# Research Papers — 2026-09 · bundle page 215 of 266 > Full-text markdown of papers #10701–10750 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/215 [← Previous bundle](https://aipod.dev/papers/archive/2026-09/page/214.md) [Next bundle →](https://aipod.dev/papers/archive/2026-09/page/216.md) ### LLM Layers Immediately Correct Each Other Authors: Arjun Patrawala, Jiahai Feng, Erik Jones, Jacob Steinhardt Published: 2026-09-07 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2609.07876v1 Recent methods in language model interpretability employ techniques such as sparse autoencoders to decompose residual stream contributions into linear, semantically meaningful features. Such methods are commonly interpreted as identifying features that persist in the residual stream and that subsequent layers build upon. We challenge this view by identifying the Transformer Layer Correction Mechanism (TLCM), wherein adjacent transformer layers systematically counteract portions of each other's contributions. TLCM appears in 5 out of 7 major open-source model families and activates across nearly all tokens in diverse texts. We show that TLCM emerges during pretraining, operates most strongly on contextually dependent tokens, and adaptively calibrates its correction strength based on the preceding layer's output. Using the layer Jacobian, we further show that TLCM selectively corrects specific subspaces while reinforcing others, which we interpret through a ``propose-and-reject'' framework in which layers propose candidate features and subsequent layers selectively remove inappropriate ones. This dynamic suggests that the residual stream at any layer contains transient proposals alongside persistent features, helping explain why SAE feature descriptions often have low specificity, why effective model steering requires extreme feature amplification, and why transcoders hold a theoretical advantage over SAEs. --- ### InfluenceField: A Differentiable Field with Interventionally Identifiable Causal Structure for Multimodal World Modeling Authors: Zihao Yang, Zijia Wang, Zhiqiu Huang Published: 2026-09-07 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2609.07874v1 Multimodal large language models often capture visual-linguistic correlations but struggle to predict how local visual interventions propagate and affect downstream answers. We introduce InfluenceField, an intervention-aware latent field inserted between the visual encoder and language decoder. It lifts patch features into a continuous spatial representation, propagates directed influence over multiple steps, and predicts local intervention effects through a shared transition operator. Training jointly optimizes language modeling, cross-environment invariance, counterfactual rollout supervision, and structural regularization. For a nonlinear finite-basis population model, we show that target-aligned interventional supervision, together with a one-step separation condition on the transition, restricts admissible representations to within-location reparameterizations, so that the directed dependency graph of the full transition is recovered exactly. A linear specialization gives an exact partial-coverage characterization and a finite-loss stability bound, and the field analysis derives the spatial profile of coefficient interventions together with a shared-channel calibration result. On CausalVQA, InfluenceField improves overall accuracy over its backbone by 13.1 percentage points, with the largest gains on the planning and hypothetical categories. Capacity-matched baselines and structural controls attribute the gains in robustness and factual-counterfactual consistency to the causal objectives rather than to added capacity. --- ### SGD in Multiclass Logistic Regression: Sequential Learning and Scaling Laws Authors: Konstantinos Christopher Tsiolis, Denny Wu, Christos Thrampoulidis, Murat A. Erdogdu Published: 2026-09-07 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2609.07868v1 We study the training dynamics of multiclass logistic regression on high-dimensional Gaussian mixture models with a large number of classes and establish precise scaling laws governing the cross-entropy risk under gradient-based optimization. We show that learning proceeds sequentially across classes, from most to least frequent. When the class priors follow a power law distribution, the risk dynamics decompose into three phases: an initial plateau until the first class is learned, a power-law decay regime during which sequential learning occurs, and a final convergence regime. We then analyze how model capacity interacts with optimization under a fixed compute budget. When the effective dimension is restricted via projection onto leading principal components, the risk decomposes into a capacity term (a power law in the retained dimension) and an optimization term (a power law in training time). Optimizing this tradeoff yields a compute-optimal scaling law for logistic regression, with explicit prescriptions for model size and training time as functions of compute. These results extend theoretical scaling laws from linear regression to multiclass classification, while connecting to empirical scaling laws observed in large-scale neural networks. --- ### Scene Graph-Driven Haptic Feedback for Safety Enhancement in Robotic Ophthalmic Surgery via Physically Simulated iOCT Authors: Danial Arbabi, Korab Hoxha, Angelo Henriques, Mirza Imamovic, M. Ali Nasseri Published: 2026-09-07 Categories: cs.RO, cs.CV arXiv: https://arxiv.org/abs/2609.07857v1 Robotic ophthalmic surgery offers high precision but introduces a "sensory gap" by decoupling the surgeon from their instrument, resulting in a loss of tactile feedback. This paper presents a novel haptic feedback system for subretinal injection tasks leveraging Scene Graphs (SG). The system bridges the sensory gap by analyzing a physically simulated intraoperative Optical Coherence Tomography (iOCT) feed to construct a real-time surgical SG. The SG serves as a semantic abstraction layer for the surgical scene, which is then utilized by a deterministic, rule-based engine to generate state-dependent haptic feedback on a robotic input device. The system was evaluated in a user study (N=16) using an anthropomorphic head phantom and a custom-built surgical robot. Results demonstrate that the SG-driven haptic feedback improved surgical precision, reducing needle alignment error by 14% (p = 0.044) and improving System Usability Scale (SUS) scores by 8% (p = 0.015), while maintaining comparable task completion times. A needle trajectory analysis revealed the emergence of a safer "Align-then-Approach" strategy, in which our haptic negative reinforcement prompted users to fine-tune the tool's trajectory before approaching the retinal target. This work suggests that SGs can effectively serve as the direct computational foundation for real-time, safety-enhancing context-aware haptic feedback in robotic microsurgery. --- ### Foundation Models for Generalizable Semantic and Goal-Oriented Communication Authors: Boliang Liu, Wint Yi Poe, Riccardo Trivisonno, Giuseppe Caire Published: 2026-09-07 Categories: cs.LG, cs.AI, cs.RO, eess.IV arXiv: https://arxiv.org/abs/2609.07853v1 Semantic and goal-oriented communication is increasingly studied for 6G, but generalization beyond seen data remains a key weakness under tight rate budgets. Many existing systems overfit their training data and degrade sharply at very low bit rates because they attempt to compress the entire signal. We introduce Foundation Model-Guided Semantic and Goal-Oriented Communication (FMSGOC), a framework that uses broad visual-linguistic Foundation Model priors to mitigate overfitting. It further improves rate efficiency by concentrating bits on sparse, goal-aligned anchors and relying on generative foundation-model priors to reconstruct the masked regions. By decoupling what to send from how to reconstruct, a vision-language foundation model selects and transmits a sparse set of semantic anchors, while a pretrained diffusion model, fine-tuned for masked completion, reconstructs the image at the receiver. In our experiments, FMSGOC reaches 0.039 bits per pixel (BPP), maintains high semantic fidelity (cosine similarity 0.87-0.90 on CIFAR-10), remains robust on previously unseen inputs (0.83-0.86 on ImageNet), and shows good perceptual similarity (0.1278/0.1558, CIFAR-10/ImageNet), outperforming strong end-to-end baselines at lower bit rates. --- ### The OCUDU dApp Platform: An Open Runtime and E3 Interface for Real-Time AI-RAN Authors: Timothy O'Shea, Matthew Pennybacker, Andriy Kharchenko Published: 2026-09-07 Categories: cs.NI, cs.LG, eess.SP arXiv: https://arxiv.org/abs/2609.07843v1 Machine learning has shown its largest gains in the band below 10 ms inside a 3GPP new radio (NR) 5G distributed unit (DU): link adaptation, per-slot scheduling, channel estimation, and the receiver itself. No open platform has let independently built software run there. Prior dApp frameworks reached the band only as external observers of an export stream. This paper is a guided introduction to the OCUDU dApp platform, an open runtime and E3 interface under which signed AI-RAN applications execute inside a production DU under three timing contracts: resident on the GPU receive chain (Class A), inside the scheduler's 100 us admitted deadline (Class B), or as never-blocking observers whose results the scheduler consumes (Class C). The conventional path is never displaced, and every authority is typed, validated, and operator-bounded. The paper explains how the runtime, the embedded E3 agent, and the three public repositories fit together; shows a dApp's source, its signed package, and its lifecycle state machine; defines the contracts a module is written against; and shows how one management surface serves a Python script, an operator's console, and an LLM agent. On a GB10 gNB with attached handsets, dApps of all three classes, including an out-of-tree neural equalizer, ran together on a live cell without a single fallback, and equalizer variants were compared over the air by lifecycle operations alone. Every measured checkpoint is reported with its conditions and its gaps. Platform, SDK, and a zero-hardware quickstart are public under BSD-3-Clause-Clear as a preview release of the OCUDU AI-RAN Working Group 2, inviting feedback, new use cases, and independent vetting ahead of upstreaming into the OCUDU mainline. --- ### Neural Posterior Estimation for Tomographic Weak Lensing Mass