# Research Papers — 2026-09 · bundle page 262 of 266 > Full-text markdown of papers #13051–13100 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/262 [← Previous bundle](https://aipod.dev/papers/archive/2026-09/page/261.md) [Next bundle →](https://aipod.dev/papers/archive/2026-09/page/263.md) ### Hints Help But Do They Teach? Evaluating Skills Transfer in Code Generation Authors: Will Badr Published: 2026-09-01 Categories: cs.SE, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2609.01106v1 When a hint turns a failing generated program into a passing one, does it provide missing information or merely steer the model toward a solution it could already produce? We test these hypotheses on HumanEval+ and MBPP+ using executable evaluation. For Qwen2.5-3B-Instruct, adaptive relevant hints rescue 36 of 79 selected failures; an unrelated hint rescues 19, while eight unhinted samples solve 46 and recover 31 of the 36 relevant-hint rescues. Phi-3.5-mini shows the same pattern: relevant hints rescue 42 of 101 failures, an unrelated hint rescues 17, and unhinted sampling solves 57, including 36 of the 42 relevant-hint rescues. Because the hint conditions use different attempt budgets, these comparisons do not isolate a purely semantic effect. Mechanistic tests on Qwen identify a stable activation direction shared by relevant and unrelated hints. Persistently adding this direction yields 14 rescues and 18 regressions, with no detectable net accuracy gain; learned low-rank interventions have a positive but imprecise estimated effect. Full textual specifications solve 22 of 24 context-defined problems, versus 5-11 for tested virtual-KV prefixes. Post-generation hidden-state probes transfer across benchmarks, with pooled AUROC 0.806 and 0.780, but their top-one selection advantage over token confidence is statistically unresolved. Overall, relevant hints can rescue failures, but most rescued solutions are already reachable through ordinary sampling, and the internal interventions tested here do not establish task-general capability transfer. --- ### When Modality Gap Reduction Fails: Prediction-Level Hubness in CLIP Authors: Shota Sato, Hajime Kiyama, Tosho Hirasawa, Mamoru Komachi Published: 2026-09-01 Categories: cs.CL, cs.CV arXiv: https://arxiv.org/abs/2609.01103v1 Reducing the modality gap between image and text representations in CLIP is widely expected to improve cross-modal alignment and downstream performance. However, a smaller average image-text gap does not necessarily lead to consistent accuracy gains. We analyze this mismatch from the perspective of the decision structure in zero-shot classification, i.e. selecting the most similar class-text prototype for an input image. Zero-shot accuracy depends not only on average image--text alignment, but also on class-wise decision margins. Using Linear correction as an analytically tractable case, we show that modality gap correction can alter the relative decision structure among classes and cause predictions to concentrate on a small subset of classes. We refer to this output-space failure mode as prediction-level hubness. Furthermore, experiments across multiple datasets show that accuracy degradation under gap correction is consistently associated with increased prediction concentration, both for Linear correction and for learning-based correction methods. This provides a systematic explanation of why modality gap reduction does not consistently improve CLIP zero-shot accuracy from the perspective of downstream decision structure. Our results suggest that gap correction should be evaluated not only by average alignment, but also by its impact on downstream prediction structure. --- ### Neural Symbollic Regression Using Deep Learning and Sparse Modelling Authors: Ravi Kumar U, Sumitra S Published: 2026-09-01 Categories: cs.LG, cs.AI, cs.NE, cs.SC arXiv: https://arxiv.org/abs/2609.01102v1 Symbolic Regression (SR) seeks to find succinct mathematical expressions that represent the fundamental relationships within data, providing interpretability and scientific understanding that exceeds that of black-box models. Nevertheless, traditional methods like Genetic Programming face challenges with scalability and are highly sensitive to noise, while sparse regression techniques such as SINDy rely significantly on predetermined feature libraries. In this work, we present a Neural Symbolic Regression (NSR) framework that treats neural networks as functional preconditioners for symbolic discovery. Our approach uses a decoupled pipeline: a neural network first learns a smooth, noise-robust approximation of the target function in an interaction- aware nonlinear feature space. LASSO is then applied to extract sparse, interpretable closed-form expressions. To improve predictive accuracy and symbolic fidelity by integrating distributed hyperparameter optimization with Ray Tune and ASHA scheduling. Experiments on the Nguyen benchmark suite show that our approach consistently outperforms SINDy and non-tuned neural baselines in RMSE, noise robustness, and out-of-distribution generalization. Ablation studies confirm the significance of feature interactions, neural depth, and tuning strategies. In general, this study presents a scalable and understandable neural-symbolic framework, creating a solid link between neural approximation and the discovery of sparse equations for scientific machine learning. --- ### Beyond Magnitude: Contrastive Routing for Modular Mixture-of-Experts Authors: Nikolaos Xiros, Dimitrios Damianos, Maria-Eleni Zoumpoulidi, Leon Voukoutis, Vassilis Katsouros, Georgios Paraskevopoulos Published: 2026-09-01 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.01100v1 In current Mixture-of-Experts architectures, routing is performed based on representations dominated by structure shared across all tokens, limiting expert specialization. We show that contrasting each token against an Exponential Moving Average of the layer's hidden states, rather than routing on absolute magnitude, concentrates the routing signal onto a low-dimensional, highly separable subspace. Building on this, we propose the Contrastive Routing Mechanism (CoRM), which scores each expert by the gap between its affinity for the incoming token and its affinity for this shared reference state, interpreted through a distinct per-expert projection. The resulting experts have routing boundaries that align with linguistic structure significantly more than the Top-k baseline. Our experiments show that CoRM improves average zero-shot accuracy by +0.67 to +1.69 points (Top-1) and +1.38 to +1.77 points (Top-2) over standard Top-k MoE baselines on nine zero-shot reasoning benchmarks, at the minimal cost of 2.9% added parameters and 2.6% added FLOPs per token. --- ### IT-TextFusion: Iterative Text-Image Interaction with Text-Guided Residual Refinement for Degradation-Aware Image Fusion Authors: Siyang Liu, Peiyi Zhou, Tianle Jin, Rongrong Bian, Zheke Jin, Mengze Gao Published: 2026-09-01 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.01092v1 Text-guided image fusion has recently emerged as an effective paradigm for integrating multi-modal information while enabling flexible and task-oriented fusion control. However, existing text-guided fusion methods often rely on shallow semantic-visual interaction and limited attention mechanisms, which restrict their ability to robustly handle complex degradations and fully exploit textual guidance. In this paper, we propose an iterative text-guided image fusion framework that incorporates text-conditioned feature interaction across multiple fusion and refinement stages. The proposed method integrates deepest-level Cross-Attention, multi-scale Cross-Gate Fusion, and stage-specific text-conditioned modulation, allowing the global text embedding to condition hierarchical feature fusion and residual refinement. By repeatedly injecting the pooled text embedding across hierarchical decoder and refinement stages, the proposed framework provides degradation-aware global semantic conditioning while preserving complementary information from the visible and infrared modalities. Experiments on several benchmark datasets show that the proposed method improves several information-preservation and perceptual-quality metrics, while exhibiting metric-dependent trade-offs on some datasets. --- ### Subliminal Learning as Trait-Direction Drift: A Mechanism and Targeted Control under SFT Distillation Authors: Zhixuan Liu, Zhichen Dong, Yuyu Fan, Xiangtian Li, Chao Yang Published: 2026-09-01 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.01091v2 Beyond intended capabilities, model distillation can transfer hidden traits from a teacher. A teacher biased by a system prompt can generate semantically clean training data, such as numeric sequences, that still causes a downstream student to inherit the hidden preference, a phenomenon known as subliminal learning. Prior work has identified several parts of this process. How the signal builds up during training and produces behavioral transfer remains unclear, making targeted mitigation difficult. We propose and validate trait-direction drift as a mechanism for subliminal learning: biased generation creates measurable preference gaps in teacher data, and student-recognizable gaps induce trait-aligned updates during supervised fine-tuning that accumulate into behavioral transfer. Guided by this mechanism, we propose probe-space corridor regularization, a targeted defense that constrains drift along a calibrated trait direction during distillation. The method substantially reduces hidden-trait transfer, preserving task performance: for example, it lowers malicious-response transfer from 29.55% to 6.45% with low main-task accuracy cost, and consistently suppresses animal-preference transfer across the main Qwen setting. The preference-gap, training-trajectory, and intervention evidence links subliminal learning to trait-direction drift and motivates corridor regularization as a targeted control during distillation. --- ### Modelpedia: A Catalog of Model Findings for the Meta-Science of AI Authors: Franciszek Bernat, Dawid Płudowski, Michał Jan Włodarczyk, Luca Longo, Jianlong Zhou, Andreas Holzinger, Riccardo Guidotti, Wojciech Samek, Przemysław Biecek Published: 2026-09-01 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.01090v2 Scientific knowledge about AI models is produced faster than the community can organize it. Every