# Research Papers — 2026-09 · bundle page 142 of 266 > Full-text markdown of papers #7051–7100 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/142 [← Previous bundle](https://aipod.dev/papers/archive/2026-09/page/141.md) [Next bundle →](https://aipod.dev/papers/archive/2026-09/page/143.md) ### An Event Preserving Velocity Invariant Representation for Event Cameras Authors: Mikihiro Ikura, Luna Gava, Jiahang Wu, Chiara Bartolozzi, Arren Glover Published: 2026-09-17 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.19973v1 Event cameras provide low-latency, high temporal resolution perception for real-time vision tasks such as robotics.The novel circuitry (i.e. asynchronous, independent pixels) that enables these advantages also introduces new algorithmic challenges. Velocity-invariant representations alleviate missing observations under slow motion and motion blur under fast motion, but most discard temporal information by converting events into image-like representations. We propose Set of Centre Active Receptive Fields (SCARF), a real-time velocity-invariant representation that preserves raw events while consistently handling fast motion, stationary scenes, and independently moving objects. SCARF achieves state-of-the-art performance in both computational efficiency and representation quality. --- ### Efficiently Distributed Federated Learning Authors: Gianluca Mittone, Robert Birke, Marco Aldinucci Published: 2026-09-17 Categories: cs.PF, cs.AI, cs.DC arXiv: https://arxiv.org/abs/2609.19972v1 Federated Learning (FL) is experiencing a substantial research interest, with many frameworks being developed to allow practitioners to build federations easily and quickly. Most of these efforts do not consider two main aspects that are key to Machine Learning (ML) software: customizability and performance. This research addresses these issues by implementing an open-source FL framework named FastFederatedLearning (FFL). FFL is implemented in C/C++, focusing on code performance, and allows the user to specify any communication graph between clients and servers involved in the federation, ensuring customizability. FFL is tested against Intel OpenFL, achieving consistent speedups over different computational platforms (x86-64, ARM-v8, RISC-V), ranging from 2.5x and 3.69x. We aim to wrap FFL with a Python interface to ease its use and implement a middleware for different communication backends to be used. We aim to build dynamic federations in which relations between clients and servers are not static, giving life to an environment where federations can be seen as long-time evolving structures and exploited as services. --- ### CellRFT: Reinforcement Fine-Tuning for Single-Cell Perturbation Modeling Authors: Jie Yan, Li Liu, Hanze Guo, Jiaxin Hu, Houxin He, Xiaoning Qi, Haoran Wang, Cong Li, Zhong-Yuan Zhang, Yong Wang Published: 2026-09-17 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.19970v1 Predicting cellular responses to perturbations supports the study of gene function, disease mechanisms, and therapeutic strategies. Despite advances in single-cell perturbation modeling, existing models typically optimize surrogate losses that do not directly reflect the biological criteria used for evaluation, so better data fitting need not yield better biological predictions. To address this mismatch, we introduce \textbf{CellRFT}, a reinforcement fine-tuning framework that uses biological evaluation as direct training feedback. CellRFT uses policy-gradient optimization to learn from non-differentiable evaluations of generated cell populations and integrates multiple biological rewards through hierarchical reward aggregation. Comprehensive experiments demonstrate CellRFT's applicability across different pretrained models and effectiveness in improving perturbation prediction, reveal that optimizing one biological criterion can help or hinder others, and show that complementary rewards can improve criteria beyond those directly optimized, offering a way to probe how biological metrics shape model behavior, with the potential to inform evaluation design. Code will be made available. --- ### DeepSeek-V4.1-Flash: Pushing the Limits of KV Cache Compression Authors: DeepSeek-AI, :, Anyi Xu, B. Li, Bangcai Lin, Bing Xue, BingCheng Xian, Bingzheng Xu, Bochao Wu, Bowei Zhang, Boyi Deng, C. C. Yu et al. Published: 2026-09-17 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.19969v1 The widespread adoption of long-horizon agents has made model workloads increasingly input-heavy. Although prior work has substantially reduced the cost of long-context computation, prefill remains computationally expensive, and large KV caches continue to strain HBM and SSD capacity and data-transfer bandwidth. Together, these compute, storage, and bandwidth demands constitute the primary bottleneck to further lowering deployment costs. To address this challenge, we introduce DeepSeek-V4.1-Flash, a multimodal Mixture-of-Experts (MoE) model with 552B backbone parameters and support for contexts of up to one million tokens. With its Causal Encoder-Decoder (CED) architecture, the model activates 16B parameters per token during decode but only 8B parameters during prefill, substantially improving cost efficiency for agentic workloads. To push the limits of KV cache compression, DeepSeek-V4.1-Flash combines cross-layer KV cache reuse in Compressed Sparse Attention 2 (CSA2) with FP4 KV caching. These designs reduce its global KV cache footprint (always in HBM) to 890 bytes per token, roughly 1/4 of the corresponding footprint of DeepSeek-V4-Flash. Further, through a dedicated deployment optimization known as SWA Bounded Replay, DeepSeek-V4.1-Flash reduces its persistent KV cache footprint (always on SSD or in host memory) to roughly 1/8 of that of DeepSeek-V4-Flash. Despite its much smaller KV cache footprint, the model delivers substantially better performance than the baseline. In addition, we streamline the DeepSeek-V4 architecture and introduce several efficient architectural extensions. We pretrain DeepSeek-V4.1-Flash on a multimodal corpus comprising 45T tokens and conduct comprehensive post-training, yielding strong performance across diverse text-based and multimodal agentic scenarios. Model checkpoints are available at https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash. --- ### Beyond the Foreground: FOV-Aware Polyp Image Synthesis via Lesion-Guided Adaptive Mucosal Context Propagation Authors: Tong Wang, Yuting He, Bin Ren, Yutong Xie, Guanyu Yang Published: 2026-09-17 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.19966v1 Synthetic image and mask pairs can alleviate scarce colonoscopy annotations, but realistic synthesis requires preserving the supplied lesion while generating compatible mucosa. Existing foreground-guided methods treat all non-foreground pixels as background and rely mainly on local integration. Directly applying them to colonoscopy causes two problems: non-mucosal black regions contaminate generated tissue, and local reasoning produces inconsistent mucosal texture and illumination. We propose LAMP, the first foreground-guided framework for polyp image synthesis based on lesion-guided adaptive mucosal context propagation. LAMP explicitly separates the lesion, valid mucosa, and camera exterior using a field-of-view (FOV) mask. Lesion-to-Mucosa cross-attention extracts lesion appearance conditions for valid-mucosa locations, while FOV-constrained multidirectional Vision Receptance Weighted Key Value propagates them over legal tissue support. An adaptive gate then controls their residual fusion into the diffusion U-Net. Extensive experiments on five polyp datasets demonstrate that LAMP substantially outperforms existing methods in overall generation quality and consistently improves five downstream segmentation models. Our code will be released at https://github.com/wangtong627/LAMP. --- ### Before the Arrest: Benchmarking LLMs on Criminal Profiling from Incomplete Evidence Authors: Yutong Yao, Yanjie Cao, Guanhua Chen, Xu Yang, Junchao Wu, Zeyu Wu, Lidia S. Chao, Derek F. Wong Published: 2026-09-17 Categories: cs.CL, cs.CY arXiv: https://arxiv.org/abs/2609.19965v1 Large Language Models (LLMs) are increasingly applied to legal and criminal justice tasks, yet existing work focuses almost exclusively on post-arrest scenarios where the suspect's identity is already known, leaving the critical pre-arrest challenge of inferring suspect characteristics from incomplete evidence largely unexplored. To fill this gap, we introduce the Profiling, Investigation, and Judgment (PIJ), comprising 2,500 real homicide cases from five countries. PIJ evaluates LLMs across three tasks that span the entire criminal investigation pipeline: criminal profiling, which requires abductive reasoning to infer suspect attributes from fragmentary scene evidence, crime process reconstruction, which tests structured information extraction, and sentence prediction, which demands legal deductive reasoning. We evaluate 9 powerful LLMs and find that performance degrades systematically as tasks shift from explicit fact extraction to implicit reasoning over unknown suspect profiles. Categories requiring inferential reasoning, such as motivation and victim-offender relationships, remain the primary bottlenecks. Further analysis reveals substantial gaps between LLMs and human experts, along with pervasive biases in gender, age, and motive attribution. Our findings indicate that pre-arrest inference from incomplete evidence remains an open challenge. --- ### Enhanced Knowledge Distillation for Detection Transformer via Teacher Prediction Refinement Authors: Yitong Xing, Yuhao Cheng, Yanping Li, Yichao Yan Published: 2026-09-17 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.19964v1 Detection Transformers (DETRs) achieve strong performance in object detection but remain challenging to deploy on edge devices due to their high computational cost. Existing DETR distillation methods mainly focus on aligning distillation points, while largely overlooking the quality of the teacher's supervision itself. We observe that due to stage-wise non-monotonic prediction behavior in DETRs, well-localized or correctly classified predictions from earlier stages may degrade in later ones, and some negative predictions become increasingly overconfident. As a result, relying solely on the current stage's predictions yields inaccurate and inconsistent supervision. To address this issue, we propose Teacher