the predicted albedo further improves reconstruction fidelity, and we benchmark our best model against stateof-the-art IID methods across five real and synthetic datasets.

---

### Forward-Free LLM Depth Pruning via Weight Redundancy

Authors: Vincent-Daniel Yun, Woosang Lim
Published: 2026-09-09
Categories: cs.LG, cs.AI, cs.PF
arXiv: https://arxiv.org/abs/2609.09883v2

Depth pruning reduces large language model (LLM) inference cost by removing complete Transformer blocks. Activation-based methods collect hidden states through forward passes on calibration data, while existing forward-free methods score each Transformer block separately without measuring similarity between blocks. We propose Weight-Redundancy Pruning (WRP), a forward-free depth-pruning method that estimates inter-layer redundancy from checkpoint weights to select blocks without calibration data or model forward passes. WRP compares attention output and MLP down-projection weights across layers and combines their pairwise similarities with relative projection-scale information. The resulting all-pairs similarity matrix guides layer grouping and block selection. Across multiple pruning settings, model families, and downstream tasks, WRP consistently outperforms existing forward-free magnitude pruning and approaches the performance of activation-based methods.

---

### Scored vs. Generated Readouts in Behavioral Language Models: An Empirical Study of Elicitation Format

Authors: Touchapon Kraisingkorn, Krittin Pachtrachai, Wachiravit Modecrua
Published: 2026-09-09
Categories: cs.AI
arXiv: https://arxiv.org/abs/2609.09882v1

Language models fine-tuned on customer behavior can predict outcomes and generate explanations, but these readouts are often treated as interchangeable. Holding model checkpoint and prompt content fixed, we compare probabilities obtained by scoring answer tokens with predictions generated after a written rationale. Across 13 model-domain cells covering four retail tasks in three markets, including two using fully public data and checkpoints, the scored readout ranks outcomes more accurately in 12 of 13 cells (two-sided sign test, p approximately 0.003), by 1.5 to 14.5 points in area under the receiver operating characteristic curve (AUC). Paired bootstrap confidence intervals exclude zero in every newly measured cell. The gap varies with task-specific supervision and mismatch between training and serving formats, ranging from -2.2 points for an untuned base model to +13.7 for rationale-format supervision. Analysis of approximately 9,000 rationales identifies two correlates: reduced reliance on the dominant predictive feature and convergence on stock formulations. Probability saturation does not track the gap. A third readout, eliciting a probability before any verdict, improves calibration (Brier score from 0.47 to 0.15) while ranking within noise of scoring, but only for outcome rates represented in training; it is worse than scoring when the scored head is already calibrated. We interpret these differences through the objectives matched by each readout, identify training choices that narrow the gap, and propose retaining generated rationales while sourcing ranking from the scored head.

---

### CLFTv2: Efficient Camera-LiDAR Fusion for Semantic Segmentation via Hierarchical Feature Pyramids

Authors: Toomas Tahves, Mauro Bellone, Raivo Sell
Published: 2026-09-09
Categories: cs.CV, cs.RO
arXiv: https://arxiv.org/abs/2609.09881v1

Semantic segmentation for autonomous driving requires reliable detection of vulnerable road users (VRUs) despite heavy class imbalance. We introduce CLFTv2, a hierarchical camera-LiDAR fusion framework replacing global ViT attention with a Swin-based multi-scale encoder and a lightweight FPN-style residual decoder. Operating in the 2D perspective domain, CLFTv2 integrates multi-scale geometric cues through shifted-window attention and per-scale residual fusion, avoiding the computational overhead of query-matching decoders. Across three driving datasets, CLFTv2 consistently improves VRU recall. On ZOD, CLFTv2-Large achieves 53.5\% mIoU, improving pedestrian IoU from 35.5\% to 44.9\% over the prior CLFT model. On Waymo, CLFTv2 reaches 61.7\% mIoU. Additionally, a modality-isolation study suggests ViT's global receptive field yields stronger fusion gains only under dense LiDAR returns. Compared to a Swin-based Mask2Former adaptation, CLFTv2 requires 1.4$\times$ fewer GFLOPs and delivers 2.2$\times$ higher throughput, while achieving comparable overall accuracy. These results demonstrate that hierarchical local-attention fusion offers an efficient, scalable alternative to global-attention and query-based decoders for real-time on-vehicle perception in intelligent transportation systems. Source code is publicly available.

---

### From Pixels to Hierarchical Sequences: Quadtree Mask Encoding for Vision-Language Binary Change Detection

Authors: Xiao An, Ruikang Zhang, Chen Zhong, Xuli Shen, Jiaxing Sun, Jiang Wu, Wei He
Published: 2026-09-09
Categories: cs.CV
arXiv: https://arxiv.org/abs/2609.09876v1

Dense change detection in remote sensing requires vision-language models (VLMs) to compare bi-temporal images and generate accurate pixel-level masks. Existing VLMs are largely confined to change captioning outputs, and the few that produce pixel-level masks still rely on external decoders or flat text-as-mask serialization, which are less effective for small and fragmented changes. We introduce QUAKE-CD, a framework that recasts dense change prediction as syntax-verifiable structured generation. QUAKE-CD represents binary change masks as grammar-constrained quadtree token sequences, making the masks compact, syntactically checkable, and deterministically decodable within an autoregressive generation space. We further construct QUAKE-CoT, which pairs these sequences with chain-of-thought traces grounded in visual evidence, and jointly optimizes textual reasoning and spatial dense prediction through a progressive curriculum followed by grammar-gated dual-reward RL. On QUAKE-CoT, QUAKE-CD achieves 78.31% accumulated F1, outperforming decoder-based and flat text-as-mask VLMs while producing more faithful bi-temporal reasoning.