few months a new foundation model reshapes the field and hundreds of papers, blogs, and technical reports document how each behaves or fails. Yet, these findings remain scattered and effectively unretrievable. To address this gap we present Modelpedia, an automated, LLM-assisted framework that extracts findings about models from published papers, links it to the model, dataset, method, and concept it concerns, and aggregates the result into a searchable public catalog. Applying the prototype to accepted ICLR 2024 and 2025 papers, we extract over a thousand findings and, treating the catalog itself as an object of study, run a meta-analysis of how the community investigates models. Now, we invite the community to explore, contribute to, and build on the open catalog, and to help establish model findings as a shared foundation for the meta-science of AI. --- ### StateSwap: Probing Support-Elimination Hidden States in Multiple-Choice Questions Authors: Chao Gao, Haijiang Liu, Qiyuan Li, Caicai Guo, Frank van Harmelen, Jinguang Gu Published: 2026-09-01 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2609.01081v2 Large language models often answer the same multiple-choice question inconsistently when it is posed under support-oriented and elimination-oriented framings. We investigate whether these discrepancies arise from different internal representations induced by the two framings. We introduce a dual-framing protocol with minimally varied prompts that use either support- or elimination-oriented framing while keeping the evaluation target fixed. To probe the internal computation, we append an untrained special token, (STATE), and treat its residual-stream activation as an intervention interface. Across both models, the two framings induce separable (STATE) activations concentrated in intermediate layers. Swapping these activations between paired prompts systematically changes predictions and improves cross-framing agreement, providing intervention-based evidence that the activations are behaviorally relevant. Beyond instance-level substitution, mean-difference steering directions derived from the dual-framing contrast exhibit more bounded layer-wise responses than matched contrastive activation addition directions under the evaluated protocol. --- ### Text-guided flow matching enables sample-efficient crystal structure generation Authors: Wentao Li Published: 2026-09-01 Categories: cond-mat.mtrl-sci, cs.AI arXiv: https://arxiv.org/abs/2609.01076v2 Crystal generators can now propose periodic structures, but their control interfaces remain poorly matched to the mixed descriptors used in materials design. Text provides a compact way to combine composition, symmetry, prototype and property cues, yet it has not been clear whether such information can steer flow-based crystal generation. Here we introduce TFMat, a text-conditioned flow-matching framework that uses structured materials language as a semantic prior for a CrystalFlow generator. Across Perov-5, Carbon-24 and MP-20 crystal structure prediction benchmarks, TFMat improves one-candidate match rates over CrystalFlow and reaches a 92.04% MP-20 match rate with 20 candidates; in de novo generation, it improves element-count and density distribution alignment while retaining coarse property consistency in composition-selected outputs. These results position structured text as an inspectable control layer for translating human-readable materials intent into candidate crystals for downstream simulation and validation. --- ### Post-hoc Alignment of LLM-judges to Human Judgment Distribution Authors: Sebastian Steindl, Nikos Voskarides, Alberto Gasparin, Diego Marcheggiani Published: 2026-09-01 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.01073v1 The LLM-as-a-judge (LLMaJ) framework offers a cost-effective and reproducible solution for automatic evaluation. However, current evaluation practices typically compare LLMaJ judgments against aggregated ground-truth labels, overlooking the valuable information contained in Human Label Variation (HLV). Inspired by an increasing line of work that proposes to leverage HLV, we systematically study LLMaJ performance on predicting both a single, aggregated ground truth hard-label and unaggregated soft-labels that represent Human Judgment Distributions (HJD). Our results across five diverse datasets reveal that while LLMs achieve near human-level performance at hard-label prediction on most tasks, they exhibit poor performance when predicting soft-labels. To address this limitation, we propose NAPHA (eNtropy-Aware Post-Hoc Alignment), a simple yet effective lightweight post-hoc alignment method that matches the LLM distribution to the HJD by first assigning an instance to a discrete entropy class and then routing it to specialized, trained alignment models. We find that NAPHA consistently improves soft-labels prediction across base LLM models and datasets, with particularly strong gains on high-entropy instances where capturing diverse human perspectives is most critical. We also show via oracle experiments that improving entropy class prediction can substantially enhance NAPHA's practical effectiveness. --- ### Let Confidence Change, Not the Prediction: Prediction-Preserving Repair for Post-hoc Calibration Authors: Daehwan Kim, Haejun Chung, Ikbeom Jang Published: 2026-09-01 Categories: cs.LG, cs.CV arXiv: https://arxiv.org/abs/2609.01072v2 Post-hoc calibration corrects reported confidence, yet a multiclass calibrator can also change the associated top-1 prediction. Accuracy captures only the net effect of these changes on correctness, not how often predictions change; the Top-1 Prediction Change Rate (TPCR) instead measures this frequency. We propose Calibrator-Output Repair for Top-1 Decision Preservation (CORD), the first post-fit adapter to impose exact prediction preservation by repairing the full calibrated probability vector. From the original and calibrated outputs alone, CORD determines the mass assigned to the original top-1. The calibrated conditional distribution allocates the remaining mass over the other classes, yielding a repaired vector whose own argmax recovers the original prediction. On the calibration split, CORD coordinates the repaired masses to retain the calibrated outputs' mean mass on original predictions whenever attainable. The adapter alters neither the fitted calibrator nor its direct output, fits no additional supervised map, and requires no user- or validation-tuned hyperparameter. Across CIFAR-10/100 and ImageNet-1K, CORD attains zero TPCR by construction and lowers mean ECE, NLL, and Brier relative to the corresponding direct outputs in every dataset; paired gains persist under distribution shift and across calibration-set sizes. CORD thus removes the preservation constraint from calibrator fitting and assigns exact recovery of the original decision to subsequent output repair. Our code is available at https://github.com/labhai/CORD. --- ### OUTLETS: Output-Length Prediction from Speculative Decoding Backbones Authors: Weihuang Wen, Yingying Liu, Yichuan Liu, Wenqi Zeng, Li Zhou, Chumin Sun, Jie Sun, Tianshu Yu Published: 2026-09-01 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.01068v2 The heavy-tailed distribution of output lengths in Large Language Model (LLM) serving poses major challenges for resource provisioning and cluster scheduling. Although output-length prediction can mitigate these issues, existing approaches have key drawbacks: external proxy models add substantial latency and often have limited fidelity, whereas internal state-based methods are efficient but rely on shallow probes of current model states. We identify a structural connection between speculative decoding (SD) and length prediction: latent representations produced by the draft decoder in advanced frameworks (e.g., EAGLE-3) encode signals that are predictive of generation length. Building on this insight, we introduce OUTLETS (Output-Length Prediction from Speculative Decoding Backbones), which repurposes the speculative backbone as a trajectory-aware length predictor. When its draft representations are already computed for speculative decoding, OUTLETS adds only a lightweight regression head and achieves lower MAE than the evaluated methods. Under saturated disaggregated serving, OUTLETS predictions enable standard scheduling policies to prioritize shorter requests and distribute requests more evenly across decoding instances, reducing short-request P99 latency by 34.8%. --- ### Artificial Rosetta Stone: Constrained Maximum A Posteriori (MAP) Reconstruction of Symbolic Raga Sequences via Order-k Markov Models Authors: Saanvi Raghavendran, Abhishek Bhattacharjee Published: 2026-09-01 Categories: cs.SD, cs.LG, stat.ML arXiv: https://arxiv.org/abs/2609.01064v1 Reconstructing a damaged musical fragment is an inverse problem: the observed sequence contains partial information, while a raga encodes constraints limiting allowable completions. This paper formalizes a mathematical framework for this, proposing the Artificial Rosetta Stone (ARS). We separate three claims often conflated: a symbolic sequence can be reconstructed probabilistically; a sequence can be consistent with an explicit grammar; and a historical performance can be authenticated. We only support the first two. We model a raga via a finite alphabet and constraint system, using an order-k Markov model for melodic probabilities. A symmetric Dirichlet prior yields a tractable posterior. We pose missing-note reconstruction as a constrained MAP problem. For fixed-length sequences and finite-order constraints, optimization admits an exact dynamic-programming solution with worst-case time complexity $O(TN^{k+1})$. We derive the parameter count $N^k(N - 1)$, prove a concentration bound under explicit mixing assumptions, and analyze estimation error propagation. A reproducible synthetic experiment uses six raga-inspired alphabets, orders $k \in \{1, 2, 3\}$, and masking rates up to 50%. This is a proof of concept, not historical reconstruction. A real-audio feasibility pilot evaluates 30 usable sequences from 42 Yaman clips via automated pitch extraction, segmentation, and quantization. Lacking documented provenance and relying on automated transcription, this is not expert-validated archival reconstruction. Claims are tied to stated conditions, not universal properties of Hindustani music. Code: https://github.com/mathacker23/ArtificialRosettaStone. --- ### Space