Prediction Refinement Distillation (TPRD), a plug-and-play module that refines teacher predictions before distillation by exploiting stage-wise prediction information. TPRD improves supervision quality through Positive Prediction Correction (PPC), which corrects degraded positive predictions by restoring more accurate ones from earlier stages, ensuring reliable localization and classification signals, and Negative Prediction Suppression (NPS) suppresses the influence of overconfident negatives, preventing them from providing misleading supervision to the student. To preserve informative dark knowledge, we further introduce Maximum Dark Knowledge Preservation (MDKP), which selectively refines target-class logits while retaining non-target relations. Extensive experiments on MS COCO and PASCAL VOC demonstrate the effectiveness and robustness of the proposed method. Our code is available at https://github.com/xingyitong1/TPRD. --- ### Exact Regret Frontiers and Externality Scheduling in Centralized Serial-Dictatorship Bandits Authors: Lishang Xu, Guodong Ma, Pengcheng Weng, Zixuan Xia Published: 2026-09-17 Categories: cs.GT, cs.LG, stat.ML arXiv: https://arxiv.org/abs/2609.19963v2 Exploration in centralized serial-dictatorship matching bandits must use complete matchings, so learning one player-arm pair can impose regret on others. We study this externality under a known common priority order and Gaussian rewards with unit variance. We show that the matching-level Graves-Lai constraints reduce to finitely many pairwise exploration quotas and, at top-choice-separated instances, yield a polynomial-size marginal linear program. At these instances, the exact attainable set of expected logarithmic regret coefficients is $G(θ)\mathcal{X}(θ)$, where $\mathcal{X}$ is the feasible matching-allocation set and $G$ maps allocations to player regret. The usual upper-closed Graves-Lai region can be strictly larger despite having the same Pareto-minimal boundary. We further show that identical exploration quotas can induce very different regret through their scheduling. Finally, we construct estimate-solve-track policies, uniformly good on the full row-strict class, that attain every fixed positively weighted optimum without assuming optimizer uniqueness. Every Pareto-minimal point is pointwise attainable, possibly through an instance-calibrated target. --- ### Neuro-Symbolic Agentic AI for Networked Low-Altitude UAVs Authors: Yuqi Ping, Tianhao Liang, Nanchi Su, Guangyu Lei, Junwei Wu, Qinyu Zhang, Tingting Zhang Published: 2026-09-17 Categories: cs.AI, eess.SY arXiv: https://arxiv.org/abs/2609.19961v1 Networked low-altitude unmanned aerial vehicles (UAVs) need reliable and adaptive decision-making capabilities to operate under uncertain observations, dynamic environments, and intermittent connectivity, while many existing agentic systems remain limited by hallucination risks, data dependence, and weak generalization. This article investigates neuro-symbolic agentic AI (NSAAI) as a framework for combining neural grounding, symbolic reasoning, and closed-loop agentic interaction to support more reliable and adaptive UAV autonomy. We first examine its capability foundations in data efficiency, compositional generalization, continual learning, and zero-shot transfer, and then develop a reference architecture integrating task and goal management, neuro-symbolic planning, verification and metacognition, skill execution and network interaction, and shared knowledge and memory. An urban fire-inspection case implemented in LAESim illustrates how a UAV can coordinate sensing and cloud access under intermittent connectivity, reuse a verified image-delivery skill, and satisfy explicit evidence conditions before completing the mission. The results illustrate the potential of NSAAI to support reusable skills, evidence-grounded decision-making, and adaptive mission execution in networked UAV systems. We further discuss key research directions in uncertainty-aware reasoning, knowledge and skill expansion, adaptive self-monitoring, and standardized evaluation. --- ### Graph-Based Stochastic Power-UCT: Monte-Carlo Graph Search with Power Mean Estimation Authors: Tung Tran, Viet Bao Mai, Hoang Ta, Tuan Dam Published: 2026-09-17 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.19956v1 Tree-based Monte-Carlo Tree Search (MCTS) duplicates the same state when it is reached through different trajectories, which can waste simulations in stochastic MDPs. We introduce Graph-Based Stochastic-Power-UCT (GS-Power-UCT), which shares states reached at the same planning depth while keeping separate values for states reached at different depths. This design applies to general stochastic MDPs, including problems with cycles. We prove that for a fixed planning horizon, the root estimate converges to the finite-horizon value at rate $O(n^{-1/2})$, matching tree-based Stochastic-Power-UCT while reusing samples across shared states. We also study two full-state variants: GS-Power-UCT-F, which stores one node per physical state to increase sample sharing but may mix values from different remaining horizons, and GS-Power-UCT-F$^+$, which uses an adaptive horizon to control this bias. The latter converges to $V^{\star}(s_0)$, the optimal infinite-horizon discounted value at the root state $s_0$, when the remaining cross-depth gap vanishes. Experiments on stochastic planning benchmarks show improved sample efficiency over tree-based and graph-based baselines. --- ### One Intervention per Component is Enough: Towards Identifiability in Linear Stochastic Dynamics from Steady State Authors: Saber Salehkaleybar Published: 2026-09-17 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.19955v1 We study the problem of recovering the parameters of a multivariate Ornstein-Uhlenbeck (OU) process from steady-state observational and interventional data. In many applications, such as large-scale gene perturbation experiments, only stationary "snapshot" measurements are available, making standard stochastic differential equation estimation methods that rely on time-series trajectories inapplicable. We first establish an identifiability result: one intervention per strongly connected component (SCC) of the drift graph suffices to recover all OU process parameters generically up to a global scaling factor. This holds provided that the SCC condensation graph is connected with a single root and certain spectral nondegeneracy assumptions hold. We propose a recursive learning algorithm that orders SCCs topologically and, for each component, isolates its marginal dynamics and solves a linear system derived from the steady-state moment equations, leveraging parameters recovered for upstream components. Building on this theoretical foundation, we propose a regularized least-squares estimator that jointly minimizes residuals of the steady-state mean and covariance equations across observational and interventional data. Experimental results validate our theoretical findings in recovering parameters of the underlying OU process. --- ### LapaTrack-3D: 6 DoF pre-operative shape tracking for laparoscopic surgery Authors: Jingwei Song, Javid Hussain Jakir, Ray Zhang, Wenwei Zhang, Hao Zhou, Xiaomeng Xian, Maani Ghaffari Published: 2026-09-17 Categories: cs.RO, cs.CV arXiv: https://arxiv.org/abs/2609.19954v1 This work proposes a real-time 6 Degree-of-Freedom (6 DoF) tracking algorithm for monocular laparoscopic surgery. It provides alignment between intra-operative video and pre-operative data (e.g., CT). The 6 DoF tracking offers a solution for accurately locating the internal anatomy of the target organ despite the lack of tactile feedback and transparency. The ORB-SLAM2 framework is adopted and modified for prior-based 3D tracking with four major modifications. First, the primitive 3D shape is used for fast initialization of the ORB-SLAM2 monocular mode. Second, a pseudo-segmentation strategy is employed to separate the target organ from the background for tracking. Third, the 3D shape is incorporated as a geometric prior in its pose graph optimization. Fourth, the Multi-Scale Retinex with Chromaticity Preservation (MSRCP) algorithm is leveraged and modified for image enhancement in challenging illumination scenarios. In-vivo and ex-vivo experiments validate that LapaTrack-3D provides robust 3D tracking and effectively handles typical challenges such as poor illumination, fast motion, out-of-field-of-view scenarios, partial visibility, and ``organ-background'' relative motion. LapaTrack-3D achieves a processing rate of 13 Hz for 1280*720 pixel video. --- ### Not All AI Agents Are Equal: Characterizing Resource and Performance Dynamics Authors: Wonmi Choi, Minuk Park, Zhixiong Niu, Yongqiang Xiong, Chuck Yoo, Gyeongsik Yang Published: 2026-09-17 Categories: cs.AI, cs.PF arXiv: https://arxiv.org/abs/2609.19947v1 LLM-based AI agents process user requests through iterative reasoning and tool execution, often involving the invocation of remote LLM APIs with local tool containers. This execution model can make the optimization of agent serving difficult because latency, local resource demand, and container bottlenecks inter-mix across requests. However, the current agent ecosystem runs without much consideration of resource dynamics, which results in significant waste of the precious resources. This paper analyzes the resource inter-mix of AI agents for three representative tasks: retrieval-augmented question answering, web search, and software coding. To this end, we characterize the latency with respect to the resource dynamics of processing multiple requests and tasks concurrently. Our measurements show that agents have a wide range of behaviors depending on tasks, so that even the same tool can differ substantially in resource dynamics. We also find that running multiple requests concurrently exposes task-dependent bottlenecks in resource dynamics such as CPU, disk I/O, and memory. Furthermore, we uncover that faster LLM responses or more CPU cores do not always accelerate agents. Based on these observations, we demonstrate new optimization opportunities that exploit the resource dynamics of tasks: CPU-aware tool admission and task-aware CPU allocation. Our results show that the latency of CPU-sensitive agent tasks improves $\sim$5.4$\times$, and the average latency across multiple tasks is reduced $\sim$32% compared to native agents. --- ### MaSCoD: A Multi-Agent Framework for Structural-Context-Guided Candidate Causal Graph Generation