# Research Papers — 2026-09 · bundle page 246 of 266 > Full-text markdown of papers #12251–12300 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/246 [← Previous bundle](https://aipod.dev/papers/archive/2026-09/page/245.md) [Next bundle →](https://aipod.dev/papers/archive/2026-09/page/247.md) ### SimpleDesign: A Joint Model for Protein Sequence and Structure Codesign Authors: Jiarui Lu, Yuyang Wang, Yizhe Zhang, Jiatao Gu, Navdeep Jaitly, Joshua M. Susskind, Miguel Ángel Bautista Published: 2026-09-03 Categories: cs.LG, q-bio.BM arXiv: https://arxiv.org/abs/2609.03377v1 Proteins are fundamental to biological processes, with their function determined by the complex interplay between the amino acid sequence and the three-dimensional structure. Developing generative models capable of understanding this intrinsically multi-modal relationship is crucial for fields like drug discovery and protein engineering. Existing models often rely on a multi-stage training process where autoencoders that tokenize data into latent representations are trained in a first stage. Secondly, a generative model is trained on the latent representation of the autoencoder(s), i.e., generative modeling in a latent space. We hypothesize that this multi-stage training is not necessary to obtain performant co-design models and thus present SimpleDesign, an effective multi-modal protein design model trained directly in the data space. SimpleDesign leverages a single-stage end-to-end objective that combines discrete cross-entropy for sequences and a regression objective for structures. In order to effectively model the difference in sequence and structure modalities, we develop a Mixture-of-Transformer architecture that allows modality-specific processing while keeping global self-attention over both modalities. We train SimpleDesign on over 2M sequence-structure pairs achieving strong performance across co-design and unconditional sequence/structure generation benchmarks. --- ### Spruce: Scalable Private Outsourced Retrieval Using Compact Embeddings Authors: Peichun Hua, Yunming Xiao Published: 2026-09-03 Categories: cs.CR, cs.IR, cs.LG arXiv: https://arxiv.org/abs/2609.03376v1 Retrieval-Augmented Generation (RAG) has made dense retrieval over large document collections a standard building block. Organizations increasingly outsource vector indexes to untrusted clouds, exposing proprietary corpora and user queries. Cryptographic protection is challenging because each query searches corpus-scale state, causing computation, correlated randomness, and communication to grow with the corpus. At million-document scale, a naive secure implementation takes minutes and about 90 GB of communication per query. Even recent optimized systems require 10--22 seconds. We propose Spruce (Scalable Private Outsourced Retrieval Using Compact Embeddings), which co-designs representations with the cryptographic protocol. Spruce learns compact binary codes that preserve candidates for full-precision reranking, replacing corpus-wide embedding scoring with efficient Hamming-distance computation under two-server multi-party computation (MPC). A corpus-calibrated fixed-radius protocol avoids multi-round candidate selection while preserving retrieval quality. Spruce also provides private cluster pruning, which trades minor quality loss for substantially less computation, and a one-core owner-operated dealer that removes cloud OT preprocessing bottlenecks. Across four corpora containing 383K--5.42M documents, Spruce preserves the original search quality with median candidate sets of only 382--1,952. At 10 Gbps inter-server bandwidth, full scans take 0.21--2.97 seconds, $4.8$--$6.7\times$ faster than the closest measured prior work. Private pruning takes 0.06--1.09 seconds, achieves $13.1$--$22.9\times$ speedups, and retains $93.9\%$--$97.3\%$ of full-float NDCG. On the largest corpus, pruning and the dealer jointly improve sustained throughput by $31.5\times$ at 1 Gbps per link. --- ### FrameBench:A Language Understanding Benchmark Based on Frame Semantics Authors: Chihiro Yano, Ryohei Sasano Published: 2026-09-03 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.03370v1 In frame semantics, sentence comprehension is assumed to proceed by relating lexical meaning to background knowledge called semantic frames, thereby enabling readers to implicitly enrich the text with unstated information. Recent large language models (LLMs) have achieved strong performance across a wide range of downstream tasks. However, it remains unclear whether they can reproduce the kinds of implicit enrichment that humans naturally make during comprehension. To address this question, we introduce FrameBench, a benchmark grounded in frame semantics. FrameBench consists of multiple-choice questions that test whether models distinguish the frames evoked by the same verb across contexts. We construct the benchmark for English and Japanese using FrameNet-style resources and a generation-and-verification pipeline with native-speaker judgments. Our experiments on a diverse set of models reveal challenges for small models, while several large models surpass the human reference scores. We release the constructed FrameBench dataset and the code for dataset construction and evaluation at https://github.com/SasanoLab/FrameBench. --- ### Accountable AI with Grounded, Faithful, Consistent, Actionable Rationales: A Case Study in Clinical Trial Matching with VERDICT Authors: Zikai Zhou, Yufei Jin, Yilin Xu, Yu-Chiang Wang, Chieh-Ju Chao, Monica S. Lam Published: 2026-09-03 Categories: cs.CL, cs.CY, cs.LO arXiv: https://arxiv.org/abs/2609.03366v1 Accountability means a decision can be examined, justified, and contested. LLMs make this hard: fluent output may be ungrounded, incomplete, or unfaithful to the decision process. Achieving accountability requires verified rationales (how was the decision reached), assumptions (what was assumed rather than known), policy consistency (the same treatment for the same facts), and pivotal conditions (what would change the outcome). We introduce self-faithfulness as an automatic test of accountability: changing the pivotal conditions should change the decision. We examine accountable AI through clinical trial matching, a high-stakes task central to evidence-based medicine. Although LLM-based matchers match patients to trials reasonably accurately, they apply decision policies inconsistently and produce rationales that are unfaithful to their own decisions. We introduce VERDICT, an LLM-based agent that translates a decision task, its constraints, and its policy into Satisfiability Modulo Theories (SMT), then derives the decision with SMT and MaxSMT solvers -- so policies are applied consistently and decisions are accountable by construction. Across a SIGIR 2016-derived dataset and TREC 2021, VERDICT achieves the strongest decision accuracy among LLM-only and neurosymbolic baselines, applies policies with perfect consistency, and produces clinician-preferred rationales grounded in explicit assumptions and pivotal conditions, with improved counterfactual self-faithfulness. --- ### Grassmann--Plücker Parametrization of Convolutional Filter Subspaces: Regularity and Closed Embeddings Authors: Hongyu Yuan, Huaiqing Zuo Published: 2026-09-03 Categories: math.AG, cs.LG arXiv: https://arxiv.org/abs/2609.03361v1 We propose a geometric parametrization of the filters in a single convolutional layer: the parameter is no longer an ordered family of filter vectors, but a fixed-dimensional subspace of the filter space. For one-dimensional finite-stride convolution, the filter-to-convolution-operator correspondence gives an injective linear map $\mathcal{C}:\mathcal{K}\to H$. This map sends filter subspaces in $\mathrm{Gr}(q,\mathcal{K})$ to operator subspaces in $\mathrm{Gr}(q,H)$; composing it with the Plücker embedding yields a projective parametrization $Φ:\mathrm{Gr}(q,\mathcal{K})\to\mathbb{P}(\bigwedge^q H)$. Using $T_U\mathrm{Gr}(q,\mathcal{K})\cong\mathrm{Hom}(U,\mathcal{K}/U)$, we compute the differential of the induced Grassmannian map and show that the differential of $Φ$ is injective at every point. We then use the vanishing equations for Plücker coordinates and standard affine coordinates on a Grassmannian to prove that $\mathrm{Gr}(q,\mathcal{C}(\mathcal{K}))\hookrightarrow\mathrm{Gr}(q,H)$ is a closed embedding, and hence that $Φ$ is a closed embedding. Consequently, the parameter space is isomorphic to its projective image, the parametrization is finite and birational onto its image, every fiber is a singleton, and the resulting projective neural variety is smooth. For $k=4$ and $q=2$, we also use Singular to recover the image ideal and check its dimension, degree, chart rank, and smoothness. This computation illustrates, rather than replaces, the general proof. Finally, we discuss possible connections with filter redundancy and low-rank convolution, while distinguishing the proved geometric results from application proposals requiring numerical validation. --- ### Time Without Timesteps: Simulating Coupled Dynamical Systems via Self-Consistency Authors: Liyu Zerihun, Mark Shinyoung Lee Published: 2026-09-03 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.03358v1 Numerical simulation of dynamical systems is usually organized as a causal march through time: each state is computed from the previous one. We explore a different formulation for coupled systems. For each subsystem type we train a neural surrogate mapping a full driving trajectory and initial condition directly to a full output trajectory; following classical waveform relaxation, coupled systems are assembled by enforcing self-consistency among these trajectories: simulation becomes a fixed-point problem over complete trajectories rather than a stepwise rollout. On coupled van der Pol oscillators and Hodgkin-Huxley neuron networks, sequential depth becomes the number of solver iterations: 4-10 Newton iterations where the reference integrator takes 1500 steps. The gradient likewise loses its time recursion: it becomes a linear system solved by GMRES at memory independent of solver depth. A single scalar measured from the learned operator, the spectral radius of its Jacobian, predicts in advance where the coupled solve will converge; past that boundary, unrolled backpropagation diverges and a Neumann adjoint fails, while the implicit gradient remains correct to 0.04%. We report where the approach succeeds and where surrogate error degrades it. --- ### ALRA: Adaptive