Generative AI with Solar Energy Harvesting Authors: Jierui Zhang, Jianhao Huang, Zhanwei Wang, Kaibin Huang Published: 2026-09-01 Categories: cs.AI, cs.NI, eess.SP arXiv: https://arxiv.org/abs/2609.01062v1 Satellites are emerging as promising platforms to extend generative \emph{artificial intelligence} (AI) services to remote areas lacking terrestrial infrastructure. However, deploying space generative AI is fundamentally constrained by the limited, time-varying onboard energy supplied by solar \emph{energy harvesting} (EH). This paper presents a framework for solar-powered space generative AI in which a satellite receives a user prompt, executes a diffusion-based image-generation model, and downlinks the compressed result within a strict time window. We identify the fundamental \emph{computation--communication} (C$^2$) trade-offs governed by the shared harvested-energy budgets. Specifically, increasing the number of generation steps improves intrinsic image quality but depletes energy and time available for downlink transmission, whereas prioritizing communication guarantees reliable delivery but sacrifices semantic quality. To balance these trade-offs and maximize \emph{end-to-end} (E2E) generative performance, we exploit the predictable solar-EH dynamics induced by deterministic orbital motion and develop a joint C$^2$ resource-optimization framework using a tractable two-step approach. First, we characterize the maximum downlink throughput for a fixed generation depth under continuous solar EH. This establishes a separation principle that decouples waiting-time selection from optimal transmit-power control. Next, we formulate a joint C$^2$ utility-maximization problem and derive a closed-form, low-complexity step-selection policy in the dominant constant-power regime. Extensive experiments under realistic orbital dynamics demonstrate that the proposed policy dynamically balances generation quality and transmission reliability. This yields significant E2E performance gains over static computation- and communication-centric baselines across diverse solar-EH states. --- ### Accelerating Reinforcement Learning via MPC Solver-Gradient Guidance for Weights-varying MPC Authors: Baha Zarrouki, Arslan Thobani, Jasper Hoffmann, Mattia Piccinini, Rudolf Reiter, Felix Jahncke, Sébastien Gros, Davide Scaramuzza, Johannes Betz Published: 2026-09-01 Categories: cs.RO, cs.LG, eess.SY arXiv: https://arxiv.org/abs/2609.01061v1 In Model Predictive Control (MPC), cost-function weights shape closed-loop behavior, yet changing conditions often make fixed parametrizations suboptimal and motivate context-dependent online adaptation. Learning such policies is difficult because behavior depends implicitly on numerical MPC solutions, producing nonlinear, potentially nonsmooth, long-horizon dependencies on policy parameters. This creates a bias-variance tradeoff: Reinforcement Learning (RL) optimizes realized closed-loop return from environment samples but is sample-inefficient, whereas Gradient-Based Policy Learning (GB-PL) uses low-variance solver gradients from differentiable MPC to optimize surrogate losses on predicted trajectories but can be biased under model mismatch. We propose Solver-Gradient Guided Reinforcement Learning (SG-RL), a solver-sensitivity augmentation for RL-based online MPC cost-weight adaptation. SG-RL keeps sampled closed-loop return as the objective and uses bounded solver-derived gradients as auxiliary guidance to improve stability and sample efficiency. We instantiate SG-RL in Proximal Policy Optimization (PPO) with four modular algorithms that inject solver-gradient guidance into actor-update scaling, policy loss, advantage estimation, and value-function learning. On two full-scale autonomous racing platforms with intentional model mismatch, SG-RL reaches PPO's best closed-loop return with up to 70.6% fewer samples, outperforms GB-PL baselines by at least 54% in closed-loop return, and generalizes zero-shot to unseen environments. --- ### Lightweight Interpretable RGB-Guided Hyperspectral Super-Resolution under Real Cross-resolution Misalignment Authors: Mohamad Jouni, Aurélien Godet, Mauro Dalla Mura Published: 2026-09-01 Categories: eess.IV, cs.CV arXiv: https://arxiv.org/abs/2609.01060v1 Compact snapshot hyperspectral cameras provide rich instantaneous spectral measurements for ground-level machine vision, but at lower spatial resolution than standard RGB cameras. RGB-guided hyperspectral super-resolution (HSR) addresses this limitation by transferring spatial detail from a high-resolution RGB guide to a low-resolution hyperspectral image (HSI). These dual-camera systems are typically in a horizontal rig geometry, requiring cross-camera image alignment due to different fields of view. However, residual misregistration can inject spurious high-frequency details. Existing learned unaligned-fusion methods are usually trained for a fixed spectral support and spatial scale factors and can be computationally demanding, limiting their flexibility across sensors. We propose a lightweight and interpretable RGB-guided HSR framework combining cross-modal flow alignment with model-based Gram-Schmidt orthogonalization fusion. The method first warps the RGB guide onto the HSI grid, then estimates an energy-based confidence weight map by measuring local alignment reliability. This map is then used both in a weighted least-squares spectral regression and in a gated fusion between the super-resolved estimate and an HSI-preserving estimate. Unlike existing learned methods, the proposed framework has a low computational footprint and supports VIS-NIR spectral supports and scale factors without retraining. Experiments on the Real benchmark show that the proposed method improves reconstruction accuracy over learned fusion baselines while remaining substantially faster. On a 34-frame sequence acquired with our real RGB-HSI dual-camera setup, a reduced-resolution quantitative evaluation validates the method under genuine cross-sensor radiometric, noise, and geometric differences, while native-resolution qualitative results demonstrate deployment on the full 51-band VIS-NIR acquisition. --- ### Dyn-3D: Unveiling and Resolving Ego-Motion Ambiguity in Vision-Language Models Authors: Jiayu Ding, Zhuodong Liu, Lei Zhang, Manyu Xiong, Hongbo Jin, Haoran Tang, Hongbo Zhang, Changen Zhu, Wenbo Xing Published: 2026-09-01 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.01059v1 As Vision-Language Models (VLMs) tackle dynamic 3D spatial reasoning, ego-motion perception becomes essential to resolve monocular scale ambiguity. However, current models often overfit to smooth trajectory priors rather than genuinely understanding physical motion. Consequently, their spatial reasoning degrades severely under large displacements, a phenomenon we term Kinematic Collapse. This failure stems from spurious visual-motion correlations in natural videos and a lack of explicit physical supervision. To evaluate this, we introduce Dyn-3D, a benchmark using counterfactual 3D rendering to rigorously decouple visual changes from true kinematic properties. Furthermore, we propose the TempoVista framework, featuring the Kinematic-GSPO algorithm. By embedding metric physical ground truth into policy optimization, TempoVista explicitly grounds visual representations in 3D space. Experiments demonstrate that our approach significantly improves both motion estimation and robust spatial reasoning by utilizing camera dynamics as an effective geometric calibration signal. --- ### ARISE-RL: Agentic Rubric-Grounded Iterative Self-Evolution with Reinforcement Learning Authors: Fanrui Zhang, Ruixue Ding, Qiang Zhang, Xi Chen, Boli Chen, Shihang Wang, Qiuchen Wang, Hongmin Zhan, Jinxin Bian, Li xingchao, Peijin Zheng, Hao cheng et al. Published: 2026-09-01 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.01058v1 Training open-ended agents via reinforcement learning (RL) is hindered by the lack of verifiable gold answers and scalable rubrics. Moreover, even near the model's capability boundary, long-horizon open-ended agentic tasks often yield brittle and unstable rewards, resulting in weak or noisy rollout contrast that obscures fine-grained optimization signals for group-based policy learning. To address these challenges, we propose ARISE-RL, a novel full-cycle self-evolution framework that couples a task/rubric Generator and a reasoning Solver through rubric-mediated co-evolution. The Generator grounds tool-related rubric criteria in real tool observations and is rewarded for producing valid, intermediate-difficulty tasks aligned with the Solver's evolving capability boundary. The Solver, in turn, learns from fine-grained rubric satisfaction signals through multi-step reasoning and tool use. We further introduce Reward-Gated Self-Evolution Distillation (RG-SED), which selectively distills a memory-augmented variant of the same policy back into itself only when the memory yields empirical reward improvement, thereby reducing distribution mismatch and avoiding blind imitation of noisy guidance. Finally, to support rigorous evaluation, we present ECR-Bench, an expert-calibrated rubric benchmark suite covering single-tool deep research and multi-tool travel planning. Extensive experiments demonstrate that ARISE-RL consistently achieves robust and stable overall state-of-the-art performance across all evaluated benchmarks. --- ### User Representation via Cross Multi-source Behavior Pre-training for Mobile Games Authors: Chengqi Yang, Yiran Qiao, Feng Liu, Xingyu Lou, Zijun Zhou, Xiaoyun Mo, Changwang Zhang, Jiayuan Xu, Jun Wang, Xiang Ao Published: 2026-09-01 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.01057v1 User representation pre-training has become a fundamental paradigm for alleviating data sparsity in downstream personalization tasks. However, existing studies predominantly focus on single-app or app-level behaviors, overlooking the inherently cross-source and multi-granular nature of user activities on mobile devices. At the device level, user intent emerges from complex interactions among heterogeneous behavior sources and hierarchical action structures, posing challenges that cannot be addressed by conventional app-centric modeling. To tackle this issue, we propose CM-PTM, a novel Cross Multi-source Behavior Pre-Training Model tailored for mobile game user representation learning on device-level behavioral