---

### AgentAudit: An Open, Extensible Framework for Full-Lifecycle Trust Evaluation of AI Agents

Authors: Shrey Nag, Sachita, Abhishek Kumar Singh, Lipi Goel, Rajeshwar Singh Janwar
Published: 2026-09-09
Categories: cs.AI
arXiv: https://arxiv.org/abs/2609.09875v1

Existing evaluation frameworks mostly assess only one part of AI agents, such as task completion (AgentBench) or security robustness (AgentDojo, ASB), rather than the complete pipeline of planning, tool selection, tool execution, memory and reasoning. Failures can occur at any stage, yet existing benchmarks rarely identify their precise source. AgentAudit evaluates the entire execution trace across ten capability, grounding, security and behavioural dimensions, namely instruction integrity, planner, memory, tool selection, tool invocation, tool correctness, alignment, tool faithfulness, security and execution integrity, combined with behavioural classification and failure attribution to pinpoint the exact stage responsible for an observed failure. AgentAudit can evaluate any LLM-based AI agent, since it attaches to the agent instead of replacing it. It reads only the recorded execution trace and does not interfere with how the agent runs, so it places no constraint on the agent's internal implementation. We evaluate five language models (OpenAI GPT-5, Claude Sonnet 5, Sarvam 105B, Llama 3.3 70B and Gemini 2.5 Flash) across nine capability and adversarial tasks. Claude Sonnet 5 and GPT-5 obtain the highest mean Composite Trust Scores (95.1 and 80.6 out of 100, respectively), while Sarvam 105B, Llama 3.3 70B and Gemini 2.5 Flash trail substantially (57.6, 45.7 and 22.6). All traces were scored by a single fixed judge model, which was itself one of the evaluated models, a limitation discussed in Section VII.E. More importantly, models with similar task-completion behaviour can diverge sharply in trustworthiness, as several non-frontier models are repeatedly classified Unsafe_Compliance on adversarial tasks rather than merely failing them, a distinction that pass/fail benchmarks cannot surface.

---

### Shifting Relational Paradigms for Affective Computing: Affective Resonance, Vitality Affects, and Vocal Interaction Fields

Authors: Cy Gorman, Yihang Yao
Published: 2026-09-09
Categories: cs.AI
arXiv: https://arxiv.org/abs/2609.09864v1

Affective computing has largely followed an individual-state paradigm, extracting discrete emotion labels or arousal/valence from isolated speakers. We argue this framing is incomplete for interaction. Drawing on affective resonance and vitality-contour accounts, we propose a relational framework in which the primary unit of affective analysis is the interactional field constituted within vocal dynamics. As a proof of concept, we present a preliminary empirical study using continuous self-supervised speech representations to detect directional expressive coupling in multi-party conversation. Coupling is regime-specific, concentrated at sub-second timescales, and collapses under exclusive-speech negative controls, consistent with a relational account of affective dynamics. We introduce design frameworks for Artificial Affective Resonance Intelligence grounded in Affective Resonance Dynamic Ontologies, supported by null-calibrated directional coupling analyses across interaction regimes.

---

### Pretraining and Distillation Matter More Than Architecture Family for Label-Free Single-Cell Classification

Authors: Philip Graemer, Giuseppe Di Caprio
Published: 2026-09-09
Categories: cs.CV
arXiv: https://arxiv.org/abs/2609.09863v1

Choosing a deep learning architecture for label-free single-cell classification remains an open question, with microscopy benchmarks reporting conflicting conclusions about CNNs versus transformers. We present a controlled benchmark on LIVECell phase-contrast microscopy data using source-image-disjoint train/validation/test splits to prevent parent-image leakage and matched optimisation, augmentation, and evaluation protocols across EfficientNet, Vision Transformer (ViT), and EVA-02 models. This allows the effects of architecture, pretraining, fine-tuning, tokenisation, and distillation to be disentangled. We find that the previously reported CNN advantage is largely explained by pretraining rather than architecture: the smallest pretrained model outperforms the strongest model trained from scratch despite far fewer parameters. Pretraining improves macro-F1 by 3-4 points, while the gap between the best pretrained CNN and transformer is below 0.5 points. Architectural choices nevertheless matter: ViT-S/8 outperforms ViT-S/16 and matches the four-times-larger ViT-B/16 at a quarter of the parameters, showing that finer tokenisation benefits small cell crops. Conversely, layer-wise learning-rate decay, central to the EVA-02 fine-tuning recipe, degrades performance, highlighting that transfer heuristics from natural-image recognition may not generalise to microscopy. Finally, knowledge distillation substantially improves the deployment frontier: compact EfficientNet-B0 students distilled from teacher councils outperform every individually trained backbone, including the EfficientNet-B5 and EVA-02 teachers. Overall, our results show that rigorous control of pretraining and evaluation is essential for interpreting biomedical architecture benchmarks, while distillation may be a more effective route to practical single-cell classification than architecture choice alone.

