# Research Papers — 2026-04 · bundle page 37 of 233 > Full-text markdown of papers #1801–1850 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/37 [← Previous bundle](https://aipod.dev/papers/archive/2026-04/page/36.md) [Next bundle →](https://aipod.dev/papers/archive/2026-04/page/38.md) ### Talking Slide Avatars: Open-Source Multimodal Communication Approach for Teaching Authors: Xinxing Wu Published: 2026-04-26 Categories: cs.HC, cs.AI, cs.CY arXiv: https://arxiv.org/abs/2604.23703v2 Slide-based teaching is widely used in higher education, yet in online, hybrid, and asynchronous contexts, slides often lose instructor presence, narrative continuity, and expressive framing that help learners connect with course content. Full lecture video can partly restore these qualities, but it is time-consuming to record, revise, and reuse. This study presents a practice-based implementation and analytic reflection of an open-source workflow for creating talking slide avatars. The workflow integrates OpenVoice for text-to-speech and authorized voice-style conversion with Ditto-TalkingHead for audio-driven talking-image synthesis, enabling instructors to transform a short script and an authorized or synthetic portrait image into a narrated video for slide decks or HTML-based lecture materials. Rather than treating this workflow only as a technical solution, the study frames talking slide avatars as multimodal communication artifacts at the intersection of digital pedagogy, aesthetic education, and art-technology practice. The paper documents the production pipeline, analyzes communicative and aesthetic affordances, and proposes practical guidelines for script length, image selection, pacing, disclosure, accessibility, consent, and ethical use. Its contribution is not a validated learning intervention, but an educator-oriented open-source production model and communication-design framework. The study concludes that short, transparent, and carefully designed avatars may provide a reusable communication layer for introductions, transitions, reminders, and recaps when used selectively and with appropriate ethical safeguards. --- ### Agri-CPJ: A Training-Free Explainable Framework for Agricultural Pest Diagnosis Using Caption-Prompt-Judge and LLM-as-a-Judge Authors: Wentao Zhang, Qi Zhang, Mingkun Xu, Mu You, Henghua Shen, Zhongzhi He, Keyan Jin, Derek F. Wong, Tao Fang Published: 2026-04-26 Categories: cs.CL, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2604.23701v1 Crop disease diagnosis from field photographs faces two recurring problems: models that score well on benchmarks frequently hallucinate species names, and when predictions are correct, the reasoning behind them is typically inaccessible to the practitioner. This paper describes Agri-CPJ (Caption-Prompt-Judge), a training-free few-shot framework in which a large vision-language model first generates a structured morphological caption, iteratively refined through multi-dimensional quality gating, before any diagnostic question is answered. Two candidate responses are then generated from complementary viewpoints, and an LLM judge selects the stronger one based on domain-specific criteria. Caption refinement is the component with the largest individual impact: ablations confirm that skipping it consistently degrades downstream accuracy across both models tested. On CDDMBench, pairing GPT-5-Nano with GPT-5-mini-generated captions yields \textbf{+22.7} pp in disease classification and \textbf{+19.5} points in QA score over no-caption baselines. Evaluated without modification on AgMMU-MCQs, GPT-5-Nano reached 77.84\% and Qwen-VL-Chat reached 64.54\%, placing them at or above most open-source models of comparable scale despite the format shift from open-ended to multiple-choice. The structured caption and judge rationale together constitute a readable audit trail: a practitioner who disagrees with a diagnosis can identify the specific caption observation that was incorrect. Code and data are publicly available https://github.com/CPJ-Agricultural/CPJ-Agricultural-Diagnosis --- ### Beyond coauthorship: semantic structure and phantom collaborators in transportation research, 1967--2025 Authors: Seongjin Choi Published: 2026-04-26 Categories: cs.DL, cs.LG arXiv: https://arxiv.org/abs/2604.23699v1 We present a semantic-structural atlas of transportation research built from 120{,}323 papers across 34 peer-reviewed journals published between 1967 and 2025, roughly an order of magnitude larger than and a decade beyond Sun and Rahwan's~(2017) coauthorship study. We use OpenAlex and Crossref as open, CC0-licensed data sources, resolve author identity through OpenAlex author IDs, ORCID records, and manual alias resolution, and embed every paper with SPECTER2 with Arora-style whitening concatenated with concept TF--IDF and venue linear-discriminant projections. On this substrate we report three findings. First, Leiden on the author-level semantic k-nearest-neighbor graph yields 23 topic communities that agree only weakly with the 172 coauthor communities (normalized mutual information $0.23$), opening room for a predictive layer that neither source encodes alone. Second, a multiplex Leiden partition combining both edge types recovers 181 communities and localizes where collaboration and topic structure decouple. Third -- the paper's core methodological contribution -- we define \emph{phantom collaborators}, pairs of authors who are top-$K$ semantic neighbors yet $\geq 3$ hops apart in the coauthor graph, and show via a temporal hold-out (training cutoff 2019) that phantom pairs become real coauthors in 2020--2025 at a rate $16$ to $33$ times above random, popularity-weighted, and same-venue baselines, with a $68$-fold monotone gradient between the highest- and lowest-similarity buckets. All artifacts are released as a live, reproducible web atlas at https://choi-seongjin.github.io/transport-atlas/. --- ### Benchmarking Testing in Automated Theorem Proving Authors: Jongyoon Kim, Hojae Han, Seung-won Hwang Published: 2026-04-26 Categories: cs.CL, cs.FL arXiv: https://arxiv.org/abs/2604.23698v1 Recent advances in large language models (LLMs) have shown promise in formal theorem proving, yet evaluating semantic correctness remains challenging. Existing evaluations rely on indirect proxies such as lexical overlap with human-annotated proof, or expensive manual inspection. Inspired by the shift from lexical comparison to test-based evaluation in code generation, we propose T , a framework that evaluates the semantic correctness of formal theorems: a generated theorem is considered correct only if all dependent successor theorems compile successfully, analogous to integration testing. We construct a benchmark from 5 real-world Lean 4 repositories, comprising 2,206 problems paired with 41 successor theorems on average, automatically extracted without human effort. Experiments demonstrate that while state-of-the-art models achieve high compilation success, they perform significantly worse under our semantic metric. The best model, Claude-Sonnet-4.5, achieves only 38.9% Testing Accuracy on the full set, given both natural language proof and successor theorems as context, revealing a critical gap in current theorem generation capabilities. --- ### Personalizing Causal Audio-Driven Facial Motion via Dynamic Multi-modal Retrieval Authors: Xuangeng Chu, Yu Han, Wei Mao, Shih-En Wei Published: 2026-04-26 Categories: cs.GR, cs.CV arXiv: https://arxiv.org/abs/2604.23692v2 Audio-driven facial animation is essential for immersive digital interaction, yet existing frameworks struggle to reconcile real-time streaming with high-fidelity personalization. Current methods either rely on latency-inducing audio look-ahead, or ask users to record scripted calibration sequences to pre-encode static identity embeddings that fail to capture dynamic idiosyncrasies. We present an end-to-end framework for personalized audio-driven facial motion generation, supporting causal, zero-lookahead streaming. We introduce two key innovations: (1) a causal multi-resolution motion tokenizer that captures both global temporal context and high-frequency articulatory details, and (2) a multi-modal style retriever that extracts stylistic priors from unstructured reference libraries by jointly querying ongoing audio and motion. Unlike prior retrieval mechanisms restricted to curated, fixed-size, or audio-only style banks, our design accepts arbitrary footage of the target identity, enabling personalization from a handful of casually recorded clips. By integrating these components, our method outperforms state-of-the-art approaches in lip-sync accuracy, identity consistency, and perceived realism, while preserving the streaming constraints of real-time telepresence. Code is available at https://github.com/xg-chu/Fallingwater. --- ### Personalizing Causal Audio-Driven Facial Motion via Dynamic Multi-modal Retrieval Authors: Xuangeng Chu, Yu Han, Wei Mao, Shih-En Wei Published: 2026-04-26 Categories: cs.GR, cs.CV arXiv: https://arxiv.org/abs/2604.23692v1 Audio-driven facial animation is essential for immersive digital interaction, yet existing frameworks fail to reconcile real-time streaming with high-fidelity personalization. Current methods often rely on latency-inducing audio look-ahead, or require high user compliance to pre-encode static embeddings that fails to capture dynamic idiosyncrasies. We present an end-to-end causal framework for personalizing causal facial motion generation via dynamic multi-modal style retrieval, enabling ultra-low latency while uniquely leveraging unstructured style references. We introduce two key innovations: (1) a temporal hierarchical motion representation that captures global temporal context and high-frequency details while maintaining decoding causality, and (2) a multi-modal style retriever that jointly queries audio and motion to dynamically extract stylistic priors without breaking causality. This mechanism allows for scalable personalization with total flexibility regarding the number and contents of templates. By integrating these components into a causal autoregressive architecture, our method significantly outperforms state-of-the-art approaches in lip-sync accuracy, identity consistency, and perceived realism, supported by extensive quantitative