# Research Papers — 2026-07 · bundle page 60 of 222 > Full-text markdown of papers #2951–3000 of 11075 published in 2026-07, newest first. AI-readable mirrors of the full 11075-paper 2026-07 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2026-07/page/60 [← Previous bundle](https://aipod.dev/papers/archive/2026-07/page/59.md) [Next bundle →](https://aipod.dev/papers/archive/2026-07/page/61.md) ### Deconstructing Off-Policy Ratios: Entropy-Scaled Trust Regions for Asynchronous Reinforcement Learning Authors: Guanqun Zhao, Zijun Xie, Binbin Zheng, Enlei Gong, Jiafeng Lu, Yehan Yang, Aoqi Hu, Zeyu Chen Published: 2026-07-24 Categories: cs.AI arXiv: https://arxiv.org/abs/2607.22186v3 Asynchronous reinforcement learning (RL) accelerates large language model (LLM) post-training by overlapping rollout generation with policy optimization, but the resulting stale, off-policy data can destabilize optimization and ultimately cause policy collapse. Existing methods typically retain or discard tokens based solely on the magnitude of their importance ratios, applying the same threshold uniformly across token positions. In this work, we reveal that the natural scale of the importance ratio varies systematically with token entropy. Under asynchronous dynamics, this entropy-ratio scaling dictates two distinct phenomena: at low entropy, the inherent train-inference discrepancy is drastically amplified into substantial sampling noise; at high entropy, in-flight weight updates naturally induce pronounced, legitimate exploratory deviations. Consequently, magnitude-only correction inadvertently admits the amplified noise while strictly masking out the essential exploration triggered by in-flight updates. To address this, we propose the Entropy-Scaled Trust Region (ESTR), which scales each token's off-policy deviation by its local entropy, requiring no auxiliary forward passes or explicit version-switch detection. Across long-horizon agentic tasks and mathematical reasoning benchmarks, ESTR consistently outperforms existing asynchronous methods and achieves the best train-inference consistency. It reaches $37.34$ avg@1 on BrowseComp-Plus and $95.69$ on multi-turn GSM8K, matching synchronous GRPO while achieving a $2.6\times$ speedup. --- ### From Isolated Tasks to Structured Capabilities: A Multilayer Taxonomy for Large Language Models Authors: Shixin Fang, Jiachen Wo, Wenjuan Qin, Sihang Jiang, Yanghua Xiao Published: 2026-07-24 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2607.22182v1 Large language model (LLM) evaluation spans diverse tasks and benchmarks, yet evidence remains organized around tasks rather than the capabilities they probe. This fragmentation limits cross-study comparison, obscures capabilities tasks recruit, and makes coverage gaps difficult to identify. We introduce a multi-layer taxonomy of 14 capability domains and 91 subskills across Primitive, Constructed, and Integrative layers. Human cognitive science guides capability definition and organization, not LLM architecture. Layer assignments draw on developmental precedence and hypothesized functional support, while human-origin constructs are adapted to observable model behavior. To demonstrate operational utility, we screened 31,505 papers from ACL, AAAI, ICML, and NeurIPS between 2023 and 2025 and mapped 15,934 LLM-focused papers through multi-model annotation, consensus, and arbitration. Direct research attention concentrated on Language-Semantic Competence (3,551; 22.3%), Reasoning (3,388; 21.3%), Planning and Decision-Making (2,149; 13.5%), and Perception (1,954; 12.3%), whereas six domains appeared in fewer than 2% of papers. Within domains, the most frequent subskill had a median prevalence of 97.9% and appeared in at least 90% of papers in 10 of 14 domains. Language-Semantic Competence and Reasoning formed the highest-volume pair (n = 1,864; 11.7%; lift = 2.47), whereas Theory of Mind and Social Reasoning and Interaction showed the highest lift among pairs with at least 20 co-occurrences (n = 62; lift = 30.84). By shifting the unit of analysis from isolated tasks to structured capabilities, the taxonomy supports research organization, coverage audits, evaluation interpretation, and testable hypotheses for diagnosis, training, and transfer. --- ### Bowel Obstruction Detection and Localization on Abdominal CT with Deep Learning Authors: Moritz Vandenhirtz, Andrea Agostini, Dana Belde, Mélanie Roschewitz, Ismaiel Chikh Bakri, Tilo Niemann, André Euler, Julia E Vogt Published: 2026-07-24 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2607.22173v1 Bowel obstruction is a common and potentially life-threatening gastrointestinal condition. In the face of rising diagnostic workloads, the automated diagnosis of bowel obstruction on CT scans supports radiologists by accelerating detection and improving patient outcomes. In this work, we propose a deep learning framework with a multi-task objective that jointly detects bowel obstruction and localizes its transition zone. Additionally, we extend the method with an inherently interpretable classification method that locates the suspected transition point within a slice. It does so by learning a probabilistic selection mask that faithfully bases the classifier's prediction solely on a small image region. The proposed method is evaluated on an internal dataset comprising 1,427 abdominal CTs. Here, the model achieves an obstruction detection test accuracy of 93% and a Hit@10 transition zone localization of 95%. As the first method to reliably localize the transition zone, this marks a significant step towards the automated identification of this critical clinical landmark. --- ### JustDepth: Real-Time Radar-Camera Depth Estimation with Single-Scan LiDAR Supervision Authors: Wooyung Yun, Dongwook Kim, Soomok Lee Published: 2026-07-24 Categories: cs.CV, cs.RO arXiv: https://arxiv.org/abs/2607.22172v1 Accurate yet low-latency depth is essential for radar-camera perception in autonomous systems. Cameras provide rich appearance but lack metric scale, whereas automotive radar offers metric range but is sparse and noisy. Many pipelines are multi-stage or depend on auxiliary annotations, increasing latency and limiting portability. We introduce JustDepth, a single-stage radar-camera depth estimator trained only with radar, camera, and single-scan LiDAR. All radar returns are aggregated into a fixed-width 1D representation, decoupling runtime from point count. A Height Fusion Block fuses modalities, a lightweight GNN propagates depth globally, and a training-only confidence decoder stabilizes learning with zero test-time cost. We mitigate stripe artifacts via simple augmentations and quantify them using the Vertical-Horizontal Gradient Ratio (VHGR). On nuScenes, compared to recent state-of-the-art methods, JustDepth maintains accuracy while reducing inference time by 39.7x and stripe artifacts by 66% as measured by VHGR. --- ### Learning Spatiotemporal Decision Priors for Efficient Path Planning under Partial Observability Authors: Yi Liu, Hongda Zhang, Leyao Zou, Chunlei Meng, Ziqing Zhou, Yuning Chen, Zhuo Zou, Lida Xu, Zhongxue Gan, Chun Ouyang Published: 2026-07-24 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2607.22166v1 Path planning under partial observability remains challenging because an agent must make long-horizon navigation decisions from only locally bounded observations. Nevertheless, historical trajectories contain reusable experience-guided directional preferences. Classical planners, however, typically solve each instance from scratch and lack an explicit mechanism to exploit such transferable decision knowledge, often leading to redundant node expansions and locally myopic search behaviors. Motivated by this limitation, this paper proposes ImiPath, a prior-guided learning framework that distills reusable spatiotemporal decision priors from demonstration trajectories and uses them as experience-informed directional guidance to bias planners toward reliable and promising search directions under partial observability. Specifically, ImiPath first constructs a local spatiotemporal observation representation, which encodes the spatial information of the local environment and the temporal information of historical trajectories. The SpatioTemporal-Attention Policy Network (STAPNet) then transforms this representation into dicision priors. These priors are further incorporated into heterogeneous planners as directional guidance, biasing the search toward locally promising regions. Extensive experiments demonstrate that ImiPath achieves competitive path quality and improves search efficiency by reducing redundant node expansions under local observability. Additional physical experiments on a magnetic microrobot platform further validate the adaptability and practical deployment potential of the proposed framework. --- ### DBA-Bench: A Production-Fidelity Benchmark for LLM-Based Database Operations Agents Authors: Junming Chen, Junyang Jiang, Xu Chen, Zibo Liang, Kai Zheng Published: 2026-07-24 Categories: cs.DB, cs.AI, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2607.22165v1 LLM-based database agents show promise, but differing task scopes, testbeds, and metrics hinder comparison. We identify four gaps between evaluation and production operations: live-environment fidelity (multi-turn read-write interaction with a running database); observation-space scale and complexity (causal diagnosis across thousands of time series, business logs, and concurrent activity); solution-space openness (multiple remediations with different operational trade-offs); and scenario complexity and coverage (faults cascading across internal mechanisms and operational domains). We present DBA-Bench, a benchmark addressing these gaps through production fidelity, outcome-first evaluation, and controlled scenario reproducibility. It uses instrumented PostgreSQL environments with active workloads, persistent state, and multi-source observations; defines success by measurable recovery or fault elimination under safety constraints; and restores snapshots with scenario-specific checks before each run. The benchmark contains 106 scenarios across seven task domains, with two public difficulty labels based on reference-path diagnostic depth and environmental complexity. We evaluate nine baseline groups, including six foundation-model systems, two GPT-5.5-backed database agents, and a Human DBA reference. Across 848 automated runs, Diagnosis, Outcome, and Safe Pass rates are 32.7%, 19.6%, and 12.4%; the best automated baseline reaches 17.9% Safe Pass versus 93.4% for the Human DBA reference. Automated Safe Pass falls from 19.6% on Easy scenarios to 7.6% on Hard scenarios, underscoring the difficulty of safe end-to-end remediation. --- ### Learning on the Job: Continual Learning from Deployment Feedback for Frozen-Weights Agents Authors: Valentin Tablan, Scott Taylor, Kristoffer Bernhem Published: 2026-07-24 Categories: cs.AI arXiv: https://arxiv.org/abs/2607.22157v1 AI agents encounter