logs. CM-PTM employs hierarchical cascaded mask-then-predict proxy tasks that first infer the source of the next behavior and then progressively refine predictions at the app-action level. This design enables unified modeling of cross-source dependencies and fine-grained behavioral dynamics within a single pre-training paradigm. Extensive experiments on large-scale real-world mobile datasets demonstrate that CM-PTM effectively captures users' endogenous interests and consistently delivers significant performance gains on downstream mobile game recommendation tasks. --- ### WorldBench: Culturally Grounded Benchmark for Multilingual Agents Authors: Leonardo Ranaldi, Sherrie Shen, Jushi Kai, Alexandra Birch Published: 2026-09-01 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2609.01056v1 Despite the growing use of LLM-powered agents to solve multi-step tasks in complex environments, existing benchmarks rarely test state preservation, performance across languages, and application to realistic, grounded scenarios. To address these concerns, we present WorldBench: a comprehensive, multilingual benchmark of genuine, persona-grounded everyday workflows, where agents can act in a sandbox via structured actions. WorldBench comprises 1,600 tasks across seven languages and eight cultures, filtered and refined through feedback from human annotators with language- and culture-specific expertise. For evaluation, we extend metrics from previous works and introduce Constrained Task Success (CTS), which combines natural language instructions and testbeds to score task completion, minimal modification, and other complementary metrics through deterministic and LLM-as-a-Judge evaluations. Our experiments show that frontier models reach only 49.2% CTS, with all models demonstrating large gaps between correctness and environment preservation. We thereby show that current agents remain brittle in multilingual, agentic scenarios, especially for long-horizon tasks and under state-preservation constraints --- ### SAGE: Subpopulation-Aware Generative Enhancement for Mitigating Spurious Correlations Authors: Yiming Luo, Rongqiang Zhao, Jie Liu Published: 2026-09-01 Categories: cs.LG, cs.CV arXiv: https://arxiv.org/abs/2609.01051v1 Spurious correlations pose a significant challenge to the robustness of modern machine learning. The inherent imbalance in dataset distributions often leads traditional Empirical Risk Minimization (ERM) models to rely on majority spurious attributes for classification, resulting in poor performance on minority groups. This problem becomes particularly challenging when the spurious attributes are unavailable. Existing group-label-free methods often upsample minority groups or misclassified real training examples; repeating the same instances can reduce effective diversity and encourage overfitting. To mitigate these spurious correlations from a data-centric perspective in the absence of prior knowledge, we introduce Subpopulation-Aware Generative Enhancement (SAGE), a two-stage generative augmentation framework. Using cluster-derived sub-labels and class labels, we fine-tune a conditional generative model and text encoder, generating targeted synthetic data to fill underrepresented regions in the training set and construct a balanced validation set for last-layer reweighting. We experimentally show that SAGE achieves 89.5%, 85.7%, and 79.1% worst-group accuracy on Waterbirds, CelebA, and MetaShift, respectively, outperforming the best group-label-free baselines by up to 7.7 percentage points. --- ### QILP-0: Constructing Observational Declarative Twins of Quantum Circuits Authors: Marina de la Cruz Echeandía, César Luis Alonso, Tony Ribeiro, Alfonso Ortega de la Puente Published: 2026-09-01 Categories: cs.AI, quant-ph arXiv: https://arxiv.org/abs/2609.01049v1 This paper introduces QXymb, a general framework for constructing observational declarative twins of quantum circuits, and develops QILP-0, its first complete order-0 specialization. QILP-0 constructs a finite multi-valued propositional logic program from observed circuit behaviour within a declared observational scope. The pipeline traverses a declared family of quantum observables incrementally according to a reproducible structural grading and a declared observational reference horizon. Progress is quantified through reference-relative coverage against a fixed target-independent reference. Observable responses are organized through target-independent geometry, while retained latent structure is mapped deterministically back to original observable columns before symbolic processing, preserving observational semantics and provenance. Selected observable profiles are converted into a finite relation through admissible target-independent discretization. The target is used only afterwards to audit twin-admissibility and induce the declarative theory. A theory is certified as an exact observational declarative twin when it completely and correctly reconstructs the resulting finite task-conditioned discrete relation. Logical exactness is therefore separated from numerical, backend, provider, and discretization uncertainty, which is retained as audit metadata. Validation uses two complementary QML settings. Exhaustive Bars & Stripes experiments compare product and grid-CZ embeddings from 16 to 100 qubits and exercise the native-discrete branch. Low-Depth MNIST analyses all 14,708 digit-0/1 instances before and after a trained variational quantum transformation and exercises continuous discretization. In every reported relation, the induced QILP-0 theory achieves complete, conflict-free reconstruction with strict accuracy equal to one. --- ### Lagged Coupling: Internal Representations Become Readable Before They Become Causal Authors: Xining Xun Published: 2026-09-01 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2609.01048v1 Across the full Pythia suite (160M-12B, eight checkpoints, four task families), a linear probe can read a target variable from the residual stream as early as step 1,000 at every scale -- yet steering along that same reading direction remains null-equivalent in 43 of 48 model-checkpoint cells. Internal readability systematically outruns causal efficacy, and the lag does not shrink with scale. We call this structure lagged coupling and decompose it into three dissociable tracks: (i) internal readability, saturated (AUROC >= 0.990) from the first checkpoint everywhere; (ii) behavioral readability, which develops gradually and progressively later at larger scales (12B reaches 0.909 only at the final checkpoint); (iii) causal efficacy, almost always null-equivalent, occasionally counterproductive early, with one isolated positive pulse (12B, step 8,000, z = +2.49) our grid cannot resolve. The ordering is dominantly read-before-write (11/11 units, no inversion). Representation headroom along the probe direction grows up to 57x with training and scale while causal write-in stays below 0.11% of headroom -- the variable is increasingly written into the representation and increasingly ignored by the readout. Under a fully pre-registered protocol, both single-onset hypotheses resolve INDETERMINATE (scale slope +0.24, 95% CI (-0.60, +0.87); time vote 3:3) -- a disciplined negative explained by the three-track decomposition. A pre-registered OLMo-2 replication preserves the direction at attenuated magnitude. Our results caution against inferring steerability from probe accuracy and establish a developmental bottleneck: representation formation reliably outpaces causal readout consolidation. --- ### HiveTraceGuard-Pro: A Compact Generative Guardrail for Prompt Injection, Jailbreaks, and Adversarial Obfuscation Authors: Nikita Oblakov, Sabrina Sadiekh, Evgeniy Kokuykin Published: 2026-09-01 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2609.01046v1 Production LLMs must handle inputs that attempt to override system instructions, bypass safety policies or elicit harmful responses. A common mitigation is a separate guardrail model. Existing reports, however, provide little evidence on Russian prompt injection or Russian surface obfuscation. We present HiveTraceGuard-Pro, a 0.6B generative guardrail LoRA-tuned from Qwen3-0.6B. It is trained on Russian and English and uses one binary scoring rule (safe/unsafe) for the final target turn. Its training corpus pairs harmful examples, where a counterpart exists, with benign examples from the same domain and applies eight obfuscation transforms to both labels. In one harness, we compare HiveTraceGuard-Pro with thirty-four other guards on nineteen benchmark groups, sixteen of which are public. Its aggregate key is 0.7432, behind 0.7641 and 0.7552 for the two higher-scoring guards. Over the sixteen public groups alone, its key is 0.7153 and four of the thirty-four other suite guards score higher. In a fifteen-model comparison, HiveTraceGuard-Pro has the highest clean Russian robustness combined-F1 (0.88) and Russian prompt-injection recall (0.999). Both results use Russian sets assembled by our team, and at least 27.1% of the prompt-injection set overlaps the training corpus. Its 14.3 ms median latency is the lowest among those fifteen models in that run. Across the suite, FPR is 0.268 and FNR is 0.156. All reported response results use a legacy standalone-reply serialization rather than the natural assistant-role path of the shipped chat template. We release the merged weights on Hugging Face under Apache-2.0. The corpus, evaluation sets and evaluation code remain internal. --- ### AgentFactory: Towards Automated Agentic System Design and Optimization Authors: Enci Zhang, Haofeng Wang, Yuesheng Zhu, Xiaole Cui, Guibo Luo Published: 2026-09-01 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.01045v1 Large Language Models (LLMs) have demonstrated remarkable capabilities as powerful components in agentic systems, enabling sophisticated reasoning and complex task execution. However, current approaches to manually designing and optimizing agentic systems heavily rely on manual effort, limiting their adaptability and scalability. Recent work has explored the automated optimization of workflow designs. However, these approaches often overlook the crucial role of model capabilities and focus on single performance metrics, failing to address real-world deployment constraints. In this paper, we present AgentFactory, a framework that jointly optimizes both foundation models and workflow structures in