# Research Papers — 2026-04 · bundle page 121 of 233 > Full-text markdown of papers #6001–6050 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/121 [← Previous bundle](https://aipod.dev/papers/archive/2026-04/page/120.md) [Next bundle →](https://aipod.dev/papers/archive/2026-04/page/122.md) ### Improving Molecular Force Fields with Minimal Temporal Information Authors: Ali Mollahosseini, Mohammed Haroon Dupty, Wee Sun Lee Published: 2026-04-14 Categories: physics.chem-ph, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2604.19806v1 Accurate prediction of energy and forces for 3D molecular systems is one of fundamental challenges at the core of AI for Science applications. Many powerful and data-efficient neural networks predict molecular energies and forces from single atomic configurations. However, one crucial aspect of the data generation process is rarely considered while learning these models i.e. Molecular Dynamics (MD) simulation. MD simulations generate time-ordered trajectories of atomic positions that fluctuate in energy and explore regions of the potential energy surface (e.g., under standard NVE/NVT ensembles), rather than being constructed to steadily lower the potential energy toward a minimum as in geometry relaxations. This work explores a novel way to leverage MD data, when available, to improve the performance of such predictors. We introduce a novel training strategy called FRAMES, that use an auxiliary loss function for exploiting the temporal relationships within MD trajectories. Counter-intuitively, on two atomistic benchmarks and a synthetic system we observe that minimal temporal information, captured by pairs of just two consecutive frames, is often sufficient to obtain the best performance, while adding longer trajectory sequences can introduce redundancy and degrade performance. On the widely used MD17 and ISO17 benchmarks, FRAMES significantly outperforms its Equiformer baseline, achieving highly competitive results in both energy and force accuracy. Our work not only presents a novel training strategy which improves the accuracy of the model, but also provides evidence that for distilling physical priors of atomic systems, more temporal data is not always better. --- ### Agent-GWO: Collaborative Agents for Dynamic Prompt Optimization in Large Language Models Authors: Xudong Wang, Chaoning Zhang, Chenghao Li, Shuxu Chen, Qigan Sun, Jiaquan Zhang, Fachrina Dewi Puspitasari, Tae-Ho Kim, Jiwei Wei, Malu Zhang, Guoqing Wang, Yang Yang et al. Published: 2026-04-14 Categories: cs.NE, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2604.18612v1 Large Language Models (LLMs) have demonstrated strong capabilities in complex reasoning tasks, while recent prompting strategies such as Chain-of-Thought (CoT) have further elevated their performance in handling complex logical problems. Despite these advances, high-quality reasoning remains heavily reliant on manual static prompts and is sensitive to decoding configurations and task distributions, leading to performance fluctuations and limited transferability. Existing automatic prompt optimization methods typically adopt single-agent local search, failing to simultaneously optimize prompts and decoding hyperparameters within a unified framework to achieve stable global improvements. To address this limitation, we propose Agent-GWO, a dynamic prompt optimization framework for complex reasoning. Specifically, we unify prompt templates and decoding hyperparameters as inheritable agent configurations. By leveraging the leader-follower mechanism of the Grey Wolf Optimizer (GWO), we automatically select three leader agents ($α$, $β$, and $δ$) to guide the collaborative updates of the remaining agents, enabling iterative convergence toward robust optimal reasoning configurations that can be seamlessly integrated for inference. Extensive experiments on multiple mathematical and hybrid reasoning benchmarks across diverse LLM backbones show that Agent-GWO consistently improves accuracy and stability over existing prompt optimization methods. The code will be released publicly. --- ### Medical thinking with multiple images Authors: Zonghai Yao, Benlu Wang, Yifan Zhang, Junda Wang, Iris Xia, Zhipeng Tang, Shuo Han, Feiyun Ouyang, Zhichao Yang, Arman Cohan, Hong Yu Published: 2026-04-14 Categories: cs.CV, cs.CL arXiv: https://arxiv.org/abs/2604.16506v2 Large language models perform well on many medical QA benchmarks, but real clinical reasoning often requires integrating evidence across multiple images rather than interpreting a single view. We introduce MedThinkVQA, an expert-annotated benchmark for thinking with multiple images, where models must interpret each image, combine cross-view evidence, and answer diagnostic questions with intermediate supervision and step-level evaluation. The dataset contains 8,067 cases, including 720 test cases, with an average of 6.62 images per case, substantially denser than prior work, whose expert-level benchmarks use at most 1.43 