# Research Papers — 2026-09 · bundle page 157 of 266 > Full-text markdown of papers #7801–7850 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/157 [← Previous bundle](https://aipod.dev/papers/archive/2026-09/page/156.md) [Next bundle →](https://aipod.dev/papers/archive/2026-09/page/158.md) ### FreqSpaNet: Frequency and Spatial Learning of SFPF for Physical Layer Hardware Integrity Detection Authors: Xiaoxuan Huang, Jinlong Xu, YiZhe Wang, Meng Zhang, Xian Li, Yuying Bian Published: 2026-09-15 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.17491v1 Unauthorized hardware replacement can preserve a wireless device's logical identity while altering its physical implementation, posing a challenge to hardware integrity verification. Spatio-frequency polarization fingerprints (SFPFs) capture device-dependent responses across multiple frequencies and directions, but their frequency and spatial dimensions exhibit different structural dependencies. We propose FreqSpaNet, an SFPF representation learning network for open set hardware anomaly detection. A frequency branch captures local variations among neighboring frequencies, while a geometry-aware spatial branch models directional relationships using angular information. The two representations are combined through adaptive fusion, and complementary pretraining further captures shared information while preserving the distinct characteristics of the frequency and spatial representations. Experiments show that FreqSpaNet achieves a mean AUROC of 96.31\%, 9.05 points above the baseline. Results under seven hardware replacement scenarios further verify the effectiveness of FreqSpaNet. --- ### LimiX-2: A Contextual Mechanism Network Towards General Structured-Data Intelligence Authors: Xingxuan Zhang, Gang Ren, Hao Yuan, Hao Zou, Hongze Tan, Hui Wang, Jianhao Song, Jiansheng Li, Jiayao Zhang, Jinghan Zhang, Kaifang Li, Lang Mo et al. Published: 2026-09-15 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.17488v1 We introduce LimiX-2, a new model in the LimiX family, developed through model and data scaling guided by our previously established scaling laws. LimiX-2 adopts the Contextual Mechanism Networks (CMNs) paradigm and is pretrained with Context-Conditional Masked Modeling (CCMM). CMNs shifts the organizing principle of in-context learning from target-centric prediction to mechanism-oriented joint modeling. Rather than centering the network on the $p(y \mid x, D_{\mathrm{context}})$ objective of conventional tabular PFNs, it is designed around learning $p(x, y \mid D_{\mathrm{context}})$, a context-dependent representation of the joint structure underlying data generation. Pretraining uses synthetic datasets generated by structural causal models (SCMs) spanning diverse graph structures, functional mechanisms, and observation processes. Evaluations on TabArena, TALENT, and BCCO show that LimiX-2 outperforms current dataset-specific models and tabular foundation models. Beyond predictive performance, the CMN paradigm also promotes causal awareness in LimiX-2: its feature attention encodes direct causal relationships, enabling accurate causal skeleton recovery. --- ### Bridging the Gap Between Homogeneous and Heterogeneous Asynchronous Optimization Is Surprisingly Difficult Authors: Alexander Tyurin Published: 2026-09-15 Categories: math.OC, cs.LG arXiv: https://arxiv.org/abs/2609.17483v1 Modern large-scale machine learning tasks often require multiple workers, devices, CPUs, or GPUs to compute stochastic gradients in parallel and asynchronously to train model weights. Theoretical results typically distinguish between two settings: (i) the homogeneous setting, where all workers have access to the same data distribution, and (ii) the heterogeneous setting, where each worker operates on different data distributions. Known optimal time complexities in these settings reveal a significant gap, with far more pessimistic guarantees in the heterogeneous case. In this work, we investigate whether these pessimistic optimal time complexities can be overcome under different assumptions. Surprisingly, we show that improvement is provably impossible under widely used first- and second-order similarity assumptions for any randomized algorithm. We then turn to the interpolation regime and demonstrate that the weak interpolation assumption alone is also insufficient. Finally, we introduce a minimal combination of irreducible assumptions, strong interpolation and the local Polyak-Lojasiewicz condition, to derive a new time complexity bound that matches the dependence on worker computation times in the best-known result in the homogeneous setting, without requiring identical data distributions. --- ### Det-LIME: Detector-Aware, Multi-Instance Local Interpretable Model-Agnostic Explanations for Automated Marine Mammal Detection Authors: Jiayi Zhou, David W. Johnston, Brinnae Bent Published: 2026-09-15 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2609.17479v1 Despite the rapid uptake of black-box object detectors in marine mammal research and monitoring, explainability techniques are rarely integrated into conservation workflows. Furthermore, most classification-oriented explainability tools are ill-suited to detection tasks involving imagery of social organisms or those with colonial life histories, as they ignore multiple detections within a scene and produce single-instance outputs that blur evidence across individuals. These methods also generate low-resolution, often biologically irrelevant visuals, limiting their utility for debugging, targeted data augmentation, and refined data collection. We proposed Det-LIME, a detector-aware, multi-instance adaptation of Local Interpretable Model-Agnostic Explanations (LIME) that produced instance-specific, box-aligned explanations by combining per-detection weighting, a proximity kernel that emphasizes regions near each box, and Intersection-over-Union-based matching to track the same instance across perturbations. We evaluated Det-LIME on aerial drone imagery for harbor seal detection, with an additional seabird case study to assess generality, and compared it with vanilla LIME, Stabilized LIME, Deterministic LIME, and gradient-based attribution methods. Using the Attribution Ratio and Max Saliency Hit Rate metrics, we showed that Det-LIME consistently improved multi-instance attribution. In practice, these higher-resolution, instance-aware explanations provide insight into model outputs and support post-processing, debugging, and actionable improvements in modeling and data collection or augmentation. --- ### Bias-Induced Crossover in Absolute Capacity of Dense Associative Memory Authors: Yuto Sakurai, Takeaki Shimokawa, Kazunori Iwata, Kazushi Mimura Published: 2026-09-15 Categories: cond-mat.dis-nn, cs.LG arXiv: https://arxiv.org/abs/2609.17477v1 The absolute capacity of dense associative memory has mainly been analyzed for unbiased patterns. Here we examine the effect of bias in centered binary patterns under the Krotov-Hopfield single-site criterion $P_{\mathrm{error}}=1/N$, where $P_{\mathrm{error}}$ is the probability that a single-site flip lowers the energy of a stored pattern and $N$ is the number of neurons. Each pattern component takes $1-q$ with probability $q$ and $-q$ otherwise, where $0<q\le1/2$. For polynomial interactions of order $n$, a signal-to-noise analysis gives an absolute capacity of order $N^{n-1}/\ln N$ at $q=1/2$. For fixed $q<1/2$, however, the capacity is $O(N^{n/2})$ for even $n\ge4$ and $O(N^{(n+1)/2})$ for odd $n\ge5$. For $n=3$, both the unbiased and fixed-bias capacities remain $O(N^2/\ln N)$. For $n\ge4$, these different asymptotic forms imply a nonuniform large-$N$ limit near $q=1/2$. Asymptotic matching predicts a bias-induced crossover in the region $1-2q=O(\ln N/N^{\lfloor n/2\rfloor-1})$. The crossover originates from a bias-dependent crosstalk mean that reduces the stability of sites carrying the more frequent value $-q$. Computer simulations are compared with the finite-size conditioned-Gaussian predictions. An activity-dependent control potential that cancels the conditional crosstalk mean restores the $N^{n-1}/\ln N$ capacity for fixed $0<q<1/2$ within the conditioned-Gaussian approximation. --- ### JustFit: Just-in-Time State Management for Local LLM Serving Authors: Yuhua Chen Published: 2026-09-15 Categories: cs.AI, cs.PF arXiv: https://arxiv.org/abs/2609.17475v2 Local agents need memory for model execution and working history. We present JustFit, an MLX runtime that coordinates their overlapping allocations: KVExec executes and checkpoints four-bit KV with bounded workspace, PhaseSwap loads phase-dependent components, and StateTrans preserves history across execution modes. With Qwen3.8-27B MXFP4 on a 24 GiB M4 Pro MacBook, JustFit reaches 327,680 retained positions across two requests, 10.67 times the evaluated baseline's 30,720-position single-request record. One request completes the full 262,144-position native window at median 5.986 tokens/s. Each shape completes 16,384 outputs per request in three fresh processes: B1 uses one cold build and two prefix extensions; B2 uses three ordered prefix extensions (Section 4). Image encoding can proceed while preserving a live 196,608-input text request. A controlled, repetitive 32K+6K workload reaches median 18.284 tokens/s at 15,626 MiB; a separate AIME 2026 evaluation scores 29/30. Coordinating execution and state lifetimes makes longer histories feasible on personal hardware. --- ### JustFit: 200K-Token LLM Serving on a 24 GiB Laptop with Just-in-Time State Management Authors: Yuhua Chen Published: 2026-09-15 Categories: cs.AI, cs.PF arXiv: https://arxiv.org/abs/2609.17475v1 Capable open-weight models make local coding and reasoning attractive, but their context and execution state strain laptop memory. We present JustFit, an MLX-based inference runtime that combines KVExec for compressed KV execution, PhaseSwap for component residency, and StateTrans for state-preserving serving transitions. These mechanisms fuse reconstruction and coordinate just-in-time