# Research Papers — 2026-06 · bundle page 255 of 260 > Full-text markdown of papers #12701–12750 of 12993 published in 2026-06, newest first. AI-readable mirrors of the full 12993-paper 2026-06 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2026-06/page/255 [← Previous bundle](https://aipod.dev/papers/archive/2026-06/page/254.md) [Next bundle →](https://aipod.dev/papers/archive/2026-06/page/256.md) ### Multimodal Action Diffusion for Robust End-to-End Autonomous Driving Authors: Jorge Daniel Rodríguez-Vidal, Diego Porres, Gabriel Villalonga Pineda, Antonio M. López Peña Published: 2026-06-01 Categories: cs.CV arXiv: https://arxiv.org/abs/2606.02105v1 End-to-End Autonomous Driving (E2E-AD) systems have largely converged on predicting intermediate trajectory waypoints, delegating final control to hand-crafted controllers with GPS access. Direct control-signal prediction (outputting throttle, steer and brake in an end-to-end fashion) remains underexplored, and critically, the role of action multimodality in such systems is not well understood. We argue that moving beyond deterministic, single-action outputs is not merely a modelling choice, but a key driver of driving performance, representational quality, and training stability. To validate this, we introduce the Action Diffusion Transformer (ADT), an anchor-free diffusion transformer trained with a MSE objective that natively models the multimodal distribution of plausible driving actions. Rather than committing to a single deterministic command, ADT generates K action candidates and selects the most suitable one at inference via Nearest Neighbour Matching (NNM). Beyond strong benchmark numbers, we show that action multimodality yields measurable benefits in learned representations and behavioral consistency, effects that deterministic architectures cannot replicate. ADT surpasses previous state-of-the-art on the challenging closed-loop Bench2Drive benchmark while achieving ten times lower latency, demonstrating that expressive, multimodal action modelling is both practically efficient and conceptually essential for robust end-to-end driving. --- ### It does what it says on the tin: safe synthetic data from coarsened margins Authors: Gillian M Raab Published: 2026-06-01 Categories: stat.ML, cs.LG, stat.AP arXiv: https://arxiv.org/abs/2606.02101v3 This paper proposes a method of creating synthetic data (SD) that will have two important advantages for the user compared to other methods currently available. The first is transparency; unlike other methods, the person in receipt of the SD will know which of the relationships between variables in the original data will be approximately maintained in the SD. The second is a guarantee that the SD is derived from information that has already been judged to be free of disclosure risk. This is achieved by first defining and calculating the margins where relationships between variables will be maintained in the SD. Each margin will then be subject to statistical disclosure control (SDC) to the standards defined by the data custodian, e.g. top-coding and bottom-coding, combination of small categories and/or modifying small counts. Further adjustment of the curated margins is advised by coarsening all counts in the table to multiples of the disclosure limit. These adjusted margins are used to create SD by the Iterative Proportional Fitting (IPF) algorithm. The practical steps involved in creating such SD are illustrated using data from the 1901 Census of Scotland. --- ### PortBERT: Navigating the Depths of Portuguese Language Models Authors: Raphael Scheible-Schmitt, Henry He, Armando B. Mendes Published: 2026-06-01 Categories: cs.CL arXiv: https://arxiv.org/abs/2606.02100v1 Transformer models dominate modern NLP, but efficient, language-specific models remain scarce. In Portuguese, most focus on scale or accuracy, often neglecting training and deployment efficiency. In the present work, we introduce PortBERT, a family of RoBERTa-based language models for Portuguese, designed to balance performance and efficiency. Trained from scratch on over 450 GB of deduplicated and filtered mC4 and OSCAR23 from CulturaX using fairseq, PortBERT leverages byte-level BPE tokenization and stable pre-training routines across both GPU and TPU processors. We release two variants, PortBERT base and PortBERT large, and evaluate them on ExtraGLUE, a suite of translated GLUE and SuperGLUE tasks. Both models perform competitively, matching or surpassing existing monolingual and multilingual models. Beyond accuracy, we report training and inference times as well as fine-tuning throughput, providing practical insights into model efficiency. PortBERT thus complements prior work by addressing the underexplored dimension of compute-performance tradeoffs in Portuguese NLP. We release all models on Huggingface and provide fairseq checkpoints to support further research and applications. --- ### WebSpline: Structure-Informed Splines for Real-Time 3D Gaussians from Monocular Videos Authors: Jongmin Park, Jeonghwan Yun, Minh-Quan Viet Bui, Munchurl Kim Published: 2026-06-01 Categories: cs.CV arXiv: https://arxiv.org/abs/2606.02096v1 Dynamic scene reconstruction from monocular videos remains highly challenging, as existing methods often struggle to balance global structural coherence and local fine-grained details under limited multi-view cues. To address this challenge, we propose WebSpline, a novel dynamic 3D Gaussian framework that enables structurally coherent and high-fidelity reconstruction from monocular videos with fast rendering. The core of WebSpline is the Structure-Informed Spline (SIS) representation, which models each dynamic Gaussian trajectory using a learnable cubic Hermite spline whose motion is structurally organized with an auxiliary Structural Proxy Graph (SPG). The proposed framework is optimized in two stages: (i) in the first stage, the SPG is initialized from 2D point tracks and refined with temporal rigidity regularization to establish structural coherence for moving objects across the sequence; and (ii) in the second stage, the SIS representation is initialized from the refined SPG and optimized under both spatial and structural neighborhood constraints. At inference, Gaussian motion is obtained solely by evaluating the learned SIS, enabling fast rendering. Extensive experiments on the challenging monocular dynamic scene benchmarks, iPhone and NVIDIA, demonstrate that our WebSpline achieves state-of-the-art rendering quality while rendering over 10 times faster than WorldTree, the second-best method on the iPhone dataset. --- ### The Role of Ambiguity in Error Prediction via Uncertainty Quantification Authors: Ieva Raminta Staliūnaitė, James Bishop, Andreas Vlachos Published: 2026-06-01 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2606.02093v1 The task of Error Prediction, namely predicting whether a model output is correct, is commonly tackled with Uncertainty Quantification (UQ). However, while uncertainty metrics capture when models lack knowledge or capacity to make a prediction, they also reflect aleatoric uncertainty, which is inherent in the model input and context. This paper presents a method for improving error prediction for Large Language Models (LLMs), by disentangling input ambiguity from UQ signal. We conduct experiments on the task of Question Answering (QA) with six UQ metrics and show that UQ metrics are more predictive of errors on unambiguous instances than on questions with multiple plausible answers. We use Gated Experts and Selective Prediction to incorporate gold and predicted ambiguity labels into the error prediction pipeline. We find that ambiguity information improves error prediction scores across model families, training and evaluation paradigms, datasets (including allegedly unambiguous ones), and sources of aleatoric uncertainty, yielding improvements of over 10 points of PRR for individual UQ metrics on standard datasets. --- ### LALE: Lightweight-Transformer Architecture for Land-Cover Estimation Authors: Ümit Mert Çağlar, Alptekin Temizel Published: 2026-06-01 Categories: eess.IV, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2606.02092v2 Semantic segmentation of remote sensing imagery requires models that capture both global context and local detail under tight computational budgets. Prior work typically optimizes for one of these axes: attention for global context, convolution for local detail, or compactness for efficiency. While hybrid approaches aim to capture both, they require architectural changes and encoder backbones with computational overhead, limiting efficiency and performance. We present LALE (Lightweight-transformer Architecture for Land-cover Estimation), an end-to-end remote sensing image segmentation architecture, that bifurcates its encoder by resolution: lightweight ConvMixer stages handle high-resolution local features, while transformer stages handle low-resolution global context, confining the quadratic cost of self-attention to deep, downsampled feature maps. An all-MLP multi-scale decoder, together with RMSNorm and StarReLU throughout, further reduces compute and parameter count. On the large-scale ARAS400k remote-sensing segmentation benchmark, LALE establishes a strong efficiency-performance trade-off against CNN, transformer, and hybrid baselines. Our smallest variant, (just 1.6M parameters), reaches within 2.6 F1 points of the best baseline (UPerNet) while using 4.5x fewer parameters, 7x less storage, 17x fewer GMACs, and delivering 1.8x higher throughput. The codebase for LALE is publicly available at https://github.com/caglarmert/LALE. --- ### DFlare: Scaling Up Draft Capacity for Block Diffusion Speculative Decoding Authors: Jiebin Zhang, Zhenghan Yu, Song Liu, Eugene J. Yu, Zheng Li, Dawei Zhu, Jiangshan Duo, Weimin Xiong, Yifan Song, Guanghua Yu, Jianchen Zhu, Sujian Li Published: 2026-06-01 Categories: cs.CL arXiv: https://arxiv.org/abs/2606.02091v2 Block diffusion speculative decoding accelerates LLM inference by predicting all tokens within a block simultaneously for the target model to verify in parallel. Predicting an entire block at once requires a sufficiently capable draft model and effective utilization of the target model's internal knowledge. However, the state-of-the-art method DFlash constrains all draft layers to share a single fused representation derived from only a few target layers, limiting per-layer expressiveness