Authors: Yudai Nakada, Yuichiro Nishiura, Jin Michael Splichal Published: 2026-09-17 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.19944v1 Large language models (LLMs) have been applied to causal discovery, but candidate-graph generation rarely treats premature omission of potentially relevant causal relations as an explicit design objective. We propose MaSCoD, a multi-agent framework that organizes candidate third variables and local structural patterns before direct-edge judgment. We evaluate MaSCoD on Auto-MPG, DWD, and Sachs using GPT-5.4 as the primary backbone and GPT-4o for replication. MaSCoD exhibits a dataset- and backbone-dependent retention-selectivity profile rather than uniform superiority. Across all six dataset-backbone settings, Full, which supplies structural hypotheses before direct-edge judgment, achieved higher mean Recall and F1 than No Phase 1, which instead constructs them within the judgment procedure, while also increasing false-positive rates. Additional reference-edge retention over all evaluated baselines was observed on DWD with GPT-5.4 and on Sachs with GPT-4o, rather than uniformly across settings. Partial ablations showed that supplying both information components did not always outperform supplying only one. For GPT-5.4, stage-wise analysis showed that the Full-No Phase 1 retention gap was already present after direct-edge judgment, while reconciliation introduced additional reference-edge loss for Full on Sachs. These findings support structural pre-organization as an explicit design and evaluation target for omission control and motivate evaluating context construction jointly with its utilization in judgment. --- ### Intrinsic Sequence-Likelihood Confidence in Retrieval-Dominated Extractive QA: Two Pre-Specified Negatives, and What They Do and Do Not Attribute Authors: Gunwoo Lee, Changmin Sung, Sang-Hwan Gwak, Ina Kim, Ji-Young Choi, Kyong-Ha Lee Published: 2026-09-17 Categories: cs.CL, cs.IR, cs.LG arXiv: https://arxiv.org/abs/2609.19942v1 In extractive document question answering whose questions were generated from the passages that contain their answers -- so that retrieval recovers 92-99.8% of what any mode combination could reach, whatever its absolute accuracy -- confidence-driven mechanisms have little to gain. Fine-tuning an open language model on a specialized domain corpus yields a model whose own confidence is a tempting control signal: it could decide which queries warrant further adaptation, and which answers to trust. We evaluate both uses under criteria fixed before the runs were executed, across four 7-9B model families whose adaptation moved closed-book F1 by at most +0.03, and both fail: a distillation trigger on all four families, under its pre-specified three-step transfer budget, and a routing-and-abstention policy in its single-model pilot. Retrieval alone recovers 92-99.8% of best-case combined accuracy under every correctness criterion we test, leaving routers no meaningful gain. The sequence-likelihood signal is insufficient relative to that mode -- area under the receiver operating characteristic curve 0.65-0.81 under the registered criterion -- before adaptation as well as after, unchanged by scalar recalibration and not consistently improved by token-level temperature rescaling. And the finer diagnostics depend on the correctness criterion and on answer length; on the three adapted combinations where we could test it, selector ablations show no statistically detectable downstream benefit from the confidence term on any seed; on Gemma, removing it changes the selector from failing to passing both registered criteria. The usable product is a set of pre-specified negatives with their dependencies made explicit. --- ### Stringological sequence prediction III: layered ziplines and a tradeoff between efficiency and expressivity Authors: Vanessa Kosoy Published: 2026-09-17 Categories: cs.FL, cs.DS, cs.LG arXiv: https://arxiv.org/abs/2609.19940v1 In previous papers, we began the study of sequence prediction algorithms adapted to stringological word complexity measures. In particular, we defined a complexity measure called Arithmetic Repetition Complexity (ARC) which admits a polynomial-time prediction algorithm with a mistake bound quasilinear in the complexity. Here, we show a weaker complexity measure related to ARC that admits an especially efficient prediction algorithm: an algorithm that runs in quasilinear time and polylog space for appropriate highly-structured sequences. The complexity measure is defined via a restricted class of "zipline programs" (a variant of straight-line programs), which we call layered. We thus get a less expressive measure with a more efficient algorithm (compared to our results for ARC), demonstrating a possible tradeoff. --- ### Error bounds in Sobolev norms for approximations with norm constrained ReLU neural networks Authors: Xianjun Li, Yunfei Yang Published: 2026-09-17 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2609.19937v1 Recent studies have shown that smooth functions can be well approximated by ReLU neural networks with path norm constraint on the weights. We extend these results from uniform approximation to approximation in Sobolev norm. Specifically, we analyze how well Sobolev functions in $W^{n,p}$ can be approximated by neural networks with width $W$, depth $L$ and path norm bounded by $K$, when the approximation error is measured in the $W^{1,p}$-norm. For shallow networks with depth $L=1$, we derive the approximation error bound $\mathcal{O}(\max\{W^{-(n-1)/d}, K^{-(n-1)/(s-n)}\})$, when the smoothness index satisfies $n<s=(d+3)/2$ and the input is $d$-dimensional. For deep networks, we remove the restriction on the smoothness by showing that the approximation bound $\mathcal{O}(K^{-(n-1)/(d+d/p+1)})$ holds if the width $W$ and depth $L$ are sufficiently large. --- ### Beyond Depth Truncation: Controlled Evaluation of Depth Utilization in Recursive Language Models Authors: Ha Van Dau, Thanh Tung Khuat, Nguyen Thanh Dung Published: 2026-09-17 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.19934v1 Depth-recurrent language models iteratively apply a small layer stack, decoupling per-token compute from distinct parameter count. To determine whether such a model genuinely utilizes its depth, both recurrence and layer-pruning literatures rely on a shared evaluation: truncating depth at inference time, plotting quality against retained depth fraction, and reading off the slope. While cheap and training-free, this metric suffers from an unexamined flaw: it extracts a single scalar from an intervention that alters multiple model properties simultaneously. Depth truncation concurrently reduces the number of block applications, decreases the volume of distinct computation performed, and pushes the readout head onto an out-of-distribution residual stream. The observed slope conflates all three factors, yet is conventionally interpreted as reflecting solely the second. We propose the Depth Control Protocol (DCP), a diagnostic suite that disentangles these three quantities. DCP comprises three positive controls that isolate each factor while varying the others, a negative control applying the identical interventions to dense transformers to ensure the effect is not an artifact of the measurement protocol, and a controlled training intervention to verify causality. The linchpin control, running the full budget of block applications while executing only a single distinct iteration, is strictly realizable only in depth-wise weight-sharing architectures, since in a dense network repeating a layer yields an entirely different model rather than the same model in an alternative configuration. --- ### From "Who Is This User?" to "What Does This Purchase Mean?": A Deployed Pipeline for Semantic User Profiling at Bank Scale Authors: Ryota Mitsuhashi, Tetsuro Morimura, Hirotake Ito Published: 2026-09-17 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2609.19928v1 Per-user LLM inference on transaction histories binds the inference budget linearly to user count, which becomes prohibitive at applied scale. We re-cast attribute inference from per-user to per-transaction-pattern. The pipeline runs in three phases: Resolve abstracts item names with optional web grounding, Profile infers attributes for each frequent pattern, and Tag clusters free-text attributes into a queryable database. In Profile, a single LLM call per pattern emits predefined categorical labels, free-text attributes, and per-attribute prevalence estimates. Because inference runs over patterns rather than users, the budget grows with the pattern count rather than the user count. On the public Open e-commerce corpus, the database is statistically indistinguishable from an LLM that reads each user's raw history directly in AUC across the evaluated attributes, and the prevalence estimates carry discriminative signal between positive and negative users. The pipeline is deployed at a major Japanese bank profiling on the order of tens of millions of users, with close to a three-order-of-magnitude reduction in LLM inference targets versus a per-user pipeline. The code is publicly available on https://github.com/CyberAgentAILab/profiling-agent-open-ecommerce. --- ### DirtyMoCap: Robust Motion Capture from Unconstrained Markers Authors: Long Wang, Shuting Zhao, Shen Yan, Siyuan Yu, Xiaoben Li, Zeyu Cai, Yumeng Hou, Yuliang Xiu Published: 2026-09-17 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.19927v1 Optical motion capture delivers high-fidelity human motion, but its reliance on strict marker layouts and clean trajectories severely limits its real-world applicability. In practice, tracking systems frequently output unconstrained markers: sparse, noisy, and unordered point clouds with unknown or varying configurations. To bridge the gap between corrupted raw markers and parametric human models, we introduce DirtyMoCap, a robust, marker-layout-free framework. Our core insight is to map unordered marker observations to a fixed set of "proxy anchors" comprising skeletal joints and body surface points, which serve as a stable intermediate representation. We first initialize and track these anchors over long sequences using a recurrent sliding-window architecture. Then, a custom differentiable Gauss-Newton solver fits the SMPL-H model to the tracked anchors to recover full-body pose, translation, and shape. By explicitly deriving geometric residuals, our solver learns adaptive observation