images per case. On the test set, the best closed-source models, Claude-4.6-Opus, Gemini-3-Pro, and GPT-5.2-xhigh, reach only 57.2%, 55.3%, and 54.9% accuracy, while GPT-5-mini and GPT-5-nano reach 39.7% and 30.8%. Strong open-source models lag behind, led by Qwen3.5-397B-A17B at 52.2% and Qwen3.5-27B at 50.6%. Further analysis identifies grounded multi-image reasoning as the main bottleneck: models often fail to extract, align, and compose evidence across views before higher-level inference can help. Providing expert single-image cues and cross-image summaries improves performance, whereas replacing them with self-generated intermediates reduces accuracy. Step-level analysis shows that over 70% of errors arise from image reading and cross-view integration. Scaling results further show that additional inference-time computation helps only when visual grounding is already reliable; when early evidence extraction is weak, longer reasoning yields limited or unstable gains and can amplify misread cues. These results suggest that the key challenge is not reasoning length alone, but reliable mechanisms for grounding, aligning, and composing distributed evidence across real-world multimodal clinical inputs. --- ### Predicting Blastocyst Formation in IVF: Integrating DINOv2 and Attention-Based LSTM on Time-Lapse Embryo Images Authors: Zahra Asghari Varzaneh, Niclas Wölner-Hanssen, Reza Khoshkangini, Thomas Ebner, Magnus Johnsson Published: 2026-04-14 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2604.16505v1 The selection of the optimal embryo for transfer is a critical yet challenging step in in vitro fertilization (IVF), primarily due to its reliance on the manual inspection of extensive time-lapse imaging data. A key obstacle in this process is predicting blastocyst formation from the limited number of daily images available. Many clinics also lack complete time-lapse systems, so full videos are often unavailable. In this study, we aimed to predict which embryos will develop into blastocysts using limited daily images from time-lapse recordings. We propose a novel hybrid model that combines DINOv2, a transformer-based vision model, with an enhanced long short-term memory (LSTM) network featuring a multi-head attention layer. DINOv2 extracts meaningful features from embryo images, and the LSTM model then uses these features to analyze embryo development over time and generate final predictions. We tested our model on a real dataset of 704 embryo videos. The model achieved 96.4% accuracy, surpassing existing methods. It also performs well with missing frames, making it valuable for many IVF laboratories with limited imaging systems. Our approach can assist embryologists in selecting better embryos more efficiently and with greater confidence. --- ### From Handwriting to Structured Data: Benchmarking AI Digitisation of Handwritten Forms Authors: Nicholas Pather, Joshua Fouché, Sitwala Mundia, Karl-Günter Technau, Thokozile Malaba, Alex Welte, Ushma Mehta, Bruce A. Bassett Published: 2026-04-14 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2604.16504v1 Manual digitisation of structured handwritten documents is slow and costly. We benchmark 17 leading frontier multi-modal large language models and open-source models against a very challenging real-world medical form that mixes dates; structured, printed text; hand-written responses and significant variability challenges. None of the smaller or older models perform well but the latest Google and OpenAI models reach accuracies around $85\%$ with weighted F1 scores $\simeq 90\%$ across the discrete or predefined fields despite the very challenging nature of the responses. Clear task specific strengths emerge: GPT 5.4 excels in noisy date extraction as well as reliability with the lowest hallucination rate ($6\%$). Claude Sonnet 4.6 had the best average performance across formatted fields (dates and numerical values), while Gemini 3.1 delivered the best overall performance, with the lowest free text error rates (WER = $0.50$ and CER = $0.31$) and the strongest results across discrete classification metrics. We further show that prompt optimisation dramatically improves macro precision, recall and F1 by over $60\%$, but has little impact on weighted metrics (only $\sim2-5\%$ improvement). These results provide evidence that the rapid improvements of multimodal large language models offer a compelling pathway toward fully automated digitisation of complex handwritten workflows that is particularly relevant in low- and middle-income countries. --- ### Motif-Video 2B: Technical Report Authors: Junghwan Lim, Wai Ting Cheung, Minsu Ha, Beomgyu Kim, Taewhan Kim, Haesol Lee, Dongpin Oh, Jeesoo Lee, Taehyun Kim, Minjae Kim, Sungmin Lee, Hyeyeon Cho et al. Published: 2026-04-14 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2604.16503v2 Training strong video generation models usually requires massive datasets, large parameter counts, and substantial compute. In this work, we ask whether