# Research Papers — 2026-09 · bundle page 162 of 266

> Full-text markdown of papers #8051–8100 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/162
[← Previous bundle](https://aipod.dev/papers/archive/2026-09/page/161.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-09/page/163.md)

### Stable by Construction: Variational Latent Markov Operators for Long-Horizon PDE Prediction

Authors: Junyi Liao, Johann Guilleminot, Vahid Tarokh
Published: 2026-09-15
Categories: cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2609.16621v1

Neural PDE solvers provide efficient surrogates for time-dependent physical systems, but autoregressive prediction over long horizons remains challenging because local errors can induce distribution shift and accumulate under recursive deployment. We develop a variational approach to this problem by introducing latent Markov dynamics in which physical states are represented by latent distributions and evolved through probabilistic transitions. The framework is formulated directly on function spaces and specialized to functional Gaussian models, where structured latent perturbations induce a spectral geometry and variational transition alignment regularizes the learned dynamics. We further analyze how these mechanisms affect autoregressive error propagation, providing a theoretical connection between variational training and long-horizon prediction. We instantiate the framework as the Variational Autoencoding Markov Operator (VAMO), which combines spatially resolved latent fields, structured Gaussian perturbations, and a neural-operator transition. Empirically, we demonstrate the effectiveness of VAMO on several fluid-dynamics benchmarks with prediction horizons extending substantially beyond those represented during training, where it consistently reduces error accumulation and improves rollout stability over several deterministic and noise-injection baselines. Overall, these results highlight variational modeling as a complementary approach to robust long-horizon neural PDE dynamics.

---

### Divergence Timing and Cumulative Disagreement under KV-Cache Eviction

Authors: Xinyue Luo, Fei Yu
Published: 2026-09-15
Categories: cs.LG
arXiv: https://arxiv.org/abs/2609.16617v2

KV-cache eviction perturbs the conditional token distributions governing autoregressive generation. We investigate how first-divergence timing and subsequent token mismatch determine cumulative disagreement. We derive an exact decomposition under a specified stepwise maximal coupling: the expected mismatch fraction equals a first-mismatch contribution plus post-divergence exposure multiplied by its mismatch rate. An explicit construction over unrestricted autoregressive kernel pairs realizes the sharp interval of risks compatible with a finite divergence-aligned observation window. Residual-branch conditional Monte Carlo provides unbiased joint estimates of occurrence, occupation, and window/tail contributions, with per-replicate variance dominance for total token loss. Complete trajectories from Meta-Llama-3.1-8B-Instruct and Qwen2.5-7B-Instruct show that SnapKV at 50% retention enters divergence later and less often than SnapKV-512 or recent-token retention with the same 50% prompt-cache budget, while post-divergence total variation (TV) remains high. In an exploratory analysis of 288 documents, post-divergence exposure accounts for 85-90% of four aggregate mismatch gaps. On 288 independent documents at 90% retention, prespecified comparisons show higher branch-aligned TV in the late than in the early window in both models.

---

### RoleBreak: Benchmarking Long-Horizon Role-Playing Robustness in Spoken Dialogue

Authors: Yuqi Wang, Fengyuan Liu, Haochen Luo, Zhiqi Yu, Qi Liu
Published: 2026-09-15
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2609.16614v1

Speech-to-speech dialogue models increasingly support persona control, yet existing spoken role-playing benchmarks remain largely character-centric and short-horizon. This leaves open whether spoken dialogue models can sustain diverse roles over extended interactions, especially beyond predefined fictional characters. We introduce RoleBreak, an open benchmark for long-horizon role-playing robustness in spoken dialogue. RoleBreak contains 310 character-based and user-centered roles, 6,688 human-verified dialogue turns, and 11,743 fine-grained evaluation criteria, with 1,856 turns carrying expressive emotion targets for evaluating vocal emotion. Its scenarios are designed to stress role consistency, interaction quality, safety, and affect over extended conversations. We evaluate nine configurations spanning full-duplex, omni-modal, and cascaded ASR--LLM--TTS paradigms. We find four key patterns. First, current systems are substantially stronger at semantic role adherence than at vocal emotion. Second, semantic robustness remains brittle over long interactions: even the strongest evaluated system encounters its first persona and safety failures after only 10.4 and 11.6 turns on average. Third, scaling the LLM substantially improves semantic robustness and delays failure, but yields little improvement in vocal emotion. Finally, user vocal emotion affects role-playing behavior even when linguistic content is fixed. These findings highlight persistent gaps in both long-horizon robustness and vocal expressiveness in spoken role-playing systems.

---

### Structure Across Voices: Comparing acoustic-event type accumulation and sequence dependence across four vocal repertoires using frozen audio encoders

Authors: Mudit Sinha, Sanika Chavan
Published: 2026-09-15
Categories: cs.SD, cs.AI
arXiv: https://arxiv.org/abs/2609.16612v1

Vocal repertoires can differ in acoustic-event type accumulation and temporal organization, yet direct comparison is difficult because corpora use different native events and unequal amounts of sequence. We compare sperm whale codas, human speech phones, Bengalese finch syllables, and common marmoset calls using the same frozen-audio-encoder procedure while matching event count and local sequence opportunity. Whale shows the fastest type accumulation; Finch shows the strongest immediate dependence and repeated-subsequence recurrence. Physically interpretable acoustics recover complementary parts of this profile, continuous analyses without clustering support broad Whale acoustic coverage, and source- and position-preserving nulls retain both Finch order effects. Extending predictive context shifts the comparison toward Whale. Thus repertoire differences depend on the acoustic property and temporal scale measured rather than forming a single hierarchy.

---

### EgoPathBench: Evaluating Zero-Shot Egocentric Waypoint Decision-Making in Vision-Language Models

Authors: Yang Zhao, Zhuo Chen, Xubo Yang
Published: 2026-09-15
Categories: cs.CV
arXiv: https://arxiv.org/abs/2609.16610v1

Zero-shot waypoint navigation requires vision-language models to select, from the current first-person observation, a sequence of spatial actions that is feasible for the agent and reaches the goal, placing joint demands on the integrated spatial intelligence of today's foundation VLMs. Existing spatial-intelligence benchmarks primarily evaluate isolated judgments of relations, directions, or targets and therefore do not directly measure the integrated navigation ability required to combine target recognition, action-consequence assessment, distance estimation, and path planning. To fill this evaluation gap, we introduce EgoPathBench, a dataset and five-task benchmark for first-person waypoint decision-making. Each question presents an egocentric RGB image, a natural-language goal, and numbered visible waypoints; a model returns traversable candidates or an ordered route. Predictions are evaluated for candidate feasibility, adjacent-edge legality, and goal arrival under point-agent or embodied geometry. EgoPathBench contains 31,852 training, 1,345 validation, and 1,111 benchmark questions and retains at least one geometrically verified reference route for every route question. Across nine VLMs, the highest EgoPath Score is only 28.3. The top-ranked model reaches 35.9% success on Point Path, but only 2.9% and 4.0% on Embodied Path and Intent Path, respectively, showing that current models remain limited in forming complete, goal-consistent routes under embodiment constraints. Beyond the evaluation data, we release the corresponding training resource. Fine-tuning Qwen 3.5 4B on the released training split raises its EgoPath Score from 3.9 to 38.9 and improves all four reported evaluations across three external spatial benchmarks, with gains of 1.4--9.6 points.

---

### A Weighted Kernel Method for Approximation that Adapts to Learned Multivariable Structure

Authors: John E. Darges, Laura Weidensager
Published: 2026-09-15
Categories: cs.LG, math.NA
arXiv: https://arxiv.org/abs/2609.16606v2

Approximating the input-output behavior of a multivariable black-box function from limited data is challenging when blind to the importance of its inputs and their interactions. We introduce total sensitivity kernels (TSKs), a method based on families of weighted ANOVA kernels that learn and adapt to this multivariable structure. TSKs parameterize the weights on each multivariable component of the target function by factors for each input. We propose learning these factors directly from function evaluations by selecting the reproducing kernel Hilbert space (RKHS) in which the target function has minimum norm. Under suitable conditions, we show that this norm-minimization problem admits a unique solution, and we establish consistency of a finite-data formulation based on minimum-norm interpolation. The learned TSK factors characterize the participation of individual inputs across interactions and main effects, providing a kernel-dependent notion of input sensitivity related to total Sobol indices. Numerical experiments demonstrate that adapting the kernel to learned multivariable structure can substantially improve approximation accuracy over a standard product kernel.