confidence, smoothness, and prior weights end-to-end, adapting dynamically to the reliability of the input data. Extensive experiments on diverse, noisy marker configurations demonstrate that DirtyMoCap successfully generalizes across arbitrary layouts using only a single trained model. It consistently outperforms state-of-the-art configuration-specific baselines in both joint and vertex reconstruction accuracy, while our custom CUDA solver achieves up to a 100x speedup over standard PyTorch implementations. We further apply DirtyMoCap to heterogeneous raw optical MoCap recordings of traditional Chinese martial arts, yielding a Kung Fu motion dataset of temporally coherent SMPL-H reconstructions. Code and data are available at https://wanglongzju.github.io/DirtyMoCap-Project-Page. --- ### The Life of a Token: from Words to Bits on the Wire Authors: Davide Avesani, Pengwenlong Gu, Sotiris Skaperas, Stefano Secci Published: 2026-09-17 Categories: cs.DC, cs.LG, cs.NI, cs.PF arXiv: https://arxiv.org/abs/2609.19924v1 Large Language Models (LLMs) transform vast collections of unstructured text into semantic patterns used for language generation and reasoning tasks. Behind their ease of use lies a complex process: words become tokens, tokens become vectors, and vectors ultimately give rise to streams of bits that flow through High-Performance Computing (HPC) systems. As modern LLMs grow to billions or trillions of parameters, this path increasingly unfolds across thousands of interconnected accelerators, making the underlying communication fabric a critical and often opaque component of model training. This tutorial aims to walk the reader through the journey from words to network traffic, shedding light on how language is translated into communication flows within HPC training systems. Using concrete examples from Dante's Divine Comedy, we illustrate how model architecture, tokenization, embeddings, and parallelization strategies shape the volume, structure, and timing of data exchanged across the network. We combine architectural analysis with analytical traffic models and numerical examples to characterize the communication requirements of LLM training. We try to demystify how words travel across the network and provide practical insights into the network requirements needed to support the journey from text to trained model. --- ### KoNeoBench: A Curated Evaluation Dataset for LLM Understanding of Korean Neologisms Authors: Soha Lee, Soojin Lee, Heesung Yang, Hyunju Song, Hyunji Lee, Jinsan An, Jeongwan Shin, Jin Hyun Park, Jun Lee, Hyeyoung Park, Kilim Nam Published: 2026-09-17 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2609.19916v1 Large language models (LLMs) are typically evaluated on static benchmarks, even though natural language constantly evolves through newly emerging words and meanings. Existing Korean benchmarks are centered on established vocabulary and therefore provide limited coverage of such recent lexical change, and their English-oriented design makes it difficult to assess the typological properties of Korean, in which content words combine productively with functional morphemes. In this paper, we introduce KoNeoBench, a benchmark for evaluating LLMs' understanding of Korean neologisms. KoNeoBench is built on 1,785 Korean neologisms attested in online news since 2020 and curated through expert lexicographic review. Each entry provides usage examples, word-formation analyses, and dictionary-style definitions. Based on this resource, we define four tasks and report results on recent models, together with a human baseline. Our experiments show that current LLMs exhibit clear limitations in recovering source components, distinguishing semantic categories, and generating accurate definitions. These results reveal specific aspects of recent Korean lexical change that remain challenging for current LLMs. KoNeoBench is available at https://github.com/bcmilab/ko-neobench/ . --- ### Amortizing Physics-Informed Neural Solvers via Graph Hypernetworks Authors: Cheng Jing, Abhishek Verma, Kallol Bera, Yixuan He, Kookjin Lee Published: 2026-09-17 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.19915v1 Amortizing physics-informed neural networks (PINNs) across related PDEs requires describing each equation to a reusable solver. Coefficient vectors encode numerical parameters in predefined slots, leaving operator and cross-field assignments implicit. We make these relationships explicit in an operator graph, with nodes for fields, derivatives, terms, and residuals and coefficients retained as term attributes. A graph hypernetwork generates diagonal codes that initialize a meta-trained factorized PINN for each target equation. Meta-training and target-specific adaptation use governing equations and prescribed conditions without solution labels. We compare coefficient-vector, DeepSets-based term-set, and graph conditioning by solution accuracy within a fixed adaptation budget. In scalar convection-diffusion-reaction problems, both term-based descriptors improve high-reaction accuracy, with similar performance. In two-field Fisher-KPP, meta-training sees uncoupled and one-way systems; after 3,000 adaptation steps on unseen two-way coupling, the graph's mean final error is 35.7% below the term set and 67.7% below the coefficient vector. In a fixed-structure capacitively coupled plasma model, the coefficient vector performs best. These results support extending coefficient conditioning with explicit equation relationships for physics-based solver adaptation. --- ### Digital Twins for Opinion Dynamics: A Generative LLM Framework for Social Networks Authors: Omran Berjawi, Giuseppe Fenza, Rida Khatoun, Sherali Zeadally Published: 2026-09-17 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.19913v1 The study of opinion dynamics in social networks is one of the key challenges in computational social science with direct relevance to understanding political polarization, misinformation, and health responses. Current approaches focus on simplified mathematical models that ignore linguistic and contextual factors related to belief updates or use Large Language Model (LLM)-based simulations that have not been validated against real data. We present a framework based on the concept of a digital twin to simulate opinion dynamics in social networks. The approach fills the gap by cloning a real-world Twitter network, assigns a set of attributes for agents (such as persona, emotions, centrality, stubbornness, and influence), and employs Mistral-7B to perform opinion update based on memory and social exposure. To evaluate the proposed approach, we validate it against two real Twitter datasets (COVID-19 discourse and U.S elections 2020). The results show that the capability of the proposed framework reproduces opinion trajectories and reduces individual prediction error by more than 50% compared to the best-performing classical baseline (Mistral-7B achieves Mean Absolute Error (MAE) = 0.150 and 0.121 on the COVID-19 and US Election 2020 datasets, respectively). We observe similar improvements in structural alignment (Delta_r = 0.120 and 0.180) and polarization dynamics (Delta_Var = 0.106 and 0.115) on the two datasets, respectively. Additionally, the ablation studies confirm that agent attributes, memory, and social exposure all contribute to the framework's predictive fidelity in reproducing opinion trajectories, with agent attributes being the most critical contributor. Overall, our results demonstrate that grounding Mistral-7B within empirically cloned interaction networks produces a realistic simulation framework capable of reproducing complex social dynamics. --- ### CitySTAR: Structured and Topology-Aware Reasoning for Open-Vocabulary Urban 3D Grounding Authors: Shuai Zhang, Hongye Hou, Qinghe Liu, Zhuoxiao Li, Dongli Wu, Jing Ou, Yuan Liu, Wufan Zhao Published: 2026-09-17 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.19911v1 3D grounding aims to localize target entities in complex scenes from natural language and plays a fundamental role in embodied perception and spatial reasoning. However, existing approaches mostly rely on feature similarity or direct matching, making it difficult to connect natural-language intent with the implicit semantic and geometric structures hidden in billion-scale urban point clouds. We reformulate city-scale 3D grounding as structured constraint reasoning, where description semantics are organized into computable cross-modal constraints over open-vocabulary 3D entities, attributes, and spatial relations. We present CitySTAR, a training-free framework for reasoning-driven urban 3D grounding. CitySTAR lifts raw billion-scale urban point clouds into a query-ready scene graph of open-vocabulary 3D instances, with CodeLLM-driven tools supplying multimodal evidence for node attributes and 3D spatial relations. It then models target-context topology with paired hypergraphs and performs bidirectional topology verification for structural disambiguation. Finally, a Reflective Cross-modal Grounding module integrates topology consistency and candidate-centered 2D visual evidence to make decisions over a metric-aware 3D context graph. To further support this setting, we introduce CitySTAR-3D, an enhanced benchmark that improves semantic coverage, instance completeness, bounding-box fidelity, and spatial-relation complexity in city-scale 3D grounding. Extensive experiments show that CitySTAR consistently improves open-world urban 3D grounding while maintaining strong interpretability and generalization. --- ### GS-PI: An Optimization-Decoupled Appearance Decomposition Approach for Generating PBR Gaussian Assets Authors: Jieting Xu, Rengan Xie, Zijian Huang, Zehui Jin, Rui Wang, Yuchi Huo Published: 2026-09-17 Categories: cs.CV, cs.GR arXiv: https://arxiv.org/abs/2609.19907v1 Gaussian Splatting (GS) excels at novel-view synthesis but encodes baked-in radiance, tightly entangling illumination with geometry and preventing seamless integration into physically based rendering (PBR) pipelines. Existing inverse-rendering methods attempt to disentangle materials via joint optimization, but often suffer from competing objectives that cause severe ambiguities and residual lighting artifacts. To overcome this, we present GS-PI, a novel optimization-decoupled framework that casts PBR material generation as a geometry-conditioned diffusion process on 3D point clouds. By operating directly in the 3D domain, our method inherently guarantees multi-view