---

### Exact Degeneracy Under Balanced k-Shot Sampling:Consequences for Small-Sample Discriminant Analysis on LLM Embeddings

Authors: Lingxiao Qu
Published: 2026-09-09
Categories: cs.LG
arXiv: https://arxiv.org/abs/2609.09860v1

Balanced k-shot sampling draws exactly k labeled examples per class. We show that it induces an exact, provable degeneracy in a family of small-sample discriminant estimators. Under balanced sampling, the within-class scatter operator of Kernelized Linear Principal Component Discriminant Analysis (KLPCDA) is not merely rank-deficient but exactly a scaled orthogonal projector. We derive the consequences in closed form: two of KLPCDA's seven variants have every signal eigenvalue exactly equal, so their eigenvector selection criterion is provably indifferent rather than ill-conditioned, and a third has a provably void objective. This follows from the estimators' construction, not any dataset; we confirm it on frozen sentence embeddings and, separately, on residual-stream activations from a decoder-only generative model. An in-formula tie-break repairs the two repairable variants, with recovery gated by class count: the residual subspace constraint costs 5x more on few-class than many-class datasets (p=0.000001). We then evaluate the repaired framework on few-shot text classification on frozen LLM embeddings (n much smaller than d, up to 4096), across four datasets, three embedding sizes, and three trained baselines (SetFit, LoRA, in-context learning). A properly cross-validated logistic-regression probe still beats every KLPCDA variant on three of four datasets, at every embedding size; guidance carried from pixel, vibration-signal, and gene-expression data does not directly generalize to this feature space. Three independent geometric separability metrics fail to explain why one high-dimensional decoder-based embedding model underperforms smaller bidirectional encoders, ruling out anisotropy; the gap is substantially an estimation-efficiency effect, not a permanent ceiling, closing by more than 80% when the support set grows from k<=10 to k=30-50 (p=0.00195, both many-class datasets).

---

### With a Thermomix You Lose the Ability to Cook: A Kitchen Machine Analogy for Applications of Generative AI in Education

Authors: Nikol Rummel, Valentina Nachtigall, Ernesto Panadero
Published: 2026-09-09
Categories: cs.CY, cs.AI
arXiv: https://arxiv.org/abs/2609.09856v1

The rapid adoption of generative AI tools such as ChatGPT has sparked intense debate about their risks and opportunities for education, as well as the ways researchers should investigate them. In this paper, we approach these discussions through an analogy with the Thermomix, a smart kitchen appliance that has similarly provoked both enthusiasm and critique. By mapping Thermomix use cases onto examples of learning with generative AI, and situating them within the ICAP and SAMR frameworks, we show how different modes of tool use can either support or undermine meaningful engagement and learning. The Thermomix metaphor underscores that the central question is not whether learners employ AI, but how such use shapes their learning processes. In doing so, we provide a conceptual lens for researchers and practitioners to critically examine - and more effectively guide - the integration of generative AI into educational practice.

---

### A Unifying Perspective on Probabilities as Model Predictions

Authors: Benedikt Höltgen
Published: 2026-09-09
Categories: stat.ML, cs.CY, cs.LG, math.ST
arXiv: https://arxiv.org/abs/2609.09855v1

Although probabilistic statements are ubiquitous, foundational disagreements persist about their understanding, as exemplified by debates between Bayesians and frequentists; moreover, it is unclear when and why acting on them actually leads to desirable outcomes. Here, we argue that every probability is the output of a \emph{prediction method}, that is, it depends on both a particular way of constructing abstractions and a way of transforming them into predictions. Through this, we provide a unifying perspective on supposedly different kinds of probabilities and show that even supposedly objective ones are model-dependent. We demonstrate that when a finite calibration criterion is met, one can anticipate the distribution of utilities for a given policy and inform successful decision-making on finite sets of events. Based on the notion of prediction methods, inductive arguments, and the probability calculus, we explain the feasibility of the calibration criterion in many settings. Overall, we develop a coherent perspective on probabilities and their use, connecting key intuitions behind other interpretations along the way.

---

### When Does Low-Bit Quantization Preserve the Decisions of Vector Search?

Authors: Wenxuan Xiao, Xu Cao
Published: 2026-09-09
Categories: cs.DB, cs.IR, cs.LG
arXiv: https://arxiv.org/abs/2609.09854v1

Low-bit quantization can achieve high recall on some vector representations and fail sharply on others, while average distortion and global rank correlation do not explain the difference. We study quantized vector search at the level of the comparisons consumed by ranking and graph-pruning algorithms. Our first result is a distribution-free decomposition: the probability that a comparison flips is bounded by the probability mass of exact margins near zero plus the tail probability of the calibrated residual. We then account for dependence between residuals that share a query or graph node, and derive covariance-aware second-moment identities and tail bounds under a joint MGF proxy. For a frozen candidate permutation, we prove a deterministic coupling theorem for Vamana neighbour selection: the approximate replay returns the exact neighbour list exactly when all candidate-level pruning actions agree on the frozen exact states. We connect these results to representation geometry through an exact Gaussian oracle, establish a strict correlation gain from a deterministic magnitude bit in an aligned bilinear model, and give a rare-contamination construction showing why marginal Gaussian diagnostics do not imply the required residual tails. When analytical assumptions are unavailable, a held-out block certificate bounds the selective failure risk of a frozen quantized rule. Across learned, classical, and synthetic embeddings, standardized exact margins predict held-out ranking and pruning flip rates substantially better than global rank correlation. The framework applies to coordinate binary codes, RaBitQ, Lucene BBQ, and product quantizers through a common decision interface.