learning opportunities in every episode they run, and discard nearly all of them: the underlying models are frozen at deployment, so an agent that resolves a difficult request today starts from zero when it recurs tomorrow. Yet ordinary operation already produces feedback, in the form of outcome verdicts and after-the-fact corrections. We show that this feedback is a sufficient signal for continual learning when the frozen model is paired with an external memory that distils each episode into retrievable natural-language rules. On the banking domain of $τ$-bench, against a static-RAG control retrieving over the complete policy corpus, learning from the one-bit outcome verdict lifts single-trial success to 1.6$\times$ the baseline, and learning from corrections to 2.6$\times$, converting 22 of the 84 tasks the baseline never solves. The result spans the deployment spectrum, measured on Mistral Large, an open-weights model that organisations with data sovereignty requirements can self-host, and replicated on a frontier model, Claude Sonnet 5. The accumulated memory also transfers: each model, reading the store built by the other, rises above its own no-memory baseline. The harness, protocol, and data are released. --- ### Industrial Tokenization for LLM-Based Health Intelligence: A Federated Architecture for Industrial Evidence Integration Authors: Deshui Li, Xiao-Ming Yuan, Zishun Wang Published: 2026-07-24 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2607.22153v1 Industrial health management increasingly relies on heterogeneous information sources, including condition monitoring systems, supervisory control and data acquisition systems, maintenance records, inspection results, and prognostic models. Although large language models provide new opportunities for cross-source reasoning, industrial data and analytical outputs differ substantially in structure, temporal resolution, physical meaning, and reliability. Directly integrating such heterogeneous information into a monolithic model may reduce interpretability, traceability, and adaptability to equipment and data changes. This paper introduces Industrial Tokenization, a conceptual interface for transforming source-specific analytical outputs into structured and machine-interpretable units of industrial evidence, termed Industrial Tokens. Unlike numerical tokens used to encode raw time-series data, Industrial Tokens represent domain-grounded evidence together with source, temporal scope, operating context, analytical meaning, quality or confidence information, and provenance. Based on this concept, a federated industrial architecture is proposed, where heterogeneous analytical subsystems retain autonomy while exposing standardized Industrial Tokens to a central reasoning layer. As an initial implementation, this study presents an end-to-end DiagnosisToken pathway based on vibration-diagnostic outputs, rule-based event aggregation, structured textual token generation, and LLM-based interpretation. Other Industrial Tokens, including SCADA-based condition-monitoring tokens, maintenance tokens, and prognostic tokens, are reserved as future extensions. The proposed framework positions Industrial Tokenization as a semantic interface between domain-specific industrial intelligence and LLM- or agent-based reasoning, rather than another method for encoding raw industrial data. --- ### Unbiased Open World Regularization for Fair Self-Supervised Learning Authors: L{é}o Nicollier, Marc Pic, Pablo Mus{é}, Enric Meinhardt-Llopis, Gabriele Facciolo Published: 2026-07-24 Categories: cs.LG arXiv: https://arxiv.org/abs/2607.22149v1 Despite recent advances, self-supervised learning (SSL) models and Joint-Embedding Predictive Architectures (JEPAs) remain susceptible to learning spurious biases in the dataset. These techniques rely on regularization, which prevents representation collapse by enforcing a global target distribution such as a multivariate Gaussian or a uniform distribution on the sphere. However, these global constraints are insufficient to prevent bias entanglement, as task-irrelevant features can still segregate the latent space into distinct sub-regions. While recent approaches like Entangling and Disentangling (EnD) and Fair Supervised Contrastive Learning (FSCL) empirically debias the latent space, we show that they act as partial approximations of conditional distribution matching. To enforce this matching explicitly, we propose Unbiased Open World Regularization (UOWReg), an encoder-only framework. We show that this shift from a global to a conditional objective guarantees statistical independence between the learned representations and the targeted attributes, regardless of the chosen target distribution. We empirically validate this framework across both Gaussian and spherical latent spaces, using statistical measures to enforce these target distributions. While conditional matching successfully mitigates bias with both distributions, we demonstrate that enforcing conditional uniformity on the sphere yields a lower linearprobing classification error. Empirically, UOWReg reduces Equalized Odds violations on the CelebA benchmark while maintaining competitive classification accuracy compared to existing encoder-only baselines. Furthermore, we introduce the Synthetic Engraving Task-a novel setting in which a dominant macro-structure masks a fine-grained micro-signature. We show that UOWReg effectively prevents the subpopulation collapse observed in standard SSL, successfully isolating micro-signatures even when heavily entangled with the global structure. --- ### dRAE: Representation Autoencoder with Hyper-Spherical Codes Authors: Tianren Ma, Lin Long, Chuyan Chen, Mu Zhang, Junbo Zhao, Tong Zhang, Qixiang Ye Published: 2026-07-24 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2607.22148v1 In this work, we aim to discretize the high-dimensional visual representations to bridge the gap with language models - a non-trivial challenge, as existing quantization methods suffer from codebook collapse, failing to scale while preserving semantic coherence. We identify the root cause as metric mismatch: standard Euclidean codebook objectives are fundamentally misaligned with the anisotropic geometry of representation space, leading to codebook embeddings with high-variance magnitude scales and uneven angular distributions that hinder scalability. To address this, we propose Hyper-Spherical Quantization (HSQ), which decouples semantic content from feature magnitude via angular routing, preventing code assignment from being dominated by scale rather than meaning. The resulting discrete Representation Autoencoder (dRAE) achieves high-fidelity reconstruction while preserving semantic integrity and supporting scalable codebook budget. Extensive experiments demonstrate consistent performance gains as the vocabulary size scales to 131{,}072, along with 100\% codebook utilization, simplified training pipeline, and strong performance across understanding and generation tasks. --- ### Visual Relocalization from Sparse Views in Aliased and Low-Texture Environments via Novel View Synthesis Authors: Maria Peribañez, Javier Civera, Rudolph Triebel, Riccardo Giubilato Published: 2026-07-24 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.22147v1 Visual localization becomes extremely challenging in planetary-like terrains characterized by low texture, perceptual aliasing, harsh illumination, and sparse, weakly overlapping viewpoints induced by forward rover motion and unconstrained driving directions. Under these conditions, state-of-the-art image-to-image and image-to-map matching pipelines suffer significant performance degradation. In this work, we propose a visual relocalization method that departs from classical correspondence-based pipelines by directly estimating camera poses against a differentiable map representation built with 3D Gaussian Splatting (3DGS). Our key contribution is a geometry-aware training strategy that combines photometric and geometric losses, where the geometric supervision is provided for the first time by combining multi-view stereo (MVS) and LiDAR depths. We show that this joint optimization produces a 3DGS model that better fits the underlying scene geometry, leading to improved photometric and geometric consistency and more robust, accurate single-image 6-DoF pose estimation. Extensive experiments on data acquired in planetary-analog environments validate the effectiveness of our approach, showing substantial gains in relocalization accuracy under challenging conditions. Code is available at https://github.com/DLR-RM/multimodal-gsplat-relocalization. --- ### TriGlue: a Biology-Inspired Generative Model for Generating Molecular Glue-Induced Ternary Complex Authors: Yuliang Yan, Shuo Yan, Haochun Tang, Yiqin Sun, Enyan Dai Published: 2026-07-24 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2607.22143v2 Molecular glue degraders have emerged as a promising strategy for targeted protein degradation by inducing ternary complex formation between an E3 ubiquitin ligase and a target protein. Despite their therapeutic potential, computational design of molecular glues remains largely unexplored. Unlike conventional structure-based drug design, molecular glue design is governed by the unknown protein-protein interface and requires the simultaneous modeling of ligand generation, protein-protein docking, and ternary complex assembly. In this work, we formulate molecular glue design as a ternary complex generation problem and propose a biology-inspired generative framework, TriGlue. Motivated by the mechanism of molecular glue action, we decompose ternary complex generation into two coupled stages: interface estimation and interface-conditioned complex generation. First, we develop an SE(3)-equivariant interface estimation module that predicts a geometrically constrained protein-protein interface from unbound monomer structures. Second, we introduce an interface-conditioned ternary flow matching network that jointly generates the molecular glue and predicts the rigid-body transformation required to assemble the ternary complex. Extensive experiments demonstrate that TriGlue generates chemically valid molecules and produces plausible ternary complexes, which highlight the potential of biology-inspired generative modeling for accelerating molecular glue discovery. Our code is available at https://github.com/yuliangyan0807/molecular-glue-design. --- ### CARDIAG: A Dense Segment Classification Benchmark of Deep Learning Architectures for Coronary Angiography Authors: Dominik Bernard Lau, Hubert Malinowski, Jerzy Szyjut, Adam Brzeski, Tomasz Dziubich, Radosław Targoński, Tomasz Figatowski, Natalia Zielińska Published: 2026-07-24 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2607.22139v1 Accurate pixel-level classification of coronary angiograms is critical for cardiovascular disease assessment, yet the field lacks standardized evaluation protocols. In this work we demonstrate a new benchmark for the assessment