and hindering further scaling of draft capacity. In this paper, we present \modelname, which flares out the narrow conditioning bottleneck of DFlash through a lightweight layer-wise fusion mechanism: each draft layer attends to its own learnable combination of a broad set of target layers at negligible overhead, simultaneously injecting richer target knowledge and providing every draft layer with a distinct input. This enhanced per-layer expressiveness enables scaling the draft model to deeper architectures with consistent gains. We further scale training data from 800K to 2.4M samples to fully exploit the enlarged capacity. On six benchmarks spanning mathematical reasoning, code generation, and conversation, \modelname attains average wall-clock speedups of 5.52x on Qwen3-4B, 5.46x on Qwen3-8B, and 3.91x on GPT-OSS-20B, improving over DFlash by roughly 11\%, 8\%, and 5\% respectively. Our code is available at https://github.com/Tencent/AngelSlim. --- ### FocusDiT: Masking Queries in Diffusion Transformers for Fine-grained Image Generation Authors: Xueji Fang, Liyuan Ma, Jianhao Zeng, Jinjin Cao, Mingyuan Zhou, Guo-Jun Qi Published: 2026-06-01 Categories: cs.CV arXiv: https://arxiv.org/abs/2606.02090v2 Diffusion transformer (DiT) has been widely adopted in the generative diffusion field, advancing the denoising of query tokens through attention and Feed-Forward (\text{FFN}) layers. FFN actually acts as the key-value vocabulary for decoding visual contents where the value embeds the visual semantical knowledge. We present that focusing on critical query tokens corresponding to more complex details and encouraging the model to improve these tokens is essential for fine-grained visual generation. To this end, we propose FocusDiT, which applies a Masking scheme to focus on critical query tokens that are exclusively fed into FFN. The masked queries can retrieve visual tokens from the FFN vocabularies, and use them to decode their visual details. Extensive text-to-image experiments validate the effectiveness of token masking in enhancing generative performance. --- ### Decision-calibrated prediction sets for robust power system operations Authors: Akylas Stratigakos, Honglin Wen, Elina Spyrou, Pierre Pinson Published: 2026-06-01 Categories: math.OC, stat.ML arXiv: https://arxiv.org/abs/2606.02081v1 Robust optimization offers a tractable approach to balance operating costs and reliability in power systems dominated by weather-dependent renewable uncertainty, but its performance depends critically on the uncertainty set. Standard data-driven approaches often calibrate uncertainty sets to attain predictive coverage, which can produce unnecessarily large sets and costly operating decisions. In contrast, we introduce decision-calibrated prediction sets and embed them as uncertainty sets in robust optimization problems; these are conditional multivariate prediction sets where calibration is defined in terms of the reliability of downstream decisions, rather than in terms of the coverage. First, we learn these conditional prediction sets as sub-level sets of norm-based score functions represented by partially input-convex neural networks, capturing contextual information and multivariate dependence while preserving convexity and tractability in downstream robust formulations. Second, inspired by conformal risk control, we calibrate a score-threshold parameter that sets the volume of the uncertainty set, thereby controlling the expected violations of downstream operational constraints. We apply our approach to 15-minute-ahead reserve scheduling with network-constrained deliverability, which we formulate as a robust DC optimal power flow problem with affine recourse. Numerical experiments show that decision-calibrated sets attain prescribed constraint-satisfaction targets within about three percentage points, whereas standard coverage-based calibration systematically exceeds these targets by more than eleven percentage points, leading to larger sets and higher operating costs. --- ### Agentic-J: An AI Agent for Biological Microscopy Image Analysis Authors: Lukas Johanns, Marilin Moor, Davide Panzeri, Yu Zhou, Xinyi Chen, Nora F. K. Pauly, Zixuan Pan, Matthias Gunzer, Andreas Müller, Yiyu Shi, Hedi Peterson, Jianxu Chen Published: 2026-06-01 Categories: cs.MA, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2606.02080v1 Biological image analysis increasingly demands integration across heterogeneous tools, programming environments, and domain knowledge that few researchers can command simultaneously. We present Agentic-J, a containerised, multi-agent AI assistant, primarily for ImageJ/Fiji that enables biologists to specify analysis tasks in natural language, from nuclei segmentation and cell tracking to multi-condition quantification. The agent generates executable scripts organised into a documented project structure, so every analysis decision is traceable and the workflow can be reproduced or shared. The specialised sub-agents handle plugin management, code generation, debugging, quality assurance, and statistical reporting. In this paper we introduce the system's design, demonstrate real biological microscopy image analysis workflows, and detailed the technical implementation. --- ### FACT: A Simple and Efficient Framework for Active Finetuning Authors: Wenshuai Xu, You Song, Yuzhuo Cui, Minjie Ren, Qingjie Liu, Zhenghui Hu Published: 2026-06-01 Categories: cs.CV arXiv: https://arxiv.org/abs/2606.02079v1 The main goal of active finetuning is to improve a pretrained model's performance on a specific task or domain by finetuning it with carefully selected informative or challenging data. Previous research has predominantly focused on the active aspect (i.e., data selection) while uniformly employing full finetuning for model adaptation, which inevitably distorts pretrained features due to distribution shift. This issue becomes particularly pronounced when the model size is large relative to the finetuning data quantity, leading to heightened overfitting risks. To address this critical gap, we formally outline the FiAF task that emphasizes systematic exploration of finetuning methodologies in active learning. We propose FACT, a three-phase hierarchical finetuning framework featuring both efficiency and simplicity, specifically designed for active finetuning scenarios. Our comprehensive experiments span: (1) Three major dataset categories encompassing classic (CIFAR10, CIFAR100, ImageNet-1k), imbalanced (CIFAR10-LT, CIFAR100-LT), and fine-grained (StanfordCars, FGVCAircraft) image classification datasets, each evaluated under 3-5 distinct sampling ratios; (2) Diverse pretrained architectures including Convolutional Neural Network (ConvNeXt), Vision Transformer (ViT), and Vision LSTM (ViL) networks; (3) A systematic investigation of frozen feature augmentation (FroFA) strategies. (4) A comprehensive and rigorous analysis of efficiency and generalizability. The results demonstrate significant improvements with strong generalization and robustness. Notably, under low sampling ratios, our framework achieves remarkable performance gains of over 20% on the ViT model for CIFAR10, CIFAR100, and ImageNet-1k benchmarks. This systematic approach establishes new state-of-the-art performance while maintaining parameter efficiency, proving particularly effective when labeled data is scarce. --- ### Beyond $\ell_2$-norm and $\ell_\infty$-norm: A Curvature-Inspired $\ell_p$-Norm Scheme for Deep Neural Networks Authors: Jianhao Xu, Zhuang Yang Published: 2026-06-01 Categories: cs.LG arXiv: https://arxiv.org/abs/2606.02078v1 The existing optimizers for deep neural networks (DNNs) typically rely on either the $\ell_2$ norm or the $\ell_\infty$ norm, resulting in optimizers that do not adapt well to substantial changes in curvature across parameter dimensions. Generally, the training process of DNNs often exhibits strong curvature anisotropy in the early period, whereas in the later period, the training process of DNNs tends to move toward flatter regions with weaker anisotropy. Particularly, optimizers based on the \(\ell_2\)-norm are usually dominated by high-curvature directions, restricting updates of optimizers along with lower curvature direction and thus leading to a slower convergence rate. While optimizers based on the \(\ell_\infty\)-norm are prone to oscillations in flatter regions, due to the coordinate-wise updates of the same magnitude. To address these two extreme cases generated by $\ell_2$ and $\ell_\infty$ norms, we propose a novel $\ell_p$-norm scheme with a dynamical value of $p$ and incorporate it into stochastic gradient descent (SGD) and SGD with momentum (SGDM), leading to two novel optimizers with better generalization performance: ${\ell_p}$-SGD (LPSGD) and ${\ell_p}$-SGDM (LPSGDM). Particularly, the resulting optimizers suppress the dominance of high-curvature directions in the early period by utilizing a large $p$ ($p>2$), followed by a gradual decrease of $p$ toward 2 to enable more stable and refined updates, where the latter process is motivated by the cosine annealing strategy. We establish theoretical guarantees of the resulting algorithms and analyze that both LPSGD and LPSGDM achieve an \(O(T^{-1/2})\) convergence rate for the nonconvex setting. Extensive experiments are conducted on benchmark datasets, including CIFAR-10, CIFAR-100, and ImageNet-1K, with multiple DNNs such as VGG-11, ResNet-18, and ResNet-50. --- ### Planar Symmetric Pattern Generation Authors: Ning Lin, Luxi Chen, Huaguan Chen, Jiacheng Cen, Chongxuan Li, Wenbing Huang, Hao Sun Published: 2026-06-01 Categories: cs.LG arXiv: https://arxiv.org/abs/2606.02073v2 Generating objects with specific symmetries is essential in various real-world scenarios. However, adapting existing 2D continuous representations to enforce planar group symmetry remains a challenge, as the transformation of non-reflective group elements may disrupt continuity. To overcome this limitation, we propose a symmetrization framework for arbitrary planar groups. Our method transforms any 2D continuous representation into a symmetric one while preserving continuity. We provide the mathematical formulation of this representation, demonstrate its approximation capability for symmetric functions, and detail the construction methodology. We validate our approach through three visual design tasks (pattern design, paper-cutting design and stylized topology design) and