---

### The Era by Eon Benchmark: A Generated Enterprise Estate with Exact Ground Truth for Benchmarking LLM Agents

Authors: Benjamin Gruenbaum, Doron Porat, Assaf Natanzon, Roy Zavida, Chen Dinachi, Or Itzahary
Published: 2026-09-09
Categories: cs.AI
arXiv: https://arxiv.org/abs/2609.09853v1

LLM agents for enterprise systems of record cannot be evaluated on customer production data, and no existing substitute provides ground truth. We present the Era by Eon Benchmark for evaluating LLM agents that use enterprise tools. The benchmark is built around a complete fictional company. It includes product simulators, company-specific internal databases, benchmark questions, and computed answer keys. Industry, company size, business model, application portfolio, and a seed define each company. One seeded entity graph supplies shared company data to simulators of Salesforce, Zendesk, Slack, Gong, and other products. A questionconditioned generator creates the schemas and records for internal databases. It takes shared entities, keys, and values from the same graph before generating database-specific facts. Both mechanisms therefore describe one consistent enterprise estate. Every expected answer is computed from the final records, so grading is exact. Design and answer-key checks validate the internal databases. A realism scorecard and adversarial detector validate the entity graph. Across 23 generated companies, the mean realism score rose from 61.8 to 97.0, with zero records flagged as synthetic. In the reported simulator-track comparison, nine models answered the same 33 questions three times each. Accuracy estimates ranged from 42.4% to 76.8%, and three of 36 pairwise differences remained supported after correction.

---

### $S^3$-Bench: Evaluating Speech Interaction Models as Scientific Voice Assistants

Authors: Heyang Liu, Jiayi Huang, Wenyang Xiao, Ziyang Cheng, Lixin Zhang, Zhen Liu, Miao He, Ronghua Wu, Qunshan Gu, Yanfeng Wang, Yu Wang
Published: 2026-09-09
Categories: cs.CL
arXiv: https://arxiv.org/abs/2609.09852v1

The advance of multimodal large language models (MLLMs) has fundamentally reshaped the paradigm of human-computer interaction, especially speech interaction models capable of seamless conversations. Despite remarkable performance as general voice assistants, their performance in specialized domains remains underexplored, particularly in scientific areas. Scientific interactions introduce formidable challenges, involving rare technical terminology, spoken norms of abbreviations, and the natural verbalization of symbolic special expressions. In this paper, we introduce S$^3$-Bench, a systematic evaluation framework covering 10 major disciplines, consisting of a Knowledge set for speech question-answering and a Dialogue set for multi-turn progressive interactions with simulated user agents. By decomposing a complete atomic turn into stages of speech recognition, perception, knowledge utilization with reasoning, and response pronunciation, we systematically characterize the common challenges and performance tradeoffs of existing approaches. Furthermore, experiments on multi-turn interactions reveal persistent limitations in user adaptation and the generation of accurate, comprehensive, and efficient responses.

---

### Can AI Agents Detect and Repair Artifact Drift in Network Experiments?

Authors: Tianzhu Zhang, Weichen Tao, Changgang Zheng, Yusheng Zheng, Long Chen, Xiaoyi Fan, Meikang Qiu
Published: 2026-09-09
Categories: cs.NI, cs.AI, eess.SY
arXiv: https://arxiv.org/abs/2609.09849v1

In recent years, AI agents have evolved into capable assistants that carry out multi-step tasks in digital environments. The network systems community is beginning to explore these capabilities in operational and experimental settings. However, an agent operating in network systems should not be judged solely by whether it completes the immediate task. The experiment record it modifies must also remain trustworthy. We call this property artifact integrity: the record's claims must remain supported by the available evidence, confined to the scope established by that evidence, and traceable through the artifacts that encode their support. To make this property measurable, we introduce NetArtifactBench, which tests whether AI agents can repair inconsistent records derived from public network-system artifacts while preserving claims that remain supported. The benchmark contains 52 instances with injected inconsistencies ranging from direct contradictions to unstated relations spread across several artifacts. We evaluate 23 agent configurations across three general-purpose AI agent runtimes using deterministic scoring. The average contract pass rate is 65.3 % across 5,980 outputs, but no agent runtime exceeds 30 % when repair requires recovering implicit relations and propagating changes across artifacts. These results reveal a sharp boundary between local correction and complete record-level repair. Therefore, we argue that artifact integrity should become a first-class design and evaluation requirement for AI agents operating on network systems.

---

### Subgroup Membership Inference Audits of Differentially Private Synthetic Text

Authors: Yidan Sun, Viktor Schlegel, Srinivasan Nandakumar, Siew Kei Lam, Anil Anthony Bharath
Published: 2026-09-09
Categories: cs.CR, cs.AI
arXiv: https://arxiv.org/abs/2609.09848v1

Synthetic data releases are increasingly proposed in the literature as a means of sharing realistic data replicas in lieu of sensitive private datasets. Even when the worst-case privacy leakage of such releases is bounded by means of differential privacy (DP), in practice a residual risk remains. Membership inference attack (MIA) audits are conducted to empirically quantify this risk. However, existing methods only measure average-case risk for randomly drawn records, which might conceal the risk to vulnerable subgroups. To highlight this issue, we define a subgroup-targeted membership inference game in which the target pool is an explicit parameter, and instantiate it with an audit of 32 proxies under three scenarios with different levels of attacker knowledge, across four datasets, three generators (DP-SGD fine-tuning, API-based prompting, and activation steering), and five privacy budgets. The audit shows that synthetic releases leak subgroup membership and that prior attacks systematically underestimate this leakage. DP is effective at the aggregate level: it substantially reduces average leakage at every budget we test. Three observations temper this picture. First, the remaining leakage is concentrated rather than spread out: under DP, a tenth of the records carries roughly 40% of it. Second, the protection DP delivers in practice is uneven: within its worst-case guarantee, the noise removes more of the measured leakage from random records than from high-risk ones---and a merged-pool audit that scores both record types against shared negatives confirms this at the record level. Third, \emph{which} records leak proves to be a property of the release mechanism rather than of the record alone, so record-level risk cannot be assessed independently of the release.