of deep learning models which densely classify pixels of coronary angiograms to one of SYNTAX classes (or background). The evaluation covers 24 distinct architectures starting with classic convnets to recent state-space-based vision algorithms. We release CARDIAG - a multi-center, multi-label dataset which we carefully split to reliably compute metrics, accounting for diameter error, overlap, centerline quality and calibration. The data contains SYNTAX labels, binary, uncertainty and segmentation masks as well as intermediate frames together with the selected non-sensitive DICOM metadata. From the multitude of algorithms, we nominate ConvNeXt V2 encoder with DeepLab V3 Plus decoder as the best performing, achieving macro $F_1=0.456$, which we then ensemble with Mamba U-Net and Feature Pyramid Network, for an increased $F_1=0.479$. We demonstrate all the architectures to be well calibrated and determine the generalization of the top 5 methods, together with the data efficiency of these architectures. We highlight the importance of both high-resolution and low-resolution features in encoding. We also demonstrate the model correctness in the context of patient demographic, vessel sides and projection angle configurations. Overall the released benchmark allows for future studies to robustly and rigorously assess the proposals, not only for SYNTAX segmentation, but lesion detection and many more. --- ### Dynamic Commonsense Coordination for Empathetic Response Generation Authors: Zhengyu Qi Published: 2026-07-24 Categories: cs.CL arXiv: https://arxiv.org/abs/2607.22136v1 Empathetic Response Generation (ERG) requires models to recognize users' emotions and generate empathetic responses. Commonsense knowledge has been shown to support such reasoning, yet existing approaches typically reuse fixed commonsense representations across understanding and generation, limiting their ability to coordinate such knowledge across different stages. We propose DCC, a Dynamic Commonsense Coordination Framework with three complementary modules: residual-based commonsense interaction (SCE-AttnRes) to integrate contextual and situational commonsense representations, Association-Guided Commonsense Filtering (AGCF) to down-weight low-relevance commonsense relations, and Iterative Commonsense-Aware Decoding (ICAD) to dynamically retrieve commonsense memories during generation. Experiments on the Empathetic-Dialogues benchmark show that DCC improves emotion classification accuracy and response diversity over the CEM baseline while maintaining comparable perplexity. An LLM-based blind evaluation further demonstrates that DCC generates responses with better relevance, coherence, and informativeness. The code and implementation details will be publicly available at https://github.com/Hanabi-Q/DCC-ERG. --- ### GLI-AL: A Multi-Modal Glioma MRI Label Resource with Unified Anatomy-Lesion Labels Authors: Xingyu Xiang, Shuang Hao, Fan Wang, Jianhua Ma, Chunfeng Lian Published: 2026-07-24 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.22135v2 Existing BraTS-GLI datasets provide a widely used benchmark for adult glioma MRI segmentation, but their task definition focuses on tumor subregions and does not systematically represent coexisting white matter hyperintensities (WMH). In joint segmentation settings, such unlabeled abnormalities introduce task-specific label noise by treating pathological regions as normal tissue. To address this limitation, we introduce BraTS-GLI Anatomy-Lesion, a controlled-access, labels-only derived resource built from the BraTS 2023-GLI training cohort. The resource provides 1,251 unified eight-class anatomy-lesion label sets aligned with the original four-modal MRI cases, including image-repair labels for 116 cases requiring repaired imaging inputs. The cohort is organized into a 394-case purified subset and an 857-case extended subset, with case-level metadata covering label source, image-repair requirements, quality-control status, access conditions, checksums, and release boundaries. Compared with the original BraTS-GLI annotations, the resource substantially expands foreground supervision by incorporating healthy brain tissues and previously unlabeled coexisting abnormalities within a unified label space. A validation study using MedNeXt and T1/FLAIR inputs suggests that WMH-aware supervision preserves healthy-tissue segmentation performance across both in-domain GLI and external WMH datasets, while improving sensitivity to coexisting lesions relative to noisy-control training. The resource is intended for scientific research and supports joint anatomy-lesion supervision, label-noise analysis, and reproducible evaluation. Data are available at https://www.synapse.org/Synapse:syn75210889/wiki/, and code is available at https://github.com/xyx200/brats-gli-anatomy-lesion-code. The data resource DOI is https://doi.org/10.7303/SYN75210889. --- ### A Framework for Individual Tree Growth Reconstruction Using Multi-Platform Laser Scanning Authors: Daniella Tavi, Valtteri Soininen, Lassi Ruoppa, Jesse Muhojoki, Juha Hyyppä Published: 2026-07-24 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.22129v1 Accurate tree-level forest monitoring using laser scanning data requires reliable tree delineation, consistent tree correspondence across multitemporal point clouds, and accurate estimation of tree attributes and their change. Reconstructing tree growth in boreal forests is challenging due to the scarcity of historical stem-level data, propagation of errors from older sensors into change estimation, and growth rates with a magnitude of measurement uncertainty. This study investigates a framework for estimating individual tree diameter at breast height (DBH) and stem volume growth using 136 point clouds acquired between 2014--2025 with 11 scanners on airborne (ALS), mobile (MLS), and terrestrial laser scanning (TLS) platforms across boreal forest test sites. Trees were delineated from an MLS point cloud using deep learning-based segmentation which was transferred to the remaining point clouds, resulting in reliable multitemporal tree correspondence. Stem curves were derived from MLS/TLS data, with ALS data used for height estimation, enabling DBH and volume estimation and time series. A height growth-based scaling model was used to reconstruct stem attributes across time and estimate growth. Results showed that modeled growth achieved higher agreement with manual growth estimates than differencing independently estimated attributes from point clouds. The modeled-manual 5- and 10-year growth RMSEs were 55--111\% and 26--67\% for DBH, and 31--87\% and 21--67\% for volume, respectively, depending on plot difficulty. The scaling model was temporally robust, with errors remaining stable or stabilizing after 5--6 years, reaching maximum RMSEs of 8--12\% for DBH and 12--23\% for volume after 12 years. Combining MLS/TLS-derived stem measurements with multitemporal ALS-derived heights provided a robust framework for individual tree growth estimation without requiring multiple under-canopy scans. --- ### One Hand Watches The Other: Dynamic Multi-Agent Cooperation for Sample-Efficient Bimanual Manipulation in Dynamic Environments Authors: Jan Ole von Hartz, Abhinav Valada, Joschka Boedecker Published: 2026-07-24 Categories: cs.RO, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2607.22119v1 Multi-stream robot manipulation policies achieve unparalleled sample efficiency and generalization by modeling actions relative to environmental reference frames. However, existing approaches typically assume these frames to be strictly exogenous. This causal assumption collapses in dynamic settings, such as when a single robot arm manipulates a moving object or when two arms coordinate, where each arm effectively becomes part of the dynamic environment of the other. We propose DynaMAC, a lightweight, policy-agnostic framework that resolves this causal limitation while preserving the sample efficiency, computational speed, and flexibility of multi-stream policies, DynaMAC treats the opposite arm as a dynamic task parameter, thereby providing a unified formulation for dynamic manipulation and bimanual coordination without requiring an explicit leader-follower relationship. To rigorously evaluate these capabilities, we introduce DynaBench, a novel benchmark for robot manipulation in dynamic environments. Across both dynamic environments and bimanual manipulation tasks, DynaMAC outperforms leading probabilistic and generative baselines by over 35 percentage points while requiring 20 times fewer samples. Crucially, DynaMAC generalizes zero-shot from static demonstrations to dynamic environments, substantially simplifying data collection and establishing an elegant bridge toward human-robot collaboration. --- ### Projection Pursuit CPCANet for Domain Generalization Authors: Yu-Hsi Chen, Abd-Krim Seghouane Published: 2026-07-24 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.22117v1 Domain Generalization (DG) aims to learn representations robust to distribution shifts. Recent geometric alignment methods, such as CPCANet, extract domain-invariant structures through batch-wise Common Principal Component Analysis (CPCA). However, CPCANet suffers from rank-deficient covariance estimation due to the small-sample-size issue in mini-batch training. To address this limitation, we propose Projection Pursuit CPCANet (PP-CPCANet), a covariance-free framework that learns a global orthogonal basis on the Stiefel manifold and jointly optimizes it with network parameters via the Cayley transform. We further introduce a symmetry-breaking detached-median PP dispersion objective to extract common principal components (CPCs) with dense and robust optimization signals. Experiments on four DG benchmarks show that PP-CPCANet achieves SOTA performance while maintaining stable training. --- ### Benchmarking Text-to-SQL under Role-Based Access Control Authors: Yang Fei, Yangfan Jiang, Yin Yang, Xiaokui Xiao Published: 2026-07-24 Categories: cs.DB, cs.AI arXiv: https://arxiv.org/abs/2607.22115v2 Given a database S and a natural language question Q, text-to-SQL systems aim to generate an SQL query that correctly answers Q when executed against S. Currently, popular text-to-SQL benchmarks mostly assume unrestricted access to S; in practice, however, user access is often restricted, e.g., through role-based access control (RBAC) policies. This leads to a potential disconnect between benchmarking results and real-world performance: an LLM with high benchmark scores might perform poorly in an access-controlled environment, by frequently violating RBAC, or rejecting a query q that could be answered with only permitted data in S. Motivated by this, we present a comprehensive text-to-SQL benchmarking framework with realistic RBAC constraints, which features an LLM-assisted workflow that augments existing text-to-SQL benchmarks with plausible user roles and access policies. To do so, we formulate the problem of role synthesis as a structured