one material design task. Experiments confirm that our representation enables effective symmetry control and demonstrate its broader applicability. --- ### Planar Symmetric Pattern Generation Authors: Ning Lin, Luxi Chen, Huaguan Chen, Jiacheng Cen, Chongxuan Li, Wenbing Huang, Hao Sun Published: 2026-06-01 Categories: cs.LG arXiv: https://arxiv.org/abs/2606.02073v1 Generating objects with specific symmetries is essential in various real-world scenarios. However, adapting existing 2D continuous representations to enforce planar group symmetry remains a challenge, as the transformation of non-reflective group elements may disrupt continuity. To overcome this limitation, we propose a symmetrization framework for arbitrary planar groups. Our method transforms any 2D continuous representation into a symmetric one while preserving continuity. We provide the mathematical formulation of this representation, demonstrate its approximation capability for symmetric functions, and detail the construction methodology. We validate our approach through three visual design tasks (pattern design, paper-cutting design and stylized topology design) and one material design task. Experiments confirm that our representation enables effective symmetry control and demonstrate its broader applicability. --- ### Fast and Lightweight Novel View Synthesis with Differentiable Multiplane Image Authors: Kaidi Zhang, Guanxu Zhu Published: 2026-06-01 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2606.02068v1 Recently, novel view synthesis has witnessed remarkable progress, with mainstream methods such as Neural Radiance Fields (NeRF) and 3D Gaussian Splatting (3DGS) delivering impressive results. However, these approaches often struggle to balance rendering speed and model size, and their optimization-based training can be highly time-consuming. Furthermore, they typically rely on dense observations, often failing to produce satisfactory results under sparse-view conditions. Although feed-forward reconstruction significantly reduces the optimization time of 3DGS, its pixel-aligned formulation generates millions of Gaussians from a single image, severely limiting its practical deployment on mobile devices. To address these limitations, we revisit the Multiplane Image(MPI) representation, which represents scenes using a compact set of planar layers for efficient novel view synthesis. Leveraging recent advances in visual foundation models, we utilize predicted point maps for reliable geometric initialization, followed by differentiable optimization. To address the issues of holes and artifacts in sparsely initialized MPI, we introduce one-step diffusion, which participates in both the differentiable optimization of MPI and the postprocessing of rendering results. Compared with a representative GS-based method, our approach is 30.7% faster and uses only 14.8% of its model size, while achieving competitive synthesis quality on front-view scenarios --- ### Ablating Archetypes: The Stability of Archetypal SAEs is an Artifact of Initialization and Metric Design Authors: Michał Brzozowski, Neo Christopher Chung Published: 2026-06-01 Categories: cs.LG arXiv: https://arxiv.org/abs/2606.02061v1 Dictionary learning with sparse autoencoders (SAEs) produces overcomplete bases from neural network activations that are often interpretable and reduces polysemanticity. However, features from SAEs vary substantially across random seeds -- a problem known as instability. Archetypal SAEs (Fel et al., 2025) were proposed as a general dictionary-learning intervention for more reliable concept extraction, and report more stable dictionaries at the end of training. We demonstrate that the stability claimed by archetypal SAEs is a result of setting identical initialization across multiple runs. Through our analyses, we attempt to clarify two distinct notions in mechanistic interpretability that may be ambiguously used: stability is agreement between two independently trained models, whereas stabilization is the convergence of independently initialized runs toward a common solution. This distinction is critical for mechanistic interpretability of natural language processing (NLP), where feature stability is increasingly used as evidence that SAE features are reusable units of analysis. Experiments from archetypal SAEs share a deterministic k-means decoder initialization, setting inter-run dictionary distance to zero before training begins. When this initialization is removed, the archetypal constraint provides no stabilization advantage in our setting. We further identify a preprocessing-dependent cosine geometry issue that complicates interpretation of endpoint stability metrics. Overall, our study supports the value of studying SAEs within the larger dictionary-learning tradition while showing that stability claims require trajectory diagnostics and initialization ablations. --- ### Where Do Deep-Research Agents Go Wrong? Span-Level Error Localization in Agent Trajectories Authors: Jiaming Wang, Ziteng Feng, Jiangtao Wu, Ruihao Li, Qianqian Xie, Yuxiang Ren, He Zhu, Xueming Han, Fanyu Meng, Junlan Feng, Jiaheng Liu Published: 2026-06-01 Categories: cs.AI arXiv: https://arxiv.org/abs/2606.02060v2 Deep-research agents solve tasks through long trajectories of search, tool use, evidence inspection, and answer synthesis. Evaluation based on final answers shows whether an agent succeeds, but not which parts of the trajectory make the answer unreliable. We study span-level error localization for deep-research agents. We collect 2,790 real trajectories from two agent frameworks, three backbone models, and three benchmarks, convert raw logs into semantic spans, and annotate harmful error spans through LLM-assisted expert review. From these annotations, we build TELBench, a 1,000-instance benchmark for identifying error spans among normal exploration, failed searches, tentative hypotheses, and harmless noise. We further propose DRIFT, a claim-centric auditing framework that tracks agent claims, checks their support in trajectory evidence, and marks spans where unsupported or conflicting claims affect the answer path. Experiments across model families and auditing frameworks show that DRIFT improves span-level error localization and first-error accuracy by up to 30 percentage points. Our work provides a process-level view of reliability in deep-research agents. --- ### TIDES: Time-Derivative Event Simulation via Deformable Reconstruction Authors: Christopher Thirgood, Dipon Kumar Ghosh, Simon Hadfield Published: 2026-06-01 Categories: cs.CV, cs.RO arXiv: https://arxiv.org/abs/2606.02058v1 Event cameras emit asynchronous events in response to environmental appearance changes. The scarcity of real-world event datasets makes simulation essential. However, most simulators infer event timestamps from frame sequences, forcing many threshold crossings to share a small set of discrete times; a failure mode we term timestamp batching that worsens under fast motion and occlusion. We present TIDES, a continuous-time event simulator built on dynamic Gaussian splatting. Because TIDES operates on an explicit 3D scene representation with learnt geometry and motion, it can derive per-pixel intensity dynamics directly from the scene, rather than by differencing rendered frames. This enables accurate threshold-crossing prediction, including multiple crossings per rendering step, without temporal upsampling or frame interpolation. The same 3D scene model reveals where objects partially occlude one another; TIDES uses this to guide adaptive time stepping, concentrating computation only in regions where occlusion dynamics make simple models of brightness change unreliable. Finally, we model finite sensor bandwidth using a tile-level arbiter whose throughput, jitter, and event drops reproduce realistic sensor artifacts. Across paired RGB-event benchmarks, TIDES attains state-of-the-art event-stream fidelity. We also show that events simulated by TIDES transfer more effectively to real downstream tasks than competitors'. --- ### Query-Limited Community Recovery in Stochastic Block Models Authors: Sabyasachi Basu, Manuj Mukherjee, Lutz Oettershagen, Suhas Thejaswi Published: 2026-06-01 Categories: cs.IT, cs.LG, cs.SI, stat.ML arXiv: https://arxiv.org/abs/2606.02055v1 We study exact community recovery in the two-community stochastic block model on $n$ vertices under limited and noisy access to network data. The learner may query a noisy neighborhood oracle that reveals each true neighbor of a queried vertex independently with fixed probability and never returns non-neighbors, subject to a finite query budget. We consider both oracle-only access and a combined model where the learner also observes a single subsampled copy of the underlying graph. For oracle-only access, balanced uniform querying gives a sharp non-adaptive benchmark: when each vertex is queried the same integer number of times, the observations reduce to an SBM with attenuated edge probabilities and the Abbe-Bandeira-Hall exact-recovery threshold applies. We show that this benchmark is not adaptively optimal: a two-stage adaptive strategy succeeds with $n+o(n)$ queries in a regime where balanced uniform querying requires $m n$ queries for some $m>1$. With an additional subsampled graph, we prove a sublinear-query adaptivity gap: balanced data-independent uniform querying with a sublinear budget does not improve over the subsampled graph alone, whereas adaptive querying can target a small set of uncertain vertices and achieve exact recovery. Thus adaptive data acquisition can strictly improve the information-theoretic limits of exact recovery. --- ### eMoT: evolving Memory-of-Thought via Symbolic Anchoring and Memory Corrosion Authors: Xiang Li, Jiwei Wei, Ke Liu, Yitong Qin, Jinyu Guo, Malu Zhang, Peng Wang, Yang Yang Published: 2026-06-01 Categories: cs.AI arXiv: https://arxiv.org/abs/2606.02054v1 While Large Language Models (LLMs) achieve impressive performance on multi-step reasoning tasks, their reliability is persistently hindered by critical limitations such as unconstrained hallucinations and poor numerical computation. Fundamentally, these issues arise because standard models treat reasoning as a transient, one-off generation process rather than retaining and refining successful procedural logic. To address these challenges, we propose eMoT (evolving Memory-of-Thought), a unified framework that stabilizes