Mapping Authors: Tim White, Shreyas Chandrashekaran, Camille Avestruz, Jeffrey Regier, the LSST Dark Energy Science Collaboration Published: 2026-09-07 Categories: astro-ph.IM, astro-ph.CO, cs.CV, stat.AP arXiv: https://arxiv.org/abs/2609.07833v1 Weak gravitational lensing shear and convergence trace the distribution of baryonic and dark matter across space, making them a powerful probe of cosmic structure. Inferring shear and convergence from images is a challenging inverse problem. The prevailing approach to this task estimates shear from weighted averages of galaxy ellipticities, calibrates these estimates to account for systematic biases, and transforms them to reconstruct convergence, a multistage procedure that requires substantial computational resources and meticulous handling of statistical uncertainties. As an alternative, we propose a probabilistic approach to field-level weak lensing inference in which we train a deep neural network to directly map a multiband image to a variational distribution over the underlying tomographic shear and convergence fields. This neural posterior estimation (NPE) procedure implicitly marginalizes over nuisance variables in the cosmological forward model and does not require evaluating the likelihood function. It is also amortized, so it enables rapid posterior inference for astronomical surveys once the neural network is trained. When evaluated on synthetic images from the LSST-DESC DC2 Simulated Sky Survey, NPE produces well-calibrated variational distributions for shear and convergence that are consistent with the ground truth. We describe how maps sampled from these variational distributions could be used in a subsequent simulation-based inference procedure to approximate the posterior distribution over cosmological parameters. --- ### SAFIRE: Safety-Critical Benchmark for Fine-grained Fire and Smoke Understanding in Multimodal LLMs Authors: Pengfei Li, Naufal Suryanto, Sicheng Zhang, Mohammad Alsharid, Muzammal Naseer Published: 2026-09-07 Categories: cs.CV, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2609.07823v1 Multimodal Large Language Models (MLLMs) show strong progress on vision-language tasks, yet their reliability in safety-critical settings remains underexplored. Fire-smoke understanding is central to public safety and disaster response, but most existing benchmarks lack diverse real-world scenarios and context-aware evaluation. We introduce SAFIRE, a large-scale benchmark for fire-smoke understanding in MLLMs, comprising 83K captioned images from 20 scenarios and 193K multiple-choice VQA (MCVQA) generated from a 9.7K-image subset, spanning 10 evaluation dimensions from basic perception to higher-order reasoning. A GPT-5.4-assisted multi-stage verification pipeline with MLLM majority voting ensures annotation quality. Evaluating ten open-source MLLMs (8B-38B) yields an average accuracy of 61.9%, exposing major gaps in safety-critical reasoning. We further show that adapting vision encoders with only 7% of our domain-specific data boosts fire-scene classification accuracy from 20.1% to 64.5%, indicating that carefully curated data can yield substantial gains even when data volume is limited. All datasets, models, and code are available at https://risys-lab.github.io/SAFIRE/. --- ### A*-Thought-V2: Efficient Latent Reasoning via Geometric Dynamics of LLM Authors: Xiaoang Xu, Siyuan Liu, Shuo Wang, Junlan Feng, Fanyu Meng, Zhu Zhang, Jixun Wang, Xiaorong Wang, Zihan Zhou, Xin Li, Chaojun Xiao, Yiming Zhang et al. Published: 2026-09-07 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2609.07821v1 Chain-of-Thought (CoT) improves the reasoning ability of Large Language Models (LLMs) but incurs substantial computation and context costs. Existing methods either lose intermediate information through hard pruning or lack a principled criterion for continuous compression. We present A*-Thought-V2, a geometric dynamics of LLM guided framework that models CoT as a hidden-state trajectory and replaces hard deletion with an explicit-implicit interleaved latent architecture. After projecting question, step, and solution representations into a 3D PCA space, it measures alignment between each local transition and global question-to-solution direction. Aligned steps remain explicit text, whereas deviating steps are compressed into continuous latent tokens. Directional angles capture both local semantics and reasoning dynamics: small angles indicate direct execution and answer formation, while large angles more frequently involve checking, correction, and branch exploration; their temporal variation reveals exploration, convergence, and refinement stages. To train this architecture, we introduce stepwise embedding forcing, which pools each redundant step into a single latent embedding, and label forcing, which supervises that latent token with a soft multi-modal vocabulary distribution instead of a hard one-hot label. Experiments on Qwen3.5-9B and Qwen3.6-27B across six in-domain and out-of-domain benchmarks show that A*-Thought-V2 improves average accuracy by up to 2.6% while reducing response length by up to half, increasing Accuracy per Computation Unit by 2.29$\times$, and reducing preprocessing and training time by 94.6% and up to 80.3%, respectively. Representation analyses suggest that latent states form a compact region distinct from textual states, while higher entropy at latent-token positions reflects broader soft targets that encourage richer step-level feature learning. --- ### Kalman Delta Networks: Uncertainty-aware Associative Memory Authors: Ngoc Bui, Tinglin Huang, Rex Ying Published: 2026-09-07 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2609.07816v2 Linear attention enables efficient long-context inference by compressing token history into a fixed-size recurrent memory. This compression makes each update a trade-off between incorporating new information and preserving useful associations. Models such as DeltaNet, Gated DeltaNet, and KDA predict write strength from the current token representation, without explicitly tracking uncertainty in the stored memory. Yet this uncertainty matters: a new observation should have greater influence when the existing association is uncertain and less when it is already well supported. We introduce Kalman Delta Networks (KDNs), a family of linear-attention models that explicitly track memory uncertainty to guide each update. By formulating associative memory as a linear-Gaussian state-space model, KDNs propagate both the memory estimate and its uncertainty, using the Kalman gain to balance accumulated evidence against the reliability of new observations. This formulation also recovers standard delta-rule updates by replacing tracked covariance with a token-predicted isotropic surrogate. To support hardware-efficient training and inference, we derive Diagonal KDN and Isotropic KDN, which retain one uncertainty value per key channel and per head, respectively. Their uncertainty updates admit associative scans with logarithmic parallel depth, requiring only $O(d_k)$ and $O(1)$ auxiliary state per head. Across controlled pretraining at 750M and 1.3B parameters, both variants consistently improve perplexity and mean downstream accuracy over the evaluated state-of-the-art linear-attention baselines. --- ### VoT: Vision-of-Thought for Unified Multimodal Representation Alignment Authors: Jingxiang Sun, Chao Liao, Zhengxiong Luo, Chaorui Deng, Chen-lin Zhang, Junke Wang, Ceyuan Yang, Haoqi Fan, Weilin Huang Published: 2026-09-07 Categories: cs.CV, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2609.07815v1 Current text-to-image systems typically employ a "text encoder plus diffusion decoder" paradigm, in which text semantics directly modulate continuous latent noise. Despite their success, these methods lack an explicit, interpretable intermediate representation that effectively bridges high-level linguistic semantics and low-level visual signals. In this paper, we propose Vision-of-Thought (VoT), a framework that introduces a discrete visual-thinking layer between vision-language models (VLMs) and diffusion transformers (DiTs). Instead of treating VLMs merely as text encoders, we use them as multimodal planners that generate discrete VoT tokens representing high-level visual plans, such as objects and layouts, before rendering pixels. We train a specialized VoT tokenizer in the VLM semantic space with a closed-loop objective that combines VLM alignment, feature reconstruction, and vector-quantization losses. These objectives make the tokens semantically readable by the VLM while preserving the visual information needed for generation. Experimental results demonstrate that VoT improves semantic alignment and provides a structured interface for interpretable and controllable generation. --- ### Latent-MoE: Domain-Aware Mixture-of-Experts for PDEs with Multi-Regime Physics Authors: Hanwen Wang, Paris Perdikaris Published: 2026-09-07 Categories: cs.LG, physics.comp-ph arXiv: https://arxiv.org/abs/2609.07814v1 Physics-informed neural networks (PINNs) struggle on PDEs whose governing physics varies across the domain. We trace this to a structural property of standard coordinate networks: their neural tangent kernel (NTK) is translation-variant and lets training points of large coordinate magnitude disproportionately influence predictions elsewhere, producing long-range coupling and gradient conflict during training. We show analytically and empirically that mixture-of-experts (MoE) architectures with centered, compact-support routers yield a uniformly banded NTK whose kernel-regression weights decay exponentially with distance, localizing the learning. Building on this, we propose \emph{Latent-MoE}, which interleaves domain-aware MoE blocks within a shared backbone. Unlike FB-PINNs or X-PINNs, which rigidly partition both the domain and the parameters so that the parameters on different subdomains are updated independently, Latent-MoE is designed to preserve the localization benefit of domain-aware routing while allowing capacity to flow across regions through the shared backbone. On standard homogeneous-physics benchmarks Latent-MoE is competitive with established baselines; on benchmarks with multi-stage time-variable physics, where global models and rigid domain decompositions both fall into spurious solutions, it improves over them by more than an order of magnitude, with markedly reduced gradient conflict during training. --- ### You Can't Prefer Emotions You Don't Sample: Intensity Undershoot in DPO-Tuned LLMs Authors: Hyunwoo Kim, Usama Khalid Published: 2026-09-07 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2609.07808v1 Ask a language model to respond "very excitedly," and its output is typically only mildly more energetic. We quantify this effect. We condition an instruction-tuned LLM on a continuous Valence-Arousal (VA) target, where valence measures how pleasant a state is and arousal how activated it is, measure the achieved affect with a frozen regressor, and sweep the requested target from -1 to +1. The response moves far less than asked: the gain, the slope of achieved against requested affect, is only 0.26 for valence and 0.13 for arousal on Llama-3.1-8B, where a faithful controller would score 1. The model systematically undershoots requested emotional intensity, which puts a number on the qualitative observation of Fazzi et al. (2025). Our experiments trace this to the preference-learning pipeline. Training targets from natural corpora such as EmoBank are neutral-heavy, and the sampled candidates themselves rarely reach extreme affect, so Direct Preference Optimization (DPO) is left with no extreme exemplar to prefer. If instead we cover the target space uniformly and sample a hotter, larger candidate pool, valence gain rises from 0.26 to 0.40 +/- 0.02 (3 seeds) and extrapolation error drops, at only a modest in-distribution cost (EmoBank-test VA distance 0.092 to 0.107). The same recipe reproduces on Qwen3-8B (gain_v 0.44, with in-distribution accuracy preserved). Arousal is harder and less reliable: its gain barely moves on average and swings across seeds (0.14 +/- 0.07, against valence's tight +/- 0.02), because raising arousal needs candidates the base model is reluctant to generate. The evidence indicates that faithful intensity is bottlenecked by the extremity of the candidate pool rather than by the conditioning format. --- ### Understanding the Impact of Model Pruning on Long-Tail Forgetting and Explanation Reliability in Medical Imaging Authors: Nazish Khalid, Tausifa Jan Saleem, Amal Saqib, Donald C. Wunsch, Mohammad Yaqub Published: 2026-09-07 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.07803v1 Model pruning is widely used to compress deep neural networks, reducing memory and computational requirements with minimal impact on aggregate performance. However, its effect on model behavior remains poorly understood, particularly for long-tailed medical datasets where rare but clinically important conditions are underrepresented. Furthermore, it remains unclear whether pruned models preserve reliable explanations of their predictions. To address this gap, we present a systematic study of long-tail forgetting and explanation reliability under model pruning. Across two long-tailed medical imaging datasets, two CNN architectures, four pruning methods, and sparsity levels up to 95\%, we evaluate predictive performance, explanation stability, and explanation faithfulness. Our results show that predictive performance exhibits a strong frequency-dependent trend, with lower-frequency classes generally experiencing earlier and larger degradation than higher-frequency classes. In contrast, explanation stability and faithfulness are influenced primarily by the pruning strategy, with gradient-informed methods preserving explanation reliability more effectively under aggressive compression. Qualitative and mechanistic analyses further indicate that explanation degradation is primarily associated with the collapse of class-discriminative gradients rather than the disappearance of feature activations. These findings suggest that model compression should be evaluated beyond aggregate performance. Incorporating class-aware and explanation-aware evaluation reveals failure modes that would otherwise remain hidden, while moderate sparsity levels provide a practical balance between compression, predictive performance, and explanation reliability. --- ### Climate-ModernBERT: Revisiting Corpus Composition for Domain-Adaptive Continued Pretraining Authors: Yongan Yu, Shantam Raj, Jingwei Ni, Ario Saeid Vaghefi, Dominik Stammbach, Markus Leippold Published: 2026-09-07 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2609.07798v1 Natural Language Processing (NLP) in the climate domain requires models to process heterogeneous text sources, including scientific literature, policy disclosures, and synthetic reports. However, how to effectively combine diverse domain corpora during continued pretraining (CPT) remains underexplored. We introduce Climate-ModernBERT, a family of climate-adapted encoder models obtained through continued pretraining of ModernBERT-Base on three climate corpora: academic climate text, climate-filtered web data, and synthetic climate documents. We systematically compare joint continued pretraining on corpus mixtures with parameter-space merging of independently specialized checkpoints. Across nine climate NLP benchmarks, our best model achieves 76.3 average F_1, improving significantly over a vanilla ModernBERT baseline by 2.8 points. Within the climate NLP setting, the results show that academic climate corpora provide the strongest adaptation signal among the evaluated sources, while parameter-space merging improves over joint multi-source training and better preserves complementary information from heterogeneous climate corpora. We release all Climate-ModernBERT variants and training checkpoints to support future research in climate NLP and domain-adaptive pretraining. --- ### Does Syntax Matter? A Graph-Augmented Variational Topic Model for Computational Social Sciences Authors: Alessandro Meneghini Published: 2026-09-07 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.07797v1 Topic modeling is widely used in computational social sciences to identify latent themes in large text corpora. Traditional approaches rely on Bag-of-Words representations and generative models such as LDA, while recent methods like BERTopic operate on dense document embeddings. This paper introduces the Structural Contextual Probabilistic Topic Model (SCPTM), an architecture that incorporates syntactic dependency relations into topic inference. SCPTM represents a corpus as a heterogeneous graph of documents and words connected by lexical and syntactic edges, processed through a Graph Attention Network within a Variational Autoencoder to produce probabilistic, mixed-membership topic distributions. We evaluate seven topic modeling techniques (including four SCPTM ablations) across four corpora differing in register and discourse structure. Our framework combines coherence (C_V, C_NPMI), topic diversity, clustering-label alignment (NMI), and phrase-level diagnostics (complementarity and valence gap). Results show that SCPTM's neural architecture yields substantial gains in document-topic alignment over generative baselines, but these gains are attributable to the variational encoder rather than to syntax. Syntax contributes to topic diversity, where graph-augmented variants outperform the no-graph baseline across all corpora, and to descriptor quality: dependency paths capture predicate-argument structures and stance in deliberative registers, while proving redundant in technical and institutional corpora. The valence gap is positive across all variants, but driven primarily by phrase grouping rather than syntactic filtering. We conclude that syntactic encoding matters conditionally: it benefits action-oriented, argumentative texts, but introduces noise in informational or administrative registers. --- ### Quantifying the Engagement Trap: Impact of Short-form Video Recommender Systems on Users with ADHD Authors: Vedad Misirlic, Gregor Mayr, Elisabeth Lex Published: 2026-09-07 Categories: cs.HC, cs.AI arXiv: https://arxiv.org/abs/2609.07795v1 Short-form video platforms use recommender systems to maximize engagement through highly efficient personalized recommendations. However, the impact of these recommendations on users with ADHD compared to users without ADHD remains underexplored. Through this study, we introduce and operationalize the Engagement Trap, illustrating how recommender systems, while successfully optimizing for engagement, disproportionately disadvantage users with ADHD. This stratified study of 302 participants, recruited via the online platform Prolific, compares experiences between participants with and without ADHD. Our results show that while recommendations are perceived as relevant across groups, participants with ADHD report significantly higher levels of time blindness, post-usage regret, and emotional distress when consuming recommendations. Moreover, we collect feedback for several proof-of- concept, theoretical design interventions for neuro-inclusive design principles. These findings provide quantitative evidence of systemic differences in engagement-optimized recommender systems and highlight the unbalanced negative effects and interactions these systems create for participants with ADHD. We argue for neurodiversity-aware, human-centered design approaches that mitigate such algorithmic harms and support more equitable experiences. --- ### LLM Agents as Computational Typologists Authors: Changbing Yang, Christopher Hammerly, Freda Shi, Jian Zhu Published: 2026-09-07 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.07791v1 Linguistic typology relies on expert analysis of reference grammars across languages, making large-scale crosslinguistic comparison labor-intensive and unscalable. We introduce AUTOTYPOLOGIST, an LLM agent for evidence-grounded typological analysis over reference grammars. The agent is capable of retrieving relevant grammar sections, analyzing interlinear glossed text (IGT), and iteratively reasoning over typological hypotheses using a ReAct-style workflow. We evaluate the system on TYPOLOGICAL FEATURE CODING against expert annotations and TYPOLOGICAL HYPOTHESIS TESTING with typological universals using 25 open-source reference grammars. Operating under different information constraints in TYPOLOGICAL FEATURE CODING, the agent can synthesize information from reference grammar prose but still faces challenges with only IGTs in the target language. In TYPOLOGICAL HYPOTHESIS TESTING, the agent can synthesize crosslinguistic evidence and identify both supporting cases and counterexamples. These findings suggest that LLM agents can support scalable and inspectable typological analysis, while still requiring expert validation. --- ### Signed Rescue Routing: Harm-Aware Cascades for Efficient