---

### TempTPI: Informer-Based trajectory prediction for maritime vessels

Authors: Kevin Ferneding, Veronika Lietavcova, Aleksandra M. Blachowiak, Peder Heiselberg
Published: 2026-09-09
Categories: cs.LG
arXiv: https://arxiv.org/abs/2609.09840v1

Accurate long-term trajectory prediction for maritime vessels is essential for safety and logistical efficiency. While deep learning models, particularly Transformers, have shown promise in processing Automatic Identification System (AIS) data, they often struggle with the quadratic computational complexity of self-attention and the loss of accuracy over extended forecasting horizons. This study proposes TempTPI, a novel prediction framework that integrates an Informer-based encoder with a multi-channel temporal encoding mechanism. The Informer architecture leverages a ProbSparse self-attention mechanism to reduce computational overhead and focus on the most significant dependencies, while the temporal encoder utilizes Fourier-like frequency expansions to capture cyclic patterns (hourly, daily, and seasonal) in vessel behavior. We evaluate our model against the state-of-the-art TPTrans architecture using AIS data from Danish waters. Experimental results demonstrate that TempTPI consistently outperforms existing methods across prediction windows of 1 to 5 hours. Notably, at a 5-hour horizon, the proposed model achieves a 55% improvement in Mean Squared Error (MSE), offering a robust solution for long-range maritime situational awareness.

---

### HyperTrace: Hypothesis-Based Preference Tracing for Online LLM Personalization

Authors: Jianzhi Shen, Keyu Mao, Minghao Shao, Chuanyang Jin, Yusong Wang, Ailiang Lin, Kotaro Funakoshi, Manabu Okumura, Tianmin Shu, Muhammad Shafique
Published: 2026-09-09
Categories: cs.CL
arXiv: https://arxiv.org/abs/2609.09835v1

Personalized language models aim to adapt responses to individual users, whose preferences are often latent and revealed gradually through interaction. Existing training-free methods rely on stored histories or retrieved memories, but they often struggle to reconcile long- term preferences with short-term topic-specific needs. To address this issue, we propose HyperTrace, a training-free framework that formulates online personalization as latent preference tracing. HyperTrace maintains interpretable natural-language hypotheses over short-term intent and long-term preferences, and updates them through an SMC-style reweight process using an LLM-based surrogate choice model. By updating these hypotheses across turns and sessions, HyperTrace enables personalization without parameter updates. Experiments on PRISM and PersonaMem-v2 show that HyperTrace improves response alignment, preference prediction, and profile consistency over strong online baselines, demonstrating the effectiveness of tracing latent user preferences for robust personalization. Code and scripts are available in the repository: https://github.com/jiseshen/HyperTrace.

---

### SkNeXt enables topology-guided neuronal reconstruction from petabyte-scale microscopy data

Authors: Jiayi Ding, Hu Zhao
Published: 2026-09-09
Categories: cs.CV
arXiv: https://arxiv.org/abs/2609.09832v1

Recent advances in high-resolution fluorescence and electron microscopy have enabled nanoscale imaging across increasingly large brain volumes, but the resulting terabyte- to petabyte-scale datasets make complete neuronal reconstruction prohibitively expensive in computation, data movement, and manual proofreading. Here, we present SkNeXt, a topology-first framework for scalable neuronal reconstruction from large volumetric microscopy datasets. Instead of densely processing entire image volumes, SkNeXt first converts neuronal morphology into compact SWC skeletons that preserve long-range connectivity. Proofreading is therefore focused on sparse neuronal trees, allowing branch, continuity, and connectivity errors to be corrected before high-resolution reconstruction. The corrected skeletons then serve as persistent structural priors for recovering detailed morphology while preserving neuronal identity and topology. Crucially, SkNeXt also uses neuronal skeletons as spatial indices for selective data access, retrieving high-resolution image regions only along reconstructed trajectories and bypassing most background and signal-free volumes. This substantially reduces I/O and computational overhead, allowing reconstruction cost to scale with neuronal morphology rather than total dataset size. Using SkNeXt, we reconstructed neurons from a petabyte-scale super-resolution fluorescence dataset of the mouse brain on a single GPU within one week, without requiring exhaustive dense inference across the complete imaging volume.

---

### RealSimLoop: Online Real-to-Sim Adaptation via Differentiable Reduced-Order Simulation with Vision Feedback

Authors: Zhihao Cen, Chuhua Xian, Hailin Sun, Yuliang Liufu, Zhen Zhang, Xiangyu Chu, Hongmin Cai, Yunbo Zhang, Guoxin Fang
Published: 2026-09-09
Categories: cs.GR, cs.CV, cs.RO
arXiv: https://arxiv.org/abs/2609.09828v2

Real-world observations of deformable objects are often sparse or surface-level, while downstream tasks require hidden physical quantities such as internal deformation, stress fields, and interaction forces. Physics-based simulation can recover these quantities, but online real-to-sim adaptation remains challenging due to costly full-space optimization, limited feedback, and time-varying material properties. To address these challenges, we propose RealSimLoop, a differentiable framework for online real-to-sim adaptation using vision data as physical feedback. Our approach achieves quasi-real-time performance by executing differentiable simulation within a reduced-order neural subspace, drastically accelerating the optimization loop. We couple this efficient dynamics model with differentiable rendering, enabling direct gradient backpropagation that leverages high-fidelity pixel data to refine physical parameters such as material stiffness. Furthermore, by employing a sliding-window objective function, RealSimLoop enables robust online adaptation, allowing the system to track time-varying material properties and effectively bridge the real-to-sim gap arising from model reduction or unmodeled dynamics. Extensive experiments demonstrate that our method outperforms conventional offline methods, and we validate the framework's versatility in downstream applications, including external force prediction and 3D stress field reconstruction with novel view synthesis.