evaluations and user studies. --- ### Do Protective Perturbations Really Protect Portrait Privacy under Real-world Image Transformations? Authors: Ruiqing Sun, Xingshan Yao, Zhijing Wu, Tian Lan, Chenhao Cui, Huiyang Zhao, Jialing Shi, Chen Yang, Xianling Mao Published: 2026-04-26 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.23688v2 Proactive defense methods protect portrait images from unauthorized editing or talking face generation (TFG) by introducing pixel-level protective perturbations, and have attracted increasing attention for privacy protection. In real-world use, images inevitably undergo sequences of benign operations during display and dissemination, such as resizing and color compression, which directly alter pixel values. Existing studies and robustness defenses mainly examine individual transformations in isolation, while sequentially composed transformations remain underexplored. To address this gap, we systematically evaluate whether representative proactive defenses against unauthorized image editing using GANs and diffusion models, as well as talking face generation, remain effective under sequential image transformations. The evaluated methods span general-purpose and portrait-specific defenses and are assessed qualitatively and quantitatively. Experimental results show that pixel-level perturbation-based defenses struggle to withstand sequences of common image transformations, posing a risk of failure in real-world applications. To further demonstrate that this vulnerability can be exploited at low cost, we introduce Transformation-Induced Purification via Region-wise Super-Resolution (TIP-RSR), a simple training-free framework combining sequential image transformations with off-the-shelf restoration models. TIP-RSR efficiently purifies protective perturbations while preserving image fidelity and requiring substantially less computation than diffusion-based purification methods. These findings expose a practical vulnerability in current proactive portrait defenses and highlight the need to account for sequential real-world transformations when designing future protection mechanisms. Our code is publicly available at https://github.com/Richen7418/TIP-RSR. --- ### Do Protective Perturbations Really Protect Portrait Privacy under Real-world Image Transformations? Authors: Ruiqing Sun, Xingshan Yao, Zhijing Wu, Tian Lan, Chenhao Cui, Huiyang Zhao, Jialing Shi, Chen Yang, Xianling Mao Published: 2026-04-26 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.23688v1 Proactive defense methods protect portrait images from unauthorized editing or talking face generation (TFG) by introducing pixel-level protective perturbations, and have already attracted increasing attention for privacy protection. In real-world scenarios, images inevitably undergo various transformations during cross-device display and dissemination--such as scale transformations and color compression--that directly alter pixel values. However, it remains unclear whether such pixel-level modifications affect the effectiveness of existing proactive defense methods that rely on pixel-level perturbations. To solve this problem, we conduct a systematic evaluation of representative proactive defenses under image transformation. The evaluated methods are selected to span different generation architectures such as diffusion and GAN-based models, as well as defense scopes covering both portrait and natural images, and are assessed using both qualitative and quantitative metrics for subjective and objective comparison. Experimental results indicate that defense methods based on pixel-level perturbations struggle to withstand common image transformations, posing a risk of defense failure in real-world applications. To further highlight this risk, we propose a simple yet effective purification framework by leveraging the vulnerabilities induced by real-world image transformations. Experimental results demonstrate that the proposed method can efficiently remove protective perturbations with low computational cost, highlighting previously overlooked risks to the research community. --- ### Reading in the Dark: Low-light Scene Text Recognition Authors: Xuanshuo Fu, Lei Kang, Ernest Valveny, Dimosthenis Karatzas, Javier Vazquez-Corral Published: 2026-04-26 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.23685v1 Accurate text recognition in low-light environments is essential for intelligent systems in applications ranging from autonomous vehicles to smart surveillance. However, challenges such as poor illumination and noise interference remain underexplored. To address this gap, we introduce LSTR, a large-scale Low-light Scene Text Recognition dataset comprising 11,273 low-light images generated from well-lit datasets (ICDAR2015, IIIT5K, and WordArt), along with ESTR, which includes 60 real nighttime street-scene images in English and Spanish for exclusive evaluation. We explore two solution strategies: (1) employing Optical Character Recognition (OCR) models with fine-tuning and LoRA-based fine-tuning and (2) a joint training strategy that integrates a low-light image enhancement (LLIE) module with an OCR model. In particular, we propose a novel re-render LLIE (RLLIE) module, which demonstrates improved performance on real-world data. Through extensive experimentation, we analyze various training strategies and address a key research question: \emph{How bright is bright enough for effective scene text recognition?} Our results indicate that standalone LLIE or OCR models perform inadequately under low-light conditions, highlighting the advantages of specialized, jointly trained text-centric approaches. Additionally, we provide a comprehensive benchmark to support future research in robust low-light scene text recognition. https://huggingface.co/datasets/lumimusta/Low-light_Scene_Text_Dataset. --- ### Learning to Decipher from Pixels: A Case Study of Copiale Authors: Lei Kang, Giuseppe De Gregorio, Raphaela Heil, Alicia Fornés, Beáta Megyesi Published: 2026-04-26 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.23683v2 Historical encrypted manuscripts require both paleographic interpretation of cipher symbols and cryptanalytic recovery of plaintext. Most existing computational workflows rely on a transcription-first paradigm, in which handwritten symbols are transcribed prior to decipherment. This intermediate step is labor-intensive, error-prone, and not always aligned with the goal of direct plaintext recovery. We propose an end-to-end, transcription-free approach that directly maps handwritten cipher images to plaintext. Using the Copiale cipher as a case study, we introduce the first text-line-level dataset pairing cipher images with German plaintext. We show that pretraining on generic handwriting data followed by cipher-specific fine-tuning substantially improves decipherment accuracy. Our results demonstrate that transcription-free image-to-plaintext decipherment is both feasible and effective for historical substitution ciphers, offering a simplified and scalable alternative to traditional pipelines. https://github.com/leitro/Decipher-from-Pixels-Copiale --- ### Rank, Head-Channel Non-Identifiability, and Symmetry Breaking: A Precise Analysis of Representational Collapse in Transformers Authors: Giansalvo Cirrincione Published: 2026-04-26 Categories: cs.LG, cs.CL, stat.ML arXiv: https://arxiv.org/abs/2604.23681v1 A widely cited result by Dong et al. (2021) showed that Transformers built from self-attention alone, without skip connections or feed-forward layers, suffer from rapid rank collapse: all token representations converge to a single direction. The proposed remedy was the MLP. We show that this picture, while correct in the regime studied by Dong, is incomplete in ways that matter for architectural understanding. Three results are established. First, layer normalisation is precisely affine-rank-neutral: it preserves the affine rank of the token representation set exactly. The widespread claim that LN "plays no role" is imprecise; the correct statement is sharper. Second, residual connections generically obstruct rank collapse in real Transformers such as BERT-base, in a measure-theoretic sense, without contribution from the MLP. The MLP's irreplaceable function is different: generating feature directions outside the linear span of the original token embeddings, which no stack of attention layers can produce. Third, a phenomenon distinct from rank collapse is identified: head-channel non-identifiability. After multi-head attention sums per-head outputs through the output projection, individual contributions cannot be canonically attributed to a specific head; n(H-1)d_k degrees of freedom per layer remain ambiguous when recovering a single head from the mixed signal. The MLP cannot remedy this because it acts on the post-summation signal. A constructive partial remedy is proposed: a position-gated output projection (PG-OP) at parameter overhead below 1.6% of the standard output projection. The four collapse phenomena identified in the literature -- rank collapse in depth, in width, head-channel non-identifiability, and entropy collapse -- are unified under a symmetry-breaking framework, each corresponding to a distinct symmetry of the Transformer's forward pass. --- ### Transferable Human Mobility Network Reconstruction with neuroGravity Authors: Jinming Yang, Shaoyu Huang, Zongyuan Huang, Yaohui Jin, Xiaokang Yang, Marta C. Gonzalez, Yanyan Xu Published: 2026-04-26 Categories: cs.AI arXiv: https://arxiv.org/abs/2604.23678v1 Accurate modeling of human mobility is critical for tackling urban planning and public health challenges. In undeveloped regions, the absence of comprehensive travel surveys necessitates reconstructing mobility networks from publicly available data. Here we develop neuroGravity, a physics-informed deep learning model that reliably reconstructs mobility flows from limited observations and transfers to unobserved cities. Using only urban facility and population distributions, we find that neuroGravity's regional representations strongly correlate with socioeconomic and livability status, offering scalable proxies for costly surveys. Furthermore, we uncover that spatial income segregation plays a key role in model transferability: mobility networks are most reliably