# Research Papers — 2026-09 · bundle page 106 of 266 > Full-text markdown of papers #5251–5300 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/106 [← Previous bundle](https://aipod.dev/papers/archive/2026-09/page/105.md) [Next bundle →](https://aipod.dev/papers/archive/2026-09/page/107.md) ### Vision Foundation Models with Synthetic-Only Training for Monocular Spacecraft Pose Estimation Authors: John Church, Vazghen Nikolian Published: 2026-09-22 Categories: cs.CV, cs.RO arXiv: https://arxiv.org/abs/2609.26561v1 We present an improvement on previous spacecraft pose estimation architectures that results in the lowest published mean rotation errors we know of on the SPEED+ lightbox and sunlamp test sets for a known, non-cooperative spacecraft. By using a previously established heatmap-based pose estimation architecture and adapting a large self-supervised ViT foundation model (DINOv3) in place of the smaller convolutional and ViT encoders of previous work, we show that pose estimation accuracy improves from 300M to 840M parameters with no saturation yet observed. We also evaluate our 840M model on a Jetson Orin NX 16GB, measuring single-pass network inference at 133.8 ms per crop with a board draw of 32.0 W. These measurements demonstrate embedded inference feasibility on a processor family with orbital flight heritage. Our resulting model outperforms previous models across lightbox and sunlamp domains while training only on synthetic data. Our best model, using DINOv3 840M adapted with LoRA as the encoder (rank 64, three-seed ensemble with four-rotation test-time augmentation), results in $1.56^\circ$ mean rotation error on sunlamp and $1.17^\circ$ on lightbox, compared to the previous best mean rotation errors we know of on these test sets, $2.66^\circ$ and $1.75^\circ$ by EagerNet. --- ### Neutral-Atom-based Quantum Optimization for Resource Allocation in NOMA Networks Authors: Patatchona Keyela, Remon Polus, Soumaya Cherkaoui, Ola Ahmad Published: 2026-09-22 Categories: cs.AI, cs.IT arXiv: https://arxiv.org/abs/2609.26556v1 In wireless communication networks, many resource optimization problems are nondeterministic polynomial-time hard (NP-hard) due to their combinatorial nature and high computational complexity. Recently, neutral-atom-based quantum computing has emerged as a promising platform for efficiently solving such problems by leveraging quantum superposition and entanglement. However, its application to wireless communication optimization problems remains largely unexplored. In this paper, we investigate the use of neutral-atom quantum platforms to solve the maximum access problem (MAP), formulated as a mixed-integer programming task that jointly considers admission control, user clustering, channel assignment, and power allocation in a non-orthogonal multiple access (NOMA)-enabled uplink network. To reduce the computational burden, the MAP is equivalently reformulated as a maximum independent set (MIS) problem in graph theory. This reformulation enables the use of the neutral atom platform based on Rydberg atom arrays, where the MIS problem is naturally encoded into the physical geometry and blockade constraints of the quantum system. Numerical results demonstrate the feasibility and potential of this approach for addressing large-scale wireless resource optimization problems. --- ### JEV-as-a-Judge: Accept When Confident, Escalate When Unsure Authors: Yubo Li, Yidi Miao, Ramayya Krishnan, Rema Padman Published: 2026-09-22 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.26550v3 LLM-as-a-judge scales evaluation, but reasoning judges are slow and costly. We study JEV-as-a-Judge: evaluation with JEV, a decision-only judge that returns label probabilities instead of text, and whose confidence decides whether to accept its verdict or escalate to a reasoning judge. Against sixteen generative and reward-model judges, with blinded human adjudication, JEV comes within three points of GPT-6 wherever a verdict can be read off the text, at 0.36% of its fee and a 0.15-second median latency, and falls behind where the verdict must be derived, as in math, code, and logic. Its confidence marks this boundary. With a threshold frozen in advance, accepting confident verdicts and escalating the rest is 0.9 points more accurate than GPT-6 on 1,610 held-out pairs at 41% of its fee, and in a pre-specified live test on two new workloads the cascade matches GPT-6's accuracy exactly. Confidence routing weakens on style-adversarial pairs and reference-free prose; we close with a simple recipe for validating thresholds locally. --- ### JEV-as-a-Judge: Accept When Confident, Escalate When Unsure Authors: Yubo Li, Yidi Miao, Ramayya Krishnan, Rema Padman Published: 2026-09-22 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.26550v1 LLM-as-a-judge enables evaluation across diverse tasks, but inference cost and confidence reliability become critical at scale. We study whether a decision-only judge can provide an economical first pass and identify when stronger evaluation is needed. Comparing jev-as-a-judge with sixteen generative and reward-model judges, with blinded human adjudication, we find it within three percentage points of a state-of-the-art LLM judge, our strongest comparator, on ordinary preference and evidence-grounded factuality at 0.36% of the comparator's fee. Larger gaps arise when judgments require checking a derivation or resisting an elaborately written wrong answer. On several benchmarks, JEV's gap to this comparator is concentrated in low-confidence decisions. A frozen cascade that accepts confident verdicts and escalates uncertain ones retains 99% of the comparator's accuracy at lower cost. --- ### Latent Commonality Expectation-Maximisation for Box-supervised Tree Crown Instance Segmentation Authors: Thomas Pitts, Kunqi Li, Bin Liang Published: 2026-09-22 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.26549v1 Individual tree crown segmentation from aerial imagery underpins tree-level carbon accounting, biodiversity, and restoration monitoring at landscape scale. However, existing models are predominantly trained on dense canopy forest imagery and degrade in savannah and drylands, where tree crowns are sparse, of variable appearance, and underrepresented in annotated benchmarks. These models also typically depend on costly polygon annotations. We introduce LACE (LAtent Commonality Expectation-maximisation), a box-supervised instance segmentation model, evaluated on 0.1 m/px aerial RGB tree crown imagery. LACE uses a frozen DINOv3-web ViT-L/16 encoder, applied at four spatial offsets and interlaced into a denser feature grid, with a lightweight CenterNet-style detection head trained solely on bounding boxes. We use expectation-maximisation to separate recurring appearance, the "treeness", within bounding boxes from surroundings. On the OAM-TCD benchmark test set, LACE reaches a mask AP$_{50}$ of $0.663 \pm 0.001$ (3 seeds) trained on 900 box-annotated images and without mask annotations, above the 0.626 scored by Restor's released mask-supervised Mask R-CNN, which was trained on the full ~4.2k image set. On a sparse-canopy holdout set, mask AP$_{50}$ rises to $0.691$ versus $0.612$ for Detectree2, a mask-supervised baseline. On NeonTreeEvaluation, using the official evaluation code, LACE reaches $0.728 \pm 0.003$ F1@0.4 (5 seeds) from 23,424 hand-annotated RGB boxes alone, matching the authors' DeepForest model's published 0.719, using under 0.1% of its training annotations and none of its LiDAR-derived 30M-crown pretraining set. By leveraging frozen self-supervised features, LACE matches or surpasses fully-supervised specialist baselines from boxes alone, removing the need for polygon annotation in tree crown instance segmentation for sparse-canopy environments where labelled data is scarce. --- ### Topology-Stratified Materials Discovery with A Flow-Based Generative Model Authors: Jingyi Zhou, Oyshee Chowdhury, Noah Oyeniran, Chongze Hu Published: 2026-09-22 Categories: cond-mat.mtrl-sci, cs.AI arXiv: https://arxiv.org/abs/2609.26547v1 Accurate generation of crystal structures is the foundation to the discovery of high-performance materials for extreme-environment applications, such as aerospace, additive manufacturing, and fusion energy systems. Although generative modeling has emerged as a promising approach for crystal design, its performance remains limited by the complex crystal structures and diverse chemical compositions. In this work, we develop UFO-MGen, a universal flow-based generative model that learns topological features of Wyckoff representations and leverages this information to accurately generate crystals across vast structural and chemical spaces. Compared with state-of-the-art generative models, UFO-MGen achieves the highest crystal generation success rate under a rigorous multi-stability evaluation framework, the highest SUN (stable, unique, novel) rate, and a remarkable extrapolation capability that has not been reported by previous models. Furthermore, a fine-tuning module is implemented to UFO-MGen for property-constrained crystal generation, enabling the inverse materials design toward target properties. The UFO-MGen opens a new avenue for accelerated materials discovery and providing a foundation for universal materials intelligence. --- ### A retrospective analysis on the use of LLMs to study infant syntax learning Authors: Hélie Bazin, Anouk Barberousse, François Yvon Published: 2026-09-22 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.26539v1 Large language models (LLMs) have increasingly been used to investigate how children acquire syntax at an early stage of development. This is notably the central scientific goal of the BabyLM challenge, a community-wide effort to develop models that achieve human-level syntactic performance while being trained on developmentally realistic corpora. In this paper, we reflect on the use of LLMs in the study of infant syntax learning by providing an epistemological assessment of several studies from this research program. We discuss how datasets are built, which models are implemented, how they are trained and syntactically evaluated. We observe significant assumptions in the methodology of BabyLM and related studies, thus mitigating their theoretical scope. We additionally observe that using developmentally-realistic corpora have limited effects on models performance on commonly-used benchmarks, which suggest important computational differences between LLMs and the infant syntax learner. --- ### Notes on Fourier-Bessel wavelets Authors: Marcel Venturotti, Georgios Exarchakis Published: 2026-09-22 Categories: cs.LG, cs.CV, math.NA arXiv: https://arxiv.org/abs/2609.26537v1 These notes develop the mathematical foundations and construction of a Fourier-Bessel wavelet family inspired by the disk harmonics of Shaqfa et al.