reasoning process over the database schema, in which the LLM first infers the application context from the schema, and then derives role responsibilities and access scopes consistent with this context. This process is audited by human-in-the-loop quality control, in which domain experts perform metric-guided screening on the generated roles. Besides the augmented dataset, the proposed framework also contains evaluation metrics that identify RBAC-specific failure modes, and disentangle SQL utility from access-control compliance. We apply the proposed framework to several widely-used benchmarks, and conduct a systematic empirical study of state-of-the-art text-to-SQL systems. The results show that many solutions (especially open-weight LLMs) with high benchmarking scores under an unrestricted setting suffer sharp performance degradation once access constraints are in place, due to frequent RBAC violations. --- ### Benchmarking Text-to-SQL under Role-Based Access Control Authors: Yang Fei, Yangfan Jiang, Yin Yang, Xiaokui Xiao Published: 2026-07-24 Categories: cs.DB, cs.AI arXiv: https://arxiv.org/abs/2607.22115v1 Given a database S and a natural language question Q, text-to-SQL systems aim to generate an SQL query that correctly answers Q when executed against S. Currently, popular text-to-SQL benchmarks mostly assume unrestricted access to S; in practice, however, user access is often restricted, e.g., through role-based access control (RBAC) policies. This leads to a potential disconnect between benchmarking results and real-world performance: an LLM with high benchmark scores might perform poorly in an access-controlled environment, by frequently violating RBAC, or rejecting a query q that could be answered with only permitted data in S. Motivated by this, we present a comprehensive text-to-SQL benchmarking framework with realistic RBAC constraints, which features an LLM-assisted workflow that augments existing text-to-SQL benchmarks with plausible user roles and access policies. To do so, we formulate the problem of role synthesis as a structured reasoning process over the database schema, in which the LLM first infers the application context from the schema, and then derives role responsibilities and access scopes consistent with this context. This process is audited by human-in-the-loop quality control, in which domain experts perform metric-guided screening on the generated roles. Besides the augmented dataset, the proposed framework also contains evaluation metrics that identify RBAC-specific failure modes, and disentangle SQL utility from access-control compliance. We apply the proposed framework to several widely-used benchmarks, and conduct a systematic empirical study of state-of-the-art text-to-SQL systems. The results show that many solutions (especially open-weight LLMs) with high benchmarking scores under an unrestricted setting suffer sharp performance degradation once access constraints are in place, due to frequent RBAC violations. --- ### Pretraining EHR Foundation Models with Patient-Aware Sampling Authors: Joshua Placidi, Yuxuan Liu, Jinpei Han, Marek Rei, A. Aldo Faisal Published: 2026-07-24 Categories: cs.LG arXiv: https://arxiv.org/abs/2607.22114v1 Autoregressive foundation models for electronic health records (EHRs) typically inherit pretraining methods from language modeling, where patient trajectories are concatenated into a single token stream and windows are sampled from that stream. In EHR data, this choice is consequential: windows may mix multiple patients, and patients with longer records contribute more optimization updates, potentially introducing bias. We propose Patient Sampling, a pretraining sequence-construction method that allows us to control how training signal is distributed across patients. We compare this method to the standard approach, which we refer to as Global Stream. We show that stochastic Patient Sampling with controllable weighting improves performance on real-world EHR data. Across downstream clinical tasks on MIMIC-IV v2.2 and v3.1, Patient Sampling improves Macro AUROC and AUPRC over the Global Stream baseline. These results identify training and validation sequence construction as important and underexplored design choices for autoregressive EHR foundation models. --- ### InnoText: A Unified Model for Visual Text Generation and Editing Authors: Haowei Liu, Runze He, Jian Lu, Ao Ma, Run Ling, Ke Cao, Jiasong Feng, Wei Feng, Shuo Lu, Yexing Xu, Yun Wang, Jing Wang et al. Published: 2026-07-24 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.22101v1 Diffusion models have recently achieved remarkable success in high-fidelity image synthesis, yet their application to visual text generation and editing remains relatively underexplored. Unlike general image generation, visual text tasks demand precise structural regularity and legibility, which may pose additional challenges for small-scale text and non-Latin scripts such as Chinese. Existing UNet-based models often struggle to produce clear and coherent text, while DiT-based models, though more expressive, are typically limited to a single task, which may lead to redundant training pipelines, inconsistent visual styles, and reduced cross-task generalization. To address these challenges, we propose InnoText, a unified DiT-based framework capable of performing both text generation and editing within a single model. We introduce a Font Size-Aware Modulation (FSAM) module to enhance representations across font scales, a Small-Character Aware Augmentation strategy to improve fine-grained fidelity, and a Task-Specific Region Weighted Loss for adaptive optimization. To support training and evaluation, we also construct a high-quality bilingual (English-Chinese) visual text dataset covering diverse fonts, sizes, and backgrounds. Experimental results demonstrate that our method achieves superior generation accuracy and editing quality, producing visually appealing and realistic text images. --- ### MEUSLI: a Multilingual Projector for LLM-based ASR and Beyond Authors: Lorenzo Concina, Seraphina Fong, Marco Matassoni, Alessio Brutti Published: 2026-07-24 Categories: cs.CL, cs.AI, eess.AS arXiv: https://arxiv.org/abs/2607.22100v1 Lightweight projectors are an established way to connect pre-trained speech encoders with large language models (LLMs), mapping acoustic features into token-level embeddings for tasks like ASR and spoken question answering. Existing systems, however, typically only support a few languages and are often limited to English. We introduce MEUSLI, the first open-science multilingual projector family that links a Whisper encoder with open-source multilingual LLMs, enabling fully open-source end-to-end ASR in 28 European languages. MEUSLI extends prior monolingual pipelines, delivering strong results across high- and low-resource languages. Using proper continual leaning techniques, MEUSLI can be easily extended to other languages not seen in training. We further demonstrate that the MEUSLI projector can be leveraged beyond ASR, enabling multilingual speech translation and topic identification with only a few hours of task specific supervision per language. Overall, MEUSLI provides a solid foundation for multilingual speech understanding tasks, supporting scalable and inclu- sive open-source SpeechLLM --- ### Reasoning Denoiser: Denoising Reasoning Traces for Hallucination Detection in Large Reasoning Models Authors: Junlin Fang, Do Nguyen-Thanh, Xiaogang Xu, Zhen Fang, Sean Du Published: 2026-07-24 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2607.22098v1 Large reasoning models (LRMs) generate long reasoning traces before producing final answers. While these traces may contain useful signals for hallucination detection, harnessing them is non-trivial because long trajectories often include noisy steps that obscure the cues relevant to truthfulness assessment. In this paper, we identify two prevalent forms of reasoning noises, i.e., irrelevant steps and repetitive steps, and show that both substantially degrade hallucination detection performance. Existing confidence-based scores and naive embedding-based filtering fail to reliably separate noisy from informative steps. To address this challenge, we propose REDE, a novel learning framework for denoising reasoning traces for hallucination detection. Specifically, REDE leverages final-answer attention as an automatic supervision signal to shape the step-level representation space, yielding refined embeddings in which noisy steps can be reliably identified and filtered. REDE can be readily plugged into diverse hallucination detectors by operating on the filtered reasoning trajectory after removing noisy steps. Extensive experiments on multiple reasoning benchmarks show that REDE consistently improves detection performance over competitive baselines. --- ### Spectral Prior for Reducing Exposure Bias in Diffusion Models Authors: Yuya Kobayashi, Masato Ishii, Yuhta Takida, Takashi Shibuya, Yuki Mitsufuji Published: 2026-07-24 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.22091v1 Diffusion models typically suffer from error accumulation during iterative sampling, commonly referred to as exposure bias. We reveal systematic frequency-dependent discrepancies between training and inference, which can be interpreted as frequency-dependent SNR error. Crucially, the direction of this mismatch varies across models and timesteps, indicating that fixed correction rules do not generalize. We propose Spectral Alignment (SPA), a lightweight, guidance-based method that calibrates the power spectrum of intermediate predictions to a pre-computed prior. Our approach consists of two stages: (1) offline fitting of a parametric spectrum model from training data, and (2) inference-time guidance via efficient FFT-based gradient computation. SPA introduces minimal computational overhead (3-4\%) and is complementary to Classifier-Free Guidance (CFG). We demonstrate consistent improvements across diverse architectures, from pixel-space models (DDPM, ADM) to latent diffusion models (SD2.0, SDXL) and flow-matching models (SD3.5, FLUX). Our implementation is available at https://github.com/SonyResearch/SPA. --- ### FAIR: Feature-Augmented Implicit Regularization for AI-generated Fake Image Detection Authors: Md Redwanul Haque, Manzur Murshed, Manoranjan Paul, Tsz-Kwan Lee Published: 2026-07-24 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.22087v1 Generalization remains a critical bottleneck in AI-generated image detection. Because many modern generators are proprietary or adversarially modified, existing detectors overfit to the low-level textural patterns of accessible training data, resulting in severe failures on unseen domains. Conventional regularization techniques (e.g., $L_1$/$L_2$ norms, Dropout) apply indiscriminate parametric constraints and fail to provide the domain-invariant structure necessary for cross-generator robustness. To address this, we propose Feature-Augmented Implicit Regularization (FAIR). FAIR introduces