---

### G3AR: Graph-Guided Neural Visual Geometry for Scalable Multi-Sequence Aerial Registration

Authors: Jeng Wen Joshua Lean, Ting-Yu Yen, Wei-Fang Sun, Simon See, Hung-Kuo Chu, Shih-Hsuan Hung
Published: 2026-09-15
Categories: cs.CV
arXiv: https://arxiv.org/abs/2609.16603v2

Full-context neural visual geometry is impractical for thousands of images, while sequence-based chunking poorly captures irregular non-local overlap in multi-sequence aerial collections. We present Graph-Guided Neural Visual Geometry for Aerial Registration (G3AR), a graph-guided framework for scalable dense neural geometry. Before local inference, G3AR builds a geometrically verified image-proximity graph that guides bounded overlapping chunks and induces a chunk graph whose maximum spanning tree defines alignment topology. Compatible backbones process chunks independently; shared-image predictions then estimate three-dimensional similarity (Sim(3)) transforms that register local cameras and geometry in a common frame. Across four real aerial scenes, G3AR improves pose error and runtime in matched VGGT- and Pi3-backed comparisons, while its DA3 variant achieves the lowest pose error among evaluated neural-geometry methods.

---

### SAVOR: Self-Aware Visual Grounding via Confidence-Calibrated Reinforcement Learning for Multimodal Hallucination Mitigation

Authors: Zixiu Ding, Zilin Zhao, Yingjie He, Xinlang Kang, Guansu Wang, Wei Zhang
Published: 2026-09-15
Categories: cs.CV
arXiv: https://arxiv.org/abs/2609.16601v1

Multimodal large language models (MLLMs) have made strong progress on visual question answering and image captioning, yet they still produce fluent claims about objects, attributes, or relations that are not grounded in the image. Many remedies either modify decoding at test time, which adds latency, or fine tune with preferences such as DPO variants, which teach which answer is preferred but not when the model's own answer is unreliable. We argue that calibrated self assessment is the missing signal. We introduce Savor, a training framework that (i) augments the output schema with token and answer confidence, (ii) optimises the policy with a Group Relative Policy Optimisation (GRPO) objective that penalises calibration error and poor abstention decisions, and (iii) uses the learned confidence at inference time to revisit visual evidence only when the model is uncertain. Experiments on POPE, HallusionBench, AMBER and MMHal-Bench across two recent backbones (InternVL3-8B and Qwen3-VL-8B) show that Savor reduces hallucination while preserving general capability on MME and MMBench, with lower Expected Calibration Error than DPO and decoding baselines.

---

### Large Language Models in the Loop: A Stability- and Network-Aware Survey in Networked Control, Cyber-Physical, and Multi-Agent Systems

Authors: Haiping Du, Linping Chan
Published: 2026-09-15
Categories: eess.SY, cs.AI
arXiv: https://arxiv.org/abs/2609.16599v1

Modern networked control systems (NCSs), cyber-physical systems (CPSs), and complex multi-agent network systems (CNSs) increasingly rely on large language models (LLMs) for high-level decision-making. However, the slow, stochastic nature of LLMs directly conflicts with the strict stability and safety guarantees required by these physical systems. This survey presents a unified analysis of how LLMs can be admitted into the control loop of NCS, CPS, and CNS without compromising closed-loop guarantees. We organize this around a core principle: the LLM operates as a slow supervisor adjusting high-level goals and constraints, while a fast, certified inner loop maintains physical stability. Under this framework, LLM integration maps directly to classical networked control challenges, where inference latency acts as delay, API failures as packet dropouts, tokenization as quantization, and hallucinations as bounded disturbances. We assess current developments across all these three domains, highlighting that rising model capabilities are frequently accompanied by a drop in formal safety assurances. Finally, we propose concrete future research directions, identifying the widespread lack of formal stability proofs as the field's central open problem.

---

### A Vision-Language Foundation Model for Precise and Comprehensive Brain Tumor Diagnosis from Preoperative Multimodal Data

Authors: Yinong Wang, Jianwen Chen, Zhou Chen, Shuwen Kuang, Haoning Jiang, Yanzhao Shi, Huichun Yuan, Yan-ran, Wang, Bing Wang, Lei Wu, Bin Tang et al.
Published: 2026-09-15
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2609.16597v4

We developed BrainVLM to classify all 12 World Health Organization (WHO) 2021 brain tumor types. BrainVLM integrates an uncertainty quantification strategy to indicate prediction reliability and a module for generating radiology reports to elucidate the clinical rationale. BrainVLM was trained on multi-modal data (MRI scans, demographics, and radiology reports) from 40,043 individuals. It was validated on 5,211 patients with pathologically confirmed brain tumors, including 3,877 held-out patients from the primary hospital and 1,334 patients from 11 independent hospitals. We further conducted two proof-of-concept studies to validate its clinical utility in AI-clinician workflows: 1) a blinded multireader study where 12 neuroradiologists across varying experience levels interpreted 248 retrospective cases with or without AI assistance, and 2) a real-world prospective study in which 1,009 patients were independently and blindly assessed by BrainVLM and radiologists before surgery. Additionally, we demonstrated BrainVLM's utility in preoperative molecular subgroup prediction for adult-type diffuse gliomas, using a multi-center cohort of 632 patients. In primary evaluation, BrainVLM achieved an area under the curve (macro-AUC) of 0.85 (95% CI: 0.84-0.86), and an F1 score of 0.82 (95% CI: 0.81-0.83), surpassing neuroradiologists (F1 = 0.80 (95% CI: 0.79-0.81)). In external validation across 11 centers, BrainVLM achieved an AUC = 0.80 (95% CI: 0.79-0.82) and F1 = 0.75 (95% CI: 0.73-0.78), compared with F1 = 0.71 (95% CI: 0.69-0.73) for neuroradiologists. In prospective real-world evaluation, BrainVLM maintained performance comparable to neuroradiologists. The BrainVLM project page is available at https://hku-healthai.github.io/brainvlm_project.github.io/.

---

### FRPSS: Feature Rearrangement in Pre-Shape Space for Single-Image Generation

Authors: Yuexing Han, Haoxuan Zhang, Bing Wang
Published: 2026-09-15
Categories: cs.CV
arXiv: https://arxiv.org/abs/2609.16594v1

Generative models trained on a single image often struggle to balance global structural integrity and local diversity. Existing single-image generation methods commonly rely on random noise to drive the generation process and lack explicit global structural constraints, making the generated results prone to spatial structural misalignment when structural variations occur. To address the issue, Feature Rearrangement in Pre-Shape Space for Single-Image Generation (FRPSS) is proposed in this paper. The core of FRPSS is the Manifold Structural Rearrangement with Feature Augmentation on Geodesic Surface (MSR-FAGS) module. MSR-FAGS replaces the randomly initialized features of the low-scale generator with rearranged Pre-Shape features and uses the features to guide image generation at subsequent scales, thereby reducing the risk of structural misalignment. To support downstream tasks such as stylization, a Scale-adaptive Sliding-window Patch Extraction (SSPE) strategy is further designed, and a directional Contrastive Language-Image Pre-training supervision module with SSPE (CLIP-SSPE) is constructed. Qualitative and quantitative experiments demonstrate that FRPSS achieves the best Single Image Fréchet Inception Distance (SIFID) scores on all three datasets while maintaining competitive Learned Perceptual Image Patch Similarity (LPIPS). Further qualitative experiments verify the effectiveness of FRPSS across multiple downstream tasks with the CLIP-SSPE module.

---

### A Framework for Generating Valid Context-Specific Benchmarks through Expert Guidance

Authors: Kimberly Le Truong, Nari Johnson, Anna Kawakami, Hoda Heidari
Published: 2026-09-15
Categories: cs.AI, cs.CY
arXiv: https://arxiv.org/abs/2609.16592v1

This paper presents an end-to-end approach for generating context-specific large language model (LLM) benchmark datasets by combining expert input with synthetic data generation. Existing benchmark construction methods often trade off validity and scalability: datasets designed with domain experts can produce high-quality evaluations but are slow and costly to create, while synthetically generating data may scale efficiently but often results in unrealistic, redundant, or out-of-scope examples. To address this gap, we introduce a schema eliciting key information about the goals, scope, and context of an evaluation task, and use this information to guide synthetic data generation. We further define four criteria grounded in measurement validity for assessing dataset quality: coverage, diversity, content realism, and stylistic realism. Using these criteria, we show how expert-informed scaffolds can guide synthetic data generation toward more valid benchmarks. Through quantitative evaluations and a real-world case study with domain experts, we demonstrate that our approach improves benchmark data quality over existing methods while preserving validity. We additionally analyze how different types of schema information affect different dataset quality criteria, and provide practical guidance on which information to prioritize collecting under resource constraints.