materialization and release, independently of model-weight quantization. In full-execution capacity tests on a 24 GiB M4 Pro MacBook running Qwen3.8-27B MXFP4, three independent runs complete 196,608 input and 16,384 output tokens, increasing completed single-request context from the mlx-vlm baseline's 30,720 positions to 212,992 (6.93x); a separate two-request run retains 229,376 positions in aggregate. In separate performance tests, a 32K-input, 64-output probe reaches 19.11 tokens/s, and a repeated 32K+6K workload has a median peak process footprint of 16,374 MiB. The integrated runtime answers 29 of 30 AIME 2026 problems correctly, showing how compact state and lifetime-aware execution expand local serving capacity while supporting extended generated reasoning. --- ### Coupled Calibration and Learning: Mitigating Teacher Bias in LLM Distillation without Target-Domain Reward Feedback Authors: Haichen Hu, Yuheng Zhang, David Simchi-Levi Published: 2026-09-15 Categories: cs.LG, cs.AI, math.ST, stat.ML arXiv: https://arxiv.org/abs/2609.17474v1 Large language model (LLM) distillation aims to transfer the capabilities of a powerful teacher to a smaller student. Direct imitation, however, can also transfer the teacher's systematic bias and errors. This challenge is particularly pronounced under covariate shift, when the teacher's reliability on target questions is uncertain and target-domain reward feedback is unavailable. We propose Coupled Calibration and Learning (CCL), an LLM distillation algorithm that couples teacher calibration with student updates through token-level branching, using reward feedback only on source questions. Each iteration calibrates the teacher using source feedback and then uses the calibrated teacher to train the student on target questions. The updated student, in turn, informs subsequent calibration. In an autoregressive policy framework, we prove that the output student's expected average Kullback-Leibler divergence to the oracle student converges to zero at a polynomial rate in the number of iterations. The oracle maximizes the true reference-regularized target reward within the student class, which need not represent the unrestricted optimal policy. Our analysis quantifies the progress of projected student gradient updates while controlling the error in teacher calibration. We further establish a separation from regularized direct matching: its error relative to the oracle student can remain bounded away from zero even when the teacher achieves higher regularized target reward than every student policy. These results demonstrate that LLM distillation can overcome persistent teacher bias and recover the optimal student through coupled calibration and learning, without target-domain reward feedback. --- ### Decomposition Buys Integrity, Not Yield Authors: Rong He Published: 2026-09-15 Categories: cs.MA, cs.AI, cs.DC arXiv: https://arxiv.org/abs/2609.17464v1 Multi-agent systems split a task across a tree of agents and justify the split with folklore: smaller contexts, cleaner separation, parallelism. We ask what the split does to how much of what the leaves discover reaches the root. Model a decomposition as a tree in which an agent handed $b$ items keeps any one with probability $r(b)$. If $r(b)=1/b$, every tree delivers exactly one finding, for every task size and every shape; we verify this to $2.4 \times 10^{-15}$ on 20,000 random irregular trees. If $r(b)=Cb^{-δ}$, a depth-$k$ tree over $N$ findings yields $C^k N^{1-δ}$: task size and architecture separate, and architecture contributes only $C \le 1$ per level, so flat is optimal for yield and no arrangement of agents escapes the exponent $δ$. On 600 production deep-research traces $δ= 0.34$ (0.30, 0.38), by three identifications that do not share a failure mode. At a hop where item boundaries come from the tool rather than a text heuristic, and where $b=1$ occurs 550 times, $C = 0.571$ (0.527, 0.615) is observed rather than extrapolated, over 16,082 hops. A tier also costs alignment: on 1,012 annotated multi-agent traces one brief in sixteen goes off-target, giving $μ= 0.939$ and a per-tier penalty $Cμ= 0.536$. Depth is bought on two other axes. The root context is the only state that persists and the only one that cannot cheaply forget, and depth cuts its exposure from $N$ items to $N^{1/k}$. Depth is also cheaper: production flat agents bill as $N^{1.39}$, not the $N^2$ an append-only context predicts, and at equal spend two tiers overtake flat at 403 findings. Across every parameter we measured the model says 0.7% to 11.3% of production sessions are worth delegating, against 7.8% that do. A hazard model on 743,819 production tool calls finds that delegation does not respond to a filling context and is instead an opening move. --- ### Tables Decoded: DELTA for Structure, TARQA for Understanding Authors: Jahanvi Rajput, Dhruv Kudale, Saikiran Kasturi, Utkarsh Verma, Ganesh Ramakrishnan Published: 2026-09-15 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2609.17458v1 Table understanding is a core task in document intelligence, encompassing two key subtasks: table reconstruction and table visual question answering (TabVQA). While recent approaches predominantly rely on vision- language models (VLMs) operating on table images, we propose a more scalable and effective alternative based on structured textual representations. These representations are easier to process, align more naturally with LLMs, and eliminate the need for language-specific visual encoders, making them particularly suitable for multilingual documents. We present DELTA, which separates physical structure recognition, logical structure recognition, and OCR to extract both layout and content accurately. DELTA outputs tables in Optimised Table Structure Language (OTSL), a compact and unified format that encodes cell arrangements and textual content. On table structure recognition (TSR), DELTA achieves TEDS- Structure scores comparable with state-of-the-art methods across FinTabNet, PubTabNet, and PubTables-1M. We further establish its robustness on non-English tables through our curated Hindi benchmark, TORQUE. Building on this, we introduce TARQA, an LLM fine-tuned on OTSL sequences. Our approach yields gains of 9.3 p.p. on WTQ (TabQA) and 9.2 p.p. on FinTabNetQA (TabVQA), respectively. On TORQUE, our method ranks second among all VLMs and DELTA + LLM variants. We release our code, models, and benchmark at: https://github.com/Tihiitborg/Tables-Decoded --- ### ORCA: Occlusion-Aware Refinement and Completion for Novel View Synthesis Authors: Weronika Jakubowska, Maciej Zięba, Przemysław Spurek Published: 2026-09-15 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.17450v1 Novel-view synthesis from a single image is a fundamentally ambiguous problem. As the camera moves away from the input viewpoint, previously hidden regions become visible, exposing missing geometry and holes in the reconstructed scene. Existing methods often rely on generative models to complete such regions. However, many of these artifacts are small gaps near depth boundaries and do not require generating new scene content. In order to eliminate expensive process of generating image we introduce ORCA, an occlusion-aware method for reconstructing and completing explorable 3D scenes from a single image. ORCA first introduces 3D structure into a Gaussian-anchor representation using monocular depth while preserving the original camera-ray correspondence. During scene exploration, missing regions are handled based on their size and structure. Small disocclusions are repaired using RGB-D information already available in the reconstruction, while generative inpainting is reserved for larger regions that cannot be reliably recovered from the scene. New Gaussian anchors are added and optimized locally without modifying the existing representation. By reducing unnecessary reliance on generative inpainting, ORCA limits generation-induced hallucinations and better preserves the content and structure of the original scene. On DIV2K, ORCA improves novel-view quality over VistaDream across all reported metrics, increasing MUSIQ from 61.60 to 68.71 and CLIP-IQA from 0.474 to 0.574. These results show that many novel-view artifacts can be repaired effectively by reusing information already present in the reconstructed scene. --- ### BrainFocus: EEG-Guided ROI Selection for Efficient Vision-Language Models Authors: Yihui Peng, Guorui Lu, Qinyu Chen Published: 2026-09-15 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.17443v1 Vision-language models (VLMs) achieve strong visual question answering (VQA) performance, but processing large cluttered images is computationally expensive when only a small region is relevant. Electroencephalography (EEG) signals, which capture human neural responses to visual stimuli, can provide a human-derived semantic cue about the region of interest (ROI). However, EEG-guided visual category decoding remains imperfect, making direct ROI routing unreliable. In this work, we propose BrainFocus, a reliable EEG-guided efficient VLM framework for VQA. An EEG classifier predicts a target category, and a YOLO detector localizes the matching ROI. The VLM receives the cropped ROI only when both predictions pass confidence thresholds; otherwise, it processes the full image. For evaluation, we build on EEG-ImageNet to construct a 40-class benchmark comprising generated cluttered images and real object-centric images, with target-ROI annotations and 600 English visual question-answer pairs. Across Qwen3.5-VL 2B, 4B, and 9B models, BrainFocus improves VQA accuracy by 4.14-9.87 percentage points (pp) on cluttered scenes while reducing input tokens and total tokens by 23.2%-39.4% and 23.2%-39.3%, and end-to-end floating-point operations (FLOPs) by 23.2%-39.5%. These results demonstrate that EEG can guide efficient VLM inference even when its semantic decoding is imperfect. --- ### Reduced-Space Multi-Fidelity Bayesian Optimization of Process Simulation Models Authors: Niki Triantafyllou, Andrea Bernardi, Maria