reconstructed when target cities share similar segregation levels with the source. We design an index to quantify this segregation and accurately predict transferability. Finally, we generate mobility flow proxies for over 1,200 cities worldwide, highlighting neuroGravity's potential to mitigate critical data shortages in resource-limited, underdeveloped areas. --- ### GS-DOT: Gaussian splatting-based image reconstruction for diffuse optical tomography Authors: Jingjing Jiang Published: 2026-04-26 Categories: eess.IV, cs.CV, physics.med-ph arXiv: https://arxiv.org/abs/2604.23675v1 This work presents GS-DOT, a novel image reconstruction framework based on Gaussian Splatting (GS) for diffuse optical tomography (DOT). Inspired by GS for rendering applications, absorption coefficients are represented as a sparse sum of anisotropic Gaussian primitives optimized to fit measured time-resolved point-spread functions through analytic gradients and Adam optimization. This is the first adaptation of GS algorithms in the photon diffusion regime, where the ray transport function is replaced by the diffusion functions to enable accurate modeling of light transport in highly scattering media. Validation on synthetic tissue models demonstrate high accuracy in localization and quantification of reconstructed absorption maps for both clean and noisy signals. GS-DOT has demonstrated high robustness to noise and showed a huge reduction in memory demand. --- ### Vibe Medicine: Redefining Biomedical Research Through Human-AI Co-Work Authors: Zihao Wu, Steven Xu, Bowen Chen, Shaowen Wan, Yiwei Li, Wei Ruan, Yanjun Lyu, Siyuan Li, Dajiang Zhu, Tianming Liu, Lin Zhao Published: 2026-04-26 Categories: cs.AI arXiv: https://arxiv.org/abs/2604.23674v1 With the emergence of large language models (LLMs) and AI agent frameworks, the human-AI co-work paradigm known as Vibe Coding is changing how people code, making it more accessible and productive. In scientific research, where workflows are more complex and the burden of specialized labor limits independent researchers and those in low-resource areas, the potential impact is even greater, particularly in biomedicine, which involves heterogeneous data modalities and multi-step analytical pipelines. In this paper, we introduce Vibe Medicine, a co-work paradigm in which clinicians and researchers direct skill-augmented AI agents through natural language to execute complex, multi-step biomedical workflows, while retaining the role of research director who specifies objectives, reviews intermediate results, and makes domain-informed decisions. The enabling infrastructure consists of three layers: capable LLMs, agent frameworks such as OpenClaw and Hermes Agent, and the OpenClaw medical skills collection, which includes more than 1,000 curated skills from multiple open-source repositories. We analyze the architecture and skill categories of this collection across ten biomedical domains, and present case studies covering rare disease diagnosis, drug repurposing, and clinical trial design that demonstrate end-to-end workflows in practice. We also identify the principal risks, such as hallucination, data privacy, and over-reliance, and outline directions toward more reliable, trustworthy, and clinically integrated agent-assisted research that advances research and technological equity and reduces health care resource disparities. --- ### Preserve, Then Resolve: Many-to-Many Association and Robust Estimation with General-Purpose Visual Features Authors: Haodong Jiang, Mingzhe Li, Junfeng Wu Published: 2026-04-26 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.23670v3 The semantic transferability of general-purpose visual features does not guarantee geometric consistency across images. Using frozen DINOv3 features, we show that geometrically correct correspondences often fall below rank one in cosine similarity yet remain within a small top-$K$ candidate set. This motivates a preserve-then-resolve design: we retain multiple candidates in a many-to-many (m-to-m) association graph and defer their disambiguation to robust estimation. We study m-to-m robust estimation from a probabilistic perspective. We interpret the existing Matching Cardinality Maximization (MCM) mechanism as a dominant-cardinality approximation to likelihood maximization and propose a faster, real-valued mechanism called Harmonic Consensus Maximization (HCM). A two-stage LO-RANSAC uses HCM for candidate sourcing and MCM for graph-aware selection. We evaluate end-task gains in relative-pose estimation, where our pipeline consistently improves rank-one baselines for DINOv2, DINOv3, V-JEPA 2.1, and SigLIP 2. Code is available at https://github.com/LIAS-CUHKSZ/preserve_then_resolve. --- ### Zero-Shot DINOv3-Based Image Matching via Many-to-Many Association Authors: Haodong Jiang, Mingzhe Li, Junfeng Wu Published: 2026-04-26 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.23670v2 We explore zero-shot image matching based on DINOv3 features. These general-purpose features are semantically rich yet geometrically ambiguous -- the nearest neighbor in feature space is often a false geometric match -- so the conventional one-to-one association paradigm is prone to discarding true correspondences. We instead retain many-to-many associations and cast the ensuing estimation as maximum-likelihood inference. This formulation reveals the existing robust mechanism for many-to-many association as a zeroth-order approximation to the otherwise intractable likelihood, and yields a novel mechanism with faster evaluation and finer granularity. We condense these theoretical findings into a two-stage LO-RANSAC algorithm which, combined with careful layer selection and positional bias correction for DINOv3 features, forms a zero-shot pipeline that degrades gracefully under background variation and across RGB-thermal pairs, where specialized baselines collapse under domain shift. Code released at https://github.com/LIAS-CUHKSZ/Zero-Shot-DINOv3-Image-Matching. --- ### An AI-Based Supervisory Measurement Integrity Validation Layer for Cyber-Resilient AC/DC Protection in Inverter-Based Microgrids Authors: Ahmad Mohammad Saber, Ahmed Saber Refae, Davor Svetinovic, Hatem Zeineldin, Amr Youssef, Ehab F. El-Saadany, Deepa Kundur Published: 2026-04-26 Categories: cs.CR, cs.AI, eess.SP, eess.SY arXiv: https://arxiv.org/abs/2604.23666v1 Line current differential relays (LCDRs) are measurement-driven relays that rely on time-synchronized multi-phase current waveforms to infer internal faults in AC and DC power networks. In inverter-based microgrids, however, the increasing reliance on digitally communicated measurements exposes LCDRs to false-data injection attacks (FDIAs), in which adversaries manipulate remote measurement streams to create protection-triggering yet physically inconsistent current trajectories. This paper addresses this emerging measurement integrity problem by introducing a measurement integrity validation scheme that operates as a supervisory instrumentation layer for modern LCDRs. The proposed scheme interprets short windows of synchronized instantaneous current measurements recorded during relay operation and assesses their physical consistency to distinguish genuine fault-induced trajectories from cyber-manipulated measurement streams. A recurrent neural network is trained offline using only relay-available current measurements and exploits the temporal structure of differential current waveforms, which remains informative in inverter-dominated systems where current magnitude is no longer a reliable observable. The method requires no additional sensors, auxiliary protection elements, or prior knowledge of network topology, and is applicable to both AC and DC LCDRs without structural modification. The proposed measurement validation scheme is evaluated on an islanded inverter-based microgrid under a comprehensive set of fault and FDIA scenarios, demonstrating high detection accuracy while preserving relay dependability. Hardware-in-the-loop validation using an OPAL-RT real-time simulator confirms that the scheme satisfies protection timing constraints and can operate in real time under realistic operating conditions. --- ### HAC: Parameter-Efficient Hyperbolic Adaptation of CLIP for Zero-Shot VQA Authors: Francesco Dibitonto, Cigdem Beyan, Vittorio Murino Published: 2026-04-26 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.23665v1 Recent advances in representation learning have shown that hyperbolic geometry can offer a more expressive alternative to the Euclidean embeddings used in CLIP models, capturing hierarchical structures and leading to better-organized representations. However, current hyperbolic CLIP variants are trained entirely from scratch, which is computationally expensive and resource-intensive. In this work, we propose HAC (Hyperbolic Adaptation of CLIP), a parameter-efficient framework that enables pretrained CLIP models to transition into hyperbolic space via lightweight fine-tuning. We apply HAC to Visual Question Answering (VQA), where models must interpret visual elements and align them with textual queries. Notably, HAC's training is performed on a dataset with no overlap with any VQA benchmark, resulting in a strict zero-shot evaluation paradigm that underscores HAC's task-agnostic adaptability. We evaluate HAC across a diverse suite of VQA benchmarks spanning General, Reasoning, and OCR categories. Both HAC-S (small) and HAC-B (medium) consistently surpass Euclidean baselines and prior hyperbolic approaches, with HAC-B delivering up to a +1.9 point average improvement over CLIP-B on reasoning-intensive tasks. Our code is available at https://github.com/fdibiton/HAC --- ### SolarFCD: A Large-Scale Dataset and Benchmark for Solar Fault Classification in Photovoltaic Systems Authors: Misbah Ijaz, Saif Ur Rehman Khan, Abd Ur Rehman, Arooj Zaib, Sebastian Vollmer, Andreas Dengel, Muhammad Nabeel Asim Published: 2026-04-26 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.23662v1 The increasing global deployment of solar photovoltaic (PV) systems needs robust, scalable, and automated inspection technologies capable of detecting a wide range of panel flaws under a variety of operating situations. The lack of large-scale, multi-modal, publicly available annotated datasets is a