strong text-to-video quality is possible at a much smaller budget: fewer than 10M clips and less than 100,000 H200 GPU hours. Our core claim is that part of the answer lies in how model capacity is organized, not only in how much of it is used. In video generation, prompt alignment, temporal consistency, and fine-detail recovery can interfere with one another when they are handled through the same pathway. Motif-Video 2B addresses this by separating these roles architecturally, rather than relying on scale alone. The model combines two key ideas. First, Shared Cross-Attention strengthens text control when video token sequences become long. Second, a three-part backbone separates early fusion, joint representation learning, and detail refinement. To make this design effective under a limited compute budget, we pair it with an efficient training recipe based on dynamic token routing and early-phase feature alignment to a frozen pretrained video encoder. Our analysis shows that later blocks develop clearer cross-frame attention structure than standard single-stream baselines. On VBench, Motif-Video~2B reaches 83.76\%, surpassing Wan2.1 14B while using 7$\times$ fewer parameters and substantially less training data. These results suggest that careful architectural specialization, combined with an efficiency-oriented training recipe, can narrow or exceed the quality gap typically associated with much larger video models. --- ### Topology-Aware Layer Pruning for Large Vision-Language Models Authors: Pengcheng Zheng, Chaoning Zhang, Ya Wen, Wang Liu, Qigan Sun, Jiarong Mo, Jiaquan Zhang, Jewon Lee, Tae-Ho Kim, Kuien Liu, Tianyu Li, Caiyan Qin et al. Published: 2026-04-14 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.16502v2 Large Language Models (LLMs) have demonstrated strong capabilities in natural language understanding and reasoning, while recent extensions that incorporate visual inputs enable them to process multimodal information. Despite these advances, Large Vision-Language Models (LVLMs) incur substantial computational and memory costs, hindering deployment in resource-constrained scenarios. Existing layer pruning methods typically rely on local similarity metrics or static proxy signals, failing to capture the global and dynamic evolution of representations across model depth, which often leads to the removal of transition-critical layers. To address this limitation, we propose a topology-aware layer pruning framework for LVLMs. Specifically, we represent layer wise hidden states as point clouds and models their evolution using \textit{simplicial complexes}. By leveraging \textit{zigzag persistent homology}, we quantify inter-layer topological consistency and enable adaptive pruning that preserves critical representational transitions. Extensive experiments on diverse multimodal benchmarks demonstrate that the proposed framework consistently outperforms existing pruning methods across a wide range of sparsity ratios. Our code is available at https://github.com/zpc456/TopoVLM. --- ### Semantically Stable Image Composition Analysis via Saliency and Gradient Vector Flow Fusion Authors: Armin Dadras, Robert Sablatnig, Franziska Proksa, Markus Seidl Published: 2026-04-14 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.16500v1 The reliable computational assessment of photographic composition requires features that are discriminative of spatial layout yet robust to semantic content. This paper proposes a low-level representation grounded in the assumption that composition can be understood as the flow of visual attention across geometric structure. We introduce VFCNet, which fuses saliency and edge information into a gradient vector flow (GVF) field. The model computes dual-stream GVF representations, integrates them via attention, and extracts multi-scale flow features with a DINOv3 backbone. VFCNet achieves state-of-the-art performance on the PICD benchmark (CDA-1: 0.683, CDA-2: 0.629), improving by 33.1\% and 36.1\% over the previous best method. We also show that a simple classifier on self-supervised DINOv3 features substantially outperforms more sophisticated, composition-specialized models. Code is available at https://github.com/ADadras/VFCNet --- ### HQA-VLAttack: Towards High Quality Adversarial Attack on Vision-Language Pre-Trained Models Authors: Han Liu, Jiaqi Li, Zhi Xu, Xiaotong Zhang, Xiaoming Xu, Fenglong Ma, Yuanman Li, Hong Yu Published: 2026-04-14 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2604.16499v1 Black-box adversarial attack on vision-language pre-trained models is a practical and challenging task, as text and image perturbations need to be considered simultaneously, and only the predicted results are accessible. Research on this problem is in its infancy, and only a handful of methods are available. Nevertheless, existing methods either rely on a complex iterative cross-search strategy, which inevitably consumes numerous queries, or only consider reducing the similarity of positive