M. Papathanasiou Published: 2026-09-15 Categories: cs.LG, math.OC arXiv: https://arxiv.org/abs/2609.17440v1 Optimizing industrial process flowsheets is often computationally prohibitive due to the high cost of rigorous simulations and the curse of dimensionality inherent in complex design spaces. To address these challenges, we present a reduced-space multi-fidelity Bayesian optimization (RS-MFBO) framework designed for high-dimensional, expensive black-box functions. The approach integrates Global Sensitivity Analysis (GSA) for dimensionality reduction with a fidelity-augmented Gaussian process that captures correlations between low-cost approximations and expensive high-fidelity evaluations. A cost-aware acquisition strategy, augmented with cooldown and promotion mechanisms, adaptively guides the allocation of samples across fidelities. The framework is validated on two distinct industrial process simulators: a plasmid DNA bioprocess in SuperPro Designer and a green fuel synthesis plant in Aspen HYSYS. Results across diverse economic and physical objectives demonstrate that the proposed method substantially reduces the number of high-fidelity simulator evaluations while maintaining competitive optimization performance compared to single-fidelity baselines. These results highlight RS-MFBO as a scalable, simulator-agnostic approach for cost-constrained black-box optimization. --- ### Evaluating Verified Autonomy in Quantum Engineering Authors: Naixu Guo, Changhao Li, Siyu Cheng, Qicheng Tang, Binzhao Luo, Bikun Li, Yuxuan Du, Shihao Ru, Jiaqi Cai Published: 2026-09-15 Categories: quant-ph, cs.AI arXiv: https://arxiv.org/abs/2609.17439v1 Reliable quantum engineering is essential for turning quantum phenomena into practical technologies. As quantum platforms grow in scale and complexity, their characterization and operation require increasing human effort and coordination. Scientific artificial intelligence agents, which can plan experiments, operate instruments, and analyze observations, offer a promising route towards autonomous quantum engineering. Yet whether current agents can perform reliably in this setting has not been systematically established. To fill this gap, we developed Quantum-Harbor, a virtual laboratory that provides a controlled execution environment for agents to interact with quantum systems. This design enables direct verification of both the actions taken and the conclusions drawn. Building on this framework, we introduce QIQCBench, a benchmark of $49$ expert-authored tasks spanning multiple layers including calibration and control, error correction and compilation, sensing and networking. Across $17$ frontier agentic systems, QIQCBench reveals wide variation in verified performance. These results expose a substantial gap between demonstrating capability and achieving reliable operation, and establish Quantum-Harbor as a foundation for measuring progress towards verified autonomy in quantum engineering. --- ### Right Tool, Right Job: Native-Language Evaluation, Tokenizer Sensitivity, and Methodological Findings from a French-Only BabyLM Authors: Adam Zachary Wasserman, David Beauchemin Published: 2026-09-15 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.17435v1 We submit MéTRON-FR, a 125M GPT-2 pretrained on 92.47M words of French, to the BabyLM 2026 Strict track. It scores 85.97 +/- 0.17% on QFrBLiMP (a native Quebec-French benchmark of grammatical minimal pairs) and 62.80% on the BabyLM-weighted leaderboard. A cross-lingual GLUE (General Language Understanding Evaluation) protocol that combines French task-data translation with rank-16 LoRA (Low-Rank Adaptation) produces a sharp task-type gradient: relational tasks gain measurably, while world-knowledge tasks regress. Bilingual Lexicon Induction aligns the French embeddings to GPT-2 at p@1 = 68.84 +/- 8.61%, 18X above chance, suggesting cross-lingual alignment tracks acquired grammatical competence rather than training duration. An ablation study shows that single-token zero-shot scoring is dominated by tokenizer and template artifacts at the child scale, motivating tokenizer-swap sensitivity, placebo-controlled prompting, and native-language minimal-pair benchmarks as standard diagnostics. --- ### CareMirror: Bringing Caregiver Wellbeing into the Dementia Care Ecosystem Authors: Jiayue Melissa Shi, Ethan Nguyen, Drishti Goel, Upasana Natarajan, Shashwat Srivatsa, Daniel S. Brown, Violeta J. Rodríguez, Dong Whi Yoo, Ravi Karkar, Koustuv Saha Published: 2026-09-15 Categories: cs.HC, cs.AI, cs.CL, cs.CY arXiv: https://arxiv.org/abs/2609.17434v1 Family caregivers of people living with dementia shoulder emotional and practical responsibilities, yet their own wellbeing often remains peripheral to dementia care. We built CareMirror, an envisioned caregiver wellbeing ecosystem with interconnected caregiver- and clinician-facing interfaces for longitudinal reflection, personalized support, and caregiver-controlled sharing with clinical care. We conducted semi-structured interviews with 14 caregivers, using CareMirror as a design probe to examine how they perceived this ecosystem and what expectations, concerns, and boundaries emerged around clinical connection. Caregivers valued attention to their wellbeing, longitudinal awareness, context-sensitive support, and clinical visibility when it could lead to meaningful follow-up. However, repeated reflection could become burdensome or emotionally difficult, automatic clinical sharing could inhibit candid disclosure, and participants wanted control over what information entered clinical care. They also expected AI to support reflection and communication without replacing caregiver voice or clinician judgment. We contribute design considerations for proactive, clinically connected caregiver wellbeing support. --- ### Learning-Guided Planning in Large Dynamic Action Spaces: Budgeted Tree Search for One-to-Many Mobile Charging Authors: Liang-Ching Tao, Pi-Chung Wang Published: 2026-09-15 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2609.17429v1 Many learned sequential decision systems map the current state directly to an action. That shortcut becomes brittle when candidate actions are numerous, geometrically structured, and rebuilt with the state. One-to-many mobile charging makes this setting concrete: with N=250 sensors, the initial state induces about 1,125 candidate charging-stop actions; each chosen stop simultaneously serves its in-range sensors, and the action universe changes as sensors die. LP-BTS is a learning-guided planning architecture: a graph proposal policy concentrates a small candidate support, a learned value critic evaluates leaves, and edge-budgeted PUCT compares short simulated futures before committing an action. Because the policy scores this set without a fixed output head, a single frozen checkpoint covers every evaluated setting, spanning action universes from 736 to 2,813 stops. Matched ablations reveal complementary effects: uniform sampling costs 8.8 survival percentage points, while, with targeted support fixed, PUCT jointly retains 1.4 points (about 3.5 of 250 sensors) and direct policy selection travels 23% farther. On a prospectively specified, sealed 30-scenario confirmatory bank evaluated once, LP-BTS attains the highest observed survival (0.4545) and alive-AUC (0.8031). Its estimated survival advantage over the strongest domain-engineered comparator is +0.0066 (95% CI (-0.0037, +0.0184)), an unresolved difference, while it exceeds a deadline heuristic and two source-derived direct-policy reconstructions on every paired scenario. Both learned rows are trained, source-derived reconstructions of variants reported by Gong et al. In this setting, the results provide controlled evidence about learning-guided planning in a large, dynamic action space. --- ### Tracking the Unseen: An Occlusion-Robust Framework for Target Tracking Under Full and Long-Term Occlusion Authors: Mais Mohammed, Sharifa Mohammed, Hanan Awadh, Haneen Bamaas, Raghad Bawazeer, Elham Alghamdi Published: 2026-09-15 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2609.17427v1 Real-time multi-object tracking systems remain highly vulnerable to full and long-term occlusion, where targets temporarily or completely disappear from the camera's field of view. Conventional trackers may terminate trajectories prematurely, resulting in identity loss and reduced situational awareness in applications such as defense and surveillance. This work proposes an occlusion-robust target tracking framework that maintains target identity and trajectory continuity through the integration of YOLOv11n object detection, Kalman Filter motion prediction, and occlusion-aware appearance-based re-identification. The framework consists of three stages: object detection, position estimation during occlusion, and identity recovery after target reappearance. Six Re-Identification (Re-ID) architectures were evaluated within the same tracking framework under identical conditions, with the Occlusion-Aware Mask Network (OAMN) achieving the best overall performance and therefore selected for the final pipeline. The framework was benchmarked against OccluTrack on the public OVIS dataset, achieving relative improvements of 18.1 percent in Multiple Object Tracking Accuracy (MOTA) and 25.1 percent in Identity F1 Score (IDF1), while reducing identity switches by 12.8 percent. On a custom military dataset simulating surveillance and battlefield-like environments with long-term occlusion, the framework achieved a MOTA of 0.734 and an IDF1 of 0.729, corresponding to relative improvements of 14.2 percent and 5.8 percent over OccluTrack. The system demonstrated strong tracking continuity, robust identity preservation, and reliable trajectory estimation under challenging occlusion conditions, highlighting its effectiveness for defense-related surveillance applications requiring continuous target tracking during visibility loss. --- ### SlotDiT: Object-Centric Representations for Diffusion Transformers Authors: Gjergj Plepi, Sven Behnke Published: 2026-09-15 