# Research Papers — 2026-04 · bundle page 31 of 233

> Full-text markdown of papers #1501–1550 of 11612 published in 2026-04, newest first. AI-readable mirrors of the full 11612-paper 2026-04 archive (50 papers per file).

Canonical page: https://aipod.dev/papers/archive/2026-04/page/31
[← Previous bundle](https://aipod.dev/papers/archive/2026-04/page/30.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-04/page/32.md)

### Global Context or Local Detail? Adaptive Visual Grounding for Hallucination Mitigation

Authors: Yubo Jiang, Xin Yang, Abudukelimu Wuerkaixi, Zheming Yuan, Xuxin Cheng, Fengying Xie, Zhiguo Jiang, Cao Liu, Ke Zeng, Haopeng Zhang
Published: 2026-04-27
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2604.24396v1

Vision-Language Models (VLMs) are frequently undermined by object hallucination--generating content that contradicts visual reality--due to an over-reliance on linguistic priors. We introduce Positive-and-Negative Decoding (PND), a training-free inference framework that intervenes directly in the decoding process to enforce visual fidelity. PND is motivated by our key finding of a critical attention deficit in VLMs, where visual features are empirically under-weighted. Our framework corrects this via a dual-path contrast: The positive path amplifies salient visual evidence using multi-layer attention to encourage faithful descriptions, directly counteracting the attention deficit. Simultaneously, the negative path identifies and degrades the core object's features to create a strong counterfactual, which penalizes ungrounded, prior-dominant generation. By contrasting the model's outputs from these two perspectives at each step, PND steers generation towards text that is not just linguistically probable, but visually factual. Extensive experiments on benchmarks like POPE, MME, and CHAIR show that PND achieves state-of-the-art performance with up to 6.5% accuracy improvement, substantially reducing object hallucination while also enhancing descriptive detail--all without requiring any model retraining. The method generalizes effectively across diverse VLM architectures including LLaVA, InstructBLIP, InternVL, and Qwen-VL.

---

### Aligning with Your Own Voice: Self-Corrected Preference Learning for Hallucination Mitigation in LVLMs

Authors: Byeonggeuk Lim, JungMin Yun, Junehyoung Kwon, Kyeonghyun Kim, YoungBin Kim
Published: 2026-04-27
Categories: cs.AI
arXiv: https://arxiv.org/abs/2604.24395v1

Large Vision-Language Models (LVLMs) frequently suffer from hallucinations. Existing preference learning-based approaches largely rely on proprietary models to construct preference datasets. We identify that this reliance introduces a distributional mismatch between the proprietary and target models that hinders efficient alignment. To address this, we propose Alignment via VErified Self-correction DPO (AVES-DPO), a framework that aligns LVLMs using in-distribution data derived from the model's intrinsic knowledge. Our approach employs a consensus-based verification mechanism to diagnose diverse hallucinations and guides the model to self-correct, thereby generating preference pairs strictly compatible with its internal distribution. Extensive experiments demonstrate that AVES-DPO surpasses existing baselines in hallucination mitigation while requiring only 5.2k samples.

---

### Complexity of Linear Regions in Self-supervised Deep ReLU Networks

Authors: Mufhumudzi Muthivhi, Terence L. van Zyl
Published: 2026-04-27
Categories: cs.LG, cs.CV
arXiv: https://arxiv.org/abs/2604.24393v1

There has been growing interest in studying the complexity of Rectified Linear Unit (ReLU) based activation networks. Recent work investigates the evolution of the number of piecewise-linear partitions (linear regions) that are formed during training. However, current research is limited to examining the complexity of models trained in a supervised way. Self-Supervised Learning (SSL) differs in that it directly optimises the representation space using a loss function to enhance the model's performance across multiple downstream tasks. This study investigates the local distribution of linear regions produced by SSL models. We demonstrate that the evolution of linear regions correlates with the representation quality by utilising SplineCam to extract two-dimensional polytopes near the data distribution. We track the number, area, eccentricity, and boundaries of regions throughout training. The study compares supervised, contrastive, and self-distillation methods over two standard benchmark datasets, MNIST and FashionMNIST. The analysis of the experimental results shows that self-supervised methods create substantially fewer regions to achieve comparable accuracy to supervised models. Contrastive methods rapidly expand regions over time, whereas self-distillation methods tend to consolidate by merging neighbouring regions. Lastly, we can detect representation collapse early within the geometric space of linear regions. Our analysis suggests that polytopal metrics can serve as reliable indicators of representation quality and model performance.

---

### Structural Pruning of Large Vision Language Models: A Comprehensive Study on Pruning Dynamics, Recovery, and Data Efficiency

Authors: Yiran Huang, Lukas Thede, Massimiliano Mancini, Wenjia Xu, Zeynep Akata
Published: 2026-04-27
Categories: cs.CL
arXiv: https://arxiv.org/abs/2604.24380v1

While Large Vision Language Models (LVLMs) demonstrate impressive capabilities, their substantial computational and memory requirements pose deployment challenges on resource-constrained edge devices. Current parameter reduction techniques primarily involve training LVLMs from small language models, but these methods offer limited flexibility and remain computationally intensive. We study a complementary route: compressing existing LVLMs by applying structured pruning to the language model backbone, followed by lightweight recovery training. Specifically, we investigate two structural pruning paradigms: layerwise and widthwise pruning, and pair them with supervised finetuning and knowledge distillation on logits and hidden states. Additionally, we assess the feasibility of conducting recovery training with only a small fraction of the available data. Our results show that widthwise pruning generally maintains better performance in low-resource scenarios, where computational resources are limited or there is insufficient finetuning data. As for the recovery training, finetuning only the multimodal projector is sufficient at small compression levels. Furthermore, a combination of supervised finetuning and hidden-state distillation yields optimal recovery across various pruning levels. Notably, effective recovery can be achieved using just 5% of the original data, while retaining over 95% of the original performance. Through empirical study on three representative LVLM families ranging from 3B to 7B parameters, this study offers actionable insights for practitioners to compress LVLMs without extensive computation resources or sufficient data. The code base is available at https://github.com/YiranHuangIrene/VLMCompression.git.

---

### Certified geometric robustness -- Super-DeepG

Authors: Noémie Cohen, Mélanie Ducoffe, Christophe Gabreau, Claire Pagetti, Xavier Pucel
Published: 2026-04-27
Categories: cs.AI, cs.LG, cs.SC
arXiv: https://arxiv.org/abs/2604.24379v1

Safety-critical applications are required to perform as expected in normal operations. Image processing functions are often required to be insensitive to small geometric perturbations such as rotation, scaling, shearing or translation. This paper addresses the formal verification of neural networks against geometric perturbations on their image dataset. Our method Super-DeepG improves the reasoning used in linear relaxation techniques and Lipschitz optimization, and provides an implementation that leverages GPU hardware. By doing so, Super-DeepG achieves both precision and computational efficiency of robustness certification, to an extent that outperforms prior work. Super-DeepG is shared as an open-source tool on GitHub.

---

### Learning Evidence of Depression Symptoms via Prompt Induction

Authors: Eliseo Bao, Anxo Perez, David Otero, Javier Parapar
Published: 2026-04-27
Categories: cs.CL
arXiv: https://arxiv.org/abs/2604.24376v1

Depression places substantial pressure on mental health services, and many people describe their experiences outside clinical settings in high-volume user-generated text (e.g., online forums and social media). Automatically identifying clinical symptom evidence in such text can therefore complement limited clinical capacity and scale to large populations. We address this need through sentence-level classification of 21 depression symptoms from the BDI-II questionnaire, using BDI-Sen, a dataset annotated for symptom relevance. This task is fine-grained and highly imbalanced, and we find that common LLM approaches (zero-shot, in-context learning, and fine-tuning) struggle to apply consistent relevance criteria for most symptoms. We propose Symptom Induction (SI), a novel approach which compresses labeled examples into short, interpretable guidelines that specify what counts as evidence for each symptom and uses these guidelines to condition classification. Across four LLM families and eight models, SI achieves the best overall weighted F1 on BDI-Sen, with especially large gains for infrequent symptoms. Cross-domain evaluation on an external dataset further shows that induced guidelines generalize across other diseases shared symptomatology (bipolar and eating disorders).