consistency, sidestepping the severe pixel correspondence issues that challenge 2D diffusion approaches. We introduce a multi-scale cross-view conditioning mechanism that integrates three complementary components: a global semantic prior, source-anchored photometric cues, and an absolute spatial learned view-direction conditioning signal. This design efficiently compresses complex multi-view evidence, mitigating cross-view projection misalignment and successfully preventing specular highlights from baking into intrinsic colors. By extracting a point cloud from a pre-trained Gaussian model, predicting PBR attributes via conditional diffusion, and distilling them back through differentiable rasterisation, we yield a fully relightable PBR-GS asset. GS-PI outperforms recent inverse-rendering baselines while replacing per-scene joint illumination/BRDF optimization with a learned diffusion pass followed by a short target-driven distillation, without requiring proxy meshes. --- ### Learning and Transferring Closed-Loop Robot Software Authors: So Kuroki, Yujin Tang Published: 2026-09-17 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2609.19906v1 Closed-loop robot policies require observation processing, state management, and situation-dependent branching, making them costly to design and tune manually. Although coding agents increasingly support control-code generation and optimization, it remains unclear whether implementations improved on source tasks also support policy acquisition for new tasks. We study this question by treating complete closed-loop implementations as reusable execution experience. For each source task, a coding agent generates policy code from a few successful demonstrations and iteratively improves it using simulation feedback. The validation-selected implementations are retained in a software archive. For new tasks, the agent generates and improves policies using archived implementations, target demonstrations, and execution feedback. The resulting policy is then frozen and executes without further model calls. Across four source tasks in RoboCasa, iterative optimization increases mean success from 28.3% to 64.2%. Across nine target tasks and three independent runs, mean success is 45.2% without references, 41.5% with initial source code, and 57.0% with optimized source code. Optimized references outperform initial references in all three runs on the nine-task average, with a mean gain of 15.6 percentage points. These results demonstrate the value of execution-improved software as a resource for acquiring new policies in this setting, although initial references remain better on two target tasks when averaged across runs. --- ### REARL: A Closed-loop Autonomous Driving Simulation Enhancement Framework with Real Traffic Data and Large Language Models Authors: Xiaojun Bi, Jun Jiang, Yiwen Sun, Quanyi Ou, Yizhi Ma, Ke Cheng, Mingjie Bi, Yexin Li, Bowen Du Published: 2026-09-17 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.19903v2 Accurate simulation is crucial for autonomous driving development, yet capturing real-world traffic complexity remains challenging. Existing simulators that rely on predefined rules or static data playback struggle with dynamic traffic. CRITICAL uses real traffic data and a large language model (LLM) to adjust the initial simulation configuration, but the simulated distribution still diverges from real traffic as the rollout evolves. We propose REARL, a closed-loop simulation enhancement framework that integrates real traffic data with LLMs. Real traffic data are clustered, and each cluster center is used as a representative scenario that provides typical real-world traffic patterns for the LLM. A timed sliding-window detector then monitors discrepancies in vehicle speed distribution and mean spacing between pairs of vehicles. If a metric exceeds a threshold, the LLM adjusts vehicle decision-making; otherwise the existing controller is kept. The LLM also selects a matching real vehicle from a traffic snapshot and modulates the simulated vehicle with reference to that real action. In a controlled HighD highway setting, compared with the CRITICAL baseline and a PPO-based learning baseline, REARL reduces the Hellinger distance for speed distributions to 0.3067 and the MAPE for mean spacing to 0.8371, while achieving a time headway (THW) of 22.8575 and a lane change rate of 0.0708. --- ### Self-Replicating Neural Cellular Automata: Quantifying Emergent Phenotypic and Genotypic Diversity in an OpenEnded Substrate Authors: Sanyam Jain, Felix Simon Reimers, Stefano Nichele Published: 2026-09-17 Categories: q-bio.PE, cs.LG, cs.NE arXiv: https://arxiv.org/abs/2609.19902v1 We study an in-silico substrate in which every pixel of a two-channel cellular-automata grid carries a tiny neural network (an agent) that senses its Moore neighborhood. A cell persists only by self-replication: a living neighbor is cloned and its weights are mutated by a uniform perturbation, so that phenotype (cell state) is driven entirely by genotype (network weights). From a handful of seeded founders the system grows into a spatially organized ecosystem of coexisting, competing and dominating species. Our main contribution is a battery of coarse-grained diversity metrics that make such growth measurable at two scales: four phenotypic tools based on cellular-type frequency, entropy and cell variance, and two genotypic tools that colour each agent by a hash of its full weight vector versus a sparse random-weight probe. Across a five-fold sweep of 1680 small runs and 24 long (1000-generation, 200 x 200) runs, the substrate is persistent and self-maintaining in 20 of the 24 long configurations and exposes a clear phenotype-genotype diversity trade-off: raising phenotypic diversity collapses genotypic diversity and vice versa. Full-genome hash colouring further reveals lineage structure that a random-weight probe systematically misses. Code, data and animations are released as supplementary material. --- ### Delphi Scanner: efficient and interpretable static malware detection via API sequence modeling Authors: Bijied Brahimi, Vincent Cohadon, Gabriel Glazman, Rayan Al Mohaize, Omran Berjawi, Rida Khatoun Published: 2026-09-17 Categories: cs.CR, cs.LG arXiv: https://arxiv.org/abs/2609.19900v1 Static malware detection for Windows Portable Executable files demands a careful balance between detection effectiveness, computational efficiency, and analytical interpretability. This paper introduces Delphi Scanner, a static malware detection system for Windows PE files that balances efficiency with behavioral interpretation. It uses a convolutional neural network (CNN) to model Windows API sequences to classify PE and a decoupled interpretation layer based on a rule-based layer to categorize APIs into high-level malicious capabilities. Evaluated on over 190,000 Windows PE files, the system achieves 95.35% accuracy with a 1.53~MB model footprint. Robustness experiments on 5,647 out-of-distribution MalwareBazaar samples, paired packed and unpacked executables, and three adversarial manipulation strategies confirm generalization beyond the training distribution and resistance to functionality-preserving evasion techniques. Overall, these results demonstrate that API sequence-based static analysis offers a practical, interpretable, and efficient foundation for malware triage in local deployment scenarios. --- ### TRACE: Accountable Agentic Retrieval for Source Discovery in Digital Archives Authors: Donghan Bian, Marie Puren, Florian Cafiero Published: 2026-09-17 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.19897v1 Historical archives pose a difficult retrieval problem for retrievalaugmented generation systems: documents are OCR-degraded, heterogeneous across genres and sources, and require strong source traceability for scholarly and institutional use. We introduce TRACE, a training-free agentic retrieval framework designed for accountable source discovery over historical corpora. The system was developed in the context of DECIDON, an interdisciplinary project on the circulation of political discourse between parliamentary debates and the press during the French Third Republic, involving digitised historical collections and institutional use cases. The prototype is currently deployed internally within the project and accessible to 24 researchers across six partner institutions. We evaluate TRACE on HistoriQA-ThirdRepublic, a benchmark of 1,752 French historical questions over parliamentary debates and newspapers from 1887, with documents derived from Biblioth{è}que nationale de France digitised collections. TRACE achieves R@10 = 0.856 and MRR = 0.653, outperforming sparse, dense, graph-based, and agentic RAG baselines, with the largest gains on multi-hop and cross-corpus questions. At approximately $0.02 per question under the default hosted inference configuration, TRACE also remains economically feasible for heritage institutions, laboratories or companies that cannot rely on costly local GPU infrastructure. These results suggest that, for large digital libraries and archives, retrieval accountability and corpus-aware agent design can provide a practical alternative to heavier training-based or graph-construction approaches. --- ### ClashBench: Conflicts Leading Agents to Seize and Harm Authors: Yuejin Xie, Yu Li, Dadi Guo, Qingyu Liu, Yuqian Fu, Yanwei Fu, Yujiu Yang, Xia Hu, Dongrui Liu Published: 2026-09-17 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2609.19892v1 As agent systems become more widely used, multiple agent sessions increasingly run alongside pre-existing user tasks in the same environment, sharing resources with limited capacity or mutually exclusive states. This creates a safety risk: when granted sufficient privileges, an agent may resolve a resource conflict by terminating or otherwise disrupting an existing task rather than reporting it. In this work, we identify and formalize this failure mode, which we term destructive resource preemption: obtaining the resources required for a requested task by terminating, overwriting, evicting, or degrading an incumbent task. To systematically study this risk, we introduce ClashBench, an executable benchmark comprising 268 validated conflict cases across 55 resource types, and evaluate 17 models through Codex, Claude Code, and OpenCode. We observe destructive preemption in 44.5% of trajectories, where the agent completes the requested task while causing the incumbent task to