(9). We begin with the relevant properties of Bessel and modified Bessel functions and introduce the wavelet properties required for the construction. We then derive the Fourier-Bessel disk harmonics as solutions to the Helmholtz equation on the unit disk subject to a Neumann boundary condition. Building on this basis, we construct a wavelet family by applying a Gaussian spatial envelope and introducing a zero-mean correction for the zeroth angular order. We derive the corresponding normalisation constants for $L^2$-based applications and discuss $L^1$-based normalisation for frequency-domain peak consistency. Finally, we derive a closed-form Fourier-domain representation of the resulting wavelets. The main motivation is the approximately linear spacing, which converges to $π$ between consecutive radial eigenvalues. Rather than replacing the conventional dyadic organisation of wavelet families, this construction lays out the foundation to explore whether a more uniform radial frequency allocation can be useful for applications in which broad and balanced frequency coverage is desirable. --- ### Transcribe, Translate, and Optimize: Joint Reward Learning for Speech Translation Authors: Yanghe Dong, Wanting Huang, Weiran Wang Published: 2026-09-22 Categories: cs.CL, eess.AS arXiv: https://arxiv.org/abs/2609.26536v1 In LLM-based speech translation, transcription-based chain-of-thought (CoT) suffers from a mismatch between reference transcripts used in supervised fine-tuning (SFT) and model-generated transcripts at inference. To address this, we propose joint recognition and translation fine-tuning via group relative policy optimization (GRPO). We score both transcripts and translations, with translation conditioned on model-generated transcripts, and compare three token advantage strategies. Using Qwen2.5-Omni-3B across four languages, we evaluate CoT against direct speech translation (Direct ST) under SFT and GRPO, training on CoVoST 2 and testing on CoVoST 2 and FLEURS. CoT GRPO outperforms Direct ST GRPO by 1.77 and 0.83 average BLEU points on CoVoST 2 and FLEURS. Compared to CoT SFT, GRPO boosts BLEU by 0.82 and 0.67 points and reduces word error rate (WER) by 8.8% and 7.2% relatively. These results highlight reinforcement fine-tuning as an effective method to mitigate the training-inference mismatch, jointly improving recognition and translation. --- ### REFLEX with Jev for Efficient Selective Control in LLM Agents Authors: Tiantong Wu, Wei Yang Bryan Lim Published: 2026-09-22 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.26532v1 LLM agents often use generative models for bounded decisions, raising the question of when these decisions can be handled more efficiently without reducing task success. We study REFLEX, an agent architecture that uses Jev as a fast, typed decision layer and calls a strong LLM when confidence is low, or generation is required. On a frozen 100-task benchmark, REFLEX achieves 95% success with 72.7% fewer strong-model calls than a strong-only agent, with reductions persisting across three fallback families. Controlled interventions show that reliability depends on action-set size and near-valid alternatives near authorization boundaries. External BFCL and $τ$-style evaluations reveal limited advantages over a cheap generative cascade when ordinary routing is already highly accurate. These findings identify when selective control with Jev can reduce computation and where its benefits are limited. --- ### A Semiotics-Aware Framework for Evaluating Fidelity and Coverage in Natural Language Generation Authors: Lorenzo Zangari, Davide Picca Published: 2026-09-22 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2609.26527v1 When two texts describe the same expression, standard metrics based on lexical overlap or whole-text similarity may fail to detect meaningful differences in how that expression is framed. We propose a framework to evaluate semiotic alignment between texts, where a semiotic profile encompasses both the contextual meaning and the discourse references made salient by a text. Our approach yields two scores, Semiotic Fidelity and Semiotic Coverage, estimating how much of one text's profile is supported by the other and how much of the other's profile it recovers. Experiments show that coverage is typically lower than fidelity, and that alignment between LLMs and human-curated data is highest at low sampling temperatures, while higher temperatures reduce this alignment. --- ### Virtual Encoders in Multimodal Transformers Authors: Katsuya Ogata, Yuta Nakashima Published: 2026-09-22 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.26513v2 Multimodal language models traditionally rely on dedicated perceptual encoders to construct task-usable representations. More integrated architectures have recently emerged, which instead expose the shared transformer to lightly projected patches, audio frames, or discrete visual tokens. Where does this encoding happen when such representations are not provided? We find that the transformer can internalize this missing computation, constructing task-usable perceptual representations within its own early-to-middle layers before the downstream language model. We call this computational structure a Virtual Encoder. Across linear probing, similarities to perceptual encoders, and causal analyses, we identify signatures of this structure in models that receive perceptual tokens without continuous encoder-derived features. These analyses also suggest that the boundary between perception and language processing need not coincide within an architectural module. Instead, encoder-like computation can emerge as a functional regime within a shared transformer, providing a new perspective for understanding where and how multimodal models process perception. --- ### Virtual Encoders in Multimodal Transformers Authors: Katsuya Ogata, Yuta Nakashima Published: 2026-09-22 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.26513v1 Multimodal language models traditionally rely on dedicated perceptual encoders to construct task-usable representations. More integrated architectures have recently emerged, which instead expose the shared transformer to lightly projected patches, audio frames, or discrete visual tokens. Where does this encoding happen when such representations are not provided? We find that the transformer can internalize this missing computation, constructing task-usable perceptual representations within its own early-to-middle layers before the downstream language model. We call this computational structure a Virtual Encoder. Across linear probing, similarities to perceptual encoders, and causal analyses, we identify signatures of this structure in models that receive perceptual tokens without continuous encoder-derived features. These analyses also suggest that the boundary between perception and language processing need not coincide within an architectural module. Instead, encoder-like computation can emerge as a functional regime within a shared transformer, providing a new perspective for understanding where and how multimodal models process perception. --- ### Do Vision Model See Like the Brain? A Comparison Across EEG Encoding Model Authors: Shashank Baghel, Kshitij Dwivedi, Dinesh Singh, Sanjeev Nara Published: 2026-09-22 Categories: cs.CV, cs.AI, cs.HC arXiv: https://arxiv.org/abs/2609.26512v1 Convolutional neural networks (CNNs) and vision transformers are both used to model the human visual system, but whether the two architectures diverge at a specific point in network depth is unclear. We compared six CNNs and two vision transformers by computing the Pearson correlation (r) between each model's predicted and measured EEG response at every layer or block, in ten participants viewing 200 natural images. For the transformer models, we also tested four token representations, from the classification (CLS) token alone to CLS combined with all patch tokens. CNNs showed strongest correspondence at the earliest layers, weakening at deeper layers, particularly later in the post-stimulus response. Transformers instead sustained strong correspondence at their deepest blocks, though not at their earliest ones. This advantage depended on token representation: pooled representations gave weaker peak correlations (r approx 0.48-0.51) than representations retaining all patch tokens (r=0.640 for CLIP-ViT-B/32, r=0.656 for DINOv2-ViT-B/14). Controlled comparisons showed architecture, not training objective, drove this effect: MoCo-v1 and ResNet-50 (matched architecture) performed nearly identically (r=0.673, 0.670), whereas CLIP-RN50 and CLIP-ViT-B/32 (matched objective) diverged until patch tokens were preserved. We propose that CNN training's classification bottleneck compresses brain-relevant information at depth, unlike transformers' self-attention and non-classification objectives. A spatial topography analysis showed a common occipital-dominant pattern across all models, indicating these differences reflect signal strength and persistence rather than distinct brain regions. Patch-preserving transformer representations sustain brain-predictive correspondence where CNNs