image-text pairs but ignore that of negative ones, which will also be implicitly diminished, thus inevitably affecting the attack performance. To alleviate the above issues, we propose a simple yet effective framework to generate high-quality adversarial examples on vision-language pre-trained models, named HQA-VLAttack, which consists of text and image attack stages. For text perturbation generation, it leverages the counter-fitting word vector to generate the substitute word set, thus guaranteeing the semantic consistency between the substitute word and the original word. For image perturbation generation, it first initializes the image adversarial example via the layer-importance guided strategy, and then utilizes contrastive learning to optimize the image adversarial perturbation, which ensures that the similarity of positive image-text pairs is decreased while that of negative image-text pairs is increased. In this way, the optimized adversarial images and texts are more likely to retrieve negative examples, thereby enhancing the attack success rate. Experimental results on three benchmark datasets demonstrate that HQA-VLAttack significantly outperforms strong baselines in terms of attack success rate. --- ### Forge-UGC: FX optimization and register-graph engine for universal graph compiler Authors: Satyam Kumar, Saurabh Jha Published: 2026-04-14 Categories: cs.AR, cs.AI, cs.DC arXiv: https://arxiv.org/abs/2604.16498v1 We present Forge-UGC (FX Optimization and Register-Graph Engine for Universal Graph Compilation), a four-phase compiler for transformer deployment on heterogeneous accelerator hardware, validated on Intel AI Boost NPU. Existing frameworks such as OpenVINO and ONNX Runtime often use opaque compilation pipelines, limited pass-level visibility, and weak buffer management, which can lead to higher compilation cost and runtime overhead. Forge-UGC addresses this with a hardware-agnostic design that separates graph capture, optimization, intermediate representation lowering, and backend scheduling. Phase 1 captures graphs with torch.export at the ATen operator level, supporting modern transformer components such as rotary position embeddings, grouped-query attention, and SwiGLU without manual decomposition. Phase 2 applies six optimization passes: dead code elimination, common subexpression elimination, constant folding, attention fusion, operator fusion, and layout optimization, reducing graph node count by 14.2 to 21.9%. Phase 3 lowers the optimized graph into a typed intermediate representation with explicit virtual register assignments. Phase 4 performs liveness analysis, linear-scan buffer allocation, reducing peak buffer count by 30 to 48%, and device-affinity scheduling, reducing NPU-CPU transitions by 42 to 65%. Across six model families ranging from 125M to 8B parameters, evaluated on WikiText-103 and GLUE, Forge-UGC delivers 6.9 to 9.2x faster compilation than OpenVINO and ONNX Runtime, 18.2 to 35.7% lower inference latency, and 30.2 to 40.9% lower energy per inference. Fidelity is preserved, with max absolute logit differences below 2.1e-5 and KL divergence below 8.4e-9. We also introduce Fusion Gain Ratio, Compilation Efficiency Index, and per-pass execution profiling for systematic evaluation of NPU compilation pipelines. --- ### Gradient-Free Continual Learning in Spiking Neural Networks via Inter-Spike Interval Regularization Authors: Samrendra Roy, Kazuma Kobayashi, Souvik Chakraborty, Sajedul Talukder, Syed Bahauddin Alam Published: 2026-04-14 Categories: cs.NE, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2604.16496v1 Continual learning, the ability to acquire new tasks sequentially without forgetting prior knowledge, is essential for deploying neural networks in dynamic real-world environments, from nuclear digital twin monitoring to grid-edge fault detection. Existing synaptic importance methods, such as Elastic Weight Consolidation (EWC) and Synaptic Intelligence (SI), rely on gradient computation, making them incompatible with neuromorphic hardware that lacks backpropagation support. We propose ISI-CV, the first gradient-free synaptic importance metric for SNN continual learning, derived from the Coefficient of Variation (CV) of Inter-Spike Intervals (ISIs). Neurons that fire regularly (low CV) encode stable, task-relevant features and are protected from overwriting; neurons with irregular firing are permitted to adapt freely. ISI-CV requires only spike time counters and integer arithmetic, all of which are native to every neuromorphic chip. We evaluate on four benchmarks of increasing difficulty: Split-MNIST, Permuted-MNIST, Split-FashionMNIST, and Split-N-MNIST using real Dynamic Vision Sensor (DVS) event data. Across three seeds, ISI-CV achieves zero forgetting (AF = 0.000 +/- 0.000) on Split-MNIST and Split-FashionMNIST, near-zero forgetting on Permuted-MNIST (AF = 0.001 +/- 0.000), and the highest accuracy with the lowest forgetting on real neuromorphic DVS data (AA = 0.820 +/- 0.012, AF = 