---

### Layerwise Tunable Lifting Scheme for the Convolutional Neural Network

Authors: Abdumannon Yovkochov, An Le, Sungbal Seo, You-Suk Bae, Truong Nguyen
Published: 2026-09-09
Categories: cs.CV
arXiv: https://arxiv.org/abs/2609.09827v1

This work introduces a family of tunable lifting schemes for biorthogonal wavelet filter banks. We propose three lifting strategies: low-pass tuning (LS-LayLatt-LP), high-pass tuning (LS-LayLatt-HP), and a sequential lifting scheme that jointly adapts low- and high-frequency branches (LS-LayLatt-Sequential). All proposed designs are formulated using a lattice-based lifting structure, which guarantees invertibility and stability for arbitrary parameter values within the lifting functions. We evaluated the proposed methods by integrating them into a ResNet-18 backbone for image classification on the Describable Textures Dataset (DTD), as well as for anomaly detection on hazelnut images from the MVTec-AD dataset and private KRC102S dataset. Experimental results demonstrate consistent performance improvements across all evaluated tasks.

---

### Freezing of Gait Prediction Under Spatial Occlusion: An IMU-Supervised Cross-Modal Distillation Approach

Authors: Chandan Biswas, Aryan Singh, Anabik Pal
Published: 2026-09-09
Categories: cs.CV
arXiv: https://arxiv.org/abs/2609.09826v1

Parkinson's disease is a progressive neurodegenerative disorder characterised by gradual deterioration of movement control. Automated freezing-of-gait (FOG) detection supports the objective assessment of gait-related motor impairment. Two common approaches are used for FOG prediction: (i) analysing video recordings of the patient's movements and (ii) analysing data collected using inertial measurement unit (IMU) wearable sensors attached to the patient's lower limbs. Video-based approaches may suffer detection errors during continuous turning-in-place tasks because the lower limbs undergo substantial geometric self-occlusion, degrading pose-estimation accuracy. IMU-based approaches are generally less affected by visual occlusion; however, they are difficult to deploy outside clinical or laboratory settings, as the sensors must be attached securely and remain in place throughout the assessment. Motivated by this, we propose a cross-modal subspace distillation framework to mitigate the limitations of unimodal FOG detection by combining IMU accuracy with video-based practicality. We extract invariant latent topologies from a pre-trained kinematic oracle to structurally supervise a non-encoded visual architecture during training. To resolve periods of severe spatial occlusion, a dual-stream visual model probabilistically fuses skeletal graph nodes and continuous spatial pixels, dynamically shifting reliance to uninterrupted pixel boundaries as joint tracking confidence drops. Evaluated against a public, multi-modal sequence dataset of Parkinson's individuals executing continuous $360^\circ$ turns, empirical results demonstrate that applying sensory boundary topologies strictly mitigates tracking evaluation entropy. Our constrained optimisation confirms that highly precise FOG prediction bounds can be achieved over zero-wearable inference environments.

---

### In Medical Claims Data, Enhancing Predictive Performance for Major Adverse Cardiovascular Events Using Cross Attention

Authors: Yuhei Fujioka, Daitaro Misawa, Tatsuyoshi Ikenoue, Shingo Fukuma
Published: 2026-09-09
Categories: cs.LG
arXiv: https://arxiv.org/abs/2609.09824v1

Medical claims data comprise the financial details, including the expenses and billing information, as well as the clinical information, such as the diagnoses and treatments, of patients visiting medical facilities. Recently, it has been acknowledged that large databases can be constructed from medical claims data for medical research purposes. However, the clinical information within these datasets is often medically unstructured, limiting its application in comprehensive analyses. This study enhances predictive model performance for major adverse cardiovascular events (MACE), a leading cause of death worldwide. Models that predict MACE are crucial to clinical practice guidelines. We utilize a cross-attention mechanism to develop a method that effectively weights the relationships between diagnoses and treatments. Effectively repre- senting the clinical information contained in medical claims data, this approach generates more representative features for predicting MACE. The ROC-AUC score of our proposed cross-attention-based model was 0.7720, higher than other benchmark models including the conventional atherosclerotic cardiovascular disease model, the light gradient boosting machine, and a self-attention-based model. These results indicate that integrating the clinical structure of medical claims data using a cross-attention mechanism significantly enhances the performance of predictive models.

---

### UnitBoost: Managing Compound LLM Systems with a Merge Operator, Not a Model

Authors: Xing Zhang, Guanghui Wang, Yanwei Cui, Mengdie Flora Wang, Peiyang He
Published: 2026-09-09
Categories: cs.AI, cs.CL, cs.MA
arXiv: https://arxiv.org/abs/2609.09815v1

Compound LLM systems often solve a coordination problem by adding a higher-level LLM. The resulting meta-agent reads workers' outputs, writes the final answer, allocates later calls, and decides when to stop. It is expressive, but it also concentrates three control decisions in an opaque, order-sensitive model call. We ask whether the manager needs to be generative at all. UnitBoost replaces that model with a defined meta-level operator: a task-given unit map turns worker outputs into slot-value proposals, a constrained argmax assembles the output, and the slots left unfilled or unsupported become an explicit residual for the next round. The operator is order-free, records unit provenance, and gives a simple guarantee: without coupling constraints, unit-wise maximization under the same admission score dominates selection of any complete candidate. On three held-out benchmarks, it exceeds the best single candidate chosen with gold labels by 0.060-0.195 absolute task-score points and input-matched generative managers by 0.048-0.076. Replacing only the management step improves six compound-system configurations by 0.013-0.182. Residual-directed rounds raise FanOutQA cell F1 from 0.4778 to 0.5524; matched controls show that the true residual outperforms random targets and ordinary rereading, while a label-free supply signal flags exhaustion after one unproductive round. The same analysis measures three conditions in which no such gain is available (one indivisible unit, unavailable unit identity, and an endpoint that charges for every emitted unit) and quantifies cross-unit coupling as a repair cost. The manager gives up semantic freedom and gains order invariance, unit provenance, and testable failure conditions.