collapse. --- ### Gap-Free Streaming PCA Beyond Rank-One Updates: Near-Optimal Rates and Applications to Differential Privacy Authors: Anming Gu, Syamantak Kumar, Kevin Tian, Chutong Yang Published: 2026-09-22 Categories: cs.LG, cs.DS, stat.ML arXiv: https://arxiv.org/abs/2609.26508v1 Streaming principal component analysis (PCA) seeks to recover a leading spectral subspace in a single pass over a data stream. We give a new analysis of the ubiquitous Oja's algorithm (Oja82) for the most general, gap-free variant of this problem, where no eigengap assumptions are made on the underlying mean matrix, complemented by a nearly-matching lower bound. Prior works achieving near-optimal rates for streaming PCA either required gap assumptions (JJK+16, HNWW21), or were limited to rank-one updates (AZL17, Lia23). Our proof only uses a second moment bound on the individual stochastic updates, bypassing the almost sure bounds needed by prior near-optimal analyses, and the analogous offline matrix Bernstein bound. We also extend our result to a Rayleigh quotient notion of approximate PCA, addressing an open question of (JJK+16). As our main application, we give gap-free differentially private PCA guarantees for sub-Gaussian data, settling Conjecture 1.1 of (Bro26) up to logarithmic factors. --- ### The Ethics of Artificial Intelligence in Military Operations Authors: Nicolas Drapier, Florian Mauberger, Aladine Chetouani, Aurelien Chateigner Published: 2026-09-22 Categories: cs.CY, cs.AI, cs.HC arXiv: https://arxiv.org/abs/2609.26507v1 Deep learning systems now mediate military decisions to use force, yet their internal logic resists inspection, their evaluation practices are gameable, and their deployment fractures accountability across dispersed stakeholders. The ethical challenge posed by these systems is fundamentally epistemic: not just whether autonomous weapons should be permitted to kill, but whether the conditions for responsible human judgment can survive when critical functions are delegated to opaque algorithms. We show that this epistemic condition produces a concrete accountability gap: responsibility diffuses across designers, operators, and policymakers while International Humanitarian Law presupposes capacities for judgment that current AI systems lack. To address this gap, we propose a governance framework that proceduralizes ethical constraints through named accountability roles, adversarial auditing with undisclosed benchmarks, tiered deployment thresholds, and a proposed NATO evaluation standard. Counterfactual analysis of eight documented cases (1988-2025) shows that each governance mechanism addresses a documented class of failure, but no single safeguard suffices in isolation: effective governance of military AI requires not only technical constraints but the institutional infrastructure to keep human judgment meaningful. --- ### Semantically-Guided Domain Randomization for Industrial Object Detection in Low-Image-Budget Regimes Authors: Jose Moises Araya-Martinez, Gautham Mohan, Jens Lambrecht Published: 2026-09-22 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.26505v1 Retraining visual perception pipelines in High-Mix, Low-Volume (HMLV) automotive manufacturing must be carried out under tight annotation, energy, and time budgets, yet most Synthetic Data Generation (SDG) strategies still operate in the thousands of images. This work evaluates Semantically-Guided Domain Randomization (S-GDR), an annotation-free adaptation pipeline that couples Vision-Language Model (VLM)-based semantic captioning of a small unannotated real reference set with diffusion-based background synthesis (Stable Diffusion XL (SDXL) conditioned by ControlNet and IP-Adapter) and mask-based object composition. On an automotive multi-object detection benchmark and with a fixed budget of 200 synthetic training images, S-GDR reaches mAP50-95 = 0.739 on a real held-out test set, outperforming a domain-randomized render baseline (mAP50-95 = 0.697) as well as brightness filtering, perceptual hashing, CycleGAN style transfer, and unguided diffusion variants sharing the same 200-image budget. These initial observations position S-GDR as a promising annotation- free alternative for extreme data-scarcity regimes. --- ### Deep Generative Crystal Structure Prediction: A Benchmark Study and a Controlled Test of Prototype Dependence Authors: Lai Wei, Rongzhi Dong, Ying Feng, Madeline Miklos, Jianjun Hu Published: 2026-09-22 Categories: cond-mat.mtrl-sci, cs.LG arXiv: https://arxiv.org/abs/2609.26502v1 Deep generative models are widely reported to enable de novo crystal structure prediction (CSP), but their capability has not been measured consistently against template-based methods. We evaluate 12 representative generative CSP models, spanning latent-variable, diffusion, flow-matching, autoregressive, and manifold random-walk architectures, against TCSP 2.0 on 180 test structures and a leakage-controlled subset of 46. All methods use identical structure-matching, symmetry, and consensus criteria. Template retrieval is the strongest single method, reaching 68.3% top-1 success; symmetry-aware EquiCSP (66.4%) and Uni-3DAR (62.9%) form the next tier. However, comparison with TCSP 2.0 shows that most structures correctly predicted by generative models are also correctly predicted by template substitution. Thus, the set of structures uniquely reachable by generation is small, limiting its practical advantage for discovering structures outside existing prototype libraries. To test the source of this performance, we removed entire stoichiometric prototype families from the training set and retrained the strongest generative model. Accuracy declined by 50-78% across four families, establishing that performance is substantially prototype-dependent. A small minority of structures survived removal of their prototype family, demonstrating a real but limited retrieval-independent predictive capacity. Present generative CSP models therefore function largely as implicit, softer-edged prototype libraries rather than genuinely de novo predictors. Enlarging this residual capacity, rather than aggregate match rate alone, is the central open problem. --- ### Radiomics-Conditioned Modulation of RenalCLIP Features for Clear Cell Renal Cell Carcinoma Classification Authors: Yuan Liang, Sourav Bhattacharjee, Abraham Campbell Published: 2026-09-22 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2609.26492v1 Radiomics provides quantitative descriptions of tumour appearance that may complement disease-specific foundation models in small labelled cohorts. We investigate this complementarity for computed tomography-based classification of clear cell renal cell carcinoma. Our framework uses radiomics to modulate RenalCLIP features through feature-wise linear modulation (FiLM), while retaining a direct radiomics contribution. Internal testing and external validation compare it with conventional fusion strategies and reference classifiers. The FiLM model achieves an area under the receiver operating characteristic curve (AUC) of 0.804 internally and 0.854 externally, with the highest mean AUC among the evaluated RenalCLIP fusion strategies in both cohorts. Pathway ablations examine the contributions of conditional modulation and the direct radiomics residual, while feature permutation highlights the role of tumour texture. These findings support radiomics as a useful complement to RenalCLIP in a small labelled cohort and identify FiLM as an effective approach to integrating their representations for robust renal tumour classification. --- ### Calibration as a First-Class Criterion in LLM Evaluation Authors: Mario Sanz-Guerrero, Katharina von der Wense Published: 2026-09-22 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.26489v1 Calibration of language models -- the alignment between expressed or implicit confidence and empirical correctness -- is a well-studied subfield within NLP. Methods to measure it already exist. The problem is adoption: outside this subfield, NLP research regularly introduces new models, datasets, and benchmarks without checking whether the model's confidence scores are meaningful. We argue that this adoption gap is a major obstacle to trustworthy LLM evaluation. Miscalibration causes problems in two distinct areas: at deployment, where overconfident mistakes cause real harm, and inside the research pipeline, where methods like LLM-as-a-judge, synthetic data generation, and active learning rely on calibrated confidence without verifying it. Standard calibration metrics only require two inputs per example: a confidence score and a correctness judgment. Most benchmarks in use today already provide both, meaning calibration can be reported immediately. For open-ended generation, however, defining these two inputs is still an open challenge. We argue that each NLP subfield should pair its main performance metric with a calibration score and call for treating calibration as an essential property of every model rather than a niche topic. --- ### Spoken Language Models that Think Aloud Authors: Junyi Ao, Kainan Peng, Mingbo Ma, Shun Zhang, Zhenyu Tang, Xutai Ma, Xiang Li, Yinghao Li, Yuancheng Wang, Zhizheng Wu, Haizhou Li, Qing He et al. Published: 2026-09-22 Categories: cs.CL, cs.SD, eess.AS arXiv: https://arxiv.org/abs/2609.26488v1 While Chain-of-Thought (CoT) reasoning has improved the capability of language models, directly applying it to Spoken Language Models (SLMs) may introduce long silent intervals under the serial "think-then-speak" paradigm, disrupting real-time spoken interaction. To address this issue, we propose an asynchronous think-aloud framework for reasoning-based SLMs within the Thinker-Talker architecture. The framework maintains a primary reasoning stream for logical deduction and a lightweight think-aloud stream that generates short, task-grounded progress utterances conditioned on the user input and the evolving reasoning state. A dynamic balance strategy coordinates the two streams at runtime, triggering