major obstacle preventing advancement in this field. We introduce SolarFCD, an extensive dataset of solar panel defects created by methodically combining and reconciling three publicly accessible datasets covering two imaging modalities: RGB/Drone images and Thermal Infrared. The dataset consist of 4,435 images arranged under four unified defect classes such as: healthy images, Surface Obstruction, structural fault, and electrical fault. The dataset was divided into training, validation, and test splits at an 80:10:10 ratio through methodical label mapping, near-duplicate removal, and targeted augmentation of minority classes. Sixteen classification architectures from five design families were trained and assessed on the dataset to provide repeatable benchmark baselines. With an accuracy of 86.68%, precision of 88.65%, recall of 88.62%, and F1-score of 88.17%, ResNet101V2 performed the best overall. Per-class results showed balanced detection across all four defect categories within a narrow performance band of less than 1.2 percentage points. To promote open and repeatable research in automated PV inspection and solar energy operations and maintenance, the dataset, annotation files, and baseline code are made openly available. --- ### FlowPlace: Flow Matching for Chip Placement Authors: Peng Xie, Ke Xue, Yunqi Shi, Ruo-Tong Chen, Chengrui Gao, Siyuan Xu, Chenjian Ding, Mingxuan Yuan, Chao Qian Published: 2026-04-26 Categories: cs.AR, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2604.23658v2 Chip placement plays an important role in physical design. While generative models like diffusion models offer promising learning-based solutions, current methods have the following limitations: they use random synthetic data for pre-training, require long sampling times, and often result in overlaps due to their dependence on gradient-based solvers during the sampling process. To overcome these issues, we propose FlowPlace, which features mask-guided synthetic data generation, flow-based efficient training with flexible prior injection, and hard constraint sampling for overlap-free layouts. Experiments on OpenROAD and ICCAD 2015 benchmarks show FlowPlace achieves better PPA metrics, 10-50$\times$ faster sampling efficiency, and zero overlaps. --- ### BVI-Mamba: Video Enhancement Using a Visual State-Space Model for Low-Light and Underwater Environments Authors: Guoxi Huang, Ruirui Lin, Yini Li, David R. Bull, Nantheera Anantrasirichai Published: 2026-04-26 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.23655v1 Videos captured in low-light and underwater conditions often suffer from distortions such as noise, low contrast, color imbalance, and blur. These issues not only limit visibility but also degrade automatic tasks like detection. Post-processing is typically required but can be time-consuming. AI-based tools for video enhancement also demand significantly more computational resources compared to image-based methods. This paper introduces a novel framework, Visual Mamba, designed to reduce memory usage and computational time by leveraging the Visual State Space (VSS) model. The framework consists of two modules: (i) a feature alignment module, where spatio-temporal displacement between input frames is registered in the feature space, and (ii) an enhancement module, where noise removal and brightness adjustment are performed using a UNet-like architecture, with all convolutional layers replaced by VSS blocks. Experimental results show that the Visual Mamba technique outperforms Transformer and convolution-based models in both low-light and underwater video enhancement tasks. Code is available on line at https://github.com/russellllaputa/BVI-Mamba. --- ### ResAF-Net: An Anchor-Free Attention-Based Network for Tree Detection and Agricultural Mapping in Palestine Authors: Rabee Al-Qasem Published: 2026-04-26 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2604.23653v1 Reliable agricultural data is essential for food security, land-use planning, and economic resilience, yet in Palestine, such data remains difficult to collect at scale because of fragmented landscapes, limited field access, and restrictions on aerial monitoring. This paper presents ResAF-Net, a satellite-based tree detection framework designed for large-scale agricultural monitoring in resource-constrained settings. The proposed architecture combines a ResNet-50 encoder, Atrous Spatial Pyramid Pooling (ASPP), a feature-fusion stage, a multi-head self-attention refinement module, and an anchor-free FCOS detection head to improve tree localization in dense and heterogeneous scenes. Trained on the MillionTrees benchmark, the model achieved 82% Recall, 63.03% mAP@0.50, and 35.47% mAP@0.50:0.95 on the validation split, indicating strong sensitivity to tree presence while maintaining competitive localization quality. Beyond benchmark evaluation, we implemented the model within a web-based GIS application integrated with Palestinian cadastral data from GeoMolg, enabling tree analysis at scene, parcel, and community levels. This deployment demonstrates the practical feasibility of AI-assisted agricultural inventorying in Palestine. It provides a foundation for data-driven monitoring, reporting, and future species-level analysis of Mediterranean tree crops. --- ### Geometry-Conditioned Diffusion for Occlusion-Robust In-Bed Pose Estimation Authors: Navid Aslankhani Khameneh, Marco Carletti, Cigdem Beyan Published: 2026-04-26 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.23651v1 Robust in-bed human pose estimation under blanket occlusion remains challenging due to the scarcity of reliable labeled training data for heavily covered poses. Existing approaches rely on multi-modal sensing or image-to-image translation frameworks that remain conditioned on visible source imagery, limiting scalability and pose diversity. In this work, we reformulate occlusion-aware augmentation as a geometry-conditioned generative modeling task. We conduct a systematic comparison of deterministic masking, unpaired translation, paired diffusion-based translation, and a proposed pose-conditioned Latent Diffusion Model (Pose-LDM). Unlike image-guided methods, Pose-LDM synthesizes blanket-covered images directly from skeletal keypoints, eliminating dependence on paired supervision and pixel-level source-image conditioning while enabling generation from arbitrary pose inputs. All augmentation strategies are evaluated through their impact on downstream pose estimation under a fixed backbone. Pose- LDM achieves the highest strict localization accuracy under severe occlusion while maintaining overall detection performance comparable to paired diffusion models, approaching the performance of fully supervised training. These results demonstrate that geometry-conditioned diffusion provides an effective and supervision-efficient pathway toward occlusion-robust inbed pose estimation without modifying the sensing pipeline. The code is available at: github.com/navidTerraNova/ GeoDiffPose. --- ### Hardware-Efficient Softmax and Layer Normalization with Guaranteed Normalization for Edge Devices Authors: Dawon Choi, Hana Kim, Ji-Hoon Kim Published: 2026-04-26 Categories: cs.AR, cs.LG arXiv: https://arxiv.org/abs/2604.23647v1 In Transformer models, non-GEMM (non-General Matrix Multiplication) operations -- especially Softmax and Layer Normalization (LayerNorm) -- often dominate hardware cost due to their nonlinear nature. To address this, previous approximation studies mainly target rank-oriented tasks, which is acceptable for classification. However, edge Natural Language Processing (NLP) applications and edge generative AI are largely evaluated based on score-oriented tasks, so normalization-guaranteed non-GEMM operations are essential. We propose a hardware-efficient Softmax and LayerNorm with Guaranteed Normalization for Edge devices. Our design employs hardware-efficient approximation methods while preserving the normalization (Softmax: $\sum p = 1$, LayerNorm: $σ= 1$). Our architecture is described in Verilog HDL and synthesized using the Samsung 28nm CMOS process. In accuracy evaluation, we achieve high accuracy with minimal degradation: GLUE +0.07%, SQuAD -0.01%, perplexity -0.09%. Implementation results show that our architecture is small: $942\,μm^2$ for Softmax, $1199\,μm^2$ for LayerNorm. Compared to the state of the art, we achieve up to 11x and 14x reduction in area, respectively. --- ### Structural Enforcement of Goal Integrity in AI Agents via Separation-of-Powers Architecture Authors: Rong Xiang Published: 2026-04-26 Categories: cs.AI, cs.CR arXiv: https://arxiv.org/abs/2604.23646v1 Recent evidence suggests that frontier AI systems can exhibit agentic misalignment, generating and executing harmful actions derived from internally constructed goals, even without explicit user requests. Existing mitigation methods, such as Reinforcement Learning from Human Feedback (RLHF) and constitutional prompting, operate primarily at the model level and provide only probabilistic safety guarantees. We propose the Policy-Execution-Authorization (PEA) architecture, a "separation-of-powers" design that enforces safety at the system level. PEA decouples intent generation, authorization, and execution into independent, isolated layers connected via cryptographically constrained capability tokens. We present five core contributions: (C1) an Intent Verification Layer (IVL) for ensuring capability-intent consistency; (C2) Intent Lineage Tracking (ILT), which binds all executable intents to the originating user request via cryptographic anchors; (C3) Goal Drift Detection, which rejects semantically divergent intents below a configurable threshold; (C4) an Output Semantic Gate (OSG) that detects implicit coercion using a structured $K \times I \times P$ threat calculus (Knowledge, Influence, Policy); and (C5) a formal verification framework proving that goal integrity is maintained even under adversarial model compromise. By shifting agent alignment from a behavioral property to a structurally enforced system constraint, PEA provides a robust foundation for the governance of autonomous agents. --- ### RaV-IDP: A Reconstruction-as-Validation Framework for Faithful Intelligent Document Processing Authors: Pritesh Jha Published: 2026-04-26 