Categories: cs.CV, cs.RO arXiv: https://arxiv.org/abs/2609.17414v1 Text-conditioned latent diffusion models perform strongly in video generation and are promising backbones for robotic applications. However, existing approaches rely on pixel-level or VAE-based latent representations that lack explicit semantic structure, leaving the impact of the representation space largely unexplored. Slot-based object-centric representations offer a structured alternative by decomposing scenes into object-level latents, or slots. While they have shown success in dynamics modeling and planning, they have not yet been explored for diffusion-based generative modeling. We introduce SlotDiT, a text-guided Diffusion Transformer (DiT) that operates in a slot-based latent space. Given a reference image and a language instruction, SlotDiT decomposes the scene into object-centric slots representing individual entities. Conditioned on the instruction and observed scene context, the model autoregressively denoises future slot trajectories to predict scene dynamics. To systematically investigate latent-space design for diffusion transformers, we compare slot-based representations against VAE-based and semantics-aligned alternatives within a unified DiT framework. Our experiments show that using slots as DiT latents yields competitive video generation quality while consistently improving task-completion rates across four robotic datasets. Furthermore, their compact representation provides a computationally efficient alternative to VAE-based and semantics-aligned latent spaces. Overall, our results demonstrate that object-centric structure is a powerful inductive bias for diffusion-based generative modeling in robotic environments. The project page is available at https://slot-dit.github.io/. --- ### SSC-Priors: Exploring Semantic and Visibility Priors to Boost Lidar Semantic Scene Completion Authors: Tetiana Martyniuk, Jonathan Seele, Alexandre Boulch, Gilles Puy, Renaud Marlet, Raoul de Charette Published: 2026-09-15 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.17413v1 This paper investigates easy strategies to boost the performance of existing networks for lidar semantic scene completion (SSC) without requiring complex architectural redesigns. The fact is that, over the last years, SSC methods have mostly pursued architectural innovations, making the models heavier and more complex, e.g., by jointly training a point cloud semantic segmentation branch. In this work, we take a step back and explore two priors used as simple ingredients (possibly noisy) to improve existing approaches: semantic pseudo-labels and sensor visibility information. Concretely, we provide both kinds of information directly as additional inputs to a given SSC network, requiring only a minimal adaptation of the original architecture. We first demonstrate that endowing input point clouds with semantic pseudo-labels from off-the-shelf segmenters significantly improves the performance of existing SSC models. In fact, by evaluating these models against an oracle, we establish that high-quality semantic priors are a primary driver of semantic gains (mIoU), and that the SSC model can be trained just once with ground-truth semantics and then exploited without retraining using any segmenter. Furthermore, we equip the input lidar point cloud with visibility information that distinguishes between empty spaces (between the lidar and a scanned point) and unknown spaces (outside of lines of sight), providing a secondary performance boost across the tested architectures. We study the design space of data for representing visibility information and bound the remaining headroom with a ground-truth oracle on the free-space labels. On SemanticKITTI, these enhancements make older models competitive with state-of-the-art systems across four architectures, in one case even outperforming them. On the SSCBench-nuScenes benchmark, both priors also transfer with the sparser 32-beam sensor. --- ### Enhancing Accessibility of Medical Texts through Large Language Model-Driven Plain Language Adaptation Authors: Ting-Wei Chang, Hen-Hsen Huang, Hsin-Hsi Chen Published: 2026-09-15 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.17398v1 This paper addresses the challenge of making complex healthcare information more accessible through automated Plain Language Adaptation (PLA). PLA aims to simplify technical medical language, bridging a critical gap between the complexity of healthcare texts and patients' reading comprehension. Recent advances in Large Language Models (LLMs), such as GPT and BART, have opened new possibilities for PLA, especially in zero-shot and few-shot learning contexts where task-specific data is limited. In this work, we leverage the capabilities of LLMs such as GPT-4o-mini, Gemini-1.5-pro, and LLaMA for text simplification. Additionally, we incorporate Mixture-of-Agents (MoA) techniques to enhance adaptability and robustness in PLA tasks. Key contributions include a comparative analysis of prompting strategies, finetuning with QLoRA on different LLMs, and the integration of MoA technique. Our findings demonstrate the effectiveness of LLM-driven PLA, showcasing its potential in making healthcare information more comprehensible while preserving essential content. --- ### Coding Agents Have Converged: Why the SWE-bench Leaderboard Can No Longer Order Its Top Entries, and What to Measure Instead Authors: Fengshuo Liu, Ying Liu, Ruize Sun, Lie Luo, Siyuan Guo Published: 2026-09-15 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2609.17394v1 Small differences on coding-agent leaderboards are often read as an ordering of systems. We audit whether the published verdicts support this reading, using 254 SWE-bench submissions across four splits without running models. On Verified, the leading two entries each resolve 396 of 500 instances. The top ten share 285 successes and 51 failures, leaving 164 instances that distinguish their outcomes. Frontier solution sets have median nesting 0.935 against a score-implied baseline of 0.774, indicating strongly shared successes. Scores also depend on the evaluated model-scaffold pair: observed within-model scaffold ranges reach 29.8 percentage points, compared with the 8.8-point spread of the top thirty. Six of nine cell-mean interaction tests remain significant after Holm correction, although this observational design does not identify causal scaffold effects. Exact paired McNemar tests separate none of the 29 adjacent Verified top-thirty pairs at alpha=0.05, while the larger Test split separates 14 of 23. A stated leader-based rule yields three descriptive tiers, or two after Holm correction; non-rejection does not establish equivalence. We release the partition and a five-step audit protocol that profiles shared outcomes, tests paired differences, reports grouping sensitivity, and estimates the instance budget needed for resolution. The results motivate reporting comparison-set-specific resolution and model-scaffold provenance instead of interpreting small aggregate gaps as established rank differences. --- ### FlashVector: Agent for Hierarchical Model Serving Stack Optimization Authors: Qi Wu, Lohan Lemire, Kai Meng, Zhongmou Cai, Raphael Bargues, Petr Zhitnikov, Zeyuan Cao, Yao Wang, Shujun Bian, Wei Chen, Sean Sheng Published: 2026-09-15 Categories: cs.AI, cs.PF arXiv: https://arxiv.org/abs/2609.17391v1 Model serving is one of the largest cost drivers in production recommender systems. Maximizing its throughput requires navigating a deeply layered hierarchy: GPU kernels, the ML framework computation graph, the model server, and on-demand feature processing -- each demanding specialized domain expertise. Such cross-layer expertise is inherently difficult to acquire, and does not scale with a workload that continuously grows and evolves, leaving significant cost efficiency gains unrealized. While recent AI agents have demonstrated human expert level efficiency in standalone GPU kernel optimization, automated tuning and optimization for the rest of the serving stack remain largely unexplored. We present FlashVector, an agentic system that optimizes performance across all layers of the model serving stack. The key contribution is an extensible framework to generalize the single kernel optimization agent paradigm to heterogeneous technical stacks, and to deliver performance improvements holistically. After deployment in Unity's Vector advertising platform, FlashVector achieved up to 2x throughput increase and up to 1.98x latency speedup on model server, and up to 1.6x throughput increase on feature store. These optimizations were discovered not only at the GPU kernel and computation graph levels, but also across the other components of the model serving stack, such as the model server (NVIDIA Triton's C++ codebase) and the on-demand feature transformation service (Python codebase), demonstrating the extensibility of the framework to more complex system architectures. --- ### PanoGS-SLAM: Panoramic 3D Gaussian Splatting SLAM Authors: Yongqi Mao, Hao Shi, Yufan Zhang, Zhonghua Yi, Xiangfei Guo, Kaiwei Wang Published: 2026-09-15 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.17387v1 Real-time dense SLAM is a core capability for robotics applications that require robust localization and high- quality mapping in dynamic or fast-changing environments. Recent 3D Gaussian Splatting (3DGS)-based SLAM methods have shown promising performance, but most are designed for narrow-FoV pinhole cameras, where limited angular coverage weakens pose observability and often leads to unstable photo- metric optimization under rapid motion and large viewpoint changes. We present PanoGS-SLAM, the first panoramic dense SLAM system built on 3D Gaussian Splatting. Our method per- forms differentiable rendering and pose optimization directly in the spherical domain, enabling omnidirectional photometric constraints for more stable tracking. To improve geometric consistency and robustness, we introduce (1) a sphere-consistent photometric loss that compensates for the area distortion