---

### MIPIC: Matryoshka Representation Learning via Self-Distilled Intra-Relational and Progressive Information Chaining

Authors: Phung Gia Huy, Hai An Vu, Minh-Phuc Truong, Thang Duc Tran, Linh Ngo Van, Thanh Hong Nguyen, Trung Le
Published: 2026-04-27
Categories: cs.CL
arXiv: https://arxiv.org/abs/2604.24374v2

Representation learning is fundamental to NLP, but building embeddings that work well at different computational budgets is challenging. Matryoshka Representation Learning (MRL) offers a flexible inference paradigm through nested embeddings; however, learning such structures requires explicit coordination of how information is arranged across embedding dimensionality and model depth. In this work, we propose MIPIC (Matryoshka Representation Learning via Self-Distilled Intra-Relational Alignment and Progressive Information Chaining), a unified training framework designed to produce structurally coherent and semantically compact Matryoshka representations. MIPIC promotes cross-dimensional structural consistency through Self-Distilled Intra-Relational Alignment (SIA), which aligns token-level geometric and attention-driven relations between full and truncated representations using top-k CKA self-distillation. Complementarily, it enables depth-wise semantic consolidation via Progressive Information Chaining (PIC), a scaffolded alignment strategy that incrementally transfers mature task semantics from deeper layers into earlier layers. Extensive experiments on STS, NLI, and classification benchmarks (spanning models from TinyBERT to BGEM3, Qwen3) demonstrate that MIPIC yields Matryoshka representations that are highly competitive across all capacities, with significant performance advantages observed under extreme low-dimensional.

---

### SeaEvo: Advancing Algorithm Discovery with Strategy Space Evolution

Authors: Sichun Luo, Yi Huang, Haochen Luo, Fengyuan Liu, Guanzhi Deng, Lei Li, Qinghua Yao, Zefa Hu, Junlan Feng, Qi Liu
Published: 2026-04-27
Categories: cs.CL, cs.AI, cs.NE
arXiv: https://arxiv.org/abs/2604.24372v2

Large Language Model (LLM)-guided evolutionary search is increasingly used for automated algorithm discovery, yet most current methods track search progress primarily through executable programs and scalar fitness. Even when natural-language reasoning is used through heuristic descriptions or reflection, it typically remains transient mutation context or unstructured memory, rather than organized as persistent population-level state over strategic directions. As a result, evolutionary search can struggle to distinguish syntactically different implementations of the same idea, preserve lower-fitness but strategically promising directions, or detect when an entire family of strategies has saturated. We introduce \model, a modular strategy-space layer that turns language-level strategic reasoning into first-class population-level evolutionary state in LLM-driven program search. \model represents each candidate program with an explicit natural-language strategy, clusters the archive by strategy semantics, retrieves behaviorally complementary inspirations, and periodically navigates the strategy landscape to avoid saturated directions. Without modifying the underlying evolutionary algorithms, \model improves existing evolutionary backbones across algorithm discovery, systems optimization, and agent-scaffold design tasks in most settings. Across four systems benchmarks, \model achieves a 20.6% average relative improvement, with the best single run on Prism scoring 3$\times$ higher. These results suggest that persistent strategy representations provide a practical mechanism for improving the effectiveness and cost-efficiency of LLM-guided evolutionary search, pointing toward compound AI systems whose search capabilities benefit from the structured accumulation and reuse of algorithmic strategies.

---

### PathMoG: A Pathway-Centric Modular Graph Neural Network for Multi-Omics Survival Prediction

Authors: Di Wang, Chupei Tang, Junxiao Kong, Jixiu Zhai, Moyu Tang, Tianchi Lu
Published: 2026-04-27
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2604.24371v1

Cancer survival prediction from multi-omics data remains challenging because prognostic signals are high-dimensional, heterogeneous, and distributed across interacting genes and pathways. We propose PathMoG, a pathway-centric modular graph neural network for multi-omics survival prediction. PathMoG reorganizes genome-scale inputs into 354 KEGG-informed pathway modules, introduces a Hierarchical Omics Modulation module to condition gene-expression representations on mutation, copy number variation, pathway, and clinical context, and uses dual-level attention to capture both intra-pathway driver signals and inter-pathway clinical relevance. We evaluated PathMoG on 5,650 patients across 10 TCGA cancer types and observed consistent improvements over representative survival baselines. The framework further provides gene-level, pathway-level, and patient-level interpretability, supporting biologically grounded and clinically relevant risk stratification.

---

### Multispectral airborne laser scanning dataset for tree species classification: MS-ALS-SPECIES

Authors: Matti Hyyppä, Klaara Salolahti, Eric Hyyppä, Xiaowei Yu, Josef Taher, Leena Matikainen, Matti Lehtomäki, Paula Litkey, Teemu Hakala, Harri Kaartinen, Juha Hyyppä, Antero Kukko
Published: 2026-04-27
Categories: cs.CV
arXiv: https://arxiv.org/abs/2604.24370v2

The shift from stand-level to individual-tree-level forest assessments supports improved species mapping and biodiversity monitoring, particularly in boreal ecosystems where tree species like aspen (Populus tremula L.) play a keystone role. Airborne laser scanning (ALS) is the standard for such inventories, but a major limitation for developing improved species classification methods is the small number of publicly available ALS datasets containing high-quality, field-validated reference data. Recently, multispectral ALS data has shown promise for tree species classification, but the progress is hindered by the lack of open multispectral ALS datasets with high-quality field reference data. This paper presents and details an open multispectral ALS dataset for tree species classification that was used before its public release for an international benchmarking study of machine learning and deep learning classification methods in a related publication by Taher et al.,(2026). The dataset comprises 6326 segment-level point clouds of individual trees representing nine species in southern Finland. The point cloud data has been acquired using two multispectral laser scanning systems each operating at three laser wavelengths: a helicopter-borne system (HeliALS) with a point density exceeding 1000 points\m2 and an Optech Titan system with approximately 35 points\m2. Furthermore, we present a crowdsourcing application that facilitates the collection of high-quality field reference data of tree species in an efficient and scalable manner. Our article showcases the versatility of the open dataset by presenting new analyses on species classification using multispectral data building upon the initial findings of Taher et al.,(2026).

---

### Multispectral airborne laser scanning dataset for tree species classification: MS-ALS-SPECIES

Authors: Matti Hyyppä, Klaara Salolahti, Eric Hyyppä, Xiaowei Yu, Josef Taher, Leena Matikainen, Matti Lehtomäki, Paula Litkey, Teemu Hakala, Harri Kaartinen, Juha Hyyppä, Antero Kukko
Published: 2026-04-27
Categories: cs.CV
arXiv: https://arxiv.org/abs/2604.24370v1

The shift from stand-level to individual-tree-level forest assessments supports improved biodiversity mapping, particularly in boreal ecosystems where tree species like aspen (Populus tremula L.) play a keystone role. While airborne laser scanning (ALS) is the standard for such inventories, a major limitation is the small number of publicly available ALS datasets containing high-quality, field-validated reference data. Furthermore, open multispectral ALS datasets with high-quality field reference data are completely lacking despite the potential of multispectral ALS data for tree species classification. This paper presents and details an open multispectral ALS dataset used in a recent international benchmarking study of machine learning and deep learning methods for tree species classification by Taher et al. (2026). The dataset comprises 6326 segment-level point clouds of individual trees representing nine species in Southern Finland. The point cloud data has been acquired using two multispectral laser scanning systems each operating at three laser wavelengths: a helicopter-borne system (HeliALS) with a point density exceeding 1000 points/m$^2$ and an Optech Titan system with approximately 35 points/m$^2$. We provide a detailed description of field data collection techniques developed in the study to facilitate the collection of high-quality ground truth data in an efficient and scalable manner. Additionally, our article presents new analyses on species classification using multispectral data building upon the initial findings of Taher et al. (2026). Furthermore, we study the relation between classification accuracy and tree height to highlight the versatility of the open dataset and to demonstrate the advantage of the point transformer model for small trees and minority species.

---

### SAGE: Sparse Adaptive Guidance for Dependency-Aware Tabular Data Generation

Authors: Shuo Yang, Zheyu Zhang, Bardh Prenkaj, Gjergji Kasneci
Published: 2026-04-27
Categories: cs.LG
arXiv: https://arxiv.org/abs/2604.24368v1

Generating high-fidelity synthetic tabular data remains a critical challenge for enhancing data availability in privacy-sensitive and low-resource domains. Recent approaches leverage LLMs by representing table rows as sequences, yet suffer from two fundamental limitations: (1) they model feature dependencies densely, introducing spurious correlations; and (2) they assume static relationships between features, ignoring how these dependencies vary with feature values. To overcome these limitations, we introduce SAGE (Sparse Adaptive Guidance), a novel LLM-based generation framework that enforces sparse and dynamic dependency guidance. SAGE discretizes features into value-aware pseudo-features and constructs a mutual information-based sparse dependency graph. This graph adaptively guides generation through explicit context selection or implicit logit correction, enabling LLMs to focus on truly relevant information during synthesis. Our extensive experiments across six datasets and multiple tasks reveal that SAGE not only improves data fidelity and downstream utility, boosting F1 scores by 10% compared to previous LLM-based methods, but also reduces policy violations by one point. These results highlight the importance of adaptive structure in tabular data generation and provide new insights into context-sensitive control of LLMs.