0.221 +/- 0.014). On N-MNIST, gradient-based methods produce unreliable importance estimates and perform worse than no regularization; ISI-CV avoids this failure by design. --- ### Photonic AI: A Hybrid Diffractive Holographic Neural System for Passive Optical Real-Time Image Classification Authors: Prakul Sunil Hiremath Published: 2026-04-14 Categories: cs.AR, cs.LG arXiv: https://arxiv.org/abs/2604.15364v1 Edge intelligence is constrained by the energy and latency costs of shuttling data through electronic memory hierarchies. Optical systems offer a fundamentally different computational regime: once an input wavefront is launched into a structured medium, propagation, diffraction, and interference jointly enact a linear transformation whose cost is determined by wave physics rather than by clocked arithmetic. This paper develops a rigorous systems-level treatment of that regime and introduces a hybrid diffractive holographic architecture for image classification. The proposed model couples a Diffractive Optical Neural Network (DONN) with a Holographic Interference-Based Learning (HIBL) operator a formal map from digitally optimized phase distributions to physically realizable, fabrication-compatible interference patterns embeddable in passive optical elements. We express the full inference pipeline as a composition of encoding, phase modulation, free-space propagation, and intensity measurement operators, making explicit which quantities are learned, which are fixed by design, and where nonlinearity enters through photodetection. This operator-theoretic view resolves a persistent gap in the optical-ML literature between learning a transformation and physically realizing it. In physics-informed simulation on MNIST, a three-layer system with approximately 25,000 phase elements achieves 91.2% test accuracy with propagation-limited nanosecond-scale latency. The primary contribution is not a performance claim but a precise computational framework: learned representations can be physically embedded into structured optical media so that inference is executed by wavefront transformation through a passive, fabricated object rather than by sequential electronic multiply accumulate operations. --- ### Graph-Based Fraud Detection with Dual-Path Graph Filtering Authors: Wei He, Wensheng Gan, Philip S. Yu Published: 2026-04-14 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2604.14235v1 Fraud detection on graph data can be viewed as a demanding task that requires distinguishing between different types of nodes. Because graph neural networks (GNNs) are naturally suited for processing information encoded in graph form through their message-passing operations, methods based on GNN models have increasingly attracted attention in the fraud detection domain. However, fraud graphs inherently exhibit relation camouflage, high heterophily, and class imbalance, causing most GNNs to underperform in fraud detection tasks. To address these challenges, this paper proposes a Graph-Based Fraud Detection Model with Dual-Path Graph Filtering (DPF-GFD). DPF-GFD first applies a beta wavelet-based operator to the original graph to capture key structural patterns. It then constructs a similarity graph from distance-based node representations and applies an improved low-pass filter. The embeddings from the original and similarity graphs are fused through supervised representation learning to obtain node features, which are finally used by an ensemble tree model to assess the fraud risk of unlabeled nodes. Unlike existing single-graph smoothing approaches, DPF-GFD introduces a frequency-complementary dual-path filtering paradigm tailored for fraud detection, explicitly decoupling structural anomaly modeling and feature similarity modeling. This design enables more discriminative and stable node representations in highly heterophilous and imbalanced fraud graphs. Comprehensive experiments on four real-world financial fraud detection datasets demonstrate the effectiveness of our proposed method. --- ### Anomaly Detection in IEC-61850 GOOSE Networks: Evaluating Unsupervised and Temporal Learning for Real-Time Intrusion Detection Authors: Joseph Moore Published: 2026-04-14 Categories: cs.CR, cs.LG arXiv: https://arxiv.org/abs/2604.14233v1 The IEC-61850 GOOSE protocol underpins time-critical communication in modern digital substations but lacks native security mechanisms, leaving it vulnerable to replay, masquerade, and data injection attacks. Intrusion detection in this setting is challenging due to strict latency constraints (sub-4ms) and limited availability of labeled attack data. This paper evaluates whether unsupervised temporal modeling can provide effective and deployable anomaly detection for GOOSE networks. Five models are compared on the ERENO IEC-61850 dataset: a supervised Random Forest baseline, a feedforward Autoencoder, and three recurrent sequence autoencoders (RNN, LSTM, and GRU). The supervised Random Forest achieves the highest detection performance (F1=0.9516) but fails to meet real-time constraints at 21.8ms per prediction. All four unsupervised models satisfy the 4ms requirement, with the GRU achieving the best accuracy to latency tradeoff among them (F1=0.8737 at 1.118ms). A cross-environment evaluation on an independent dataset shows that all models degrade under distribution shift. However, recurrent models retain substantially higher relative performance than the supervised baseline, suggesting that temporal sequence modeling generalizes better than fitting labeled attack distributions. Anomaly thresholds for the unsupervised models are selected on a held out validation partition to avoid test set leakage. These results support unsupervised temporal models as a practical choice for real-time GOOSE intrusion detection, particularly in environments where labeled training data may be unavailable or where large-scale deployment across diverse substations is required. --- ### Explainable Graph Neural Networks for Interbank Contagion Surveillance: A Regulatory-Aligned Framework for the U.S. Banking Sector Authors: Mohammad Nasir Uddin Published: 2026-04-14 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2604.14232v1 The Spatial-Temporal Graph Attention Network (ST-GAT) framework was created to serve as an explainable GNN-based solution for detecting bank distress early warning signs and for conducting macro-prudential surveillance of the interbank system in the United States. The ST-GAT framework models 8,103 FDIC insured institutions across 58 quarterly snapshots (2010Q1-2024Q2). Bilateral exposures were reconstructed from publicly available FDIC Call Reports using maximum entropy estimation to produce a dynamic directed weighted graph. The framework achieves the highest AUPRC among all GNN architectures (0.939 +/- 0.010), trailing only XGBoost (0.944). Ablation analysis confirms the BiLSTM temporal component contributes +0.020 AUPRC; temporal attention weights exhibit a monotonically decreasing pattern consistent with long-run structural vulnerability weighting. Permutation importance identifies ROA (0.309) and NPL Ratio (0.252) as dominant predictors, consistent with post-mortem analyses of the 2023 regional banking crisis. All data are publicly available FDIC Call Reports and FRED series; all code and results are released. --- ### Shapley Value-Guided Adaptive Ensemble Learning for Explainable Financial Fraud Detection with U.S. Regulatory Compliance Validation Authors: Mohammad Nasir Uddin, Md Munna Aziz Published: 2026-04-14 Categories: cs.LG, cs.AI, cs.NE arXiv: https://arxiv.org/abs/2604.14231v1 Financial crime costs U.S. institutions over $32 billion each year. Although AI tools for fraud detection have become more advanced, their use in real-world systems still faces a major obstacle: many of these models operate as black boxes that cannot provide the transparent, auditable explanations required by regulations such as OCC Bulletin 2011-12 and Federal Reserve SR 11-7. This study makes three main contributions. First, it offers a thorough evaluation of explanation quality across faithfulness (sufficiency and comprehensiveness at k=5, 10, and 15) and stability (Kendall's W across 30 bootstrap samples). XGBoost paired with TreeExplainer achieves near-perfect stability (W=0.9912), while LSTM with DeepExplainer shows weak results (W=0.4962). Second, the paper introduces the SHAP-Guided Adaptive Ensemble (SGAE), which dynamically adjusts per-transaction ensemble weights based on SHAP attribution agreement, achieving the highest AUC-ROC among all tested models (0.8837 held-out; 0.9245 cross-validation). Third, a complete three-architecture evaluation of LSTM, Transformer, and GNN-GraphSAGE on the full 590,540-transaction IEEE-CIS dataset is provided, with GNN-GraphSAGE achieving AUC-ROC 0.9248 and F1=0.6013. All results are mapped directly to OCC, SR 11-7, and BSA-AML regulatory compliance requirements. --- ### Magnitude Is All You Need? Rethinking Phase in Quantum Encoding of Complex SAR Data Authors: Sakthi Prabhu Gunasekar, Prasanna Kumar Rangarajan Published: 2026-04-14 Categories: quant-ph, cs.AI, cs.LG, eess.IV arXiv: https://arxiv.org/abs/2604.14229v2 Synthetic Aperture Radar (SAR) data is inherently complex-valued, while quantum machine learning (QML) models operate in complex Hilbert spaces. This similarity suggests that using both the magnitude and phase of SAR data in quantum encoding should help automatic target recognition in SAR images. In this study, we test this assumption by comparing five encoding strategies for quantum models: magnitude-only encoding, joint magnitude-phase encoding, in-phase and quadrature encoding, preprocessed phase encoding, and a purely quantum architecture. All approaches are evaluated under a unified experimental setup on the MSTAR benchmark dataset. Surprisingly, we find that magnitude-only encoding performs better than phase-inclusive encodings in hybrid quantum-classical models. It achieves 99.57 percent accuracy on the 