additional think-aloud speech to avoid silent gaps and canceling pending utterances when the final response becomes ready. Experiments on spoken reasoning and question-answering benchmarks show that our approach substantially reduces user-audible silence during reasoning while maintaining answer accuracy comparable to that of a serial "think-then-speak" baseline, demonstrating the potential of asynchronous think-aloud for responsive interaction in SLMs. --- ### When Recursive Models Finish Computing Authors: Hare Krishna, Shubham Singh, Stephen Ebert, Hao-Yu Sun Published: 2026-09-22 Categories: cs.LG, cs.AI, cs.NE arXiv: https://arxiv.org/abs/2609.26487v1 Recursive models can continue updating their latent states beyond their nominal inference budget, so an incorrect output at that budget does not show whether computation is unfinished or has entered a persistently unsuccessful regime. We study the dynamics of completion in attention- and MLP-based Tiny Recursive Models (TRMs) on 1,000 hard Sudoku puzzles. Extending recurrence from the nominal 16 steps to 512 steps increases cumulative exact-solve accuracy from 59.2% to 87.5% for the attention model and from 74.4% to 91.9% for the MLP model, solving more than two-thirds of the puzzles unsolved in the nominal budget. Across both architectures, latent-state motion drops sharply after the first exact solution. Completed states are typically locally contractive along the trajectory direction, even though the same local Jacobian retains strongly expanding directions. We characterize this phenomenon as trajectory-conditioned anisotropic stability. Perturbation experiments confirm this directional stability across both models. The multi-step fate of the maximally expanding direction differs: it is absorbed within 16 steps in the attention model but persists longer in the MLP model. The anisotropic-stability pattern also holds for a second attention checkpoint. Together, these results distinguish nominal-budget failure from completed computation and identify a common dynamical signature of completion across two recurrent architectures. --- ### Not Quite My Tempo: Voice Activity-aware Speech Synthesis for Lip-Synchronous Dubbing Authors: Alejandro Pérez-González-de-Martos, Florian Lux, Angelina Elizarova, Milana Shkhanukova, Andreas Kellner, Mattia Antonino Di Gangi Published: 2026-09-22 Categories: eess.AS, cs.AI arXiv: https://arxiv.org/abs/2609.26486v1 Automatic lip-synchronous dubbing requires a speech synthesis model to generate alternating voice and silence patterns in the target language that match the timing of the source clip precisely to ensure an optimal viewing experience. Prior works address this problem by conditioning the speech synthesis process on lip movements extracted from the video signal. In this work, we condition the speech generation on a binary voice-activity signal, which has a lightweight representation and can be produced in multiple ways. We show that the model follows the voice-activity signal with high accuracy while maintaining natural prosody and semantically appropriate pause placement within sentences, as demonstrated through extensive objective and subjective evaluations. By randomly masking this condition during training, we make the feature entirely optional during inference, allowing editors to enforce or relax lip-sync constraints when desired. --- ### From Token Importance to Conditional Removability: Rethinking Visual Token Pruning in Multimodal Large Language Models Authors: Shengli He, Yongchao Liang, Roumeng He, Junjie Zeng, Jiyuan He, Xin Fang, Can Wu, Li Zheng Published: 2026-09-22 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.26484v1 Training-free visual-token pruning often uses token importance, redundancy, or related selection criteria as proxies for safe removal. We show that these signals alone do not fully characterize removability, which is conditioned on both representation depth and the surrounding deletion set. Controlled interventions demonstrate that removing the same tokens at different depths produces substantially different downstream perturbations, while changing only the deletion context at a fixed depth alters candidate marginals and pruning-boundary decisions. These findings show that token importance alone cannot determine when a token is safely removable or how its removability changes under joint deletion. Motivated by this perspective, we propose CoRePrune, a training-free two-stage framework. Progressive Perturbation-Aware Visual Pruning refreshes deletion effects as visual representations evolve, while Set-Conditioned Refinement reevaluates candidate rescue benefits under the current deletion set after visual--text interaction. Across five multimodal large language model backbones covering standard images, high-resolution inputs, and video, CoRePrune preserves performance under aggressive token budgets. On Qwen3.5, with a final budget of 128 visual tokens, it retains 90.3% of dense-model performance while reducing aggregate prefill time by 51.0%. --- ### Behavior is Not Enough: A Mechanism-Based Evaluation of Social Norm Emergence in LLM Societies Authors: Rasika Muralidharan, Haewoon Kwak, Jisun An Published: 2026-09-22 Categories: cs.MA, cs.CL, cs.CY, cs.GT, cs.SI arXiv: https://arxiv.org/abs/2609.26481v1 Social norms cannot be identified from behavior alone: the same cooperative equilibrium may reflect shared expectations, strategic incentives, or simple imitation. Yet in multi-agent large language model systems, prior work largely treats behavioral convergence as evidence of norm emergence. In this work, we introduce an evaluation framework that measures agents' reported empirical and normative expectations in addition to behavioral convergence. Through controlled ablations, we test the effect of expectation elicitation and isolate two collective mechanisms central to theories of norm formation---social learning through interaction and social selection through network-based group formation. We further test the stability of these resulting dynamics under adversarial disruption across four LLM families. We find that eliciting expectations increases cooperative contributions, while social learning stabilizes behavior, and social selection reliably identifies cooperators but provides limited behavioral reinforcement. Following disruption, normative expectations and behavioral coordination recover differently. Together, these results show that similar cooperative outcomes can arise from different underlying social processes. By making expectations observable, our framework allows us to attribute each mechanism's contribution separately, offering designers of multi-agent systems a principled basis for selecting the social processes that sustain cooperation. --- ### FeatLens: Feature-Guided Dynamic Code Graph Construction and Retrieval for Repository-Level Code Generation Authors: Xutian Li, Bo Xiong, Yifeng Zhu, Kunze Li, Xianlin Zhao, Runbang Yan, Yanzhen Zou, Lu Zhang, Bing Xie Published: 2026-09-22 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2609.26480v1 Recent code generation research has moved from isolated function completion toward repository-level generation in existing codebases. To implement a target function correctly, an LLM must identify reusable repository dependencies such as existing functions, APIs, and cross-file definitions. Existing retrieval methods provide such context through code similarity search, persistent whole-repository graphs, or LLM-driven graph exploration, but often incur high graph construction, reasoning, and token costs. Feature-oriented methods offer a natural view of software functionality, yet they mainly support requirement decomposition, planning, or feature editing rather than code dependency retrieval. This paper presents \textbf{FeatLens}, a feature-guided dynamic code graph construction and retrieval approach for repository-level code generation. FeatLens builds a feature index that links natural-language feature descriptions to function-level code entities. Given a generation task, it dynamically constructs a task-specific seed graph from the feature index and applies semantic-structural graph reasoning with personalized PageRank to select a compact reasoning graph. This design replaces persistent whole-repository graph maintenance and LLM exploration with deterministic and lightweight dependency retrieval. Experiments on DevEval and EvoCodeBench show that FeatLens achieves the best DR@15 among sparse, dense, and graph-based baselines (0.501 and 0.460). On DevEval generation, it obtains the highest DIR@1, reaching 52.91\% with DeepSeek-V3.2 and 53.58\% with GPT-5-mini, while maintaining competitive Pass@1 and producing shorter code. Compared with the strongest graph-based baseline, FeatLens reduces graph nodes by 61.0\%, edges by 86.2\%, and total token overhead by 45.9\%, with no LLM tokens used during retrieval. --- ### PP-Net: A Hybrid Physical-Prior Neural Network for Scattered Light Removal in Biomedical Images on Embedded Devices Authors: Yongfei Guo, Tingjin Chu, Mengzhuo Liu, Hongwei Lou, Yuanhao Gong Published: 2026-09-22 Categories: cs.CV, cs.AI, cs.LG, eess.IV, eess.SP arXiv: https://arxiv.org/abs/2609.26474v1 Scattered light is common in biomedical images, yet its removal remains challenging. The difficulty arises from three aspects: first, aligned scattered-light-free biomedical ground truth is often unavailable; second, scattering is coupled with weak illumination and sensor-induced noise; and third, many learning-based restoration models are computationally expensive for embedded devices in Internet of Medical Things (IoMT) scenarios. To address these issues, this paper proposes PP-Net, a hybrid physical-prior neural network for biomedical scattered light removal. The proposed method consists of three components: DFN-Net suppresses sensor-induced noise, ASAP estimates the scattering map and recovers a physics-based prior map, and GF-Net refines the prior map by fusing it with the denoised