of equirectangular projection, and (2) a depth-guided Gaussian initialization strategy that stabilizes incremental mapping in newly observed regions. Extensive experiments on both real and synthetic panoramic benchmarks (PALVIO and SynPano) show that PanoGS-SLAM consistently outperforms geometric and GS-based baselines in tracking accuracy and rendering quality, while achieving fast front-end convergence and real-time perfor- mance. In addition, controlled field-of-view experiments reveal a clear monotonic improvement in optimization conditioning and convergence stability as angular coverage increases, high- lighting the fundamental role of sensing geometry in shaping the optimization landscape of differentiable Gaussian-based SLAM. The source code will be made publicly available. --- ### Bridging the Confidence Gap: Temperature Scaling for Calibrating Test-Time Prompt Tuning Authors: Yuwei Liang, Jian Liang, Dapeng Hu, Yinuo Xu, Ran He Published: 2026-09-15 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.17386v1 Test-time prompt tuning (TPT) enables adaptation on a single test instance, achieving improved accuracy but often sacrificing calibration performance. Most existing calibration methods introduce additional regularization terms to promote dispersion across text embeddings and reduce calibration error, yet these methods often suffer from a drop in accuracy. Motivated by the well-calibrated nature of zero-shot predictions, we propose CoTS, a simple yet effective post-hoc calibration method that preserves accuracy. Specifically, CoTS applies temperature scaling to minimize the confidence gap between adapted and zero-shot predictions. To fully exploit the potential of multiple augmentations during adaptation, we introduce a weak-strong ensemble strategy that further boosts accuracy. We then apply CoTS to this ensemble, termed E-CoTS, to maintain its well-calibrated property. Extensive experiments on diverse datasets and backbones show that our approaches effectively mitigate miscalibration without compromising primary accuracy. For instance, E-CoTS reduces the average expected calibration error of TPT from 11.90% to 5.38% on ImageNet variants, while even increasing accuracy from 60.74% to 62.95%. Moreover, when integrated with existing calibration methods, E-CoTS usually enhances both accuracy and calibration simultaneously. --- ### OPEN-1B: A Fully Auditable Training Run Authors: John Donaghy, Brian Wilcox, Oğuzhan Ersoy, Shikhar Rastogi, Adam St Arnaud, Alexey Titov, Jordan Greenberg, Ben Fielding, Harry Grieve Published: 2026-09-15 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.17380v1 Open-source language models have a reproducibility problem. Despite releasing weights, training data, and recipes, none of them are provably reproducible due to the non-associativity of floating-point arithmetic. Deep learning frameworks often offer a deterministic execution mode, allowing reproducible operations on the same machines. Unfortunately, this determinism does not carry across hardware such that a user can verify that a released checkpoint was actually produced using the declared training recipe. This leaves room for undisclosed data, injected biases, or backdoors that existing techniques such as proof-of-learning or proof-of-training-data cannot rule out. We introduce a new tier of model transparency, fully auditable, in which every operation on every data sample during training is independently reproducible on heterogeneous commodity hardware with bitwise certainty. By imposing a definite order on the sources of training nondeterminism, GPU kernel reductions, data batch ordering across a data-parallel cluster, and inter/intra-node collective communication, we make it possible to replay any individual step of a large, distributed training run on a single piece of commodity hardware and check it against the published trajectory. Because replaying an entire run on one machine is infeasible, we support this with a collective verification scheme in which many independent auditors each certify individual steps, together covering the whole run. We release Open-1B, a model trained under this regime, together with its full pretraining dataset, every intermediate checkpoint, the training codebase, and the audit harness needed to reproduce and verify any step of its training. --- ### Large Language Models Develop Belief State Geometry In-Context Authors: Daniel Balcells, Andrew Jun Lee, Chirag Rastogi, Paul M. Riechers, Adam Shai, Xavier Poncini Published: 2026-09-15 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2609.17376v1 Large language models (LLMs) trained on next-token prediction exhibit remarkable in-context learning (ICL) abilities, yet the representations that support ICL remain poorly understood. We consider such representations in a controlled setting: prompting LLMs with data emitted from hidden Markov models (HMMs) and probing for the corresponding belief state -- the posterior distribution over the HMM's hidden states given the observed token history. Across six open-source LLMs prompted with data from 40 HMMs selected for non-trivial belief structure, we find that belief states are linearly decodable from residual stream activations, with peak probe $R^2$-values from 0.83-0.99 across HMM and LLM combinations, ranging from early to late layers. To establish functional relevance, we intervene directly on the probe-identified subspace via patching and steering, resulting in downstream prediction quality on the order of the untampered model, while controls degrade performance substantially. Together, these results provide representation-level evidence that ICL in open-source LLMs approximates optimal Bayesian prediction over a context-inferred generative model. More broadly, our findings extend prior results linking input-distribution structure to activation geometry: from toy networks trained explicitly on HMM data to production-scale LLMs. --- ### Same Words, Different Actions: Paired Turn-Taking Evaluation under Rewritten Dialogue Contexts Authors: Shuofeng Zhao, Hongwei Cai, Wenke Fan, Qingxiang Guo, Zhou Wang, Dawei Yang, Zhiyang Zhou, Yingxin Shang, Weixu Wang, Lin Yang, Shuran Zhou, Yang Song Published: 2026-09-15 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.17360v2 Real-time spoken dialogue systems must distinguish interruptions that require yielding the floor from backchannels that permit continued speaking. Existing benchmarks typically score events independently and may therefore assign high scores to systems with fixed action preferences rather than context-sensitive decision policies. We introduce ECHO, a paired diagnostic benchmark for Chinese turn-taking evaluation. ECHO pairs examples with the same overlap transcript but contrasting preceding multi-turn dialogue contexts, with one requiring Yield and the other Keep. It additionally includes off-talk examples for diagnosing unnecessary yielding. We introduce pair accuracy, which requires correct decisions on both members of a pair and assigns no credit to constant-action policies. Experiments on four speech systems show that three exhibit a severe over-yielding bias: they correctly keep the floor on fewer than 13% of backchannels, resulting in near-zero pairwise success rates equal or less than 4%. While the remaining system remains comparatively balanced across contexts, these findings broadly demonstrate that interruption-only evaluation can severely overestimate practical turn-taking reliability. --- ### ECHO: A Matched-Contrast Benchmark for Context-Sensitive Turn-Taking in Full-Duplex Dialogue Authors: Shuofeng Zhao, Hongwei Cai, Wenke Fan, Qingxiang Guo, Dawei Yang, Zhou Wang, Zhiyang Zhou, Yingxin Shang, Weixu Wang, Lin Yang, Shuran Zhou, Yang Song Published: 2026-09-15 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.17360v1 Full-duplex spoken dialogue systems must distinguish interruptions that require yielding the floor from backchannels that permit continued speaking. Existing benchmarks typically evaluate events independently and may therefore reward fixed action preferences rather than context-sensitive decisions. We introduce ECHO, a paired diagnostic benchmark for Chinese full-duplex turn-taking. ECHO pairs examples with the same overlap transcript but contrasting preceding multi-turn dialogue contexts, with one requiring Yield and the other Keep. It additionally includes off-talk examples for diagnosing unnecessary yielding. We introduce pair accuracy, which requires correct decisions on both members of a pair and assigns no credit to constant-action policies. Experiments on multiple full-duplex systems show that most exhibit a pronounced bias toward \textsc{Yield}, performing substantially better on interruptions than on backchannels, while another system remains comparatively balanced. These findings demonstrate that interruption-only evaluation can overestimate practical turn-taking reliability. ECHO and its metadata will be publicly released. --- ### Hybrid Variational Quantum Circuits for Multivariate Regression and High-Dimensional Data Reconstruction Authors: Koffi Ognandon Ayena, Frédéric Holweck, Serge Iovleff, Amah S d'Almeida Published: 2026-09-15 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2609.17358v1 Variational quantum circuits (VQCs) are parameterized quantum circuits optimized classically. We propose a hybrid variational quantum circuit (HVQC) extending VQCs with a classical affine post-measurement layer, enabling vector-valued regression without the linear overhead of independent scalar circuits. Theoretically, we show that elementary one-and two-qubit circuits can approximate quadratic functions and products via data re-uploading and entanglement, providing the foundations of the full architecture. Experimentally, on two synthetic image reconstruction datasets and the Friedman1 benchmark (40,568 test samples), our HVQC matches Gaussian Process Regression and outperforms XGBoost and Random Forest. An ablation study confirms that both quantum and classical components are essential, and results