3-class task and 71.19 percent accuracy on the 8-class task, outperforming complex-valued alternatives under the same framework. Adding phase information provides little or no improvement and can sometimes degrade performance. However, in purely quantum models with only 184 to 224 trainable parameters and no classical neural-network layers, phase information becomes much more important, improving accuracy by up to 21.65 percentage points. These findings show that the usefulness of phase information depends not only on the data, but also on the architecture used to process it. Hybrid models can compensate for missing phase information through their classical components, while pure quantum models rely more strongly on phase information for class discrimination. The results provide practical guidance for encoding complex-valued data in quantum machine learning and highlight the importance of jointly designing encoding strategies and model architectures for current quantum systems. --- ### Dive into Claude Code: The Design Space of Today's and Future AI Agent Systems Authors: Jiacheng Liu, Xiaohan Zhao, Xinyi Shang, Zhiqiang Shen Published: 2026-04-14 Categories: cs.SE, cs.AI, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2604.14228v2 Claude Code is an agentic coding tool that can run shell commands, edit files, and call external services on behalf of the user. This study describes its architecture by analyzing the publicly available source code and comparing it with two independent open-source AI agent systems, OpenClaw and Hermes Agent, that answer many of similar or even the same design questions. Our analysis identifies five human values, philosophies, and needs that motivate the architecture: human decision authority, safety, security, and privacy, reliable execution, capability amplification, and contextual adaptability. We then trace them through thirteen design principles to implementation choices. The core of the system is a simple while-loop that calls the model, runs tools, and repeats. Most of the code, however, lives in the systems around this loop: a permission system with seven modes and an ML-based classifier, a five-layer compaction pipeline for context management, four extensibility mechanisms (MCP, plugins, skills, and hooks), a subagent delegation and orchestration mechanism, and append-oriented session storage. Comparisons with OpenClaw and Hermes Agent show that the same design questions produce different answers across three deployment contexts. Claude Code emphasizes per-action safety, OpenClaw emphasizes perimeter-level access, and Hermes renders per-action approvals across many surfaces. At the runtime layer, Claude Code uses a single CLI loop, OpenClaw embeds the runtime within a gateway control plane, and Hermes uses one process whose role is set by its entry point. At the context and extension layer, Claude Code extends the context window, OpenClaw registers gateway-wide capabilities, and Hermes provides pluggable memory and model backends. We finally identify six open design directions for future agent systems, grounded in recent empirical, architectural, and policy literature. --- ### FRESCO: Benchmarking and Optimizing Re-rankers for Evolving Semantic Conflict in Retrieval-Augmented Generation Authors: Sohyun An, Hayeon Lee, Shuibenyang Yuan, Chun-cheng Jason Chen, Cho-Jui Hsieh, Vijai Mohan, Alexander Min Published: 2026-04-14 Categories: cs.IR, cs.AI arXiv: https://arxiv.org/abs/2604.14227v1 Retrieval-Augmented Generation (RAG) is a key approach to mitigating the temporal staleness of large language models (LLMs) by grounding responses in up-to-date evidence. Within the RAG pipeline, re-rankers play a pivotal role in selecting the most useful documents from retrieved candidates. However, existing benchmarks predominantly evaluate re-rankers in static settings and do not adequately assess performance under evolving information -- a critical gap, as real-world systems often must choose among temporally different pieces of evidence. To address this limitation, we introduce FRESCO (Factual Recency and Evolving Semantic COnflict), a benchmark for evaluating re-rankers in temporally dynamic contexts. By pairing recency-seeking queries with historical Wikipedia revisions, FRESCO tests whether re-rankers can prioritize factually recent evidence while maintaining semantic relevance. Our evaluation reveals a consistent failure mode across existing re-rankers: a strong bias toward older, semantically rich documents, even when they are factually obsolete. We further investigate an instruction optimization framework to mitigate this issue. By identifying Pareto-optimal instructions that balance Evolving and Non-Evolving Knowledge tasks, we obtain gains of up to 27% on Evolving Knowledge tasks while maintaining competitive performance on Non-Evolving Knowledge tasks. --- ### TRACE: A Conversational Framework for Sustainable Tourism Recommendation with Agentic Counterfactual Explanations Authors: Ashmi Banerjee, Adithi