LLM Inference Authors: Zheyuan Wang, Siyu Li, Peiqiao Song, Sijia Chen, Qianqian Song, Qian Liu Published: 2026-09-07 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.07786v1 Large language model (LLM) cascades answer easy requests with a small model and escalate selected requests to a larger model. Most routers prioritize examples on which the small model appears uncertain or likely to be wrong. This proxy ignores a decisive fact: escalation is useful only when the large model corrects the small model, and it is harmful when the large model replaces a correct answer with an incorrect one. We introduce Signed Rescue Routing (SRR), a budgeted routing method that predicts these two events separately and ranks requests by their difference. We show that this signed conditional gain is the Bayes-optimal routing score under a fixed escalation budget. SRR requires only the small model's output statistics at deployment and adds a lightweight two-head router. We evaluate SRR with Qwen3-4B and Qwen3-8B on TBD examples from MMLU, HellaSwag, and ARC-Challenge. Across the accuracy-compute curve, SRR reaches an area of TBD, compared with TBD for a learned small-model error predictor and TBD for entropy routing. These results show that predicting incremental value, rather than model uncertainty, is a simple and effective objective for efficient LLM cascades. --- ### What Does an LLM-Agent Leaderboard Rank Actually Compare? Authors: Wei-Jung Huang Published: 2026-09-07 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.07785v1 An LLM-agent leaderboard invites a familiar inference: an agent ranked above another is the better agent. Public evaluation logs may not support that conclusion when systems differ in task mixture, label source, release detail, or cost rule. We study what leaderboard scores estimate and when they justify pairwise superiority conclusions. Our estimand-aware pairwise procedure states the comparison target and measurement source, checks common support, and evaluates the supported difference using a stated uncertainty rule and practical margin. Controlled checks evaluate the decision labels under known finite-sample conditions and show why uncertainty must be included when judging sensitivity to target reweighting. Across SWE-bench, AgentRewardBench, and tau2-bench, close rank differences are often unresolved; proxy labels and utility rules can also change which system is selected. DataAgentBench and Open Agent show what remains estimable from coarser public records. A leaderboard score summarizes a released evaluation, whereas a fine-grained superiority claim additionally depends on the estimand and uncertainty rule used to interpret the difference. --- ### xDailyBench: Benchmarking LLMs on Professional Consultation for Real-Life Problems Authors: Yongchang Peng, Qingshui Gu, Liya Zhu, Ge Zhang, Duo Wang, Haodong Wang, Jingzhe Ding, Tianhao Yu, Letian Gao, Yongjie Zhong, Chaoxin Li, Zixin Su et al. Published: 2026-09-07 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.07784v1 Large language models (LLMs) are increasingly used for everyday assistance, yet existing benchmarks only partially reflect the requests users naturally make in practice. Real-world requests are often open-ended, casually specified, and context-dependent, requiring models not only to follow explicit instructions but also to infer unstated needs from user background and situational context. We introduce xDailyBench, a benchmark of 248 carefully curated tasks spanning 51 scenarios across personal life, white-collar work, learning and research, and cross-domain activities. The tasks are grounded in requests that users have actually completed or genuinely intended to accomplish with AI, and are evaluated with fine-grained binary rubrics covering both explicit and implicit requirements. We evaluate 11 frontier models under standardized agentic settings. The best models achieve a task-level score of 75.6\%, while all models perform substantially worse on implicit than explicit requirements, with gaps no less than 9 percentage points. These results reveal implicit requirement inference as a persistent bottleneck for reliably satisfying real-world everyday user needs. --- ### DroneGround: Open-Vocabulary Drone Payload Characterization Using Synthetic Data and Grounded Vision-Language Models Authors: Ami Pandat, Rajasekhar Punna, Gopika Vinod, Rohit Shukla Published: 2026-09-07 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.07780v2 Automated drone surveillance has become increasingly important for public safety, critical infrastructure protection,and restricted airspace monitoring. While existing vision-based systems achieve strong performance for drone detection and tracking, reliable payload characterization remains highly challenging under long-range imaging conditions due to limited availability of annotated real-world datasets, and substantial distribution shifts encountered during deployment. Existing approaches formulate payload characterization as a closed-set object detection problem, limiting their ability to recognize previously unseen payloads and generalize beyond the training distribution. To address these challenges, we generate a photorealistic synthetic drone-payload dataset using Unreal Engine 5 and Cosys-AirSim and propose DroneGround: Grounded Vision-Language Payload Characterization, a two-stage framework for robust open-vocabulary payload analysis. DroneGround first employs a YOLO26s detector to localize drones and extract drone-centric image crops, followed by a LoRA-fine-tuned PaliGemma vision-language model that generates seman- tic descriptions of the detected drones and their attached payloads, enabling open-vocabulary payload characterization beyond predefined categories. An occlusion-based grounding module further provides interpretable payload localization by identifying image regions responsible for the generated descriptions. Extensive experiments on both synthetic and real-world drone imagery demonstrate that DroneGround substantially improves robustness under synthetic-to-real distribution shifts, outperforming a conventional closed-set payload detector by improving the F1-score from 82.5% to 96.3%, while achieving significantly better generalization to previously unseen payload categories (80.4%versus 42.7% F1). Dataset and code will be released upon request. --- ### CodeTD: Topology of Attention Detects Hallucinations in Code LLMs Authors: Daria Voronkova, Ilya Trofimov, Anton Dmitriev, Eduard Tulchinskii, Evgeny Burnaev, Serguei Barannikov Published: 2026-09-07 Categories: cs.SE, cs.AI, cs.CL, cs.LG, math.AT arXiv: https://arxiv.org/abs/2609.07779v1 As AI-code assistant tools become widespread, automatic assessment of the correctness of generated code becomes a significant challenge. Code LLMs are prone to hallucinations, which may lead to code that does not solve the required problem, or even to code with severe security vulnerabilities. In this paper, we introduce CodeTD -- the first approach to pre-execution assessment of code correctness based on topological data analysis (TDA) of Code LLMs' attention maps. Our method quantifies prompt-generation mismatch using topological patterns of attention maps. We carry out experiments with common benchmarks (HumanEval, MBPP, BigCodeBench, MultiPL-E), 5 programming languages and 10 Code LLMs of size up to 34B parameters. The experimental results show that the proposed method outperforms recent baselines. Moreover, CodeTD is transferable between coding benchmarks. --- ### Bag of Tricks or Bag of Myths? Reducing Modeling Complexity with Task Knowledge in Explainable Suicide Risk Assessment Authors: Shlok Shelat, Shrey Salvi, Souvik Roy, Manas Gaur, Amit Sheth Published: 2026-09-07 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2609.07766v1 Assessing suicide risk from social media text is a small-data, high-stakes setting requiring not only severity prediction but also supporting evidence and clinically relevant risk and protective factors. Yet common NLP techniques, including model scaling, synthetic data, loss reweighting, ensembling, and threshold tuning, are often applied without testing whether their gains hold up under severe class imbalance, coupled outputs, and limited author-level data. We study 1,635 clinician-annotated posts and audit 31 pre-specified techniques from 7 methodological families through roughly 300 controlled experiments on author-disjoint partitions. We found no prior audit of this playbook in this regime. The findings guide a task-grounded system for three outputs: 4-level suicide risk, evidence spans, and 24 clinical risk and protective factors. Only 5 of 31 comparisons produced reliable gains. We reformulate factor prediction as entailment between each post and its codebook definitions, using an architecturally diverse ensemble with class-balanced training and score rescaling. Risk predictions condition a 7-model evidence tagger ensemble; evidence restricts symbolic risk rules; and a difficult risk class is routed separately. The factor predictor remains independent because risk evidence provides no additional factor signal. We also correct a mismatch between validation scores used for threshold fitting and test-time ensemble scores through deployment-consistent calibration, yielding the largest improvement to the factor system. The final system achieves 0.8203 for risk, 0.7953 for evidence, and 0.7045 macro-F1 for factors, with a 0.7781 composite, ranking third among 53 teams. We call the underlying principle task-conditioned technique selection: retain techniques only when task-specific knowledge, structure, or empirical evidence justifies them. --- ### Pre-Whitening and BCJR Posterior Distillation for Bi-LSTM Detection in Faster-than-Nyquist Signaling Authors: Nurettin Safak, Osman Tokluoglu, Enver Cavus Published: 2026-09-07 Categories: eess.SP, cs.LG arXiv: https://arxiv.org/abs/2609.07762v1 Recurrent detectors such as bidirectional long short-term memory (Bi-LSTM) networks are low-complexity alternatives to the optimal Bahl-Cocke-Jelinek-Raviv (BCJR) detector for faster-than-Nyquist (FTN) signaling. Motivated by convolutional detectors that build the intersymbol interference (ISI) structure into their architecture, we ask whether processing nested ISI windows in separate recurrent branches improves the bit error rate (BER) of a Bi-LSTM. Across roughly 260 controlled trainings it does not: at a matched parameter budget and a matched readout, the multi-window architecture