# Research Papers — 2026-09 · bundle page 190 of 266 > Full-text markdown of papers #9451–9500 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/190 [← Previous bundle](https://aipod.dev/papers/archive/2026-09/page/189.md) [Next bundle →](https://aipod.dev/papers/archive/2026-09/page/191.md) ### Receiver-Surface Hit Patterns via Legendre Approximation for Molecular Signal Detection Authors: Yasin Bastug, Erencem Ozbey, H. Birkan Yilmaz Published: 2026-09-10 Categories: cs.IT, cs.LG arXiv: https://arxiv.org/abs/2609.12089v1 Detecting whether a transmitter is actively communicating with a receiver is a fundamental problem in molecular communications. A spherical receiver may measure not only the number and arrival times of absorbed molecules, but also their absorption locations on the receiver surface. These locations contain a directional signature that is lost in count-only detection. In this letter, we develop a molecular signal detector based on a Legendre polynomial expansion of the receiver-surface hit density and extend it to a Legendre-based Viterbi sequence detector. By exploiting the surface-level directional signature of molecular arrivals, the proposed detectors provide geometry-aware, efficient, and better-performing alternatives to count-only detection. --- ### Creating an Atomic User Model for Personality-Aware Large Language Model Interaction Authors: B. Sankar, Deepthika S, Pawni Yadav, Amogh A S Published: 2026-09-10 Categories: cs.HC, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2609.12086v2 Assistants built on large language models are expected to write in their users' own voice. Most systems summarise the user's preferences and include the summary in the prompt. This is the wrong way round. Preferences are only the surface of a person and change with the task, while the underlying personality stays the same, so storing preferences alone means relearning the user afresh whenever the task changes. This paper makes four contributions. First, we describe an effect we call personality seepage: the wording of a prompt carries traces of the writer's personality, which the assistant copies without knowing the writer. Second, we propose the Atomic User Model (AUM), a readable profile with a stable identity core surrounded by four layers covering psychological, cognitive, experiential, behavioral, and social details, plus notes on inner conflict and authenticity. Third, instead of inserting the entire profile, we use AUM as a searchable index, in which a task classifier, a selection step, and a budgeted retriever pass along only a few relevant fields. Fourth, we test the pipeline with 16 simulated users, 6 style-sensitive tasks, and 3 seeds. Eight retrieved fields matched the writing quality of the whole profile, while using only 23 percent of the context (211 tokens instead of 915). They scored 0.24 points higher than a plain preference note on a five-point scale. Accuracy in picking a user's own writing from four samples rose from 14.9 to 42.7 percent, where guessing gives 25 percent. Four pre-registered controls showed no effect, so the gain comes from the profile's structure rather than the search method. Personalization helps most for the users for whom a generic assistant imitates them the worst. --- ### What Counts as a Mistake? Annotating Recitation Events in Quran Memorization Transcripts Authors: Mohamad Al Mdfaa, Nursultan Askarbekuly, Ahmed Helaly, Ubai Sandouk, Manuel Mazzara Published: 2026-09-10 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.12085v1 Checking Quran recitation from an ASR transcript requires distinguishing unresolved mistakes from repetitions, repairs, opening formulas and accepted spelling differences. We report a completed human annotation of 100 production recording cases: 348 scored units and 162 localized events across ten combined labels. An executable evaluator scores labels and word positions together. A plain diff reaches label-aware F1 0.525 and localization F1 0.826; adapted production cleaner/alignment components reach 0.518 and 0.786, with exact-span F1 0.505 for both. Correcting the adapter's word coordinates recovers all five annotated repetition events, showing why annotation interfaces must be checked before interpreting baseline failures. In a preliminary pilot, eight single 20-minute runs across three coding agents and eight models span label-aware F1 0.143 to 0.892: seven land far above every baseline, and one collapses below the naive diff from a missing normalization step. Across the six, 970 of 972 gold-event instances draw an overlapping prediction, so what remains is not detection but convention: span extent, and the labels whose boundary is stipulated by adjudication rather than visible in the text. Seven of 162 events defeat all six same-day runs, five of them one orthographic rule, and the strongest run still misses the same ones. No run annotated before building, so the pilot measures the algorithm half of the task only. --- ### MoPA: Coordinated Mobile Manipulation via Subsystem-Specific Perception Alignment Authors: Guangyu Chen, Qiwei Liang, Shaolong Zhu, Tianxing Chen, Zikuan Xiao, Yifan Xie, Lingfeng Zhang, Ping Luo, Renjing Xu, Wenbo Ding Published: 2026-09-10 Categories: cs.RO, cs.CV arXiv: https://arxiv.org/abs/2609.12081v2 Mobile manipulation requires perceptual evidence at different spatial scales for base motion and arm control, while the two action modalities remain kinematically coupled. Existing policies often employ specialized action generation for different subsystems but condition heterogeneous action branches on a shared perceptual representation, leaving subsystem-specific perception-action correspondence implicit. We present MoPA, a framework that aligns perceptual conditioning with mobility and manipulation while preserving coordination at the action level. Dual Perceptual Streams employ two mutually masked query banks to extract separate perceptual representations from a shared vision-language context. Perception2Action Adaptation jointly updates each query bank and its corresponding action stream at every layer of a structured Mixture-of-Transformers decoder, while enabling information exchange between the two action streams. Coupled conditional flow matching learns a joint vector field for coordinated generation of both action chunks. On the ManiSkill-HAB benchmark, MoPA achieves state-of-the-art performance across all three task suites. Across four real-world tasks, MoPA achieves a mean full-task success rate of 76.3%, outperforming the best baseline by 12.5 percentage points. Ablation studies and further analyses validate the effectiveness of the proposed design. Website is available at: https://mopa-policy.github.io/. --- ### Hierarchical Prototype Emergence in Modern Hopfield Models Authors: Aditya Cowsik, Adithya Sriram Published: 2026-09-10 Categories: cond-mat.dis-nn, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2609.12079v1 Hierarchical correlations are a universal feature of any realistic model of data, and the question of how associative memory models may learn these correlations and generalize beyond them to construct new sensible images is an important step towards understanding more complex modern architectures such as diffusion models. We consider a hierarchical model for memories which are sampled and stored in a dense Hopfield network with polynomial activation. We analytically derive conditions for each level of this hierarchy to be locally stable - that is they are local energy minima. We use prototype reconstruction as a minimal model of generalization and we find that it takes only a quasi-polynomial amount of information to generalize beyond particular memories and even particular groups in the hierarchy. We observe a qualitatively analogous phase diagram in the number of memories, sharpness of the activation function (polynomial degree) for data from Fashion-MNIST. --- ### Feature Recovery for Object Understanding After Irreversible Fire Damage Authors: Aditi Tiwari, Sofia Stoica, Savya Khosla, David Forsyth, Heng Ji Published: 2026-09-10 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.12078v1 Objects in post-fire environments often undergo irreversible physical transformations that change their geometry, material state, and visual appearance. Detecting and identifying these remnants is critical for locating hazards, reconstructing pre-incident contents, and inventorying losses. Unlike standard image corruptions, these degradations affect the physical structure of the object itself. To study this setting, we introduce TRACE, a transformation-aware benchmark for post-fire object understanding. TRACE contains 21.4K real-image-grounded synthetic scenes and paired object-level pristine-to-degraded progressions spanning 499 object identities across 189 categories. We define five tasks targeting localization and pre-degradation understanding: degraded-object detection, pristine-state recovery and retrieval, original material recovery, pristine description generation, and functional reasoning. Existing models degrade sharply with severity. From the least to the most severe level, RF-DETR mAP decreases by 71% relative, while InternVL3.5 retrieval R@1 falls from 93.85 to 28.11. To address this, we propose the Feature Recovery Module (FRM), a plug-and-play module that maps degraded encoder features to pristine-aligned representations while keeping the host frozen. Trained only with paired feature supervision, FRM improves scene-level detection, CLIP/SigLIP2 feature recovery, and all four object-level VLM tasks, with larger gains under more severe degradation. Across VLM hosts and severity levels, relative gains average 12.5% for retrieval, 20.1% for material recovery, 13.2% for description generation, and 12.4% for functional reasoning. --- ### Efficient Vision-Language-Action Management and Serving for Robot Factories Authors: Dionysios Adamopoulos, Nattapol Chanpaisit, Basel Fakhri, Christina Giannoula Published: 2026-09-10 Categories: cs.DC, cs.AR, cs.LG, cs.PF, cs.RO arXiv: https://arxiv.org/abs/2609.12075v1 Vision-Language-Action (VLA) models show high robotic manipulation capabilities via a two-stage design: a Vision-Language Model (VLM) stage followed by an Action Diffusion Transformer (ADiT) stage. Since robots must meet strict Service-Level