---

### Culture-Aware Machine Translation in Large Language Models: Benchmarking and Investigation

Authors: Zekun Yuan, Yangfan Ye, Xiaocheng Feng, Baohang Li, Qichen Hong, Yunfei Lu, Dandan Tu, Bing Qin
Published: 2026-04-27
Categories: cs.CL
arXiv: https://arxiv.org/abs/2604.24361v1

Large language models (LLMs) have achieved strong performance in general machine translation, yet their ability in culture-aware scenarios remains poorly understood. To bridge this gap, we introduce CanMT, a Culture-Aware Novel-Driven Parallel Dataset for Machine Translation, together with a theoretically grounded, multi-dimensional evaluation framework for assessing cultural translation quality. Leveraging CanMT, we systematically evaluate a wide range of LLMs and translation systems under different translation strategy constraints. Our findings reveal substantial performance disparities across models and demonstrate that translation strategies exert a systematic influence on model behavior. Further analysis shows that translation difficulty varies across types of culture-specific items, and that a persistent gap remains between models' recognition of culture-specific knowledge and their ability to correctly operationalize it in translation outputs. In addition, incorporating reference translations is shown to substantially improve evaluation reliability in LLM-as-a-judge, underscoring their essential role in assessing culture-aware translation quality. The corpus and code are available at CanMT.

---

### DPRM: A Plug-in Doob h transform-induced Token-Ordering Module for Discrete Diffusion Models

Authors: Dake Bu, Wei Huang, Andi Han, Si Wu, Hau-San Wong, Qingfu Zhang, Taiji Suzuki, Atsushi Nitanda
Published: 2026-04-27
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2604.24357v3

Discrete diffusion models admit many token orders, yet most systems rely on confidence-based decoding. Confidence is a strong and efficient heuristic, but it can be myopic because local certainty does not measure a position's effect on terminal quality. We introduce DPRM (Doob h-transform Process Reward Model), a plug-in token-ordering module induced by a terminal-reward-tilted trajectory distribution. The Doob transform converts terminal reward into a process reward for each candidate position. A compact estimator indexed by generation progress, confidence, and optional positional or task state makes this correction reusable across partial states. DPRM changes only token order; the host architecture, denoising objective, supervision, and token sampler remain fixed. We derive the exact reward-tilted law and bound its shortlist and online approximations. Across nine recent open-source hosts spanning language, multimodal generation, and scientific sequences, DPRM improves reasoning, numeric VQA, visual-codebook ordering, and preference-conditioned generation. Relative to confidence, it improves PUMA GSM8K by 14.6%, Omni-Diffusion CLIP-L/14 by 13.2%, Prism voted accuracy from 82.41% to 83.85%, and RealWorldQA numeric/count accuracy by 8.97 points. Matched scientific gains include 8.3% in DCM nonzero recovery, 15.0% in GenMol QED, and 53.3% in SDPO-DNA total utility. Entropy and random-order controls show that the gains do not come from favoring uncertain tokens indiscriminately. Token-order traces and shared-state interventions instead show how terminal reward can correct a locally confident but globally poor choice. Code is available at: https://github.com/DakeBU/DPRM-DLLM.

---

### DPRM: A Plug-in Doob h transform-induced Token-Ordering Module for Diffusion Language Models

Authors: Dake Bu, Wei Huang, Andi Han, Hau-San Wong, Qingfu Zhang, Taiji Suzuki, Atsushi Nitanda
Published: 2026-04-27
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2604.24357v2

Diffusion language models generate without a fixed left-to-right order, leaving token ordering as a central algorithmic choice. Existing systems mainly use random masking or confidence-driven ordering, which respectively suffer from train--test mismatch and myopic exploration. We introduce DPRM (Doob -transform Process Reward Model), a plug-in token-ordering module that keeps the host architecture, denoising objective and supervision unchanged, and modifies only the ordering policy. DPRM starts from confidence-driven ordering and gradually shifts to process-reward-guided ordering through online estimates. We characterize the exact DPRM policy as a reward-tilted Gibbs reveal law, prove convergence of its stagewise Soft-BoN approximation, show that the online bucketized controller tracks the exact DPRM score at empirical-Bernstein rates, and establish a sample-complexity advantage under tractable optimization assumptions. Across nine hosts covering language reasoning, test-time scaling, protein, single-cell, molecular, DNA, text-to-image generation, and VQA, DPRM order variants improve several language, DNA, and multimodal settings while also identifying boundary cases where confidence-only ordering or task-specific utilities are preferable. Code is available at: https://github.com/DakeBU/DPRM-DLLM

---

### Primitive Recursion without Composition: Dynamical Characterizations, from Neural Networks to Polynomial ODEs

Authors: Olivier Bournez
Published: 2026-04-27
Categories: cs.CC, cs.LG, cs.LO, cs.NE
arXiv: https://arxiv.org/abs/2604.24356v1

What do recurrent neural networks, polynomial ODEs, and discrete polynomial maps each bring to computation, and what do they lack? All three operate over the continuum--real-valued states evolved by real-valued dynamics--even when the target functions are discrete. We study them through primitive recursion. We prove that primitive recursion admits equivalent characterizations in all three frameworks: bounded iteration of a fixed recurrent ReLU network, robust computation by a fixed polynomial ODE, and iteration of a fixed polynomial map with an externally supplied step-size parameter. In each, the time bound is itself primitive recursive, composition emerges from the dynamics rather than as a closure rule, and inputs are raw integer vectors. Every primitive recursive function is first compiled into bounded iteration of a single threshold-affine normal form, then interpreted as a ReLU computation and as a polynomial ODE. The equivalences expose a structural asymmetry: no fixed polynomial map can round uniformly to the nearest integer or realize exact phase selection--operations polynomial ODEs perform robustly via continuous-time flow. Each formalism compensates for a limitation the others lack: the ReLU gate provides exact branching, continuous time provides autonomous rounding and control, and the step-size parameter recovers both at the cost of discretization precision. This opens dynamical characterizations of subrecursive hierarchies and complexity classes by restricting time bounds, polynomial degrees, or discretization resources within one framework. More broadly, these models do not compute by composing subroutines: they shape the trajectory of a dynamical system through clocks, phase selectors, and error correction built into the dynamics. This differs structurally from symbolic programming, and our theorem gives a precise framework to study the difference.

---

### An Aircraft Upset Recovery System with Reinforcement Learning

Authors: Mahir Demir, Atahan Cilan, Seyyid Osman Sevgili, Özgün Can Yürütken, Ümit Can Bekar
Published: 2026-04-27
Categories: cs.LG
arXiv: https://arxiv.org/abs/2604.24355v1

This article explores the progress made in the creation of a pilot activated recovery system (PARS) for advanced jet trainers that utilizes artificial intelligence (AI) in an effort to enhance operational efficiency. The PARS model employs an advanced reinforcement learning (RL) architecture, incorporating a cutting-edge soft-actor critic (SAC) model and hyper-parameter optimization methods. Negative-g punishments and other handcrafted features remarked upon by control engineers and domain experts regarding PARS are also taken into account by the system. When evaluated by them, the AI model's behavior is deemed more desirable than that of conventional control methods.

---

### ARETE: Attention-based Rasterized Encoding for Topology Estimation using HSV-transformed Crowdsourced Vehicle Fleet Data

Authors: Daniel Fritz, Dimitrios Lagamtzis, Michael Mink, Markus Enzweiler, Steffen Schober
Published: 2026-04-27
Categories: cs.CV, cs.AI, cs.LG, cs.RO
arXiv: https://arxiv.org/abs/2604.24353v1

The continuous advancement of autonomous driving (AD) introduces challenges across multiple disciplines to ensure safe and efficient driving. One such challenge is the generation of High-Definition (HD) maps, which must remain up to date and highly accurate for downstream automotive tasks. One promising approach is the use of crowdsourced data from a vehicle fleet, representing road topology and lane-level features. This work focuses on the generation of centerlines and lane dividers from crowdsourced vehicle trajectories. We adopt a Detection Transformer (DETR)-based approach, where a rasterized representation of vehicle trajectories is used as input to predict vectorized lane representations. Each lane consists of a centerline with an associated direction and corresponding lane dividers that are geometrically constrained by the centerline. Our method includes the extraction of local tiles, from which crowdsourced vehicle trajectories are aggregated. Each tile undergoes a transformation into a rasterized representation encoding both the presence and direction of each trajectory, enabling the prediction of vectorized directed lanes. Experiments are conducted on an internal dataset as well as on the public datasets nuScenes and nuPlan.