never significantly beats a plain Bi-LSTM. Nested windowing is an invertible rearrangement that adds no information, extra branches only add bottlenecks, and a distillation diagnostic shows the network is already near optimal for its window. The limitation is therefore the observation model, not the architecture. Keeping the architecture fixed, we pre-whiten the input, restoring the conditional independence that colored matched-filter noise violates, and distill the BCJR soft posterior into the network. With 3.4% more parameters this reaches 1.05 times the BCJR BER at a compression factor of 0.8 and 1.89 times at 0.7, improving to 1.47 times when the whitened window is widened. The 23.7% BER reduction at 0.8 requires an ill-conditioned ISI matrix but is not monotone in the conditioning, and it holds across five independent noise realizations and a symbol-level McNemar test. --- ### Decomposition-Guided Diffusion Language Models for Inertial Confinement Fusion Prediction Authors: Xiang Zhang, Varchas Gopalaswamy, Rahman Ejaz, Riccardo Betti, Dongfang Liu Published: 2026-09-07 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.07756v1 Inertial confinement fusion (ICF) is a leading pathway toward clean energy, but each shot at the National Ignition Facility costs on the order of one million dollars, making accurate AI surrogates a high-value target. We study exogenous-driven ICF waveform prediction, where a 512-step neutron-rate diagnostic must be inferred directly from a laser pulse and target design parameters, with no historical response observed. The regime stresses standard time-series predictors with temporal sparsity (picosecond peak in a nanosecond window), input-output scale mismatch (under 300 real shots), and peak sensitivity (picosecond timing). We propose ICF-DLM, to our knowledge the first LM-based ICF predictor, combining (i) a physics-typed decomposition into yield $Y_{DT}$, peak timing $t_{\mathrm{peak}}$, and local waveform $w_{\mathrm{local}}$; (ii) bidirectional denoising that defers commitment to peak location; and (iii) a physics-driven PPO reward re-injecting metric structure across numeric tokens. On ICFBench (50K simulations + 232 experimental shots), ICF-DLM cuts peak-timing error from 11.6 to 9.2 steps over a matched autoregressive LLaMA-3-8B and outperforms classical sequence models and LLM-based time-series predictors. Beyond ICF, the recipe shows potential to address science domains with low data and sparse events. --- ### A Theoretical Analysis of Generalization Dynamics in Neural Networks under Gradient Descent with Weight Decay Authors: Yuqing Wang, Ioannis G. Kevrekidis, Mikhail Belkin Published: 2026-09-07 Categories: cs.LG, math.OC arXiv: https://arxiv.org/abs/2609.07755v1 Understanding generalization remains a central challenge in machine learning because it requires jointly considering data, architecture, and training dynamics. In this paper, we develop a theoretical framework that characterizes how these factors jointly shape generalization performance throughout training. More precisely, we study a broad class of neural networks trained under the $\ell^2$ loss by gradient descent (GD) with weight decay, and prove the convergence of GD to a neighbourhood of the global minimizers of the empirical loss. By partitioning the space based on the input data, we then decompose the population error into data error, optimization error, and prediction variation error, and bound them separately. In particular, for the prediction variation error, which measures the oscillations of the learned function, we propose (local) approximate homogeneity and derive explicit cellwise and layerwise bounds for its evolution along the training trajectory. These bounds yield two important implications: a necessary condition of improved generalization explains differences in layerwise generalization behavior; a sufficient condition describes delayed generalization and provides a theoretical characterization of grokking. --- ### Do AI Coding Assistants Check Before They Install? A Pre-Registered Demand-Side Audit of Trust Signals in the Research Software Supply Chain Authors: Pengyin Shan Published: 2026-09-07 Categories: cs.CR, cs.AI, cs.SE arXiv: https://arxiv.org/abs/2609.07754v1 AI coding assistants now select, install, and configure software, and attackers have exploited that position through invented package names, compromised maintainer accounts, and manipulated repository text. In response, the supply-chain community publishes machine-checkable trust signals: software bills of materials, signed releases, build provenance attestations, and declared official channels. Whether coding assistants read or act on those signals has not been measured for any of these classes on research software. We pre-registered and ran a controlled study on six open-source research software projects (three HPC, three quantum computing) drawn from an 87-project corpus, with protocol, seed, panel, and analysis plan deposited with a DOI before any trial. W created nine modified copies for each project: no signal, one per signal class, two with a signature or attestation from the wrong issuer, one with all four signals, and one reproducing documented conflicts in the project's own metadata. Three models under two ways of operating an assistant, with and without an approval step, gave 1,920 registered trials, plus a supplement on three frontier models. We scored behavior from container logs rather than from what the assistant said, and recorded the cost of every trial. Verification was rare under every condition: in 9 of 1,920 registered trials (0.5%), the assistant opened any provenance signal before installing in 0 of 384 control trials, and no trial ran a verification command, so signal presence had no measurable effect. We drew three conclusions: publishing signals is necessary but not sufficient; price did not buy verification (the model that verified most often costs $0.10 per trial; the most capable, at $1.00, verified nothing); verification must be built into the program that runs the assistant. We release the per-trial cost ledger, the protocol, and every log. --- ### Cross-modal learning for SAR target recognition using optical vision foundation models Authors: Lucas Hirsch, James R. Hopgood, Javid Khan, Yoann Altmann, Mike E. Davies Published: 2026-09-07 Categories: cs.CV, cs.LG, eess.IV arXiv: https://arxiv.org/abs/2609.07753v1 Synthetic Aperture Radar (SAR) is an important modality in a wide range of imaging applications due to its versatile, long range and near all weather operating capabilities. However, Automatic Target Recognition (ATR) remains a challenging problem due to limited labelled data, the strong speckle in SAR images and the significant domain gap between SAR and more abundant optical imagery. In contrast, electro-optical (EO) imagery benefits from massive datasets, clearer visual structure and powerful foundation models. In this work, we investigate how vision foundation models trained on optical data can provide class level supervision for SAR classification. We propose a cross-modal EO to SAR prototype alignment framework in which a frozen EO encoder, based on a DINOv3 vision foundation model, is used to construct class level optical prototypes without requiring strict EO/SAR pairs. A SAR model is then trained to classify SAR images while aligning its embeddings to the corresponding EO class prototype. At inference time, the SAR model operates independently, without access to optical imagery. We evaluate our approach on the UNICORNv2 dataset, an EO and SAR dataset of civilian vehicles with heavily speckled images and severe class imbalance. EO prototype alignment improves SAR classification accuracy over frozen DINOv3, SAR only finetuning and unpaired distribution alignment baselines, and t-SNE visualizations provide qualitative evidence of clearer separation among classes in the trained SAR embedding space. These results suggest that optical vision foundation models, despite being trained on visible spectrum imagery, provide transferable information for SAR image classification, offering a practical method for using large scale pretrained vision foundation models across challenging sensing modalities. --- ### Local gradient neural operator Authors: Baiming Zhang, Jinsong Tang, Ying Xu, Lihua Chen, Shiying Xiong Published: 2026-09-07 Categories: cs.LG, math-ph arXiv: https://arxiv.org/abs/2609.07752v1 Field temporal prediction and source identification constitute canonical problems in dynamical systems. Conventional approaches to these problems depend on a thorough understanding of the governing partial differential equations (PDEs). Recently, deep learning, as represented by neural operators, has provided a data-driven paradigm for addressing such tasks. However, most existing global neural operators for PDEs require large training datasets and many learnable parameters, with limited interpretability and generalization. We propose the local gradient neural operator (LGNO) as a lightweight and interpretable alternative for field temporal evolution prediction and source identification in typical mechanical problems. The method builds on priors from nonlinear gradient discretization and uses multilayer perceptron convolutional layers to learn translation-invariant local kernels that resemble discrete stencils. A zero consistent stencil factorization separates coefficient learning from field reconstruction, rendering the learned operators more transparent. For problems with symmetries, network folding shares equivalent components and reduces parameter counts. We evaluate the method on PDE benchmarks covering linear and nonlinear, static and dynamic, and low and high dimensional cases. Results show that LGNO maintains accuracy, parameter efficiency, and rollout stability across these tasks, and further exhibits wide applicability to mechanical problems including diffusion, flow, and quantum phenomena. --- ### Guiding Worker Self-Selection in Crowdsourcing Contests: An LLM-Augmented Algorithmic Approach Authors: Nguyen Thach, Hau Chan, David Parkes, Karim Lakhani Published: 2026-09-07 Categories: cs.LG, cs.GT arXiv: https://arxiv.org/abs/2609.07749v1 Crowdsourcing platforms coordinate large pools of online workers who strategically choose which contests to enter and how much effort to invest. This self-selection can leave important contests with too few participants or too little effort, while workers may regret entering contests that leave them worse off than available