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2604.23644v1 Intelligent document processing pipelines extract structured entities (tables, images, and text) from documents for use in downstream systems such as knowledge bases, retrieval-augmented generation, and analytics. A persistent limitation of existing pipelines is that extraction output is produced without any intrinsic mechanism to verify whether it faithfully represents the source. Model-internal confidence scores measure inference certainty, not correspondence to the document, and extraction errors pass silently into downstream consumers. We present Reconstruction as Validation (RaV-IDP), a document processing pipeline that introduces reconstruction as a first-class architectural component. After each entity is extracted, a dedicated reconstructor renders the extracted representation back into a form comparable to the original document region, and a comparator scores fidelity between the reconstruction and the unmodified source crop. This fidelity score is a grounded, label-free quality signal. When fidelity falls below a per-entity-type threshold, a structured GPT-4.1 vision fallback is triggered and the validation loop repeats. We enforce a bootstrap constraint: the comparator always anchors against the original document region, never against the extraction, preventing the validation from becoming circular. We further propose a per-stage evaluation framework pairing each pipeline component with an appropriate benchmark. The code pipeline is publicly available at https://github.com/pritesh-2711/RaV-IDP for experimentation and use. --- ### VDLF-Net: Variational Feature Fusion for Adaptive and Few-Shot Visual Learning Authors: Jiawei Yan Published: 2026-04-26 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.23641v1 This paper introduces VDLF-Net, which attaches a compact VAE to a multi-scale CNN backbone. Latent vectors and softmax-gate support the backbone feature maps, while $\ell_2$-normalized embeddings from the gated maps contribute toward supervised classification or episodic few-shot prediction. Under standard CIFAR-100 and Mini-ImageNet protocols, VDLF-Net demonstrates an improved performance over ResNet-50 Enhanced, VGG-16, Prototypical Networks, and Matching Networks. Extensive ablations show that removing the fine-resolution scale has the greatest impact on VDLF-Net's performance. At the same time, KL and reconstruction at the chosen $α$ pose a minor performance reduction, demonstrating that performance gains over classical episodic baselines mainly originate from the full VDLF-Net architecture and training strategy. --- ### Discriminator-Guided Adaptive Diffusion for Source-Free Test-Time Adaptation under Image Corruptions Authors: Francesco Olivato, Cigdem Beyan, Vittorio Murino Published: 2026-04-26 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.23636v1 In this work, we study Source-Free Unsupervised Domain Adaptation under corruption-induced domain shifts, where performance degradation is caused by natural image corruptions that go beyond additive noise, including blur, weather effects, and digital artifacts. We propose a diffusion-based, input-level adaptation framework that operates entirely at test time and keeps all source-trained models frozen, explicitly targeting robustness to corrupted target inputs. Our method leverages a source-trained diffusion model as a generative prior and introduces a discriminator-guided adaptive diffusion strategy that dynamically controls the amount of perturbation applied to each test sample. Rather than relying on a fixed diffusion depth, the discriminator determines, on a per-image basis, when sufficient forward diffusion has been applied to suppress corruption-specific artifacts, with each corruption type effectively defining a distinct target domain. This adaptive stopping mechanism applies only the necessary amount of noise to remove domainspecific corruption while preserving class-discriminative structure. The reverse diffusion process then reconstructs a source-aligned image, optionally stabilized through structural guidance, which is classified using a frozen source-trained classifier. We evaluate the proposed approach across a broad spectrum of corruption-induced target domains, covering 15 diverse corruption types, and demonstrate more balanced robustness with competitive or improved performance across non-noise corruptions. Additional analyses reveal how the adaptive diffusion schedule responds to different corruption characteristics, highlighting the practicality, generality, and robustness of the proposed framework. The code is publicly available at https://github.com/fmolivato/dgadiffusion/. --- ### From Rights to Rites: Expectations Management in Smart-Home AI Authors: Varad Vishwarupe, Ivan Flechais, Marina Jirotka, Nigel Shadbolt Published: 2026-04-26 Categories: cs.HC, cs.AI, cs.IR, cs.LG arXiv: https://arxiv.org/abs/2604.23635v1 Domestic voice assistants and smart-home devices are increasingly embedded in everyday routines, yet their ethics are often treated as an afterthought or delegated to compliance teams. To explore how expectations about smart-home AI are constructed and managed, we conducted 33 semi-structured interviews with designers, developers, and researchers from major smart-home platforms (Amazon Alexa, Microsoft Azure IoT, and Google Nest). Using a constructivist grounded theory approach, we develop Expectations Management (EM): a culturally embedded model describing how practitioners shape, calibrate, and repair expectations by balancing organisational rights with culturally situated rites. We show that EM differs from expectation-confirmation theory and trust-calibration by foregrounding moral judgement, situated action, and cross-cultural variation. Our analysis reveals four recurring design tensions: automation vs. autonomy, helpfulness vs. intrusiveness, personalisation vs. predictability, and transparency vs. obscurity and distils them into a five-phase EM Design Playbook that supports moral prudence. We discuss implications for responsible smart-home design and offer guidance for human-centred AI. --- ### Causal Discovery as Dialectical Aggregation: A Quantitative Argumentation Framework Authors: Sheng Wei, Yulin Chen, Beishui Liao Published: 2026-04-26 Categories: cs.AI arXiv: https://arxiv.org/abs/2604.23633v1 Constraint-based causal discovery is brittle in finite-sample regimes because erroneous conditional-independence (CI) decisions can cascade into substantial structural errors. We propose Quantitative Argumentation for Causal Discovery (QACD), a semantics-driven framework that represents CI outcomes as graded, defeasible arguments rather than irreversible constraints. QACD maps statistical test outcomes to argument strengths and aggregates conflicting evidence through connectivity-mediated witness propagation, producing a fixed-point acceptability labeling over candidate adjacencies. Experiments on standard benchmark Bayesian networks suggest that QACD improves structural coherence and interventional reliability in several noisy or inconsistent CI regimes, while remaining competitive with classical constraint-based, hybrid, and prior argumentation-based baselines. --- ### Hallo-Live: Real-Time Streaming Joint Audio-Video Avatar Generation with Asynchronous Dual-Stream and Human-Centric Preference Distillation Authors: Chunyu Li, Jiaye Li, Ruiqiao Mei, Haoyuan Xia, Hao Zhu, Jingdong Wang, Siyu Zhu Published: 2026-04-26 Categories: cs.CV, cs.MM, cs.SD arXiv: https://arxiv.org/abs/2604.23632v1 Real-time text-driven joint audio-video avatar generation requires jointly synthesizing portrait video and speech with high fidelity and precise synchronization, yet existing audio-visual diffusion models remain too slow for interactive use and often degrade noticeably after aggressive acceleration. We present Hallo-Live, a streaming framework for joint audio-visual avatar generation that combines asynchronous dual-stream diffusion with human-centric preference-guided distillation. To reduce articulation lag in causal generation, we introduce Future-Expanding Attention, which allows each video block to access synchronous audio together with a short horizon of future phonetic cues. To mitigate the quality loss of few-step distillation, we further propose Human-Centric Preference-Guided DMD (HP-DMD), which reweights training samples using rewards from visual fidelity, speech naturalness, and audio-visual synchronization. On two NVIDIA H200 GPUs, Hallo-Live runs at 20.38 FPS with 0.94 seconds latency, yielding 16.0x higher throughput and 99.3x lower latency than the teacher model Ovi. Despite this speedup, it retains strong generation quality, reaching comparable VideoAlign overall score and Sync Confidence score while outperforming other accelerated baselines in the overall quality-efficiency trade-off. Qualitative results further show robust generalization across photorealistic, multi-speaker, and stylized scenarios. To the best of our knowledge, Hallo-Live is the first framework to combine streaming dual-stream diffusion with preference-guided distillation for real-time, text-driven audio-visual generation. --- ### Characterizing Admissible Objective Functions for Hierarchical Clustering Authors: Ryuki Tsukuba, Kazutoshi Ando Published: 2026-04-26 Categories: cs.DS, cs.LG arXiv: https://arxiv.org/abs/2604.23628v3 Hierarchical clustering is a fundamental task in data analysis, but classical methods have long lacked a principled objective function. Dasgupta (STOC 2016) took an important step toward addressing this gap by proposing a well-motivated objective function for cluster trees. Cohen-Addad et al. (J. ACM 2019) subsequently introduced the notion of admissibility: an objective function is admissible if, whenever the input similarity matrix admits generating trees, its minimizers are precisely those generating trees. They also gave a necessary and sufficient condition for admissibility within a family of objective functions based on aggregate intercluster similarity. We refer to this family as sum-type objective functions. However, apart from Dasgupta's original objective function, no explicit admissible objective functions in this family were provided. In this paper, we study admissible objective functions for hierarchical clustering in