an orthogonal, macro-structural prior, specifically, Scene Composition Structure (SCS), during training to geometrically constrain the model's optimization trajectory. By augmenting the primary feature space with domain-invariant SCS features, FAIR explicitly penalizes texture-biased shortcut learning. Crucially, this structural prior is entirely discarded at inference, yielding a smoothed, generalized decision boundary with zero architectural or computational overhead. Extensive evaluations across five massive benchmarks demonstrate that integrating FAIR into state-of-the-art detectors significantly improves cross-generator generalization, boosting accuracy by up to 8.04% and establishing new state-of-the-art robustness in zero-shot transfer scenarios. --- ### MemNMF: Memory-Augmented NMF on LPC Spectra for Anomalous Sound Detection Authors: Phurich Saengthong, Takahiro Shinozaki Published: 2026-07-24 Categories: cs.SD, cs.LG arXiv: https://arxiv.org/abs/2607.22086v1 Autoencoder-based anomalous sound detection is attractive for machine condition monitoring because it can be trained using only normal recordings and yields an interpretable anomaly score from reconstruction error. Most prior work uses spectrogram autoencoders, but reconstructing detailed time--frequency patterns is sensitive to noise and transients, and models can reconstruct some anomalous inputs well, weakening normal--anomaly separation. We propose MemNMF, a constrained reconstruction method that operates on the Linear Predictive Coding spectrum, a compact estimate of the spectral envelope. MemNMF initializes a memory module from an NMF dictionary learned on normal LPC spectra and reconstructs each input as an attention-weighted combination of prototypical normal spectral patterns. Experiments on MIMII and DCASE 2020 Task 2 across multiple machine types and operating conditions show that LPC-spectrum inputs improve a standard autoencoder baseline and that MemNMF yields further gains, with especially strong robustness under noisy, non-stationary settings. --- ### Nanbeige4.2-3B: Unlocking Agentic Capabilities in a Compact Model Authors: Nanbeige Lab, :, Chen Yang, Chengrui Huang, Fufeng Lan, Hanhui Chen, Hao Zhou, Huatong Song, Jiaqi Cao, Jiaying Zhu, Jinlin Niu, Kai Wang et al. Published: 2026-07-24 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2607.22083v2 We present Nanbeige4.2-3B, a compact general agentic model with 3B non-embedding parameters. It delivers strong performance across code-agent, office-agent, and complex tool-use tasks while maintaining highly competitive reasoning capabilities in mathematics, coding, and science. Nanbeige4.2-3B is pretrained from scratch on 28T tokens with a Looped Transformer that reuses the layer stack to increase capacity without adding parameters. For SFT data and trajectory construction, we expand the diversity of executable environments, task assets, and agentic scaffolds through real-world deployment and large-scale synthesis. Our RL pipeline applies mixed-mode RLHF over Think and Non-Think responses to improve overall model quality and reduce failure cases, length-controlled reasoning RL to balance accuracy and reasoning efficiency, and agentic RL with outcome and process rewards to stabilize long-horizon training. Extensive evaluations show that Nanbeige4.2-3B outperforms larger models, including Qwen3.5-9B and Gemma4-12B, across diverse agentic benchmarks while remaining competitive on reasoning and alignment tasks. Performance with OpenClaw further supports its use as a compact local personal assistant. --- ### A Leakage-Free Stacked Ensemble Method for Multiclass Classification Authors: S. P. Sharmila, Aruna Tiwari Published: 2026-07-24 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2607.22081v1 Multiclass classification is a fundamental problem across a wide range of domains. It is still challenging due to possession of high inter-class similarity, class imbalance datasets, and variability in data distributions. Rule-based classifiers such as XGBoost often achieve stronger performance on structured features, but they are limited in capturing smooth functional relationships among variables. Similarly, neural network models can represent complex nonlinear interactions but frequently suffer from overfitting and generalization issues. To address these limitations, we propose LFS-FRAME, a Leakage-Free Stacked ensemble framework that integrates functional learning using Kolmogorov-Arnold Networks (KAN) and rule-based learning via XGBoost for robust multiclass classification. The proposed framework constructs unbiased meta-features by employing a strict out-of-fold stacking strategy to ensure complete isolation between training and validation data hence preventing performance leakage. By learning over probabilistic outputs from heterogeneous base learners, the meta-classifier effectively exploits both global functional patterns and sharp decision boundaries present in the complex data. Experimental evaluations on multi-class datasets demonstrate that LFS-FRAME improves performance metrics, and overall accuracy is 89.85% in identifying major families and 81.74% in identifying sub-families relative to strong single-model baselines. These results highlight the effectiveness of leakage-free functional and rule-based stacking for reliable and generalizable multiclass classification. --- ### CommandLM: Data driven behavior level descriptor for ego vehicles Authors: Boris Tokic, Constantin Selzer, Fabian B. Flohr Published: 2026-07-24 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.22078v1 As autonomous driving systems move toward real-world deployment, interpretable, behavior-level decision-making is essential for safety, trust, and regulation. We introduce CommandLM, a multimodal large language model that generates concise, human-readable behavior descriptions for ego vehicles from fused multi-sensor data. Our model processes temporally fused bird's-eye view representations from LiDAR and multi-camera inputs via a Q-Former adapter connected to a quantized, LoRA-fine-tuned large language model. Trained on our CommandLM-nuScenes dataset, CommandLM produces intent-aware, interpretable captions suitable for planner supervision and safety auditing. Experiments demonstrate strong linguistic and behavioral alignment, achieving CIDEr 0.67, and BERT-F1 0.88, substantially outperforming the BLIP-2 baseline (CIDEr 0.52, BERT-F1 0.86). In human evaluation, 58% of the generated descriptions were rated accurate, efficient and rule-compliant, confirming their real-world plausibility. While the remaining descriptions may not always select the most efficient, goal-oriented behavior, CommandLM's interpretable outputs enable downstream validation systems to identify and correct such cases, making it an effective tool for transparent behavior auditing. These results show that integrating multimodal fusion with language reasoning yields efficient and transparent behavior-level understanding for autonomous driving. We release our code and dataset at: https://github.com/b-tok/CommandLM --- ### The Lift Spectrum: How Measurement-to-Space Adaptivity Shapes Robustness in Image-Free Single-Pixel Sensing Authors: Yuyuan Han, Jingwei Li, Xiaoxia Zhang, Long Qiu, Chong Wang, Wenxuan Hao, Jiangyu Han, Xinyu Yao, Yuchen He, Hui Chen, Jianbin Liu, Huaibin Zheng Published: 2026-07-24 Categories: eess.IV, cs.CV, physics.optics arXiv: https://arxiv.org/abs/2607.22077v2 Single-pixel sensing encodes a scene as a short sequence of coded measurements, and image-free methods infer the task directly from that sequence. We show that removing image reconstruction relocates the central design problem to the lift: how 1D measurements become a 2D task representation. We organize this choice as a lift spectrum from a fixed-physics inverse, through a learned static projection, to content-adaptive retrieval. These are not interchangeable forms of reconstruction: the fixed-physics route reconstructs an image consumed at inference, whereas our spatiotemporal soft-fusion (STSF) network lifts measurements directly into task features, and task-prioritized loss scheduling (TPLS) uses a separate learned reconstruction branch only as scheduled training supervision. A probe-selected recurrent encoder and a parameter-matched lift ablation identify the STSF design. In simulation, STSF+TPLS exceeds the prior image-free baseline on three datasets at 3.13% sampling (+3.2 to +9.9 pp foreground mIoU) and remains competitive down to 0.39%. The strongest clean-trained reconstruct-then-segment baseline wins without measurement noise, but measurement noise reverses the ranking: the reconstructed task input carries a 20-70x larger normalized relative perturbation than the measurements themselves. Stressed to failure, the three lift regions exhibit distinct dominant signatures--collapse, imprinting, and coarsening. STSF+TPLS transfers without fine-tuning to a real single-pixel bench, where the reversal reappears as a proof of concept; inference takes about 14 ms per mask on an RTX 4090. Within the tested fixed-acquisition regime, measurement-to-space adaptivity therefore organizes both the clean-to-noisy operating envelope and the failure a system encounters. Code and pretrained weights: https://github.com/Hanyuyuan6/STSF-TPLS. --- ### The Lift Spectrum: How Measurement-to-Space Adaptivity Shapes Robustness in Image-Free Single-Pixel Sensing Authors: Yuyuan Han, Jingwei Li, Long Qiu, Chong Wang, Wenxuan Hao, Jiangyu Han, Xinyu Yao, Yuchen He, Hui Chen, Jianbin Liu, Huaibin Zheng Published: 2026-07-24 Categories: eess.IV, cs.CV, physics.optics arXiv: https://arxiv.org/abs/2607.22077v1 Single-pixel sensing encodes a scene as a short sequence of coded measurements, and image-free methods infer the task directly from that sequence. Removing reconstruction does not remove the difficulty: it relocates it to the lift, the map from 1D measurements to a 2D representation, which prior work treats as a trivial reshape. We recast the lift as the central design axis of image-free sensing and order methods by how strongly it adapts to its input: a fixed-physics inverse (reconstruct-then-segment), a learned static projection, or a content-adaptive retrieval; position on this lift spectrum predicts behavior as acquisition degrades. The spatiotemporal soft-fusion (STSF) network pairs a probe-selected recurrent encoder with a cross-attention lift chosen by a parameter-matched ablation, ahead of its U-Net++ decoder, and trains under task-prioritized loss scheduling (TPLS), a scheduled reconstruction prior. In simulation, STSF+TPLS surpasses the prior image-free baseline on three datasets at 3.13% sampling (+3.2 to +9.9 pp foreground mIoU) and plateaus down to 0.39%. The strongest clean-trained reconstruct-then-segment baseline wins the noiseless limit, but under calibrated measurement noise image-free inference overtakes it, for a measured reason: the reconstruction pipeline amplifies the identical measurement noise before its segmenter reads