---

### FLAT: Resampling Image and Text into 1D Flexible-Length Aligned Transmodal Tokens for Retrieval and Generation

Authors: Guangyu Sun, Shlok Kumar Mishra, Wentao Bao, Robert Zhenheng Yang, Xiao Wang, Xiyuan Wang, Yujunrong Ma, Chen Yuan, Max Xiangjun Fan, Jun Xiao, Jianpeng Cheng
Published: 2026-09-15
Categories: cs.CV
arXiv: https://arxiv.org/abs/2609.16591v1

Traditional multimodal representation learning and generation are two stages: a contrastive or self-supervised visual encoder is trained first, followed by a separate downstream generative model. This setup bottlenecks generative performance behind frozen embeddings. To bridge this gap, we revisit joint multimodal representation learning and generation to produce linearly interpolatable embeddings that are directly consumable by generative decoders. We present FLAT (Flexible-Length Aligned Transmodal representations), a representation pre-training framework that jointly optimizes a shared multimodal encoder alongside downstream text-to-image (T2I) and image-to-text (I2T) decoders. By combining contrastive alignment with bidirectional cross-modal generative objectives, FLAT ensures its representations function as both discriminative semantic descriptors and generative conditions. Architecturally, FLAT maps visual and textual inputs into a unified continuous 1D sequence space, applying nested dropout over prefix-K tokens to enable dynamic output lengths. A single pre-training stage allows FLAT to perform cross-modal retrieval and generation across variable prefix K, achieving a T2I GenEval score of 71.1. Task-specific fine-tuning aligns model performance with state-of-the-art baselines: 83.1 GenEval on T2I generation; 40.5 BLEU-4 and 138.6 CIDEr on MS-COCO image captioning; and Recall@5 scores of 86.8 (I2T) / 75.8 (T2I) on MS-COCO alongside 98.3 (I2T) / 93.6 (T2I) on Flickr30K. Finally, qualitative evaluations demonstrate that FLAT representations natively support linear interpolation, latent space arithmetic, and zero-shot composed retrieval.

---

### Challenges of Auditing: Variability in Outputs of Large Language Models for Health

Authors: Yuan Pu, Yewon Chang, Furong Jia, Xunjian Yin, Jessica Ma, Ayman Ali, Monica Agrawal
Published: 2026-09-15
Categories: cs.CL
arXiv: https://arxiv.org/abs/2609.16590v1

People increasingly use frontier AI models for health advice, but via different access modes (e.g., ChatGPT, ChatGPT Health, APIs) with varying settings. Here, we find systematic differences across access modes. Because evaluations typically rely on APIs while consumers interact through chatbot interfaces, these discrepancies limit evaluation validity. Our findings underscore an urgent need for model providers to enable faithful replication of consumer experiences and settings for rigorous audits.

---

### Do LLMs Have Values? A Quantitative Analysis and Alignment Framework for Values in Large Language Models

Authors: Keqing Zhang, Jingyu Chen, Yufan Liu, Yongqiang Zhu, Nai Ding, Lai Jiang, Congyan Lang, Bing Li, Weiming Hu
Published: 2026-09-15
Categories: cs.AI
arXiv: https://arxiv.org/abs/2609.16589v1

As Large Language Models (LLMs) increasingly handle complex subjective tasks, aligning their intentions and behaviors with human values has become a critical scientific challenge. However, current efforts are confounded by a striking behavioral paradox: they fluctuate unpredictably under minor wording changes ("swing"), yet stubbornly ignore explicit instructions to correct ingrained biases ("rigidity"). Resolving this duality is critical for reliable AI alignment. To systematically understand and safely steer these latent subjective preferences, our study is structured around three fundamental questions. First, do LLMs possess an intrinsic value system? By projecting responses from 106 LLMs (150,000 queries per model) and 95,000 human survey profiles into a shared sociological space, we empirically confirm that they do. However, they do not mirror human diversity, instead crystallizing into a highly concentrated, idealized value core. Second, how can these values be quantified? We propose the Prior-Environment-Cognition (PEC) framework. This model mathematically defines value expression as the joint outcome of inherent dispositions like parameter weights (Prior), external contexts such as user prompts (Environment), and internal reasoning processes like Chain-of-Thought (Cognition). Finally, how can LLMs' values be aligned toward a desired target? Using PEC diagnostics, we establish an adaptive "Alignment Prescription". Rather than blindly applying resource-intensive training, this method identifies the minimum effective intervention needed for each dimension, ranging from zero-cost prompts to targeted parameter updates. Extensive empirical validation confirms that our approach successfully verifies the presence of LLM values, accurately quantifies their shifts, and achieves more efficient and precise steering than conventional blind training, all without degrading general capabilities.

---

### ProxiDex: Learning Dynamics-Guided Proximity Policy for Dexterous Manipulation

Authors: Yushan Bai, Boyu Zheng, Zhiyang Mao, Hongzheng Sun, Yuchuang Tong, En Li, Zhengtao Zhang
Published: 2026-09-15
Categories: cs.RO, cs.AI
arXiv: https://arxiv.org/abs/2609.16586v1

Multi-finger dexterous manipulation relies on stable hand-object interactions, yet these interactions are partially observable in practice. Visual observations are often occluded by the hand, tactile sensors introduce hardware-specific modalities and calibration burdens, and existing policies rarely model how these cues evolve under actions, making them brittle under contact uncertainty. To address these, we present ProxiDex, a dynamics-guided proximity policy framework that treats hand-object proximity as an interaction state for dexterous manipulation. ProxiDex reconstructs interaction point clouds and converts geometric distances into proximity cues, forming a hardware-agnostic contact representation that provides immersive feedback during VR teleoperation. Built on this representation, ProxiDex learns action-conditioned proximity dynamics with a coupled forward-inverse design: future observation latents are predicted from actions, while proximity variations are decoded from latent changes. Leveraging these dynamics, ProxiDex adaptively reweights proximity tokens across manipulation phases and uses dynamics-consistency supervision to guide policy inference, stabilizing action generation under unreliable visual feedback. Simulation and real-world experiments demonstrate improved success rates and robustness over representative baselines across standard, unseen objects, and perturbation scenarios. Additional visualizations are available at https://proxidex.github.io/.

---

### CLASH: Counterfactual Auditing of Lexical and Prosodic Reliance in Spoken Sarcasm Detection

Authors: Qiyang Sun, Xudong Li, Yupei Li, Jiabin Xue, Yuhang Dai, Jiaming Li, Bjorn W. Schuller
Published: 2026-09-15
Categories: cs.SD, cs.CL
arXiv: https://arxiv.org/abs/2609.16582v1

Spoken sarcasm detectors may exploit lexical content, prosody, or their interaction, yet conventional evaluation cannot reveal which cues drive their predictions. We introduce CLASH (Controlled Lexical-Acoustic Separation Harness), a bilingual counterfactual diagnostic framework that evaluates each utterance under original, lexical-preserving, prosody-preserving, and approximately neutralised conditions. We evaluate handcrafted acoustic-feature systems, self-supervised learning (SSL) probes, and large audio language models (LALMs) on CMMA and MUStARD. For target-only Qwen3-Omni, lexical-preserving speech retains a 0.135--0.148 AUROC advantage over prosody-preserving speech after duration balancing, with cluster-bootstrap intervals above zero; alternative lexical resynthesis preserves this advantage. Acoustic interventions shift scores without consistently improving discrimination or changing binary predictions under the evaluated conditions. Context and interaction estimates vary across corpora. These findings distinguish acoustic sensitivity from sarcasm discrimination while exposing duration, identity, and transformation effects.

---

### Recovering Governing Dynamics from Distributed Observations via Exact Spline Merging

Authors: Naveen Mysore
Published: 2026-09-15
Categories: cs.LG, physics.comp-ph
arXiv: https://arxiv.org/abs/2609.16579v3

Scientific observations are frequently distributed across locations, time periods, and institutions. Combining such observations into a continuous, differentiable field enables recovering governing physical parameters from its derivatives. This paper makes two contributions in this setting. First, the established additive structure of fixed-basis ridge-regression statistics is applied to tensor-product spline fields: each data holder computes a local Gram matrix and moment vector, and the merged solution is mathematically identical to centralized fitting, with no raw data shared and no iterative synchronization. This property is specific to the fixed-feature squared-error setting; the present derivation does not establish an analogous guarantee for general jointly trained multilayer networks. Second, a complete pipeline connects distributed observations to physical parameter inference through field reconstruction, derivative extraction, and linear regression. The pipeline is validated on four PDEs: diffusion, wave, heat-with-source, and the nonlinear viscous Burgers equation, recovering governing parameters to sub-percent accuracy in the linear cases and 5\% for Burgers. In all cases, distributed merging introduces zero degradation relative to centralized fitting. Synthetic experiments validate parameter recovery; application to 41 years of NOAA sea-surface temperature data validates field reconstruction and aggregation equivalence on real spatiotemporal observations. Source code to reproduce all experiments is available at https://github.com/NAVEENMN/splinemerge.