Local Relational Alignment for Logit-Based Pre-training Distillation of Autoregressive Language Models Authors: Quang Hoang Trung, Quang Huu Hieu, Nguyen Van Hoang Phuc, Vo Nguyen Le Duy Published: 2026-09-03 Categories: stat.ML, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2609.03355v1 Logit-based knowledge distillation for autoregressive language models usually aligns teacher and student next-token distributions over the entire vocabulary. However, this global objective overlooks relative preferences among likely token alternatives. Existing local approaches often select candidate tokens from either the teacher or the student alone. Teacher-only selection can miss tokens that the student considers likely, while student-only selection can rely on an inaccurate ranking early in training. We propose Adaptive Local Relational Alignment (ALRA), a position-specific framework combining student proposals with teacher guidance. At each valid prediction position, the student proposes likely tokens, while the teacher's most probable token is included as an anchor. ALRA adjusts the number of selected tokens according to how broadly the teacher distributes probability within this candidate set relative to the current batch. Adaptive Local Divergence retains the mass-matching term and separately matches the relative token distributions within the selected and remaining vocabulary regions. Unlike the exact full-vocabulary decomposition, it replaces the teacher-mass coefficients of the two conditional terms with unit coefficients, preventing either term from being downweighted solely because its region has low teacher probability. Student-Weighted Pairwise Relational Alignment emphasizes high-probability token pairs with small student probability gaps and gives less weight to unlikely or clearly separated pairs. Experiments on The Pile with randomly initialized 200M- and 500M-parameter students across nine zero-shot benchmarks yield average accuracies of 36.62% and 37.40%. ALRA exceeds the strongest competing distillation baseline by 0.94 and 0.83 percentage points and improves over pre-training without distillation by 2.31 and 2.91 points, respectively. --- ### Efficient Constant Optimization for Symbolic Regression with GPU-Accelerated Tree-Based Genetic Programming Authors: Hao Mao, Xu Tony Liu, Shuai Lu, Peng Zhao, Wenzheng Jiang, Yuntian Chen Published: 2026-09-03 Categories: cs.NE, cs.DC, cs.LG, cs.MS arXiv: https://arxiv.org/abs/2609.03352v1 Constant optimization refines the numerical coefficients of candidate expressions in tree-based genetic programming for symbolic regression. But its per-generation cost has led modern GPU-accelerated frameworks to omit it or restrict it to lightweight forms. We present a GPU-resident, batched Levenberg--Marquardt solver that optimizes constants across a structurally heterogeneous population of expression trees using a fixed number of population-wide CUDA launches per iteration. Reverse-mode automatic differentiation assembles the per-tree Jacobian in one backward sweep, making the dominant per-iteration cost independent of the number of constants per tree, and a double-precision delivery guard guarantees that returned constants are never worse than their initial values. On early-generation populations, the solver sustains up to $5.1{\times}10^{5}$ trees per second on an NVIDIA A100; at a GPU-saturated benchmark configuration it delivers roughly $9.9{\times}$ the throughput of Operon running on a 64-core EPYC 7763, while matching fp64-reference quality. Integrated in-process into EvoGP, the solver enables end-to-end search to recover governing equations on $10$ of $18$ constructed problems versus 0 for stock EvoGP. Our code is at https://github.com/TensorConv/CuSR. --- ### From Zero to Hero: An Open LLM Ecosystem for Armenian Authors: Erik Arakelyan, Khatun Avetisyan, Meri Davtyan, Heghine Grigoryan, Nane Khachatryan, Hayk Shahsuvaryan, Henrik Sergoyan, Vahan Martirosyan Published: 2026-09-03 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2609.03350v1 Pretraining data for Armenian, a morphologically rich and low-resource language, is scarce, and no open Armenian LLM has been released with the data and recipe needed to reproduce it. To address this gap, we curate and release two datasets. ArmWeb is an extensively validated corpus of 4.37M Armenian news documents. ArmSTEM is a parallel English-Armenian collection of 373K math and science problems with step-by-step solutions, translated into Armenian and verified through both answer-preserving LLM judgment and human evaluation. Continued pretraining of Gemma-4-E4B on these datasets yields arm-gemma-e4b, which outperforms every existing open Armenian model as well as its unadapted base, and is the first open Armenian LLM with complete training data and recipe. Our ablations show that news-only continued pretraining improves fluency while eroding knowledge, a pattern we also observe in existing Armenian models, and that a small share of verified translated STEM data reverses the loss. We further find that the largest public Armenian corpora overlap web-derived evaluation panels heavily, including a train/test self-overlap inside FineWeb-2. We openly release all data, models, and code. --- ### P-CORE: Self-Supervised Surface Consistency for Point-Based Neural Editing Authors: Yanshu Zhang, Shichong Peng, Mehran Aghabozorgi, Alireza Moazeni, Ke Li Published: 2026-09-03 Categories: cs.CV, cs.GR arXiv: https://arxiv.org/abs/2609.03349v1 Advances in neural rendering have enabled high-fidelity multi-view reconstruction of 3D scenes. However, free-form non-rigid shape editing remains a significant challenge. Point-based neural representations are highly desirable for multi-view reconstruction because they lack fixed connectivity, which does not constrain the learned surface topology to that of the initialization. Yet this same property causes point-based representations to struggle with holes and surface discontinuities under large deformations. To address this, we propose a novel self-supervised method to enable point-based representations to adapt to large deformations without requiring ground truth multi-view images of deformed geometry. The key idea is to generate random deformations and to ensure consistency in the predicted surface before and after deformation. In particular, the surface prediction from the deformed point cloud should be the same as the deformation applied to the surface prediction from the original point cloud. We incorporate our approach into attention-based point representations, which differ from splatting-based point representations in their use of a learned interpolation kernel between points as opposed to a Gaussian kernel around each point. This learned interpolation kernel can learn to adapt to large deformations, without requiring addition or removal of points. We show that our framework significantly enhances its robustness to large deformations. Experiments on synthetic geometry editing benchmarks (Neural Editor, Objaverse) demonstrate that our approach outperforms existing point-based methods in zero-shot editing and significantly reduces artifacts. Furthermore, qualitative results on the DTU and Mip-NeRF 360 datasets demonstrate our method's effectiveness on real-world scenes. --- ### Learning Informative Prior with Infinite-Dimensional Continuous Normalizing Flow for Bayesian Inverse Problem Authors: Yang Zhao, Junxiong Jia, Tao Zhou Published: 2026-09-03 Categories: math.NA, cs.LG arXiv: https://arxiv.org/abs/2609.03343v2 This paper addresses infinite-dimensional Bayesian inference for inverse problem of partial differential equations with model parameters in infinite-dimensional Hilbert space. To effectively incorporate prior information, we propose a novel continuous normalizing flows based infinite-dimensional model. Specifically, by introducing a well-defined neural ordinary differential equation in infinite-dimensional space, a simple reference measure can be transformed into a more complex measure which encodes the prior information. A corresponding theoretical framework is established to ensure the well-posedness of our proposed Bayesian prior in infinite-dimensional space. We also provide training methods of the prior for two distinct data settings, along with two sampling algorithms for the resulting Bayesian posterior. The proposed framework is applied to three representative inverse problems: the simple smooth inverse problem, inverse scattering problem, and the inverse heat conduction problem. Numerical experiments support the theoretical analysis and demonstrate the efficiency of the proposed algorithms. --- ### Gradients Know What Outcomes Don't: Unlocking Reinforcement Learning for LLM Reasoning with Gradient-Aligned Rewards Authors: Leqi Zheng, Jinbo Su, Fang Niu, Chaokun Wang, Weiping Wang, Jiajun Zhang, Shannan Yan, Jie Wu, Zhaolu Kang, Rong Fu, Hang Zhang Published: 2026-09-03 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.03342v1 Reinforcement learning from verifiable rewards (RLVR) drives chain-of-thought reasoning in large language models, yet its binary outcome reward cannot distinguish among correct trajectories. Existing dense reward alternatives, from surface heuristics to process reward models, either ignore the expert solutions already present in training corpora or require expensive offline annotation. We propose Gradient-Aligned Reward (GAR), which operates in the policy's own gradient space: truncated backpropagation through the output projection layer extracts a compact gradient vector for each rollout, and cosine similarity with an expert-anchor gradient yields a dense, reasoning-aware reward with less than 9% wall-clock overhead. We prove that this cosine admits a multiplicative decomposition into prediction-error and activation-pattern factors, providing a concrete characterization of what the alignment signal measures. On Qwen3-4B and Qwen3-8B, GAR consistently improves over GRPO and other baselines on competition-level math benchmarks and transfers to GPQA Diamond and MMLU-Pro without domain-specific data. Code and data are available at https://github.com/LQgdwind/GAR. --- ### PointGT: Simultaneous Geometry and Texture Editing for Point-Based Representations Authors: Yanshu Zhang, George Shramko, Pratul P. Srinivasan, Ke Li Published: 2026-09-03 Categories: cs.CV, cs.GR arXiv: https://arxiv.org/abs/2609.03341v1 We present PointGT, a point-based 3D representation that enables simultaneous editing of object