Objectives (SLOs) for safety, VLA inference is inherently latency-critical. Meeting these SLOs requires high-end GPUs, yet weight, cost, and power constraints preclude integrating such GPUs on-robot. Prior works offload VLA inference to edge servers that serve many robots on VLA models. However, current VLA systems lack support for multi-request, multi-model execution on a multi-GPU server under SLOs, while existing serving systems for multi-stage models are optimized for throughput and stage disaggregation across separate GPUs, which are ill-suited for the millisecond-scale stages of VLA models. We design Robion, the first VLA serving and management system for multi-robot, multi-model requests on multi-GPU edge servers that meets SLOs. Our serving engine disaggregates the VLM and ADiT stages within a GPU via two streams, dynamically restricting the SMs on VLM stream so ADiT always finds SMs to run alongside it, and co-locates multiple models by sharing these streams across them, prioritizing requests by least remaining SLO time. Our management engine enables flexible model placements on multi-GPU servers, and integrates an intelligent traffic controller that maximizes per-model batching under the chosen placement while bounding each GPU's load to meet SLOs. For individual models, Robion serves on average 6.7$\times$ and 1.5$\times$ higher robot load within 98% SLO attainment over vLLM-Omni, the most widely used multi-stage serving system, and Monolithic, which runs VLM and ADiT as a single pipeline, respectively. In a large-scale experiment of serving 8 different models on a 4-GPU server, Robion can serve up to 64 robots within 98% SLO attainment. --- ### Scalable Discrete-to-Continuous Channel Simulation for Compression and Privacy Authors: Joseph Rowan, Buu Phan, Ashish J. Khisti Published: 2026-09-10 Categories: cs.LG, cs.IT arXiv: https://arxiv.org/abs/2609.12067v1 Channel simulation has recently emerged as a useful component in machine learning systems where samples from a prescribed probability distribution are to be compressed. Yet, general channel simulation algorithms often suffer from high computational costs, random stopping times or, in the worst case, can require generating an infinite number of shared random samples. We introduce a scheme for both exact and approximate simulation of discrete-to-continuous channels which conversely uses a fixed number of random samples, and therefore has a runtime independent of the channel and the input. Unlike existing channel simulation schemes which generate a sequence of independent samples from a proposal distribution, our approach generates one sample, or alternatively a fixed number of samples, from each potential target distribution. We then apply a latent permutation to the samples before performing sample selection using an exponential race. Our scheme provides a flexible tradeoff between the number of generated samples and the compression rate. Using polar and multilevel coding, we scale our approach to handle long blocklengths in $O(n \log n)$ time in order to benefit from reduced per-symbol overhead. We conclude by demonstrating applications to variable-rate compression with stochastic VQ-VAEs and communication-efficient differentially private distributed mean estimation via exact simulation of the Gaussian mechanism. --- ### Fast BIB simulation at a future Muon Collider with generative machine learning Authors: Radha Mastandrea, Shiyu Peng, Benjamin Rosser, Matt LeBlanc Published: 2026-09-10 Categories: physics.ins-det, cs.LG, hep-ex arXiv: https://arxiv.org/abs/2609.12054v1 Beam-induced background (BIB) from muon decay products will be an overwhelming and unavoidable background at a future Muon Collider. In order to develop robust event reconstruction algorithms, we need large amounts of accurate BIB simulation to test on. BIB simulation is currently compute-limited: the simulated sample presently used for BIB overlay, which statistically represents approximately $10\%$ of a single unique event's worth of simulated BIB, requires on the order of $10^6$ HS23$\cdot$hours to generate and occupies approximately $100$ GB on disk. In this work, we develop the first machine learning models for fast BIB generation in tracking detectors. We consider two classes of architectures: a slower but higher-fidelity tabular diffusion model, and a faster but lower fidelity circular spline flow model. We find that both classes of architectures produce BIB hits and tracks that closely resemble those of available full simulation hits and tracks, and that the machine learning models can produce BIB in over an order of magnitude less time than what is needed to produce full simulation BIB. We release the model weights with the paper so that the Muon Collider community can use these fast BIB hits for future R&D. --- ### Reality Is the Final Verifier: On Two Key Gaps in Agentic Software Engineering Authors: Alexander Krentsel, Shubham Agarwal, Mert Cemri, Shu Liu, Sidharth Sankhe, Ziming Mao, Matei Zaharia, Ion Stoica Published: 2026-09-10 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2609.12039v1 Software development follows an implementation-verification loop in which developers or agents iteratively revise an implementation until an evaluator, such as a test suite, accepts it. The evaluator checks the implementation against a set of requirements under a model of the deployment environment. Yet even a formal proof that the implementation satisfies the requirements under the model cannot guarantee acceptable behavior after deployment. Requirements only approximate stakeholder intent, and the model only approximates the real deployment environment. We call these together - requirement gap and model gap - the two-gap framework, which unifies the main failure modes of agentic software engineer-ing: reward hacking exploits omissions in the requirements or model, while hallucination widens the gaps by fabricating requirements or environment assumptions. Because neither gap can generally be certified closed in an open, changing world, the goal shifts from closing them to continuously narrowing them. We therefore propose an assurance-revision loop that uses deployment evidence to revise the requirements, model, or evaluator when stakeholders reject the resulting behavior. We then cast assured agentic development as a resource-allocation problem over human judgment, agent capability, and compute. The two principal bottlenecks mirror the two gaps: human judgment for the requirement gap and faithful, costly evaluation for the model gap. Reality remains the final verifier: acceptable behavior under actual deployment conditions is the ultimate test, while predeployment evaluations remain proxies for it. --- ### Pelican-Sim 1.0: A General World Model Simulator for Embodied Intelligence Authors: Shilong Zou, Shilin Zhang, Yingji Zhang, Yuhang Huang, Yi Zhang, Zeyuan Ding, Han Dong, Junwei Liao, Yong Dai, Jian Tang, Xiaozhu Ju Published: 2026-09-10 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2609.12036v1 In this technical report, we propose Pelican-Sim 1.0, a general world model simulator for embodied intelligence that predicts future observations from visual context and robot actions to support downstream learning and decision making. The model incorporates four key design features: (1) Unified action representation: a 28-dimensional action value space covering most mainstream embodiments, keeping one model valid across heterogeneous devices. (2) Action-visual injection: URDF- and camera-rendered action videos bridge actions and pixels, giving markedly better controllability across embodiments, scenes, and tasks (PSNR +0.904 over alternative fusion baselines). (3) Sparse mixture-of-experts (MoE): sparse MoE layers add capacity for heterogeneous dynamics and absorb the action modality while reducing inter-modality conflict (FVD -6.530 vs. the dense backbone). (4) Efficient rollout generation: causal adaptation and few-step distillation yield a four-step autoregressive simulator, achieving a 5.67-fold speedup over the 35-step model. Benefiting from these designs, we train on approximately one million real-world and simulated trajectories and obtain large gains in action controllability and video quality: PSNR improves over the strongest evaluated baselines by 4.636 on AgiBotWorld Beta, 2.080 on RoboMIND, and 10.343 on RoboTwin, with the adapted EWMBench DYN score up 0.426 on RoboTwin. Relying on this, four downstream applications on RoboTwin succeed: 500 generated trajectories added to 50 demonstrations per task raise policy success from 70% to 93%; policy evaluation reaches a Pearson correlation of 0.994 across five checkpoints; and relative success gains reach 47.7% for action selection and 20.3% for policy improvement. Qualitative generalization across trajectory, scene, object, embodiment, and viewpoint shifts highlights its potential as a general-purpose world model simulator. --- ### Reading the Whole Heart: Latent-Attention Masked Autoencoders for Multimodal Cardiac Representation Learning Authors: Andrea Agostini, Simon Böhi, Moritz Vandenhirtz, Samuel Ruiperez-Campillo, Max Krähenmann, Silke Mühlstedt, Irene Cannistraci, Ece Özkan Elsen, Julia E. Vogt, Thomas M. Sutter Published: 2026-09-10 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.12035v1 Cardiovascular diagnosis rests on integrating complementary modalities, like ECG, echocardiography, chest radiographs, and clinical variables, each capturing distinct but correlated aspects of cardiac physiology. Yet most medical foundation models remain modality-specific, combining modalities only for finetuning or post-training. This discards the cross-modal evidence clinicians naturally integrate and ignores the structure within each modality. We introduce Latent-Attention Masked Autoencoders (LAMAE), a multimodal, structure-aware masked autoencoder that jointly learns patient-level representations during self-supervised pretraining. Rather than fusing modalities post hoc, LAMAE exchanges information directly in the latent space through a shared latent-attention module operating over a study-view-entity hierarchy, enabling aggregation of variable observations and graceful handling of missing modalities. Pretrained on over 1.2 million MIMIC-IV hospital stays, LAMAE outperforms