multi-step reasoning by treating reasoning trajectories as dynamic, evolving memories rather than static templates. The framework primarily consists of three interconnected modules: (i) a memory corrosion mechanism that reinforces high-utility reasoning structures while gradually decaying less frequent ones; (ii) a symbolic anchoring engine that utilizes Python for deterministic computation, much like a human uses a calculator; and (iii) a consistency-driven refinement process that aligns neural inference with symbolic outcomes, reducing the accumulation of logical discrepancies. Across multiple reasoning benchmarks, eMoT improves accuracy and solution consistency over standard Chain-of-Thought and structured reasoning baselines.On the traditional task Game of 24, eMoT achieves 100% accuracy, surpassing the baseline by up to 17.6%. Evaluations on mathematical task GSM8K, ASDiv, SVAMP, and MGSM further show consistent gains in multi-step mathematical reasoning. In our evaluation, we achieve superior performance despite utilizing a lightweight backbone model with constrained baseline capabilities. Compared to alternative methods that rely on massively scaled models, our results demonstrate that the performance gains are fundamentally driven by the eMoT framework's reasoning control rather than sheer model size. --- ### Explainable Data-driven Deep Reinforcement Learning Methods for Optimal Energy Management in Buildings Authors: Hallah Shahid Butt, Qiong Huang, Gökhan Demirel, Kevin Förderer, Erfan Tajalli-Ardekani, Simnon Waczowicz, Luigi Spatafora, Veit Hagenmeyer, Benjamin Schäfer Published: 2026-06-01 Categories: cs.AI arXiv: https://arxiv.org/abs/2606.02049v1 The increasing integration of renewable energy sources into power systems, particularly in buildings equipped with photovoltaic (PV) panels and energy storage systems, introduces significant complexity in energy systems. Volatile power generation, varying electricity tariffs, and increased entities, e.g., PV systems, and heat pumps, have increased the complexity and made the system harder to operate. This leads to the demand for additional control and optimization routes including data-based controls, such as reinforcement learning. While deep reinforcement learning (DRL) has emerged as a promising solution to optimize building operations in dynamic and ever more complex environments, its black-box nature impedes user trust and practical adoption. This paper presents a framework for explainable deep reinforcement learning (XRL) applied to energy management in residential buildings. We demonstrate its usage on both synthetic data but also on real-world data from the Living Lab Energy Campus (LLEC) at KIT. We train and compare both on-policy and off-policy DRL agents on an expanded state space that incorporates real-time measurements (demand, PV generation, battery power, state of charge), external signals (dynamic electricity price, local weather data), calendrical and holiday indicators, and forecasts for demand and price. Our experimental results indicate that on-policy algorithms, particularly Advantage Actor Critic (A2C) and Proximal Policy Optimization (PPO), outperform off-policy methods in terms of cumulative rewards and policy stability. To explain these models, we employ post-hoc interpretation techniques to elaborate the learned control policies. Our findings demonstrate that the XRL framework not only reduces electricity costs through optimal battery management, but also provides transparent, actionable insights into the agent's decision-making process. --- ### Topological texture analysis of microscopy images of dynamic casein gelation and its relation to rheological properties Authors: Zahra Tabatabaei, Diana Soto Aguilar, Jose C. Bonilla, Mathias P. Clausen, Jon Sporring Published: 2026-06-01 Categories: cs.AI, cs.CV, physics.bio-ph arXiv: https://arxiv.org/abs/2606.02048v1 We propose a novel computational toolbox that integrates Topological Data Analysis (TDA), Differential Box Counting (DBC), Multifractal Partition (MFP), and Local Binary Patterns (LBP), applied to time-lapse super-resolution STED microscopy images of sodium caseinate gelation induced by glucono-delta-lactone (GDL) at 30 °C and 40 °C and two GDL concentrations (1.8% and 3.5% w/v). TDA tracked topological loops, closed ring-like structures reflecting protein network interconnectivity, via max-Betti-1 curves, which revealed a lag phase of dispersed aggregates, a sharp decay coinciding with network percolation and the rheologically observed sol-gel transition, and a post-gelation increase corresponding to network rearrangements. These topological transitions were corroborated by DBC and MFP as these methods were able to resolve changes in structural complexity and spatial heterogeneity. The toolbox was validated on simulated fractal images prior to experimental application. Together, these descriptors provided sensitivity to subtle microstructural transitions that bulk rheology captured as averaged bulk mechanical responses. This integrated approach provides a robust quantitative tool for characterizing complex microstructure in food and material science with evolving microstructural dynamics. Code is available at https://github.com/Zahratabatabaei/Delifood_CV_paper.git --- ### Convex Distance Operator Transport: A Convex and Geometry-Preserving Formulation Authors: Junhyoung Chung, Euijong Song, Won Hwa Kim, Gunwoong Park Published: 2026-06-01 Categories: stat.ML, cs.LG, math.ST, stat.ME arXiv: https://arxiv.org/abs/2606.02047v1 We introduce Convex Distance Operator Transport (CDOT), the first convex optimal transport framework that aligns distributions across heterogeneous domains by jointly preserving feature correspondence and intrinsic geometric structure. Specifically, CDOT employs an operator-based regularization that aligns aggregated distance structures by introducing distance and conditional expectation operators. Consequently, the proposed regularization improves the robustness to local geometric variations. We further prove that the resulting CDOT discrepancy is a valid pseudometric on the space of attributed compact metric-measure spaces. In addition, we characterize the relationship between CDOT and Gromov--Wasserstein (GW) through a new notion of dispersion gap, formally elucidating the geometric source of non-convexity in GW compared to the convexity of CDOT. In the finite-sample regime, we derive a non-asymptotic risk bound decomposed into optimization and statistical errors, establishing risk consistency under a globally convergent Frank--Wolfe algorithm. Experiments on synthetic point clouds, brain connectomes, and graph classification benchmarks demonstrate better performance over existing methods, with stable and reliable behavior in practice. --- ### Quantifying and Mitigating Domain Shift in Peach Leaf Damage Classification: Attention Mechanisms and Fine-Tuning Strategies Authors: Adrián Cánovas-Rodriguez, Miguel A. González-Illán, Maria Fernanda García-Cruz, Pedro Nortes Tortosa, José Salvador Rubio-Asensio, Miguel A. Zamora Izquierdo, Juan Antonio Martínez Navarro, Antonio F. Skarmeta Published: 2026-06-01 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2606.02045v3 Deep learning models for crop damage assessment are typically trained and validated on curated public imagery, yet their behaviour when deployed in real orchards remains poorly quantified. This work measures and mitigates that gap for peach leaf damage classification, where climate-driven abiotic and biotic stresses produce visually similar foliar symptoms. A benchmark of 1366 manually annotated peach leaves covering six damage types was assembled from public sources, and a second, independently acquired dataset of 180 field images across four classes was collected in a commercial orchard as an unseen target domain. Eleven convolutional backbones and three attention-enhanced variants were compared; CBAM-EfficientNetB5 achieved the best source-domain performance (93.3\% accuracy, 0.849 macro F1). Applied directly to the target domain, source-trained models lost on average 0.21 macro F1 points (26.5\% relative), with 12 of 14 architectures degrading, confirming that benchmark performance substantially overestimates field behaviour. Three fine-tuning strategies were then evaluated as mitigation: feature extraction proved insufficient in nearly all cases, whereas full fine-tuning recovered performance, with CBAM-EfficientNetB3 reaching 0.9459 accuracy and 0.9297 macro F1 on the local domain. Attention mechanisms improved minority-class recall and adaptation efficiency, but did not by themselves confer robustness to domain shift. The results establish a transferability baseline for peach leaf diagnosis and quantify the adaptation cost of moving from public benchmarks to operational orchards. --- ### Attention mechanisms and transfer learning for robust peach leaf damage classification under domain shift Authors: Adrián Cánovas-Rodriguez, Miguel A. González-Illán, Maria Fernanda García-Cruz, Pedro Nortes Tortosa, José Salvador Rubio-Asensio, Miguel A. Zamora Izquierdo, Juan Antonio Martínez Navarro, Antonio F. Skarmeta Published: 2026-06-01 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2606.02045v2 Artificial intelligence provides a practical framework for crop damage assessment from imagery data, supporting early decision-making in agricultural management. In peach orchards, climate change increases abiotic stress and biotic pressures, including pests and diseases, which often produce visually similar foliar symptoms. This overlap makes manual diagnosis difficult, especially across multiple fields with varying environmental conditions, highlighting the need for automated models with strong generalization ability. We propose an image-based classification approach for peach leaf damage detection. A benchmark dataset was created through manual annotation of publicly available images, consisting of 1,366 peach leaves across six damage categories. Several deep learning architectures were evaluated. EfficientNet models achieved the best results, with EfficientNetB0 reaching 92.9 percent accuracy, EfficientNetB3 achieving 91.5 percent, and EfficientNetB5 showing the strongest performance on minority classes. DenseNet121 reached 92.6 percent accuracy. The integration of the Convolutional Block Attention Module (CBAM) improved performance in several backbones, particularly