highlight the central role of the feature map in hybrid quantum-classical models. --- ### A Spatiotemporal Extension of the Neuromorphic DBSCAN Implementation Authors: Charles P. Rizzo, James S. Plank Published: 2026-09-15 Categories: cs.NE arXiv: https://arxiv.org/abs/2609.17357v1 DBSCAN is an algorithm that denoises and clusters data. In prior work, we implemented the DBSCAN algorithm neuromorphically, introducing two constructions termed ``flat'' and ``systolic''. The ``flat'' construction prioritizes throughput, while the ``systolic'' construction trades time for space resulting in a smaller, more hardware-friendly architecture at the cost of throughput. In this work, we offer spatiotemporal extensions of these two constructions to better leverage the spatiotemporal nature of event sensor data. Moreover, as in our prior work, we discuss partial or segmented implementations that further leverage time for space when hardware resources are constrained. All network constructions are provided as open-source implementations. --- ### Where Should a Document Live: Context, Representations, or Parameters? Authors: Nathanaël Carraz Rakotonirina, Momchil Hardalov, Gonzalo Iglesias, Adrià de Gispert Published: 2026-09-15 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2609.17346v1 To answer questions outside of their pre-training data, large language models (LLMs) need access to new information, which can be presented in the context window as documents, encoded into the model's parameters, or injected as latent representations. However, each of these methods comes with different efficiency, cost, and performance trade-offs, with no single winner. We present a controlled comparison of representation-based (KV-cache based) and parametric (fine-tuning-based) adaptation methods on five knowledge-intensive benchmarks. We show that in the oracle setting, Cartridges (KV) are the most accurate injection method at nearly every storage budget, outperforming parametric methods by 10 points. Compaction (KV) matches Cartridges only at low compression rates, lagging behind the parametric methods by 10 points at rates higher than $50\times$. In the more realistic multi-document retrieval scenario, Cartridges are the only method that matches in-context learning (ICL), leading the parametric methods by 29 points and Compaction by 15 points. Nonetheless, Cartridges are also the only method, besides full fine-tuning and large MLP adapters, that suffers from catastrophic forgetting, i.e., a 6% performance degradation on control benchmarks, with 13% in coding. --- ### Type-IV Code Clone Detection via Layer-Wise Non-Contrastive Representation Learning Authors: Luciano Marchezan, Kevin Delcourt, Eugene Syriani, Houari Sahraoui Published: 2026-09-15 Categories: cs.SE, cs.LG arXiv: https://arxiv.org/abs/2609.17338v1 Software clones are fragments of code that are similar or functionally equivalent to each other. They pose significant challenges for maintenance, refactoring, and bug detection. Detecting Type-IV clones, which are semantically equivalent but may differ syntactically, is particularly difficult for traditional token- or syntax-based methods. Recent machine learning approaches rely on contrastive learning, which requires careful negative sampling and can introduce bias. In this paper, we propose LWVIC4Code, a non-contrastive representation learning approach specifically designed for Type-IV clone detection. Building on the Variance-Invariance-Covariance Regularization (VICReg) framework and prior layer-wise VICReg training, LWVIC4Code introduces cross-layer consistency regularization and depth-dependent layer weighting to progressively refine semantic information across transformer layers, producing robust and discriminative code representations. We conduct an empirical study comparing LWVIC4Code against a contrastive learning baseline and zero-shot large language models on Python (Kamino) and multi-language (GPTCloneBench) datasets. Results show that LWVIC4Code achieves competitive or superior performance without negative samples, benefits from layer-wise supervision, and generalizes effectively from Python to other languages, particularly Java and C#. These results demonstrate that non-contrastive, layer-wise representation learning is a promising direction for robust semantic code clone detection. --- ### Self-Emergence Agent Architecture:Behavior-Inertia HMM, Reflexive Metacognition,and Social-Contrastive Self-Modeling Authors: Xiaoyang Liu Published: 2026-09-15 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.17331v1 Large language model (LLM) agents exhibit strong language-generation and problem-solving capabilities, yet suffer from three structural limitations: personality drift, non-evolutionary reflection, and the absence of a self-other boundary. Existing generative-agent simulations rely on static memory and fixed prompts, maintaining neither behavioral inertia nor endogenous self-evolution. We propose the Self-Emergence Agent Architecture (SEAA), which integrates three components: (i) a Hidden Markov Model (HMM) that encodes long-term behavioral and cognitive inertia as an editable state-transition matrix; (ii) a Reflexion-style verbal metacognition loop whose output updates the HMM parameters themselves, rather than merely being stored as text; and (iii) a multi-agent social environment in which initially identical agents continuously compare their behavior with others'. The three components form a closed loop: social action $\to$ feedback $\to$ self-reflection $\to$ inertia update $\to$ differentiated action. We state three falsifiable hypotheses and provide a reproducible experimental protocol with operational metrics. A language-model-free prototype shows the loop spontaneously breaks symmetry: initially identical agents consolidate distinct, stable personalities whereas matched controls do not. Experiments with a hosted LLM surface these differences as distinct first-person self-narratives, and a five-agent deliberation spontaneously develops social structure---a consensus hub and a unanimously rejected outlier---absent in the control. Following an epistemologically agnostic stance inspired by Zhuangzi, SEAA studies only observable behavioral emergence and makes no claim about subjective qualia. This work contributes a unified framework, a concrete architecture with pseudocode, mechanistic evidence, and a microscope-style sandbox for studying artificial-self emergence. --- ### Vroom-Vroom at SHROOM-Visions: A Multi-Judge Committee for Detecting Hallucinated Spans in Vision-Language Outputs Authors: Toqeer Ehsan, Nico Penttilä, Richard Schmidt, Arash Hajikhani, Victoria Palacin Published: 2026-09-15 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2609.17327v2 This paper describes our submission to the SHROOM-Visions shared task on detecting and classifying hallucinated character spans in vision-language model outputs across four languages. We employ several fine-tuned vision-language models as independent annotators and combine their span predictions through character-level majority voting, and additionally explore activation probes. The approach ranks first in three of four languages and places on the podium in every language and metric. Our analysis indicates that disagreement among diverse models tracks disagreement among human annotators. --- ### Vroom-Vroom at SHROOM-Visions: A Multi-Judge Committee for Detecting Hallucinated Spans in Vision-Language Outputs Authors: Toqeer Ehsan, Nico Penttilä, Richard Schmidt, Arash Hajikhani, Victoria Palacin Published: 2026-09-15 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2609.17327v1 This paper describes our submission to the SHROOM-Visions shared task on detecting and classifying hallucinated character spans in vision-language model outputs across four languages. We employ several fine-tuned vision-language models as independent annotators and combine their span predictions through character-level majority voting, and additionally explore activation probes. The approach ranks first in three of four languages and places on the podium in every language and metric. Our analysis indicates that disagreement among diverse models tracks disagreement among human annotators. --- ### From Transient Prompts to Persistent Control: Scientific Poster Generation via Recursive Semantic-Geometric Contracts Authors: Runze Li, Yukun Zhao, Can Xu, Yucheng Shen, Shuaiqiang Wang, Jianmin Wu, Lingyong Yan, Dawei Yin Published: 2026-09-15 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.17326v1 Scientific poster generation distills a multimodal paper into a single-page visual artifact, forcing strict trade-offs between informational coverage and readability under a fixed spatial budget. Existing methods pass plans as transient prompts and validate individual stages in isolation. This strategy causes requirements to drift across content and layout modules, and previous checks to be silently invalidated. We introduce PosterVisor, a control framework that shifts poster generation from transient prompts to persistent control. An Orchestrator grounds rubrics in the paper and visual assets, compiling them into a Semantic-Geometric Contract (SGC) that binds claims and sources to required visuals, budgets, and spatial commitments. Only fully instantiated records become executable assertions; other usable requirements remain soft guidance. Recursive Contract Enforcement (RCE) dynamically triggers checks across stages as evidence emerges. Crucially, during repairs, RCE rechecks affected checkpoint states, preventing repair-induced regressions from propagating silently. We instantiate PosterVisor in HTML/CSS and editable PPTX generators. On the 100-paper Paper2Poster benchmark, PosterVisor-PPT improves observed mean poster-grounded QA accuracy over PosterGen (64.47% vs. 58.53%) and is preferred by human judges in 72.5% of non-tied pairwise comparisons (95% CI, 61.6-83.4%). A secondary 30-paper study also yields higher VLM Overall and PaperQuiz means. These results support rubric-compiled contracts and