modality-specific pretraining and strong contrastive and vision-language baselines across multimodal hospital-stay tasks, such as in-hospital mortality, ICD-10 and DRG coding, and length of stay, while remaining competitive on unimodal tasks. These gains persist even when only a single modality is available at test time, showing that modeling both intra- and inter-modal structure yields more robust, transferable representations. --- ### Learning the Geometry of Collider Events with Metric-Aware Deep Sets Authors: Lauren Hay, Rishabh Jain, Matt LeBlanc, Jennifer Roloff Published: 2026-09-10 Categories: hep-ph, cs.LG arXiv: https://arxiv.org/abs/2609.12024v1 Optimal transport gives structured data a geometry, but exact evaluation is costly in large pairwise analyses that exploit relationships among distances. Learned surrogates are faster, but need not preserve this metric structure. We develop a Deep Sets surrogate for OT between variable-size weighted point clouds that enforces non-negativity, exchange symmetry, and zero self-distance, leaving the triangle inequality unconstrained. Applied to the Energy Mover's Distance between collider events in a particle physics application, the Metric-Aware Particle Flow Network achieves percent-level mean absolute percentage error while significantly improving inference throughput over other exact and approximate methods surveyed. The architectural constraints are found to improve properties that are not explicitly enforced: across $10^6$ held-out event triplets, triangle-inequality violations fall from 199 for a matched unconstrained network to 2, and the maximum from 149.5 to 5.8 GeV. These results demonstrate that targeted inductive biases can yield fast neural surrogates with substantially improved geometric fidelity. --- ### Continuous Learning of Gravity Field Irregularities Around Small Bodies via Neural Hamiltonian ODEs Authors: Giacomo Acciarini, Dario Izzo Published: 2026-09-10 Categories: astro-ph.IM, astro-ph.EP, cs.AI, math.OC, physics.space-ph arXiv: https://arxiv.org/abs/2609.12022v1 We propose to learn the unknown dynamics in the proximity of a small body directly from tracking data, representing them as a feed-forward neural network embedded in the system Hamiltonian. The equations of motion form a Neural Hamiltonian Ordinary Differential Equation, whose variational equations provide exact training gradients: estimation uses position and velocity arcs at realistic noise levels, without acceleration or potential labels, and a continual learning approach warm-starts the network as new data are acquired. The known part of the Hamiltonian carries whatever is available, from the central term and spin state to the constant-density model of the imaged shape. We assess the method against a normalized spherical harmonics expansion estimated from identical arcs through the same machinery, on scenarios built on the shapes of Itokawa, 67P, Bennu and Eros. The network remains usable inside the Brillouin sphere: it plans ballistic descents at Itokawa to \SI{4.6}{m} median touchdown error from tracking alone, against 5.1--\SI{48.9}{m} for harmonics of degree 4--12, and to \SI{0.9}{m} with the imaged shape as prior, a configuration that also recovers localised density anomalies invisible to any harmonics degree. The two representations are complementary, and we discuss their combined use across the phases of a small-body mission. --- ### Reinforcement Learning for Syndrome Extraction Authors: John Zhuoyang Ye, Aarav Pabla, Jens Palsberg Published: 2026-09-10 Categories: cs.LG, quant-ph arXiv: https://arxiv.org/abs/2609.12020v1 A key subtask of quantum error correction is to extract a syndrome that, if nontrivial, signals an error. The number of possible ways to extract a syndrome grows exponentially with the syndrome size, and these implementations vary greatly in fault tolerance, as measured by their logical error rates. This creates a natural search problem: find an implementation with a low logical error rate. Previous work solves this problem but sacrifices either solution quality or scalability. In this paper, we use reinforcement learning and importance sampling to outperform previous work at all scales. Compared with the state of the art automatic scheduling tools AlphaSyndrome and PropHunt, our tool reduces the logical error rate by 25.9\% and 71.7\% on average, respectively, culminating with a reduction of 97.8\% for a surface code with distance 15. --- ### Toward Reliable Railway-Bogie Response Prediction Using Multifidelity TDNN and Physics-Informed Residual Learning Authors: Gyeolhee Lee, Moosun Kim, Taewook Kwon, Jaehun Kim, Changsung Jeon, Dongjin Lee Published: 2026-09-10 Categories: cs.LG, physics.app-ph arXiv: https://arxiv.org/abs/2609.12018v2 Railway engineers need simulation models that predict vehicle responses across operating scenarios that cannot be tested exhaustively. Agreement with representative measurements provides essential evidence, but calibration at a limited set of conditions does not guarantee accuracy elsewhere. We present a multifidelity railway-bogie response-correction method that treats multibody simulation histories as low-fidelity information and roller-rig measurements as high-fidelity evidence. This method combines an experiment-anchored fidelity assignment with physics-informed discrepancy learning for multichannel bogie-response histories. A time-delay neural network (TDNN) represents the condition-dependent simulation trend, and development-fitted amplitude alignment defines the low-fidelity baseline. A residual-correction network then models the reproducible response component not explained by this baseline and adds it to the baseline. An effective dynamic-balance equation constrains the learned discrepancy by representing differences in inertia, damping, stiffness, and external forcing between the simulated and physical systems. The training objective combines this constraint with residual matching, temporal smoothness, and a combined channel-2 acceleration loss selected using displacement-acceleration consistency evidence. For the evaluated reconstruction case, the corrected response gives a mean coefficient of determination of 0.8197, a mean normalized root-mean-square error (NRMSE) of 4.6055 %, and a mean normalized mean absolute error (NMAE) of 1.9297 %. These results provide initial evidence of accurate response prediction at the held-out 385 km/h condition. --- ### When Agent Metrics Measure Different Things: An Evidence-Grounded Audit of the Praxa AI Pipeline Authors: Stefan G. Creadore, Peyton Woakz Published: 2026-09-10 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2609.12017v1 Agent evaluations can be numerically correct while measuring a different construct from the one implied by their labels. We present a retrospective measurement audit of selected Praxa AI implementation files, historical evaluation artifacts, and operational records. A 139-case offline routing report contains 112 passes and 27 failures despite zero gating failures, because known gaps are explicitly exempted from the gate. An identifier-free export represents 8,843 tool-attempt rows: 8,395 recorded durations and 448 missing values. Of the durations, 121 equal the signed 32-bit maximum and carry abandoned-client labels; inspected database code clamps elapsed lifecycle age. The pooled recorded 99th percentile is 2,147,483,647 ms, versus 38,118.31 ms among server-observed completed calls. This is a stratum contrast, not a treatment effect. In a documented single-trajectory compaction pilot, the reported follow-up input reduction is 94.39%, but the reduction across the trigger and follow-up calls together is 46.54%. We reproduce the descriptive calculations, verify 91 timing statistics through a separate weighted rational-arithmetic implementation, and execute 13 scoring-function and 12 analysis-verifier tests. Finite-completion bounds show how missing durations limit all-row timing statements without imputing values. The contribution is a source-linked case study and reusable verification package for separating gate policy, lifecycle timing, and request-level accounting from broader agent-performance claims. Historical provider runs and the full current pipeline were not independently reproduced; general capability superiority and population-level statistical significance are not established. --- ### Inverting Self-Triggered Control: Adversarial Reinforcement Learning for Sparse Denial-of-Service Attacks Authors: Adam Haroon, Erick J. Rodríguez-Seda, Tristan Schuler, Cody Fleming Published: 2026-09-10 Categories: cs.LG, eess.SY arXiv: https://arxiv.org/abs/2609.12016v1 Self-triggered reinforcement learning control (RL-STC) learns the sparsest control schedule that preserves Lyapunov-decreasing stability under a Run-Time Assurance (RTA) override. We invert this: an adversarial RL agent learns the sparsest jamming or Denial-of-Service (DoS) schedule that destabilizes the closed loop, with a Lyapunov-increase admissibility predicate mirroring the defender's safety certificate. We prove a plant-property lower bound on the minimum jam count required for an immediate hold-last medium-access-control adversary to force a crash against a self-triggered controller (STC) satisfying a Lyapunov contract, and recover a certificate-level analog of the consecutive-grouping optimality of prior count-budget DoS scheduling as a corollary. This extends the DoS-scheduling count-budget analysis from periodic and linear-time-invariant to STC controllers. Empirically, we train against four fixed defenders per plant (one Linear Quadratic Regulator (LQR) and three RL-STC) on Pendulum, CartPole, and Quadrotor2D. The learned adversary is the only adversary that crashes every defender on every plant at $100\%$: greedy misses Quadrotor2D LQR on $42\%$ of episodes and periodic misses Pendulum LQR on $97\%$. On jam-time-per-failure it beats baselines by up to $2.8\times$, and shows its widest absolute margin on Quadrotor2D LQR. Robustness ablations show that Gaussian observation noise exceeding the initial-state magnitude and position-only observation both preserve $100\%$ failure rate and keep the learned adversary strictly ahead of both baselines on jam-time-per-failure. --- ### Certified Safety Curation: Distribution-Free Guarantees