---

### GraLoD: Graphics-Inspired Continuous Level-of-Detail Learning for Image Restoration

Authors: Hu Gao, Lizhuang Ma, Yulong Chen
Published: 2026-09-15
Categories: cs.CV
arXiv: https://arxiv.org/abs/2609.16578v1

The spatial support required for image restoration varies across degradation types, image regions, and reconstruction stages. However, most existing methods rely on predefined multi-scale hierarchies and aggregate features through fixed fusion or attention, leaving the representation scale itself largely determined by the network architecture. This limitation becomes more pronounced when a task-specific backbone is extended to heterogeneous degradations in all-in-one restoration. Inspired by level-of-detail (LOD) rendering in computer graphics, we propose GraLoD, a plug-and-play framework that treats restoration scale as a spatially varying and stage-dependent continuous variable. GraLoD reuses the native encoder hierarchy, aligns its multi-scale features into a shared LOD representation space, and predicts a stage-conditioned LOD field at each decoder stage. Each spatial location then continuously queries only two neighboring representation levels, enabling the effective restoration scale to adapt to both local image content and reconstruction progress. To prevent degenerate or arbitrary scale selection, we further introduce minimal-sufficient footprint calibration (MSFC) together with structure-aware regularization (SAR) to encourage restoration-effective and spatially coherent LOD assignments. GraLoD can be directly integrated into existing restoration backbones without redesigning their fundamental feature-processing blocks. Extensive experiments demonstrate consistent improvements in task-specific and all-in-one restoration.

---

### AsyncCouple-Flow: Asynchronous Cross-Modal Coupling and Flow Matching for Spatio-Temporal Forecasting

Authors: Zhixiang Wu, Yining Liu, Bo Zhao, Szu-Yu Chen, Huiran Duan, Chu Lin, Chuanguang Yang
Published: 2026-09-15
Categories: cs.LG
arXiv: https://arxiv.org/abs/2609.16573v1

Multi-modal spatio-temporal forecasting (MM-STF) supports weather nowcasting, traffic prediction, and earth-system modeling by combining heterogeneous sources such as physical fields, satellite imagery, and in-situ sensors. Three obstacles persist: (i) modalities have different spatio-temporal sampling rates, forcing lossy interpolation onto a unified grid; (ii) modalities are frequently missing at deployment due to sensor outages or revisit gaps, while most methods train with full availability; and (iii) autoregressive decoders accumulate errors over long horizons, amplified by multi-modal conditioning. We propose AsyncCouple-Flow to address these issues jointly. A Modality-Aware Token Sparsification (MATS) module performs scale-aware tokenization and uses a shared importance scorer to select top-k tokens per timestep, producing equal-length sequences. An Asynchronous Cross-Modal Coupling Graph (ACCG) replaces fixed cross-attention with a learnable graph whose edges encode time offsets, semantic similarity, and modality-specific physical priors, enabling fusion under arbitrary asynchrony and missingness. A Flow-Matching Forecasting Head models multi-step prediction as a conditional ODE, trained with stochastic modality dropout and integrated jointly to avoid autoregressive drift. Experiments on ERA5+GOES+ISD weather forecasting and PEMS-BAY traffic prediction with multi-source side information show that AsyncCouple-Flow outperforms state-of-the-art baselines and remains robust with up to two missing modalities. The code will be released upon acceptance.

---

### Efficient Text-to-Image Generation: An Adaptive Step Schedule Controller for Diffusion Models

Authors: Kuluhan Binici, Cihan Acar, Shivam Aggarwal, Siying Liu, Tulika Mitra
Published: 2026-09-15
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2609.16572v1

Text-to-image diffusion models often use a fixed number of denoising steps, balancing time costs and image quality. However, the optimal number of steps depends on the complexity of the input text prompt. We propose an adaptive diffusion controller that dynamically adjusts the number of steps to generate high-quality images efficiently, without additional model training. By leveraging a mixture of step schedules with varying step sizes and evaluating the error term discrepancy at each timestep, our method transitions between schedules to optimize performance. Experiments on COCO and DiffusionDB show that our approach reduces inference time while maintaining visual fidelity, offering a more efficient alternative for text-to-image diffusion models.

---

### Counterfactual Reasoning for Robust Visual Question Answering

Authors: Truong-Binh Duong, Thanh-Ngan Tran, Ngoc-Thao Nguyen, Bac Le
Published: 2026-09-15
Categories: cs.CV
arXiv: https://arxiv.org/abs/2609.16567v1

Modern Visual Question Answering (VQA) models often exploit spurious correlations in training data, leading to poor out-of-distribution (OOD) generalization due to language bias. Although counterfactual learning has shown promise, existing methods can be improved to better guide attention toward causal evidence and strengthen feature discrimination. To address this, we propose a novel training framework that enhances counterfactual contrastive learning for VQA. Our framework introduces three key contributions: (1) a three-stage curriculum for stable multi-objective optimization, (2) an enhanced Batch-Contrastive loss for more discriminative feature learning, and (3) two novel regularizers, Answer-Contrastive (AC) loss to refine the prediction space and Gradient-Discrepancy (GD) loss to enforce causal visual grounding. Our model achieves a competitive accuracy of 61.64% on the bias-sensitive VQA-CP v2 benchmark while maintaining 62.80% on the standard VQA v2 dataset, yielding a small generalization gap of 1.16%. This demonstrates a strong balance between OOD robustness and in-distribution performance.

---

### Vision And Text Transformer For Predicting Answerability On Visual Question Answering

Authors: Tung Le, Huy Tien Nguyen, Le Minh Nguyen
Published: 2026-09-15
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2609.16565v1

Answerability on Visual Question Answering is a novel and attractive task to predict answerable scores between images and questions in multi-modal data. Existing works often utilize a binary mapping from visual question answering systems into Answerability. It does not reflect the essence of this problem. Together with our consideration of Answerability in a regression task, we propose VT-Transformer, which exploits visual and textual features through Transformer architecture. Experimental results on VizWiz 2020 dataset show the effectiveness and robustness of VT-Transformer for Answerability on Visual Question Answering when comparing with competitive baselines.

---

### Query-Aware Source-Risk Triage for Retrieval-Augmented Generation

Authors: Kainan Zhou, Gangzhen Qian, Chuhong Xu, Lu Yi
Published: 2026-09-15
Categories: cs.AI
arXiv: https://arxiv.org/abs/2609.16564v1

Retrieval-augmented generation (RAG) pipelines may omit a source's material relationship to the query. We study a pre-generation triage layer that treats this relationship as query dependent. The method routes canonical query families for enhanced review and assigns retrieved pages to pass, contextualize, exclude, or review. It combines a four-dimension page score, rank-discounted family aggregation, intent-preserving query mutations, and a family-held-out router. A single-coded pilot of 200 real URLs supplies provisional calibration anchors; a 20,000-row scenario with synthetic domain identifiers supports controlled workload analysis. An oracle page gate defines a risk-coverage target for a future learned classifier. The evaluation shows why page-level frequency cannot substitute for family-level exposure and quantifies how calibration changes scenario activation. Annotation reliability remains unmeasured, and synthetic rankings omit real retrieval dynamics. The result is an auditable triage method and validation plan, not an estimate of deployed review workload, live-Web prevalence, or downstream answer-quality gains.