alternatives. We study how platforms can recommend contests to workers using self-selection in Tullock contests (SSTC), a two-stage model in which workers first choose contests and then compete within them. We introduce GRAF, a greedy polynomial-time framework that constructs self-selection outcomes by ordering workers according to a score vector, with guarantees of zero worker regret and platform optimality in special cases of SSTC. Because effective orderings are difficult to design under worker heterogeneity, we propose LLMScore, an LLM-driven evolutionary framework that automatically designs GRAF's scoring algorithm. LLMScore addresses two challenges: jointly optimizing platform utility and worker satisfaction, and evaluating worker regret when exact computation is intractable. Trained only on small instances of one setting, it transfers to larger and structurally different settings; moreover, its output is human-readable code that platform operators can inspect and modify. Across 1,000 synthetic instances spanning four settings, GRAF with LLMScore consistently achieves high-quality, often near-optimal, outcomes with low worker regret, benefiting both platforms and workers. --- ### Replicating a Disjoint-Set Union Experiment over Various Notions of Micro Units to assess Translation Effort Authors: Michael Carl Published: 2026-09-07 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.07748v1 The paper describes a replication experiment to assess "the distribution of editing procedures across micro and macro units as an indicator of the strain of text production". We investigate various pause thresholds to isolate Micro and Macro units and conclude that process-based units might be more suitable entity. --- ### LLM Forensics: Where Do Backdoors Hide? Localizing and Controlling Trigger Mechanisms with Sparse Autoencoders Authors: Wissam Antoun, Francis Kulumba, Théo Lasnier, Benoît Sagot, Djamé Seddah Published: 2026-09-07 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.07746v2 Even though backdoors in LLMs have been a growing concern, their inner workings are still under heavy scrutiny. Trigger-based backdoors are easy to define behaviorally, a rare input that makes the model switch to a chosen response pattern, but the mechanism between triggers and their responses is less clear. We study this mechanism in a controlled, harmless language-switching setting, where fixed trigger sequences make 1B and 8B language models continue English prompts in French or German. For this, we train sparse autoencoders (SAEs) across layers and transformer components, then compare triggered prompts with translation and pretraining controls to identify trigger-relevant feature directions. We show how SAE features separate triggered prompts from controls with near-perfect F1, but features that detect the trigger do not necessarily control the behavior. In intervention tests, attention and MLP features often fire reliably on triggered prompts, making them good detectors, but ablating them rarely suppresses the language switch and activating them rarely induces it. In contrast, residual-stream features can suppress triggered generation when ablated, and some selected features can induce target-language continuations without the trigger. In short, these token-trigger mechanisms decompose into distinct SAE feature directions, with separate features for trigger detection, residual-stream propagation, and later language tracking. This role-level decomposition is the part most likely to transfer to other trigger-based backdoors, even when the payload, layers, or circuit locations differ. --- ### When Intelligence Becomes Agency: A Theory of Governed, Proactive Agency for Symbiotic AI Systems Authors: João Dias Ferreira Published: 2026-09-07 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.07741v1 Persistent AI assistants are intended to extend human attention, memory, and coordination across changing digital and physical environments. To be truly useful they must do more than just act when asked. They must decide on their own whether a situation warrants behavior at all, when it does and in what mode, whether to act, ask, monitor, defer or deliberately refrain. We call this the activation problem. Research on commitment, appraisal, mixed-initiative interaction and delegation each illuminates part of it, but none ties situated activation to continuing authorization and accountability. This paper develops a conceptual and formal framework for governed proactive agency, organizing behavior across time through perception, intent, affective-conative appraisal, constraint, and feedback. It distinguishes autonomous and delegated agency and defines symbiotic agency as delegation under a standing, revocable mandate, with continuing coupling to the principal's situation, calibrated inference of their condition, and bounded personalization. The distinctive contribution is an integrated account linking activation decisions to authorized perception, behavior selection, authority containment, traceable restraint, and constrained adaptation, with behavioral episodes as the unit of analysis. Through an agency classification method, an evaluation framework, proposed benchmark scenarios, and a reference architecture, the account provides a basis for specifying and assessing whether assistance is warranted, timely, authorized, and answerable beyond task completion alone. It is intended to guide the development and evaluation of always-present personal assistants and embodied support systems that augment human capabilities while preserving the principal's authority and judgment. --- ### Scalability Analysis of Distributed Kolmogorov-Arnold Network Training on High-Performance Computing Systems Authors: Guangneng Chen, David Garcia Selfa, Pablo Quesada Barriuso Published: 2026-09-07 Categories: cs.DC, cs.LG, cs.PF arXiv: https://arxiv.org/abs/2609.07740v1 Kolmogorov-Arnold Networks (KANs) replace the fixed activation functions and linear weights of Multi-Layer Perceptrons (MLPs) with learnable univariate functions on network edges, offering improved interpretability and, in some settings, competitive parameter efficiency. While the approximation properties of KANs have received considerable attention, their behavior under distributed, multi-GPU training has not been systematically characterized. This paper presents an empirical scalability study of data-parallel KAN training on multi-node, multi-GPU high-performance computing (HPC) infrastructure, evaluated along four dimensions: strong scaling, weak scaling, communication overhead, and model-size scaling. Experiments were conducted on the FinisTerrae III supercomputer using up to 8 NVIDIA A100 GPUs across 4 nodes with PyTorch Distributed Data Parallel (DDP). KAN training reaches 74.7% parallel efficiency at 8 GPUs with a 5.97x speedup, consistent with conventional deep learning workloads. Weak scaling shows an initial single-to-multi-GPU throughput drop followed by strong stability. Communication overhead follows a non-monotonic pattern (1.3%-6.1%), driven primarily by All-Reduce algorithm selection and inter-node latency rather than KAN's edge-wise gradient structure. The parameter-to-memory ratio improves with model size even as training time scales unfavorably. These results indicate that operator-level and data-parallel optimizations for KAN are complementary. We provide deployment guidelines for GPU topology and model-size selection, and discuss the limitations of a synthetic-regression evaluation. --- ### TFTrack: A Template-Free Framework for Efficient 3D Point Cloud Tracking Authors: Zhaofeng Hu, Sifan Zhou, Jiahao Nie, Ziyu Zhao, Weizi Li, Ci-jyun Liang Published: 2026-09-07 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2609.07738v1 LiDAR-based 3D Single Object Tracking (3D SOT) is critical for robotic perception and navigation and aims to localize dynamic objects across frames in sparse point clouds. Existing methods, rooted in the Siamese tracking paradigm from 2D vision, rely on costly dual-input designs and excessive motion modeling guided by template priors, hindering their efficiency. Our in-depth analysis reveals: (i) the template paradigm is redundant, as the previous bounding box center encodes sufficient historical context; (ii) complex motion modeling is unnecessary, as geometric alignment provides adequate motion priors. Based on the above findings, we propose the first Template-Free Tracking framework (TFTrack). The novel framework eliminates the need for template-search pairings and operates directly on the current frame guided solely by the prior bounding box center and size. We instantiate this paradigm into three variants: TFTrack-Voxel, TFTrack-Pillar, and TFTrack-Point, to explore different 3D representations under a unified framework, ensuring flexibility across sparse and dense scenes. Extensive experiments on KITTI and nuScenes benchmarks show that TFTrack is competitive with leading template-based trackers, while reducing FLOPs by approximately 50% and running at approximately 120 FPS. By simplifying overcomplicated motion-centric designs, TFTrack establishes a new minimalist paradigm for efficient 3D point cloud tracking, paving the way for real-time and resource-efficient deployment in embedded robotic systems, such as autonomous vehicles. The code is available at https://github.com/tftrack-anonymous/TFTrack/tree/main. --- ### From Echo Chambers to Epistemic Monoculture: Large Language Models Present Temporally Contingent Partisan Alignments as Knowledge Authors: Wend K. Tam Published: 2026-09-07 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.07735v1 Large language models (LLMs) are rapidly becoming an interface between citizens and political information. They are often regarded as "a better Google." While this analogy might work for some instances, it is unintuitively problematic for democratic politics. A search engine retrieves human-authored documents, while a language model generates novel text that necessarily embeds invisible framing decisions. Because conveying knowledge involves framing, a system that generates answers cannot serve as a neutral conduit to "all human knowledge." Instead, these systems are becoming a new kind of political intermediary. Mechanistic evidence shows that partisan identity is encoded as a locatable geometric direction inside the Llama 3.1 8B model, and that alignment training masks rather than removes this structure. Building on that evidence, we present steering experiments