agentic systems while considering multiple objectives including performance, cost, and efficiency. AgentFactory leverages advanced LLMs as optimizers to navigate the vast search space of possible configurations, employing a three-stage optimization pipeline to automatically discover effective combinations of fine-tuned models and optimized workflows. Through an iterative optimization process, our framework systematically explores and evaluates different agentic system designs, adapting to task-specific requirements while maintaining operational efficiency. We evaluate AgentFactory across eight benchmarks spanning five domains, including general reasoning, coding, mathematics, medicine, and finance. Our experiments demonstrate that AgentFactory consistently outperforms both manually designed methods and existing automated approaches, achieving an average improvement of 9.1% across all benchmarks, with particularly significant gains in domain-specific tasks (19.6% on MedQA and 18.7% on FinEval). These results establish AgentFactory as a promising approach for developing more capable and efficient agentic systems through automated optimization. --- ### From Truncation to Commitment: Persistent Context in Uniform Discrete Diffusion Authors: Satoshi Hayakawa Published: 2026-09-01 Categories: cs.LG, cs.AI, math.PR, stat.ML arXiv: https://arxiv.org/abs/2609.01043v1 Uniform-state discrete diffusion models update all tokens in parallel while keeping every position revisable. Even when the commonly used top-$p$ rule leaves only one candidate at a position, that choice affects only the current reverse step and can be revised at the next sampling step. We ask what changes when selected hypotheses instead become persistent context for later predictions. We therefore propose committed reveal sampling (CRS), a training-free sampler that stores selected argmax tokens and inserts them into subsequent model inputs. Our analysis gives a rationale for selecting later and for keeping selected tokens visible. Under the exact forward process, the Bayes error of selecting a clean token cannot increase as noise decreases, while in a simple latent-mode model, keeping the selected token visible helps later parallel predictions agree on the same sequence-level choice. Empirically, paired experiments on Duo-distilled then separate this persistent effect from single-step top-$p$ restriction and scalar temperature scaling. Under the same finalization rule, CRS without top-$p$ truncation reaches lower generative perplexity (GenPPL) than fixed $p=0.95$ and $p=0.9$ baselines across budgets of 8--64 function evaluations (NFE). At 64 NFE, the comparison at matched unigram entropy also gives lower GenPPL for CRS, yielding a more favorable GenPPL--entropy tradeoff. Base Duo shows the same direction in a descriptive comparison, while other diversity and continuation metrics can rank these operating points differently. These results identify support restriction and persistent context as distinct controls of that tradeoff. --- ### ViTAMINS: An Empirical Study of Training Self-Supervised Vision Transformers with Synthetic Hard Negatives Authors: Nikos Giakoumoglou, Andreas Floros, Kleanthis-Marios Papadopoulos, Tania Stathaki Published: 2026-09-01 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2609.01041v1 We introduce ViTAMINS, a method that integrates synthetic hard negatives into unsupervised vision transformer pretraining to improve representation quality. Our approach is thoroughly benchmarked on ImageNet and transfer learning, image retrieval, copy detection, and image, video segmentation tasks. Notably, our proposed negatives give rise to emergent properties, where learned representations contain explicit information about the semantic content of an image and serve as excellent classifiers (up to +11.3% over baselines). ViTAMINS achieves these benefits through simple modifications to existing contrastive frameworks and outperforms competing methods while being more resource efficient, e.g., our ViT-B surpasses V-JEPA with ViT-L. Our findings motivate reconsidering contrastive learning as a simpler yet powerful alternative to dominant generative and self-distillation approaches. --- ### Causal Evidentiary Governance for High-Risk Machine Learning Systems Authors: Samah Kareem, Barış Çeliktaş Published: 2026-09-01 Categories: cs.CY, cs.AI arXiv: https://arxiv.org/abs/2609.01040v1 Machine learning systems deployed for credit, hiring, and resource distribution are increasingly subject to regulatory oversight from policies such as the EU AI Act and GDPR. Current fairness governance practices rely on observational fairness metrics, post-hoc explainability, and immutable audit logs, but provide limited support for causal attribution and efficient evidentiary verification. We introduce Causal Evidentiary Governance (CEG), a framework in which regulated institutions commit to a versioned directed acyclic graph (DAG) that partitions causal pathways into allowable and disallowed groups. The Causal Harm Rate measures prediction variation attributable to disallowed causal pathways. Each decision is accompanied by a signed Decision-Evidence Packet (DEP), cryptographically binding the prediction to a digest of the published DAG and path-specific attributions. DEP digests can be appended to a Merkle tree to enable logarithmic-cost inclusion proofs. We validate CEG through a two-layer empirical methodology using demographic summaries from four years of PMA credit supervisory data to construct 10,000 synthetic credit applicants across four strategic DAG counterfactuals. Causal Harm Rate isolates injected causal effects more clearly than demographic parity or equalized odds. Cross-model validation and ablation studies assess robustness. Evaluation on the German Credit dataset shows that harm associated with specific causal pathways can be substantially understated by associational fairness metrics. Finally, a proof-of-concept implementation demonstrates operationally plausible throughput and highlights relevant performance tradeoffs. --- ### Data-Driven Persona-Conditioned Agents for A/B Test Simulation Authors: Ziyad Benomar, Weronika Łajewska, Leonardo Perelli, Saab Mansour Published: 2026-09-01 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.01038v1 A/B testing is the gold standard for evaluating product changes, but each experiment requires real user traffic, engineering effort, and weeks of measurement. We propose a simulation framework that predicts A/B test outcomes using LLM-powered agents conditioned on data-driven personas grounded in real user behavioral signals. Unlike prior work that relies on synthetic or rule-based personas, our agents are constructed from anonymized behavioral data-activity patterns, engagement signals, and inferred demographics-enabling more faithful population modeling. We frame A/B test simulation as a structured question task and systematically study (i) question design formats, (ii) the impact of persona data source and domain alignment, (iii) the trade-off between per-persona behavioral depth and population diversity, and (iv) efficient population subsampling. On a benchmark of 40 A/B tests spanning two metric types, our best configuration achieves 0.75-0.90 directional accuracy depending on the test metric, demonstrating that data-driven personas are a viable path toward fast, low-cost experiment pre-screening. --- ### MultiGait: A Multi-Sensor Multi-Perspective Multi-Session Biometric Inference Benchmark and its Dataset Authors: Julian Todt, Felix Morsbach, Philip Dissert, Thorsten Strufe Published: 2026-09-01 Categories: cs.CR, cs.CV arXiv: https://arxiv.org/abs/2609.01036v1 A lack of suitable datasets has limited the research into the privacy risks of novel smart city sensors, such as thermal cameras, depth cameras, and lidar. Given the number of unsubstantiated privacy claims and their potential widespread deployment into many people's everyday life, understanding the privacy risks of these sensors -- in isolation and in like-for-like comparisons -- is crucial. With MultiGait, we collected the first multi-sensor, multi-perspective, multi-session gait-focused dataset, for the corresponding, and additional more far-reaching investigations. The dataset, validated with multiple state-of-the-art recognition systems, comprises various walking modes and annotated personal attributes for 199 individuals, to ensure the benefit for advanced studies including cross-sensor recognition and anonymization at the edge. MultiGait represents a foundation for rigorous privacy investigations, demonstrated through an extensive identity inference benchmark across eight sensors, four perspectives, and three recording sessions. Our benchmark incidentally reveals that sensors often assumed to be privacy-friendly do still entail considerable identity inference risks, while the poor cross-session generalization of existing methods underscores an important research gap. --- ### Spawn Freely, Act Sparingly: Progressive Risk Vesting for Recursive LLM-Agent Trees Authors: Molly Wang Published: 2026-09-01 Categories: cs.AI, cs.LG, math.PR arXiv: https://arxiv.org/abs/2609.01035v1 Recursive LLM agents can broaden their search by spawning specialists. Some branches later request tools that send data or deploy code. When should a branch receive authority to act? We distinguish sandbox spawning, in which external controls prevent the specified harm, from capability activation, in which a selected branch crosses an irreversible-action boundary. Progressive Risk Vesting (PRV) holds a trajectory-level risk budget in escrow and debits it as branches are activated. We prove an anytime harm bound for adaptively generated trees. Branch outcomes may be dependent, but each local certificate needs to remain valid conditional on the full pre-activation history, including the information used to select the request. When activation gates, branch charges, and compute constraints are held fixed, delayed vesting preserves every policy available under irrevocable spawn charging. Marginal risk estimates can still fail after branch selection. In a stylized branching model, trajectory harm changes as the authority reproduction number $\mathcal{R}_A$ crosses one. As local risk $p$ approaches zero, trajectory harm is proportional to $p$ below criticality, proportional to $\sqrt{p}$ at criticality, and retains a positive floor above it. A finite-type occupancy