for Safe Offline Reinforcement Learning Authors: Adam Haroon, Cody Fleming Published: 2026-09-10 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.12014v2 Safe offline reinforcement learning assumes a cost function on every transition. We ask what remains possible when safety can be judged only by comparing short clips and occasionally asking whether an episode exceeded its budget. Certified safety curation answers with a filter-then-clone pipeline: a state-only value trained from segment comparisons scores whole trajectories, Learn-then-Test calibration certifies a selection threshold under a distribution-free $(α, δ)$ bound on the unsafe fraction of the selection, and behavior cloning follows. What is certified is the training set, not the policy, whose cost we report rather than bound. Where no threshold attains the target, the procedure refuses. We are not aware of prior work certifying the composition of a training set for offline RL or imitation. Oracle controls justify the design: reweighting individual transitions fails even with an exact value, so the value selects whole trajectories. The policies satisfy the cost budget on twelve of fifteen DSRL tasks, matching a clone of the ground-truth safe subset, which needs a label on every trajectory. Retrained on the certified selection, the strongest full-label method becomes safe where no setting of its own cost target rescues it. Refusal is predictable: the certificate's probability has a closed form in the purity of the pool's top quantile, which the calibration sample estimates and through which the scorer enters. --- ### QTrans: A Quantum Transformer for Sentiment Classification Authors: Ren-Xin Zhao, Xinjie Huang, Yahong Liu, Maoyu Ye, Jinjing Shi, Shi Wang, Yaonan Wang Published: 2026-09-10 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.12011v1 In small-scale binary sentiment classification scenarios, factors such as negation, contrastive shifts, and cross-word dependencies lead to the non-linear coupling of sentiment cues, making it difficult for conventional lightweight models to fully capture the contextual relationships between tokens. To address this issue, we propose a model named QTrans, which uses parameterized quantum circuits to construct query, key, and value features and derives attention coefficients from Gaussian distances between quantum measurements. By further integrating a quantum feed-forward neural network, residual connections, and layer normalization, the model establishes an end-to-end trainable quantum-classical hybrid framework for sentiment classification. Experimental results on the MR, CR, and MPQA datasets show that QTrans achieves test accuracies of 72.13\%, 69.51\%, and 63.45\%, respectively, representing improvements of 2.88, 3.17, and 3.79 percentage points over the best-performing classical baselines for each dataset. Overall, QTrans expands the application of parameterized quantum circuits in lightweight sentiment analysis and lays an experimental foundation for further research into quantum multi-head self-attention for modeling textual relationships. --- ### Learning Interaction Kernels from Collective Steady States Authors: Baoli Hao, Mauro Maggioni, Ming Zhong Published: 2026-09-10 Categories: stat.ML, cs.LG, math.DS, math.NA, nlin.AO arXiv: https://arxiv.org/abs/2609.12004v2 We propose a learning procedure for system identification in interacting particle systems from single-snapshot observations of collective behaviors, unlike existing approaches that rely on observations of trajectories. This setting leads to a fundamentally ill-posed inverse problem, which we solve by using a regularization strategy based on the empirical distribution of observed configurations, drawn from different, unobserved initial conditions. We test our learning procedure on a variety of representative models with steady-state and quasi-stationary patterns, where collective behaviors encode implicit information about the interaction mechanisms, demonstrating that our approach enables stable and accurate recovery of the underlying interaction laws, leading to faithful reproduction of the collective behavior, and in many cases even of the dynamics leading up to it. --- ### Can We Trust LLM Judges: A Study of Capability-Dependent Biases and Multi-Judge Ensemble for Bias Calibration Authors: Gemma Zhang, Prachi Badarayani, Asmi Kumar, Sadid Hasan, Sulaiman Vesal Published: 2026-09-10 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2609.12002v1 LLMs are increasingly used as automated judges for model training and evaluation, yet individual judges exhibit systematic biases that undermine reliability. Much of prior work has studied biases in pairwise LLM-as-a-judge settings; in this paper, we focus on absolute scoring tasks, which mirror more realistic use cases. Across four benchmarks and six models (36 judge-examinee pairs), we show that a model's task accuracy strongly predicts its judging accuracy (Pearson $r \geq 0.90$ on most models) and inversely predicts its directional bias ($r \leq -0.83$), but that accuracy alone does not ensure fair evaluation: more capable examinee models consistently receive more lenient judgments from all judges ($r \geq 0.83$). To address this, we propose calibrated weighted majority voting (WMV), an ensemble evaluation method that aggregates multiple LLM judges weighted by online estimates of their false-positive and false-negative rates. We introduce a disagreement-based estimator that derives these error rates purely from inter-judge agreement patterns, requiring no ground-truth labels or task metadata. In a simulated experiment with shifting task distributions, our label-free WMV tracks an oracle with perfect error-rate knowledge to within 0.5 percentage points on average, outperforming both individual judges and unweighted majority voting. These results demonstrate that principled multi-judge calibration can simultaneously improve accuracy and correct for systematic leniency without requiring labeled data, offering a scalable path to reliable automated evaluation as model capabilities increase. --- ### Is Bash All You Need? An Empirical Study of Tool Interfaces for Enterprise Digital Worker Agents Authors: Hazel Mak, Susheel Suresh, Sahil Bhatnagar, Barry Wang, Chhaya Methani, Alejandro Gutierrez Munoz Published: 2026-09-10 Categories: cs.SE, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2609.11999v1 In this study, we examine whether a general shell can outperform specialized tools on enterprise tasks. Shell-based agents have shown strong results in coding, but enterprise work also involves moving between applications and services, coordinating with coworkers, and performing professional analysis. We compare five tool interfaces on TheAgentCompany and APEX-Agents using Opus-4.8 and GPT-5.5: typed tools, typed tools plus bash, bash alone, bash with persistent agent-synthesized tools, and programmatic tool calling (PTC), which runs programs whose actions are restricted to a typed tool catalog. Bash alone outperforms typed tools on both benchmarks, improving score by 21.8-24.5 pp on TheAgentCompany and 4.8-7.4 pp on APEX-Agents while using 19-72% fewer total tokens. Adding typed tools or persistent tool synthesis to bash produces no detectable pooled score gain. PTC uses fewer tokens than direct typed calls with broadly similar task performance, but generally underperforms bash alone in both quality and cost efficiency. For enterprise practitioners, these results favor bash alone when arbitrary execution can be isolated and PTC when security or compliance policies require a fixed tool catalog. --- ### SenseNova-U1.5: Towards Native Unified Visual Intelligence Authors: Haiwen Diao, Jiahao Wang, Chenjing Ding, Hanming Deng, Jiangnan Chen, Ruixi Zhang, Ruohui Wang, Wenwen Tong, Xiangyu Fan, Yubo Wang, Yue Zhu, Yuwei Niu et al. Published: 2026-09-10 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.11929v1 We launch SenseNova-U1.5, an 8B-MoT native unified multimodal model that understands, reasons about, and generates visual content within an encoder-free and VAE-free architecture. We strengthen its visual interface through spatially coherent patch reconstruction and scale its training with carefully curated generation and editing data, improved task formulation, structural prompt enhancement, and native resolutions of up to 4K. For post-training, we optimize specialized experts for visual aesthetics, bilingual text rendering, infographic generation, and image editing, and consolidate their capabilities through multi-expert on-policy distillation. Across extensive evaluations, SenseNova-U1.5 largely advances image fidelity, text rendering, complex composition, multi-reference editing, and interleaved generation, while improving instruction following and preserving subject identity, geometry, and unmodified regions. Despite limited exposure to structured formats in its generation data, SenseNova-U1.5 generalizes effectively to long, complex, and structured visual instructions, further proving that multimodal understanding can transfer to visual planning and creation. Together, these findings position native unified modelling as a promising path towards systems that perceive, reason and create within a fully end-to-end framework. We will open-source training code, including supervised fine-tuning, reinforcement learning, and on-policy distillation. --- ### GPU-CFR: 80x Faster Counterfactual Regret Minimization by Compiling the Game to Static Dataflow and CUDA Graph Replay Authors: Boning Li, Longbo Huang Published: 2026-09-10 Categories: cs.DC, cs.AI, cs.GT, cs.MS, cs.PL arXiv: https://arxiv.org/abs/2609.11923v1 Counterfactual regret minimization (CFR) is one of the few large numerical workloads that still runs faster on CPUs than on GPUs. Each iteration sweeps a game tree with up to billions of states in millions of small, interdependent gather and scatter steps issued through a generic tree interface. On a GPU every kernel finishes in microseconds, so kernel launches and framework dispatch dominate the run time, and prior GPU implementations have lost to optimized CPU code. We observe that for a fixed game, everything about a CFR iteration except the numerical values is known before the first iteration runs. We propose GPU-CFR, a compiler and runtime