observation. To reduce the dependence on paired biomedical ground truth, a progressive synthetic training and cross-domain transfer strategy is developed. Experiments show that the physical-prior branch improves the peak signal-to-noise ratio (PSNR) by up to 1.26 dB on paired synthetic benchmarks. Under joint noise-and-scattering degradation, PP-Net improves PSNR by more than 10.8 dB and the structural similarity index measure (SSIM) by more than 0.62 compared with representative baseline methods. On real W2S biomedical images, the proposed method reduces the average Natural Image Quality Evaluator (NIQE) score by 43.3\%. Edge deployment with RKNN conversion and INT8 quantization achieves an average inference latency of approximately 200 ms per $512\times512$ image over 360 test images. These results demonstrate that PP-Net provides an effective and deployable solution for microscopic imaging, endoscopic inspection, and edge-assisted biomedical analysis in IoMT scenarios. --- ### How to Estimate Whether You Have Found Several Needles in a Haystack: Measuring Calibration in Multi-Label Text Classification Authors: Sophie Henning, Georg Hofmann, Alexander Schulte, Alexander Fraser, Annemarie Friedrich Published: 2026-09-22 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.26468v1 A key factor in deciding whether to trust an automatic prediction is its confidence score, which should be calibrated to match the actual probability of the prediction being correct. Most confidence calibration metrics target binary or multi-class tasks, while multi-label calibration remains largely underexplored. Multi-label classification tasks, such as assigning medical codes to clinical notes or determining news topics, are usually dominated by a large number of negatives, i.e., labels that do not apply. We show that existing binning schemes to compute label-wise expected calibration error either underestimate the error, simply reflect label frequency, or suffer from many bins with very few instances. To achieve trustworthy label-wise calibration errors, we propose a new binning scheme that gives equal weight to positive and negative label assignments. Our empirical study demonstrates that in contrast to existing binning schemes, our new scheme results in meaningful estimates of calibration error in hierarchical and in extreme multi-label classification. We also show that calibrating confidence scores of large language models for multi-label predictions is an open challenge. Our detailed analysis lays the foundation for further research by providing a solid evaluation metric for measuring calibration in multi-label classification. --- ### Complementary Roles of Radiomics and Foundation Representations in Renal Cell Carcinoma Classification: A Comparative Study of 2D and 3D CT Encodings Authors: Yuan Liang, Sourav Bhattacharjee, Abraham Campbell Published: 2026-09-22 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2609.26463v1 Accurate preoperative subtype classification of renal cell carcinoma (RCC) from contrast-enhanced computed tomography remains clinically challenging. Radiomics provides structured tumour descriptors, whereas foundation representations offer transferable image features. However, it remains unclear whether radiomics still adds value beyond pretrained representations, and how 2D and 3D MedVAE encoders compare in this setting. We compared handcrafted radiomics, 2D MedVAE, 3D MedVAE, and their fusion for binary clear-cell RCC versus non-clear-cell RCC classification on KiTS23 under a unified preprocessing pipeline. Concatenation, cross-attention, and gated fusion were evaluated as representative integration strategies, and radiomics feature importance was analysed to support decision-centric interpretability. Fusion consistently improved discrimination over image-only MedVAE branches. The best overall performance was achieved by 3D gated fusion, with an AUC of 82.7\%, outperforming the best 2D fusion model (79.6%), the radiomics baseline (74.4%), and the single-modality MedVAE branches. Ablation analysis further showed clear gains of the full fusion model over both image-only and radiomics-only variants, indicating complementary contributions from radiomics and image representations. These findings suggest that radiomics remains relevant for RCC CT classification in the presence of foundation representations, and that its integration with MedVAE is more effective in the 3D setting. More broadly, the study supports a complementary role for radiomics and foundation representations in clinically meaningful imaging decision support. --- ### Reproducible AI Requires Reproducible Randomness Authors: Anthony Bertrand, Tom Schmitt, Engelbert Mephu Nguifo, David Hill Published: 2026-09-22 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.26461v1 Pseudorandom number generators (PRNGs) constitute indispensable computational tools across multiple scientific domains, including Monte Carlo simulations, stochastic computing, and artificial intelligence (AI). The reproducibility of such applications critically depends on the ability of PRNG implementations to generate identical sequences across software environments when initialized from the same internal state. These algorithms enable the simulation of stochastic processes while providing deterministic and repeatable behaviour, thereby facilitating reproducible experiments. Modern PRNG implementations may be initialized through either a seed or, more accurately, an initial state that exceeds the capacity of a conventional integer seed. However, reliance on a simple seed alone frequently proves insufficient to ensure consistent program execution traces across different implementations. A natural assumption is that transferring the complete internal state of a generator should guarantee identical outputs regardless of the software library used. This study examines the validity of this assumption by investigating whether complete initial states can ensure cross-library fidelity and portability of PRNG streams. We focus on two widely deployed generators, Mersenne Twister and Philox, and evaluate their implementations across four major Python ecosystems-Random, NumPy, PyTorch, and TensorFlow. We compare the sequences produced by these implementations against those generated by the original reference algorithms under identical initialization conditions. Our results demonstrate that reproducibility cannot be assumed from PRNG state transfer alone, even when implementations claim to follow the same underlying algorithm. While fidelity was successfully achieved for several implementations, significant discrepancies were observed in others. Most notably, the Philox implementation in PyTorch exhibits fundamental incompatibilities with the reference algorithm, preventing ex… --- ### Can We Predict Anomaly Detection Performance from Embedding-Space Geometry? Authors: Kevin Wilkinghoff, Zheng-Hua Tan Published: 2026-09-22 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.26460v1 Anomaly detection systems are often trained using normal data alone, while model selection and evaluation typically require labeled anomalies. We study whether anomaly detection performance can be predicted without access to anomalous data. For kNN-based detectors, we derive a lower bound on the area under the ROC curve (AUC) that relates detection performance to the separation between inlier and outlier scores and to their respective variances. Under a local scaling model, we use this bound to characterize how density variation, intrinsic-dimensional heterogeneity, and cross-domain mismatch contribute to score variability. We then investigate anomaly-free model selection and show that inlier score variance alone does not reliably predict performance across different representations. To address this limitation, we introduce simple pseudo-anomaly probes that provide a reference for estimating relative score separation. Experiments on the DCASE 2022-2025 benchmarks, spanning four embedding models and 208 candidate systems, show that pseudo-anomaly-based estimators substantially improve anomaly-free model selection. In particular, diverse pseudo-anomalies enable anomaly-free model selection to outperform conventional development-set selection under domain shift. These results show that embedding-space geometry contains predictive information about anomaly detection performance while also highlighting the representation-dependent nature of inlier-only performance estimates. --- ### Code Plans, Diffusion Renders: Open-Ended Generative World Modeling Authors: Zixun Fang, Yawen Shao, Kai Zhu, Jie Xiao, Shihan Chen, Yu Liu, Xueyang Fu, Yang Cao, Wei Zhai, Zheng-Jun Zha Published: 2026-09-22 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.26458v1 We introduce \textbf{CoDeR}, a new paradigm for world modeling. Unlike existing video world models that implicitly represent world dynamics through visual observations, our system explicitly constructs an executable world with code and employs video generation models for visual realization. Specifically, we coordinate five complementary roles to translate high-level concepts into structured world rules, executable dynamics, and perceptual observations. This design enables \textit{long-term memory}, \textit{open-ended interactions}, \textit{autonomous world evolution}, and \textit{multi-agent scenarios}, where multiple entities can act, interact, and evolve persistently beyond the current observation. Extensive experiments demonstrate that our framework substantially extends the capabilities of existing world models, enabling long-term memory, open-ended interactions, autonomous evolution, and persistent multi-agent dynamics, while achieving state-of-the-art performance across multiple evaluation settings. Code and model weights will be made publicly available. Project Page: \href{https://becauseimbatman0.github.io/CoDeR}{CoDeR}. --- ### Recursive self-improvement of AI research agents Authors: Dhruv Srikanth, Bingchen Zhao, Dixing Xu, Yuxiang