model yields risk and compute shadow prices. For nested fanout modes with decreasing marginal value per unit risk, these prices produce a threshold rule. Branching calculations and a split-sample experiment illustrate the results. These synthetic studies do not estimate safety in deployed agents. The analysis suggests a design rule: search broadly in the sandbox and grant recursive authority sparingly, with an explicit risk charge. --- ### The Multiple Timescales of Gradient Descent on the Edge of Stability: A Perturbative Derivation of the Central Flow Authors: Raphaël Berthier Published: 2026-09-01 Categories: cs.LG, math.OC, stat.ML arXiv: https://arxiv.org/abs/2609.01034v1 The central flow of Cohen et al. (2025) is an empirically accurate continuous-time model of gradient descent at the edge of stability in deep learning, However, its derivation is heuristic. We propose a perturbative regime in which the central flow is the limit of gradient descent: we assume that the loss decomposes as $f = g + \varepsilon h$; in the limit $\varepsilon \to 0$, the dynamics of gradient descent with learning rate $η$ converge to the gradient flow of $h$ constrained to the minimizers of $g$ of sharpness at most $2/η$. Our approach is formal rather than rigorous; it treats gradient descent as a singularly perturbed dynamical system in $\varepsilon$. Three timescales emerge: a fast timescale of oscillations along the sharpest direction, an intermediate timescale of the self-stabilization mechanism, and a slow timescale of the dynamics along the minimizers of $g$-the central flow. Using the method of multiple scales, a classical formal method from singular perturbation theory, we derive the expansion of the dynamics in $\varepsilon$: the central flow emerges as the leading-order term in the expansion, while the self-stabilization mechanism appears in the next-order term. We study this mechanism beyond previous analyses: with a single eigenvalue at the edge of stability, we compute the slow drift of the energy of the fluctuations; with several eigenvalues at the edge of stability, we derive the self-stabilization system and explain why fluctuations persist. --- ### On Synthesis of Metric Interval Temporal Logics Authors: Hsi-Ming Ho, Shankaranarayanan Krishna, Khushraj Madnani Published: 2026-09-01 Categories: cs.LO, cs.AI arXiv: https://arxiv.org/abs/2609.01032v1 Automated mining of formal specifications is vital for verifying real-time systems. However, existing passive learning approaches remain restricted to deterministic specifications or limited fragments of Timed Regular Expressions (TRE). To our knowledge, this paper presents the first framework to tackle \emph{precise} passive learning for an expressive timed logic, \emph{Metric Interval Temporal Logic} (MITL) without relying on predefined templates or restricted logic fragments. Our approach formally reduces the timed learning problem into a scalable untimed one. By identifying quantitative timing differences between positive and negative traces, we synthesise precise timed constraints and inject them as new Boolean atomic propositions. This embeds timing into the alphabet, delegating the complex formula evaluation to highly optimised, off-the-shelf untimed LTL tools. Crucially, our framework is complete, guaranteeing a separating specification can always be found. We evaluate our implementation across several benchmarks, demonstrating the effectiveness of our approach. --- ### Web Price Extraction: State of the Art and an Adaptive Browserless Implementation Authors: Evgeniia Kositsyna, Jorge Lloret-Gazo Published: 2026-09-01 Categories: cs.IR, cs.LG, cs.NE arXiv: https://arxiv.org/abs/2609.01030v1 Price extraction from websites is a key task for market monitoring, price comparison, and business analytics in e-commerce. Existing approaches can be broadly divided into four groups, and understanding their trade-offs in accuracy and scalability is essential for selecting suitable extraction strategies. Classical methods rely on manually written wrappers and rule induction from labeled pages, offering high accuracy but adapting poorly to structural changes and requiring considerable maintenance effort. Browser-based methods, using tools such as Selenium and Puppeteer, handle dynamic JavaScript content but consume large computational resources and scale poorly. Browserless approaches retrieve HTML directly via HTTP requests, offering significant gains in speed and cost, but rely on rules calibrated for specific sites. Methods based on machine learning and large language models offer adaptability but require training data and substantial computation. Our main contribution is an adaptive browserless price extraction system that improves robustness to structural differences between websites. We implemented a baseline architecture combining HTML page fragmentation with syntactic, semantic, and frequency rules, and extended it in two ways: a Bayesian approach that dynamically updates rule weights, and a genetic algorithm that optimizes the system's global parameters. This hybrid scheme increased precision from 77.2% to 87.3% and reduced average per-page processing time by approximately 14% relative to the baseline, confirming it as a competitive alternative to manually tuned browserless solutions and to more resource-intensive browser- or LLM-based methods, offering high extraction accuracy at low computational cost. --- ### Fi-ImageNet-1k: An OOD Benchmark From the Inside of the ImageNet-1k Validation Set Authors: Ruslan Rozumnyi, Matěj Suchánek, Tomáš Vojíř, Klára Janoušková, Jiří Matas Published: 2026-09-01 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.01027v1 Out-of-distribution (OOD) detection predicts whether a test image belongs to none of the predefined classes. To evaluate this task, benchmarks need images from outside the in-distribution (ID) data; typically, these are defined or collected in an ad hoc fashion. Since no ground truth is perfect, ID-labeled datasets themselves contain a natural source of OOD images. We exploit such annotation errors and present Fi-ImageNet-1k, an OOD dataset built from ImageNet-1k validation images that the recent ReImageNet reannotation effort assigned to no ImageNet-1k class. Each image was examined by expert human annotators supported by evidence from MLLMs, VLMs, and reverse image search, comparing it against all visually similar ID classes. We keep only images that could be assigned a specific class outside the ImageNet-1k label space. The resulting Fi-ImageNet-1k, with 655 images from 522 classes, is substantially more challenging than any commonly used OOD dataset. No evaluated combination of classifier and OOD detector achieves a false positive rate below 51% at 95% true positive rate (FPR@95). Compared to the recent NINCO, our dataset is 3.8x more challenging in the FPR@95 metric for state-of-the-art supervised OOD detection methods. --- ### PCoMoE: Shifting MoE Inference from Monolithic Expert Selection to Fine-Grained Path Composition Authors: Ziyan Gan, Fangxin Liu, Chenyang Guan, Junjie Wang, Ning Yang, Haomin Li, Xiang Li, Siran Yang, Jiamang Wang, Lin Qu, Zongwu Wang, Li Jiang et al. Published: 2026-09-01 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.01024v1 Mixture-of-Experts (MoE) architectures scale Large Language Model (LLM) capacity efficiently by activating a sparse subset of experts per token. However, modern MoE inference remains heavily constrained by the rigid, whole-expert abstraction. Existing frameworks manage, schedule, or prune experts as atomic execution units, which fixes the optimization boundary too early and leaves fine-grained intra-expert computational redundancy underexplored. In this work, we present PCoMoE, a path-compositional execution framework that shifts MoE inference from coarse-grained expert selection to fine-grained path composition. PCoMoE incorporates a path-level formulation of expert computation, a compatibility-aware layer-wise pruning strategy to suppress low-value path combinations, and a hardware-friendly execution engine to exploit reusable sub-expert structures under strictly bounded overheads. Experimental results demonstrate that PCoMoE achieves up to a 1.31x end-to-end inference speedup while enhancing model accuracy by 10%. The code is available at https://github.com/gzyyy0/PCoMoE --- ### PyDoseRT Proton: A GPU Pencil-Beam Engine with a Convolutional Residual-Correction Network for Fast Proton Dose Calculation Authors: Lukas Zimmermann, Hermann Fuchs, Attila Simkó, Gerd Heilemann Published: 2026-09-01 Categories: physics.med-ph, cs.CV arXiv: https://arxiv.org/abs/2609.01018v1 Architecture category. Hybrid method: a physics-based analytical pencil-beam (PB) dose engine followed by a 3-D convolutional residual-correction network (RepVGG-U-Net). We addressed the DoseRAD2026 proton dose-prediction task with PyDoseRT Proton, a GPU-accelerated engine implemented in PyTorch and augmented by a learned residual toward Monte Carlo (MC) accuracy. A double-Gaussian PB kernel was calibrated to GATE/Geant4 integrated depth doses in water in two stages: a classical per-energy curve fit, then a gradient-based fit of the full 3-D dose through the PyTorch physics engine as it retains a differentiable execution path for gradient-based optimization of dose-dependent objectives. The engine computes each beamlet on a beam's-eye-view (BEV) lattice with variance-preserving Gaussian splitting, an analytic nuclear halo, and a Fermi-Eyges heterogeneity term, then rotates the result into the patient frame. Additionally, a compact residual U-Net predicts an additive correction in BEV space. It is conditioned on voxelwise material-label embeddings, a discrete energy embedding and spot size. The same model was used for all anatomical sites (thoracic and abdominal). It was trained with a patient-space L1 objective emphasizing the scored high-dose region and multi-scale BEV deep supervision. The submitted CT configuration obtained preliminary-test beamlet MAE 0.0066, image-z IDD distance 0.0025, plan MAE 0.0049, 98.30\% gamma pass rate (1\%/1 mm), and DVH error 0.460. --- ### Phrase-Localized Language-Contrastive Guidance: Training-Free Localized Accent Control for Code-Switching Text-to-Speech Authors: Che Hyun Lee, Sangkwon Park, Donghun Kang, Dongwook Lee, Youngho Cho, Heeseung Kim, Sungroh Yoon Published: 2026-09-01 Categories: cs.CL, cs.SD arXiv: https://arxiv.org/abs/2609.01016v1 