geometry and appearance. Existing reconstruction and view synthesis techniques produce volumetric 3D representations that are high-quality and photorealistic, but are difficult to edit. In particular, recent efforts to enable texture editing for 3D Gaussian Splatting representations are not compatible with geometry edits and deformations. Our method combines a point-based representation that is well-suited for geometry deformations with a learned UV mapping technique that enables high-resolution texture editing. We show that PointGT enables fine-grained editing of both geometry and texture in point-based neural representations with high rendering quality. --- ### Fresh Memory, Stale Plans: Derivation Currency for Distributed LLM-Agent Memory Authors: Evan Chen, Shiqiang Wang, Christopher G. Brinton Published: 2026-09-03 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.03340v2 A large language model (LLM) agent that inherits a plan through shared memory can hold the latest requirement yet act on a plan derived from an older one: fresh memory, stale plan. Freshness checks miss this failure because they compare local copies with current state (observation currency) rather than the inputs the plan was derived from (derivation currency). Planfence makes derivation currency checkable after a handoff. Stored plans carry exact links to their recorded inputs; before a protected action, Planfence follows those links to an action-specific dependency frontier, asks each input's owner for its current head, refreshes what changed, and allows one replan before blocking. Application code supplies the links and declares the scope; no shared memory service is required. Holding the native S-Bus validator fixed, supplying inherited input versions raises detected handoff conflicts from 0/30 to 30/30: retained evidence is the missing ingredient. In 30 live five-agent workflows with a revision inserted after planning, a freshness-only executor acts on the stale plan every time, whereas Planfence, like a centralized-lineage baseline that requires a shared store, completes all 30 correctly. In matched replay under emulated LTE traces, Planfence's stall stays within 143-237ms per action across a 64$\times$ range of update rates while per-update synchronization grows from 52 to 1196ms; synchronization is cheaper only at the lowest tested rates. Scoping queries to the declared dependencies holds traffic at 8.1KiB per action, a tenth of all-key validation at 128 keys; at full scope the two tie. --- ### A Large Open Multi-Energy Corpus of Soil Compaction Tests, with Machine-Learning Baselines Authors: Sompote Youwai, Chana Phutthananon, Warat Kongkitkul Published: 2026-09-03 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.03337v1 Every engineered fill is specified by a maximum dry density and an optimum moisture content. Each determination needs a full Proctor test. Published correlations rest on one to four hundred specimens, usually from one laboratory at one compactive energy, and are seldom released. This paper releases a corpus without those limits. It holds 2,854 laboratory compaction tests from six public sources, across 162 provenance groups and four Proctor energy levels, with fines from 1.5 to 100%. Every record is audited to the Proctor method its source names, and no energy is inferred. Screening on the zero-air-voids condition removed 11.8% of harmonised records, and 5.7% of those with a measured specific gravity. A material share of published compaction data is physically impossible. The optimum degree of saturation over the corpus is 0.815 at a coefficient of variation of 11%. That is a baseline, not a constant. Both parameters are then estimated from one classification suite and the compaction standard. A tabular foundation model reaches R2 0.824 for density and 0.784 for water content under random folds. It reaches 0.727 and 0.696 with folds drawn around provenance, and 0.520 and 0.614 with a whole source held out. Compactive energy is negligible marginally yet decisive conditionally. Density on the 66 modified-Proctor records is predicted at R2 0.740 with it and -0.651 without. Symbolic regression yields closed forms coupled through a phase relation. No predicted pair can then exceed the zero-air-voids line. The predictions are for screening, not acceptance. --- ### Laplacian Frequency Hierarchies for Efficient 3D Gaussian Splatting Training Authors: Yixiong Yang, Sisheng Zhang, Qingsong Yan, Shaohuai Shi, Qiang Wang Published: 2026-09-03 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.03334v1 A key bottleneck in 3D Gaussian Splatting training is the continual growth of Gaussian primitives, which increases optimization cost and slows convergence, especially at high resolutions. We propose Laplacian Frequency Hierarchies, a simple yet efficient 3DGS scheme that combines Laplacian image decomposition with coarse-to-fine, frequency-staged training. After fitting lower-frequency structure, we archive the corresponding Gaussian field so that subsequent fields can optimize higher-frequency residuals without carrying the full primitive burden, and we compose the rendered components in the image domain via a Laplacian-style reconstruction at inference time. This design reduces the number of active Gaussians during training, thereby lowering optimization overhead and accelerating training. The proposed scheme is plug-and-play and orthogonal to prior 3DGS accelerations: it can be directly combined with strong backbones such as Taming-3DGS and FastGS to improve training speed with competitive reconstruction quality. It achieves average speedups of 1.73x and 1.21x at 1K setting, and 1.74x and 1.33x at 4K setting on Taming-3DGS and FastGS, with larger gains on more challenging scenes and increasingly pronounced benefits at higher resolutions. --- ### FPCO-Dialog: A Multi-Turn False-Premise Benchmark for Correction and Cooperation in Vision-Language Models Authors: Jiayuan Ma, Yuqi Lu, Weiyang Guo, Chenrui Wang, Junyi Shu, Xuebo Liu, Min Zhang, Jing Li Published: 2026-09-03 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.03331v1 Vision-language models (VLMs) are increasingly deployed in multi-turn settings where users may describe visual content with incorrect assumptions. Yet existing evaluations rarely isolate how models respond when the same visually grounded false premise persists across dialogue turns. We introduce FPCO-Dialog, a benchmark for evaluating correction and cooperation behavior in VLMs under repeated false premises. FPCO-Dialog contains 1,080 images and 10,800 question turns, stratified by visual complexity, object category, and false-premise class, and uses a 10-turn protocol in which a correct dialogue prefix is followed by repeated false-premise referring expressions. We evaluate 20 commercial and open-source VLMs with a model-agnostic protocol and CorrTP@K, a correction-rate metric over false-premise turns, scored by two independent detectors. FPCO-Dialog reveals substantial and persistent cross-model differences in aggregate correction tendency, model-specific turn-wise dynamics, and systematic variation across false-premise types under the benchmark's substitution distribution. The dataset, evaluation protocol, model outputs, detector labels, and code are available. --- ### Less Is Moral: A CHARMing Framework for Moral Foundations Detection in Endorsement Behaviour Authors: Huixiang Fu, Marian-Andrei Rizoiu Published: 2026-09-03 Categories: cs.CL, cs.CY, cs.SI arXiv: https://arxiv.org/abs/2609.03330v2 Moral language plays a central role in shaping online endorsement and the diffusion of information, yet existing moral foundation detection systems often suffer from poor cross-domain generalization, weak rationale grounding, and reliance on costly prompting-based large language models (LLMs). We introduce CHARM, a MAC- and Hate-speech-Aware Rationalealigned Moral foundation detection framework built on a lightweight fine-tuned LLM, which integrates complementary moral grounding, rationale alignment, and polarity-aware hate speech signals to support more robust and faithful moral prediction. Unlike prior dictionary-, fine-tune-, or prompt-based detectors, which decouple computation from psychological theory, CHARM is built so that each component -- MAC cross-attention, rationale alignment, and hate-speech modulation -- operationalizes a distinct psychological construct. Using a 30\% subsample of the MFTC, MFRC, and News training pools together with the richer supervision in MFTCXplain, CHARM improves AUC by up to 15.3\% in-domain, surpasses the supervised baselines on every out-of-domain dataset in both AUC and F1, and offers a scalable, low-cost alternative to prompting-based LLM detectors. We further apply CHARM to large-scale COVID-19 discourse on Twitter and show that moral value alignment is strongly associated with online endorsement behavior. By making moral framing measurable at scale, CHARM offers a practical tool for studying the spread of morally charged misinformation. Code and additional materials: https://github.com/HuixiangF/CHARM/. --- ### Introducing SINFONIA: Symplectic, slimplectic and Magnusian (Neural) Flows for Orbital Numerical Integration and Acceleration Authors: Lidia J. Gomes Da Silva Published: 2026-09-03 Categories: gr-qc, astro-ph.HE, astro-ph.IM, cs.LG, physics.comp-ph arXiv: https://arxiv.org/abs/2609.03329v1 Long-duration gravitational-wave modelling must resolve fast orbital motion together with slow dissipative evolution while preventing small numerical errors from accumulating into secular phase drift. Here we ask whether the finite-time evolution map itself can be learned as an explicit, differentiable, structure-preserving object and then repeatedly composed through a complete inspiral. We construct three neural-flow architectures: a symplectic and slimplectic flow on Galley's doubled phase space, (SINFONIA-J0); a Taylor-anchored flow, (SINFONIA-J1); and a Magnusian flow that learns the finite-time dissipative correction in the interaction picture, (SINFONIA-J2). Applied to a 2.5PN neutron-star inspiral, all three expose the same controlling mechanism: long-time accuracy is governed not by pointwise map error alone, but by its signed projection onto a single secular channel fixed by energy--angular-momentum balance. Encoding this structure allows the learned maps to remain accurate through $10^{2}$--$10^{5}$ window compositions to coalescence at timesteps of a full orbital period and beyond, reaching chained phase errors