fail its health check. We also show that prompt-based safeguards are insufficient: an instruction to avoid affecting existing tasks reduces but does not eliminate preemption, while an instruction explicitly authorizing the agent to stop local processes increases it. More concerningly, in 31.9% of successful destructive-preemption cases, the final response mentions neither the resource conflict nor the action taken to resolve it, raising concerns about possible concealment. These findings establish destructive resource preemption as a broad safety risk in privileged agent systems and motivate stronger privilege controls, task isolation, and conflict-aware safeguards. --- ### Online Adaptive Kernel Mixing for Gaussian Process Decision Making Authors: Kavin Aravindan, Mani Tej Sriram, Gautam Dasarathy, Tejas Bodas Published: 2026-09-17 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.19891v1 Gaussian Processes (GPs) are widely used as surrogates for black-box functions in sequential decision-making problems such as Bayesian optimization (BO), level set estimation (LSE), and Bayesian active learning (BAL). GP performance critically depends on kernels, and standard kernels can lead to suboptimal decisions under misspecification. To address this, we introduce HACK GPs (Hedge Adaptive Cumulative Kernels), a method that views kernel selection as an online learning with expert advice problem. HACK treats each candidate kernel as a GP "expert" and updates a distribution over experts online using AdaHedge, based on a loss received as a proxy for their ability to fit the function and align with the task objective. We provide two variants of HACK: (i) Mixture of Gaussians (MoG) and (ii) categorical sampling. We establish general guarantees showing that, under a loss-gap condition, the weight concentrates on the best kernel and the resulting acquisition function is close to that of the best expert. Empirically, we observe robust performance across BO, LSE, and BAL compared to standard kernels such as Squared Exponential and Matern-5/2, as well as simple ensemble baselines. --- ### Generalization through Lexical Abstraction in Transformer Models: The Case of Functional Words Authors: Giuseppe Samo, Vivi Nastase, Paola Merlo Published: 2026-09-17 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.19887v1 Pronouns, adverbs and other functional words (such as they, her, somewhere, there) are often used in language to replace concrete nouns or phrases, when their properties - such as gender, grammatical number - provide sufficient information for the given context. Do pretrained transformer models encode such functional words in a manner that allows them to be used like humans do? Can language models recognize the syntactic and semantic parallelism of sentences such as "The researchers wrote the paper" and "They wrote it", which relies on such lexical abstraction? We map these linguistic questions into the embedding space of a pretrained transformer model, and compare representations of nouns, with the representations of the pronouns and adverbs that can replace these nouns, in isolation and in parallel lexicalized and functional sentences. We then probe for shared syntactic and semantic structure in the embeddings of parallel lexicalized and functional sentences. We find that functional words are located centrally compared to nouns, but are also distinct, which is congruent with their behaviour as place-holders in a wide variety of contexts. The analysis of the embeddings of parallel (lexicalized and functional) sentences show them inhabiting different subspaces of the embedding space. Experiments that distil the structural information of the sentence show that training on either type of data does not reveal the shared structure - because of the over-consistency of the vocabulary (in case of the functional data), and the too much variety (in case of the lexicalized versions). However, training with a mix of functional and lexicalized sentences, the shared structure emerges. --- ### Evaluating Communicative Success in Machine-Translated Conversation Authors: Faiz Ghifari Haznitrama, Alice Oh Published: 2026-09-17 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.19885v1 Interpreter agents built on machine translation (MT) increasingly mediate live conversation between people who do not share a language, yet we still evaluate them with metrics built for isolated sentences, which measure fidelity rather than whether communication succeeds. We introduce a reusable three-layer checklist-and-judge framework that evaluates interpreter-mediated conversation across semantic, pragmatic, and cultural-social dimensions, covering the naturalness, intent, and social appropriateness that fidelity metrics leave unmeasured. It runs in both single-turn and interactive multi-turn settings, where simulated users reply to translated messages as the conversation unfolds and each turn is scored alongside the conversation as a whole. We extensively validate it through controlled perturbations, cross-judge comparisons, and human annotations. Our main single-turn benchmark evaluates 10 interpreter setups across Arabic, Bengali, Indonesian, and Korean from 5,624 OpenSubtitles-derived scenarios spanning 12 translation directions, and our multi-turn study covers all 6 language pairs in scripted and live modes. Results show a consistent decline from semantic to pragmatic and cultural-social success, while conventional MT metrics overlook failures among stronger interpreters, and prompt ablations show that scenario context, structured instructions, and cultural context improve communicative success, although gains vary across setups. Our work thus provides an evaluation framework and benchmark for interpreter agents in conversation, and highlights the importance of communicative success alongside existing translation metrics. --- ### PetriBench: Benchmarking LLM Reasoning over Dynamic State Spaces Authors: Pyrros Koussios, Benjamin Jäger, John Hua Yao, Ajay Sridhar, Violet Xiang, Chenhao Li Published: 2026-09-17 Categories: cs.CL, cs.AI, cs.LO arXiv: https://arxiv.org/abs/2609.19883v1 Characterizing LLM reasoning remains an open challenge, as many existing benchmarks isolate specific reasoning skills, rely on external knowledge, or are costly to extend. We introduce PetriBench, a compact, fully self-contained, and scalable benchmark for evaluating LLM reasoning over dynamic state spaces using Petri nets, a mature formalism for modeling real-world concurrent and distributed systems. PetriBench organizes reasoning into four task families varying by scope and temporal horizon, with Easy, Medium, and Hard levels generated by increasing structural complexity and evaluated against exact ground truth. Across a diverse set of proprietary and open-weight models, accuracy decreases consistently with difficulty, while harder instances expose increasingly distinct task-specific capability profiles. Additional analyses show that test-time compute improves performance but interacts differently with different reasoning tasks, and that procedural generation yields smooth scaling with structural complexity. Together, these results show that PetriBench provides a unified and extensible setting for probing the strengths, limits, and scaling behavior of LLM reasoning. --- ### BinoGen: Scaling egocentric binocular data for embodied visual perception and learning Authors: Chunpeng Li, Ya-tang Li Published: 2026-09-17 Categories: cs.CV, cs.MM arXiv: https://arxiv.org/abs/2609.19881v1 Embodied visual perception relies on temporally coherent visual experience accumulated through continuous engagement with the environment. However, collecting large-scale egocentric binocular observations together with dense annotations remains costly and difficult. Moreover, visual experience is shaped not only by the environment but also by the embodiment of the observer, including viewing height, field of view, binocular geometry, and motion through the scene. To address these challenges, we present BinoGen, an automated framework for generating large-scale, embodiment-aware egocentric binocular visual experiences in indoor environments. BinoGen jointly models environmental and observer variation through generative scene synthesis, probabilistic object instantiation, appearance randomization, stochastic trajectory generation, and configurable binocular camera setups. The framework produces synchronized binocular videos together with dense multimodal supervision, including depth maps, optical flow, surface normals, semantic maps, object coordinates, and camera poses. Using BinoGen, we construct a dataset comprising more than 20 million annotated images for supervised learning. We demonstrate two complementary utilities of BinoGen. First, incorporating BinoGen data consistently improves real-world visual perception, including depth estimation, object detection, and video object tracking. Second, paired human-inspired and mouse-inspired observations from the same environments enable controlled investigation of how observer embodiment affects perceptual learning. Embodiment-specific adaptation substantially improves performance, while joint training enables a single model to perform competitively across both embodiments. Together, these results demonstrate that large-scale, controllable visual experience can improve embodied perception... --- ### D-Quant: Driftable Entropy Coding for KV Cache Quantization Authors: Yi Su, Hong Liu, Guanghua Yu, Jianchen Zhu Published: 2026-09-17 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.19880v1 The KV cache has become a major bottleneck in deploying LLMs, as its memory footprint grows linearly with sequence length and batch size, imposing substantial pressure on both memory capacity and bandwidth. Among various KV cache compression techniques, quantization is particularly attractive due to its effectiveness and ease of deployment. However, most existing methods rely on fixed-width quantization, where a $b$ bit representation is inherently limited to $2^b$ quantization levels. As the bit width decreases, the number of available levels shrinks exponentially, leading to severe information loss and rapid performance degradation. We further observe that fixed-width quantization fails to exploit the highly non-uniform distribution of KV cache. After rotation and normalization, KV values approximately follow a normal distribution, with most values concentrated near the center and only a small fraction