EfficientNetB5 and InceptionV3, while showing limited or negative impact in others. The CBAM-enhanced EfficientNetB5 achieved the best overall accuracy of 93.3 percent. To evaluate robustness under realistic conditions, a local dataset of 180 images across four classes was collected, and transfer learning strategies were applied to address domain shift. Three fine-tuning strategies were tested. EfficientNetB3 combined with CBAM achieved the best performance in the local domain, reaching a 93 percent macro F1-score after transfer. Overall, attention-based models showed improved robustness for minority classes and better generalization across different field conditions. --- ### Realistic noise synthesis reduces bias and improves tissue microstructure estimation with supervised machine learning Authors: Bradley G. Karat, Maëliss Jallais, Ali R. Khan, Santiago Aja-Fernández, Jelle Veraart, Marco Palombo Published: 2026-06-01 Categories: cs.LG, physics.med-ph arXiv: https://arxiv.org/abs/2606.02044v2 Diffusion MRI enables non-invasive probing of tissue microstructure, but accurate parameter estimation is challenged by noise-related effects. In supervised machine learning frameworks trained on simulated data, discrepancies between the noise characteristics of simulated and acquired signals introduce a form of covariate shift, whereby the input signal distribution differs between training and inference. We investigated the impact of this mismatch on microstructure parameter estimation and propose a realistic noise synthesis (RNS) framework to mitigate it. RNS incorporates both the Rician expectation and the effective post-processing noise variance into simulated training signals. The Rician expectation was modelled using a noise standard deviation estimated with MPPCA, while the effective standard deviation was derived from spherical harmonic residuals of preprocessed data. The method was evaluated using the cylinder-zeppelin and the SANDI models on simulated datasets across multiple SNR levels and on in vivo diffusion data with repeated acquisitions. Sensitivity to noise misestimation was also assessed. Ignoring magnitude-induced noise effects during training produced systematic, SNR-dependent parameter bias, particularly at low SNR. Incorporating the Rician expectation substantially reduced bias to the level of noise-aware nonlinear least-squares fitting. Modelling the effective standard deviation further improved precision. Performance was largely independent of regression architecture but sensitive to accurate noise estimation. These findings demonstrate that realistic noise modelling in simulated training data mitigates signal-domain covariate shift and is essential for unbiased supervised microstructure estimation, particularly in low-SNR regimes associated with high b-values or high spatial resolution. --- ### Normality-Preserving Continual Industrial Anomaly Detection via Orthogonal LoRA Banks Authors: Weibai Fang, Haijun Che, Feiyang Ren, Qiancheng Lao Published: 2026-06-01 Categories: cs.CV arXiv: https://arxiv.org/abs/2606.02042v1 Continual industrial anomaly detection with diffusion models suffers from historical normality prior drift and catastrophic forgetting. Existing continual diffusion methods preserve previous knowledge through replay or constrained optimization, but they lack an explicit mechanism for isolating and protecting category-specific normality priors during sequential adaptation. Although low-rank adaptation provides modular residual updates, standard LoRA neither freezes historical normality subspaces nor prevents new adapters from interfering with previous ones. To address this issue, we propose a normality-preserving continual anomaly detection framework based on two modules: History Frozen Orthogonal LoRA Bank (HF-OLB) and Hierarchical Novelty Adaptive Bank Growth module (HNABG). HF-OLB freezes both the pre-trained U-Net backbone and the learned LoRA banks, and constrains new task-specific normality residuals to the orthogonal complement of historical LoRA subspaces. HNABG further allocates layer-dependent residual capacity and expands the bank only when the residual normality novelty exceeds the expressive capacity of existing banks. Extensive experiments on MVTec and VisA demonstrate the effectiveness of the proposed method. On the challenging VisA 2x6 setting, our method achieves 83.6/91.8 image and pixel level A-AUROC with 3.8/3.9 FM, improving pixel level A-AUROC over the state of the art by 3.2 points while reducing pixel level FM by 1.3. These results show that our method effectively preserves historical normality priors in long horizon continual category sequences. --- ### SentGuard: Sentence-Level Streaming Guardrails for Large Language Models Authors: Jiaqi Yu, Xin Wang, Yixu Wang, Jie Li, Yan Teng, Xingjun Ma, Yingchun Wang Published: 2026-06-01 Categories: cs.CL arXiv: https://arxiv.org/abs/2606.02041v1 Large language models increasingly stream long, reasoning-intensive responses in real time, making when to moderate as critical as whether to moderate. Existing guardrails fall into two unsatisfactory extremes: response-level methods delay intervention until the full output is generated, whereas token-level methods act on incomplete semantics, often producing unstable decisions and excessive guard invocations. To address this challenge, we propose SentGuard, a sentence-level streaming guardrail that operates in parallel with generation. A lightweight waiting buffer groups streamed tokens into sentence chunks and releases only verified chunks to the user, introducing a small offset that enables SentGuard to assess the current prefix while the target LLM decodes subsequent content. To support this, we construct StreamSafe, a benchmark with structured per-sentence annotations across 8 harm categories, capturing the evolution of safety risks across both reasoning and response segments. We further train SentGuard with a coarse-to-fine objective to detect unsafe intent as soon as it emerges at sentence boundaries. Experiments on 5 safety benchmarks show that SentGuard outperforms existing baselines, detecting 90.5% of unsafe cases within two sentences while maintaining a low streaming false-positive rate of 7.41%. --- ### Uncertainty-Aware Graph Neural Reconstruction of Urban Temperature Fields from Sparse Sensors under Deployment Constraints Authors: Reda Snaiki, Abdelatif Merabtine Published: 2026-06-01 Categories: physics.app-ph, cs.LG arXiv: https://arxiv.org/abs/2606.02038v1 Reconstructing spatially continuous daily temperature fields from sparse observations is important for urban climate monitoring and heat-risk analysis, but practical deployments are limited by sensor budgets and spacing constraints. This study proposes an uncertainty-aware graph neural network (GNN) framework for reconstructing daily maximum temperature fields from sparse sensors while supporting distance-constrained sensor placement and probabilistic exceedance mapping. The model predicts both the temperature field and a spatially varying predictive uncertainty field using a graph-attention-based mean-residual architecture trained with a Gaussian negative log-likelihood. Sensor placement is addressed using a Proper Orthogonal Decomposition with QR factorization (POD-QR) strategy with a 4 km minimum inter-sensor distance constraint and is compared with random feasible placement and farthest-point sampling. The framework is evaluated over a Montreal-area polygon using Daymet v4.1 daily temperature data (1 km resolution) under a strict temporal hold-out protocol (training: 2020-2023; testing: 2024). Across sensor budgets (10-40 sensors), the proposed GNN consistently outperforms inverse distance weighting and ordinary kriging in RMSE and MAE on unobserved nodes. Sensor-placement effects are most pronounced at low budgets and diminish at higher budgets, with a practical saturation regime emerging around 30 sensors under the imposed spacing constraint. Probabilistic evaluation further shows improved uncertainty calibration with increasing sensor density and a better sharpness-calibration trade-off than kriging. These results support the proposed framework as an effective tool for uncertainty-aware temperature field reconstruction and decision-oriented heat-risk mapping. --- ### RL-ACRGNet: Reinforcement Learning-Based Chest Radiology Report Generation Network Authors: Yogesh Kumar Meena, Saurabh Agarwal, K. V. Arya Published: 2026-06-01 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2606.02035v1 Medical imaging interpretation is a foundational pillar of modern clinical diagnostics, yet the manual generation of radiology reports remains a time-consuming process prone to interpretation inconsistencies. Within the field of medical AI, automating these descriptions through deep learning promises to streamline clinical workflows and standardise diagnostic output. However, accurate disease detection and precise report generation remain significant challenges due to limitations in capturing fine-grained visual features and ensuring clinical coherence. To address these issues, we propose RL-ACRGNet, an improved encoder-decoder model that integrates a pre-trained DenseNet encoder with a multilevel LSTM decoder within an off-policy reinforcement learning framework. Using a dual-network approach to refine visual-semantic embeddings through a metric-based reward mechanism, we demonstrate that RL-ACRGNet consistently outperforms state-of-the-art baselines on the IU-Xray dataset, achieving quantitative improvements in BLEU-4 (0.47%), METEOR (0.17%) and ROUGE-L (0.518). Furthermore, comprehensive evaluations on the large-scale MIMIC-CXR data set confirm the robust generalisation of the model and its ability to generate high-quality, clinically relevant reports --- ### OpenWebRL: Demystifying Online Multi-turn Reinforcement Learning for Visual Web Agents Authors: Rui Yang, Qianhui Wu, Yuxi Chen, Hao Bai, Wenlin Yao, Hao Cheng, Baolin Peng, Huan Zhang, Tong Zhang, Jianfeng Gao Published: 2026-06-01 Categories: cs.LG, cs.AI, cs.CL, cs.CV arXiv: https://arxiv.org/abs/2606.02031v2 Building capable visual web agents requires long-horizon reasoning, precise grounding, and robust interaction with dynamic real-world websites. Despite rapid progress, the strongest systems remain largely proprietary, while open agents still depend heavily on supervised post-training over large collections of curated web trajectories. This