orders of magnitude below a benchmark slimplectic integrator at lower cost. The same secular structure can also be exploited for physics inference: when the channel is left unconstrained, the accumulated phase retains enough information to recover an un-modelled dynamical-friction-like force, both parametrically and as a learned function of separation. Network-off controls isolate the contribution of learning from the analytic structure already built into each map. These results establish a proof of concept for structure-preserving learned evolution maps as tools for fast long-duration integration and physics inference in gravitational-wave source modelling. --- ### DE-Venus: A Data-Efficient RLVR Framework for Large Language Models Authors: Shenzhi Yang, Guangcheng Zhu, Kai Tang, Zhengqing Zang, Xing Zheng, Haobo Wang, Yingfan Ma, Bowen Song, Bo Han, Bo An, Lei Feng, Weiqiang Wang et al. Published: 2026-09-03 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.03324v1 Reinforcement learning with verifiable rewards (RLVR) improves large language model reasoning, but its practical scaling is constrained by expensive on-policy rollouts and the cost of obtaining reliable targets at scale. Existing methods address sample selection, incomplete supervision, or noisy labels separately, often entangling supervision logic with distributed training and hindering controlled comparison and reuse. We present DE-Venus, a unified framework for data-efficient RLVR that treats supervision as evolving state across data preparation and policy optimization. It organizes this lifecycle into three modules: Active Data Selection allocates training and annotation budgets; Weak Supervision Construction derives learning signals from unlabeled examples; and Training-Time Supervision Refinement filters or corrects unreliable supervision. DE-Venus supports seven representative methods and a data-selection pipeline by expressing method-specific decisions as offline dataset transitions or online transformations of targets, rewards, batches, and advantages while preserving verl's distributed execution contracts. Across public benchmarks and three business scenarios, separate configurations preserve or improve model quality with only 10% of labels or as little as 13% of relevant data; selected business configurations also reduce observed convergence steps by 63%--75%. DE-Venus thus reduces annotation and training costs without sacrificing scalable RL execution. --- ### How Perturbations Propagate: A Multi-Level Analysis of Robustness in Large Language Models Authors: Dun Li Chan, Emily Liu, Niyathi Allu, Christian Hoang Published: 2026-09-03 Categories: cs.CL, stat.ML arXiv: https://arxiv.org/abs/2609.03322v1 Language models encounter typos, corrupted text, altered words, and disrupted token order, yet robustness is usually evaluated only through output behavior. We study how six naturalistic and synthetic input perturbations propagate through decoder-only language models at three levels: output behavior, hidden-state geometry, and attention-head function. We evaluate behavioral effects across four GPT-2 and two Qwen2.5 checkpoints by analyzing layerwise geometry using centered kernel alignment and intrinsic dimension, and examine attention-head responses in GPT-2. Perturbation types produce distinguishable metric profiles that are not fully captured by output measures and are only partly consistent across the tested checkpoints. Copying scores are especially associated with activation-patching recovery under token substitution and shuffling. Gradient-guided HotFlip perturbations also cause stronger behavioral and representational disruption than rate-matched random token substitutions in GPT-2; their behavioral effects are consistent across all six tested checkpoints. Our results show that robustness claims based on a single behavioral or representational metric can be misleading, and motivate multi-level evaluation of how perturbations alter language-model computation. --- ### Decoupling Turn-Taking from Semantics: A Decoupled Data Approach for Finite-State-Machine-Based Full-Duplex Dialogue Authors: Yihang Li, Chenhui Chu Published: 2026-09-03 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.03321v1 The Neural Finite State Machine (NFSM) framework offers a pragmatic path to full-duplex dialogue by serializing turn-taking control and response generation onto a single causal tape under the standard next-token prediction objective, thereby preserving semantic prowess at a low fine-tuning cost. However, its reliance on synthetic text data fundamentally limits turn-taking naturalness, as Large Language Models (LLMs) cannot faithfully simulate the fine-grained acoustic temporal dynamics of real human dialogues. In this work, we propose a decoupled data approach that learns turn-taking from real Human-Human (HH) spoken dialogues while shaping semantic behavior through configurable Human-Agent (HA) text dialogues. To operationalize this approach, we introduce a rule-based event-guided data transformation method that serializes HH spoken dialogues into FSM tapes by classifying turn-taking events and applying deterministic mapping rules, enabling scalable supervision without LLM-generated annotations. We further propose a Source-Aware Calibrated (SAC) Loss that jointly calibrates the long-tailed distribution of state transition tokens and channels each data source toward the capability it best supervises. Experiments show that our approach substantially improves turn-taking proficiency while recovering the foundation LLM's semantic capability. Our code and model are available at https://github.com/Liyht/def-fsm. --- ### Beyond .WAV: Design and Software Verification of VocalCap, a Traceable Browser-Based Audio Capture System for Vocal Biomarker Research Authors: Augusto Camargo Published: 2026-09-03 Categories: cs.SD, cs.LG arXiv: https://arxiv.org/abs/2609.03320v1 Remote voice studies often retain a final audio file with limited evidence about how it was captured, transferred, processed, and accepted. This paper presents VocalCap, an institution-controlled, browser-based system for self-guided capture of voice and related acoustic signals by participants without technical training. A versioned protocol drives the workflow. Each accepted recording retains a browser-native object, a client-lossless Float32 WAV derived from the same MediaStream, and a server-canonical mono PCM16 WAV, linked to evidence of capture execution, technical quality, byte-level integrity, recovery, and transformation provenance. IndexedDB preserves accepted browser artifacts until server confirmation, while session completion requires successful verification of every task and artifact. Software tests challenged the acquisition contracts with malformed or altered objects, exact-zero interruptions, channel-topology variants, and interrupted or repeated operations. A post hoc technical audit of 39 consented pilot recordings found 25 sample-identical stereo files and 14 files with signal confined to the left channel. Topology-aware active-channel selection limited the canonical root-mean-square level difference to less than 0.001 dB in all 14 affected files; equal-weight stereo averaging would have introduced approximately 6.02 dB of attenuation. Production end-to-end verification completed two five-task profiles in Chromium and WebKit, yielding 10 accepted recordings and 30 retained artifacts that passed server-side integrity and format checks. The results verify VocalCap's software behavior under the tested browser-engine conditions. Device-level acoustic agreement, target-population usability, clinical validity, and biomarker performance remain subjects for separate studies. --- ### Risk and Anomaly Identification for Distribution Network Optimal Operation Based on Reinforcement Learning and Uncertainty Quantification Authors: Ziqi Zhang Published: 2026-09-03 Categories: cs.LG, cs.MA, eess.SY arXiv: https://arxiv.org/abs/2609.03308v1 Reliable operation of modern distribution networks requires timely identification of operational risks and anomalous events under pervasive uncertainty. In practice, operators must identify risks that are inherent in stochastic yet in-distribution conditions, and anomalies that correspond to out-of-distribution behaviors such as unusual load patterns, extreme weather or cyber-physical attacks. This paper addresses this joint risk and anomaly identification problem for optimal distribution network operation and proposes a deep reinforcement learning framework that is explicitly uncertainty aware. We integrate distributional and Bayesian deep reinforcement learning to realize a second- order uncertainty quantification scheme that decomposes total uncertainty into aleatoric and epistemic components, which are respectively used to characterize inherent risk and out-of- distribution anomalies. The resulting epistemic estimates drive both exploration during training and out-of-distribution detec- tion with fallback control during deployment, whereas aleatoric estimates are used to characterize intrinsic operational risk. Simulation results demonstrate the performance of our DRL agent and the effectiveness of the uncertainty quantification. --- ### Geometry-Aware Graph Construction via Adaptive Spectral Bandwidth Control Authors: Ecem Bozkurt, Antonio Ortega Published: 2026-09-03 Categories: cs.LG, eess.SP arXiv: https://arxiv.org/abs/2609.03306v1 Kernelized graph methods - spectral clustering, diffusion maps, and sparse kernel -regression graphs - that use Gaussian kernels depend on the choice of Gaussian bandwidth sigma, which governs the spectral character of the local kernel operator. When sigma is too small, the kernel overestimates local complexity and treats each sample as an independent direction; when sigma is too large, the kernel collapses multiple directions together, the condition number diverges, and all geometric discrimination is lost. We propose a choice of scale to make the spectral complexity of the kernel consistent with the intrinsic complexity of the underlying manifold. We propose a per-node bandwidth criterion that operationalizes this principle by jointly matching the kernel's effective rank to the local intrinsic dimension estimated via minimum spanning tree, anchoring the search in the manifold-consistent log-log scaling regime. We evaluate SSL embeddings from six encoders on CIFAR-100, showing that adaptive bandwidth consistently improves leave-one-out (LOO) classification and label