Current speech synthesis struggles with code-switching, which mixes a foreign language phrase into a primary language utterance, causing the phrase to be spoken with the primary language's accent rather than its native one. We propose Phrase-Localized Language-Contrastive Guidance (LCG), a training-free inference framework that restores a native accent to code-switched phrases in cross-lingual text-to-speech. LCG replaces the single language guidance applied across the whole utterance with a separate guidance for each region, so each part is guided by its own language. To choose where to apply this localized guidance, we propose a self-attention probing technique that finds the phrase boundaries without external alignments. Together, these components generate speech in which each region carries the accent of its own language, requiring no fine-tuning or auxiliary models. Across diverse language pairs, LCG robustly increases the nativeness of the code-switched phrase while suppressing accent leakage, and preserving overall speaker identity and naturalness. --- ### A Network Science Perspective on Evaluating Deep Graph Generative Models Authors: Tianrui Mao, Abele Malan, Megha Khosla, Lydia Chen, Huijuan Wang Published: 2026-09-01 Categories: cs.SI, cs.AI arXiv: https://arxiv.org/abs/2609.01015v1 Traditional network models from network science, such as the Erdos-Renyi and configuration models, generate random networks that reproduce few selected topological properties observed in real-world networks. Deep graph generative models emerge as a data-driven approach, leveraging deep neural network architectures to learn complex structural distributions directly from real-world networks to generate more realistic synthetic networks. Because real social contact networks cannot be shared due to privacy risks, synthetic networks serve as an alternative for developing and evaluating epidemic mitigation strategies. In this work, we evaluate deep graph generative models as well as the configuration from a network science perspective by assessing both the topological similarity between generated and real-world networks and their utility in identifying effective node immunization strategies to sup- press epidemic/misinformation spreading. It is found that two deep graph generative models produce synthetic networks that closely resemble the structural properties of real-world networks, enabling them to identify effective immunization strategies. --- ### Low-Quality Face Recognition using Center Aligned Representations and Local Margin Constraints Authors: Vedat Can Dilaver, Benjamin S. Riggan Published: 2026-09-01 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.01014v1 Low-quality face recognition (LQFR) remains challenging due to the difficulty of matching degraded query (probe) images against low-quality (LQ) enrollment (gallery) imagery and the scarcity of training data for large-scale models. While recent face recognition (FR) models perform well on high-quality (HQ) imagery, their accuracy drops significantly on LQ images with extremely low signal-to-noise ratio (SNR). Moreover, fine-tuning HQ-pretrained models on LQ data often improves LQ recognition at the expense of HQ generalization. This trade-off becomes more pronounced in modern evaluation settings spanning multiple datasets with varying image quality levels. To address these limitations, we propose a unified framework that combines three main components: (1) Local Probability Margin (LPM), which estimates per-sample difficulty directly from the model's discriminative landscape; (2) Nested Attention Module (NAM), a new low-rank adapter module that embeds a self-attention mechanism within selected transformer layers; and (3) Quality Gating Protocol (QGP), where an off-the-shelf image quality estimator modulates the adapter contribution at test time, enabling a single model to handle the full quality spectrum without sacrificing HQ performance. Experiments on surveillance (TinyFace, SurvFace) and standard (IJB-B, IJB-C) face recognition benchmarks demonstrate consistent gains in both identification and verification. Code and models will be released at github.com/candllq/nam. --- ### Figures as Programs: Recursive Generation of Editable Scientific Figures Authors: Yepeng Liu, Dasen Dai, Chengzhi Liu, Yiren Song, Hai Ci, Yu Zhang, Qi Zhang, Mike Zheng Shou, Xin Eric Wang, Yuheng Bu Published: 2026-09-01 Categories: cs.AI, cs.GR arXiv: https://arxiv.org/abs/2609.01006v1 Scientific methodology figures are essential for communicating complex methods clearly, yet creating them remains labor-intensive and typically requires multiple rounds of refinement. Recent image-generation models can synthesize visually appealing raster figures, but producing a human-satisfactory result in a single generation step remains difficult. Moreover, precise edits to raster figures are challenging for both humans and models. We formulate scientific figure generation as recursive SVG program construction and propose \textsc{FigTree}, a \textit{multi-agent} system that automatically transforms a scientific paper into a structured vector figure. \textsc{FigTree} grounds figure content in the source paper, decomposes a figure into a hierarchy of local regions, generates each region as a short SVG program, and assembles the resulting fragments. A render-critic refinement loop jointly inspects the rendered figure and its underlying program, enabling visual defects to be traced to specific statements and accurately repaired. We conduct extensive evaluations of \textsc{FigTree} on figure quality and editability, showing that \textsc{FigTree} produces high-quality figures, while also enabling more effective editing than existing raster-based methods. --- ### SinkPruner: Sink-Free Visual Token Pruning for Multimodal Large Language Models Authors: Shiyu Li, Zi-Yuan Hu, Shijia Huang, Yanyang Li, Yiwu Zhong, Liwei Wang Published: 2026-09-01 Categories: cs.CV, cs.AI, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2609.01004v1 Despite their strong multimodal understanding ability, multimodal large language models (MLLMs) incur substantial computational overhead when processing long visual token sequences. To reduce inference costs, recent studies have explored visual token pruning through vision-centric or text-guided strategies. However, these methods often overlook high-norm outlier tokens, i.e., tokens with abnormally large feature norms, leading to suboptimal pruning decisions. In this work, we show that such high-norm outlier tokens are highly redundant in both feature and spatial dimensions, yet are often mistakenly preserved as informative cues by existing methods. Motivated by this observation, we propose SinkPruner, a training-free visual token pruning framework for efficient MLLM inference. SinkPruner follows a coarse-to-fine design with two key modules: a visual sanitizer that filters high-norm redundancies and alleviates attention sink and attention dispersion, and a text-guided pruner that further retains tokens semantically aligned with the text query. Extensive experiments on twelve image-language and four video-language benchmarks demonstrate the effectiveness, efficiency, and generalizability of our framework. Notably, SinkPruner preserves 96.5% (91.8%) of the original performance of LLaVA-1.5 (Qwen2.5-VL) under an 89% token reduction. Experiments further indicate that our visual sanitizer exhibits promising transferability in enhancing the performance of existing pruning methods. Our code is available at https://github.com/LaVi-Lab/SinkPruner. --- ### Right Frame, Wrong Rule: Cultural Cues Expose the Financial Knowledge Gap They Were Meant to Close Authors: Rania Elbadry, Ahmed Heakl, Saeed Almheiri, Fan Zhang, Muhra AlMahri, Xueqing Peng, Mohsinul Kabir, Shuyao Wang, Yi Han, Saadeldine Eletter, Duzhen Zhang, Preslav Nakov et al. Published: 2026-09-01 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2609.00999v1 When a question has valid answers under different normative frameworks, a language model must decide which framework to use and whether it can answer correctly within it. We call this setting normative pluralism and study it in Islamic finance using a four-choice taxonomy that separates framework selection from within-framework correctness. This separation reveals the stereotype trap: a cultural cue steers a model toward one framework, but the model selects an incorrect answer within that framework. Across twelve models, two languages, and fifty demographic signals, cultural cues change framework selection and reveal substantial differences in accuracy, especially among non-frontier models. Under the strongest signal, large open-weight models select the Islamic framework 97% of the time. A two-choice evaluation would report near-perfect alignment, although 57--66% of those selections are incorrect. These findings motivate, but do not directly test, the competence-conditioned routing hypothesis: models may favor frameworks where they are more accurate, while cultural cues may expose framework-specific competence gaps. --- ### Inspicio: Open-Vocabulary, LLM-Based Sense Retrieval for Historical Languages Authors: Michele Ciletti Published: 2026-09-01 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2609.00998v1 Word Sense Disambiguation has advanced rapidly for English and a handful of well-resourced modern languages, but it continues to assume the existence of a sense inventory and a word-to-sense mapping in the source language (Navigli, 2026). These assumptions break down for most historical and low-resource languages, whose dedicated WordNets are either incomplete or still under construction. We present Inspicio, an open-vocabulary retrieval pipeline that links tokens in context to synsets of the Open English WordNet (McCrae et al., 2020) without requiring any source-language inventory or mapping. For each occurrence, an instruction-tuned LLM produces two English translations of the surrounding sentence, a small set of candidate dictionary-style definitions, and a few candidate English lemmas. These outputs drive a hybrid retrieval step that combines dense definition-synset similarity, sparse lemma matching, and Maximal Marginal Relevance re-ranking. We evaluate the pipeline across a 6x6 grid of LLMs and sentence-embedding models on a new bilingual set of manually annotated Latin and Ancient Greek perception verbs, on a subset of PREMOVE dataset (Farina, 