---

### The MAL Simulator: Cyber Operations Simulation based on Attack & Defense Graphs

Authors: Jakob Nyberg, Sandor Berglund, Andrei Buhaiu, Joakim Loxdal, Pontus Johnson, Mathias Ekstedt
Published: 2026-09-15
Categories: cs.CR, cs.AI
arXiv: https://arxiv.org/abs/2609.16563v1

We have developed the MAL Simulator, a cyber operation simulator based on the Meta Attack Language (MAL). The MAL Simulator is intended for decision-driven cyber attack and defense simulations, for system analysis and the development of automated agents. By building the simulator around an attack modeling language, it can be adapted to different target domains without modifying the source code. We used the simulator for two case studies where we trained two types of agents for automated cyber operations: a defensive agent and an offensive agent. To ground the experiments, we base the models in data collected from an emulated network implemented in the cyber range CRATE. We found that the trained attacker policy could reach the designated targets more efficiently than the compared search methods, and that the trained defender agent induced lower costs than a naive heuristic agent under noisy alert conditions. When testing the RL attacker against the RL defender, we found that the performance of the defenders dropped significantly. This emphasizes the importance of cyber attack simulators to facilitate training both offensive and defensive agents. The MAL Simulator and associated tooling is publicly available and provides common interfaces for compatibility with existing machine learning frameworks.

---

### PunGraph: Retrieval-Enhanced Phonetic-Semantic Graph Reasoning for Pun Understanding

Authors: Yuchen Su, Zijian Huang, Yaotian Shi, Shaoxin Zhong, Ruofan Wang, Mengze Li, Yonghua Zhu, Diana Benavides-Prado, Michael Witbrock
Published: 2026-09-15
Categories: cs.CL
arXiv: https://arxiv.org/abs/2609.16557v1

Puns are a challenging form of figurative language that exploit phonetic similarity and semantic ambiguity to convey multiple meanings. Although large language models (LLMs) demonstrate strong language understanding capabilities, they still struggle with pun reasoning due to limited phonetic modeling and uncontrolled end-to-end generation. We propose \textbf{PunGraph}, a retrieval-enhanced knowledge graph framework for pun understanding. PunGraph constructs a phonetic-semantic lexical graph using the Unisyn phonetic dictionary, IPA and G2P representations, and WordNet definitions, and retrieves candidate words or senses to constrain LLM reasoning within a structured candidate space. We further introduce \textbf{WebPun}, a new large-scale dataset containing 5,730 annotated heterographic and homographic puns. Experiments on SemEval-2017 and WebPun show that PunGraph consistently improves the performance of small-scale LLMs and achieves competitive results against strong proprietary models. Further analysis shows that retrieval-guided phonetic and semantic constraints effectively reduce common reasoning errors in pun interpretation, highlighting the benefits of integrating structured knowledge with LLMs. We release our code and dataset at https://github.com/ysu132/PunGraph.

---

### Supervising the Chain Ladder

Authors: Stephan Marais, James Grove
Published: 2026-09-15
Categories: stat.ME, stat.ML
arXiv: https://arxiv.org/abs/2609.16552v2

The chain ladder's volume-weighted pattern minimises an explicit loss function, yet is rarely booked as such. Practitioners adjust the pattern and record the final adjusted ratios. This paper treats the chain ladder's pattern selection as a supervised-learning problem. Judgement on pattern adjustments becomes a framework of defined penalties and hyperparameters on the chain ladder's loss function, treated here as an objective function in machine learning. Data weights are generalised with a decay and a power parameter for recency and volume weighting. Benchmark shaping and smoothness enter through a reference penalty and Whittaker-Henderson smoothing. The assembled objective is strictly convex and minimised by a single linear system. Each hyperparameter becomes an interpretable adjustment in its own right, declarable by judgement and categorised as an experience or a prospective adjustment. Experience adjustments can be set more objectively by a proposed training loop and a reserve validation score on held-out calendar diagonals. Further hyperparameter-based adjustments are written as almost-everywhere differentiable penalties that re-time or reshape the pattern. A worked example carries one real Schedule P triangle through an incurred and then a paid training stage, demonstrating the workflow.

---

### Which Pretext Task Transfers? Self-Supervised Pretraining Objectives for Lung Ultrasound

Authors: Moein Heidari, Junbo Rao, Jai Choraria, Wenjin Chen, David J. Foran, Ilker Hacihaliloglu
Published: 2026-09-15
Categories: cs.CV
arXiv: https://arxiv.org/abs/2609.16551v1

Self-supervised learning (SSL) can reduce the need for labelled medical images, but the choice of pretext objective remains unclear for lung ultrasound (LUS). Contrastive learning, masked reconstruction, and joint-embedding predictive architectures (JEPA) differ in the space in which their targets are defined, yet existing ultrasound studies compare them under different corpora, backbones, and evaluation protocols. We compare these three objective families using the same encoder backbone, pretraining corpus, optimisation schedule, and frozen-evaluation protocol. Encoders are pretrained on COVID-BLUeS LUS videos and evaluated with linear, $k$NN, and attentive probes at 5\%, 10\%, 50\%, and 100\% label budgets. Evaluation is performed on POCUS using patient-level five-fold cross-validation and on the independently acquired Mendeley-Uganda dataset, which is excluded from both pretraining and probe fitting. At the full label budget under linear probing, VideoMAE and V-JEPA achieve $66.5 \pm 13.1$ and $65.4 \pm 11.7$ balanced accuracy on POCUS, while MoCo achieves $42.1 \pm 1.2$. On Mendeley-Uganda, the ranking reverses: MoCo performs best at $62.7 \pm 1.0$, followed by VideoMAE at $53.8 \pm 2.8$, while V-JEPA falls near chance at $35.1 \pm 4.9$. These results show that POCUS probe accuracy alone does not identify the objective that transfers best across datasets. We also outline planned representation-level analyses to examine this reversal. Code is publicly available at https://github.com/moeinheidari7829/LUSVideoSSL.

---

### QueryFormer: Winning Solution for KDD Cup 2026 Tencent UniRec Challenge

Authors: Yuanzhe Zhou, Zhaoyang Zeng
Published: 2026-09-15
Categories: cs.AI
arXiv: https://arxiv.org/abs/2609.16548v1

Post-click conversion rate (pCVR) prediction requires jointly modeling feature interactions and sequential user behaviors. The KDD Cup 2026 Tencent UniRec Challenge calls for a unified architecture addressing both. We observe that existing unified architectures often generate query tokens---the central information hub---with projection-based multi-layer perceptrons (MLPs), without explicit token-to-query attention for refining the query side. We propose QueryFormer, centered on a stackable unified field--sequence block that bridges non-sequential multi-field features and behavioral sequences, and provide a latency-aware scaling study over view width $H$, model width, depth, data, and compute. The block generates queries through cross-attention and packs sequence queries into shared-parameter attention. QueryFormer secured 1st place in the Industrial Track, achieving an official test area under the ROC curve (AUC) of 0.83254; a modest post-competition scale-up reached 0.832713. Within our grid, $H$-scaling improves validation AUC from 0.84540 to 0.84615 and beats HyFormer at comparable budgets. Ablation identifies query generation as the largest contributor. Packed shared-parameter cross-attention keeps H=8 inference latency to only 1.89x that of H=1, positioning the bridge as an efficient stackable unified block.

---

### A Cyber Range Evaluation of Autonomous Network Incident Response Agents

Authors: Jakob Nyberg, Teodor Sommestad, Andrei Buhaiu, Joakim Loxdal, Pontus Johnson, Mathias Ekstedt
Published: 2026-09-15
Categories: cs.CR, cs.AI
arXiv: https://arxiv.org/abs/2609.16541v1

We test the performance of agents for automated network intrusion response in a cyber range intended for human operator training. The range implements an emulated networking environment with a variable network topology, red-team emulation and simulated user agents. The goal of the defensive agents is to prevent hosts in the network from being accessed by the red-team agent, while minimizing the availability costs induced from defensive measures. Alerts are generated using a SIEM platform and mapped to a data modeling language used by the agents. We test a combination of heuristic agents and policies learned using reinforcement learning. The learned policies are optimized to minimize the combined cost using a cyber attack simulator modeling the network. We found that the reinforcement learning agents were overall more efficient at defending the system than the heuristic policy, and that the performance depends highly on the policy of the adversary in combination with the simulated users.

---

### On the Importance of Gating: Memorization vs. In-Context Learning in State Space Models

Authors: William L. Tong, Aryo Lotfi, Emmanuel Abbe, Kostas Vaggelakos, Vishnu Banna, Etai Littwin, Josh Susskind, Cengiz Pehlevan, Eran Malach
Published: 2026-09-15
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2609.16540v1

State Space Models (SSMs) have emerged as a compelling alternative to Transformers, enabling sequence modeling with constant memory and linear compute. Although SSMs exhibit reasonable performance and favorable computational characteristics, they continue to lag behind Transformers on tasks that require in-context learning and precise retrieval, slowing their adoption for large-scale language modeling. In this work, we demonstrate that both the success and failure of SSMs in these domains can be explained by studying the role of the gating mechanism, a prevalent component in modern recurrent networks. Specifically, we show through theory and experiments that this gating mechanism causes SSMs to first learn an in-weights "memorization" solution, while delaying, or even preventing, convergence to a correct in-context learning solution. Importantly, this happens even in cases where there are no fundamental limitations due to the architecture or its memory capacity. On the other hand, we find that gating is often beneficial for improving generalization to long sequence lengths. Our results illuminate the crucial role of the gating mechanism in shaping both the training dynamics and generalization of SSMs, and provide a basis for understanding and improving linear-time models.