---

### Diffusion Templates: A Unified Plugin Framework for Controllable Diffusion

Authors: Zhongjie Duan, Hong Zhang, Yingda Chen
Published: 2026-04-27
Categories: cs.LG, cs.AI, cs.CV, cs.SE
arXiv: https://arxiv.org/abs/2604.24351v1

Controllable diffusion methods have substantially expanded the practical utility of diffusion models, but they are typically developed as isolated, backbone-specific systems with incompatible training pipelines, parameter formats, and runtime hooks. This fragmentation makes it difficult to reuse infrastructure across tasks, transfer capabilities across backbones, or compose multiple controls within a single generation pipeline. We present Diffusion Templates, a unified and open plugin framework that decouples base-model inference from controllable capability injection. The framework is organized around three components: Template models that map arbitrary task-specific inputs to an intermediate capability representation, a Template cache that functions as a standardized interface for capability injection, and a Template pipeline that loads, merges, and injects one or more Template caches into the base diffusion runtime. Because the interface is defined at the systems level rather than tied to a specific control architecture, heterogeneous capability carriers such as KV-Cache and LoRA can be supported under the same abstraction. Based on this design, we build a diverse model zoo spanning structural control, brightness adjustment, color adjustment, image editing, super-resolution, sharpness enhancement, aesthetic alignment, content reference, local inpainting, and age control. These case studies show that Diffusion Templates can unify a broad range of controllable generation tasks while preserving modularity, composability, and practical extensibility across rapidly evolving diffusion backbones. All resources will be open sourced, including code, models, and datasets.

---

### Unveiling the Backdoor Mechanism Hidden Behind Catastrophic Overfitting in Fast Adversarial Training

Authors: Mengnan Zhao, Lihe Zhang, Tianhang Zheng, Bo Wang, Baocai Yin
Published: 2026-04-27
Categories: cs.LG, cs.AI, cs.CR
arXiv: https://arxiv.org/abs/2604.24350v1

Fast Adversarial Training (FAT) has attracted significant attention due to its efficiency in enhancing neural network robustness against adversarial attacks. However, FAT is prone to catastrophic overfitting (CO), wherein models overfit to the specific attack used during training and fail to generalize to others. While existing methods introduce diverse hypotheses and propose various strategies to mitigate CO, a systematic and intuitive explanation of CO remains absent. In this work, we innovatively interpret CO through the lens of backdoor. Through validations on pathway division, diverse feature predictions, and universal class distinguishable triggers in CO, we conceptualize CO as a weak trigger variant of unlearnable tasks, unifying CO, backdoor attacks, and unlearnable tasks under a common theoretical framework. Guided by this, we leverage several backdoor inspired strategies to mitigate CO: (i) Recalibrate CO affected model parameters using vanilla fine tuning, linear probing, or reinitialization-based techniques; (ii) Introduce a weight outlier suppression constraint to regulate abnormal deviations in model weights. Extensive experiments support our interpretation of CO and show the efficacy of the proposed mitigation strategies.

---

### OS-SPEAR: A Toolkit for the Safety, Performance,Efficiency, and Robustness Analysis of OS Agents

Authors: Zheng Wu, Yi Hua, Zhaoyuan Huang, Chenhao Xue, Yijie Lu, Pengzhou Cheng, Zongru Wu, Lingzhong Dong, Gongshen Liu, Xinghao Jiang, Zhuosheng Zhang
Published: 2026-04-27
Categories: cs.CL
arXiv: https://arxiv.org/abs/2604.24348v1

The evolution of Multimodal Large Language Models (MLLMs) has shifted the focus from text generation to active behavioral execution, particularly via OS agents navigating complex GUIs. However, the transition of these agents into trustworthy daily partners is hindered by a lack of rigorous evaluation regarding safety, efficiency, and multi-modal robustness. Current benchmarks suffer from narrow safety scenarios, noisy trajectory labeling, and limited robustness metrics. To bridge this gap, we propose OS-SPEAR, a comprehensive toolkit for the systematic analysis of OS agents across four dimensions: Safety, Performance, Efficiency, and Robustness. OS-SPEAR introduces four specialized subsets: (1) a S(afety)-subset encompassing diverse environment- and human-induced hazards; (2) a P(erformance)-subset curated via trajectory value estimation and stratified sampling; (3) an E(fficiency)-subset quantifying performance through the dual lenses of temporal latency and token consumption; and (4) a R(obustness)-subset that applies cross-modal disturbances to both visual and textual inputs. Additionally, we provide an automated analysis tool to generate human-readable diagnostic reports. We conduct an extensive evaluation of 22 popular OS agents using OS-SPEAR. Our empirical results reveal critical insights into the current landscape: notably, a prevalent trade-off between efficiency and safety or robustness, the performance superiority of specialized agents over general-purpose models, and varying robustness vulnerabilities across different modalities. By providing a multidimensional ranking and a standardized evaluation framework, OS-SPEAR offers a foundational resource for developing the next generation of reliable and efficient OS agents. The dataset and codes are available at https://github.com/Wuzheng02/OS-SPEAR.

---

### Semantic Segmentation for Histopathology using Learned Regularization based on Global Proportions

Authors: Yangping Li, Thomas Pinetz, Michael Hölzel, Marieta Toma, Alexander Effland
Published: 2026-04-27
Categories: eess.IV, cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2604.24347v1

In pathology, the spatial distribution and proportions of tissue types are key indicators of disease progression, and are more readily available than fine-grained annotations. However, these assessments are rarely mapped to pixel-wise segmentation. The task is fundamentally underdetermined, as many spatially distinct segmentations can satisfy the same global proportions in the absence of pixel-wise constraints. To address this, we introduce Variational Segmentation from Label Proportions (VSLP), a two-stage framework that infers dense segmentations from global label proportions, without any pixel-level annotations. This framework first leverages a pre-trained transformer model with test-time augmentation to produce a pixel-wise confidence estimate. In the second stage, these estimates are fused by solving a variational optimization problem that incorporates a Wasserstein data fidelity term alongside a learned regularizer. Unlike end-to-end networks, our variational method can visualize the fidelity-regularization energy, resulting in more interpretable segmentation. We validate our approach on two public datasets, achieving superior performance over existing weakly supervised and unsupervised methods. For one of these datasets, proportions have been estimated by an experienced pathologist to provide a realistic benchmark to the community. Furthermore, the method scales to an in-house dataset with noisy pathologist labels, severely outperforming state-of-the-art methods, thereby demonstrating practical applicability. The code and data will be made publicly available upon acceptance at https://github.com/xiaoliangpi/VSLP.

---

### SycoPhantasy: Quantifying Sycophancy and Hallucination in Small Open Weight VLMs for Vision-Language Scoring of Fantasy Characters

Authors: Arya Shah, Deepali Mishra, Chaklam Silpasuwanchai
Published: 2026-04-27
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2604.24346v1

Vision-language models (VLMs) are increasingly deployed as evaluators in tasks requiring nuanced image understanding, yet their reliability in scoring alignment between images and text descriptions remains underexplored. We investigate whether small, open-weight VLMs exhibit \emph{sycophantic} behavior when evaluating image-text alignment: assigning high scores without grounding their judgments in visual evidence. To quantify this phenomenon, we introduce the \emph{Bluffing Coefficient} (\bc), a metric that measures the mismatch between a model's score and its evidence recall. We evaluate six open-weight VLMs ranging from 450M to 8B parameters on a benchmark of 173,810 AI-generated character portraits paired with detailed textual descriptions. Our analysis reveals a significant inverse correlation between model size and sycophancy rate ($r = -0.96$, $p = 0.002$), with smaller models exhibiting substantially higher rates of unjustified high scores. The smallest model tested (LFM2-VL, 450M) produced sycophantic evaluations in 22.3\% of cases, compared to 6.0\% for the largest (LLaVA-1.6, 7B). These findings have direct implications for the deployment of small, open-weight VLMs as automated evaluators within attribute-rich, synthetic image evaluation tasks, where the gap between assigned scores and cited visual evidence is both measurable and consequential.