dependence creates a major scalability bottleneck: high-quality demonstrations are expensive to collect, and static datasets offer limited coverage of the diverse, ever-changing open web. Although online RL has shown promise for text-based agents, its potential for training visual web agents directly on live websites remains largely underexplored. In this paper, we introduce OpenWebRL, an open framework for training visual web agents with online multi-turn RL on real websites. OpenWebRL covers the full training pipeline, including scalable live-browser infrastructure, supervised initialization, multimodal context management, trajectory-level success judging, and efficient multi-turn policy optimization. Using this framework, we train OpenWebRL-4B, which establishes a new open-source state of the art on challenging live-web benchmarks. With only 0.4K initialization trajectories and 2.2K open-ended RL training tasks, OpenWebRL-4B achieves 67.0% success on Online-Mind2Web and 64.0% on DeepShop, outperforming prior open agents of similar or larger scale and remaining competitive with proprietary systems including OpenAI CUA and Gemini CUA. Beyond strong benchmark performance, we systematically study the key design choices that make online RL effective for visual web agents, and analyze how RL improves agentic reasoning. Overall, our work offers a practical path toward building more capable, reproducible, and cost-efficient open web agents. We will release our training data, models, and code to support future research. --- ### World-Task Factorization for Robot Learning Authors: Eduardo Sebastián, Adrian Pfisterer, Vito Mengers, Oliver Brock, Amanda Prorok Published: 2026-06-01 Categories: cs.RO, cs.LG, cs.MA arXiv: https://arxiv.org/abs/2606.02027v1 Robot learning must produce policies that generalize to new combinations of constraints, teammates, and environments. To achieve this, we must structurally factor the policy, which is a choice that dictates what generalizes, what requires retraining, and what remains entangled. Existing methods span a wide spectrum, from expecting structure to emerge from data scaling, to hand-designing it via hierarchies, skill libraries or learned specializations. In this paper, we study what we argue is the most fundamental factorization in robotics: separating the world from the task. We investigate the conditions under which this factorization is principled. World factors are properties of the embodied system and the environment; they exist independently of intent. Task factors are defined by the task's logic over what the world admits. We formalize this asymmetry through Bayesian model evidence: it aligns with the data-generating process, maintains high likelihood through an analytical world model, and reduces the Occam razor's penalty on task parameters. We instantiate this factorization by pairing AICON, a differentiable graph of recursive estimators and interconnections that is compositional, operates without task-specific data, and propagates cost gradients to actuators, with a compact, learned policy that modulates gradient paths. Gradients serve as the interface between the two factors: they carry world structure through the graph and task structure through costs, enabling low-dimensional learning while preserving structural generalization. We test the world/task factorization across three problems that encompass heterogeneous robots, environments, task logic and sensorimotor modalities. Our framework outperforms end-to-end baselines and analytical heuristics in all settings, generalizes zero-shot to out-of-distribution configurations, and transfers to real hardware without retraining. --- ### Ranking vs. Assignment: The Metric Mismatch in Multi-View Object Association Authors: Matvei Shelukhan, Timur Mamedov, Aleksandr Chukhrov, Karina Kvanchiani Published: 2026-06-01 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2606.02022v2 Multi-view object association is an important computer vision problem that underlies many multi-camera perception tasks. While this task is naturally formulated as a constrained one-to-one matching problem, recent works heavily rely on pairwise ranking metrics like AP and FPR-95 for model evaluation. We highlight a fundamental mismatch between these metrics and the actual assignment objective. Theoretically, we show that AP and FPR-95 can be imperfect even when the assignment is already correct, and that Sinkhorn-based normalization can make them perfect. Conversely, optimal pairwise ranking can still lead to incorrect assignments. We validate this mismatch in practice by using our Sinkhorn-based normalization as a controlled post-processing stress test. We show that optimizing just a few post-processing parameters significantly boosts AP and FPR-95 without corresponding improvements in assignment-level metrics such as ACC and IPAA. --- ### Ranking vs. Assignment: The Metric Mismatch in Multi-View Object Association Authors: Matvei Shelukhan, Timur Mamedov, Aleksandr Chukhrov, Karina Kvanchiani Published: 2026-06-01 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2606.02022v1 Multi-view object association is an important computer vision problem that underlies many multi-camera perception tasks. While this task is naturally formulated as a constrained one-to-one matching problem, recent works heavily rely on pairwise ranking metrics like AP and FPR-95 for model evaluation. We highlight a fundamental mismatch between these metrics and the actual assignment objective. Theoretically, we show that AP and FPR-95 can be imperfect even when the assignment is already correct, and that Sinkhorn-based normalization can make them perfect. Conversely, optimal pairwise ranking can still lead to incorrect assignments. We validate this mismatch in practice by using our Sinkhorn-based normalization as a controlled post-processing stress test. We show that optimizing just a few post-processing parameters significantly boosts AP and FPR-95 without corresponding improvements in assignment-level metrics such as ACC and IPAA. --- ### PerBite: A Curated Diagnostic Workflow for Bite-Aware Food Volume Estimation Authors: Ahmad AlMughrabi, Farid Al-Areqi, David Fernández Gómez, Umair Haroon, Marc Bolaños, Ricardo Marques, Petia Radeva Published: 2026-06-01 Categories: cs.CV arXiv: https://arxiv.org/abs/2606.02021v1 Can a visually plausible food mesh be trusted to estimate the volume of consumed food? \method investigates this question using selected paired before- and after-consumption states from the MetaFood CVPR 2026 Continuous 3D Reconstruction While Eating Challenge. The submitted workflow follows a curated reconstruction protocol: SAM~3 segments the food and plate regions; Hunyuan3D/SAM~3D generates a dimensionless food mesh; the plate diameter provides the metric scale; the plate geometry is removed in Blender; and the remaining mesh is hole-filled, made watertight, and integrated to estimate volume. MoGe-2 is used only as an auxiliary cue for initial dish-diameter estimation when direct plate measurement is uncertain; it is not the primary scale source for the reported challenge result. \method ranks first, with an average Chamfer distance of 8.31 across 34 meshes using rigid ICP without scale correction. On 17 before- and after-pairs, it achieves 33.87\% state-level volume MAPE and zero monotonicity violations, while consumed-volume MAPE remains 53.74\%. The results show that surface reconstruction, metric scale, controlled mesh cleanup, watertight volume integration, and physical depletion consistency should be evaluated separately for dietary assessment. Source code and evaluation scripts will be available at \href{https://github.com/GCVCG/PerBite-CVPR-MetaFood-2026}{github.com/GCVCG/PerBite-CVPR-MetaFood-2026}. --- ### Unveiling the Entropy Dynamics of Chain-of-Thought Reasoning Authors: Ting Xu, Xu He, Yupu Lu, Jiankai Sun, Dong Li, Wai Lam, Jianye Hao Published: 2026-06-01 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2606.02020v1 This paper investigates the entropy dynamics of Chain-of-Thought (CoT) and uncovers a consistent two-phase structure: an Uncertainty Region of exploration transitioning sharply to a Confidence Region of convergence. We demonstrate that the Confidence Region possesses two critical properties: 1) High Reliability -- answers in the confidence region become highly accurate and stable, and 2) High Redundancy -- models generate unnecessary tokens long after reaching the correct answer. These properties unlock more efficient and reliable inference strategies: 1) Early Exit leverages reliability and redundancy to terminate computation safely when returns diminish, and 2)Test-Time Scaling uses the Confidence Region signal to prioritize converged trajectories. To operationalize these insights, we formulate Confidence Region detection as a sequential change-point detection problem, being the first to apply classical change-point methods to monitor CoT reasoning. Using the Cumulative Sum (CUSUM) algorithm, a statistically optimal change-point detector, we develop a training-free framework for real-time inference control. Experiments show our approach establishes a superior Pareto-frontier for early exit. CUSUM achieves 63.06% accuracy with 11.1% token reduction, outperforming DEER and Dynasor by 3.28% and 4.36% in accuracy respectively. For test-time scaling, CUSUM-weighted voting consistently outperforms self-consistency. --- ### PliableBVS: A flexible Bayesian variable selection method for modeling interactions with mandatory modifying variables Authors: Theophilus Quachie Asenso, Zhi Zhao, Maren-Helene Langeland Degnes, Marie Cecilie Paasche Roland, Trond Melbye Michelsen, Manuela Zucknick Published: 2026-06-01 Categories: stat.ME, stat.AP, stat.ML arXiv: https://arxiv.org/abs/2606.02017v1 High-dimensional interaction models are useful for studying, for example, how a large set of variables of interest, such as gene expression or other omics features, interact with a smaller set of modifying variables, such as clinical covariates. In this context, the pliable lasso has recently been proposed as an efficient method for screening large numbers of potential interaction terms under an asymmetric weak hierarchical constraint. In this work, we extend this framework by introducing PliableBVS, a Bayesian variable selection approach that preserves the hierarchical structure of the pliable lasso while inducing sparsity