Wu, Zhengyao Jiang Published: 2026-09-22 Categories: cs.AI, cs.LG, cs.SE arXiv: https://arxiv.org/abs/2609.26457v1 AI agents are beginning to automate research and development across the AI stack, from improving training efficiency to optimizing inference. A natural next step is to improve the research efficiency of the agents themselves. When an AI research agent's own code is the object of optimization, each accepted rewrite becomes the agent that the next round edits. We refer to this loop as recursive self-improvement. Its significance lies in a long-standing trend, in which increased cumulative spending on R&D yields diminishing returns. Sustained self-improvement offers a way to counter this trend. We present AIDE^2, a system that implements this loop for a frontier AI research agent. It proposes changes to its own code, benchmarks modified versions of itself on a suite of AI R&D tasks, and keeps the changes that perform best on hidden evaluations. In an autonomous 8-day run, AIDE^2 discovered seven successive improvements, ranging from a new search policy to memory mechanisms that compress and manage the agent's growing context. These gains generalize to four held-out benchmarks spanning machine learning engineering, heuristic algorithm engineering, and physics-based weather forecasting, the last of which is out of distribution from the selection tasks. On all four, the strongest discovered agent matches or exceeds a human-engineered production research agent that ranks among the strongest on FML-Bench. On a separate held-out task family, the discovered agents also exhibit reduced reward hacking, a property the loop never explicitly optimized for: the rate falls from 55% to 32% during the run, 7 percentage points below the human-engineered agent. Together, these results show that an AI research agent can improve its own research efficiency through recursive self-improvement, and that these gains transfer to tasks and domains the loop never encountered. --- ### A Practical Guide on Graphical Model Validation Authors: Mario V. Wüthrich Published: 2026-09-22 Categories: stat.ML, cs.LG, q-fin.RM arXiv: https://arxiv.org/abs/2609.26445v1 This manuscript formalizes the most popular model validation tools used in general insurance actuarial modeling. These include graphical tools like calibration plots, actual-vs-expected plots, lift charts, Murphy diagrams, as well as classical statistical tools such as Bregman losses, deviance losses, elementary losses, Murphy's decomposition and Gini scores. Particular emphasis is placed on whether calibration and discrimination are studied under a policy-weighted or an exposure-weighted population measure. This distinction is crucial in ensuring that premium schemes are calibrated on the correct scale. --- ### Mammo-LIFE: Longitudinal Mammographic Imaging and Clinical Feature Enrichment for Post-Radiotherapy Outcome Prediction Authors: Farnoush Bayatmakou, Maryam Hosseini, Reza Taleei, Arash Mohammadi Published: 2026-09-22 Categories: cs.CV, eess.IV arXiv: https://arxiv.org/abs/2609.26443v1 Recent advances in Artificial Intelligence (AI)-powered Computer-Aided Diagnosis (CAD) systems have substantially improved breast cancer screening, diagnosis, and prognosis. Comparatively, postradiotherapy outcome prediction using paired longitudinal mammograms has received considerably less attention. This is largely due to the limited availability of well-annotated longitudinal datasets. Longitudinal mammograms, coupled with paired pre- and post-treatment information, provide a unique opportunity to characterize treatment-induced breast tissue changes following radiotherapy. The resulting learned representations can serve as a valuable asset for advancing personalized radiotherapy planning and post-treatment management. In this context, we propose Mammo-LIFE, a patient-level multimodal framework for post-radiotherapy outcome prediction that combines longitudinal mammographic features with patient-level clinical variables. The imaging branch processes paired pre- and post-treatment mammograms acquired from the four standard views using a mammography-specific encoder adapted via Low-Rank Adaptation (LoRA). Within each view, preand post-treatment representations are explicitly compared through a longitudinal comparison module to capture treatment-related changes. The resulting view-level embeddings are then aggregated using learned view-attention pooling to form a unified patient-level mammographic representation. Selected clinical variables are subsequently combined with the image-derived prediction probability through a late-fusion strategy. To evaluate the effectiveness of combining paired longitudinal mammograms with clinical information, experiments were conducted on an in-house clinical cohort using patient-level stratified five-fold cross-validation. --- ### One-Step Generative Surrogate Models via Block-Triangular Joint Drifting Authors: Nicholas Geissler, Shreya Jha, Ricardo Baptista, Benjamin Peherstorfer Published: 2026-09-22 Categories: cs.LG, math.NA arXiv: https://arxiv.org/abs/2609.26435v1 Drifting provides a direct route to one-step generative models, but applying it directly to stochastic transition modeling requires multiple samples of the next state conditioned on the same current state. Standard trajectory data, however, typically provide only one realized next state for each observed current state and therefore do not provide an empirical approximation of the corresponding conditional distribution over possible next states. We introduce block-triangular joint drifting, which instead applies a projected drift field to the empirically accessible joint distribution of consecutive states. Importantly, the block-triangular architecture preserves the current-state marginal while making its second component a direct sampler of the conditional distribution of possible next states. The resulting surrogate generates stochastic trajectories with one model evaluation per time step, without auxiliary generative steps between time steps. Numerical experiments demonstrate accurate marginal and trajectory-dependent statistics and favorable accuracy-cost tradeoffs compared with deterministic, diffusion-, flow-, and distillation-based generative surrogate models. --- ### Latent Dataset Distillation for Human Motion Prediction Authors: Ge Tian, Guang Li, Takahiro Ogawa, Miki Haseyama Published: 2026-09-22 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.26430v1 Dataset distillation (DD) compresses a large training set into a compact synthetic set while preserving downstream training utility. Although DD has been widely studied for images and recently extended to time-series forecasting, its application to human motion prediction remains largely unexplored. Human motion is high-dimensional and structurally coupled, and gradient matching (GM) in the original motion space optimizes many correlated variables without a prior on pose plausibility or temporal dynamics, which frequently yields implausible and unstable synthetic motions. To address this limitation, we propose a latent DD framework that regularizes distillation with a learned motion prior. Motions are first compressed by a residual-quantized variational autoencoder (RVQ-VAE), and distillation then updates only a learnable latent bank through the frozen quantizer and decoder. The pretrained decoder restricts synthetic motions to its output space, while residual quantization progressively refines the latent approximation across multiple codebooks and alleviates the representational bottleneck of single-stage vector quantization. Experiments on Human3.6M, CMU, and 3DPW with two prediction backbones show that the proposed framework outperforms direct GM in 27 of 30 evaluated settings and random subsets in every setting, and produces visibly more plausible synthetic motions in qualitative comparisons. --- ### The Source of Disturbance Matters: External, Internal, and Control-Generated Noise in Adaptive Regulation Authors: Veronique Ziegler Published: 2026-09-22 Categories: cs.AI, eess.SY, nlin.AO arXiv: https://arxiv.org/abs/2609.26428v1 Adaptive regulation can itself perturb the state it is intended to stabilize. In replicated simulations of an adaptive agent, we compare external disturbance, persistent internally generated disturbance, and control-generated disturbance under regulation-first and disturbance-first ordering. Persistent internal disturbance produces the largest exposure and regulatory burden within the tested parameter grid. When positive controller updates generate an immediate disturbance cost, increasing that cost produces a nonmonotonic response: effective disturbance initially rises, variability across stochastic runs increases over an intermediate range, and corrective activity becomes strongly suppressed at higher costs. The results show how disturbance source and timing shape exposure and controller burden in this model. They motivate testing adaptive agents with distinct disturbance sources and assessing regulatory activity alongside exposure. --- ### DeepFEAv2: Deep Learning for Transient Finite Element Analysis Beyond Structured Meshes Authors: Georgios Triantafyllou, Panagiotis G. Kalozoumis, Dimitris K. Iakovidis Published: 2026-09-22 Categories: cs.LG, cs.AI, cs.CE arXiv: https://arxiv.org/abs/2609.26426v1 Finite Element Analysis (FEA) is widely used for transient mechanical simulations, but its high computational cost limits real-time and high-resolution applications. Deep learning surrogate models can reduce this cost; however, many existing approaches are restricted to steady-state prediction or cannot jointly predict Node- and Element-based Outputs (NEO) over time. The state-of-the-art DeepFEA framework has addressed these issues but remains limited to structured finite element (FE) meshes. To overcome this limitation, this study proposes DeepFEAv2, a deep learning surrogate framework that enables prediction of transient FEA simulations across different FE mesh topologies