---

### See Further, Think Deeper: Advancing VLM's Reasoning Ability with Low-level Visual Cues and Reflection

Authors: Zhiheng Wu, Tong Wang, Shuning Wang, Naiming Liu, Yumeng Zhang
Published: 2026-04-27
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2604.24339v1

Recent advances in Vision-Language Models (VLMs) have benefited from Reinforcement Learning (RL) for enhanced reasoning. However, existing methods still face critical limitations, including the lack of low-level visual information and effective visual feedback. To address these problems, this paper proposes a unified multimodal interleaved reasoning framework \textbf{ForeSight}, which enables VLMs to \textbf{See Further} with low-level visual cues and \textbf{Think Deeper} with effective visual feedback. First, it introduces a set of low-level visual tools to integrate essential visual information into the reasoning chain, mitigating the neglect of fine-grained visual features. Second, a mask-based visual feedback mechanism is elaborated to incorporate visual reflection into the thinking process, enabling the model to dynamically re-examine and update its answers. Driven by RL, ForeSight learns to autonomously decide on tool invocation and answer verification, with the final answer accuracy as the reward signal. To evaluate the performance of the proposed framework, we construct a new dataset, Character and Grounding SalBench (CG-SalBench), based on the SalBench dataset. Experimental results demonstrate that the ForeSight-7B model significantly outperforms other models with the same parameter scale, and even surpasses the current SOTA closed-source models on certain metrics.

---

### Perfecting Aircraft Maneuvers with Reinforcement Learning

Authors: Atahan Cilan, Mahir Demir, Özgün Can Yürütken, Seyyid Osman Sevgili, Ümit Can Bekar
Published: 2026-04-27
Categories: cs.LG
arXiv: https://arxiv.org/abs/2604.24338v1

This paper evaluates an advanced jet trainer's utilization of artificial intelligence (AI)-based aircraft aerobatic maneuvers with the intention of developing an AI-assisted pilot training module for specific aircraft maneuvers. A multitude of aircraft maneuvers have been simulated using reinforcement learning (RL) agents, which will serve as a training tool for future pilots.

---

### New non-Euclidean neural quantum states from hyperbolic Lorentz recurrent architectures

Authors: H. L. Dao
Published: 2026-04-27
Categories: quant-ph, cond-mat.dis-nn, cs.LG
arXiv: https://arxiv.org/abs/2604.24337v3

In this work, we construct new non-Euclidean neural quantum states (NQS) based on hyperbolic Lorentz recurrent architectures (RNN/GRU). These constructions, together with the Poincare RNN NQS also newly constructed here, extend the class of previously introduced non-Eucllidean NQS which consists only of Poincare hyperbolic GRU. Using the Heisenberg J1J2 and J1J2J3 models consisting of 100 spins in the Variational Monte Carlo (VMC) setting, we show that the four hyperbolic RNN/GRU NQS variants are always able to furnish better representations of the ground state wavefunctions of the quantum systems than their respective Euclidean counterparts with the same architecture. In our experiments, among the four hyperbolic NQS, Lorentz RNN stands out in particular because despite having almost three times fewer parameters, it is capable of surpassing the more complex Poincare GRU and Lorentz GRU to emerge as the best overall hyperbolic NQS ansatz on many instances involving different J2 and (J2,J3) couplings. Given the findings from this work showing that the four newly constructed hyperbolic RNN/GRU NQS ansatze are able to outperform the well-established Euclidean RNN/GRU NQS in Heisenberg spin models, we establish the utility and efficiency of the hyperbolic Lorentz RNN/GRU NQS as well as the Poincare RNN/GRU NQS for future variational studies of quantum many-body systems, especially those exhibiting a hierarchical structure in the form of the different degrees of nearest-neighbor interactions.

---

### Reducing Redundancy in Retrieval-Augmented Generation through Chunk Filtering

Authors: Daria Berdyugina, Anaëlle Cohen, Yohann Rioual
Published: 2026-04-27
Categories: cs.CL
arXiv: https://arxiv.org/abs/2604.24334v1

Standard Retrieval-Augmented Generation (RAG) chunking methods often create excessive redundancy, increasing storage costs and slowing retrieval. This study explores chunk filtering strategies, such as semantic, topic-based, and named-entity-based methods in order to reduce the indexed corpus while preserving retrieval quality. Experiments are conducted on multiple corpora. Retrieval performance is evaluated using a token-based framework based on precision, recall, and intersection-over-union metrics. Results indicate that entity-based filtering can reduce vector index size by approximately 25% to 36% while maintaining high retrieval quality close to the baseline. These findings suggest that redundancy introduced during chunking can be effectively reduced through lightweight filtering, improving the efficiency of retrieval-oriented components in RAG pipelines.

---

### Mitigating Error Amplification in Fast Adversarial Training

Authors: Mengnan Zhao, Lihe Zhang, Bo Wang, Tianhang Zheng, Hong Zhong, Geyong Min
Published: 2026-04-27
Categories: cs.LG, cs.CR
arXiv: https://arxiv.org/abs/2604.24332v1

Fast Adversarial Training (FAT) has proven effective in enhancing model robustness by encouraging networks to learn perturbation-invariant representations. However, FAT often suffers from catastrophic overfitting (CO), where the model overfits to the training attack and fails to generalize to unseen ones. Moreover, robustness oriented optimization typically leads to notable performance degradation on clean inputs, and such degradation becomes increasingly severe as the perturbation budget grows. In this work, we conduct a comprehensive analysis of how guidance strength affects model performance by modulating perturbation and supervision levels across distinct confidence groups. The findings reveal that low confidence samples are the primary contributors to CO and the robustness accuracy trade off. Building on this insight, we propose a Distribution-aware Dynamic Guidance (DDG) strategy that dynamically adjusts both the perturbation budget and supervision signal. Specifically, DDG scales the perturbation magnitude according to the sample confidence at the ground truth class, thereby guiding samples toward consistent decision boundaries while mitigating the influence of learning spurious correlations. Simultaneously, it dynamically adjusts the supervision signal based on the prediction state of each sample, preventing overemphasis on incorrect signals. To alleviate potential gradient instability arising from dynamic guidance, we further design a weighted regularization constraint. Extensive experiments on standard benchmarks demonstrate that DDG effectively alleviates both CO and the robustness accuracy trade off.

---

### An Affordable, Wearable Stereo-Eye-Tracking Platform

Authors: Alexander Zimmer, Yasmeen Abdrabou, Enkelejda Kasneci
Published: 2026-04-27
Categories: cs.CV
arXiv: https://arxiv.org/abs/2604.24331v2

Research on video-based eye-tracking has long explored stereo and glint-based methods, yet existing wearable eye trackers - both commercial and open-source - offer limited flexibility for algorithm development and comparative evaluation. We present an affordable, wearable stereo eye-tracking platform built from off-the-shelf and 3D-printable components that explicitly targets this gap. The system combines four infrared eye cameras, infrared illumination, an optional scene camera, and software support for calibration and synchronized data acquisition. By design, the platform supports multiple eye-tracking paradigms, including stereo, glint-based, and binocular approaches, within a single hardware configuration. Rather than optimizing for end-user robustness, the platform prioritizes modularity and extensibility for research use. This paper focuses on the hardware architecture and calibration pipeline and demonstrates the feasibility of the approach using a prototype implementation. All hardware designs and documentation are made openly available.

---

### Monocular Depth Estimation via Neural Network with Learnable Algebraic Group and Ring Structures

Authors: Qianlei Wang, Kexun Chen, Shaolin Zhang, Hongli Gao, Chaoning Zhang, Xiaolin Qin
Published: 2026-04-27
Categories: cs.CV
arXiv: https://arxiv.org/abs/2604.24328v1

Monocular depth estimation (MDE) has witnessed remarkable progress driven by Convolutional Neural Networks and transformer-based architectures. However, these approaches typically treat the problem as a generic image-to-image regression on Euclidean grids, thereby overlooking the intrinsic algebraic and geometric structures induced by perspective projection. To address this limitation, we propose LAGRNet, a novel framework that fundamentally grounds MDE in algebraic geometry by explicitly embedding learnable group, ring, and sheaf structures into the deep learning pipeline. Modeling feature maps as sections of a sheaf over an approximated image manifold, our method first establishes a Group-defined Feature Manifold (GFM) parameterized by a learned algebraic group action to enforce projective equivariance and robustness against view changes. To facilitate algebraically consistent cross-scale interactions, we subsequently introduce a Ring Convolution Layer (RCL) that formulates feature fusion as a graded ring homomorphism. Furthermore, to ensure global topological consistency, a Sheaf-based Module (SM) aggregates local depth cues via Čech nerve on the image topology. Extensive zero-shot evaluations across the KITTI, NYU-Depth V2, and ETH3D benchmarks demonstrate that LAGRNet significantly outperforms state-of-the-art methods in both accuracy and generalization capabilities.