built on this observation. It compiles any game once into static dataflow: flat edge and information-set arrays, precomputed indices, and depth-level batched passes fix the entire operation sequence, and only solver state changes between iterations. Static chance folding, depth-level execution blocks, and a dual-lane reach buffer cut the number of framework operations by up to 18.1x. Because shapes, indices, and buffer addresses never change, CUDA Graph Replay records the iteration once and replays it with a single graph launch. On one A100, across an eight-game suite that spans card games, dice games, and board games, GPU-CFR runs 29.8--80.4x faster than the fastest prior GPU CFR on the same accelerator, and 14--258x faster than LiteEFG, one of the fastest open-source CPU implementations, on the four largest games. The compiled representation carries most of that margin: on eight CPU threads with no accelerator it is already 2.2--51.1x faster than the GPU baseline. On the CPU the optimized path reproduces the reference iterates bitwise, and tree construction and graph capture pay for themselves within the first solve. GPU-CFR beats every CPU and GPU baseline on the mid-to-large games of the suite without changing the update rule. --- ### General Quantification of Covariate and Concept Shifts Authors: Hongbo Chen, Li Charlie Xia Published: 2026-09-10 Categories: cs.LG, cs.AI, stat.ML arXiv: https://arxiv.org/abs/2609.11918v1 Generalization under distribution shift remains a core challenge in modern machine learning, yet existing learning bound theory is limited to narrow, idealized settings and is non-estimable from samples. In this paper, we bridge the gap between theory and practical applications. We first show that existing definition of concept shift breaks when the source and target supports mismatch. Leveraging entropic optimal transport, we propose a key notion: $γ^{*}\!$-concept shifts, and derive a general error bound unifying covariate and $γ^{*}\!$-concept shifts, which applies to broad loss functions, label spaces, and stochastic labeling. We further develop estimators for these shifts with concentration guarantees, and the DataShifts algorithm, which can quantify distribution shifts and estimate the error bound in most applications - a rigorous and general tool for analyzing learning error under distribution shift. --- ### Data Scarcity and Model Sparsity: Mixtures-of-Experts Overfit More to Repeated Data Authors: Atindra Jha, Margaret Li, Jure Leskovec, Percy Liang, Luke Zettlemoyer Published: 2026-09-10 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2609.11917v1 As the supply of human-written text is exhausted, it has become standard practice to repeat language model training data. Prior work has studied data repetition for densely activated Transformers, but the effects of data repetition remains largely unexplored for recently dominant sparse architectures such as Mixture-of-Experts (MoE), despite their increased compute efficiency. We vary data repetition rates across single- and multi-domain data mixes, and across MoE settings, including expert count and granularity. We consistently find, for models ranging from 80M to 1B active (8.5B total) parameters, that MoEs degrade more rapidly under data repetition. This effect increases with sparsity, dictated by total rather than active parameters. While 80M dense models can repeat data over 8x with minimal degradation, MoEs instead begin to suffer at 4x, and deteriorate rapidly, ceding their performance benefits in all-unique data settings to underperform dense models after 32x. We experiment with existing regularization methods as a potential remedy. We find that some methods, such as dropout, can mitigate overfitting. In particular, with strong masking-based regularization, MoEs are able to outperform dense models even when data is repeated more than 64 times. However, no method fully matches the performance of all-unique training data. Finally, we analyze internal mechanisms correlated with MoE overfitting in high repetition regimes, and find that MoE routing universally stabilizes early in training, and that expert specialization correlates with overfitting to repeated data. In sum, our work addresses the adverse interactions between sparsity and data repetition: we present evidence for the core mechanisms of overfitting and its potential remediation, and suggest promising avenues for future methods to reduce over-specialization in model parameters by disrupting memorization patterns. --- ### Can Edge-Deployable Vision-Language Models Identify Species? Authors: William Zhou, Mayukha Siripuram, Xiao Yan, Ziqi Liu, Yi Ding Published: 2026-09-10 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.11916v1 Camera traps often run in the field on edge hardware with limited or no connectivity, making small, locally-deployable vision-language models (VLMs) -- not frontier-scale ones -- the practically relevant class to evaluate for species identification. We test whether models in this deployment-relevant 2--8B range carry genuine taxonomic knowledge, evaluating four such VLMs (Qwen3-VL 2B/4B/8B, Gemma3 4B) against the domain-specific specialist BioCLIP (300M parameters) on a 96-species task, comparing clean iNaturalist photographs against camera-trap imagery from 6 LILA.science collections, on two independently-sampled evaluation sets. All models identify species far above chance, but every model -- general-purpose or specialist -- degrades sharply on field imagery (domain gaps of 9.6--26.6 percentage points, consistent across taxonomic levels and both evaluation sets), indicating the degradation reflects general image legibility rather than fine-grained discrimination failure. BioCLIP substantially outperforms every VLM tested (by 33.2--59.2 percentage points across an expanded 200-image sample for every model) despite its far smaller size, suggesting the gap reflects specialized training data rather than model scale; yet BioCLIP's own domain gap (18.0 points) is statistically indistinguishable from the best VLM's (22.3 points), suggesting the clean-to-field degradation itself is a property of the image-quality shift rather than a general-purpose-model weakness. Under open-set prompting, 5.9--9.6% of responses are syntactically valid but taxonomically nonexistent species names; the relative fabrication-rate ranking across models replicates exactly across both evaluation sets, a more robust finding than any single point estimate. --- ### Generative Marketing Mix Modeling: A Causal Inference Framework Linking GEO and GEM to Business Impact Authors: Masahiro Kato, Daiki Honma, Taka Kato Published: 2026-09-10 Categories: stat.ML, cs.AI, cs.LG, econ.EM, stat.ME arXiv: https://arxiv.org/abs/2609.11915v1 Generative artificial intelligence changes how firms reach customers, but standard marketing data do not record how often users see and notice a firm's name in generated answers. We develop Generative Marketing Mix Modeling (GMMM) to estimate the causal effects of Generative Engine Optimization (GEO) and Generative Engine Marketing (GEM). For GEO, GMMM combines repeated generated answers with question counts, shares of use across generative systems, and notice probabilities. For GEM, it combines records of sponsored placements with notice probabilities. GMMM compares expected business responses under alternative treatment sequences and establishes sufficient conditions for identifying the resulting effects. We investigate the empirical performance of the proposed method using simulated answers to product recommendation in English and Japanese. --- ### Distance generalization in transformers: why bother with positional encoding? Authors: Daniel Henrik Nevermann, Claudius Gros Published: 2026-09-10 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.11913v1 Out-of-distribution length generalization, namely to extrapolate a task from short to longer context, has been studied intensively for transformers. Here we focus on distance generalization, which probes performance when inter-token distances are changed between training and inference, while keeping a fixed context length. We construct two synthetic delay copy tasks, both involving finite distances between source and recall, where tokens are copied either fully or selectively, and test models on delays unseen during training. We address three questions: (A) Do positional encoding schemes such as RoPE and ALiBi improve distance resolution relative to no positional encoding (NoPE)? (B) How does data diversity, the number of inter-token distances seen in training, affect performance? (C) When is distance transfer learning positive or negative? We present a thorough investigation, finding that it is paramount to improve our understanding of the underlying mechanisms. --- ### Artificial Id: Drive and Persistent Alignment in Agentic AI Authors: Yakov Pyotr Shkolnikov Published: 2026-09-10 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.11911v1 Agentic AI is moving from bounded task execution toward systems that retain consequential state, continue operating and adapt across task boundaries. That shift creates a control problem that current harnesses largely solve by hand: objectives, retries, verification, stopping rules and other behavioral transitions are specified externally. We propose an artificial id, an adaptive internal drive for determining whether behavior should continue, stop or change. In a minimal virtual Petri-dish experiment, a controller too small to perform general-purpose reasoning and receiving no task-specific behavioral objective develops useful control through differential persistence. The same mechanism selects an unintended physical strategy when that behavior persists better and later replaces a learned sensor mapping when its environmental meaning changes. These results show that adaptive direction can emerge without being explicitly specified as a behavioral objective. The same persistence that makes such adaptive agency useful can also allow misalignment, corrupted state and unintended behavior to persist across task boundaries. A scalable artificial id would carry consequential state and adaptive drive across those boundaries, making alignment a property of the continuing agentic system rather than of a model response or single