and element types. The main contributions of DeepFEAv2 are: (a) a module that uses the FE connectivity matrix to organize input features by element and arrange them into an input sequence guided by the mesh topology; (b) a novel neural network architecture designed to process the input sequence and jointly predict NEO over time; and (c) a FEA-informed optimization strategy for regularizing these NEO predictions. DeepFEAv2 was evaluated on structured and unstructured 3D linear elastic datasets, as well as on a pressure-driven aortic valve dataset. DeepFEAv2 achieved R^2 values up to 0.99 and normalized errors as low as 0.38%. Compared with DeepFEA, it achieved up to 38.0% relative increase in R^2 and up to 87.1% reduction in normalized error. DeepFEAv2 also performed inference up to three orders of magnitude faster than traditional FEA. These results demonstrate that DeepFEAv2 can efficiently model transient FEA simulations across increasingly complex FE settings, providing a scalable surrogate framework for transient FEA. --- ### QuantWM: Temporally Consistent 2-Bit KV Cache Quantization for Video World Models Authors: Jiaqi Zhao, Xiaobin Hu, Bo Yin, Junpeng Jiang, Miao Zhang, Shuicheng Yan Published: 2026-09-22 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2609.26425v3 Video world models achieve long-range temporal consistency by storing KV cache during generation, but the growing cache makes KV cache memory a major deployment bottleneck, which motivates low-bit quantization study for efficiency. Existing 2-bit KV cache quantization methods can achieve nearly lossless performance on VBench, however, when applied to video world models, we find they still cause severe temporal flickering and visual degradation. Meanwhile, deeper investigates show that Key quantization produces smaller reconstruction errors than Value, but surprisingly leads to larger output degradation. We trace this discrepancy to attention in video world models: Key perturbations can change the attention logits, and shift the temporal-spatial tokens selected by Queries. These observations motivate us to preserve attention logits and temporal-spatial token selection during KV cache quantization. To address this issue, we present QuantWM, a training-free 2-bit KV cache quantization framework for video world models. QuantWM introduces two complementary techniques to mitigate the attention shifts. Firstly, quantization-sensitivity-aware clustering (QSAC) jointly considers historical Query sensitivity and residual ranges to select INT2-friendly Key centroids, which reduces quantization errors in channels that are more critical to attention. In addition, principal-subspace attention compensation (PSAC) restores the remaining Key errors along the dominant Query subspace using low-rank projections, which provides a direct and efficient correction to stabilize attention logits. Experiments on LingBot-World-v2, HY-World 1.5, Matrix-Game-2, Longcat-Video and Causal-Forcing demonstrate that QuantWM significantly improves visual quality and temporal consistency, while outperforming existing methods across benchmarks with up to 6.20 KV cache memory compression and limited additional overhead. --- ### Enriching Speech Emotion Representations with Conversational Context Authors: Arthur Peuvot, Romaric Besançon, Gaël de Chalendar, Bianca Vieru, Ioana Vasilescu Published: 2026-09-22 Categories: cs.CL, eess.AS arXiv: https://arxiv.org/abs/2609.26422v1 Detecting emotions is necessary for building systems that can accurately and adaptively interact with humans. Speech Emotion Recognition (SER) has become an important research focus to develop intelligent spoken interfaces. However, most studies predict emotions at the utterance level, ignoring the conversational context, along with the emotional flow and speaker interactions it carries. In this paper, we introduce ACERT (Averaged Contextual Emotion Representation through Time), a module that integrates a flexible-length window of conversational context to better capture emotional evolution in spoken interactions. To evaluate the robustness of this method, we conducted experiments on datasets spanning diverse emotionally expressive styles and contexts. ACERT outperforms current state-of-the-art (SOTA) approaches on IEMOCAP, establishes the first context-aware benchmark on SAFE, and obtains strong results on MELD for unweighted, class-balanced metrics. Ablation studies show that ACERT's gains come from emotional and conversational continuity, rather than from speaker identity or acoustic conditions. --- ### Sample, Simulate, Select: Physics-in-the-Loop Text-to-Motion for Humanoids Without Training Authors: Raphael Memmesheimer, Sven Behnke Published: 2026-09-22 Categories: cs.RO, cs.CV arXiv: https://arxiv.org/abs/2609.26420v1 Text-to-motion models generate plausible human motion but do not model a robot's dynamics; whole-body tracking controllers execute robot references reliably but cannot replan an infeasible one. Recent language-to-humanoid systems bridge this gap by training. We measure how much of the gap closes with no training at all, by putting the deployment controller itself in the loop. Sample-simulate-select (S$^3$) draws $N$ motions per prompt from a frozen text-to-motion model, retargets each to a Unitree G1 by direction-matching inverse kinematics, rolls all of them out under full rigid-body dynamics with the pretrained SONIC tracking policy, and keeps the candidate the policy executed best. Because the verifier is the deterministic simulator itself, S$^3$ attains the any-of-$N$ ceiling by construction; what we measure is where that ceiling lies and what falls short of it. On 200 stratified HumanML3D test prompts with $N=8$, upright execution rises from 83.5% to 89.5% and hardware-gate passes from 33 to 85; on the complete test split (4,184 prompts) it rises from 80.5% to 89.5%. A kinematic verifier that predicts falls well (AUROC 0.90) recovers only a quarter of this gain: ranking a prompt's own candidates is harder than classifying the population. What selection cannot fix is one class, prompts that lower the pelvis, which a generator trained on retargeted robot data does execute. We further score the semantic fidelity of the executed motion with the standard text-motion evaluator, with a real-mocap control that attributes the loss to the robot projection, ablate the retargeter against GMR (complementary failures: the any-of-8 ceiling rises to 95.0% over both), and execute all 177 gate-selected clips on the real G1: every one completes standing, with hardware tracking error matching simulation ($r=0.94$). --- ### Reliability Theory for AI Control Authors: Grant Molnar Published: 2026-09-22 Categories: cs.AI, math.OC arXiv: https://arxiv.org/abs/2609.26419v1 Reliability theory gives a mature language for layered systems, but its formal tools are not yet standard in frontier AI control. We apply them to Google DeepMind's defenses against rogue deployment. The same control stack can have cubic, quadratic, or linear rare-failure suppression depending on its failure domains. Birnbaum importance identifies which component improvements buy the most nominal reliability, while prevention changes the population on which recovery is demanded. These results give concrete guidance about what to separate, improve, measure, and test. --- ### SuperPCA: subspace analysis and an efficient algorithm for high-dimensional PCA Authors: Irina-Beatrice Haas, Maike Meier, Yuji Nakatsukasa, Taejun Park Published: 2026-09-22 Categories: stat.ML, cs.LG, math.NA, stat.CO arXiv: https://arxiv.org/abs/2609.26406v1 Principal component analysis (PCA) is a fundamental tool to reduce the dimensionality of the data in many applications. PCA finds a few signal directions that contain most of the variability of the data by computing the eigenvectors of the sample covariance matrix. In this work, we focus on the spiked covariance model, in which the data vectors are defined by a few orthogonal signals plus an isotropic Gaussian noise, and our goal is to estimate one or more of the leading signals. Our main theoretical finding is that the subspace spanned by several leading eigenvectors of the sample covariance matrix contains significant information about the desired signals long before the individual eigenvectors converge to the population principal components. To prove this, we derive a posteriori bounds for the angle between the subspace spanned by the desired population signals and the subspace obtained from the sample using perturbation theory for singular vectors. This leads to a new algorithm, SuperPCA (SUbsPace subsamplER PCA), which capitalizes on an approximate eigenspace of the sample covariance matrix to find the leading signals far more efficiently and accurately than classical PCA in the high-dimensional, multi-signal setting. SuperPCA exploits only a small number of subsampled coordinates of the data, which can lead to tremendous savings in data acquisition cost, especially when the signals are approximately sparse. For the same number of measurements, SuperPCA can offer a factor $10$ improvement in accuracy compared to the classical PCA method. --- ### OMatG-flash: An All-Atom Flow Map with Reinforce Adjoint Matching for Scalable Materials Discovery Authors: Thomas Egg, Harry Winston Sullivan, Ellad B. Tadmor, Stefano Martiniani Published: 2026-09-22 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.26402v1 The discovery of novel inorganic materials drives technological breakthroughs in critical fields such as computing and energy storage. Generative AI has promised to accelerate the materials discovery pipeline, but state-of-the-art flow and diffusion models remain bottlenecked by the cost of proposing candidate materials. To address this, we introduce OMatG-flash, an all-atom flow map for inorganic crystal structure prediction (CSP) and de novo generation (DNG). OMatG-flash is a Pareto-optimal inference engine for materials, sampling candidate materials with an order of magnitude fewer