---

### X-NegoBox: An Explainable Privacy-Budget Negotiation Framework for Secure Peer-to-Peer Energy Data Exchange

Authors: Poushali Sengupta, Sabita Maharjan, Frank Eliassen, Yan Zhang
Published: 2026-04-27
Categories: cs.CR, cs.AI
arXiv: https://arxiv.org/abs/2604.24326v1

The decentralization of modern energy systems is transforming consumers into prosumers who continuously exchange data with aggregators, peers, and market operators. While such data is essential for peer-to-peer trading, demand response, and distributed forecasting, it can reveal sensitive household patterns and introduce privacy risks. Existing data sharing mechanisms rely on fixed policies or predefined differential privacy budgets, limiting their ability to adapt to variations in reliability, data sensitivity, and request purpose. As a result, prosumers rarely receive explanations for why a request is accepted, rejected, or modified, reducing trust and participation. To address these limitations, we propose X-NegoBox, an explainable negotiation framework for adaptive privacy budgeting and transparent decision making. Each prosumer data is managed locally within a private DataBox, where raw data remain confined. Incoming requests are processed by an Autonomous Privacy Budget Negotiation Protocol (APBNP), which determines an appropriate privacy budget based on trust, feature sensitivity, declared purpose, historical behavior, and risk-aware pricing. When needed, APBNP generates privacy-preserving counter-offers, such as reduced resolution or duration. An Explainable Agreement Layer (X-Contract) produces human- and machine-readable justifications for each decision. After agreement, requester code executes locally in a sandbox, and only sanitized outputs are shared. Experiments on realistic energy market settings show reduced privacy leakage, higher acceptance rates, and improved interpretability.

---

### Generative Design of a Gas Turbine Combustor Using Invertible Neural Networks

Authors: Patrick Krüger, Hanno Gottschalk, Werner Krebs, Bastian Werdelmann
Published: 2026-04-27
Categories: cs.AI
arXiv: https://arxiv.org/abs/2604.24322v1

The need to burn 100% H2 in high efficient gas turbines featuring low NOx combustion in premix mode require the complete redesign of the combustion system to ensure stable operation without any flashback. Since all engine frames featuring a power range from 4 MW up to 600 MW are affected, a huge design effort is expected. To reduce this effort, especially to transfer knowledge between the different engine classes, generative design methods using latest AI technology will provide promising potential. In this work, this challenge is approached utilizing the current advances in generative artificial intelligence. We train an Invertible Neural Network (INN) on an expandable database of geometrically parameterized combustor designs with simulated performance labels. Utilizing the INN in its inverse direction, multiple design proposals are generated which fulfill specified performance labels.

---

### DPEPO: Diverse Parallel Exploration Policy Optimization for LLM-based Agents

Authors: Junshuo Zhang, Chengrui Huang, Feng Guo, Zihan Li, Ke Shi, Menghua Jiang, Jiguo Yu, Shuo Shang, Shen Gao
Published: 2026-04-27
Categories: cs.CL
arXiv: https://arxiv.org/abs/2604.24320v1

Large language model (LLM) agents that follow the sequential "reason-then-act" paradigm have achieved superior performance in many complex tasks.However, these methods suffer from limited exploration and incomplete environmental understanding, as they interact with only a single environment per step. In this paper, we first introduce a novel paradigm that enables an agent to interact with multiple environments simultaneously and share cross-trajectory experiences. Building upon this paradigm, we further propose DPEPO, a reinforcement learning (RL) algorithm that encourages the agent to perform diverse parallel exploration. There are two stages in DPEPO: initial supervised fine-tuning (SFT) imparts basic parallel reasoning and action generation, followed by reinforcement learning stage with a hierarchical reward scheme. We design a parallel trajectory-level success reward and two step-level rewards: Diverse Action Reward and Diverse State Transition Reward, which actively penalize behavioral redundancy and promote broad exploration. Extensive experiments on ALFWorld and ScienceWorld show that DPEPO achieves state-of-the-art (SOTA) success rates, while maintaining comparable efficiency to strong sequential baselines. (Code is available at https://github.com/LePanda026/Code-for-DPEPO)

---

### Don't Pause! Every prediction matters in a streaming video

Authors: Dibyadip Chatterjee, Zhanzhong Pang, Fadime Sener, Yale Song, Angela Yao
Published: 2026-04-27
Categories: cs.CV
arXiv: https://arxiv.org/abs/2604.24317v1

Streaming video models should respond the moment an event unfolds, not after the moment has passed. Yet existing online VideoQA benchmarks remain largely retrospective. They pause the video at fixed timestamps, pose questions about current or past events, and score models only at those moments. This protocol leaves streaming predictions untested. To close this gap, we introduce SPOT-Bench, featuring multi-turn proactive queries that evaluate general streaming perception and assistive capabilities required by an always-on, real-time assistant. SPOT-Bench comes with Timeliness-F1, a consolidated metric that measures streaming predictions by their temporal precision and balanced coverage across the entire video. Our benchmark reveals: (i) offline models detect events reliably but spam predictions unprompted; (ii) post-training for silence reduces spamming but induces unresponsiveness; (iii) half of the streaming video expects no response, which we term dead-time - compute spent here does not affect response latency. These findings motivate AsynKV, a training-free streaming adaptation of offline models, that retains their event perception while improving their streaming behavior. AsynKV features a long-short term memory, utilized efficiently by scaling compute during dead-time. It serves as a strong baseline on SPOT-Bench, outperforming existing streaming models, and achieves state-of-the-art on retrospective benchmarks.

---

### Self-Abstraction Learning for Effective and Stable Training of Deep Neural Networks

Authors: Wonyong Cho, Taemin Kim, Jungmin Kim, Jeong-Rae Kim, Sung Hoon Jung
Published: 2026-04-27
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2604.24313v1

Training large-scale deep neural networks effectively and stably is essential for applying deep learning across various fields. However, conventional methods, which rely on training a single large network, often encounter challenges such as gradient vanishing, overfitting and unstable learning. To overcome these limitations, we introduce Self-Abstraction Learning (SAL), a hierarchical framework. In SAL, networks are arranged by structural complexity, where the simplest topmost network is trained first and its hidden and output layers serve as guidance for the successively more complex networks below. This top-down sequential guidance effectively mitigates optimization issues, enabling stable training of deep architectures. Various experiments across MLP, CNN, and RNN architectures demonstrate that SAL consistently outperforms conventional methods, ensuring robust generalization even in data-scarce and complex network regimes.

---

### Unconstrained Multi-view Human Pose Estimation with Algebraic Priors

Authors: Xiaolin Qin, Qianlei Wang, Jiacen Liu, Chaoning Zhang, Fei Zhu, Zhang Yi
Published: 2026-04-27
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2604.24312v1

Recovering 3D human pose from multi-view imagery typically relies on precise camera calibration, which is often unavailable in real-world scenarios, thereby severely limiting the applicability of existing methods. To overcome this challenge, we propose an unconstrained framework that synergizes deep neural networks, algebraic priors, and temporal dynamics for uncalibrated multi-view human pose estimation. First, we introduce the Triangulation with Transformer Regressor (TTR), which reformulates classical triangulation into a data-driven token fusion process to bypass the dependency on explicit camera parameters. Second, to explicitly embed the inherent algebraic relations of the multi-view variety into the learning process, we propose the Gröbner basis Corrector (GC). This pioneering loss formulation enforces constraints derived from the multi-view variety to ensure the neural predictions strictly adhere to the laws of projective geometry. Finally, we devise the Temporal Equivariant Rectifier (TER), which exploits the equivariance property of human motion to impose temporal coherence and structural consistency, effectively mitigating scale ambiguity in uncalibrated settings. Extensive evaluations on standard benchmarks demonstrate that our framework establishes a new state-of-the-art for uncalibrated multi-view human pose estimation. Notably, our approach significantly closes the performance gap between calibration-free methods and fully calibrated oracles.

---

### BIMStruct3D: A Fully Automated Hybrid Learning Scan-to-BIM Pipeline with Integrated Topology Refinement

Authors: Mahdi Chamseddine, Fabian Kaufmann, Marius Schellen, Christian Glock, Didier Stricker, Jason Rambach
Published: 2026-04-27
Categories: cs.CV
arXiv: https://arxiv.org/abs/2604.24311v2

Automatic generation of Building Information Models (BIM) from building scans is a key challenge in architecture and construction. We present a modular pipeline for generating IFC-compliant BIM from 3D point clouds. The hybrid approach combines learning-based semantic segmentation with topology-aware geometric reconstruction to model structural elements accurately. We propose vIoU, adapting voxel-based overlap evaluation to Scan-to-BIM by enabling holistic, instance-matching-free comparison of reconstructed and ground-truth models. We release the German Hospital dataset (DeKH), including high-resolution point clouds, ground truth BIMs, and semantic annotations. Experiments on DeKH and CV4AEC datasets show significant improvements over a RANSAC-based baseline, demonstrating robustness and scalability.