through spike-and-slab priors. The proposed model combines the continuous shrinkage effect of Bayesian lasso with a hierarchical spike-and-slab prior formulation that has two layers of decision variables: one governing the inclusion of main effects and another controlling the inclusion of interaction effects which is conditional on the inclusion of the corresponding main effects. This structure enables simultaneous selection of high-dimensional main and interaction effects within a coherent probabilistic framework. In simulation studies the proposed method outperforms the original pliable lasso in identifying active main and interaction effects, reducing false discoveries, and improving prediction accuracy in most scenarios. Applications with data from a labor onset study and a preeclampsia study demonstrate that PliableBVS selects biologically meaningful features and interactions. --- ### Evaluating Real-World Generalizability of Algorithm Selection Models Authors: Gjorgjina Cenikj, Jakub Kudela, Eva Tuba, Tome Eftimov Published: 2026-06-01 Categories: cs.LG arXiv: https://arxiv.org/abs/2606.02016v1 Algorithm Selection (AS) aims to automatically identify the most suitable optimization algorithm for a given problem instance by leveraging measurable problem characteristics and historical performance data. In this study, we investigate the generalization ability of AS models across both synthetic and real-world optimization landscapes. We consider two widely used academic benchmark suites (BBOB and CEC) and two real-world problem sets (robotics trajectory optimization tasks and unmanned aerial vehicle path-planning problems). Through a systematic cross-benchmark evaluation, we analyze how AS models transfer between domains, identify where generalization succeeds or breaks down, and highlight the challenges that arise when applying AS in realistic, domain-specific contexts. Our findings provide insights into the robustness of current AS approaches and inform the development of more reliable, broadly applicable AS systems for real-world optimization. --- ### Extreme Low-Bit Inference in Reasoning Models: Failure Modes and Targeted Recovery Authors: Ekaterina Alimaskina, Darya Rudas, Denis Shveykin, Gleb Molodtsov, Pavel Vasiliev, Aleksandr Beznosikov Published: 2026-06-01 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2606.02011v1 Large Reasoning Models (LRMs) rely on long reasoning traces, making inference expensive. While low-bit quantization reduces per-token decoding cost, we show that aggressive 2-bit inference can fail to deliver end-to-end speedup because instability in the generation process inflates total token count. Instead of merely lowering answer accuracy, 2-bit quantization often produces much longer traces with repetitive loops, budget exhaustion, delayed commitment, and unclosed reasoning segments. We analyze full reasoning traces of Qwen3 reasoning models across mathematical and commonsense benchmarks and show that accuracy degradation is tightly linked to these process-level failures. To address them, we introduce two lightweight controls: FP16 planning, which gives the 2-bit model a short high-precision outline, and loop rescue, which detects repetitive traces and either commits to an earlier answer or falls back to FP16. On MATH-500, loop rescue improves Qwen3-8B accuracy from 17.2% to 74.2%, while planning plus loop rescue improves Qwen3-32B from 65.0% to 87.2%. Overall, our results show that extreme low-bit reasoning becomes practical when its failures are treated as controllable generation pathologies: with lightweight detection and selective FP16 support, 2-bit inference can recover accuracy while preserving real end-to-end speed. Our code is available at: https://github.com/brain-lab-research/quantized-reasoning. --- ### PlanarBench: Evaluating LLM Spatial Reasoning via Planar Graph Drawing Authors: Oleksandr Nikitin, Anna Kravchenko Published: 2026-06-01 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2606.02010v2 Existing LLM graph benchmarks typically ask models to answer graph-theoretic questions or compute symbolic solutions rather than construct spatial layouts. Within-task difficulty is also primarily stratified by vertex count. However, existing research also suggests that task difficulty is more closely related to the number of constraints imposed by the edges than to the number of vertices being arranged. We introduce PlanarBench, a benchmark that asks models to produce crossing-free ASCII drawings of planar graphs given only an edge list. Across 91 model configurations and 199 non-isomorphic connected planar graphs with 2-7 vertices, edge count is more strongly associated with mean task score than vertex count ($r=-0.85$) versus ($r=-0.47$) and remains strongly associated after controlling for vertex count ($r_p=-0.80$). PlanarBench provides a controlled setting for separating these two difficulty axes. In addition, neither drawing area nor total response length demonstrated a meaningful correlation with score, which is evidence against a simple output-size explanation. Performance varies widely: the best model scores 159.5 out of 199, most models below 30B parameters score under 25, and substantial failures remain among frontier systems. --- ### PlanarBench: Evaluating LLM Spatial Reasoning via Planar Graph Drawing Authors: Oleksandr Nikitin Published: 2026-06-01 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2606.02010v1 PlanarBench tests whether LLMs can draw planar graphs as ASCII art given only an edge list -- a spatial reasoning task that resists memorization because edge order, edge orientation, and node labels are all permutable. We evaluate 91 models on the 199 simplest non-isomorphic connected planar graphs (2 - 7 vertices). Edge count is the dominant difficulty predictor ($r = -0.85$) -- a finding not reported in prior LLM graph benchmarks, which use only node count as the difficulty axis. --- ### Automated Essay Scoring and Language Certification: Assessing Generalizability, Agreement and Validity for French Authors: Rodrigo Wilkens, Rémi Cardon, Vincent Folny, Thomas François Published: 2026-06-01 Categories: cs.CL arXiv: https://arxiv.org/abs/2606.02009v1 In Automated Essay Scoring (AES), benchmarking practices have fostered minimalist evaluation practices, in contrast with the broader-view recommendations of evaluation frameworks, such as the argument-based validation framework (ABV), which argued in favor of a multidimensional assessment of systems, especially in the context of high-stakes language tests. In this paper, we introduce an enhanced and more practical version of the ABV framework, incorporating fairness analysis, correlations with linguistic features, prediction error evaluation, and model agreement compared with human raters. Applying this framework to French AES, we compare 8 model architectures on a corpus of 27k exam essays (2 raters each) and a generalization corpus of 961 essays (at least nine raters each). Our analyses illustrate the benefits of applying the ABV framework to better understand the capabilities and pitfalls of AES models, while also advancing the state-of-the-art for French AES. --- ### Provable Data Scaling Law for Meta Learning via Complexity Minimization Authors: Kazuto Fukuchi, Ryuichiro Hataya, Kota Matsui Published: 2026-06-01 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2606.02008v1 Pre-training has become a fundamental paradigm in modern machine learning, with one of its key empirical benefits being reduced downstream sample complexity as the scale of pre-training data increases. However, existing theoretical frameworks for pre-training do not fully explain this phenomenon. In this paper, we introduce complexity minimization, a novel meta-representation learning framework designed to enable theoretical analysis of this scaling behavior, which learns representations by evaluating the downstream model complexity best suited to each domain and minimizing the worst-case such complexity across source domains. Our end-to-end theoretical analysis, spanning pre-training through downstream regression, shows that this framework provably captures this scaling behavior; in particular, we show that the error rate of few-shot adaptation improves as the amount of meta-training data grows. Empirically, we demonstrate that incorporating complexity regularization into existing meta-learning methods consistently improves downstream sample efficiency. --- ### Machine Learning for Coding Retail Product Names to Consumer-Price Categories: A Rule-plus-Bag-of-Words Pipeline with Reliability-Weighted Human-in-the-Loop Labeling Authors: Vladimir Beskorovainyi Published: 2026-06-01 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2606.02004v3 Consumer-price measurement increasingly draws on alternative data sources -- scanner, web-scraped, and transaction/receipt data -- whose product descriptions are short, noisy, and carry no standard product code, so each item must first be mapped to a consumption classification (e.g., the UN COICOP scheme) before prices can be compared. This paper studies that mapping as a general, reproducible method. The pipeline is: (i) text normalization and tokenization of noisy item names; (ii) a prefix-tree (trie) rule-based pre-classifier driven by per-category key-phrases and stop-phrases; and (iii) a per-category binary confirmation model. For labels at scale we use a human-in-the-loop protocol in which annotators give a binary valid/reject judgment aggregated by a dynamically updated reliability weight; the model joins the same rule, enabling continual fine-tuning. On a reproducible synthetic benchmark of six COICOP-like categories, under one matched protocol, cheap models win and order-sensitive ones do not help: a character n-gram logistic regression tops every category (mean F1 = 0.997), word-order features add nothing, and small CNN/LSTM models are the weakest in this small-data regime. The trie alone admits only 32-50% of items, so the learned stage is necessary, and about 66 labels per category suffice. A Monte-Carlo study of the labeling protocol is self-critical: the reliability-weighted vote barely beats plain majority while Dawid-Skene recovers labels markedly better. No proprietary or production data are used; all code and synthetic data are released at https://doi.org/10.5281/zenodo.20909563 --- ### Parameter-Efficient Adaptation of a Multi-Stream Vision-Language