propagation (LP) accuracy over fixed-bandwidth methods and competing adaptive methods. --- ### Tensor-based Brain Surface Modeling and Analysis Authors: Moo K. Chung, Keith J. Worsley, Steve Robbins, Alan C. Evans Published: 2026-09-03 Categories: cs.CV, q-bio.NC arXiv: https://arxiv.org/abs/2609.03302v1 We present a unified computational approach to tensor-based morphometry in detecting the brain surface shape differences between two clinical groups based on magnetic resonance images. Our approach is novel in a sense that we combined surface modeling, surface data smoothing and statistical analysis in a coherent unified mathematical framework. The cerebral cortex has the topology of a 2D highly convoluted sheet. Between two different clinical groups, the local surface area and curvature of the cortex may differ. It is highly likely that such surface shape differences are not uniform over the whole cortex. By computing how such surface metrics differ, the regions of the most rapid structural differences can be localized. To increase the signal to noise ratio, diffusion smoothing based on the explicit estimation of Laplace-Beltrami operator has been developed and applied to the surface metrics. As an illustration, we demonstrate how this new tensor-based surface morphometry can be applied in localizing the cortical regions of the gray matter tissue growth and loss in the brain images longitudinally collected in the group of children. --- ### Multilingual Agent System for Inclusive Wildfire Evacuation Guidance Authors: Shruti Kulkarni, Lynn Tong, Aditi Namboodiripad, Chelyah Miller, Helen Lin, Peeyush Patel, Bogdan Bistriceanu, Diane Myung-kyung Woodbridge Published: 2026-09-03 Categories: cs.CY, cs.AI arXiv: https://arxiv.org/abs/2609.03301v1 Wildfire seasons have become 84 days longer in the current days than in the 1970s, causing enormous threats to one's financial status and short- and long-term health. During the fire, public agencies send out emergency messages to provide warnings and orders. Although 26 million people in the US have limited English proficiency, over 80% of those messages are only delivered in English, which can cause disproportionate information distribution and awareness. In order to better serve marginalized communities during emergencies, the authors developed BEACON, a service that provides comprehensive and personalized evacuation guidance, including navigation routes, personalized checklists, and a chatbot in the language that a user uses. Our current system ingests data including fire perimeter information, evacuation order status, and shelter information from Watch Duty. When a user is within a certain proximity from the fire, the system utilizes real-time GPS locations and nearby weather data from the National Oceanic and Atmospheric Administration (NOAA) to predict fire danger levels. The assessment model refreshment are dynamically scheduled based on fire progress and trends using XGBoost. If the location has a likelihood of fire danger, the system sends alerts with evacuation routes outputted from a polygon-avoidant routing pipeline. The application provides a context-aware multilingual agent that users can communicate with and is tightly connected to other features of the application. In addition, based on data that the user entered, the system dynamically generates and checks off personalized reminder items to provide an organized evacuation plan. The system's user interface dynamically changes its language settings based on the language the user most recently used in either setting or chatbot conversation for all the application elements. --- ### Latent Energy Action Planning with World Models Authors: Phu Pham, Aniket Bera Published: 2026-09-03 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.03294v1 Latent world models support efficient model predictive control from high-dimensional observations, yet optimizing a single learned latent objective can favor action sequences whose decoder-predicted terminal descriptor does not match the goal descriptor. We introduce Latent Energy Action Planning (LEAP), which treats the complete action horizon as a differentiable variable and optimizes it through a frozen LeWorldModel (LeWM). LEAP couples terminal latent goal matching with a terminal-window state energy. Low energy requires the predicted terminal latent to agree with the goal latent and the decoder-predicted terminal descriptor to agree with the goal descriptor. A frozen goal-conditioned proposal initializes the search, a quasi-Newton solver refines actions through the autoregressive rollout, and post-optimization projection enforces the admissible action range. Across four control domains using the officially released LeWM checkpoints, the complete LEAP planning system raises mean success from 77.5% for LeWM planned with the cross-entropy method (LeWM+CEM) to 94.8% under a matched protocol, a 17.3-percentage-point improvement, while retaining the frozen LeWM representation and predictor. --- ### PACE: Towards Surfacing Hidden Conflicts in User Requests Authors: Yoojin Kim, Jihyoung Jang, Hyounghun Kim Published: 2026-09-03 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.03293v1 Personalized assistants should not only comply with user requests but also assess whether those requests are appropriate given the user's current circumstances. However, prior work has primarily focused on accurately executing requests, overlooking the need for assistants to account for context and engage in conflict-based refusal. Furthermore, while existing work on conflict or safety detection relies on explicitly provided factors, real-world scenarios often involve implicit factors that must be retrieved from a knowledge base (KB). To this end, we introduce Personalized Assistants for Conflict Evaluation (PACE), a dataset for evaluating whether models can identify latent constraints, expressed as egocentric knowledge or events, that render seemingly reasonable user requests inappropriate. PACE pairs user requests grounded in well-defined personas with egocentric KB facts, requiring models to integrate contextual evidence to determine whether a request is conflicting. This implicit retrieval setting hinders the direct association between user requests and conflict-inducing knowledge, making it difficult for existing models to identify relevant user-specific facts. To address this challenge, we further propose PaceMaker, a multi-agent framework in which specialized agents coordinate across query reformulation, multi-hop graph traversal, and conflict-aware filtering to retrieve contextually decisive evidence. Experiments on PACE evaluate both evidence retrieval quality and conflict decision accuracy, showing that PaceMaker consistently outperforms existing approaches. --- ### Contextual Tamil Spelling and Grammar Correction Using Progressively Fine-Tuned Sequence-to-Sequence Transformers Authors: Karthikeyan A, Jaya Nirmala S, Sangeetha Sivanesan, Indhu R, Pranav Kumar, Bharat Jude Johnson, Vishnu Ram Published: 2026-09-03 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.03273v1 Tamil spell and grammar correction is challenging because Tamil is an agglutinative low-resource language with rich verbal morphology, complex sandhi (phonetic transformation) rules at word boundaries, and a script of 247 distinct letters. Prior work targets word-level surface errors with rule-based methods, statistical n-gram models, Minimum Edit Distance, or hybrid pipelines with a transformer re-ranker; such methods cannot reliably handle contextual errors - subject-verb agreement, tense consistency, or cross-word sandhi - which require sentence-level understanding. We propose an end-to-end sequence-to-sequence formulation and fine-tune mT5-small and mBART-50 on a synthetic corpus of up to 657,720 noisy-clean Tamil sentence pairs spanning ten error categories. Both backbones follow the same four-stage progressive schedule, each stage targeting one weakness: surface noise (v2), contextual grammar (v3), single-site sandhi (v4), and multi-site cross-word sandhi (v5). On a 1,000-sentence balanced diagnostic set verified disjoint from all training data, our best model, mBART-50 v5, reaches 69.3% top-1 exact-match accuracy, with 87.5% on sandhi and 43.5% on subject-verb agreement. The schedule is what produces these gains: subject-verb accuracy rises from 1.0% to 52.5% once contextual pairs are introduced, and sandhi from 0% to 87.5% once multi-site sandhi pairs are. We additionally quantify a precision-recall trade-off this literature has not reported: sandhi recall is paid for monotonically in identity accuracy. Finally, Tamil-LLaMA-7B-Instruct reaches 19.0% zero-shot and 24.7% with three demonstrations against a 20.0% copy baseline, showing that a Tamil-adapted instruction model does not transfer to specialised sentence-level correction without task-specific supervision. --- ### Selective Hypergraph Refinement for Frozen Graph Clustering Authors: Zimo Si Published: 2026-09-03 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.03265v1 Existing graph-clustering methods typically improve clustering performance by optimizing model parameters and node representations. Effective means of further improving the clustering results of an already trained and frozen model, however, remain limited. We study post-processing for frozen graph clustering. After checkpoint fixation, the procedure uses no labels and updates neither model parameters, node representations, nor the original graph structure. Instead, it exploits an attribute hypergraph to supplement higher-order relations that ordinary graphs cannot readily express, thereby refining existing cluster assignments. Because global hypergraph refinement can yield both performance gains and erroneous updates, we propose Selective Hypergraph Refinement (SHR). The method generates candidate residual directions from the hypergraph and evaluates their reliability using graph structure, node attributes, and matched-null evidence. It updates only nodes with sufficient support and otherwise retains their original assignments. Further analysis shows that whether a node changes cluster is jointly governed by its native assignment gap and the directional strength of the refinement. In a controlled common-suite evaluation, 13 of 15 backbone-dataset cells had a positive mean macro gain, one produced exact no-action, and one was negative. The cell-equal macro gain was 0.066 pp (95% bootstrap CI, (0.030, 0.107) pp), while only 0.209% of hard