2025), and on a diachronic sample of Italian. The best configuration reaches 96% Recall@50 on the perception-verb test set, with each component contributing measurable gains, and remains competitive in the out-of-domain and cross-lingual settings. --- ### Does This Moment Justify the Recommendation? Counterfactual Behavior-Grounded Evidence Retrieval for Personalized Video Recommendation Authors: Xin Liu Published: 2026-09-01 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.00996v1 Personalized video recommendation predicts user preference at the video level, while temporal video grounding localizes query-relevant moments. However, strong localization does not establish whether the retrieved moment constitutes valid evidence for recommending the video to a particular user. We study counterfactual behavior-grounded evidence retrieval, which separates where personalized evidence occurs from whether such evidence exists and evaluates whether model predictions respond consistently when that evidence is replaced. We introduce CBGER-10K, containing 5,000 controlled factual--counterfactual pairs for 3,026 users, where each pair replaces only the focal behavior-supported segment while preserving the user, temporal position, and hard distractors. We further propose CBGER, a compact framework that decouples segment-level localization from video-level evidence estimation and learns both through structured counterfactual supervision. CBGER achieves $0.4432$ MRR, $0.6977$ Pair Accuracy, and $0.6987$ Intervention Consistency across five adapted personalized-highlight and temporal-grounding baselines. Notably, compared with QD-DETR, its MRR improvement is not statistically significant, while Pair Accuracy improves by $11.03$ points. These results show that accurate temporal localization does not necessarily imply reliable personalized evidence existence, motivating explicit evaluation of Whether alongside Where. --- ### CQF-HMR: Continuous Quaternion Flows for Probabilistic 3D Human Mesh Recovery from a Single Image Authors: Cuong Le, Bao-Long Tran, Pavlo Melnyk, Tahereh Dehdarirad, Bastian Wandt, Mårten Wadenbäck Published: 2026-09-01 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.00995v1 Recovering 3D digital humans from a single 2D image is an ill-posed computer vision problem due to the loss of depth information. Probabilistic 3D human pose estimation compensates for this by estimating a set of 3D hypotheses from a prior distribution via generative models. However, most prior work focuses only on 3D keypoints, which often leads to implausible poses that are difficult to apply to downstream tasks, e.g. animation or digital humans. SMPL-based methods are more scalable thanks to the explicit body priors, but it requires more complex modeling of the generation process due to the non-additive nature of the joint rotations. In this work, we propose a novel approach for probabilistic 3D humans using quaternion-constrained continuous normalizing flows conditioned on 2D pose estimations. Our proposed quaternion flows show significant advantages over approaches using other rotation representations. Experiments demonstrate state-of-the-art results of our method on Human3.6M, particularly in ambiguous settings, and comparable pose estimation accuracy on challenging 3DPW and EMDB benchmarks. --- ### EvoGS: Modeling Deformation Evolution for Dynamic Gaussian Splatting Authors: Wei Dong, Shahram Shirani, Jun Chen, Han Zhou Published: 2026-09-01 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.00994v1 Recent extensions of 3D Gaussian Splatting (3DGS) enable real-time novel view synthesis in dynamic scenes by learning time-conditioned Gaussian deformations. However, existing MLP-based methods typically estimate deformations independently at each timestamp, making them less robust to large or abrupt motions. To address this issue, we propose \textbf{EvoGS}, a 3DGS-based dynamic reconstruction framework that models Gaussian deformation as a temporal evolution process. EvoGS maintains persistent deformation states for each Gaussian, extrapolates future states from historical deformation states, and corrects the predictions with MLP-derived observations. The correction is adaptively weighted using a temporal residual memory and evolution statistics such as deformation velocity and trajectory deviation. To further improve reconstruction quality, EvoGS introduces deformation-aware densification. Clone and split operations are performed along corrected deformation directions, while an uncertainty-aware strategy suppresses densification for Gaussians with unstable deformation histories. Experiments show that EvoGS improves dynamic novel view synthesis quality and achieves competitive performance across benchmarks. --- ### On the Human and Computer Alignment of Attribute-Based Music Matches Authors: Roser Batlle-Roca, Woosung Choi, Joan Serrà, Fabio Morreale, Wei-Hsiang Liao, Xavier Serra, Emilia Gómez, Yuki Mitsufuji Published: 2026-09-01 Categories: cs.SD, cs.AI arXiv: https://arxiv.org/abs/2609.00987v1 Recent advances in generative AI are raising ethical concerns regarding the originality of generated content and the potential replication of training data, with further implications for transparency, attribution, and intellectual property. In music, several computational approaches have been proposed to identify potential replication, using audio-based similarity metrics. Yet, their alignment with human judgments across distinct musical attributes remains underexplored. To address this gap, we conduct a perceptual experiment on music matches, defined as strongly similar musical excerpts. We focus on five musical attributes: melody, harmony, rhythm, voice, and timbre. We design a triplet-based forced-choice task comprising 300 cases, including plagiarism examples, cover songs, and AI-generated music. From this experiment, we introduce the MATCHA (Musical Attribute-based Triplet Comparison with Human Annotations) dataset: a collection of 1105 perceptual assessments of attribute-based music matches from 83 expert participants. Our findings reveal measurable agreement among participants in identifying matches across attributes. We further observe partial alignment between human judgments and computational similarity measures. Overall, this work underscores the importance of domain-specific and perceptually grounded evaluation frameworks for generative AI in creative practice. --- ### Semi-Supervised Virtual Staining via Morphology Preservation and Histopathological Realism Constraints Authors: Baoshun Wang, Weiping Lin, Linwu Wang, Yihuang Hu, Baptiste Magnier, Liansheng Wang Published: 2026-09-01 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2609.00984v1 Virtual staining aims to computationally generate target-stained histopathological images while reducing the cost and time associated with conventional staining procedures. However, existing methods rely predominantly on strictly paired and accurately registered training data, which are difficult and expensive to obtain in routine practice. To reduce this dependence, we propose a stable semi-supervised virtual staining framework that jointly exploits both limited paired data and abundant unpaired source images. Directly incorporating unpaired images is challenging because their generated results lack corresponding targets for supervision, potentially leading to unrealistic staining, morphological degradation, or even training collapse. To obtain reliable supervision from these images, Hessian-derived morphology preservation extracts structural cues from each source image and constrains the generated output to retain tissue morphology. Histopathological realism constraints further guide the output toward plausible target-stain characteristics, preventing the source-derived structural supervision from degenerating into contour enhancement or simple color transformation. Together, the two components suppress structural and appearance drift, stabilize semi-supervised stain translation, and promote the preservation of diagnostically relevant information. Extensive experiments on H&E-to-IHC translation for Ki67 and HER2, as well as FFPE-to-H&E translation, demonstrate consistent improvements in image quality, morphology preservation, robustness, and downstream diagnostic performance. Code will be available. --- ### Disclosure-Gated User Simulation for Companion-Agent Evaluation Authors: Yao Liu, Yu He Published: 2026-09-01 Categories: cs.CL, cs.AI, cs.HC arXiv: https://arxiv.org/abs/2609.00982v1 Using a large language model to play the user is now standard in scalable evaluation. It has a repeatedly diagnosed failure: the simulated user is excessively cooperative, so a system under test can score by the sheer number of questions it asks rather than by making the user willing to speak. We answer with a disclosure gate conditioning information release on the companion agent's behaviour: its state is a ladder of five ordered gates, merged onto three observable depth layers. We specify, ablate, and audit it, and train a user simulator against that specification. Gating behaviour is learned from the training corpus's synthetic branch, while the real branch supplies how people speak and react; after training, the simulator need not be told at runtime which gate each item sits behind. The gate is a load-bearing component of the environment: on the English corpus of a published companion-agent benchmark (CompanionBench), once training no longer states per example which gate each item sits behind, the largest rank displacement across 12 systems under test exceeds the noise band set by re-running that environment under a new seed, while per-system scores show no detectable change. We state two acceptance criteria: a ranking must be order-preserving, and absolute scores must be scale-stable. Of the candidates we examine, only one passes both -- the simulator we release -- and its leaderboard correlates at 0.993 with the benchmark's original simulator. By contrast, prompting a frontier model as the simulator barely moves the ranking while shifting every score upward -- a shift invisible to anyone checking the ranking alone. The environment we specify is the one that benchmark already used. That publication describes the mechanism in about four hundred words, and we supply what it lacked: specification, ablations, human studies, negative controls, and downstream sensitivity analysis. ---