stage-conditioned enforcement for controllable poster synthesis. --- ### Intrinsic Motivation in Reinforcement Learning: A Research Agenda for Adaptive Self-Organisation Authors: Anatoly Belikov Published: 2026-09-15 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.17325v1 Biological cells can be viewed as individual, interacting agents whose collective dynamics give rise to adaptive behaviour at multiple levels of organisation, from individual cells through tissues to whole multicellular organisms. In this perspective and tutorial article we discuss whether intrinsic rewards in artificial neural systems can support adaptation, functional specialisation and higher-level self-organisation without a shared external objective. We review empowerment, curiosity, learning progress, information gain, unsupervised skill discovery, mutual information estimation and the use of world models for intrinsic reward computation. Particular attention is given to failure modes showing when such objectives do not produce sustained exploration or increasingly complex behaviour. We argue that more capable systems may require complementary objectives, communication, memory, learning at multiple temporal scales and environmental constraints. Based on this perspective, we outline three experimental directions. These include a resource-constrained environment in which otherwise stable behavioural attractors become unsustainable, allowing us to test whether environmental constraints can mitigate characteristic failure modes of intrinsic objectives. The network of recurrent agents with per-agent intrinsic rewards, and a hierarchical world-model agent in which exploratory motor competence develops before goal-directed behaviour. These experiments are intended to test whether intrinsic learning can lead to adaptive organisation at progressively higher levels. --- ### Towards Detecting AI-Assisted Responses in Online Surveys Authors: Qizhou Wang, Bogdan Mamaev, Christopher Leckie Published: 2026-09-15 Categories: cs.CL, cs.CY arXiv: https://arxiv.org/abs/2609.17317v1 The use of LLMs to complete online surveys impacts the validity of survey-based research, but detecting such usage remains underexplored. We introduce an initial benchmark dataset, namely ASURRE, for AI-assisted survey participation to capture usage strategies ranging from full generation and revision to persona-grounded agentic completion. Controlled by these strategies, LLM-assisted survey responses are generated using multiple LLMs on three real-world surveys in different disciplines, paired with genuine human responses. Our evaluation of existing machine-generated text (MGT) detectors shows that naive AI usage is readily detectable, whereas persona-grounded agents that mimic entire respondents push detector performance toward chance. We further show that agentic completion cannot fully replicate respondent-level behaviour and leaves distinctive behavioural traces. While individual cues can be circumvented by targeted prompting, a simple few-shot, training-free aggregator over these cues improves mean AUROC by +0.14 over the best existing detector across agentic settings. Our project is available at https://github.com/mike-qz-wang/ASURRE. --- ### Zero-shot narrative detection in social messaging Authors: Jesús M. Fraile-Hernández, Anselmo Peñas, Patrick Giedemann Published: 2026-09-15 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.17310v2 This study investigates the zero-shot ability of large language models (LLMs) to identify and classify hidden narratives in social messages. Our research hypothesis is that LLMs' extensive contextual knowledge allows them to interpret messages on a deeper, pragmatic level, going beyond basic sentiment or topic analysis. Experiments on the Dipromats and SemEval datasets show that providing models with human-written narrative descriptions significantly improves performance, without the need of training examples. In contrast, automatically generated descriptions or the use of few examples (few-shot) often degrade accuracy due to subtle shifts in framing. The study also finds that ensemble methods, particularly majority voting, enhance robustness and that larger models perform best while also being less sensitive to prompt variations. The findings validate that LLMs can effectively detect strategic narratives in a zero-shot setting, and when combined with simple ensembling and human-written descriptions, they can rival supervised systems, offering a scalable solution for narrative detection, specially when there is no training data for the vast majority of domains. --- ### Zero-shot narrative detection in social messaging Authors: Jesús M. Fraile-Hernández, Anselmo Peñas, Patrick Giedemann Published: 2026-09-15 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.17310v1 This study investigates the zero-shot ability of large language models (LLMs) to identify and classify hidden narratives in social messages. Our research hypothesis is that LLMs' extensive contextual knowledge allows them to interpret messages on a deeper, pragmatic level, going beyond basic sentiment or topic analysis. Experiments on the Dipromats and SemEval datasets show that providing models with human-written narrative descriptions significantly improves performance, without the need of training examples. In contrast, automatically generated descriptions or the use of few examples (few-shot) often degrade accuracy due to subtle shifts in framing. The study also finds that ensemble methods, particularly majority voting, enhance robustness and that larger models perform best while also being less sensitive to prompt variations. The findings validate that LLMs can effectively detect strategic narratives in a zero-shot setting, and when combined with simple ensembling and human-written descriptions, they can rival supervised systems, offering a scalable solution for narrative detection, specially when there is no training data for the vast majority of domains. --- ### Optical-Flow Wingbeat Counting in MuJoCo: A Comparison of Convolutional, Spiking, and Attention-Based Temporal Models Authors: Zhang Nengbo Published: 2026-09-15 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.17308v1 Visual monitoring of flapping-wing vehicles requires distinguishing individual wingbeats from motion strength and average frequency. This paper presents a controlled MuJoCo evaluation of wingbeat counting from signed optical flow observed by virtual cameras mounted on Crazyflie vehicles. Three flapping-wing models were recorded at optical distances of 1.5 and 3.0 m, producing 1,440 clips from 240 paired scene configurations with a scene-level 3:1 training-test split. A common spatial convolutional encoder was combined with a causal temporal convolutional network, a recurrent leaky integrate-and-fire spiking network, or causal self-attention. Each model predicted phase and activity, followed by the same directed-crossing event counter. The six existing convolutional models were retained, and all twelve new models were frozen before their test predictions were generated. Exact-count accuracies at 1.5 m were 96.67%, 95.00%, and 96.67%, respectively; at 3.0 m they were 94.44%, 92.22%, and 95.00%. All paired scene-bootstrap intervals for differences in exact-count accuracy included zero. Seven far-distance spiking-model clips had correct totals despite event-timing mismatches, demonstrating why total-count and event-level measurements must be reported together. The results support the feasibility of causal optical-flow counting in the tested setting and identify boundary-sensitive errors. They do not establish an architecture ranking across repeated training, real-flight robustness, or hardware efficiency. --- ### Mo' Models, Mo' Problems: How to best select model pools when designing Multi-Agent Systems Authors: Sara Vera Marjanović, Jiacheng Xu, Aleksandr Laptev, Grigor Nalbandyan, Erik Arakelyan, Evelina Bakhaturina Published: 2026-09-15 Categories: cs.MA, cs.AI arXiv: https://arxiv.org/abs/2609.17306v1 Multi-agent Systems (MAS) combine multiple model outputs to solve complex reasoning tasks. However, despite rapid growth of available open-source models, there is limited research on how to select optimal model candidates out of this massive pool. We systematically evaluate 8 model selection strategies (including model size, accuracy and answer diversity) across before-generation (routing) and after-generation (majority-voting, LLM-as-a-judge) MAS architectures on challenging scientific benchmarks. Our findings show a significant gap between theoretical oracle potential and actual performance: Expanding candidate pool sizes often degrades performance below that of the top performing base-model. We find that candidate selection within a single model family is the strategy that yields the best relative performance over a standalone model. These results demonstrate that adding arbitrary models to a heterogeneous MAS can introduce system instability, highlighting model selection as a critical design choice for multi-agent systems. --- ### Machine Zygote: Causal Biparental Heredity Before Learning in a Germline--Soma Artificial Agent Authors: Lyes Saad Saoud Published: 2026-09-15 Categories: cs.NE, cs.RO arXiv: https://arxiv.org/abs/2609.17300v1 Artificial ontogeny, developmental encodings, robot reproduction, and inherited controllers are established research directions, yet a narrower question remains: can a newborn artificial agent exhibit measurable biparental heredity before learning, and can that dependence be isolated causally rather than inferred only from parent-offspring resemblance? We introduce Machine Zygote, a computational germline-soma architecture designed to test this question. Two parental germlines are independently mutated and recombined into a zygote that parameterizes development of an initially generic eight-module soma, which is then frozen and evaluated without learning. A preregistered 4 x 4 diallel of 640 offspring shows significant dam and sire dependence for five of six behavioral traits after