---

### SolarTformer: A Transformer Based Deep Learning Approach for Short Term Solar Power Forecasting

Authors: Ankan Basu, Jyotiraditya Roy, Aditya Datta, Prayas Sanyal, Sumanta Banerjee
Published: 2026-04-27
Categories: cs.LG, cs.AI, physics.comp-ph
arXiv: https://arxiv.org/abs/2604.24306v1

Accurate forecasting of solar power output is essential for efficient integration of renewable energy into the grid. In this study, an attention-based deep learning model, inspired by transformer architecture, is used for short-term solar power forecasting. Our proposed model, "SolarTformer", is designed to predict solar power output from meteorological data. Unlike traditional models, SolarTformer leverages self-attention mechanisms to effectively capture temporal dependencies and spatial variability in solar irradiance. In addition, the proposed methodology includes feeding power station-specific metadata into the model, which helps to generalize between power stations located at different locations and with different panel configurations and in different seasons. Our experiments demonstrate that SolarTformer significantly outperforms previous models on the same data set. In particular, the model exhibits strong performance on both clear and cloudy days, indicating high robustness and generalizability. These findings highlight the potential of attention-based architectures in enhancing the accuracy of solar forecasting, contributing to a more reliable management of renewable energy.

---

### Differentiable Faithfulness Alignment for Cross-Model Circuit Transfer

Authors: Shun Shao, Binxu Wang, Shay B. Cohen, Anna Korhonen, Yonatan Belinkov
Published: 2026-04-27
Categories: cs.CL
arXiv: https://arxiv.org/abs/2604.24302v1

Mechanistic interpretability has made it possible to localize circuits underlying specific behaviors in language models, but existing methods are expensive, model-specific, and difficult to scale to larger architectures. We introduce \textbf{Differentiable Faithfulness Alignment (DFA)}, a framework that transfers circuit information from a smaller source model to a larger target model through a learned differentiable alignment. DFA projects source-model node importance scores into the target model and trains this mapping with a soft faithfulness objective, avoiding full circuit discovery on the target model. We evaluate DFA on Llama-3 and Qwen-2.5 across six tasks spanning factual retrieval, multiple-choice reasoning, and arithmetic. The strongest results occur on Llama-3 $1$B$\rightarrow3$B, where aligned circuits are often competitive with direct node attribution and zero-shot transfer remains effective. Recovery weakens for larger source--target gaps and is substantially lower on Qwen-2.5, suggesting that transfer becomes harder as architectural and scaling differences increase. Overall, DFA consistently outperforms simple baselines and, in some settings, recovers target-model circuits with faithfulness comparable to or stronger than direct attribution. These results suggest that smaller models can provide useful mechanistic priors for larger ones, while highlighting both the promise and the limits of node-level cross-model circuit alignment.\footnote{Code is available at https://github.com/jasonshaoshun/dfa-circuits.

---

### ReVSI: Rebuilding Visual Spatial Intelligence Evaluation for Accurate Assessment of VLM 3D Reasoning

Authors: Yiming Zhang, Jiacheng Chen, Jiaqi Tan, Yongsen Mao, Wenhu Chen, Angel X. Chang
Published: 2026-04-27
Categories: cs.CV
arXiv: https://arxiv.org/abs/2604.24300v2

Current evaluations of spatial intelligence can be systematically invalid under modern vision-language model (VLM) settings. First, many benchmarks derive question-answer (QA) pairs from point-cloud-based 3D annotations originally curated for traditional 3D perception. When such annotations are treated as ground truth for video-based evaluation, reconstruction and annotation artifacts can miss objects that are clearly visible in the video, mislabel object identities, or corrupt geometry-dependent answers (e.g., size), yielding incorrect or ambiguous QA pairs. Second, evaluations often assume full-scene access, while many VLMs operate on sparsely sampled frames (e.g., 16-64), making many questions effectively unanswerable under the actual model inputs. We improve evaluation validity by introducing ReVSI, a benchmark and protocol that ensures each QA pair is answerable and correct under the model's actual inputs. To this end, we re-annotate objects and geometry across 381 scenes from 5 datasets to improve data quality, and regenerate all QA pairs with rigorous bias mitigation and human verification using professional 3D annotation tools. We further enhance evaluation controllability by providing variants across multiple frame budgets (16/32/64/all) and fine-grained object visibility metadata, enabling controlled diagnostic analyses. Evaluations of general and domain-specific VLMs on ReVSI reveal systematic failure modes that are obscured by prior benchmarks, yielding a more reliable and diagnostic assessment of spatial intelligence.

---

### Latent-Hysteresis Graph ODEs: Modeling Coupled Topology-Feature Evolution via Continuous Phase Transitions

Authors: Qinhan Hou, Jing Tang
Published: 2026-04-27
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2604.24293v1

Graph neural ordinary differential equations (Graph ODEs) extend graph learning from discrete message-passing layers to continuous-time representation flows. While it supports adaptive long-range propagation, we show that Graph ODEs with strictly positive irreducible mixing operators face an inherent \emph{monostability trap}: in the long-time regime, information leakage is unavoidable and the dynamics converge to a single global consensus attractor. We propose the \textbf{Hysteresis Graph ODE (HGODE)}, which couples feature evolution with a latent topological potential driven by a learned pairwise force. A double-well edge potential and bipolarized gate allow edge states to polarize into connected or insulated phases while preserving differentiability. We provide asymptotic analysis of the collapse mechanism and the proposed hysteretic topology dynamics, and validate HGODE on theory-driven synthetic diagnostics and real-world graph benchmarks.

---

### Model-Free Inference of Investor Preferences: A Relative Entropy IRL Approach

Authors: Chen Xu
Published: 2026-04-27
Categories: cs.LG
arXiv: https://arxiv.org/abs/2604.24280v1

We present a framework using Relative Entropy Inverse Reinforcement Learning (RE-IRL) to recover investor reward functions from observed investment actions and market conditions. Unlike traditional IRL algorithms, RE-IRL is employed to account for environments where transition probabilities are unknown or inaccessible. To address the challenge of data sparsity, we utilize a $K$-nearest neighbor approach to estimate the observed behavior policy. Furthermore, we propose a statistical testing framework to evaluate the validity and robustness of the estimated results.

---

### RAS: a Reliability Oriented Metric for Automatic Speech Recognition

Authors: Wenbin Huang, Yuhang Qiu, Bohan Li, Yiwei Guo, Jing Peng, Hankun Wang, Xie Chen, Kai Yu
Published: 2026-04-27
Categories: cs.SD, cs.AI
arXiv: https://arxiv.org/abs/2604.24278v4

Automatic speech recognition systems often produce confident yet incorrect transcriptions under noisy or ambiguous conditions, which can be misleading for both users and downstream applications. Standard evaluation based on Word Error Rate focuses solely on accuracy and fails to capture transcription reliability. We introduce an abstention-aware transcription framework that enables ASR models to explicitly abstain from uncertain segments. To evaluate reliability under abstention, we propose RAS, a reliability-oriented metric that balances transcription informativeness and error aversion, with its trade-off parameter calibrated by human preference. We then train an abstention-aware ASR model through supervised bootstrapping followed by reinforcement learning. Our experiments demonstrate substantial improvements in transcription reliability while maintaining competitive accuracy.

---

### Instance Awareness of Multi-class Semantic Segmentation Loss Functions

Authors: Soumya Snigdha Kundu, Florian Kofler, Marina Ivory, Hendrik Moller, Jonathan Shapey, Tom Vercauteren
Published: 2026-04-27
Categories: cs.CV
arXiv: https://arxiv.org/abs/2604.24276v1

Instance-sensitive losses for semantic segmentation such as blob loss and CC loss were designed to address instance imbalance, ensuring small lesions generate the same gradient as large ones, but operate only on single-class segmentation. In multi-class settings, class imbalance poses an additional problem: rare classes with few instances receive a disproportionately small share of the training signal. We show that extending instance-sensitive losses to multi-class segmentation via a one-vs-rest class decomposition repurposes them to also address class imbalance, as uniform averaging over classes ensures each class contributes equally regardless of frequency. We further show that inverse-size weighting, which destabilizes training when applied globally due to weight imbalances across rare and common classes, becomes effective when integrated within the per-component loss, confining the reweighting to each component's spatial context. On the BraTS-METS 2025 dataset (260 test cases), multi-class CC loss improves foreground Dice (0.64 +/- 0.26 vs. 0.59 +/- 0.27 baseline) and rare-class Dice, while maintaining Panoptic Quality at DSC threshold 0.5. Multi-class blob loss achieves the best Panoptic Quality at threshold 0.5 (0.40 +/- 0.24 vs. 0.38 +/- 0.25 baseline) and recognition quality (0.53 +/- 0.29 vs. 0.49 +/- 0.30). Integrating inverse-size weighting within the per-component loss increases rare-class Dice to 0.44 +/- 0.36 at the cost of reduced detection quality.