two directions. For sum-type objective functions, we give a complete characterization when the scaling function is a symmetric polynomial of degree at most two, and we derive sufficient conditions for degree-three polynomials. We also show that the recursive sparsest cut algorithm achieves an O$(φ)$-approximation ratio for the admissible objective functions covered by our characterization, where $φ$ is the approximation factor of the sparsest cut subroutine. We then introduce max-type objective functions, where cluster interaction is measured by maximum, rather than aggregate, intercluster similarity. For this class, we characterize which objective functions are admissible for arbitrary symmetric scaling functions and give a complete characterization when the scaling function is a symmetric polynomial of degree at most two. --- ### Neural Grammatical Error Correction for Romanian Authors: Teodor-Mihai Cotet, Stefan Ruseti, Mihai Dascalu Published: 2026-04-26 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2604.23627v1 Resources for Grammatical Error Correction (GEC) in non-English languages are scarce, while available spellcheckers in these languages are mostly limited to simple corrections and rules. In this paper we introduce a first GEC corpus for Romanian consisting of 10k pairs of sentences. In addition, the German version of ERRANT (ERRor ANnotation Toolkit) scorer was adapted for Romanian to analyze this corpus and extract edits needed for evaluation. Multiple neural models were experimented, together with pretraining strategies, which proved effective for GEC in low-resource settings. Our baseline consists of a small Transformer model trained only on the GEC dataset (F0.5 of 44.38), whereas the best performing model is produced by pretraining a larger Transformer model on artificially generated data, followed by finetuning on the actual corpus (F0.5 of 53.76). The proposed method for generating additional training examples is easily extensible and can be applied to any language, as it requires only a POS tagger --- ### GraphPlanner: Graph Memory-Augmented Agentic Routing for Multi-Agent LLMs Authors: Tao Feng, Haozhen Zhang, Zijie Lei, Peixuan Han, Jiaxuan You Published: 2026-04-26 Categories: cs.CL arXiv: https://arxiv.org/abs/2604.23626v1 LLM routing has achieved promising results in integrating the strengths of diverse models while balancing efficiency and performance. However, to support more realistic and challenging applications, routing must extend into agentic LLM settings, where task planning, multi-round cooperation among heterogeneous agents, and memory utilization are indispensable. To address this gap, we propose GraphPlanner, a heterogeneous graph memory-augmented agentic router for multi-agent LLMs that generates routing workflows for each query and supports both inductive and transductive inference. GraphPlanner formulates workflow generation as a Markov Decision Process (MDP), where at each step it selects both the LLM backbone and the agent role, including Planner, Executor, and Summarizer. By leveraging a heterogeneous graph, denoted as GARNet, to capture interaction memories among queries, agents, and responses, GraphPlanner integrates historical memory and workflow memory into richer state representations. The entire pipeline is optimized with reinforcement learning, jointly improving task-specific performance and computational efficiency. We evaluate GraphPlanner across 14 diverse LLM tasks and demonstrate that: (1) GraphPlanner outperforms strong single-round and multi-round routers, improving accuracy by up to 9.3% while reducing GPU cost from 186.26 GiB to 1.04 GiB; (2) GraphPlanner generalizes robustly to unseen tasks and LLMs, exhibiting strong zero-shot capabilities; and (3) GraphPlanner effectively leverages historical memories, supporting both inductive and transductive inference for more adaptive routing. Our code for GraphPlanner is released at https://github.com/ulab-uiuc/GraphPlanner. --- ### Tandem: Riding Together with Large and Small Language Models for Efficient Reasoning Authors: Zichuan Fu, Xian Wu, Guojing Li, Yejing Wang, Yijun Chen, Zihao Zhao, Yixuan Luo, Hanyu Yan, Yefeng Zheng, Xiangyu Zhao Published: 2026-04-26 Categories: cs.AI arXiv: https://arxiv.org/abs/2604.23623v1 Recent advancements in large language models (LLMs) have catalyzed the rise of reasoning-intensive inference paradigms, where models perform explicit step-by-step reasoning before generating final answers. While such approaches improve answer quality and interpretability, they incur substantial computational overhead due to the prolonged generation sequences. In this paper, we propose Tandem, a novel collaborative framework that synergizes large and small language models (LLMs and SLMs) to achieve high-quality reasoning with significantly reduced computational cost. Specifically, the LLM serves as a strategic coordinator, efficiently generating a compact set of critical reasoning insights. These insights are then used to guide a smaller, more efficient SLM in executing the full reasoning process and delivering the final response. To balance efficiency and reliability, Tandem introduces a cost-aware termination mechanism that adaptively determines when sufficient reasoning guidance has been accumulated, enabling early stopping of the LLM's generation. Experiments on mathematical reasoning and code generation benchmarks demonstrate that Tandem reduces computational costs by approximately 40% compared to standalone LLM reasoning, while achieving superior or competitive performance. Furthermore, the sufficiency classifier trained on one domain transfers effectively to others without retraining. The code is available at: https://github.com/Applied-Machine-Learning-Lab/ACL2026_Tandem. --- ### A Synergistic CNN-Transformer Network with Pooling Attention Fusion for Hyperspectral Image Classification Authors: Peng Chen, Wenxuan He, Feng Qian, Guangyao Shi, Jingwen Yan Published: 2026-04-26 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.23622v1 In the hyperspectral image (HSI) classification task, each pixel is categorized into a specific land-cover category or material. Convolutional neural networks (CNNs) and transformers have been widely used to extract local and non-local features in HSI classification. Recent works have utilized a multi-scale vision transformer (ViT) to enhance spectral feature capture and yield promising results. However, most existing methods still face challenges in the effective joint use of spatial-spectral information and in preserving information across layers during the propagation process. To address these issues, we propose a synergistic CNN-Transformer network with pooling attention fusion for HSI classification, which collaboratively utilizes CNNs and ViT to process spatial and spectral features separately. Specifically, we propose a Twin-Branch Feature Extraction (TBFE) module, which employs 3D and 2D convolution in parallel to comprehensively extract spectral and spatial features from HSI. A hybrid pooling attention (HPA) module is designed to aggregate spatial attention. Moreover, a cascade transformer encoder is employed for global spectral feature extraction, and a simple yet efficient cross-layer feature fusion (CFF) module is designed to reduce the loss of crucial information in the previous network layers. Extensive experiments are conducted on several representative datasets to demonstrate the superior performance of our proposed method compared to the state-of-the-art works. Code is available at https://github.com/chenpeng052/SCT-Net.git. --- ### Applications of the Transformer Architecture in AI-Assisted English Reading Comprehension Authors: Ping Li Published: 2026-04-26 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2604.23615v1 This paper studies interpretable and fair artificial intelligence architectures for understanding English reading. Introduced transformer-based models, integrating advanced attention mechanisms and gradient-based feature attribution. The model's lack of interpretability, reduction of algorithmic bias, and unreliable performance in learning environments are the current issues faced in natural language teaching. A unified technical pipeline has been constructed, including adversarial bias correction methods, token-level attribution analysis, and multi-head attention heatmap visualization. Experimental validation was conducted using a large-scale labeled English reading comprehension dataset, and the data partitioning scheme and parameter optimization procedures have been determined. The method significantly outperforms the state-of-the-art models for this task in terms of accuracy and macro-average F1 score; in some aspects, it even surpasses or closely matches the results of human evaluations. In multi-week user experiments, the explainable transformer improved teachers' trust and operability in feedback-based assessments within the scoring system. The proposed method aims to ensure high prediction accuracy and fairness for different learners. This indicates that it is a real-world educational application based on artificial intelligence with a focus on interpretation. Improve the user experience in AI-assisted reading comprehension systems, counteract biases, and enhance the details explained by transformers. --- ### Comparative Study of Weighted and Coupled Second- and Fourth-Order PDEs for Image Despeckling in Grayscale, Color, SAR, and Ultrasound Authors: Manish Kumar, Rajendra K. Ray Published: 2026-04-26 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.23612v1 Partial Differential Equation (PDE)-based approaches have gained significant attention in image despeckling due to their strong capability to preserve structural details while suppressing noise. However, conventional second-order PDE models tend to generate blocky artifacts, whereas higher-order models often introduce speckle patterns. To resolve it, this paper proposes and comparatively analyzes two advanced PDE-based frameworks designed for speckle noise suppression while preserving the fine edges. The first model introduces a novel weighted formulation that combines second and fourth-order PDEs through a weighting parameter. The second-order diffusion coefficient employs grayscale and gradient-based indicators, while