trajectory. Such systems require a persistent alignment boundary over trusted observations, consequence channels, persistent state, authority, identity, provenance and hard constraints. --- ### From Protocols to Evidence: Bounded Claims for AI in Service of the Common Good Authors: Nitesh V. Chawla, Paulo Benanti Published: 2026-09-10 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.11910v2 Claims that Artificial Intelligence systems improve decisions, broaden access, reduce harm, or empower users can exceed what their evaluation establishes. Predictive performance alone does not establish safety, the presence of oversight does not establish meaningful control, and faster task completion does not establish understanding or choice. Evaluation must account for unreliable outputs and uneven performance, but also for overreliance, weakened recourse, and displaced human expertise. The harder questions are what the evidence warrants, which relations of power remain unexamined, and where measurement must stop. Assessing improvement requires examining what institutions value and the conditions AI is asked to address. AI is both revelation and intervention. Its use can reveal unmet human needs and assumptions about what matters. Once deployed, it can repair, compound, substitute for, or conceal existing failures. We develop a rupture test that evaluates deployment against explicit human and non-AI baselines. Drawing on Pope Leo XIV's Magnifica Humanitas, we examine dignity and the common good alongside questions of who owns AI infrastructure and who controls its use. These commitments shape judgments about improvement; evidence alone cannot establish moral or political legitimacy. We distinguish evidence-bounded deployment, which limits claims to what has been evaluated, from measurement-bounded governance, which records constraints that favorable evidence cannot override. RISE AI provides an evidence architecture for making bounded claims about Responsibility, Inclusivity, Safety, and Empowerment. It records what is claimed, who answers for it, what evidence supports it, and what would require the claim to be qualified, revised, or withdrawn. --- ### From Protocols to Evidence: Bounded Claims for AI in Service of the Common Good Authors: Nitesh V. Chawla, Paulo Benanti Published: 2026-09-10 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.11910v1 Artificial Intelligence does more than create a governance problem. It can also reveal where institutions have already failed to provide responsiveness, belonging, care, and accountability. Once deployed, AI becomes an intervention in those conditions. It can repair, compound, substitute for, or conceal the failures it encounters. Responsible AI must therefore evaluate both the system and the institutional rupture into which it is introduced. The move from principles to protocols is already underway. The EU AI Act, NIST AI RMF, ISO/IEC 42001, and assurance practices translate commitments into roles, requirements, records, oversight, and assessment. The harder questions are what these protocols actually establish, whose power they leave untouched, and where measurement must stop. Pope Leo XIV's Magnifica Humanitas provides a broader moral frame centered on dignity, technological power, and the common good. Drawing on that frame, we develop a rupture test that links institutional baselines to system evaluation. We distinguish evidence-bounded deployment, which limits claims to what has actually been evaluated, from measurement-bounded governance, which records constraints that favorable evidence cannot override. Within those limits, RISE AI provides an architecture for making bounded, evidence-based claims about Responsibility, Inclusivity, Safety, and Empowerment. Responsible AI requires better engineering, institutional repair, and continued moral and political judgment. --- ### TART: A Modular Tool for Technique-Aware Audio-to-Tablature Guitar Transcription Authors: Akshaj Gupta, Hwi Joo Park, Andrea Guzman, Shamak Gowda, Samhita Konduri, Jiachen Lian, Robin Netzorg, Gopala Anumanchipalli Published: 2026-09-10 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.11904v1 Automatic Music Transcription (AMT) for guitar remains limited by three challenges: existing systems often fail to capture expressive techniques such as slides, bends, and percussive hits; they often assign notes to incorrect string-fret combinations; and they are typically trained on clean recordings, limiting their generalization to noisy real-world audio. To address these challenges, we propose TART, a modular four-stage audio-to-tablature pipeline consisting of (1) an audio-to-MIDI transcription model, (2) an expressive technique classifier, (3) an audio-conditioned T5 encoder-decoder for string-fret assignment, and (4) an automated tablature generator. We evaluate TART in a zero-shot setting on GuitarSet, EGDB, and two augmented benchmarks, Noisy GuitarSet and Noisy EGDB. Averaged across these four benchmarks, TART achieves 81.35% audio-to-MIDI F50 (+6.67 points over the best prior baseline), 71.8% string-fret Tab F1 (+8.5 points over the best prior baseline), and 54.08% end-to-end Tab F1. To our knowledge, TART is the first framework to generate guitar tablature with both fingering and expressive technique annotations directly from guitar audio. --- ### MindTopo: Can Foundation Models Reason in Topological Space? Authors: Yunfei Ge, Anbang Liu, Qineng Wang, Johnalbert Garnica, Jianwen Lyu, Zihan Wang, Reuben Tan, Jianfeng Gao, Ruohan Zhang, Yining Hong, Jiajun Wu, Manling Li Published: 2026-09-10 Categories: cs.AI, cs.CL, cs.CV arXiv: https://arxiv.org/abs/2609.11900v1 Spatial reasoning depends not only on metric properties such as distance, angle, and shape, but also on topological relations that remain invariant under continuous deformation. Cognitive science identifies these relations as foundational to spatial understanding, yet foundation-model evaluations largely focus on metric or viewpoint-dependent relations. We introduce MindTopo, a benchmark of topological intuition across five properties grounded in cognitive science and formal topology: continuity, separation, order, enclosure, and knots. MindTopo evaluates each property at two cognitive levels. Reasoning asks a model to identify topological relations or infer how they change. Planning instantiates a foundation model as a closed-loop agent whose policy selects environment actions. MindTopo contains 11,030 instances across 13 procedurally generated task types with controllable difficulty. We benchmark 14 MLLMs and study agent configurations augmented with image and video generation, including 3 video generative models in planning settings. Every MLLM performs better on reasoning than on planning, and the best-performing model remains far below observed human performance. On Qwen3-VL-2B-Instruct, supervised fine-tuning and reinforcement learning improve reasoning more than planning. Generated observations retain local cues and reach plausible endpoints, but audited rollouts do not reliably follow environment dynamics or preserve topology across transitions. Our website is at https://mind-topo.github.io/ --- ### Caption-once, Frames-on-Demand: Visual-Need Routing for Budget-Aware Agentic Long Video Understanding Authors: Weitong Cai, Hang Zhang, Yukai Huang, Yiqiao Xie, Shan Gao, Jiankang Deng, Songcen Xu, Jifei Song, Zhensong Zhang Published: 2026-09-10 Categories: cs.CV, cs.HC arXiv: https://arxiv.org/abs/2609.11899v1 Long-video understanding on edge devices must reason over hours of content under tight compute and bandwidth budgets. Subsampling visual tokens loses temporal structure, while text-only video memories lose fine-grained visual attributes. We observe a visual-textual duality: language memories carry long-range temporal structure better than dense frames, while pixels remain decisive for attribute-level perception. Building on this insight, we propose Caption-once, Frames-onDemand (CFD), a budget-aware edge-cloud agentic framework. The edge runs a single offline captioning pass that builds a dual-track narrative index, an event-level story skeleton plus a clip-level micro-log, cached and reused across queries without re-captioning. At query time, a cloud-side MLLM reasons over the index in a story-first loop centered on a lightweight Visual-Need Router: a per-query gating module that triggers bounded keyframe retrieval only for perceptual questions (appearance, on-screen text, attribute disambiguation) and keeps temporal-structural questions in language space. The router turns visual access into a first-class, query-conditioned cost, capping per-query frame consumption regardless of video length. Experiments on long-video benchmarks demonstrate strong accuracy-efficiency trade-offs while substantially reducing online visual processing. --- ### CausalArena: Benchmarking Causal Discovery in the Foundation Model Era Authors: Zi-Rong Li, Si-Yang Liu, Tian-Zuo Wang, Han-Jia Ye Published: 2026-09-10 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.11897v1 Causal discovery aims to uncover causal structures from data and is fundamental to scientific reasoning and intervention-based decision making. Its evaluation relies heavily on structural causal models (SCMs), which specify a causal graph together with the mechanisms that generate data, yet existing studies differ substantially in graph families, mechanisms, and evaluation protocols. The emergence of causal discovery foundation models (CDFMs) further complicates evaluation: performance may reflect not only causal discovery ability, but also overlap between pretraining environments and test SCMs, making results on fixed synthetic benchmarks difficult to interpret. We introduce CausalArena, a unified and evolvable benchmark for causal discovery under a common protocol. Synthetic SCMs supply controlled breadth over structures and mechanisms; semantic operational SCMs provide human-auditable, semantically grounded environments beyond standard synthetic generators; and formula-grounded SCMs test discovery under explicit scientific mechanisms. Public real-world datasets provide an additional external-validity check. Experiments across classical, neural, and pretrained methods reveal substantial ranking shifts across SCM families and protocols, showing