it. Each region fails in its own signature: collapse, imprinting, or coarsening. STSF+TPLS transfers without fine-tuning to a real single-pixel bench as a proof of concept, at about 14 ms per mask. Charting the lift turns a scattered design space into a map of which lift to deploy at each operating point. Code and pretrained weights: https://github.com/Hanyuyuan6/STSF-TPLS --- ### FSE: Continual Learning for Named Entity Recognition by Fast-Slow Experts Authors: Yunan Zhang, Yang Fan, Heng Li, Xiangping Wu, Qingcai Chen Published: 2026-07-24 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2607.22075v1 Continual Learning for Named Entity Recognition (CLNER) enable models to incrementally learn new entity types without forgetting previously acquired ones. However, existing methods suffer from catastrophic forgetting and insufficient exploitation of shared information across tasks. This paper proposes FSE, a Fast-Slow Experts enhanced span-based NER model for CLNER. The shared fast expert learns token-level links to efficiently filter out unlikely spans, while the task-specific slow expert performs span classification only on the remaining candidates. It stabilizes learning by promoting knowledge sharing across tasks and maintains plasticity by reducing learning burden at each task. A length-decay negative sampling strategy to mitigate span imbalance is also introduced. Extensive experiments on OntoNotes and FewNERD synthestic datasets demonstrate that FSE achieves state-of-the-art performance in CLNER scenarios, with effectiveness of each component, empirical evidence of faster convergence and expected functionality of both experts. --- ### Alleviating Regional Shortcuts for Few-Shot Class-Incremental Learning Authors: Haichen Zhou, Yazhe Lyu, Yixiong Zou, Ruixuan Li, Yuhua Li Published: 2026-07-24 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.22072v1 Few-shot class-incremental learning (FSCIL) aims to incrementally learn novel classes with only a few samples while avoiding forgetting base classes. However, current methods show a tendency to misclassify novel-class samples into base classes, which we find to be caused by the excessive focus on base-class-discriminative regions on novel-class samples. In this work, we aim to explore the underlying mechanism for an interpretation and solution. We first provide a compositional view to analyze the transferred and reused spatial patterns on novel-class samples. Then, through extensive experiments and theoretical analysis, we identify both empirically and theoretically that a shortcut exists in the model's base-class training, which naturally forms the excessive focus on only the most discriminative regions (primitives), which we term as the regional shortcut. Finally, based on this interpretation, to address this problem, we propose a compositional-learning-based method to learn two primitive sets (a common set and a discriminative set), which alleviates the regional shortcut by constraining the model to learn and utilize the common primitive set for base- and novel-class recognition. Extensive experiments on standard FSCIL benchmarks demonstrate the effectiveness of our approach, yielding consistent improvements over existing state-of-the-art methods in both accuracy and interpretability. --- ### ReCowGnition: A Realistic Biometric Benchmark for Cow Face Recognition Authors: Marco Huber, Marco Kiesewalter, Judith Louise Pieper, Bastian Kubsch, Naser Damer Published: 2026-07-24 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.22071v1 With the development of precision livestock farming and the advances in computer vision, visual animal biometrics has gained attention. Using biometric technologies that have been proven effective for humans to identify livestock can increase animal welfare as well as production efficiency. However, challenges such as complex scenarios, similar appearances, occlusions, and non-cooperative behavior, as well as the limited amount of publicly available labeled datasets, remain. In this work, we contribute a novel, publicly available cow face benchmark dataset that has been collected in a realistic automatic scenario with 6,838 images of 161 different cows at a dairy farm. In addition to the public dataset, we define two verification and four identification evaluation protocols to foster comparable research in the cow recognition research field. Further, we provide evaluation results on our dataset of six benchmark models, which include models trained on limited data, cross-species fine-tuned models, and zero-shot foundation model approaches. --- ### Rethinking Multi-Branch and Cross-Backbone Fusion for Vehicle Re-Identification under Foundation-Model Pretraining Authors: Yu Wang, Hongyu Yang Published: 2026-07-24 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2607.22068v3 Multi-branch architectures and CNN-Transformer fusion are widely believed to improve vehicle re-identification (Re-ID) by combining complementary representations. We revisit this for a DINOv3-pretrained backbone. A single DINOv3-pretrained ConvNeXt with a tuned recipe reaches 88.19 mAP on VeRi-Wild Small and 77.47 on Large from visual cues alone, within the combined evaluation and optimization noise of the strongest protocol-verified metadata-dependent multi-branch baseline, and 92.38/83.68 with training-free re-ranking. Using this baseline and retrieval-level branch diagnostics, we ask whether representational diversity still pays at this scale. In our runs, it does not. Across both benchmarks and every converged configuration, concatenating multiple heads over a shared backbone moves the best single head by under one mAP point in either direction while costing four times the embedding dimension; 99.7% of the concatenation's variance lies in 512 principal components, so the heads not only duplicate one another but each occupies a quarter of its nominal 2048 dimensions. Pushing diversity to its architectural limit, CNN versus Transformer, we grant fusion every advantage through an asymmetric frozen-anchor scheme. Every Transformer configuration still lands at least 13 mAP below the ConvNeXt backbone (13-15 for the two strongest, up to 46 for the weakest), and a paired per-query bootstrap bounds the fusion gain at +0.11 mAP (95% CI) even for the most favourable snapshot we obtained. One strong backbone with the right recipe and re-ranking is the efficiency frontier. All results use single-seed training and one foundation-model family; differences of this size are therefore reported as bounds rather than orderings, and we list falsifiers. --- ### Rethinking Multi-Branch and Cross-Backbone Fusion for Vehicle Re-Identification in the Foundation-Model Era Authors: Yu Wang, Hongyu Yang Published: 2026-07-24 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2607.22068v1 Multi-branch architectures and CNN-Transformer fusion have long been regarded as effective ways to improve vehicle re-identification (Re-ID) by combining complementary representations. In this work, we revisit this assumption in the foundation-model era through a comprehensive empirical study. A single DINOv3-pretrained ConvNeXt trained with a tuned recipe achieves 88.19 mAP on VeRi-Wild Small and 77.47 mAP on VeRi-Wild Large using visual cues alone, matching the strongest protocol-verified metadata-dependent multi-branch baseline. Applying training-free re-ranking further improves performance to 92.38 and 83.68 mAP, respectively. Using this strong baseline together with retrieval-level branch diagnostics, we evaluate whether increasing representational diversity still provides measurable gains. Across both benchmarks, concatenating multiple branches built on a shared backbone changes the best single-branch performance by less than one mAP point while increasing the embedding dimension by 4x, and the resulting representation has an effective rank close to the original feature dimension. We further study cross-backbone fusion using an asymmetric frozen-anchor strategy to combine ConvNeXt and Vision Transformer representations. Despite these favorable conditions, Transformer branches consistently remain 13-15 mAP below the ConvNeXt backbone, and paired per-query bootstrap analysis estimates the largest observed fusion gain to be only +0.11 mAP (95% confidence interval). Our results suggest that, under the evaluated setting, improving a single strong foundation-model backbone together with retrieval-stage re-ranking is more effective than increasing architectural complexity through additional branches or heterogeneous backbones. We restrict our conclusions to single-seed training and one family of foundation models and discuss conditions under which these observations may not hold. --- ### Multimodal Language Models Benchmarked Against the NRC Reactor Operator Licensing Examination: Fine-Tuning and Retrieval Strategies Authors: Isak Hwang, Yoon Pyo Lee, Syed Bahauddin Alam Published: 2026-07-24 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2607.22067v2 Competence claims for a language model in a safety-critical domain are credible when measured against a standard the domain already enforces. We evaluate an open-weight 31-billion-parameter multimodal model (Gemma 4 31B-IT) on the U.S. Nuclear Regulatory Commission Reactor Operator Generic Fundamentals Examination (GFE), scoring it paper by paper against the 80% criterion applied to every human candidate, with no rounding up. The evaluation set is a census of every GFE administered at the March sitting from 2015 to 2021, giving seven pressurized water reactor (PWR) and seven boiling water reactor (BWR) papers and 697 scored items. Eight configurations cross three model states, the base model, supervised fine-tuning (SFT) on distilled chain-of-thought rationales and retrieval-augmented fine-tuning (RAFT), with three retrieval conditions, none and BM25 retrieval over the Department of Energy Fundamentals Handbooks under fixed-size and structure-aware chunking. Out of the box it answers 51.94% correctly and passes no paper. SFT with fixed-size chunking retrieval passes 8 of 14, reaching 80.23% on PWR items and 79.77% pooled, with a Wilson interval spanning the threshold. The preferred chunking granularity reverses with training state, structure-aware before fine-tuning and fixed-size after, so chunking optimized against a base model cannot be inherited by its fine-tuned descendant. RAFT trails SFT by 2.2 to 2.3 percentage points overall, and the deficit holds in all four reactor-type and chunking strata. The pipeline runs on one workstation with no network access at run time, and the result approaches operator-level command of engineering fundamentals without reliably achieving it. --- ### Benchmarking Fine-tuning and Retrieval Strategies for a Multimodal Language Model on the NRC Reactor Operator Licensing Examination Authors: Isak Hwang, Yoon Pyo Lee Published: 2026-07-24 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2607.22067v1 The integration of large language models (LLMs) into the nuclear power