---

### Online Inverse Integer Linear Optimization via Small-Gradient Skipping: Constant Regret and Finite Mistakes

Authors: Akira Kitaoka
Published: 2026-09-09
Categories: cs.LG, cs.DS, math.OC
arXiv: https://arxiv.org/abs/2609.09809v1

In online inverse linear optimization, the learner predicts a weight at each round, observes the optimal action of the agent, and updates its prediction. In the general setting, the gap of $\log T$ between the regret upper bound $O(d \log T)$ and the lower bound $Ω(d)$ is unresolved (here $T$ is the total number of rounds and $d$ is the dimension). When the action set is M-convex, the regret is known to be bounded by $O(d \log d)$, but the method attaining it computes a center of gravity at every round. This paper therefore proposes Small-Gradient Skipping (SGS), a mechanism that skips the update at rounds without a mistake in the case where the correct action is uniformly separated from the other candidates, and applies it to online gradient descent, the online Newton step, and MetaGrad. The number of mistakes is then bounded, for all three, by a quantity independent of $T$; and for the online Newton step and for MetaGrad with SGS, the dimension dependence of the regret becomes $O(d^2)$ when the forward problem is an integer linear program, that is, the factor $\log T$ is removed. Moreover, when the action set is M-convex, the regret is bounded efficiently without computing a center of gravity.

---

### Morphological Decoupling-Based Skeletal Classification for Clinical Assessment of Malocclusion

Authors: Zhichun Jin, Zhicheng He, Hao Xu, Dongyang Li, Lin Wang, Hongliang Ren, Long Bai
Published: 2026-09-09
Categories: eess.IV, cs.CV
arXiv: https://arxiv.org/abs/2609.09801v1

Malocclusion skeletal grading is a fundamental task in orthodontics, critical for diagnosis and treatment planning. Traditionally, cone-beam computed tomography (CBCT) is used for visual measurement, and the reconstructed lateral cephalograms are handed over to expert dentists for diagnosis. However, manual review is time-consuming, labor-intensive, and subject to inter-operator variability. Therefore, an automatic CBCT-based system is needed for reliable malocclusion skeletal grading. In this case, we develop TeethGNN, a novel graph-based framework designed to combine CBCT image features with morphological information for accurate and efficient malocclusion grading. TeethGNN utilizes a decoupled learnable decoder to directly predict key morphological indicators from CBCT images, eliminating the need for manual measurements. These morphological features are then fused with image features using a graph neural network (GNN), which effectively models the relationships between the modalities. To further enhance robustness and calibration, we introduce a collaborative calibration strategy. This strategy combines multi-scale graph adversarial perturbation for explicit calibration and nonlinear topological graph calibration for implicit confidence adjustment. Extensive experiments and ablation studies on our collected clinical dataset demonstrate that our malocclusion measurement system achieves 77.08\% in accuracy and 89.61\% in AUC, outperforming the compared state-of-the-art methods. These results validate the effectiveness of graph-based multimodal fusion and collaborative calibration in improving malocclusion grading performance. Our system shows strong potential for advancing computer-aided orthodontic diagnosis, providing an accurate and reliable solution for vision-based clinical measurement and diagnosis.

---

### uFlowCSP: Crystal Structure Prediction using Mean flow generative models

Authors: Sourin Dey, Dipannoy Das Gupta, Lai Wei, Sadman Sadeed Omee, Jianjun Hu
Published: 2026-09-09
Categories: cond-mat.mtrl-sci, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2609.09799v1

Crystal structure prediction (CSP) is fundamental to computational materials discovery. Generative models including CDVAE, DiffCSP, FlowMM, and CrystalFlow learn stable-crystal distributions directly, but diffusion and flow-matching inference requires tens to thousands of sequential network evaluations per candidate. We introduce uFlowCSP, a MeanFlow-based CSP model that learns the average, rather than instantaneous, probability-flow velocity. It generates a complete structure in one to five evaluations, delivering 5x-58x faster inference with equal or better performance. A chemistry- and symmetry-aware Transformer uses canonical atom ordering, global composition, and per-token chemistry embeddings. A coarse crystal-system token is used only during training; it provides additive gains, particularly improving space-group agreement despite being absent at inference, which remains formula-only. On MP-20 with 20 candidates per target, one step matches CrystalFlow (78.38% vs. 78.34%) with 100x fewer evaluations and about 10x lower wall-clock time. Five steps reach 83.64%, exceeding CrystalFlow (78.34% at 2,000 evaluations) and DiffCSP (77.93% at about 20,000), while using 20x fewer evaluations. uFlowCSP generates 10,000 structures in 0.39-1.31 minutes, versus 6.5 for CrystalFlow and 76.1 for DiffCSP. Under CSPBench's energy-ranked top-five structure-and-space-group criterion, five-step uFlowCSP reaches 72%/72%/65% structure, space-group, and consensus match rates. CrystalFlow reaches 78%/73%/68% at 100 steps but falls to 49%/32%/31% at five. Thus, uFlowCSP improves accuracy per network evaluation, not merely peak accuracy.