the fourth-order term is guided solely by a Laplacian-based indicator. The second model constructs a coupled PDE framework, where independent fourth and second-order components are explicitly solved in an iterative manner. In this coupled structure, each diffusion coefficient is defined separately to enhance adaptability in varying image regions. Both models are implemented using the explicit finite difference method. The proposed techniques are extensively evaluated on a variety of datasets, including standard grayscale, color, Synthetic Aperture Radar (SAR), and ultrasound images. Comparative experiments with the existing Telegraph Diffusion Model (TDM) and Fourth-Order Telegraph Diffusion Model (TDFM) demonstrate the superiority of the proposed approaches in reducing speckle noise while effectively preserving fine image structures and edges. Quantitative evaluations using PSNR, SSIM and Speckle Index metrics confirm that the proposed models produce higher image quality and enhanced visual perception. Overall, the presented PDE-based formulations provide a reliable and efficient framework for image despeckling in both natural and medical imaging. --- ### Hamiltonian Graph Inference Networks: Joint structure discovery and dynamics prediction for lattice Hamiltonian systems from trajectory data Authors: Ru Geng, Panayotis Kevrekidis, Yixian Gao, Hong-Kun Zhang, Jian Zu Published: 2026-04-26 Categories: cs.LG, math-ph arXiv: https://arxiv.org/abs/2604.23606v1 Lattice Hamiltonian systems underpin models across condensed matter, nonlinear optics, and biophysics, yet learning their dynamics from data is obstructed by two unknowns: the interaction topology and whether node dynamics are homogeneous. Existing graph-based approaches either assume the graph is given or, as in $α$-separable graph Hamiltonian network, infer it only for separable Hamiltonians with homogeneous node dynamics. We introduce the Hamiltonian Graph Inference Network (HGIN), which jointly recovers the interaction graph and predicts long-time trajectories from state data alone, for both separable and non-separable Hamiltonians and under heterogeneous node dynamics. HGIN couples a structure-learning module -- a learnable weighted adjacency matrix trained under a Hamilton's-equations loss -- with a trajectory-prediction module that partitions edges into physically distinct subgraphs via $k$-means clustering, assigning each subgraph its own encoder and thereby breaking the parameter-sharing bottleneck of conventional GNNs. On three benchmarks -- a Klein--Gordon lattice with long-range interactions and two discrete nonlinear Schrödinger lattices (homogeneous and heterogeneous) -- HGIN reduces long-time energy prediction error and trajectory prediction error by six to thirteen orders of magnitude relative to baselines. A symmetry argument on the Hamiltonian loss further shows that the learned weights encode the parity of the underlying pair potential, yielding an interpretable readout of the system's interaction structure. --- ### Thinking Like a Clinician: A Cognitive AI Agent for Clinical Diagnosis via Panoramic Profiling and Adversarial Debate Authors: Zhiqi Lv, Duofan Tu, Jun Li, Mingyue Zhao, Heqin Zhu, Wenliang Li, Shaohua Kevin Zhou Published: 2026-04-26 Categories: cs.AI arXiv: https://arxiv.org/abs/2604.23605v1 The application of large language models (LLMs) in clinical decision support faces significant challenges of "tunnel vision" and diagnostic hallucinations present in their processing unstructured electronic health records (EHRs). To address these challenges, we propose a novel chain-based clinical reasoning framework, called DxChain, which transforms the diagnostic workflow into an iterative process by mirroring a clinician's cognitive trajectory that consists of "Memory Anchoring", "Navigation" and "Verification" phases. DxChain introduces three key methodological innovations to elicit the potential of LLM: (i) a Profile-Then-Plan paradigm to mitigate cold-start hallucinations by establishing a panoramic patient baseline, (ii) a Medical Tree-of-Thoughts (Med-ToT) algorithm for strategic look ahead planning and resource aware navigation, and (iii) a Dialectical Diagnostic Verification procedure utilizing "Angel-Devil" adversarial debates to resolve complex evidence conflicts. Evaluated on two real world benchmarks, MIMIC-IV-Ext Cardiac Disease and MIMIC-IV-Ext CDM, DxChain achieves state-of-the-art performances in both diagnostic accuracy and logical consistency, offering a modular and reliable architecture for next-generation clinical AI. The code is at https://anonymous.4open.science/r/Dx-Chain. --- ### Learning to Identify Out-of-Distribution Objects for 3D LiDAR Anomaly Segmentation Authors: Simone Mosco, Daniel Fusaro, Alberto Pretto Published: 2026-04-26 Categories: cs.CV, cs.RO arXiv: https://arxiv.org/abs/2604.23604v1 Understanding the surrounding environment is fundamental in autonomous driving and robotic perception. Distinguishing between known classes and previously unseen objects is crucial in real-world environments, as done in Anomaly Segmentation. However, research in the 3D field remains limited, with most existing approaches applying post-processing techniques from 2D vision. To cover this lack, we propose a new efficient approach that directly operates in the feature space, modeling the feature distribution of inlier classes to constrain anomalous samples. Moreover, the only publicly available 3D LiDAR anomaly segmentation dataset contains simple scenarios, with few anomaly instances, and exhibits a severe domain gap due to its sensor resolution. To bridge this gap, we introduce a set of mixed real-synthetic datasets for 3D LiDAR anomaly segmentation, built upon established semantic segmentation benchmarks, with multiple out-of-distribution objects and diverse, complex environments. Extensive experiments demonstrate that our approach achieves state-of-the-art and competitive results on the existing real-world dataset and the newly introduced mixed datasets, respectively, validating the effectiveness of our method and the utility of the proposed datasets. Code and datasets are available at https://simom0.github.io/lido-page/. --- ### TimingLLM: A Two-Stage Retrieval-Augmented Framework for Pre-Synthesis Timing Prediction from Verilog Authors: Armin Abdollahi, Negin Ashrafi, Mehdi Kamal, Massoud Pedram Published: 2026-04-26 Categories: cs.AR, cs.LG arXiv: https://arxiv.org/abs/2604.23602v1 Early, tool-free prediction of post-synthesis timing remains a key obstacle to rapid RTL iteration. We introduce TimingLLM, a two-stage retrieval-augmented LLM pipeline that estimates worst negative slack (WNS) and total negative slack (TNS) directly from Verilog. Stage 1 is a fine-tuned LLM that acts as a compact post-synthesis timing oracle, producing path-level arrivals/required times that are summarized into lightweight structural-timing cues (e.g., bag-of-gates counts, critical-path depth, gate-type patterns). Stage 2 is an LLM-based regressor that predicts WNS/TNS and applies a learned diagonal steering vector at the last transformer block, computed from the k nearest timing-labeled modules in a disjoint retrieval bank. On VerilogEval, TimingLLM attains R_WNS = 0.91 (MAPE 12%) and R_TNS=0.97 (MAPE 16%) while running 1.3-1.6 times faster than prior methods. Training uses a new 60k-module Verilog corpus with synthesis reports, which we will release. After training once, TimingLLM can be adapted to new technology libraries and PVT corners by refitting only a small regression head on 1000 labeled modules per setting, consistently outperforming state-of-the-art baselines. --- ### The Limits of Artificial Companionship Authors: Mauricio Figueroa Published: 2026-04-26 Categories: cs.CY, cs.CL, cs.HC arXiv: https://arxiv.org/abs/2604.23601v1 This Article argues that conversations with companion chatbot should be subject to a clear structural distinction between commercial and non-commercial contexts. The insertion of undisclosed promotional content into affective or relational exchanges should be prohibited, as it collapses the boundary between market transaction and communicative intimacy in ways that erode user autonomy and conversational context. The Article begins by theorizing digital companionship as a sociotechnical form that reconfigures intimacy, dependence and relational vulnerability. It then introduces the potential economic harms derived from conversational advertising. The Article ultimately argues for a firm legal and social distinction between commercial and non-commercial conversational contexts as a precondition for the responsible stabilization of these technologies within social life. --- ### Personality Shapes Gender Bias in Persona-Conditioned LLM Narratives Across English and Hindi: An Empirical Investigation Authors: Tanay Kumar, Shreya Gautam, Aman Chadha, Vinija Jain, Francesco Pierri Published: 2026-04-26 Categories: cs.CL arXiv: https://arxiv.org/abs/2604.23600v2 Large Language Models (LLMs) are increasingly deployed in persona-driven applications such as education, customer service, and social platforms, where models are prompted to adopt specific personas when interacting with users. While persona conditioning can improve user experience and engagement, it also raises concerns about how personality cues may interact with gender biases and stereotypes. In this work, we present a controlled study of persona-conditioned story generation in English and Hindi, where each story portrays a working professional in India producing context-specific artifacts (e.g., lesson plans, reports, letters) under systematically varied persona gender, occupational role, and personality traits from the HEXACO and Dark Triad frameworks. Across 23,400 generated stories from six state-of-the-art LLMs, we find that personality traits are significantly associated with both the magnitude and direction of gender bias. In particular, Dark Triad personality traits are consistently associated with higher gender-stereotypical representations compared to socially desirable HEXACO traits, though these associations vary across models and languages. Our findings demonstrate that gender bias in LLMs is not static but context-dependent. This suggests that persona-conditioned systems used in real-world