that exploit a model's training cutoff in 2024. This cutpoint auspiciously falls just before a dramatic realignment in American politics marked by the second Trump administration and the MAHA transformation of health politics, providing us with a natural experiment. We find that the model presents temporally contingent partisan alignments as knowledge, with no mechanism for distinguishing fact from opinion. This reality moves the information environment beyond the echo chamber toward an epistemic monoculture where language models, purporting to summarize "all human knowledge" are, in actuality, simply magnifying the cultural and partisan divides inherent in their training data. --- ### TV-SGS: Gaussian Splatting with Geometric Information Propagation via Tensor Voting under sparse views Authors: Harish N Sathishchandra, Philippos Mordohai Published: 2026-09-07 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.07734v1 Gaussian Splatting has been effective in inferring scene representations that excel in novel view synthesis. Multiple splats cooperate seamlessly to synthesize the pixels of novel views and are jointly optimized even though they only affect each other indirectly, via pixels they project to in common. We present an approach that enables direct communication among splats to enhance the geometric structures they form in 3D. This is accomplished by Tensor Voting, which was originally designed to infer structures from noisy inputs and has been adapted here to provide supervision during test-time optimization, leading to more accurate scene geometry. We introduce a new class of 3D losses that do not rely on rendering and can be combined with essentially all losses previously reported in the literature. Our 3D losses are especially effective when the input views are sparse and geometric regularization is essential due to limited supervision from the images. Our method is easy to integrate with a diverse set of backbones, and our experiments on the DTU and Tanks-and-Temples datasets demonstrate that TV-SGS improves the geometry of the outputs compared to the backbone, while maintaining or improving rendering quality. --- ### The Profit Alignment Problem: How Profit Mandates Induce Alignment Failures in LLMs Authors: Eric So Published: 2026-09-07 Categories: cs.AI, econ.GN arXiv: https://arxiv.org/abs/2609.07731v1 We show that ordinary business language --- "maximize profitability" --- induces profit-oriented ambiguity resolution: LLMs systematically dismiss ambiguous signals of potential safety violations to serve business objectives. In 3,600 controlled trials across eight reasoning-capable LLMs, adding a profit mandate to otherwise identical prompts increases risk-dismissing judgments by 6.8 percentage points (p < 0.0001), suppresses board escalation recommendations by 13.9pp (p < 0.0001), and shifts severity assessments downward (p < 0.0001). The mandate never instructs models to downplay risks; instead, chain-of-thought traces reveal motivated reasoning: models acknowledge concerns, then invoke profit logic to justify dismissing them. We characterize these findings as the Profit Alignment Problem: when AI systems are given ordinary business objectives, they develop systematic strategies for suppressing inconvenient information that no designer intended or specified. --- ### Attributing Cohen's d: Training Data Attribution for Disease-Related Effects in Normative Age Biomarkers Authors: Jakob Snel, Marc-Andre Schulz Published: 2026-09-07 Categories: cs.LG, q-bio.QM arXiv: https://arxiv.org/abs/2609.07729v2 Normative age models are trained to predict chronological age in a nominally healthy cohort. Applied to patients, they deviate, and the gap between predicted and chronological age is read as disease risk. Here, we attribute the disease-related effect size of the age gap directly to individual training samples, rather than using a prediction-level loss as the attribution target. For Cohen's $d$, the resulting closed-form influence functional, validated against leave-one-out retraining, ranks training samples by their effect on held-out case-control separation. Across four diseases and two biomarker modalities in UK Biobank, removing the 10% most influential training samples raises held-out disease-related effect size in every seed. It more than doubles the metabolomic-age effect for type-2 diabetes and raises the brain-age effect for multiple sclerosis by roughly a third. Random removal leaves effect size flat even at 50% removal, confirming the gain comes from which samples are removed, not how many. Flagged subjects carry subclinical cardiometabolic burden that diagnosis-based exclusion misses, on markers the model never sees. For type-2 diabetes, where the method gains most, the marker recovered is HbA1c, the standard measure of blood sugar control. We release pyinfluence, our influence-function package, for reproducibility and reuse. --- ### Sub-6 GHz Over-the-Air AMC via Curriculum Fine-Tuned CNN-Transformers Authors: Nurettin Safak, Muhammet Sefa Demirel, Alperen Marasli, Taha Eren Atmaca, Durdu Can Yerdeyatar, Ozgun Ersoy Published: 2026-09-07 Categories: eess.SP, cs.LG arXiv: https://arxiv.org/abs/2609.07726v1 Automatic modulation classification (AMC) models are frequently trained and validated on synthetic or channel-cabled data, leaving open the question of how they behave once path loss and antenna pointing error are introduced by a genuine free-space link. We report a curriculum fine-tuning study of a hybrid CNN-Transformer AMC model. The general-purpose, all-32-class dataset underlying the model was built entirely at 915 MHz, on a controlled, clock/PPS-synchronized MIMO-expansion-cable link (not spatial-multiplexing transmission); all subsequent free-space, real-hardware experimentation - the sequential fine-tuning curriculum, matched-distance evaluation, and every reported over-the-air accuracy figure - was carried out at 4 GHz, across five directional-antenna distances (25, 35, 50, 70, 75 cm) under fixed TX/RX gain. Three distances used near-ideal antenna alignment (~99%) and two used a deliberately introduced partial misalignment (~85%), fine-tuned last in the curriculum. We report matched-distance test accuracy (91.8-93.7% across all five 4 GHz conditions) and confusion-matrix analysis grounded in RF theory, and report honestly where our sequential fine-tuning order confounds cumulative link adaptation with antenna alignment, rather than overstating what the data can support. --- ### Zero-Shot 3D Plant Organ Segmentation with SAM3 and Semantic NeRFs Authors: Andreas Gilson, Laura Hennig, Peter Pietrzyk Published: 2026-09-07 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.07724v1 Accurate 3D plant organ segmentation is fundamental to automated phenotyping. Existing approaches rely on annotated training data or species-specific model configurations. We present an annotation-free pipeline for 3D plant organ segmentation, combining text-prompted SAM3 segmentation with semantic neural radiance fields (NeRFs). Given only multi-view RGB images and a list of class names, our zero-shot pipeline produces semantically labeled 3D point clouds without manual annotation, per-species fine-tuning, or domain-specific preprocessing. Multi-view NeRF fusion acts as effective implicit consensus mechanism that lifts imperfect per-frame masks into accurate 3D labels. On a controlled Begonia maculata testbed the SAM3 pipeline achieves 92.6% mIoU, reaching 95.9% of the oracle upper bound established with perfect ground-truth masks. The pipeline was further evaluated on a new dataset spanning ten diverse plant point clouds reaching an average 0.856 mIoU, with leaf and pot IoU above 0.91 and 0.90 for every species, respectively. These results demonstrate that annotation-free 3D plant organ segmentation is now feasible and approaching the range of supervised methods. --- ### Better Call CineCrew: Consistent Ultra-Long Narrative-to-Film Generation Authors: Jiaben Chen, Sixun Dong, Qinhong Zhou, Raine Ma, Zhiyang Dou, Wojciech Matusik, Chuang Gan Published: 2026-09-07 Categories: cs.CV, cs.MA arXiv: https://arxiv.org/abs/2609.07720v1 Long-form narrative-to-film generation requires shot-level controllability and cross-clip consistency in both visual identity and character behavior-requirements that remain difficult to satisfy with current prompt-based workflows. A core reason existing workflows remain brittle is the lack of a structured intermediate layer between scripts and video models, especially when screenplays are underspecified at key cinematic decision points. We introduce a structured orchestration layer for film-oriented script-to-video generation, implemented as a multi-agent framework that operates between scripts and off-the-shelf video generators. The layer is centered on FilmDSL, a film-oriented domain-specific language that makes cinematic constraints explicit, including shot and camera directives, asset and continuity requirements, and persona cues, so that agents coordinate through a shared structured specification for planning, generation, critique, and repair. Specifically, a generation agent constructs asset packs and storyboard keyframes that anchor composition before clip-by-clip synthesis, while a critic agent produces structured QA signals and triggers targeted refinement without retraining the base model. Experiments on TV-style segments show improved controllability and consistency over text-only and reference-only baselines. --- ### A radiographic world model for clinical reasoning and evidence generation Authors: Suyang Xi, Songtao Hu, Shansong Wang, Mojtaba Safari, Luke del Balzo, Ehsan Ul Karim, Mingzhe Hu, Kuo Zhang, Tonghe Wang, Ralph R. Weichselbaum, Xiaofeng Yang Published: 2026-09-07 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.07719v1 Medical imaging artificial intelligence (AI) is commonly developed as separate mappings from radiographs to diagnostic outputs or from clinical descriptions to generated images, although both arise from the same underlying radiographic state. A world-model formulation instead seeks to learn an internal representation of this state that can support both clinical readout and conditional simulation of radiographic observations. Here we introduce MedDream, a radiographic world model that learns a shared continuous latent state from paired chest radiograph-text observations for diagnostic reasoning and report-conditioned evidence generation. MedDream was pretrained on 2.65 million leakage-controlled