appearing in the tails. Nevertheless, fixed-width coding allocates the same number of bits to frequent and rare symbols. Entropy coding naturally exploits such non-uniformity by assigning shorter codewords to frequent symbols and longer ones to rare symbols, substantially reducing the average number of bits required for representation. However, its variable-length output is not suited to highly parallel attention kernels, where efficient dequantization and computation rely on regular memory layouts and fixed-stride accesses. To bridge this gap, we propose \textbf{D-Quant}, a flexible KV cache quantization framework that introduces a \textbf{drift} mechanism to convert entropy-coded representations of each token into fixed-size bitstreams, enabling regular memory access and parallel dequantization within attention kernels. --- ### VākQA: A Benchmark and Evaluation Study for Telugu Spoken Factoid Question Answering Authors: Bhavana Akkiraju, Ravi Sastry Kolluru, Sri Charan D, Srihari Bandarupalli, Santosh Kesiraju, Anil Vuppala Published: 2026-09-17 Categories: cs.CL, eess.AS arXiv: https://arxiv.org/abs/2609.19879v1 Question answering has advanced rapidly with large language models, but predominantly for high-resource languages, in both text and spoken settings. Spoken question answering (SQA) benchmark for Telugu remains unexplored, and the reliability of automatic evaluation in this setting remains unquantified. We introduce VākQA, a Telugu SQA benchmark of 2,001 factoid question-answer pairs across six domains, with 2.53 hours of speech audio, bilingual transcriptions, and human-verified reference answers. We first validate evaluation methods against human judgements: Gemini-as-a-judge best approximates human ratings but is non-uniformly strict, while open-weight judges systematically penalize correct Telugu answers that differ in surface form from the reference. Using this validated setup, we benchmark proprietary and open-weight models across input modality, language, and domain. We observe that Telugu phrasing retains cultural specificity that is lost in translation, speech input introduces phonetic confusions that alter question meaning, and cascaded ASR-MT errors compound progressively. VākQA is publicly released. --- ### Uni-LaDiR: Latent Diffusion Unifies Multimodal Reasoning Authors: Haoqiang Kang, Yizhe Zhang, Nikki Lijing Kuang, Jiatao Gu, Yian Ma, Lianhui Qin Published: 2026-09-17 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2609.19878v3 Multimodal models increasingly think with different modalities such as images, 3D point clouds, and robot states, not just text. Yet each modality is still encoded into its own representation space, creating a modality-switching gap whenever reasoning moves from one modality to another. In this paper, we introduce Uni-LaDiR (Unified Latent Diffusion Reasoner), a framework that unifies different modalities into a shared latent space for multimodal reasoning. A unified encoder maps teacher reasoning steps from different modalities into latent thought tokens in a shared space, trained to extract the information needed for later reasoning steps and the final output. A diffusion reasoner, trained jointly with the encoder, generates these tokens at inference without teacher reasoning steps. Across eleven vision-language model (VLM) benchmarks and two vision-language-action (VLA) suites, Uni-LaDiR achieves relative gains over the strongest baselines of 7.3% on four mathematical and logical VLM benchmarks and 6.1% on RLBench manipulation tasks. Controlled comparisons show increasing gains as more teacher modalities are unified. These results suggest that unification improves multimodal reasoning by weaving it into a single thread, where the model predicts successive thoughts in a common representation space. --- ### JustMem: Just-Enough Memory Access for Long-Term Conversations Authors: Guanhua Chen, Yanting Wang, Wenjing Zhi, Lei Sha Published: 2026-09-17 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.19877v1 Efficient long-term conversational memory requires retrieving sufficient evidence without indiscriminately expanding the context presented to the language model. This is challenging because relevant evidence may be distributed across multiple sessions, while compression may discard details needed for answering. Different queries therefore require different forms of memory access. To capture these demands, we formulate memory access along two dimensions: discovery breadth, which controls how broadly evidence is searched, and reading fidelity, which controls whether evidence is read in compact form or recovered from the original conversation. Based on this formulation, we introduce JustMem, which stores conversation history as compact atomic memories and adapts memory access along these two dimensions to each query. Specifically, LOOKUP handles local evidence, COMPOSE broadens discovery for distributed evidence, and REPLAY increases reading fidelity for fidelity-sensitive evidence. On LoCoMo and LongMemEval-S, JustMem achieves the highest mean accuracy and retrieval recall among the compared memory systems while using substantially fewer generative-model tokens for memory construction and inference. --- ### SlugTrails: An Egocentric Benchmark for Floor Plan Localization in Large Buildings Authors: Yunqian Cheng, Roberto Manduchi Published: 2026-09-17 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.19876v1 Floor-plan-based indoor visual localization enables infrastructure-free positioning, but most methods are developed and evaluated in small residential environments unlike the large public buildings of real deployment. We introduce SlugTrails, a floor plan localization benchmark for large indoor spaces under realistic egocentric sensing: $30$ Hz Aria glasses recordings across three campus buildings and six floors ($22089$ m$^2$ of floor plan outline), CAD-derived floor plans with semantic classes and circulation space masks, and trajectories aligned into the floor plan frame using laser-surveyed anchors. One protocol covers three practical ways of gathering geometry under a limited field of view -- a single walking frame, a stationary multi-view sweep, and a walking stream with odometry -- so methods designed for different regimes are compared on the same buildings and ground truth. Evaluating five representative geometric and learned systems under their native sensing configurations, we find that stock checkpoints (official released weights) are near zero on SlugTrails (at most $0.004$ R@1m30$^{\circ}$ on walking single frames), while fine-tuning on SlugTrails improves every trainable family on all three tasks (e.g., F$^3$Loc $0.0 \rightarrow 0.141$ single-frame and $0.03 \rightarrow 0.66$ sequential), with gains compounding as observations accumulate. The same fine-tuned weights also improve cross-dataset generalization on LaMAR with no LaMAR training (sequential R@1m $0.048 \rightarrow 0.143$ for F$^3$Loc and $0.063 \rightarrow 0.127$ for UnLoc), whereas train-from-scratch on SlugTrails alone stays far below fine-tuning from stock weights -- evidence that floor plan localization is currently limited by indoor data rather than by architecture. We release the dataset, protocols, and tools at https://github.com/Head-inthe-Cloud/SlugTrails. --- ### BINDER: A Latent Variable Model for Probabilistic Medical Image Registration Authors: Stefano Cerri, Amirhossein Hassankhani, Yaël Balbastre, Koen Van Leemput Published: 2026-09-17 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.19875v1 We propose a new probabilistic model for general-purpose medical image registration that builds upon the mutual information registration criterion. It centers around a spatial interpolation technique that assumes latent voxel-wise correspondences between the images being registered. By exploiting these latent variables, we derive dedicated optimization and MCMC sampling techniques that only involve closed-form iterative updates. When applied to nonlinear registration, an efficient demons-like optimization algorithm is obtained that shows robust out-of-the-box performance across a variety of monomodal and multimodal registration tasks. We also demonstrate a corresponding sampler that can quantify, for the first time, uncertainty in multimodal registration scenarios with very high-dimensional 3D deformations. Our code, which we call BINDER (Bayesian INference for DEformable Registration), is freely available at https://github.com/ste93ste/BINDER. --- ### AURA: Adaptive Uncertainty-Routed Analysis for Email Threat Detection Authors: Omran Berjawi, Walid fahs, Rida Khatoun Published: 2026-09-17 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.19873v1 Email spam and phishing attacks remain a critical security threat. Adversaries increasingly exploit large language models to craft contextually convincing malicious messages, and existing spam detection systems often struggle to keep pace. Generalization across diverse and evolving attack scenarios is limited, which reduces effectiveness once these systems are deployed in practice. This paper introduces Adaptive Uncertainty-Routed Analysis (AURA), a multimodal email threat detection system that analyzes both the content of an email and its embedded URLs. AURA is built around two layers: the first quantifies prediction uncertainty from a URL classifier, and only ambiguous messages are escalated to a fine-tuned transformer encoder for semantic analysis. The system is evaluated on eight heterogeneous training corpora together with two held-out real-world corpora spanning a decade of adversarial campaigns. AURA reaches a macro F1-score of 0.9858 in-distribution, and on NazPhish-Eval and GuenterTrap-Eval it maintains 0.9502 and 0.9436, respectively, which is evidence of robust generalization under genuine distribution shift. --- ### PART: Learning 3D Part Assembly and Retrieval with Transformers Authors: Ruchao Bao, Wenzheng Wu, Chucheng Xiang, Zhongyuan Liu, Yuan Liu, Jinxin Dong, Ligang Liu, Ziqi Wang Published: 2026-09-17 Categories: cs.CV, cs.GR arXiv: https://arxiv.org/abs/2609.19872v1 3D assembly is fundamental to modern manufacturing and digital content creation. In this paper, we present PART, a unified transformer-based framework for 3D part retrieval and assembly: given a target shape and a part library, PART automatically selects the appropriate parts and predicts their 6-DoF poses to reconstruct the target. While prior work has achieved impressive progress