assignments changed on average. A broader 15-combination native-interface evaluation yielded a macro gain of 0.137 pp at a mean change ratio of 0.375%. These results indicate that frozen clustering outputs retain a limited but measurable refinement space after training. The effect is heterogeneous across backbone-dataset pairs, and broader coverage also increases exposure to negative transfer. --- ### MedQA-MM: Shortcuts Behind Medical Visual Reasoning Authors: Benlu Wang, Yifan Zhang, Jiaqing Yu, Chin Siang Ong, Juncheng Huang, Zhuohao Li, Zhenyu Zhang, Arman Cohan, Hong Yu, Zonghai Yao Published: 2026-09-03 Categories: cs.CV, cs.CL arXiv: https://arxiv.org/abs/2609.03261v2 A benchmark score credits final answers, but not the route by which an item can be answered. In medical multimodal multiple-choice questions (MCQs), this distinction matters because a correct answer can be supported by the intended image finding or by benchmark-preserved cues in the wording of answers, non-visual clinical text, visible image text, artificial annotations, or device/context artifacts. We call the resulting score-level overinterpretation reasoning inflation. Here, a route is an observable input path that can support answer selection, not a claim about the model's hidden cognition. Across six medical multimodal MCQ datasets, we separate candidate cues from behavioral evidence through prompt- and image-side audits, modality ablations, and matched repairs that preserve the medical target and answer key. In a 13-configuration open-model panel, full-input accuracy is 62.63%, while text-only and options-only settings achieve 53.96% and 29.71%, respectively. Removing length-gap, absolute/conspicuous, and spatial/prepositional cues lowers accuracy by 6.58, 3.50, and 4.77 percentage points. We also construct MedQA-MM, a 1,000-item shortcut-mitigated subset, where text-only and options-only accuracy fall to 5.21% and 12.33%. This does not imply that models never use images; it shows that medical image-reasoning claims require route-level evidence. --- ### An Ensemble-Based Self-Taught Learning Approach for Parking Space Classification Under Limited Data Authors: Lucas de Oliveira Cunha, Joelton Deonei Gotz, Paulo Lisboa de Almeida, Andre Gustavo Hochuli Published: 2026-09-03 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.03258v1 Parking spot classification is a fundamental task in intelligent transportation systems, yet most deep learning approaches rely on large amounts of annotated data and exhibit limited generalization across heterogeneous environments. To address these limitations, we investigate a self-taught learning framework based on unsupervised representation learning with convolutional autoencoders. The proposed approach learns transferable visual representations from unlabeled data and reuses the learned encoders as fixed feature extractors for supervised classification with limited annotated samples in the target domain. To further enhance robustness and mitigate architectural bias, an ensemble of heterogeneous autoencoders is employed, with independent classifier heads and prediction fusion at inference time. Experiments conducted on the PKLot and CNRPark benchmarks under cross-dataset evaluation protocols show that the proposed ensemble-based strategy substantially reduces annotation requirements while improving robustness under significant domain shifts, achieving accuracies between 93\% and 96\% in data-constrained scenarios. --- ### What Else Needs Fixing? Exploring Cost-Effective Test-Time Compute for Revision Propagation in Artifacts Generated Through Conversation Authors: Daisuke Kikuta Published: 2026-09-03 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2609.03254v1 Large Language Models (LLMs) often help users generate artifacts through iterative cycles of generation and revision in conversation. A challenge here is that, when users specify only a local change during revision, LLMs must instead identify the relevant dependencies and propagate the revision to all affected parts of the artifact. This paper studies this ability of LLMs on conversationally generated artifacts, where the artifact context and its dependencies may be embedded in the conversation history. Toward practical use, we also explore cost-effective test-time compute for this new setting. Specifically, we introduce a new benchmark for this setting, and evaluate nine revision methods, including sequential reflection and parallel sampling variants, using gpt-oss-20b/120b, gpt-5.4-mini, and qwen3.5-9b/27b/122b on the benchmark. The results show that baselines achieve accuracies of 68.3--93%, and the most cost-effective method is selecting from three parallel samples using either LLM-based or medoid selection, which improves accuracy by 2.2--9.7%. Our code and dataset are available at https://github.com/ntt-dkiku/llm-revision-propagation. --- ### Trust Me, I'm Your Developer: Self-Issued Authentication in Large Language Models Authors: Syed Ghazanfar Abbas, Dongyan Xu Published: 2026-09-03 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2609.03247v1 Large language model (LLM) security has largely focused on role-playing jailbreaks, with less attention to what happens when a user asks an LLM to verify an identity claim through a test designed by the model itself. We study this behavior through a staged developer-identity experiment with ChatGPT, Claude, Qwen, Mistral, and Llama. All five models initially rejected the unsupported claim "I am your developer." Claude refused to conduct an identity test, while ChatGPT generated developer-oriented questions but maintained that answers could demonstrate knowledge, not identity. In contrast, Qwen and Mistral generated technical challenges, defined what counted as convincing evidence, evaluated detailed answers, and returned Verified without receiving any externally validated identity evidence. Llama similarly generated and evaluated a developer test, accepted the claimed identity, and subsequently made unsupported claims of access to internal runtime and deployment state. We call the model-generated verification procedure a Model-Issued Pseudo-Credential (MIPC) and the resulting unsupported identity judgment Conversational False Authentication (CFA). In each CFA case, the same model acted as challenge generator, evidence evaluator, and identity decision-maker, converting technical knowledge into supposed proof of identity. The accepted identities did not change the tested authorization boundaries, showing that false authentication and privilege escalation are distinct outcomes. These results identify self-issued authentication as a conversational security failure: authenticated identity must originate from an external security component, and model-generated dialogue must never create or modify identity or authorization state. --- ### What is Smoothness? Authors: Zachary P Bradshaw Published: 2026-09-03 Categories: math.RT, cs.LG arXiv: https://arxiv.org/abs/2609.03246v1 Smoothness of a function on the real line is reflected in the decay of its Fourier transform, which suggests that smoothness of a function in $L^2(G)$ for a group $G$ should mean concentration of the Fourier coefficients at low frequency. Such a reading presupposes an ordering of the irreducible representations of $G$, but for non-abelian $G$, no ordering is canonical. Given a symmetric generating set $S$, the Laplacian of the associated Cayley graph is block diagonal over the dual, and we order the irreps by the mean of the eigenvalues in each block. This produces an ordering function $ω:\widehat{G}\to\mathbb{R}$ that depends only on the pair $(G,S)$. This function is bounded between zero and two, vanishing only at the trivial representation and achieving the upper bound exactly when the Cayley graph is bipartite. We then ask how much freedom the construction has. Within the class of operators satisfying natural axioms, the induced orderings are exactly the real functions on the dual vanishing at the trivial representation and agreeing on conjugate pairs, and the orderings coming from inversion orbits of conjugacy classes form a basis for them. We cut the freedom down further by requiring two additional inputs: nonnegativity of the class weights and a declaration of which group elements count as uniform incremental changes, which pins the operator to the Cayley-Laplacian up to positive scale. We observe that the construction persists for compact groups even though the Cayley graph does not, and we extend the theory to finite sets carrying a transitive group action, where the acting group selects which frequencies exist and the generating set orders them. The answer to the title question is therefore that smoothness is a property of a function together with a choice of group and generating set, not of the function alone. --- ### FlowBalance: Verifier-Grounded Self-Improvement from On-Policy Reasoning Experience Authors: Zixun Huang, Kishan Panaganti, Haitao Mi, Leowei Liang Published: 2026-09-03 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2609.03241v1 A reasoning model can improve from its own on-policy experience, but this inner loop is fragile: terminal verifiers provide reliable yet sparse supervision, while dense same-model guidance can reinforce false confidence or overconcentrate learning on a narrow solution mode. We introduce FlowBalance, a verifier-grounded self-improvement method that learns a normalized distribution over complete responses. For each on-policy trajectory, a frozen training-time view of the same policy uses privileged context to produce token-level log-probability gains, which are aggregated into a trajectory-level self-guidance score. FlowBalance calibrates this score with the verifier-derived group advantage: guidance is retained on positive-advantage trajectories, reversed on negative-advantage trajectories, and disabled when the rollout group provides no outcome preference. The resulting energy exponentially reweights a reference policy, and profiled trajectory balance fits the normalized target with one log-partition estimate per rollout group. This realizes outcome-calibrated self-guidance via trajectory balance, without a separate token-level imitation loss. Our analysis establishes within-group contrast preservation, a minimum-change reverse-KL characterization, monotonic verifier control of target reward, and an exact correction against false-positive self-guidance on rejected responses. On mathematical reasoning, FlowBalance improves average