Framework for Blind Image Quality Assessment Authors: Bishr Omer Adam, Xu Li Published: 2026-06-01 Categories: cs.CV arXiv: https://arxiv.org/abs/2606.02002v3 Blind image quality assessment (BIQA) predicts perceived image quality without access to a pristine reference and is fundamental to applications such as image compression, transmission, and restoration. Recent BIQA methods increasingly rely on large vision-language models (VLMs). Although frozen VLMs provide an efficient alternative to computationally expensive full fine-tuning, it remains unclear how much performance is sacrificed by not adapting the backbone and, more importantly, under what conditions such adaptation is truly beneficial. Answering this question, however, is complicated by the widespread use of image-level splitting on synthetic-distortion benchmarks, where distorted versions of the same reference image can appear in both training and test partitions. This content overlap artificially inflates the apparent performance of frozen representations, masking their true generalization ability and potentially leading to incorrect conclusions about the value of backbone adaptation. We therefore address these two issues jointly. We develop an efficient BIQA framework that fuses a natural-scene-statistics descriptor with frozen SigLIP and CLIP-H embeddings through a lightweight regression head, and then apply parameter-efficient Low-Rank Adaptation (LoRA) to the SigLIP backbone, training only $0.23\%$ of its parameters. Evaluating both frozen and adapted models across six datasets under image-level and reference-level protocols, we find that image-level splitting inflates frozen-feature SROCC by up to $0.44$ and masks wide variation in true difficulty, which reference-level evaluation reveals. Under this content-independent protocol, LoRA adaptation recovers performance in proportion to the exposed difficulty, with the largest gains where frozen features generalize poorly (up to $+0.357$ SROCC on TID2013) and little benefit where they are already strong. --- ### Scaling Agentic Capabilities via Grounded Interaction Synthesis Authors: Wenhang Shi, Jinhao Dong, Yiren Chen, Zhe Zhao, Shuqing Bian, Wei Lu, Xiaoyong Du Published: 2026-06-01 Categories: cs.CL arXiv: https://arxiv.org/abs/2606.02001v1 General agentic intelligence hinges on the ability to interact with diverse real-world tools to complete complex tasks, a capability fundamentally tied to the quality of interaction data. To bypass the prohibitive costs of human annotation, prevailing paradigms depend entirely on Large Language Models (LLMs) to scale the synthesis of agentic environments and tasks. However, such unconstrained generation often degenerates into biased random sampling of LLMs' internal priors, failing to capture the diversity and difficulty of real-world domains or construct high-fidelity, long-horizon tasks. In this work, we introduce Grounded Agentic Interaction Synthesis (GAIS), a framework that automates the scalable construction of diverse environments and complex tasks via a two-phase grounding mechanism. Specifically, we construct protocol-anchored environments derived from real-world Model Context Protocol (MCP) servers to ensure functional diversity and difficulty. Subsequently, we employ structure-guided planning to navigate these environments, actively enforcing logical dependencies and adversarial policies to generate complex tasks. Experiments on BFCL, $τ^2$-Bench, and ACEBench demonstrate that GAIS-synthesized data significantly outperforms state-of-the-art baselines, enabling base models to match or even surpass their official instruction-tuned counterparts. Furthermore, GAIS exhibits superior data efficiency and scalability, achieving exceptional capabilities with significantly less data while maintaining continuous growth where baselines stagnate. Our code and dataset are publicly available at https://github.com/Eric8932/GAIS. --- ### Towards 3D-Aware Video Diffusion Models: Render-Free Human Motion Control with Mesh Tokenization Authors: Jingyun Liang, Min Wei, Shikai Li, Yizeng Han, Hangjie Yuan, Lei Sun, Weihua Chen, Fan Wang Published: 2026-06-01 Categories: cs.CV, cs.AI, eess.IV arXiv: https://arxiv.org/abs/2606.02000v1 Diffusion models have shown remarkable success in video generation. However, whether such models are truly aware of the 3D structure underlying visual observations, rather than simply reproducing plausible 2D projections, remains an open question. In this work, we investigate this question through human motion control, a task that requires precise modelling of 3D human geometry, motion, camera viewpoint, and scene context. Unlike prior methods that rely on rendered 2D motion guidance videos, we propose a render-free framework that conditions video generation directly on compressed 3D human mesh tokens. This representation preserves full 3D geometric information while enabling a unified token-based generation pipeline that processes video tokens jointly with motion tokens in a DiT-based architecture. This design requires the model to reason jointly about appearance, 3D structure, and camera viewpoint during video generation. Experimental results demonstrate strong performance on human motion control benchmarks, while reducing artifacts induced by view-dependent 2D guidance and trajectory-pose mismatches during editing. These findings suggest that video diffusion models, when equipped with mesh tokenization, can better capture complex 3D human structures and their interactions with the surrounding environment. --- ### Why Do Time Series Models Need Long Context Windows? Authors: Luca Butera, Giovanni De Felice, Andrea Cini, Cesare Alippi Published: 2026-06-01 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2606.01999v1 Modern deep learning models for forecasting groups of time series rely on increasingly longer observation windows. However, the benefit of increasing the window size is often simply attributed to capturing long-range dependencies, and broader discussion on how global forecasting models leverage input observations has been limited. In this paper, we show that forecasting groups of time series involves two objectives: (i) generative process identification (GPI), i.e., inferring the specific process generating the input sequence, and (ii) conditional forecasting (CF), i.e., predicting future values given input observations. From this perspective, optimal predictions can be interpreted as an average over plausible data-generating processes, weighted by their likelihood given the input window. This suggests another explanation for the benefits of long context windows: they reduce the uncertainty about which specific process is generating the input time series during operation. We prove that even for processes with memory length $P$, an input window size strictly larger than $P$ is necessary to achieve the minimum attainable error. Finally, we show how decoupling GPI and CF can improve computational scalability without compromising accuracy. Experiments on synthetic and real-world data validate our insights and their relevance for designing forecasting architectures. --- ### CARTE: A Benchmark for Mapping Language Model Knowledge Across France Authors: Sarah Almeida Carneiro, Christos Xypolopoulos, Xiao Fei, Yang Zhang, Michalis Vazirgiannis Published: 2026-06-01 Categories: cs.CL arXiv: https://arxiv.org/abs/2606.01995v1 We introduce CARTE 1 (Culturally Anchored Regional-Territorial Evaluation), a multiplechoice benchmark for evaluating the ability of large language models (LLMs) to perform fine-grained reasoning over geographically grounded and regionally differentiated knowledge within France. While prior benchmarks focus on national-level cultural understanding, they largely overlook intra-country variation and the need to distinguish between closely related regional contexts. CARTE addresses this gap by introducing 2,431 questions spanning the 13 metropolitan regions of France and covering 14 thematic domains, including culture, language, demographics, economy, environment, and mobility. We further introduce CARTE-LV, a subset targeting Linguistic Variation across French regions, enabling focused evaluation of language-related differences. We evaluate 27 LLMs ranging from 1B to 12B parameters under few-shot settings. Our experiments reveal performance disparities across regions and model scales, suggesting systematic gaps in pretraining coverage and limited robustness to intra-national variation. --- ### MMG2Skill: Can Agents Distill In-the-Wild Guides into Self-Evolving Skills? Authors: Xinyu Che, Junqi Xiong, Yunfei Ge, Xinping Lei, Shihao Li, Hang Yan, Han Li, Yuanxing Zhang, Zhiqi Bai, Jinhua Hao, Ming Sun, Han Li et al. Published: 2026-06-01 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2606.01993v1 Abundant procedural knowledge on the Web holds great potential for helping agents solve long-horizon tasks. However, such knowledge is often multimodal, heterogeneous, noisy, and implicitly assumes human executors, making it difficult to use directly as the skills required by agents. To bridge the gap between human-oriented guides and agent-executable skills, we formalize this problem as guide-to-skill learning: converting in-the-wild guides into executable skills and continuously improving them from trajectories observable to the agent. To evaluate the capability of existing agents on this task, we introduce MMG2Skill-Bench, the first benchmark designed for this problem. We further propose MMG2Skill, a closed-loop framework that compiles guides into editable skills, conditions a fixed vision-language model (VLM) agent on these skills during execution, and revises the skills from trajectory-level root-cause feedback without using benchmark scores. Across GUI control, open-ended gameplay, and strategic card play with six VLM backbones, MMG2Skill consistently outperforms vanilla baseline agents in every model-domain setting, achieving macro-average gains of +12.8 to +25.3 percentage points across backbones. Ablation studies show that directly prompting agents with raw guides can degrade performance, while both structured skill construction and trajectory-driven revision are necessary for the observed improvements. On success-inferable tasks, analyzer-based early stopping further prevents late-stage performance regressions and saves 25%-53% of attempts when the success signal is properly calibrated. ---