industry requires outputs grounded in domain-specific knowledge. This study evaluates a 31-billion-parameter open-weight multimodal model (Gemma 4 31B-IT) on its capacity to apply nuclear knowledge by benchmarking eight model-retrieval configurations against the U.S. Nuclear Regulatory Commission (NRC) Reactor Operator licensing examination. We evaluate 14 Generic Fundamentals Examinations (GFE) from the 2015-2021 March sittings (seven pressurized and seven boiling water reactor exams) using the standard 80% human passing criterion. The base model is compared against configurations utilizing supervised fine-tuning (SFT) on Gemini-distilled chain-of-thought (CoT) rationales, retrieval-augmented generation (RAG) with BM25 sparse retrieval over the U.S. Department of Energy Fundamentals Handbook, and retrieval-augmented fine-tuning (RAFT). Within the retrieval pipeline, we compare fixed-size sliding-window chunking against structure-aware chunking. The SFT configuration with fixed-size chunking RAG met the criterion on 8 of the 14 examinations, outperforming all alternatives, whereas no configuration without fine-tuning passed any. Aggregate accuracy reached 79.7%, with a confidence interval spanning the threshold, and 80.2% on PWR items specifically. Furthermore, two regularities emerged: the preferred chunking strategy reverses depending on the model's training state, and RAFT underperforms compared to standard SFT in matching search environments. These results demonstrate which combination of fine-tuning and search approaches achieves operator-level capabilities. --- ### A Smooth Phase-Separation Model for Weak-Boundary Segmentation of Homogeneous Structures Authors: Zihan Li, Jiebao Sun, Fanghui Song, Zhichang Guo Published: 2026-07-24 Categories: cs.CV, math-ph arXiv: https://arxiv.org/abs/2607.22053v1 Segmentation of adjacent structures with similar intensity distributions remains a challenging problem in image analysis, particularly when object boundaries are weak or ambiguous. Under such conditions, classical variational models may suffer from degenerated image-driven forces, leading to boundary leakage or undesired merging of neighboring regions. To address these limitations, we propose a smooth phase-separation variational model based on the Cahn--Hilliard equation for weak-boundary segmentation of homogeneous-appearance structures. The proposed framework integrates softmax-based region fitting with Cahn--Hilliard phase-field regularization to maintain interface discrimination under weak image-driven forces. We further introduce a mixed $L^2-H^{-1}$ gradient flow, which preserves higher-order interfacial regularization while allowing adaptive changes of phase masses, establish the continuous energy dissipation law, and prove the existence and uniqueness of weak solutions in the natural solution class. For numerical computation, we develop a stabilized scalar auxiliary variable (SAV) scheme that is linear, FFT-based, and satisfies a modified discrete energy dissipation law. Numerical experiments on synthetic and medical images demonstrate that the proposed method effectively separates adjacent homogeneous structures across weak boundaries and achieves competitive segmentation accuracy and improved boundary localization compared with representative variational, phase-field, and deep learning methods. --- ### Multiplicity of Stable Attractors in Disordered Neural Models Authors: Raffaele Marino, Roberto Livi, Antonio Politi Published: 2026-07-24 Categories: cond-mat.dis-nn, cond-mat.stat-mech, cs.AI, nlin.CD arXiv: https://arxiv.org/abs/2607.22047v1 We show how large-deviation statistics allows one to obtain reliable estimates of the multiplicity of stable fixed-points in a model of neural ordinary differential equations previously employed in computational tasks. The result is obtained by developing a suitable perturbative method in the amplitude of the disorder. It turns out that for not-too-large coupling strengths there are no qualitative differences between the symmetric case, when the dynamics is a purely gradient evolution, and the asymmetric case, when limit cycles and chaos can, in principle, arise. The selection of this specific model is dictated by pedagogical reasons, but we are confident that the approach can be extended to other many-degree-of-freedom dynamical models characterized by different classes of random coupling matrices. --- ### CEL: Comprehensive Counterfactual Explanations Library and Benchmark Authors: Oleksii Furman, Łukasz Lenkiewicz, Marcel Musiałek, Maciej Zięba Published: 2026-07-24 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2607.22045v2 Counterfactual explanations are a prominent approach in explainable artificial intelligence (xAI), providing actionable guidance on what input changes would alter a model's prediction to a desired outcome. While early methods primarily focused on minimal feature changes, recent work incorporates additional properties such as sparsity, actionability and plausibility. Despite this progress, fair and systematic evaluation remains challenging. Existing studies often rely on different data splits, predictive models, and evaluation metrics, which limits objective comparison across methods. To fill this gap, we introduce CEL (Counterfactual Explanations Library), a unified library and benchmark for counterfactual explanations designed to support consistent implementation and evaluation. CEL includes 18 datasets of varying size and complexity and provides implementations or reimplementations of 14 widely used counterfactual methods. Using this standardized setup, we conduct a comprehensive quantitative comparison across a variety of methods on datasets that differ in size, number, and types of attributes. The evaluation protocol incorporates multiple complementary metrics capturing validity, coverage, sparsity, proximity, and distributional plausibility, including density- and outlier-based measures to assess the realism of generated counterfactuals. To the best of our knowledge, this is the first comprehensive benchmark that systematically evaluates recent counterfactual explanation methods within a unified and reproducible framework. While prior libraries and benchmarking efforts exist in the literature, many are outdated, limited in scope, or lack consistent evaluation protocols. The proposed benchmark aims to improve reproducibility, enable fair comparison, and establish a workbench for the development of future counterfactual explanation methods. --- ### Scaling Native Multimodal Pre-Training From Scratch Authors: Haoyuan Wu, Aoqi Wu, Hai Wang, Jiajia Wu, Jinxiang Ou, Bei Yu Published: 2026-07-24 Categories: cs.CL, cs.CV arXiv: https://arxiv.org/abs/2607.22043v1 Although large language models (LLMs) exhibit remarkable reasoning capabilities, their reliance on text-only pre-training restricts the perception of the multimodal physical world. Native multimodal pre-training avoids this limitation by training models from scratch on multimodal inputs, thereby achieving deep cross-modal integration and mitigating optimization asymmetries inherent to traditional late-fusion architectures. Despite these advantages, the scaling properties of this paradigm remain systematically uncharacterized. To address this gap, we investigate the optimal model size and token count for training a transformer-based vision-language model under a fixed computational budget. We demonstrate that minimal objective loss adheres to a predictable compute law, whereas compute-optimal model sizes and token counts scale as power laws. Notably, language and multimodal objectives manifest distinct scaling behaviors. The language allocation law is largely invariant to the composition of the data, indicating stable language learning regardless of the multimodal data ratio. Conversely, the multimodal allocation law is highly sensitive to this composition. Specifically, text-heavy mixtures become compute-efficient only at larger model scales, shifting the optimal resource allocation toward greater model capacity. Additionally, by modeling the influence of data composition on compute laws and allocation exponents, we derive an efficiency frontier specifying precise configurations of model size, token count, and data mixture. Downstream evaluations further reveal that native multimodal pre-training induces positive cross-modal transfer, thereby enhancing pure-text spatial reasoning and enabling robust multimodal in-context learning. In summary, this empirical research establishes the essential groundwork for predictably scaling multimodal foundation models. --- ### Developing and Validating the Spanish Version of the Large Language Models Dependency Scale (LLM-D12-SP) Authors: Tran Gia Bao, Mo El-Haj, Sameha Al-Shakhsi, Antonio Garcia-Cabot, Raian Ali, Ala Yankouskaya Published: 2026-07-24 Categories: cs.CL, cs.CY arXiv: https://arxiv.org/abs/2607.22041v1 There is a growing need for reliable and culturally validated instruments to assess psychological dependency on large language models (LLMs), particularly as LLMs are increasingly used for task execution, decision-making, and communication in organizational and work-related settings. This need is especially relevant for Spanish-speaking populations, where LLM adoption is rapidly expanding, yet validated psychometric tools remain scarce. The present study reports the first validation of the Spanish version of the Large Language Model Dependency Scale (LLM-D12-SP), extending prior validations conducted in English- and Arabic-speaking samples. The LLM-D12 is a two-dimensional instrument assessing Instrumental Dependency (reliance on LLMs for performing tasks and supporting decisions) and Relationship Dependency (psychological reliance on LLMs for companionship and social interaction). A total of 386 Spanish-speaking participants (M = 28.0 years, SD = 6.1; 55% male) completed the LLM-D12-SP. Confirmatory factor analysis supported the original two-factor structure. The scale demonstrated good internal consistency (Cronbach's alpha = 0.89 total; 0.86 Instrumental; 0.85 Relationship). Discriminant validity analyses indicated that the two subscales represent related but distinct constructs. External validation showed that both dependency dimensions were positively associated with internet addiction and perceived trustworthiness of LLMs, while showing weak or no association with need for cognition. Together with prior English and Arabic validations, these findings establish cross-linguistic support for the scale's structure and provide a psychometrically sound tool for investigating psychological aspects of LLM use in organizational contexts. --- ### Enough is as good as a feast: A Comprehensive Analysis of How Reinforcement Learning Mitigates Task Conflicts in LLMs Authors: Zixuan Ren, Jinliang Lu, Junhong Wu, Yang Zhao, Dai Dai, Hua Wu, Haifeng Wang, Chengqing Zong Published: 2026-07-24 Categories: cs.CL arXiv: https://arxiv.org/abs/2607.22039v1 Model merging plays a crucial role in consolidating multiple