that strong performance in one benchmark regime does not reliably transfer to others. These results highlight benchmark diversity and pretraining--evaluation overlap as central challenges for evaluating causal discovery in the foundation model era. --- ### 3D Point Splatting for mmWave Radar Novel View Synthesis Authors: Adnan Armouti, Yixuan Gao, Rajalakshmi Nandakumar Published: 2026-09-10 Categories: cs.CV, cs.GR, cs.LG, eess.SP arXiv: https://arxiv.org/abs/2609.11894v1 Solving novel view synthesis (NVS) for millimeter-wave (mmWave) radar requires a renderer that is physically faithful, complex-valued, and multi-viewpoint-tractable. No prior method achieves these three properties simultaneously. Differentiable Monte Carlo (MC) ray tracers implement the radar forward model directly with explicit material modeling and complex outputs, but do not scale to the multi-view optimization NVS demands. Optical-NVS ports of NeRF, hash grids, and 3D Gaussians train fast but discard phase and replace explicit material modeling with opaque learned features, restricting them to power-only range-azimuth (RA) magnitudes. We propose 3D Point Splatting (3DPS), the first differentiable point renderer for radar, derived directly from the standard solid-angle form of the radar equation. Each oriented 3D point carries an ITU-R P.2040 material model, evaluated in closed form, with the resulting complex phasor splatted into range bins through a precomputed point spread function (PSF). The complex-valued output makes the renderer product-agnostic. The same optimized scene yields analog-to-digital converter (ADC), complex range profile (CRP), and RA outputs through standard fast Fourier transform (FFT) pipelines without retraining for each format. On six outdoor ColoRadar scenes, 3DPS reaches 0.587 mean Pearson correlation on held-out RA images. This is between 1.7x and 5.2x the three optical-NVS baselines (RadarSplat, Radar Fields, DART). Training takes approximately 3 minutes per scene on a single RTX 4090. --- ### Nuha-Speech: Building General-Purpose Arabic Speech-LLMs Authors: Yingzhi Wang, Reem Alhazzani, Muhammad Alqurishi Published: 2026-09-10 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.11892v1 As Speech Large Language Models (speech-LLMs) become increasingly multilingual, Arabic remains significantly underrepresented, highlighting the need for dedicated infrastructure to train and evaluate Arabic speech-LLMs. To address this gap, we introduce Nuha-Speech, a comprehensive initiative to develop general-purpose Arabic speech-LLMs spanning dataset construction, model training, and systematic evaluation. Specifically, we constructed a large-scale Arabic Speech Question-Answering (SQA) corpus comprising over 1.5 million training samples to allow instruction tuning over a broad range of core speech tasks. Then, the corpus was used for supervised fine-tuning based on Qwen-Omni model variants at different scales. Finally, we designed an evaluation framework featuring diverse tasks and tailored metrics. Through this work, we aim to establish foundational infrastructures for Arabic Speech-LLMs under constraints imposed by limited Arabic speech resources. --- ### Guided Super-Resolution of Digital Elevation Models with Diffusion-Based Image Generators Authors: Armand Mihai Nicolicioiu, Dominik Narnhofer, Nando Metzger, Daniel Panangian, Ksenia Bittner, Konrad Schindler Published: 2026-09-10 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.11886v1 High-resolution digital surface models (DSMs) play an important role in urban analysis, 3D building reconstruction, and infrastructure monitoring, yet their availability remains limited due to the high cost and complexity of data acquisition. In contrast, coarse DSMs from commercial satellite missions are widely accessible, and high-resolution optical imagery is increasingly available from aerial and satellite platforms. We address the resulting mismatch in spatial resolution and propose a DSM superresolution approach that enhances 5 m DSMs to 0.5 m resolution, using guidance from high-resolution spectral images. Our method employs denoising diffusion to transfer information that is visible only in the image, like crisp outlines and detailed roof structures, into the elevation maps. In this way, surface details are reconstructed more accurately than with conventional interpolation or filtering techniques. Experiments on several cities in Central Europe demonstrate that the proposed approach produces high-quality DSMs with improved structural detail and accurate surface geometry. Our results highlight the potential of guided super-resolution with foundational image priors as a means of reconstructing high-resolution surface models. --- ### CoRA-NAS: Coarse Ranking and Anchor-Residual Refinement for Neural Architecture Search Authors: Yifan Yang, Zhaoyan Wang, Zheng Gao, Xiaoyu Li, Jiaojiao Jiang Published: 2026-09-10 Categories: cs.LG, cs.CV arXiv: https://arxiv.org/abs/2609.11884v1 Zero-cost proxies rank architectures cheaply, but their reliability varies across search spaces. We introduce CoRA-NAS (COarse Ranking + Anchor-residual), a two-stage framework combining a static ranking prior with low-cost learning-curve refinement. CoRA-Rank aggregates capacity and structure-at-initialization proxies through an equal-weight log-rank consensus and a target-free consensus gate. CoRA-Refine samples anchors across this prior, extrapolates their early validation curves, and propagates a learned residual correction with an ExtraTrees model. The refinement uses approximately 1% of the cost of fully training the candidate set. Fully trained architecture-accuracy labels are not used to fit the ranker. One configuration is used across spaces, with space-specific architecture encodings. Across NAS-Bench-201, NAS-Bench-101, TransNAS-Bench-101, and NATS-SSS, CoRA-Refine achieves mean Spearman correlations of 0.946, 0.715, 0.786, and 0.894, respectively. Its worst-space correlation of 0.715 is the highest among the compared methods. On NAS-Bench-201/CIFAR-100, its selected architecture reaches 73.32% accuracy, near the reported ground-truth best of 73.37%. On the pure size space, refinement recovers the static prior's shortfall relative to parameter count, while remaining tied with the strongest capacity proxies within noise. The resulting framework combines cross-space ranking robustness with low-cost architecture selection. --- ### Domain-Specific Hallucination Detection in Large Language Models Authors: Varun Teja Chundru, Debasmita Biswas Published: 2026-09-10 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2609.11878v1 Large language models generate fluent text that can contain unfaithful claims -- a phenomenon known as hallucination. We present a multi-signal detection pipeline combining fine-tuned DeBERTa-v3 classification, Monte Carlo (MC) Dropout uncertainty quantification, and temperature-scaled calibration for response-level hallucination detection. Evaluated on the HaluEval benchmark, our pipeline achieves F1=0.915 and AUROC=0.977 on general-domain tasks, with per-task F1 scores of 0.97 (QA), 0.96 (Summarization), and 0.82 (Dialogue). MC Dropout inference further improves accuracy to 93.2%. A context ablation study confirms the model performs genuine entailment reasoning rather than exploiting surface patterns, with summarization F1 dropping 24% when knowledge context is removed. Learning curve analysis reveals that 25% of training data captures 77% of full-data performance. Beyond detection, we apply Direct Preference Optimization (DPO) to a Qwen2.5-0.5B generator, reducing its hallucination rate from 85.5% to 37.7% (55.9% relative reduction) as measured by our detector. Cross-domain evaluation on the SciFact biomedical benchmark shows that general-domain training transfers poorly (F1=0.52), motivating domain-specific fine-tuning. PubMedBERT fine-tuned on SciFact achieves F1=0.63 and AUROC=0.81, demonstrating that domain-matched pre-training is the strongest adaptation strategy. Code and models are available at https://github.com/varunteja99/hallucination-detection-nlp --- ### Biology-in-the-loop: Amortized Adaptive Hit Discovery in CRISPR Screens Authors: Carl Edwards, Edward De Brouwer, Xiner Li, Namkyeong Lee, Ehsan Hajiramezanali, Anne Biton, Sara Mostafavi, Gabriele Scalia Published: 2026-09-10 Categories: q-bio.QM, cs.AI, cs.CL, q-bio.GN arXiv: https://arxiv.org/abs/2609.11877v1 Many biological discovery problems require experiments to be selected sequentially under constrained budgets. CRISPR screening is a prominent example, as exhaustive perturbation testing is often infeasible and candidate perturbations must instead be prioritized over multiple experimental rounds. Despite the importance of this problem, existing benchmarks for adaptive hit discovery remain limited in scale and diversity. Here, we introduce AssayBench-Loop, a large-scale benchmark for adaptive hit discovery comprising 1,389 CRISPR screens across five phenotype categories. Beyond enabling systematic evaluation, its scale makes it possible to learn acquisition strategies across historical experiments. Building on this resource, we introduce AssayLoop, a sequential experimental design framework combining AssayFormer, a transformer-based amortized acquisition policy trained across historical screens to adapt from experimental feedback, with LLM-derived biological priors through an adaptive handoff. In this view, completed experiments become training data for learning how accumulated evidence should guide what to test next, while LLMs provide prior biological knowledge to seed the search. We further introduce AssayLLM, showing that the same principle can be extended directly to an LLM through task-specific post-training. On temporally held-out screens, AssayLoop achieves a 5.67-fold enrichment over random selection and recovers 27.7% of hits after assaying approximately 5% of the candidate library, outperforming existing adaptive-design methods and standalone LLMs, and AssayFormer alone. Performance improves with increasing historical training data and transfers to phenotype categories excluded from training. These results demonstrate the value of learning acquisition policies across historical experiments and combining them with broad biological priors for efficient