---

### What Does Layer-Importance Reveal About Transformers and State-Space Models?

Authors: Istabrak Abbes, Nizar Islah, Irina Rish, Sarath Chandar
Published: 2026-09-15
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2609.16537v1

Transformers and state-space models (SSMs) are the two dominant families of sequence models, and a central open question is how far the analytical knowledge built for transformers transfers to SSMs. We address this through the lens of layer importance which underpins compression, selective fine-tuning, and interpretability across both families. We decompose layer importance into two distinct notions. \emph{Necessity} captures how much the pretrained model depends on a layer's existing contribution, measured by the loss increase from bypassing it. \emph{Plasticity} captures where the model absorbs new information during fine-tuning, measured by the magnitude of task-specific weight updates. Our analysis reveals that the two families behave fundamentally differently: in every evaluated residual transformer up to $14$B parameters, Necessity and Plasticity anti-align across depth, whereas in the evaluated Mamba-style SSMs they point to overlapping regions. The sign of this alignment also predicts downstream adaptation behavior. In the evaluated transformers, concentrating updates in the most plastic layers increases catastrophic forgetting, while this tier-dependent effect disappears in the evaluated Mamba-style SSMs.

---

### Style-Debiased DPO: Updating LLM Knowledge with Factuality-Aware Synthetic Preference Data

Authors: Takayuki Yamamoto, Daisuke Kawahara
Published: 2026-09-15
Categories: cs.CL
arXiv: https://arxiv.org/abs/2609.16532v1

Continued pretraining (CPT) with data augmentation such as paraphrasing can store inside a large language model (LLM) the knowledge of a small source corpus. The stored knowledge, however, is not always retrieved correctly. We study the eliciting side rather than the storing side: we use preference optimization, which learns from pairs of a preferred (chosen) and a dispreferred (rejected) response, so that the model elicits its stored knowledge more accurately. One proposed approach takes the model's own erroneous response as rejected and the gold answer as chosen, so as to suppress the error. When the target knowledge is partially known, however, most of these rejected responses are factually correct. Using direct preference optimization (DPO) then pushes down rejected responses that contain correct knowledge and differ from the chosen answer only in style, such as length and wording. We propose style-debiased DPO (SD-DPO), which scores whether the rejected response of each pair is factually correct, inverts the preference of such pairs, and weights them so that the learning signal due to differences in style cancels out as a whole. We first test whether, on top of EntiGraph, a representative storing-side method that runs CPT on text synthesized from the corpus, our method adds accuracy efficiently. On QuALITY, the reading-comprehension QA benchmark on which EntiGraph was evaluated, SD-DPO exceeds a baseline we CPT on EntiGraph's synthetic data from the same base model and evaluate with the same procedure. The training tokens this requires are a few dozen times fewer than the additional CPT needed for the same gain. For knowledge updating, the main goal of this work, we use AToKE, a knowledge-editing benchmark for facts that change over time. There, SD-DPO reaches an overall accuracy of 0.982 and answers with the new or the old fact according to the queried period.

---

### FlowATC: Aircraft Trajectory Prediction via Flow Matching

Authors: Mathurin Petit, Emir Torun, Louis Brusset, Jordan Kam, Alexandre M. Bayen
Published: 2026-09-15
Categories: cs.LG
arXiv: https://arxiv.org/abs/2609.16528v1

Building accurate decision-support tools for next-generation air traffic control requires robust trajectory prediction models. We present a flow-matching architecture trained exclusively on historical aircraft trajectories, with no route labels or chart supervision. Trained on 1.15 million Automatic Dependent Surveillance-Broadcast trajectory windows collected over the San Francisco Bay Area, the model generates aircraft trajectory distributions that closely match historical traffic, reproducing known airspace structure around San Francisco Airport such as the shape of SFO's published NIITE FOUR departure procedure. Our model is trained directly on the native, irregular ADS-B sampling interval. Trajectory prediction is cast as sequence inpainting using a block-causal Transformer that denoises future state tokens conditioned on the observed history using Conditional Flow Matching or Denoising Diffusion Probabilistic Models. We compare our architecture against constant-velocity, deterministic-Long Short Term Memory, and Conditional Variational Autoencoders baselines. At matched parameter count, CFM outperforms DDPM by 11-26% in minADE@20, and both generative objectives surpass the CVAE baseline by 31-41%. We further show that the error degrades gracefully with prediction horizon, and the architecture remains effective when retrained on temporally decimated feeds. Lastly, we sample $K$ independent completions, yielding spatial probabilistic occupancy estimates that can serve as input to downstream conflict-risk estimation.

---

### QALPA: Property-guided diffusion modeling for efficient exploration of chemical spaces of flexible molecules

Authors: Michael Hanna, Julian Cremer, Zekiye Erarslan, Leonardo Medrano Sandonas
Published: 2026-09-15
Categories: physics.chem-ph, cs.AI
arXiv: https://arxiv.org/abs/2609.16527v1

Exploring the chemical space of flexible molecules remains challenging because the vast number of possible compounds and conformations, together with the increasing cost and limited generalization of 3D generative models for larger and more complex molecules, restrict access to unexplored chemistry. Here, we introduce QALPA ("Quantum-Aware Learning for Property-space Augmentation"), a property-guided generative framework that combines an E(3)-equivariant diffusion model with active learning and efficient quantum-mechanical (QM) methods to iteratively explore targeted QM property manifolds. By coupling generation with physics-based evaluation, QALPA improves molecular sampling and model reliability in sparsely populated regions of chemical space. Our results show that training on complementary QM datasets spanning both small (QM7-X) and large (Aquamarine) drug-like compounds enables accurate molecular generation across a broad size range, improving transferability beyond the training distribution for complex property manifolds involving both extensive and intensive properties. As a proof of concept, QALPA coupled with the machine learning-augmented tight-binding method EquiDTB efficiently augments alloQM, a QM dataset introduced in this work, comprising 6,253 conformers of allosteric drug molecules, by populating sparse regions of the property landscape defined by the many-body dispersion energy and HOMO-LUMO energy gap. These results demonstrate that the integration of generative AI with efficient ML/QM methods offers a practical pathway toward augmenting sparse QM datasets and sustainably expanding the exploration of chemical space for molecular discovery.

---

### AquiLLM: Evaluating Faithfulness in Open-Weight RAG-LLM Systems for Scientific Research

Authors: Bernie Boscoe, Srinath Saikrishnan, Vikram Seenivasan, Jack Stark, Andrew Lizarraga, Morgan Himes, Jonathan Soriano, PJ Allen, Tuan Do
Published: 2026-09-15
Categories: cs.AI
arXiv: https://arxiv.org/abs/2609.16519v3

Scientific research increasingly relies on large, heterogeneous data sources, motivating interest in retrieval-augmented generation (RAG) systems that provide natural language access to scientific knowledge and research workflows. Researchers are exploring the viability of these systems as natural language interfaces for document search and for generating analysis code and pipeline components. At the same time, concerns about data privacy and control over research infrastructure have motivated interest in open-weight models and open-source deployments hosted within research institutions. In astronomy, this development follows a long history of computational infrastructure development, from archival databases and Structured Query Language (SQL)-based systems to large language model (LLM)-assisted research tools. This paper presents a domain-expert evaluation of faithfulness for AquiLLM, an open-weight, offline RAG-LLM platform designed to support scientific research groups in the use and preservation of tacit and formal knowledge. We define faithfulness as the extent to which generated responses remain grounded in retrieved scientific context without unsupported claims or omissions. We report results from an astronomy case study evaluating AquiLLM across retrieval and scientific analysis tasks. AquiLLM performs most reliably on explicit retrieval-oriented questions grounded in the RAG collection, while faithfulness degrades for queries requiring synthesis or ambiguity resolution. These results highlight both the promise and limitations of open-weight RAG-LLM systems for scientific research and demonstrate the importance of domain-expert evaluation beyond standard benchmark leaderboards.