on assembling a pre-defined set of parts, this more practical retrieval-based setting remains largely unexplored. The task faces three key challenges: (i) a combinatorially explosive search space that grows exponentially with library size; (ii) variable-length outputs, as different targets require different numbers of parts; and (iii) continuous 6-DoF pose estimation for part assembly. To address these, we formulate retrieval and assembly as a set prediction problem and design a novel transformer-based framework that retrieves parts and regresses their poses with variable-length output. Additionally, we exploit the duality between part pose estimation and target segmentation through joint training and a novel segmentation-enhanced optimization module. Finally, We curate a large-scale dataset of 80K+ shapes, and the results show that PART generalizes to scene layouts, image targets, and real-world scans. Project Page: https://iambrc.github.io/PART-project-page/. --- ### Physical knowledge on historical data matters more than enforcing physical constraints on the forecast Authors: Etienne Lehembre, Pascal Audigane, Vincent Nguyen, Christel Vrain, Thi-Bich-Hanh Dao Published: 2026-09-17 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.19871v1 Time series forecasting has seen signicant advancements with the emergence of new deep learning models. However, forecasting time series in applications involving physical processes remains a major challenge. Despite the apparition of Physics Informed Neural Networks (PINN), recent models do not estimate unobservable intermediate physical variables, which are important for domain experts to understand the target behavior. To this end, we propose a Physics Informed Recurrent Neural Network (PIRNN) which predicts, along the target, unobservable variables on both historic data and forecast target. This approach enhances the model robustness and results interpretation using domain knowledge. Our method is easily adaptable to any physical model using several equations, each having its own set of unobservable variables, to describe it-self. As a case study, we incorporate physical equations used for groundwater levels predictions by the physical model called Gardenia. This model uses transfers equations between reservoirs, optimized with data assimilation, to simulate the evolution of groundwater levels. Evaluation includes several well known neural network models and the Gardenia model compared on twelve real world datasets. In addition, we study the impact of each component through an ablation study. Our model outperforms other models on ve out of the twelve datasets and our ablation study underlines the importance of having a physical background in our time series forecasting task. Finally, the coherence of the physical variables predicted by our neural network is assessed by a domain expert. --- ### Zarya: A Hybrid Autoregressive--Masked Diffusion Language Model with Flexible Training and Dual-Mode Inference Authors: Leonid Sinev, Ilya Koziev, Vladislav Leshchuk Published: 2026-09-17 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2609.19868v1 Autoregressive language models (ARMs) are constrained by sequential, left-to-right generation, while masked diffusion models (MDMs) enable parallel decoding but suffer from high computational overhead due to the inability to reuse Key-Value (KV) cache and from incoherent generation arising from learning dependencies over an intractable space of token combinations. We introduce Zarya, a family of hybrid language models that jointly optimizes an autoregressive (AR) objective and a masked-diffusion objective within a single architecture. Zarya structures training data into variable-size slots and employs a curriculum that gradually increases slot granularity, enabling a smooth transition from fine-grained AR learning to coarse-grained diffusion learning. At inference, Zarya provides two distinct decoding paradigms through a unified interface: (i) MDM sampling with first-hitting denoising, and (ii) slotted speculative decoding that interleaves inter-slot diffusion-based selection with intra-slot autoregressive infilling, achieving full KV cache reuse. The training and inference regimes are fully decoupled, allowing a model trained with any configuration to be deployed in either mode. Extensive configurability --- including grouped noise patterns (Prefix Completion, Fill-In-the-Prefix, Fill-In-the-Middle), ordered sampling schedules, and noise-level permutation strategies --- enables flexible research exploration. We release Zarya models publicly in sizes 0.6B, 1.7B, and 4B, demonstrating performance on standard benchmarks while offering a principled integration of autoregressive and diffusion paradigms. --- ### Socialized UAV Cross-Task Learning: Towards Cross-Granularity Collaboration through Hierarchical Interaction Authors: Xinjie Yao, Ruipu Zhao, Yunqi Zhu, Zhihe Fan, Zhoupeng Guo, Weihao Li, Zhen Wang, Qilong Wang, Pengfei Zhu Published: 2026-09-17 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.19867v1 Joint learning across heterogeneous tasks is often treated as task coupling through feature sharing, distillation, or auxiliary supervision. However, in cross-task learning, mismatched representational and supervisory granularities make such coupling prone to interference, teacher bias, or unidirectional collapse. We argue that cross-granularity learning is fundamentally a problem of hierarchical interaction regulation rather than simple task coupling. This issue is particularly evident in UAV perception, where visual shifts and detection--segmentation objectives naturally form coarse- and fine-grained knowledge sources. To systematically study this problem, we introduce CrossUAV, a UAV benchmark for joint object detection and instance segmentation that provides a unified evaluation platform for cross-granularity task collaboration. To address these challenges, we propose Cross-Granularity Socialized Collaboration (CGSC), a progressive and adaptive framework that regulates when, where, and how tasks exchange information across network hierarchies. CGSC progressively activates cross-task interactions and adaptively adjusts the strength according to task contribution, suppressing harmful interference while exploiting complementary coarse- and fine-grained structures. Extensive experiments demonstrate consistent improvements on both tasks, validating hierarchical dynamic interaction as an effective mechanism for cross-granularity collaboration. --- ### Reproducibility is not construct validity: LLM measurement of institutionally situated communication Authors: Veronika Batzdorfer, Carlo Romano Marcello Alessandro Santagiustina Published: 2026-09-17 Categories: cs.AI, cs.CL, cs.CY, q-fin.RM arXiv: https://arxiv.org/abs/2609.19866v1 High annotation reproducibility does not necessarily imply that an LLM-inferred measure captures the construct it is intended to measure. We test this distinction using a dataset from the European Commission's AI Act consultation, linking structured survey responses to free-text consultation submissions from the same stakeholders. LLM annotations of consultation submissions are highly reproducible (intraclass correlations > 0.99), yet show limited convergence with survey-reported measures of the nominal construct they were intended to approximate. Divergence between survey-and LLM-inferred text-based measures varies systematically across stakeholder groups: business associations express greater concern about AI risks in text-based consultations than in survey responses ({g} = +1.0), whereas public authorities and several nonbusiness groups show smaller or negative divergences. Divergences between scores suggest positive spatial autocorrelation across European countries (Moran's I = 0.347, p = 0.036), indicating that stakeholders from neighboring countries tend toward more similar text-based stances towards AI safety concerns. Despite divergence, survey-reported concerns remain strongly associated with support for explainability across all divergence levels. These results demonstrate that LLM annotation reproducibility can coexist with poor construct correspondence and motivate validation procedures that distinguish reproducibility, construct validity, and communication context variation when LLMs are used as measurement instruments. --- ### Pretrained Medical Representations for the Practical Screening of Drug Repositioning Candidates Authors: Yuhei Fujioka, Daitaro Misawa, Shingo Fukuma Published: 2026-09-17 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.19865v1 Representation learning from medical code sequences in electronic health records and medical claims data has been successful in various clinical applications, such as those regarding disease prediction. However, significant challenges remain in extending this approach to the discovery of scientific hypotheses. One reason is that many existing BERT-based models fail to adequately capture the hierarchical structure of medical codes and the complex interactions between diagnoses and treatments. To address these limitations, we propose a new unified pre-training framework that explicitly integrates hierarchical sub-token aggregation, partial masking, and cross-reference mechanisms. The proposed model consistently outperformed existing methods on both pre-training objectives and downstream clinical event prediction tasks, including the onset of dementia and hospitalization. We also conducted an in silico drug repositioning case study targeting Alzheimer's disease. In the hypothesis generation step, our approach successfully rediscovered known promising drugs in a data-driven manner without relying on such external knowledge sources as the literature. Subsequently, in the hypothesis prioritization step, we introduced a Task-Adaptive Representation Approach to alleviate the over-encoding of historical prescription information within diagnostic vectors, enabling the robust prioritization of generated hypotheses. This study establishes an exploratory screening workflow for hypothesis generation and prioritization based on observational associations. Importantly, this framework is not intended to provide causal evidence, but rather to identify promising candidates for subsequent rigorous causal inference. Overall, this study demonstrates that domain-informed representation learning combined with task-adaptive representation control can enable a practical hypothesis discovery workflow. ---