adaptive hit discovery. --- ### On the Regularization Landscape for the Linear Recommendation Models Authors: Dong Li, Zhenming Liu, Ruoming Jin, Hao Zhou, Zhi Liu, Jing Gao, Bin Ren Published: 2026-09-10 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.11876v1 Recently, a wide range of recommendation algorithms inspired by deep learning techniques have emerged as the performance leaders on several standard recommendation benchmarks. While these algorithms were built on different DL techniques (e.g., dropouts, autoencoder), they have similar performance and even similar cost functions. This paper studies whether the models' comparable performance are sheer coincidence, or they can be unified under a single framework. We find that all linear performance leaders effectively add only a nuclear-norm based regularizer, or a Frobenius-norm based regularizer. The former ones possess a (surprising) rigid structure that limits the models' predictive power but their solutions are low rank and have closed form. The latter ones are more expressive and more efficient for recommendation but their solutions are either full-rank or require executing hard-to-tune numeric procedures such as ADMM. Along this line of finding, we further propose two low-rank, closed-form solutions, derived from carefully generalizing Frobenius-norm based regularizers. The new solutions get the best of both nuclear-norm and Frobenius-norm world. --- ### The Last AI Built by Humans: Toward Genuine Recursive Self-Improvement Authors: Yi Duan, Ying Liu, Zirui Tang, Haodong Chen, Jun Zhou, Yumou Liu, Bangrui Xu, Yukai Wu, Sidi Chen, Yuhan Zhou, Haoyu Wang, Xiaoyou Yu et al. Published: 2026-09-10 Categories: cs.LG, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2609.11873v3 Recursive self-improvement (RSI) enables AI systems to turn experience and feedback into persistent changes that improve both their capabilities and the process of future improvement. We first use the Headroom-Closed Index (HCI) to reveal the problems of existing LLMs, then introduce the RSI concept and its development roadmap: from improvement-execution autonomy, improvement-strategy autonomy, experience-acquisition autonomy, and environment-adaptation autonomy, to recursive meta-improvement. Next we examine RSI across scenarios (e.g., scientific discovery, embodied intelligence, software engineering), highlighting their distinct requirements and development speeds. Drawing on diverse industry practices and preliminary empirical evidence, we connect RSI research with practical systems and identify key challenges to achieving genuine RSI. --- ### The Last AI Built by Humans: Toward Genuine Recursive Self-Improvement Authors: Yi Duan, Ying Liu, Zirui Tang, Haodong Chen, Jun Zhou, Yumou Liu, Bangrui Xu, Yukai Wu, Sidi Chen, Yuhan Zhou, Haoyu Wang, Xiaoyou Yu et al. Published: 2026-09-10 Categories: cs.LG, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2609.11873v1 Recursive self-improvement (RSI) enables AI systems to turn experience and feedback into persistent changes that improve both their capabilities and the process of future improvement. We first use the Headroom-Closed Index (HCI) to reveal the problems of existing LLMs, then introduce the RSI concept and its development roadmap: from improvement-execution autonomy, improvement-strategy autonomy, experience-acquisition autonomy, and environment-adaptation autonomy, to recursive meta-improvement. Next we examine RSI across scenarios (e.g., scientific discovery, embodied intelligence, software engineering), highlighting their distinct requirements and development speeds. Drawing on diverse industry practices and preliminary empirical evidence, we connect RSI research with practical systems and identify key challenges to achieving genuine RSI. --- ### Evaluating Time-Series Foundation Models and Multimodal Dietary Context for CGM Forecasting Authors: Bowen Zhang, Hsiu-Wen Cheng, Hongyu Yang, Evie L. Shen, Joleen Vansomphone, Yuna Li, Kerry Zhou, Zitian Qu, Suning Zhao, Xiangning Deng, Hua Zhou, Jin J. Zhou Published: 2026-09-10 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2609.11872v1 Continuous glucose monitoring (CGM) provides high-frequency measurements of glucose dynamics and enables short-term glucose forecasting for diabetes management. Although time-series foundation models have shown strong general forecasting ability, their effectiveness for CGM prediction and the added value of multimodal dietary context remain unclear. We conduct a comprehensive empirical study using eight public CGM datasets spanning Type 1 diabetes, Type 2 diabetes, and non-diabetes populations. Under a unified protocol across multiple context lengths and prediction horizons, zero-shot foundation models did not consistently outperform strong task-specific baselines such as Elastic Net and PatchTST. In contrast, lightweight fine-tuning substantially improved forecasting performance. For example, fine-tuned Chronos-Bolt reduced RMSE by 6.5%-18.4% in the T1D cohort and by 8.6%-18.2% in the non-diabetes/T2D cohort, with comparable improvements in both in-distribution and out-of-distribution test settings. We further evaluate multimodal dietary context using CGMacros, which provides temporally aligned CGM signals, food images, and macronutrient records. A residual-based fusion framework reduced overall RMSE by approximately 3% and postprandial RMSE by approximately 15% relative to the CGM-only baseline. Moreover, Chronos-based CGM representations were more strongly correlated with observed postprandial glucose increments than representations from LSTM and CatBoost, even after those models incorporated additional dietary modalities, suggesting that pretrained temporal representations better preserve meal-induced excursion patterns. These findings show that foundation models require CGM-specific adaptation for reliable forecasting and that dietary context provides clinically meaningful signals beyond CGM alone, especially during postprandial periods. --- ### Augustinian BabyLM: What Ostensive Definition Can and Cannot Teach a Small Language Model Authors: Lisa Bylinina Published: 2026-09-10 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.11870v2 A language model normally begins training with random word embeddings: whatever 'banana' means must be learned from training corpora. I implement St. Augustine's picture of word learning, meaning by ostension, for a small masked language model (DeBERTa) trained on 10M words: before training, visually grounded tokens receive embeddings derived from the image regions they label; other tokens start random. Visual initialization leaves a measurable imprint that lasts until the end of training. At the same time, the effect remains invisible under most BabyLM benchmarks, which probe abstract grammatical knowledge: visual initialization does not affect performance there. The only zero-shot exception is object-property knowledge (COMPS), where seeding helps in every configuration. To follow up on this result, I build a corpus-tailored version of the Visual-Property Swap benchmark, which tests color, material, size, and shape knowledge, with per-item training frequency and seeded status. Here, vision-seeded models have a persistent, seed-replicated advantage. Function words and abstract vocabulary also receive strong visual seeds and retain them throughout training, and the training objective draws on them: held-out mask-prediction loss falls for these words in every seed. However, no benchmark I run registers this. What evaluation would pick this up remains an open question. --- ### Augustinian BabyLM: What Ostensive Definition Can and Cannot Teach a Small Language Model Authors: Lisa Bylinina Published: 2026-09-10 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.11870v1 A language model normally begins training with random word embeddings: whatever 'banana' means must be learned from training corpora. I implement St. Augustine's picture of word learning, meaning by ostension, for a small masked language model (DeBERTa) trained on 10M words: before training, visually grounded tokens receive embeddings derived from the image regions they label; other tokens start random. Visual initialization leaves a measurable imprint that lasts until the end of training. At the same time, the effect remains invisible under most BabyLM benchmarks, which probe abstract grammatical knowledge: visual initialization does not affect performance there. The only zero-shot exception is object-property knowledge (COMPS, Misra et al. 2023), where seeding helps in every configuration. To follow up on this result, I build a corpus-tailored version of the Visual-Property Swap benchmark (Lin et al., 2026), which tests color, material, size, and shape knowledge, with per-item training frequency and seeded status. Here, vision-seeded models have a persistent, seed- replicated advantage, confined to the seeded words. As a causal test, I show that synthetic grounding of previously unseeded words transfers the advantage to exactly those words. Function words and abstract vocabulary also receive strong visual seeds and retain them throughout training, and the training objective draws on them: held-out mask-prediction loss falls for these words in every seed. However, no benchmark I run registers this. What evaluation would pick this up remains an open question. --- ### AdamX: Cosine similarity meets gradient descent Authors: Francisco Caldas, Ruben Belo, Cláudia Soares Published: 2026-09-10 Categories: cs.LG, math.OC arXiv: https://arxiv.org/abs/2609.11867v1 We introduce AdamX, a first-order optimizer that incorporates cosine similarity as an adaptive mechanism for controlling update magnitudes. The proposed method is scalable, model-agnostic, and straightforward to integrate into existing training pipelines. We further introduce a variance rectification scheme that promotes smoother optimization during the early stages of training. Overall, we provide empirical evidence that AdamX achieves competitive convergence rates across a range of benchmark datasets and architectures. Performance is evaluated in terms of the number of epochs required to reach predefined performance thresholds under a fixed hyperparameter budget. Code and Experiments available at: https://github.com/FranciscoCaldas/adamX. ---