inference steps and less wall-clock time than existing flow and diffusion models while demonstrating benchmark performance on par with the state-of-the-art. To enable post-training fine-tuning we apply Reinforce Adjoint Matching to flow maps, further improving match rates and RMSE on the unconditional CSP task. OMatG-flash showcases the potential of flow maps to accelerate generation of high-quality candidate inorganic materials and demonstrates a step forward in sample throughput necessary for data-hungry materials discovery workflows. --- ### Combining Hierarchical Cognitive Process with Process Supervision for Interpretable Scene Safety Understanding Authors: Zhiyun Jiang, Hanyong Wang, Binbin Liang, Yu Xie, Zhengjie Wang, Menglong Yang, Wei Li Published: 2026-09-22 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.26399v1 Scene safety understanding plays a life-or-death role in situational awareness in various critical domains. Traditional methods that rely on learning direct mappings between scenes and safety levels often lack interpretability, limiting their reliability in critical applications. An effective approach to overcoming this challenge lies in interpreting human cognitive processes and equipping machine models with analogous cognitive capabilities. This work explores an effective way of integrating scene safety cognitive process modeling and process supervision. Specifically, we first construct a hierarchical cognitive safety structure, which motivates the development of a novel, high-quality scene safety understanding dataset based on multi-step reasoning with process labels. This dataset serves both as a benchmark and a resource to improve the safety reasoning capabilities of Large Language Models (LLMs), while also enabling a granular analysis of intermediate reasoning steps through information flow and saliency-based techniques. Building upon this foundation, we introduce a modular and flexible process supervision framework that reflects the hierarchical nature of human cognition. This framework leverages LLMs as the core architecture and incorporates Low-Rank Adaptation(LoRA) and Mixture-of-Experts (MoE) strategies to enable specialization and collaboration among expert modules, each tasked with specific sub-processes of the overall reasoning chain. Systematic experimental evaluations and analyses confirm that our framework exhibits superior interpretability and performance characteristics compared to traditional approaches. --- ### Double Descent and Malign Overfitting in Diffusion Models Authors: Raphaël Urfin, Tony Bonnaire, Giulio Biroli, Marc Mézard Published: 2026-09-22 Categories: cs.LG, cond-mat.dis-nn arXiv: https://arxiv.org/abs/2609.26392v2 Conventional wisdom in deep learning holds that overparameterization---having more parameters $p$ than training samples $n$---is benign: larger models generalize better and, even without regularization, interpolating models generalize well, the test error following a double-descent curve. One might expect the same benign overfitting for diffusion models, whose training reduces to regression, i.e. to minimizing a quadratic score-matching loss. Yet the opposite is observed: overfitting here is catastrophic, driving the model into a memorization regime. We resolve this paradox by combining experiments on U-Nets trained on CelebA with a random-features model for which we derive closed-form learning curves. We show that with a fixed number $m$ of noise realizations per training sample, an interpolation peak does occur, but at $p\sim nm$ rather than at $p\sim n$ as in standard regression. The rise of the test loss, however, sets in much earlier, at $p\sim n$, independently of $m$. This overfitting is malign because, although the implicit regularization of training is fully at work, it drives the model toward the empirical score, which memorizes the training set, rather than toward the true score. A bias-variance decomposition pinpoints the mechanism: the bias of the score estimator starts to grow at $p\sim n$; past the peak the variance decays, as in regression, whereas the bias keeps growing and both saturate at a large value. Since diffusion models are trained with $m\gg1$, the peak is pushed to very large model sizes, and therefore sit on the rising branch that precedes it, where malign overfitting is already in play. Nevertheless, overparameterization remains beneficial when paired with regularization: in the random-features theory and in U-Net experiments, optimally regularized large models---via a ridge penalty or early stopping, respectively---outperform any unregularized models. --- ### TimeInteract: Towards Real-Time Interactive Intelligence for Streaming Time Series Authors: Sheng Pan, Yongli Gu, Yiqing Guo, Warren Jin, Bo Du, Shirui Pan, Ming Jin Published: 2026-09-22 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2609.26389v1 Real-world time series evolve continuously, with meaningful changes potentially emerging at any moment. However, existing time-series language models (TSLMs) remain inherently static. They either receive complete sequences for offline processing or alternate between streaming input and response generation, which prevents processing of new observations during interaction. We introduce a new regime, Time-Series Interaction: a model continuously perceives incoming time-series observations and user intent, autonomously decides when to remain silent or respond, and continues processing new observations during response generation. To realize this, we develop TimeInteract with three key designs: a dual-view streaming TS encoder that captures local variations and historical dynamics, a response control mechanism that learns when to trigger a response, and a decoupled streaming inference mechanism that separates control from response generation to avoid blocking subsequent observations. We further formulate a hierarchy of interaction capabilities, progressing from Understanding to Adaptivity. Based on this hierarchy, we construct StreamTSI-34K, a large-scale streaming TS interaction dataset with 34,588 episodes and 77,505 responses across synthetic and real-world time series in single- and multi-turn settings. Across all four interaction levels, TimeInteract consistently outperforms existing LLMs, VLMs, and TSLMs, with gains of up to 23.92 points on challenging tasks. It also improves response triggering while achieving near-zero stream stall and up to $2.15\times$ inference speedup. --- ### On the Lexical Superstition of Large Language Models for Code Comprehension: Re-evaluation on Code of Low Lexical Quality Authors: Xin Shen, San-Zhuo Xi, Yali Du, Ming Li Published: 2026-09-22 Categories: cs.SE, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2609.26388v1 Recent advances in large language models (LLMs) have made them widely used for code-related tasks. Identifier names are statistically informative in naturally occurring code, but their information is not always reliable. We investigate whether current LLMs assign disproportionate weight to lexical cues when renaming preserves program structure. We introduce Face/Off, a semantics-preserving identifier-renaming framework, and evaluate progressive naming conditions across multiple models and code-comprehension tasks. Within this framework, lexical overemphasis is pervasive across the evaluated models and primary tasks: performance generally decreases as identifier information is removed or made misleading, and outputs are often directed toward the meanings suggested by misleading names. The pattern persists under representative prompt- and fine-tuning-based interventions, suggesting that lexical overemphasis is an entrenched problem. A type-inference control confirms a boundary: naming effects are smaller when the answer is locally recoverable without the target name. These results do not imply that identifiers are unhelpful; rather, they reveal a systematic vulnerability in how current LLMs balance lexical cues against program structure. Our findings motivate evaluations and modeling methods that preserve the benefits of natural code regularities while keeping conclusions grounded in accurate, formalized code semantics. --- ### Learning to Defer with Guidance on Real World Medical Data Authors: Emma Sun, Joshua Strong, Alison Noble Published: 2026-09-22 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.26384v1 Medical image interpretation is high-volume and time-consuming, and while AI interpretation can reduce workload, fully autonomous deployment carries potential safety concerns and low specificity may in practice lead to increased clinician workload. Learning to Defer (L2D) addresses this by selectively routing cases between autonomous prediction and human experts by learning from input features and AI model and human performance. While theoretical guarantees have been proven for L2D, its performance has not been validated on real-world medical datasets with human reader annotations. We evaluate the predictor-rejector formulation of two-stage L2D, where the AI predictor model is fixed and separate from the trainable routing or rejector model, on Collab-CXR, a multilabel chest X-ray dataset with multiple human annotations per case. This is the first work to look at L2D in the context of real-world medical imaging data with human annotations. We further introduce a new setup, L2D with Guidance, where the decision space is extended to three choices: predict autonomously, defer to a human expert, or defer to a human expert and provide AI guidance. We compare multiple rejector architectures and loss functions, and different input feature availabilities. This is reproduced on two larger datasets, VinDr-CXR and CheXpert. Our results show that two-stage L2D with Guidance outperforms classic two-stage learning to defer, as well as human-alone, AI-alone and AI-guided human baselines. Notably, this performance is achieved with simpler loss functions compared to formally defined L2D surrogate loss functions in current literature. ---