---

### BitRL: Reinforcement Learning with 1-bit Quantized Language Models for Resource-Constrained Edge Deployment

Authors: Md. Ashiq Ul Islam Sajid, Mohammad Sakib Mahmood, Md. Tareq Hasan, Md Abdur Rahim, Rafat Ara, Md. Arafat Hossain
Published: 2026-04-27
Categories: cs.LG
arXiv: https://arxiv.org/abs/2604.24273v1

The deployment of intelligent reinforcement learning (RL) agents on resource-constrained edge devices remains a fundamental challenge due to the substantial memory, computational, and energy requirements of modern deep learning systems. While large language models (LLMs) have emerged as powerful architectures for decision-making agents, their multi-billion parameter scale confines them to cloud-based deployment, raising concerns about latency, privacy, and connectivity dependence. We introduce BitRL, a framework for building RL agents using 1-bit quantized language models that enables practical on-device learning and inference under severe resource constraints. Leveraging the BitNet b1.58 architecture with ternary weights (-1, 0, +1) and an optimized inference stack, BitRL achieves 10-16x memory reduction and 3-5x energy efficiency improvements over full-precision baselines while maintaining 85-98 percent of task performance across benchmarks. We provide theoretical analysis of quantization as structured parameter perturbation, derive convergence bounds for quantized policy gradients under frozen-backbone architectures, and identify the exploration-stability trade-off in extreme quantization. Our framework systematically integrates 1-bit quantized language models with reinforcement learning for edge deployment and demonstrates effectiveness on commodity hardware.

---

### GeoEdit: Local Frames for Fast, Training-Free On-Manifold Editing in Diffusion Models

Authors: Yiming Zhang, Sitong Liu, Ke Li, Zhihong Wu, Alex Cloninger, Melvin Leok
Published: 2026-04-27
Categories: cs.LG
arXiv: https://arxiv.org/abs/2604.24238v1

Diffusion models are a leading paradigm for data generation, but training-free editing typically re-runs the full denoising trajectory for every edit strength, making iterative refinement expensive. To address this issue, we instead edit near the data manifold, where small local updates can replace repeated re-synthesis. To enable this, we estimate a local manifold tangent space directly from perturbed samples and prove that this sample-based estimator closely approximates the true tangent. Building on this guarantee, we devise a Jacobian-free algorithm that constructs a tangent frame via small perturbations to the initial noise and alternates small tangent moves with diffusion-based projections. Updates within this frame follow principled on-manifold directions while suppressing off-manifold drift, enabling fine-grained edits without full re-diffusion or additional training. Edit strength is controlled by the number of steps for rapid, continuous adjustments that preserve fidelity and plug into existing samplers. Empirically, the resulting tangent directions yield smooth, semantic unsupervised traversals and effective CLIP-guided optimization, demonstrating practical interactive continuous editing.

---

### Deep Learning-Enabled Dissolved Oxygen Sensing in Biofouling Environments for Ocean Monitoring

Authors: Nikolaos Salaris, Adrien Desjardins, Manish K. Tiwari
Published: 2026-04-27
Categories: eess.IV, cs.AI, cs.CV, eess.SP
arXiv: https://arxiv.org/abs/2604.24236v1

The escalating climate crisis and ecosystem degradation demand intelligent, low-cost sensors capable of robust, long-term monitoring in real-world environments. Absolute dissolved oxygen (DO) concentration is a key parameter for predicting climate tipping points. Inexpensive optoelectronic sensors based on microstructured polymer films doped with phosphorescent dyes could be readily deployable; however, signal drift and marine biofouling remain major challenges. Here, we introduce a sensing paradigm that combines camera-based DO sensors with a visual transformer (ViT)-based physics-informed neural network (PINN) for high-fidelity sensing under biofouling conditions. Training and testing data were obtained from an algae-laden water tank over 14 days to capture accelerated biofouling. The ViT-PINN, which embeds the Stern-Volmer (SV) equation into the loss function, reduces mean average error (MAE) by 92% and 89% compared to classical statistical and ML approaches, achieving ~2 umol/L absolute error. A deep ensemble further quantifies predictive uncertainty, enabling self-diagnostic sensing.

---

### Touchless Intraoperative Image Access System Based on Vision-Based Hand Tracking

Authors: Yin Lin, Domenico Aquino, Alberto Redaelli, Massimiliano Del Bene, Riccardo Barbieri, Simona Ferrante
Published: 2026-04-27
Categories: cs.CV
arXiv: https://arxiv.org/abs/2604.24235v1

Touchless interaction with medical images is becoming increasingly important in the surgical field, where sterility and continuity of the operational workflow are essential requirements. This work presents a vision-based system for intraoperative navigation of medical images through hand gestures acquired using a single RGB camera. Unlike many existing solutions, the system does not require additional hardware or user-specific training. Hand tracking is performed in real time using MediaPipe Hands, which provides a 2.5D estimation of hand landmarks. Simple and intuitive gestures are then mapped into translation, rotation, and zoom commands, enabling continuous and natural interaction with the image viewer. The system architecture is independent from the visualization software and, for implementation simplicity, in this study it was integrated with PyVista. Performance was evaluated through frame-level logging and quantitative analysis of latency, stability, and interaction robustness metrics. Experimental results highlight real-time behavior, with reduced latencies and stable control, in line with the requirements of fluid interaction. The system demonstrates the feasibility of a low-cost touchless solution for intraoperative access to medical images, laying the groundwork for future clinical evaluations.

---

### Graph-augmented Segmentation of Complex Shapes in Laser Powder bed Fusion for Enhanced In Situ Inspection

Authors: Stefano Raimondo, Matteo Bugatti, Marco Grasso
Published: 2026-04-27
Categories: cs.CV
arXiv: https://arxiv.org/abs/2604.24234v2

The technological maturity of in situ inspection and monitoring methods in additive manufacturing is steadily increasing, enabling more efficient and practical qualification procedures. In this context, image segmentation of powder bed images in Laser Powder Bed Fusion (L-PBF) has been investigated by various authors, leveraging both edge detection and machine learning approaches to identify deviations from nominal geometry. Despite these developments, several challenges remain, including the sensitivity of segmentation performance to industrial illumination conditions and layer-to-layer variability in pixel intensity patterns. The study addresses these limitations by proposing a graph-augmented segmentation approach. The underlying principle consists of preserving the geometrical information at a global level rather than at pixel-wise level, modeling dependencies and relational information among spatial regions with a Graph Neural Network bottleneck embedded into a U-Net architecture. This allows enhancing the consistency and accuracy of the geometry reconstruction in the presence of spatial and layer-wise photometric variability systematically faced in real data. The method is evaluated against benchmark techniques for the in situ reconstruction of lattice structures produced by L-PBF, demonstrating its potential as a scalable solution for robust in situ inspection and geometric verification in industrial environments.

---

### Graph-augmented Segmentation of Complex Shapes in Laser Powder bed Fusion for Enhanced In Situ Inspection

Authors: Stefano Raimondo, Matteo Bugatti, Marco Grasso
Published: 2026-04-27
Categories: cs.CV
arXiv: https://arxiv.org/abs/2604.24234v1

The technological maturity of in situ inspection and monitoring methods in additive manufacturing is steadily increasing, enabling more efficient and practical qualification procedures. In this context, image segmentation of powder bed images in Laser Powder Bed Fusion (L-PBF) has been investigated by various authors, leveraging both edge detection and machine learning approaches to identify deviations from nominal geometry. Despite these developments, several challenges remain, including the sensitivity of segmentation performance to industrial illumination conditions and layer-to-layer variability in pixel intensity patterns. The study addresses these limitations by proposing a graph-augmented segmentation approach. The underlying principle consists of preserving the geometrical information at a global level rather than at pixel-wise level, modeling dependencies and relational information among spatial regions with a Graph Neural Network bottleneck embedded into a U-Net architecture. This allows enhancing the consistency and accuracy of the geometry reconstruction in the presence of spatial and layer-wise photometric variability systematically faced in real data. The method is evaluated against benchmark techniques for the in situ reconstruction of lattice structures produced by L-PBF, demonstrating its potential as a scalable solution for robust in situ inspection and geometric verification in industrial environments.

---