Holm correction, with parental and interaction components accounting for 36-53 percent of modeled variance across five principal traits. In matched-background interventions (n=60), substituting one parental germline while holding recombination and stochastic background fixed causes phenotype shifts exceeding a same-parent re-mutation control for five of six traits for both parental channels. Recombination also yields excess transgressive offspring for speed and gait frequency. A preregistered developmental-dependence hypothesis is not supported: a quasistatic no-dynamics ablation preserves the mean phenotype distribution while altering parental variance structure. Thus the study supports causal biparental pre-learning heredity in this simulation, but not the stronger claim that recurrent developmental dynamics are necessary. It does not establish physical heredity, biological genetics, or autonomous evolution. The contribution is an intervention-centered framework and reproducible benchmark for separating heredity, development, stochastic variation, and post-birth learning. --- ### Quantum-Inspired Trainable and Parameter-Efficient Tensor Networks for Image Inpainting Authors: Shiwen An, Konstantinos Slavakis Published: 2026-09-15 Categories: eess.IV, cs.CV, cs.LG arXiv: https://arxiv.org/abs/2609.17298v1 This work introduces quantum-inspired tensor-network circuits as trainable transforms for image inpainting. Among the proposed architectures, the diagonal quantum Fourier transform (QFT) relaxation is invertible with $O(N^2 \log N)$ computational cost for $N\times N$ images, inherently preserving minimum coherence throughout training via its circuit structure and eliminating the need for explicit coherence penalties. Unconstrained gradient-based phase optimization (Riemannian-optimization free) enables efficient learning from randomly sampled training data, allowing the learned transform to generalize to test images observed through fixed sampling masks. Numerical tests show that the learned models outperform fixed transforms and per-image optimization while matching the performance of much larger unitary architectures, yet with far fewer parameters. --- ### Goal-oriented probabilistic forecasting for dynamic PRB allocation in 5G networks Authors: Oier Larumbe-Lizarraga, Roberto Pereira, Cristian J. Vaca-Rubio Published: 2026-09-15 Categories: eess.SP, cs.LG arXiv: https://arxiv.org/abs/2609.17297v2 Efficient physical resource block (PRB) allocation in 5G networks requires accurate demand forecasting. Conventional methods minimize symmetric error metrics (MAE, RMSE), ignoring the operational cost asymmetry where under-provisioning (service degradation) is far costlier than over-provisioning (wasted capacity). We propose a goal-oriented probabilistic forecasting framework that aligns model training with the operator's decision-making objectives. Specifically, we train DeepAR and Temporal Fusion Transformer (TFT) models using the Pinball Loss function and derive the optimal allocation quantile from the operator's cost matrix. Evaluation on a real beam-level 5G traffic dataset shows that the proposed approach reduces operational cost compared to MSE-trained baselines while maintaining calibrated uncertainty estimates. The framework enables dynamic PRB allocation that explicitly balances service reliability against resource efficiency. --- ### Goal-oriented probabilistic forecasting for dynamic PRB allocation in 5G networks Authors: Oier Larumbe-Lizarraga, Roberto Pereira, Cristian J. Vaca-Rubio Published: 2026-09-15 Categories: eess.SP, cs.LG arXiv: https://arxiv.org/abs/2609.17297v1 Efficient physical resource block (PRB) allocation in 5G networks requires accurate demand forecasting. Conventional methods minimize symmetric error metrics (MAE, RMSE), ignoring the operational cost asymmetry where under-provisioning (service degradation) is far costlier than over-provisioning (wasted capacity). We propose a goal-oriented probabilistic forecasting framework that aligns model training with the operator's decision-making objectives. Specifically, we train DeepAR and Temporal Fusion Transformer (TFT) models using the Pinball Loss function and derive the optimal allocation quantile from the operator's cost matrix. Evaluation on a real beam-level 5G traffic dataset shows that the proposed approach reduces operational cost compared to MSE-trained baselines while maintaining calibrated uncertainty estimates. The framework enables dynamic PRB allocation that explicitly balances service reliability against resource efficiency. --- ### Conformal Policy Learning with Distribution-Free Safety Guarantees Authors: Ying Jin, Naoki Egami Published: 2026-09-15 Categories: stat.ME, cs.LG, econ.EM, math.ST, stat.ML arXiv: https://arxiv.org/abs/2609.17296v1 Policy learning aims to determine who should be treated based on individual characteristics. In high-stakes settings such as medicine and public policy where safety is a central concern, improving the average outcomes alone may not be sufficient: decision makers may also seek to protect individuals from harm, in line with the Hippocratic principle of ``do no harm.'' In this paper, we propose \textit{conformal policy learning} (CPL), a policy learning procedure with a new distribution-free safety guarantee that controls the probability of assigning treatment to an individual who would be harmed relative to control. CPL views each treatment decision as testing a hypothesis of counterfactual harm and assigns treatment by thresholding conformal p-values. These p-values use observable proxies and selective calibration to address the challenge that the potential outcomes under comparison are never simultaneously observed. For randomized experiments, under standard exchangeability conditions, CPL provides finite-sample safety guarantee at a user-specified level, without imposing any outcome modeling assumptions. Moreover, when the outcome model is consistently estimated, CPL achieves asymptotically optimal welfare subject to the safety constraint. In observational studies, CPL with learn-then-balance weights achieves doubly robust safety guarantees. We evaluate CPL through extensive simulations and apply it to an empirical study of AI-powered interventions designed to reduce conspiracy beliefs. --- ### Extracting ontology-compliant knowledge from scientific text describing irradiated materials using large language models Authors: Marco Luca Sbodio, Marcos Martínez Galindo, Vanessa Lopez, Blanca Biel, Pablo Canca, Pedro Delgado, Jesús I. Mendieta-Moreno, Raphael Tack, Maria J. Caturla Published: 2026-09-15 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.17291v1 The quest for new materials increasingly relies on predictive models and comprehensive simulations that span scales from atomic to macroscopic levels. However, essential data necessary for these models and simulations are often embedded in scientific literature as unstructured text, limiting reusability and posing challenges for researchers seeking to leverage existing knowledge effectively. While extracting structured data from unstructured text using large language models is gaining popularity, traditional methods typically generate key-value pairs data with straightforward schemas. In contrast, we introduce eolas, a modular pipeline that uses large language models to automatically transform scientific documents into knowledge graphs aligned with a specified ontology. We demonstrate eolas effectiveness in extracting useful information for scientists studying materials designed to endure the extreme temperatures and radiation levels found in fusion reactors. While a human expert might spend between thirty to ninety minutes extracting relevant data from an article, eolas can generate high-quality knowledge graphs in just a few minutes. These are presented in a tabular format with faceted navigation for easy human validation. Additionally, we introduce the first benchmark dataset designed to assess large language models capabilities in constructing knowledge graphs within the domain of irradiated materials. The analysis of 168 experiments using our dataset, various large language models and prompting techniques provides key insights that we summarize into practical guidelines for effectively extracting knowledge graphs aligned with an input ontology. --- ### Same Flow, Different Paths: Variance Reduction in Flow Matching Authors: Alexander Tyurin Published: 2026-09-15 Categories: cs.LG, math.OC arXiv: https://arxiv.org/abs/2609.17287v1 In flow matching (FM), a velocity model $v_θ$ is trained using a predefined path $g_t$ that connects data and noise samples (e.g., $g_t(x_0, x_1) = (1 - t) x_0 + t x_1$). In this work, we study the choice of this path from an optimization perspective by analyzing the variance of stochastic gradients. We consider the class $G(p_t,v^\star_t)$ of paths that induce the same marginal distributions $p_t$ and marginal velocity field $v^\star_t$, and therefore the same FM objective. Our main finding is that the choice of path $g_t$ can fundamentally change the convergence rate of SGD, even when the FM objective remains exactly the same. (i) For a linear velocity model and one-dimensional Gaussian data, we derive a tight bound on the SGD iteration complexity up to logarithmic factors and find an analytically optimal path that minimizes this bound among linear paths inducing the same FM problem. (ii) We then extend the variance analysis to general FM problems and formulate path selection at a fixed $θ$ as the variance-minimization problem PathOpt$_θ$, constrained to $g_t\in G(p_t,v^\star_t)$. We show that this constraint is essential: reducing variance without it can lead to slower convergence. (iii) Since the constraint $g_t \in G(p_t,v^\star_t)$ cannot generally be verified directly, we derive an equivalent formulation with constraints that can be estimated from samples, allowing paths to be found numerically. Our theoretical results are supported by experiments with Gaussian data, Gaussian mixture models, and real datasets. ---