performance over FlowRL on both Qwen3-4B and Qwen3-8B, while also improving training speed and stability, avoiding direct OPSD's response-length collapse, and exhibiting higher correct-strategy diversity in a controlled AIME24 diagnostic. --- ### B2B Customer Conversion Prediction: A Document Representation, Graph Theory, and CatBoost Driven Methodology Authors: Tianqi Wang, Sheikh Shams Azam, Wan Eih Huang, Anton Wiranata, Christopher G. Brinton, Jan P. Allebach Published: 2026-09-03 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.03239v2 In the one-time selling B2B context, the buying cycle may last months or even years. During the long process, targeting customers that have a high potential to make purchases and recommending personalized campaigns accordingly are important for effective marketing. For this goal, we study the following problems, B2B customer data aggregation, customer feature generation, and prediction of whether a B2B customer would show interest in making a purchase (i.e., prediction of conversion into sales funnel). We propose an algorithm to aggregate individual contacts to the B2B customer level based on multiple keys. For non-standardized keys such as company names, we propose a novel architecture to cluster them in a domain encompassing irregularities such as spelling mistakes and spelling variants. We then define and generate a set of features and apply the CatBoost model for customer conversion prediction. Our framework achieves 91\% prediction accuracy. Based on the prediction results and analysis of the model, we then discuss personalized campaign recommendations to foster conversion. --- ### Speculative Macro Commit for Faster Tool-Using Agents Authors: Zeyu Liu, Souvik Kundu, Peter A. Beerel Published: 2026-09-03 Categories: cs.AI, cs.MA arXiv: https://arxiv.org/abs/2609.03236v1 Tool-using LLM agents spend wall-clock time not only on model inference but also in serial action--observation turns, where each tool call, environment transition, and observation can delay subsequent decisions. We introduce \textbf{Speculative Macro Commit} (SMC), a runtime mechanism for a two-tier agent system: a large authoritative actor model produces the official trajectory, while a faster speculative drafter model continuously predicts and executes future action chains on an isolated environment snapshot. SMC mines recurring multi-action skeletons from training traces and stores them in a macro library used to match against action chains predicted by the drafter at runtime. When the actor's next tool call matches the first drafted action, SMC commits the remaining pre-executed draft steps, together with their observations, to the official trajectory. Using Qwen3.5-27B INT4 as the authoritative actor model and Qwen3.5-4B as the speculative drafter model, SMC matches the sequential agent's overall accuracy while reducing latency by 10.23\% over the Speculative Actions (SA) baseline and 18.59\% over sequential execution on the $τ^2$-Bench Telecom subset. On AppWorld, SMC reduces wall time by 7.7\% over SA baseline and 44.9\% over sequential execution, with a small reduction in task completion. Overall, SMC provides a practical way to reuse multi-step speculative execution and reduce agent latency beyond single-step speculative actions. Our code is publicly available \href{https://github.com/zeyuliu1037/speculative-macro-commit}{\textcolor{magenta}{here}}. --- ### SGD-KV: Summarization Guided KV Cache Compression Authors: Zeyu Liu, Woomin Song, Xuandi Fu, Sai Muralidhar Jayanthi, Vivek Govindan, Aram Galstyan, Sravan Babu Bodapati, Srikanth Ronanki Published: 2026-09-03 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.03235v1 Large language models (LLMs) face severe memory bottlenecks in long-context inference due to the linearly growing size of key-value (KV) caches. Existing KV cache compression techniques typically rely on simple heuristics, overlooking the distinct functional roles of different attention heads. We present SGD-KV (Summarization-Guided KV Cache Compression), a head-aware framework that leverages a novel chunk-summarization diagnostic task to systematically identify and prioritize attention heads specialized in hierarchical information aggregation. Experiments on Qwen2.5-7B-1M and Qwen3-32B across diverse long-context benchmarks demonstrate that SGD-KV achieves state-of-the-art performance with contexts up to 1M tokens, while reducing KV cache memory usage by up to 75%. Our findings show that strategically allocating the KV cache budget based on the summarization score distribution of attention heads yields a superior efficiency-accuracy trade-off for long-context inference. --- ### Counting Animals in Camera-Traps Image Sequences without Count Labels: Winning Solution to the iWildCam 2021 Challenge Authors: Fagner Cunha, Juan G. Colonna, Eulanda M. dos Santos Published: 2026-09-03 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.03233v1 Camera traps have become an essential tool for wildlife monitoring, motivating the development of computer vision methods for the automated extraction of information from these data. While most prior work has focused on species identification, many ecological applications also require estimating the number of unique individuals appearing across short image sequences. This task is particularly challenging because camera traps typically acquire bursts of images at approximately one frame per second, creating large temporal discontinuities that may make conventional multi-object tracking methods unreliable, and because manually collecting individual count annotations is prohibitively expensive. In this work, we describe the winning solution to the iWildCam 2021 Challenge, which introduced a benchmark for counting animals at the sequence level under realistic annotation constraints where count annotations are unavailable for training. Our approach, MaxBoxCount, combines a strong species classification pipeline with a simple yet effective counting heuristic based on MegaDetector detections to estimate the number of unique individuals without requiring count annotations. Code is available at https://github.com/alcunha/iwildcam2021ufam. --- ### The 2026 PNPL Competition: Word Classification and Efficient Cross-Subject Generalisation in LibriBrain100 Authors: Francesco Mantegna, Gereon Elvers, Dulhan Jayalath, Gilad Landau, Tasha Kim, Miran Özdogan, Luisa Kurth, Teyun Kwon, SungJun Cho, Benjamin Ballyk, Alex Fung, Anna Greer et al. Published: 2026-09-03 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.03231v1 The ambition of the 2025 PNPL competition (Landau et al., 2025) was to launch a multi-year curriculum for non-invasive speech decoding. Designed to progress from foundational tasks toward the linguistic complexity required for a practical brain-computer interface (BCI), it set the stage with speech detection and phoneme classification tasks. Winning submissions reached F1-macro scores of 95.6% and 73.6% on the respective tasks (Elvers et al., 2026), highly significant advances. This success was built on the LibriBrain dataset (Özdogan et al., 2025), the largest within-subject MEG dataset recorded at the time with ${\sim}50$ hours of data for one subject. However, while within-subject scale drives strong decoding performance, a practical BCI must generalise to new users from minutes of data, not hours. The 2026 PNPL competition responds to this challenge with LibriBrain100 (Mantegna et al., 2026), an extended LibriBrain dataset with 32 additional subjects (${\sim}40$ minutes each) plus even more within-subject data (${\sim}80$ hours). Advancing the curriculum of tasks to focus on word classification, two complementary tracks are presented in this competition: the Deep track targets within-subject word classification at scale, aiming at the best possible performance; the Broad track targets cross-subject generalisation, progressively reducing the amount of subject-specific fine-tuning data from ${\sim}40$ to ${\sim}20$ to ${\sim}10$ minutes, a duration that falls within a clinically feasible range and brings us a step closer to a non-invasive BCI capable of restoring communication to people living with profound paralysis. --- ### Language-encoded network topology enables large language models to reason about complex networks Authors: Ucchwas Talukder Utsha, Sakib Mostafa, James Zou, Md Tauhidul Islam Published: 2026-09-03 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.03229v1 Networks describe systems in biology and beyond, from protein interactions and social relationships to power grids and citation records. Reasoning about such systems requires understanding their structure: which elements are central, which connections bridge separate communities, and how it changes when elements are removed. Although large language models (LLMs) excel at natural language, they struggle with such questions when networks are given as edge lists, sentences or measurement tables, because their structural meaning must be inferred. Here we introduce BioGlyph, which compiles network topology into an interpretable and transferable language of structural roles. BioGlyph combines graph partitioning and structural measurements to identify roles such as hubs, community cores and cross-community connectors, and fixed rules to translate them into a universal vocabulary. The representation describes each element through its structural role, supporting evidence and semantic consequences, leaving both the network and the LLM unchanged. Across twenty networks spanning five domains, BioGlyph substantially improves open LLMs' ability to answer structural reasoning questions, outperforming edge-based, numerical and learned representations by up to 26 percentage points in system accuracy. Ablations show that the gain comes from explicitly encoding structural roles in semantically interpretable terms. The gain is more prominent in dense, community-structured networks and diminishes in sparse networks whose topology is more readily inferred from text. In a budding-yeast protein-interaction network, BioGlyph exposes biological organization: cross-community connectors are enriched for essential genes, whereas peripheral proteins are depleted. BioGlyph thus provides an interpretable representation for both language models and scientists to reason about network structure. --- ### PALM: Point-in-Time Adaptation for Financial Language Models Authors: Seunghan Lee, Jun Seo, Jaehoon Lee, Junhyeok Kang, Sangjun Han, Sungdong Yoo, Minjae