specialized models into a single, unified model, especially in the era of large language models (LLMs). Recent research has primarily focused on developing strategies to enhance merging performance with the trained models, while the impact of training paradigms, such as supervised fine-tuning (SFT) and reinforcement learning (RL), on the effectiveness of model merging remains underexplored. In this study, we systematically explore the merging behavior of RL-trained LLMs compared to those trained with traditional SFT. Through comprehensive evaluations across five representative tasks, we find that RL significantly reduces task conflicts and results in less performance degradation after merging, making RL-trained models particularly well-suited for this process. To unearth the reasons behind the superior suitability of RL for model merging, we conduct extensive empirical experiments and theoretical analyses. Our findings highlight three key factors: (1) On-policy training data in RL control the gradient updates in a smaller magnitude, reducing the risk of overwriting existing knowledge for other tasks in the model. (2) The RL optimization objective, which favors ``\textit{enough is as good as a feast}", progressively reduces the magnitude and the number of conflict parameter updates as the model converges. (3) Joint optimization of positive and negative examples in RL steers the model towards an unbiased task-specific parameter subspace, ensuring robust performance while further preventing parameter conflicts. --- ### Sparse by Command: Task-Conditional Compute Skipping for Multi-Task Inference Accelerators Authors: Afzal Ahmad, Gaoyu Mao, Shoubo Hu, Hui-Ling Zhen, Mingxuan Yuan, Xinyu Chen, Wei Zhang Published: 2026-07-24 Categories: cs.AR, cs.AI arXiv: https://arxiv.org/abs/2607.22038v1 Multi-task inference models share a single backbone across diverse tasks, yet execute identical computation regardless of which task is active - wasting energy and cycles on task-irrelevant operations. We observe that the task command, typically available before inference begins, provides a free signal that can be exploited to skip unnecessary computation at the hardware level. We present a HW/SW co-designed approach in which a lightweight gating network, trained jointly with the backbone, predicts per-tile binary execution masks conditioned on the task input. Each tile corresponds to a fixed group of output channels (the native scheduling granularity of the accelerator), enabling masked tiles to be skipped with zero overhead. This yields a task-dependent reduction in compute, where each command activates only the subset of the network it requires, without changes to the model architecture or inference pipeline. We co-design the full system stack: a command-conditioned training procedure that learns hardware-aligned tile masks under a sparsity objective; an instruction set architecture whose instructions carry per-tile bitmask fields, allowing the hardware to skip masked tiles without software intervention; and a tiled inference accelerator with configurable parallelism, double-buffered memory, and INT8 datapath that natively supports sparse tile execution. We prototype on an AMD/Xilinx Alveo U50 FPGA and evaluate on a closed-loop visuomotor driving task in CARLA autonomous driving simulator. Task-conditional sparsity reduces FLOPs by 66-76% while maintaining driving quality. On-device latency decreases by 51-59%, from 9.12 ms to 3.74-4.44 ms (2.1-2.4x speedup), with energy per inference dropping from 263 to 108-128mJ. --- ### On the Runtime Analysis of Reinforcement Learning Hyper-Heuristics Authors: Pietro S. Oliveto, Zhenyu Wang, Peizhou Wu, Mengqing Xu Published: 2026-07-24 Categories: cs.NE arXiv: https://arxiv.org/abs/2607.22036v1 Selection Hyper-heuristics (HHs) automate algorithmic design by selecting from a set of low-level heuristics which one to apply at each stage of the optimisation process. Several impressive results have been recently rigorously proven regarding the performance of selection hyper-heuristics (HHs) for standard benchmark functions. However, the learning mechanisms employed by these HHs are considerably simplified compared to the machine learning techniques typically used in real world applications. In this paper we analyse a Reinforcement Learning Hyper-heuristic (RLHH) from the literature. The only previous result available proved that for a wide range of parameter settings, RLHH does not learn to select heuristics appropriately for the standard LeadingOnes benchmark function. In this paper, we rigorously prove that with appropriate parameter values RLHH equipped with two random local search operators, RLS_1 and RLS_2 optimises the LeadingOnes benchmark function in the best possible expected runtime achievable with the two operators up to lower order terms. Experiments show that for realistic problem sizes it is faster than the Generalised Random Gradient HH which was previously proven to also have optimal expected runtime up to lower order terms. --- ### DCS: A Unified Conditional Sensitivity Framework for Cross-Modal Copyright Infringement Detection Authors: Xiafeng Man Published: 2026-07-24 Categories: cs.LG arXiv: https://arxiv.org/abs/2607.22035v1 Currently, most foundation models can reproduce or strongly depend on copyrighted training content, but output similarity alone is insufficient for infringement detection, because similar outputs may also arise from public-domain concepts, common stylistic conventions, or ordinary statistical generalization. In this paper, we develops a unified post-hoc detection framework that treats copyright infringement evidence as a counterfactual conditional distribution shift: a protected target is suspicious when the model's behavior under aligned conditions would change measurably if that target were included in, or removed from, the training process. We formalize this view through conditional differential privacy and introduce Dual-Branch Conditional Sensitivity (DCS), an operational statistic that measures the observable gap between two locally perturbed model states. Specifically, the proposed DCS framework creates a learning branch and an unlearning branch around the deployed model, connects their displacement to the unavailable counterfactual retraining effect through influence-function analysis, and bounds the observable sensitivity by the counterfactual privacy-budget surrogate, local curvature, training-set scale, and perturbation step size. To distinguish target-specific memorization from generic fine-tuning instability, we further define a calibrated detection statistic that subtracts the sensitivity measured under orthogonal conditions. The DCS framework is instantiated for ridge-regularized linear regression, conditional diffusion models, autoregressive language models, and multimodal models. These instantiations show how the same principle can be evaluated through prediction gaps, image-embedding divergence, token-distribution or entropy shifts, and cross-modal representation changes. --- ### Small Vision-Language Models Know When They Are Wrong But Cannot Say So: A Two-Model Study of Stated versus Internal Confidence Under Realistic Image Degradation Authors: M M Asif Ferdous Published: 2026-07-24 Categories: cs.CV, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2607.22034v1 Vision-language models (VLMs) are increasingly deployed on consumer hardware where input images are degraded by compression, camera shake, and poor lighting. In such settings, a reliable uncertainty signal matters more than raw accuracy, because it determines when a system should defer rather than answer. We evaluate two small open-weight VLMs -- Qwen2-VL-2B-Instruct and SmolVLM-Instruct -- across six realistic photographic degradations at three severity levels, comparing two confidence signals: the confidence the model states in natural language, and the model's own mean token probability over its generated answer. Across 3,800 predictions, we find a large and consistent gap. Verbalized confidence in Qwen2-VL is almost constant (mean 0.87-0.90 across all conditions) and detects its own errors at chance level (AUROC 0.39-0.75, typically ~0.50), while internal token probability from the same model separates correct from incorrect answers with AUROC 0.92-0.99. In SmolVLM, verbalized confidence proved largely unobtainable: across three prompt templates, only one of five pilot attempts produced a parseable confidence value, while internal probability again yielded above-chance error detection (AUROC 0.54-0.92). Both models fail in the same place: under severe underexposure, accuracy collapses (0.99->0.22 for Qwen2-VL, 0.97->0.42 for SmolVLM) while both confidence signals barely move, and internal error-detection falls to chance. We conclude that small VLMs encode usable self-knowledge that their verbalized output does not express, that internal probability is therefore the better deferral signal in constrained deployment, and that neither signal should be trusted under severe low-light conditions. --- ### DWT-Fusion: A Signal-Based Framework for Training-Free LLM-Generated Text Detection Authors: Mehmet Batuhan Özdaş, Murat Osmanoğlu Published: 2026-07-24 Categories: cs.CL arXiv: https://arxiv.org/abs/2607.22026v1 Detecting LLM-generated text remains challenging under zero-shot and training-free conditions, especially when detectors must generalize across datasets, domains, and unseen generators. While existing training-free approaches exploit language-model statistics as detection signals, they typically characterize a text through global measures that summarize overall model behavior. Consequently, potentially informative local and multiscale variations in token-level predictability may remain underutilized. Motivated by this observation, we introduce DWT-Fusion, a training-free signal-based framework for detecting LLM-generated text using discrete wavelet analysis of token-level log-probability sequences produced by a proxy causal language model. The proposed framework analyzes these sequences through wavelet-based multiresolution signal representations and derives detection signals from localized probability dynamics. We further evaluate four training-free voting variants, including equal-weight hard voting, equal-weight soft voting, calibration-weighted hard voting, and calibration-weighted soft voting, to combine multiple wavelet configurations without training a supervised meta-classifier. We evaluate the framework on HC3, M4, and MAGE using GPT-Neo-2.7B, GPT-J-6B, Falcon-7B, and LLaMA-3-8B as proxy models. The best single wavelet configurations achieve AUROC values of 0.9872, 0.8185, and 0.7138 on HC3, M4, and MAGE, respectively. With calibration-weighted voting, the best ensemble variants further improve AUROC to 0.9919, 0.8477, and 0.7471. These findings show that DWT-based multiresolution scoring and calibration-guided voting fusion provide effective and interpretable signals for training-free LLM-generated text detection. ---