---

### Competence-Preserving Resume Perturbations Expose Presentation Sensitivity in LLM Screening

Authors: Qiangju Chen, Yang Xiao
Published: 2026-09-15
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2609.16517v1

Resume screeners must infer job-relevant competence from resumes whose presentation can vary substantially in wording, structure, stylistic polish, and document extraction quality. Ideally, such surface variation should not change decisions when the underlying qualification evidence is unchanged. We introduce a controlled audit of this property, constructing occupation-grounded candidate profiles at controlled competence levels and rendering each profile into multiple resume presentations. A deterministic validation gate excludes variants that alter the underlying evidence before scoring. Across six open instruction-tuned LLM conditions, we find a clear disconnect between screening validity and presentation stability. Llama-3.1-8B with its native chat template achieves the strongest validity ($0.781$) yet reverses $29.6\%$ of matched pairwise decisions under competence-preserving presentation changes; Mistral-7B-v0.3 reaches validity $0.644$ with a $41.4\%$ flip rate. Native chat formatting improves validity for several chat-tuned models but does not remove this instability. These results show that resume-screening evaluations should assess not only whether a system identifies stronger candidates, but also whether those decisions remain stable when the same competence evidence is presented differently.

---

### Causal Path Analysis from Perturbational and Population-Scale Single-Cell Data with Multiscale Confounding and Measurement Error

Authors: Kwangmoon Park, Hongzhe Li
Published: 2026-09-15
Categories: stat.ME, stat.AP, stat.ML
arXiv: https://arxiv.org/abs/2609.16510v1

Single-cell perturbation experiments provide causal information on gene regulation, whereas population-scale single-cell studies characterize gene expression and phenotypes in human populations. We develop a framework that integrates these complementary data sources for causal path analysis. Rather than assuming that a perturbational gene network transfers directly to the target population, we use externally learned ancestral relationships to constrain the network topology and re-estimate its direct edges and effects from population data. To address latent heterogeneity and measurement error in multiscale single-cell measurements, we develop a surrogate-variable procedure operating at both the cell and subject levels, combined with errors-in-variables correction for network and outcome regressions. We establish theoretical guarantees for confounder recovery and high-dimensional estimation of network and gene-outcome effects. Simulations demonstrate the importance of jointly correcting confounding and measurement error. An application to acute myeloid leukemia identifies distinct regulatory pathways linking transcriptional regulators to blast count.

---

### Beyond the Name: Demographic Leakage in De-Identified Résumés and Evaluation Artifacts in LLM Bias Audits

Authors: Qiangju Chen, Yang Xiao
Published: 2026-09-15
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2609.16501v1

De-identified résumé screening assumes that redacting explicit fields prevents ethnocultural inference; however, recent audits attribute residual leakage to declared languages. We investigate whether eliminating language fields resolves this leakage across nine open-weight models and 620 counterfactual résumés. By holding language attributes strictly identical, we isolate unstructured prose across five ethnocultural conditions and three cue-salience tiers. Target-group recovery averages 0.757 overall and saturates at 1.000 under high salience, demonstrating that non-language prose sustains demographic inference. Crucially, models diverge only under faint cues (0.086-0.690), establishing salience as an essential evaluation axis. Furthermore, pairwise LLM-as-a-judge outcomes are highly sensitive to evaluation design: forbidding ties yields an apparent selection-rate ratio of 0.39 alongside strong position and content effects, whereas permitting ties produces near-universal ties for most models ($\ge94\%$). Downstream scoring shows only very small between-condition differences, highlighting the need to distinguish demographic signals recoverable from résumé content from effects introduced by the evaluation protocol.

---

### High-Performance Tensor Formulation of the Viterbi Algorithm for Hidden Semi-Markov Models

Authors: Lorenzo Piarulli, Elia Belli, Daniele De Sensi
Published: 2026-09-15
Categories: cs.LG, cs.DC, cs.DS
arXiv: https://arxiv.org/abs/2609.16500v1

Hidden Semi-Markov Models (HSMMs) are fundamental probabilistic models widely adopted across diverse domains, from computational biology to finance and signal processing. The Viterbi algorithm decodes the most likely state sequence given an HSMM and can be applied iteratively for ab initio model learning. However, existing Viterbi implementations remain sequential, and GPU-accelerated solutions are entirely absent, making HSMM decoding impractical for large-scale workloads. We present a tensor-based formulation of the Viterbi algorithm for HSMMs, restructuring the inner loops into tensor operations that naturally map onto SIMD units and massively parallel architectures. Building on this formulation, we provide optimized implementations spanning single- and multi-core CPUs, and, for the first time, GPU. Experimental evaluation demonstrates speedups of up to 14x on a single core, over 200x with multi-core, and over 570x on GPU over the state-of-the-art sequential baseline, establishing a new performance baseline for large-scale HSMM decoding.

---

### Geospatial Metadata Improves Discoverability by Connecting Datasets Across Scientific Disciplines

Authors: Daniel Ebanks, Devika Jain
Published: 2026-09-15
Categories: cs.DL, cs.AI
arXiv: https://arxiv.org/abs/2609.16498v2

Research data repositories are essential infrastructure for scientific inquiry and for ensuring that datasets follow FAIR (Findable, Accessible, Interoperable, and Reusable) principles. However, repository reuse depends on the quality and completeness of geospatial and thematic metadata, which researchers generally provide voluntarily. Given limited curation resources, it is unsurprising that even Harvard Dataverse, the world's largest general-purpose research repository, contains many incomplete metadata records. Missing fields represent lost information and reduce interoperability. We find that datasets with more missing metadata receive fewer downstream citations and have fewer resolvable connections to other datasets. The implications are particularly important for geospatial datasets: only 0.3% of research datasets include a bounding box, and most represent archival points rather than complete geographic shapes. Our analysis shows that geospatial metadata helps connect concepts across disciplines. After embedding Harvard Dataverse datasets in a metadata knowledge graph, we find that datasets are twice as likely to connect across scientific disciplines through shared geospatial metadata as through keywords. This suggests that geographic metadata is a more reliable basis for cross-disciplinary interoperability than keyword vocabularies, which often remain discipline-specific. We train and fine-tune a small language model using datasets from Harvard Dataverse. Through geospatial metadata enrichment, we increase the share of datasets from different disciplines connected through metadata elements from 58.5% to 63.2%.

---

### AI Policies: Help or Hindrance? A Software Developer's Perspective

Authors: Samuel Ferino, Rashina Hoda, John Grundy, Christoph Treude, Hashini Gunatilake
Published: 2026-09-15
Categories: cs.SE, cs.AI
arXiv: https://arxiv.org/abs/2609.16496v1

AI policies introduced by software organisations to mitigate LLM-related risks such as sensitive information leaks and unauthorised usage are not useful if software developers do not engage with them. We draw on 19 software developer interviews to show how AI policies help and hinder developers. We suggest approaches to support managers and decision makers with a developer-centric approach to introducing AI policies.

---

### From Manual Construction to AI-Driven Scenario Emergence: Rethinking Catastrophe Risk Modeling

Authors: Hang Gao
Published: 2026-09-15
Categories: cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2609.16493v1

Traditional catastrophe (CAT) risk models rely on costly manual construction to generate extreme weather scenarios, an approach largely unchanged since the 1990s. As climate extremes intensify, this creates mounting challenges to the entire risk transfer chain. This study proposes the TAISE framework, which repurposes AI weather forecasting models to produce coherent extreme weather sequences at a fraction of traditional costs. Through self-iterative generation, the framework produces continuous global atmospheric fields from which extreme events emerge. A proof-of-concept experiment demonstrates an order-of-magnitude reduction in computational cost compared with conventional methods, while capturing temporal continuity and cross-regional correlations absent in snapshot-based approaches. These findings suggest a pathway toward democratising catastrophe risk quantification and enabling dynamic, comprehensive portfolio assessment for insurers, reinsurers, ILS fund managers and public-sector risk managers.

---

### Decoder Design Matters for ECG Delineation

Authors: Joseph Scharpf, William Han, Chaojing Duan, Michael A. Rosenberg, Emerson Liu, Ding Zhao
Published: 2026-09-15
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2609.16489v1

Electrocardiogram (ECG) delineation identifies the boundaries of P waves, QRS complexes, and T waves, providing structural annotations that can guide AI models in learning to interpret ECGs. However, training accurate delineation models requires manual annotations that are scarce and time-consuming to obtain. Recent work addresses this limitation through semi-supervised learning (SSL), but the design of the architecture, particularly the decoder, has received less attention. To this end, we propose R-U-Net, an ECG delineation model that pairs a ResNet-18 encoder with a U-Net decoder. On SemiSegECG, R-U-Net outperforms the strongest evaluated ResNet-18 + fully convolutional network (FCN) head baseline in each of the 16 in-domain settings by 3.3-13.0 mIoU and achieves 82.6 mIoU in the cross-domain setting, an improvement of 8.1 mIoU. Controlled ablations show that decoder design contributes more to performance gains than the evaluated SSL methods, motivating further exploration of architectures for ECG delineation. All code is open-source at github.com/ELM-Research/ECG-Delineation.