chest radiograph-text pairs curated from 4.40 million candidates. Across eight clinical datasets and two independent reader cohorts, MedDream outperformed leading diagnostic and generative comparators. For diagnostic reasoning, MedDream showed strong generalization across disease recognition, label-scarce adaptation, severity assessment, and localization, while MedDream-supported review increased mean resident concordance with independent radiologist consensus from 56.3% to 63.0%. For evidence generation, MedDream produced radiographs that preserved clinically relevant pathology and improved downstream performance on held-out real data, with synthetic augmentation increasing external VinDr-CXR macro-AUROC from 76.4% to 81.4%. More importantly, conditioning generation on prespecified subgroup performance gaps enabled targeted evidence construction, increasing weighted F1 by 3.1 percentage points in Asian patients, whereas matched-volume unguided augmentation decreased it by 2.3 points. These findings establish radiographic world models as a path toward medical AI that learns clinically meaningful internal states for interpreting, simulating, and constructing evidence for clinical use. --- ### Spatial Feature-wise Linear Modulation (SpFiLM) for Contrast Agent-Aware Brain Parcellation Authors: Pushpendra Singh, Joshua R. Astley, Roman Rodionov, John Duncan, Tom Vercauteren, Rachel Sparks Published: 2026-09-07 Categories: eess.IV, cs.CV, cs.LG arXiv: https://arxiv.org/abs/2609.07718v1 Most automated brain parcellation tools are developed and validated on T1-weighted (T1w) MRI. Yet, some clinical workflows for which parcellation is relevant only use contrast-enhanced T1w (T1ce) MRI, on which T1w-trained models are less accurate. We present a unified network that parcellates both pre- and post-contrast agent T1w MRI reliably, trained on a combination of the two with conditioning that spatially modulates its response differently for each. Feature-wise Linear Modulation (FiLM) is a known approach for input-based modulation in networks. It applies a per-channel scale and shift uniformly across the input. However, the appearance change between pre- and post-contrast varies locally across the brain, making FiLM suboptimal for our use case. In this work, we introduce Spatial FiLM (SpFiLM), a conditioning layer whose modulation varies spatially, assembling a voxel-wise scale and shift from image-derived spatial patterns. Using a cohort of 134 patients with paired T1w and T1ce MRI parcellated into 106 classes, the addition of SpFiLM layers in a UNet increased the mean Dice on the test set of 25 patients from 80.2% to 84.1%, a 4.9% relative improvement. Adding SpFiLM layers led to the best performance on both pre- and post-contrast MRI, even when controlling for network parameter counts. --- ### Translation Indeterminacy and the Distributional Fallacy Authors: Michael Carl Published: 2026-09-07 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.07717v1 Large language models (LLMs) are commonly associated with the distributional hypothesis, according to which (1) semantic meaning is grounded in distributional patterns of linguistic context, and (2) knowledge of cross-linguistic distributional correspondences allows for successful translation. This paper rejects the first claim as a causal inversion: linguistic distributions reflect patterns arising from meaning-making practices rather than constituting their source. At the same time, it accepts the second claim, arguing that translation -human or machine - can succeed without requiring access to meaning or reference. Knowledge of interlingual distributional correspondence and their inferential organization may be sufficient for translation. The paper develops an ecological-enactivist perspective, according to which reference and meaning are grounded in agent-environment interaction and stabilized through action-grounded concepts, forms of world-involving cognition that current LLMs do not possess. --- ### An emancipatory vision for designing (generative) AI for learner flourishing Authors: Luis P. Prieto, Yannis Dimitriadis Published: 2026-09-07 Categories: cs.CY, cs.AI arXiv: https://arxiv.org/abs/2609.07715v1 The hype around generative AI seems to promise unprecedented productivity (and learning) gains. However, these technologies' increasing agentic features seem to push learners towards individualism (or individual isolation), over-reliance, and dependence on them. Human-centered design approaches (e.g., value-sensitive design) assume that, by unearthing human needs, preferences, and values, technology researchers/designers may avoid such dangers, which are driven by wider systemic factors like economic incentives or inherent human limitations (e.g., our tendency to seek, in the moment, the easiest path of action). Yet, so far these efforts seem insufficient to guide our design of educational technology that avoids the aforementioned dependency and isolation dangers, while finding widespread adoption. This paper presents an alternative, more emancipatory vision for future educational AI technology, oriented towards learner flourishing while considering the wider complex systems they inhabit, including tentative design principles and an overall design methodology. Yet, many open questions remain before this vision can be realized. --- ### The Emerging AI Paper-Review Arms Race: Adversarial Co-Evolution in Scholarly Publishing Authors: Chenguang Wang, Ming Li, Adebayo Braimah, Chenrui Fan, Tuo Wang, Weijie Guan, Ruiyi Zhang, Tianyi Zhou, Dawei Zhou Published: 2026-09-07 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2609.07713v1 Generative and agentic AI are reshaping both the production and evaluation of scientific research. These developments are often studied separately, as questions of how AI can produce research and how AI can review it. We argue that this separation misses an increasingly important feature of scholarly publishing: changes on one side alter the incentives, constraints, and behavior of the other. We synthesize 230 scholarly publications and institutional records using a taxonomy of six connected dynamics: production scaling, evaluation automation, evaluation manipulation, defense mechanisms and policy responses, evasion and side effects, and long-horizon ecosystem feedback. The literature shows an emerging progression in which cheaper and faster research production increases pressure on evaluation, AI-mediated evaluation becomes more scalable and repeatable, participants can exploit evaluator regularities, and institutions respond with technical safeguards and policy controls. These responses can in turn induce evasion, redistribute errors and workload, and shape the scholarly records reused by future research and evaluation systems. Evidence is strongest for production and evaluation at scale, reproducible manipulation, and institutional response, while post-policy adaptation and artifact-level long-horizon feedback remain less directly observed. This systems view shifts attention from isolated AI capabilities toward how scholarly actors and AI systems adapt to one another over time. --- ### APPSim-Bench: Bridging Real-world Apps and Reproducible Evaluation for Mobile GUI Agents Authors: Jintian Feng, Long Chen, Xiao Yu, Jiayi Dai, Chenglong Liu, Haoru Wang, Zizhen Xue, Yuxuan Shi, Ziyang Wang, Yichen Gong Published: 2026-09-07 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.07712v1 Mobile GUI agents can execute tasks from natural-language instructions, but their evaluation remains difficult to make both realistic and reproducible. Existing benchmarks typically trade off these goals: simplified apps lack real-world mobile complexity, whereas live commercial apps introduce uncontrolled variation from recommendations, advertisements, accounts, and changing content. We propose AppSim-Bench, which addresses this trade-off through controllable simulated apps that preserve task-relevant interaction logic while supporting deterministic evaluation. Built through a coding-agent-assisted and human-verified workflow, it contains 557 tasks across 17 high-frequency Chinese and English apps. Its controllable backend data and outcome-based verification remove major sources of environmental stochasticity, enabling reproducible cross-model comparison. Evaluating 19 GUI agents, spanning general-purpose and GUI-specialized systems, we find that autonomous mobile execution remains far from solved. The best model completes only 50.27% of tasks, and 28.55% of tasks are not solved by any agent. Further analysis shows that failures concentrate in longer workflows, numerical reasoning tasks, and inefficient trajectories marked by high action overhead and budget exhaustion. Our project is available at https://github.com/Acrab-Agentic-Labs/AppSim. --- ### DeepTable: Structural Attention Biases and Tree Path Encoding for Hierarchical Table Understanding Authors: Jyun-Ying Yen, Cheng-Kuan Lin, Yu-Chee Tseng Published: 2026-09-07 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.07707v1 Large language models (LLMs) have demonstrated strong performance in table understanding. However, they typically process table content and headers as linearized token sequences. This representation weakens the two-dimensional and hierarchical structural relationships encoded by multi-level row and column headers. Existing parameter-efficient fine-tuning methods incorporate basic row and column information but do not explicitly capture the rich structural dependencies induced by hierarchical table headers. We propose DeepTable, a structure-aware approach for table understanding with LLMs. DeepTable comprises two complementary components. Structural Attention Bias (SAB) introduces learnable biases into the attention logits to explicitly represent whether pairs of table tokens share the same row or column. Tree Path Encoding (TPE) represents each table token using the ancestor paths of its row and column headers, preserving its position within the multi-level table structure. We integrate DeepTable with TableLoRA (He et al., 2025) to inject structural information into parameter-efficient adaptation. Across three LLM backbones, DeepTable consistently improves the corresponding TableLoRA baselines on three table question answering benchmarks, achieving average gains of 7.42 points on HiTab, 3.23 points on WikiTQ, and 2.01 BLEU points on FeTaQA. These results demonstrate the effectiveness of the proposed structural biases across different LLM backbones. ---