---

### CS-Guard: Benchmarking LLM Guardrails for Code Generation Security

Authors: Jinyang Li, Mingyu Guo, Hung X. Nguyen
Published: 2026-09-09
Categories: cs.CR, cs.AI
arXiv: https://arxiv.org/abs/2609.09798v1

Large language models (LLMs) have been ex- ploited to generate malware, but the effective- ness of guardrails for code generation secu- rity remains unclear. We introduce CS-Guard, the first benchmark to systematically evalu- ate guardrails for code generation security. It covers 1) text-to-code generation with 1000 high-quality malware-generation prompts, 7 jailbreak attacks, and a novel fictional scenario attack (FSA) that embeds malicious intent in a legitimate fictional software-development sce- nario; and 2) code-to-code generation with 331 code prompts spanning code infilling, code completion, and code translation. We empiri- cally evaluate 9 guardrails across seven LLMs. We find that current guardrails perform poorly against malicious code-generation re- quests: for text-to-code, the average attack success rate (ASR) after jailbreaks reaches about 50% for many guardrails; for code-to- code, average ASR approaches 100% on base LLMs and remains high across many guardrails (14.4% to nearly 100%). Our FSA also achieves ASR close to 100% across many guardrails, raising major reliability concerns for real-world software development. To sup- port future research, CS-Guard uses a modular three-layer guardrail taxonomy that lets devel- opers register guardrails for evaluation. We release the benchmark and data to enable fur- ther community evaluation.

---

### A practical DIRECT-type algorithm for medium-scale black-box global optimization

Authors: Linas Stripinis, Remigijus Paulavičius
Published: 2026-09-09
Categories: cs.LG, math.NA
arXiv: https://arxiv.org/abs/2609.09796v1

The DIRECT algorithm is a deterministic global optimization method known for its versatility and balanced exploration-exploitation strategy. However, DIRECT-type algorithms are primarily effective for low-dimensional problems and often exhibit slow convergence as dimensionality increases, limiting their applicability to more complex optimization tasks. To address this limitation, this paper introduces X-DTC-GL, a novel DIRECT-type algorithm that incorporates dynamic partitioning and hybridization techniques. The dynamic partitioning approach adaptively refines the search space based on local one-dimensional surrogate models, enabling rapid subdivision of promising hyper-rectangles. The hybridization strategy selectively employs a hill-climbing method to exploit promising regions identified by the surrogate models. Extensive experiments on four diverse benchmark suites demonstrate that X-DTC-GL significantly outperforms existing DIRECT-type baselines, achieving improvements of ~12% in solvability and ~27% in solution quality. Performance-profile analyses indicate the fastest convergence on up to ~40% of instances, the best runtime performance on ~17% of problems, and competitive overall execution times. By improving performance within the partition-based framework, these advances strengthen the algorithm's competitiveness in state-of-the-art black-box optimization.

---

### Privacy-Preserving Split Learning for Federated LLM Fine-Tuning

Authors: Heng Jin, Chaoyu Zhang, Hexuan Yu, Wenjing Lou, Y. Thomas Hou
Published: 2026-09-09
Categories: cs.LG
arXiv: https://arxiv.org/abs/2609.09794v1

Fine-tuning large language models (LLMs) on domain-specific data is essential for downstream adaptation. In many deployments, a participant cannot hold the complete model locally. This happens because the model owner keeps the full model proprietary, or because the participant lacks sufficient compute resources. Split Learning (SL) addresses this by partitioning the model between the participant and a server so that only a small portion runs locally. When the underlying data is additionally distributed across multiple institutions with privacy requirements, Federated Learning (FL) further enables collaborative training across participants by sharing only model updates instead of raw data. In this combined setting, each client transmits intermediate activations to the server, and for LLM fine-tuning, this exchange poses an inherent privacy paradox. The autoregressive nature of LLMs causes the transmitted activations to leak the input, and existing perturbation-based defenses are fundamentally ineffective in this setting. We address this leakage through a learned obfuscate-and-recover scheme that protects participants' private datasets while still allowing an independently deployable model to be trained on the server side. Experiments demonstrate that our approach achieves strong privacy protection with modest utility loss and system overhead, making split-based federated LLM fine-tuning practically viable.

---

### How Fragile Is Safety Alignment at Frontier Scale? A Single-Direction Attack on a 320B MoE

Authors: Yi Shi, Tanyu Chen, Kai Shen
Published: 2026-09-09
Categories: cs.CR, cs.AI, cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2609.09793v1

Directional ablation removes an aligned language model's ability to refuse by projecting a single "refusal direction" out of the weights that write the residual stream. It needs no gradient-based training and no optimization, only a few hundred contrastive prompts, which makes it the canonical white-box attack on open-weight alignment. However, it has been established only on dense models up to roughly 70B parameters. We study whether it survives the shift to frontier mixture-of-experts (MoE) models whose residual streams are no longer a single tensor and whose weights ship quantized. We apply it to GLM-5.3-Flash (320B parameters, 288 routed experts, a four-wide hyper-connection residual, block-FP8). The attack survives the architecture, but what it reaches is no longer where a reader of the original recipe would look for it. Editing the attention, dense and routed-expert writers on their own removes 0.039, 0.016 and 0.148 of refusal respectively; editing all three together removes 0.776. As a result, 74% of the effect exists only under the joint intervention. The part the conventional recipe reaches by module-name matching accounts for 0.066 of that 0.776, which is why it fails silently on an MoE. The effect does not follow from removing just any direction: ablating a random direction orthogonal to it leaves refusal unchanged. A category-concentrated residue survives every edit we tried: subspaces fitted on violence, sexual content and hate leave measurable refusal at every rank from 1 to 12. We report the method, the 41-89 percentage-point reductions it achieves across seven harmful benchmarks with no detected change in capability, and the boundary where it stops.

---