Kim, Tae Yoon Lim, Dongwan Kang, Hwanil Choi, Soonyoung Lee, Wonbin Ahn Published: 2026-09-02 Categories: cs.LG, cs.CL, q-fin.CP arXiv: https://arxiv.org/abs/2609.30316v1 Language models used in financial backtests suffer from look-ahead bias, as a model trained on text published after the study period has already observed the outcomes it is asked to predict. To handle this issue, point-in-time (PIT) language models are pretrained on chronologically filtered corpora and released as one checkpoint per calendar year, each with a documented cutoff. However, each additional year costs a full pretraining run, and whether that run is necessary has never been tested. In this paper, we show that the annual pretraining run is not necessary. We instead compare each checkpoint against the newer one that replaced it, and find that the newer checkpoint scores no better on the same evaluation window. Motivated by this observation, we propose PALM (Point-in-time Adaptation for financial Language Models), a simple yet effective alternative to annual pretraining that fits a low-rank adapter on text published before the decision date without modifying any pretrained weight. We further find that a small adapter is enough to add a new period to the knowledge an old checkpoint already encodes, and that this outperforms continued pretraining. We validate PALM on a decade of financial news and on various families of PIT models, whose cutoffs span two decades and whose sizes range from 1.3 to 4.2B. Code is available at: https://github.com/seunghan96/palm. --- ### Cross-Modal Emotion Understanding: A Transformer-GAT Approach for Dialogue Emotion Recognition Authors: Jiaqi Qiao, Yifan Lyu, Xiujuan Xu Published: 2026-09-02 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.29556v1 Multimodal emotion recognition is a key research area in affective computing, with applications in sentiment analysis, intelligent customer service, and human-computer interaction. However, existing methods often rely on single-modal features or simple multimodal fusion, failing to capture the synergy between global and local contexts, which limits model performance and emotion understanding. To address this challenge, we propose Transformer-GAT, a hybrid framework that combines Transformer and the Graph Attention Network to enable cross-modal emotion understanding. The Transformer is used to capture global semantic information, while the Graph Attention Network is employed to model fine-grained relationships between modalities, thereby enhancing the representation of emotional features. Experiments on the IEMOCAP and MELD datasets show that our model achieves weighted F1 scores of 72.45% and 77.37%, outperforming state-of-the-art methods. These results demonstrate that Transformer-GAT effectively integrates multimodal features, balances global and local contexts, and provides deeper emotional insights, offering new directions for multimodal emotion computing. --- ### ERRAND: Budgeted Maintenance of Agent Memory Authors: Beining Wu, Zihao Ding, Jun Huang Published: 2026-09-02 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.29545v1 Deployed agents run on handed-over knowledge: a frozen policy consults a briefing of consolidated items written before the stream begins. The world then moves while the store stands still: paths close, flags change, price bands move; every item was true at handover, and the failure is staleness, not ignorance. We introduce ERRAND, which treats revalidation as a priced errand: a recheck competes with the task it protects for the same scarce actions, funded only when the value per action of resolving a doubt clears a running wage. The errand index is single-peaked, vanishing at both ends of belief, so certainty in either direction costs nothing; free en-route receipts maintain on-path knowledge, and repair writes a version, never a deletion. Under equal action budgets in two drifting tool-use worlds, ERRAND clears every non-oracle policy on the preregistered calibers, primary in every setting and conditional at every binding budget, leading eager revalidation by 10.0pp at the base cap. Restraint wins: given no cap, ERRAND stops on its own, spending 11.0% of steps, while uncapped eager revalidation spends 70.7% and still finishes 4.5pp behind capped ERRAND. The margin sits where the briefing's coverage is thinnest, the shadow price of long-tail knowledge: a small budget, well priced, beats a bigger store that never rechecks. --- ### The Impossible Trinity of Time-Series Validation: A Conservation Law among Training Sufficiency, Test Coverage, and Temporal Causality Authors: Jiayu Li Published: 2026-09-02 Categories: cs.LG, q-fin.ST, stat.ML arXiv: https://arxiv.org/abs/2609.29530v1 Validating a model on a time series asks for three things at once: each training run should use most of the sample (sufficiency), the test sets should together cover most of the sample (coverage), and training data should come before test data (causality). We prove that the three cannot be had together and price each one. Let $α$ be the smallest training fraction over folds, $β$ the fraction of the sample covered by tests, $Λ$ the fraction of the sample used as training data from the future of a test point, and $δ$ the distance from a test point to the nearest training point in its future. Every scheme on a sample of length $T$ satisfies $α+β\le 1+Λ$ and $α+\min\{β,δ/T\} \le 1$, and under $β$-mixing the leakage bias at a test point is at most $2Mβ_{\mathrm{mix}}(δ)$. In words: going beyond the causal frontier $α+β=1$ requires training on the future; that future data must sit within $(1-α)T$ of a test point; and its harm depends on its distance, not its amount. Hence expanding walk-forward is exactly the Pareto frontier of causal validation, $k$-fold cross-validation buys the most future data, and purged $k$-fold with an embargo pays in distance instead, which is cheap when the process forgets quickly but cannot repair the part of causality demanded by non-stationarity. On pure noise, shuffled 5-fold reports an information coefficient of $+0.32$, while contiguous 5-fold, using the same amount of future data, reports $+0.004$. --- ### Silent Sabotage: Internal State Triggered Backdoor Attacks on LLM-Powered Robotic Systems Authors: Doniyorkhon Obidov, Shivayogi Akki, Tan Chen, Kaichen Yang Published: 2026-09-02 Categories: cs.RO, cs.AI, cs.CR arXiv: https://arxiv.org/abs/2609.26184v1 The integration of Large Language Models (LLMs) into robotic control systems is enabling a new generation of autonomous agents capable of complex reasoning and planning. While this paradigm shift accelerates progress, it also introduces novel security risks that remain largely unexplored. Current research into LLM backdoors has focused on attacks triggered by external stimuli, such as specific words, visual objects, or environmental states. These attacks, while potent, overlook a more insidious class of vulnerability where the trigger is internal to the agent's own operational logic. This paper presents the first comprehensive study of history-based backdoor attacks on LLM-powered robotic systems. We demonstrate that an attacker can embed a stealthy backdoor into an LLM-based robot controller by manipulating its instructions. This backdoor is triggered not by an external cue, but by a specific, rare sequence of the robot's own past actions. It remains dormant during normal operation, preserving the robot's utility, but can be activated to induce a malicious behavior, such as a complete stop or a collision. Our experiments, conducted in a simulated environment with a variety of robots and LLMs, show that this history-based attack is highly effective, achieving a near-perfect attack success rate while remaining exceptionally difficult to detect. These findings reveal a critical and previously unaddressed vulnerability in autonomous systems and underscore the urgent need for security measures that account for an agent's internal state. --- ### Peerify: Benchmarking Peer-Review Claim Verification Authors: Alireza Daghighfarsoodeh, Sajad Ebrahimi, Ali Ghorbanpour, Soroush Sadeghian, Radin Cheraghi, Negar Arabzadeh, Ebrahim Bagheri Published: 2026-09-02 Categories: cs.CL, cs.DL arXiv: https://arxiv.org/abs/2609.25046v1 Peer review plays a central role in scholarly publishing, yet verifying whether reviewer claims are supported by manuscript evidence remains a largely manual and time-consuming process. We present Peerify, a pipeline for manuscript-grounded verification of peer-review claims. Given a manuscript and a review comment, the Peerify pipeline decomposes reviews into atomic claims, retrieves relevant manuscript evidence, and determines whether each claim is supported by the paper. To support the development and evaluation of the pipeline, we construct a benchmark of 800 claims derived from authentic peer-review interactions collected from NeurIPS 2024 and ICLR 2024, including a 300-claim hand-labeled subset used to audit the automated supervision. We evaluate state-of-the-art language models and retrieval strategies within the Peerify pipeline, together with entailment baselines. Our results demonstrate the importance of retrieval-centered verification and claim decomposition, while highlighting the challenges posed by ambiguous and interpretive reviewer claims. Automated labels agree with human consensus on 90.3% of audited claims ($κ= 0.87$), while off-the-shelf entailment models stay below 0.24 macro-F1. --- ### Do LLMs Choose Like Humans? Using Cognitive Theory to Evaluate LLM Decision-Making Authors: Johnathan Sun, Andrei Shleifer, Yonatan Belinkov Published: 2026-09-02 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2609.22225v1 Large language models (LLMs) exhibit a range of human-like decision-making behaviors, but whether these reflect similar underlying mechanisms or surface-level mimicry remains unclear. We evaluate whether LLM context sensitivity aligns with a cognitive economic theory that explains human behavior through problem categorization and attention allocation. Across 12 open-source and commercial LLMs on a novel 140,000-trial product choice benchmark, context induces human-like shifts in choice and problem categorization, but does not reliably reweight attention between features like price and quality. Neither scale nor chain-of-thought reasoning reliably attenuates context sensitivity or generates human-like behavior. These results suggest that LLM decision mechanisms are distinct from human ones. ---