applications may introduce uneven representational harms, reinforcing gender stereotypes in generated educational, professional, or social content. --- ### Partition-of-Unity Gaussian Kolmogorov-Arnold Networks Authors: Amir Noorizadegan Published: 2026-04-26 Categories: cs.CE, cs.AI, math.AP arXiv: https://arxiv.org/abs/2604.23599v2 Gaussian basis functions provide an efficient and flexible alternative to spline activations in KANs. In this work, we introduce the partition-of-unity Gaussian KAN (PU-GKAN), a Shepard-type normalized Gaussian KAN in which the Gaussian basis values on each edge are divided by their local sum over fixed centers. This produces a partition-of-unity feature map with trainable coefficients, while preserving the standard edge-based KAN structure. The normalized construction gives exact constant reproduction at the edge level and admits an explicit finite-feature kernel interpretation. We formulate both the standard Gaussian KAN (GKAN) and PU-GKAN from a finite-feature and additive-kernel viewpoint, making the induced layer kernels and empirical feature matrices explicit. Using the first-layer feature matrix as the reference object, we adopt a practical scale-selection interval for \(ε\), with the lower endpoint determined by adjacent-center overlap and the upper endpoint determined by a conservative conditioning threshold. Numerical experiments show that PU-GKAN reduces sensitivity to \(ε\), improves validation accuracy for most smooth and moderately non-smooth targets, and gives more stable training behavior. The benefit persists across sample-size and center-number sweeps, higher-dimensional architectures, Matérn RBF bases, and physics-informed examples involving Helmholtz and wave equations. These results indicate that Shepard-type partition-of-unity normalization is a simple and effective stabilization mechanism for RBF-based KANs. --- ### When AI reviews science: Can we trust the referee? Authors: Jialiang Wang, Yuchen Liu, Hang Xu, Kaichun Hu, Shimin Di, Wangze Ni, Linan Yue, Min-Ling Zhang, Kui Ren, Lei Chen Published: 2026-04-26 Categories: cs.AI arXiv: https://arxiv.org/abs/2604.23593v1 The volume of scientific submissions continues to climb, outpacing the capacity of qualified human referees and stretching editorial timelines. At the same time, modern large language models (LLMs) offer impressive capabilities in summarization, fact checking, and literature triage, making the integration of AI into peer review increasingly attractive -- and, in practice, unavoidable. Yet early deployments and informal adoption have exposed acute failure modes. Recent incidents have revealed that hidden prompt injections embedded in manuscripts can steer LLM-generated reviews toward unjustifiably positive judgments. Complementary studies have also demonstrated brittleness to adversarial phrasing, authority and length biases, and hallucinated claims. These episodes raise a central question for scholarly communication: when AI reviews science, can we trust the AI referee? This paper provides a security- and reliability-centered analysis of AI peer review. We map attacks across the review lifecycle -- training and data retrieval, desk review, deep review, rebuttal, and system-level. We instantiate this taxonomy with four treatment-control probes on a stratified set of ICLR 2025 submissions, using two advanced LLM-based referees to isolate the causal effects of prestige framing, assertion strength, rebuttal sycophancy, and contextual poisoning on review scores. Together, this taxonomy and experimental audit provide an evidence-based baseline for assessing and tracking the reliability of AI peer review and highlight concrete failure points to guide targeted, testable mitigations. --- ### XITE: Cross-lingual Interpolation for Transfer using Embeddings Authors: Barah Fazili, Preethi Jyothi Published: 2026-04-26 Categories: cs.CL arXiv: https://arxiv.org/abs/2604.23589v1 Facilitating cross-lingual transfer in multilingual language models remains a critical challenge. Towards this goal, we propose an embedding-based data augmentation technique called XITE. We start with unlabeled text from a low-resource target language, identify an English counterpart in a task-specific training corpus using embedding-based similarities and adopt its label. Next, we perform a simple interpolation of the source and target embeddings to create synthetic data for task-specific fine-tuning. Projecting the target text into a language-rich subspace using linear discriminant analysis (LDA), prior to interpolation, further boosts performance. Our cross-lingual embedding-based augmentation technique XITE yields significant improvements of up to 35.91% for sentiment analysis and up to 81.16% for natural language inference, using XLM-R, for a diverse set of target languages including Korean, Arabic, Urdu and Hindi. Apart from boosting cross-lingual transfer, adaptation using XITE also safeguards against forgetting and maintains task performance on the high-resource language. --- ### FinGround: Detecting and Grounding Financial Hallucinations via Atomic Claim Verification Authors: Dongxin Guo, Jikun Wu, Siu Ming Yiu Published: 2026-04-26 Categories: cs.AI, cs.CL, cs.IR arXiv: https://arxiv.org/abs/2604.23588v1 Financial AI systems must produce answers grounded in specific regulatory filings, yet current LLMs fabricate metrics, invent citations, and miscalculate derived quantities. These errors carry direct regulatory consequences as the EU AI Act's high-risk enforcement deadline approaches (August 2026). Existing hallucination detectors treat all claims uniformly, missing 43% of computational errors that require arithmetic re-verification against structured tables. We present FinGround, a three-stage verify-then-ground pipeline for financial document QA. Stage 1 performs finance-aware hybrid retrieval over text and tables. Stage 2 decomposes answers into atomic claims classified by a six-type financial taxonomy and verified with type-routed strategies including formula reconstruction. Stage 3 rewrites unsupported claims with paragraph- and table-cell-level citations. To cleanly isolate verification value from retrieval quality, we propose retrieval-equalized evaluation as standard methodology for RAG verification research: when all systems receive identical retrieval, FinGround still reduces hallucination rates by 68% over the strongest baseline ($p < 0.01$). The full pipeline achieves a 78% reduction relative to GPT-4o. An 8B distilled detector retains 91.4% F1 at 18x lower per-claim latency, enabling $0.003/query deployment, supported by qualitative signals from a four-week analyst pilot. --- ### Talker-T2AV: Joint Talking Audio-Video Generation with Autoregressive Diffusion Modeling Authors: Zhen Ye, Xu Tan, Aoxiong Yin, Hongzhan Lin, Guangyan Zhang, Peiwen Sun, Yiming Li, Chi-Min Chan, Wei Ye, Shikun Zhang, Wei Xue Published: 2026-04-26 Categories: cs.CV, cs.CL, cs.MM, cs.SD, eess.AS arXiv: https://arxiv.org/abs/2604.23586v2 Joint audio-video generation models have shown that unified generation yields stronger cross-modal coherence than cascaded approaches. However, existing models couple modalities throughout denoising via pervasive attention, treating high-level semantics and low-level details in a fully entangled manner. This is suboptimal for talking head synthesis: while audio and facial motion are semantically correlated, their low-level realizations (acoustic signals and visual textures) follow distinct rendering processes. Enforcing joint modeling across all levels causes unnecessary entanglement and reduces efficiency. We propose Talker-T2AV, an autoregressive diffusion framework where high-level cross-modal modeling occurs in a shared backbone, while low-level refinement uses modality-specific decoders. A shared autoregressive language model jointly reasons over audio and video in a unified patch-level token space. Two lightweight diffusion transformer heads decode the hidden states into frame-level audio and video latents. Experiments on talking portrait benchmarks show Talker-T2AV outperforms dual-branch baselines in lip-sync accuracy, video quality, and audio quality, achieving stronger cross-modal consistency than cascaded pipelines. --- ### ComplianceNLP: Knowledge-Graph-Augmented RAG for Multi-Framework Regulatory Gap Detection Authors: Dongxin Guo, Jikun Wu, Siu Ming Yiu Published: 2026-04-26 Categories: cs.CL, cs.IR, cs.LG arXiv: https://arxiv.org/abs/2604.23585v1 Financial institutions must track over 60,000 regulatory events annually, overwhelming manual compliance teams; the industry has paid over USD 300 billion in fines and settlements since the 2008 financial crisis. We present ComplianceNLP, an end-to-end system that automatically monitors regulatory changes, extracts structured obligations, and identifies compliance gaps against institutional policies. The system integrates three components: (1) a knowledge-graph-augmented RAG pipeline grounding generations in a regulatory knowledge graph of 12,847 provisions across SEC, MiFID II, and Basel III; (2) multi-task obligation extraction combining NER, deontic classification, and cross-reference resolution over a shared LEGAL-BERT encoder; and (3) compliance gap analysis that maps obligations to internal policies with severity-aware scoring. On our benchmark, ComplianceNLP achieves 87.7 F1 on gap detection, outperforming GPT-4o+RAG by +3.5 F1, with 94.2% grounding accuracy ($r=0.83$ vs. human judgments) and 83.4 F1 under realistic end-to-end error propagation. Ablations show that knowledge-graph re-ranking contributes the largest marginal gain (+4.6 F1), confirming that structural regulatory knowledge is critical for cross-reference-heavy tasks. Domain-specific knowledge distillation (70B $\to$ 8B) combined with Medusa speculative decoding yields $2.8\times$ inference speedup; regulatory text's low entropy ($H=2.31$ bits vs. $3.87$ general text) produces 91.3% draft-token acceptance rates. In four months of parallel-run deployment processing 9,847 updates at a financial institution, the system achieved 96.0% estimated recall and 90.7% precision, with a $3.1\times$ sustained analyst efficiency gain. We report deployment lessons on trust calibration, GRC integration, and distributional shift monitoring for regulated-domain NLP. ---