---

### Skill-based Agentic Evaluation for Real-time Data Science Tasks

Authors: Aniruddha Tamhane, Raghavendra Addanki, Ayushi Aggarwal, Aditya Bansal, Rui Wang, Charles Menguy, Swati Jain
Published: 2026-09-15
Categories: cs.AI, cs.LG, cs.MA
arXiv: https://arxiv.org/abs/2609.16487v1

We present a framework for evaluating data-science agents on live, continuously updated data using executable ground truth and format-agnostic factoid scoring. Consider this example query: "what were last week's audience sizes"---the reference answer changes as the underlying data changes, so static references become outdated and standard LLM-as-a-judge pipelines cannot verify responses against a fixed ground truth. Our central contribution, ground-truth-as-code, encodes each expected answer as an executable reference function that recomputes the answer directly from live data at evaluation time, ensuring the reference remains consistent with the system it describes. We combine this with a factoid-level, format-agnostic judge that decomposes both the agent's response and the computed ground truth into atomic claims and scores precision, recall, and accuracy over them, irrespective of the response format (prose, list, table, HTML, etc.). The approach is applicable to agents whose expected outputs can be expressed as executable data computations. We validate the framework through a human--LLM agreement study on an internally developed machine learning skill deployed in production, using a synthetic database constructed to reproduce production schemas and entity relationships. Relative to a natural-language ground-truth baseline, our method achieves a 29% improvement in the Matthews Correlation Coefficient (MCC)---a class-balanced measure of agreement between expert annotators and LLM-as-a-judge predictions---and a 16% reduction in token consumption per test case, while a self-directed baseline lacking explicit ground truth is anti-correlated with human judgment. Agents that perform multi-source data integration and computation over non-stationary data are routinely deployed in industry; we propose ground-truth-as-code as a practical methodology for their evaluation.

---

### VPRef: A Cross-Domain Benchmark for Referring Remote Sensing Image Segmentation

Authors: Quanwei Liu, Tao Huang, Jiaqi Yang, Wei Xiang
Published: 2026-09-15
Categories: cs.CV
arXiv: https://arxiv.org/abs/2609.16486v1

Rapid advancements in vision-language models have propelled Referring Remote Sensing Image Segmentation (RRSIS) to the forefront of Earth observation. However, practical deployments suffer severe performance degradation under a coupled dual-drift paradigm: visual domain drift from cross-spatial-resolution mismatches and spectral variations, alongside textual logic drift from unconstrained, variable user-input granularities. To mitigate these bottlenecks, this paper establishes the first cross-domain RRSIS benchmark, designated as the Vaihingen-Potsdam Referring (VPRef) dataset, comprising 46,972 language-image-annotation triplets organized into a three-tier linguistic hierarchy. Building upon this benchmark, we develop a tailored parameter-efficient domain adaptation baseline anchored on the Segment Anything Model (SAM3) via Low-Rank Adaptation (LoRA). Our framework counteracts visual distribution discrepancies through pseudo-label-driven self-training and addresses textual logic drift via random multi-granularity text prompt mixing. Crucially, the distribution of empirical metrics across ablative variants suggests a potential decoupling between cross-modal semantic robustification and visual domain alignment, demonstrating that linguistic variance drives fine-grained semantic invariance while pseudo-label propagation governs macro-scale spatial grid alignment. Extensive benchmarks demonstrate the proposed framework achieves superior cross-domain segmentation boundaries while modifying merely 1.08\% of the foundational parameter footprint, establishing a robust baseline for future multi-modal remote sensing domain adaptation research. The dataset and code will be available at https://github.com/quanweiliu/VPRef.

---

### Certified Inference and Training for Deep Equilibrium Networks: A Continuation Framework with Polynomial Complexity Guarantees

Authors: Alex Borisevich
Published: 2026-09-15
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2609.16485v2

We develop a certified continuation framework for inference and training in deep equilibrium networks (DEQs), with training posed as interpolation to accuracy $2^{-b}$. For inference, input homotopy selects an equilibrium branch from a supplied start root, and a rounded tracker follows it under quantitative conditioning, derivative, boundary, and tube-radius certificates. The framework includes structured factorized certificates, sequential block elimination, inheritance of contraction guarantees in adapted coordinates, and bordered continuation through simple folds. For smooth multidimensional DEQs, including tanh networks, rational local tests can construct and validate oriented continuation charts under explicit geometric promises. For training, programmable dormant bilinear rank-one channels provide output-preserving residual-aligned repairs. Loaded Tikhonov solves diagnose insufficient parameter-to-output directions, while certified gate realization, column stability, well-posed inference, and finite-update error budgets control each pass. Under polynomially bounded certificate, encoding, precision, and backend costs, both inference and training have bit complexity $O(\mathrm{poly}(L+b))$, where $L$ is the encoded instance length; training uses $O(b+\ell)$ passes and reserve channels from an initial residual bounded by $2^\ell$. A budgeted implementation returns either certified success or inconclusive termination. The quantitative core and local certificate machinery are machine-checked in Lean 4, while numerical experiments illustrate the training mechanism.

---

### MDN-Control: Mask-Depth-Noise Guided Region Control for Multi-Subject Video Editing

Authors: Jiayi Yu, Xi Ye, Lina Wang, Yunkun Xia
Published: 2026-09-15
Categories: cs.CV
arXiv: https://arxiv.org/abs/2609.16475v1

Multi subject video editing modifies designated subjects while preserving non target content, but faces cross subject attribute leakage, and occlusion ambiguity. Existing approaches rely on masks and struggle to distinguish overlapping subjects or ensure consistent generation. To address these limitations, we propose MDN-Control, a training free framework jointly controlling target localization, occlusion geometry, and appearance initialization. Specifically, mask-guided localization provides consistent target localization, while depth-aware occlusion control resolves ambiguous boundaries between overlapping subjects. We further introduce noise latent prompting, which retrieves Gaussian initializations from a noise library for prompt relevant priors. Experiments on MSVBench show that MDN-Control achieves the lowest CM-Err and the highest Q-Edit, while maintaining competitive text alignment and temporal consistency, demonstrating the effectiveness of combining spatial, geometric, and latent priors for multi subject video editing.

---

### Online Gradient Computation for Warping Gaussian Process Transformations

Authors: Emilio Ruiz-Moreno, Konstantinos Slavakis, Baltasar Beferull-Lozano
Published: 2026-09-15
Categories: cs.LG, eess.SP
arXiv: https://arxiv.org/abs/2609.16472v1

Warped Gaussian processes (GPs) handle non-Gaussian observations by mapping them into a latent standard GP via a parametric transformation called warping. Existing streaming variants, however, either optimize the warping parameters periodically or sacrifice analytical tractability for a higher model capacity. To bridge this gap, we show that the gradient of the instantaneous negative log-likelihood of a warped GP admits an exact recursive computation. Based on this result, we propose a novel online method for warped GPs that jointly updates the latent GP moments and optimizes the warping parameters.

---

### HairCS: Reconstructing Strand-Based Hair from Hair Cards

Authors: Zixuan Lu, Tongtong Wang, Yuefan Shen, Zhongtian Zheng, Chenfanfu Jiang, Yin Yang, Kui Wu
Published: 2026-09-15
Categories: cs.GR, cs.CV
arXiv: https://arxiv.org/abs/2609.16465v1

We present an automated pipeline that converts hair-card models into high-quality strand-based hairstyles. Given a collection of textured triangular or quad strips as input, our method produces a strand-based representation that preserves the original hairstyle while enriching it with fine-scale geometric detail and adhering to standard production requirements: strands originate from the scalp, roots are uniformly distributed, and the hair volume is plausibly filled. The resulting assets are directly compatible with strand-based rendering, physics-based simulation, and common grooming modifiers (e.g., clumping, curling, noise) for enhanced realism and artistic control. We validate our approach on a large and diverse set of hairstyles, including short and long hair, curly styles, and complex styles such as buns and ponytails.

---