Satish, Wolfgang Wörndl, Yashar Deldjoo Published: 2026-04-14 Categories: cs.IR, cs.AI arXiv: https://arxiv.org/abs/2604.14223v1 Traditional conversational travel recommender systems primarily optimize for user relevance and convenience, often reinforcing popular, overcrowded destinations and carbon-intensive travel choices. To address this, we present TRACE (Tourism Recommendation with Agentic Counterfactual Explanations), a multi-agent, LLM-based framework that promotes sustainable tourism through interactive nudging. TRACE uses a modular orchestrator-worker architecture where specialized agents elicit latent sustainability preferences, construct structured user personas, and generate recommendations that balance relevance with environmental impact. A key innovation lies in its use of agentic counterfactual explanations and LLM-driven clarifying questions, which together surface greener alternatives and refine understanding of intent, fostering user reflection without coercion. User studies and semantic alignment analyses demonstrate that TRACE effectively supports sustainable decision-making while preserving recommendation quality and interactive responsiveness. TRACE is implemented on Google's Agent Development Kit, with full code, Docker setup, prompts, and a publicly available demo video to ensure reproducibility. A project summary, including all resources, prompts, and demo access, is available at https://ashmibanerjee.github.io/trace-chatbot. --- ### Adaptive Query Routing: A Tier-Based Framework for Hybrid Retrieval Across Financial, Legal, and Medical Documents Authors: Afshan Hashmi Published: 2026-04-14 Categories: cs.IR, cs.AI arXiv: https://arxiv.org/abs/2604.14222v1 Retrieval-Augmented Generation (RAG) has become the standard paradigm for grounding Large Language Model outputs in external knowledge. Lumer et al. (1) presented the first systematic evaluation comparing vector-based agentic RAG against hierarchical node-based reasoning systems for financial document QA across 1,200 SEC filings, finding vector-based systems achieved a 68% win rate. Concurrently, the PageIndex framework (2) demonstrated 98.7% accuracy on FinanceBench through purely reasoning-based retrieval. This paper extends their work by: (i) implementing and evaluating three retrieval architectures: Vector RAG, Tree Reasoning, and the proposed Adaptive Hybrid Retrieval (AHR) across financial, legal, and medical domains; (ii) introducing a four-tier query complexity benchmark; and (iii) employing GPT-4-powered LLM-as-judge evaluation. Experiments reveal that Tree Reasoning achieves the highest overall score (0.900), but no single paradigm dominates across all tiers: Vector RAG wins on multi-document synthesis (Tier 4, score 0.900), while the Hybrid AHR achieves the best performance on cross-reference (0.850) and multi-section queries (0.929). Cross-reference recall reaches 100% for tree-based and hybrid approaches versus 91.7% for vector search, quantifying a critical capability gap. Validation on FinanceBench (150 expert-annotated questions on real SEC 10-K and 10-Q filings) confirms and strengthens these findings: Tree Reasoning scores 0.938, Hybrid AHR 0.901, and Vector RAG 0.821, with the Tree--Vector quality gap widening to 11.7 percentage points on real-world documents. These findings support the development of adaptive retrieval systems that dynamically select strategies based on query complexity and document structure. All code and data are publicly available. --- ### Fun-TSG: A Function-Driven Multivariate Time Series Generator with Variable-Level Anomaly Labeling Authors: Pierre Lotte, André Péninou, Olivier Teste Published: 2026-04-14 Categories: cs.AI arXiv: https://arxiv.org/abs/2604.14221v2 Reliable evaluation of anomaly detection methods in multivariate time series remains an open challenge, largely due to the limitations of existing benchmark datasets. Current resources often lack fine-grained anomaly annotations, do not provide explicit intervariable and temporal dependencies, and offer little insight into the underlying generative mechanisms. These shortcomings hinder the development and rigorous comparison of detection models, especially those targeting interpretable and variable-specific outputs. To address this gap, we introduce Fun-TSG, a fully customizable time series generator designed to support high-quality evaluation of anomaly detection systems. Our tool enables both fully automated generation, based on randomly sampled dependency structures and anomaly types, and manual generation through user-defined equations and anomaly configurations. In both cases, it provides full transparency over the data generation process, including access to ground-truth anomaly labels at the variable and timestamp levels. Fun-TSG supports the creation of diverse, interpretable, and reproducible benchmarking scenarios, enabling fine-grained performance analysis for both classical and modern anomaly detection models. --- ### Knowledge Graph RAG: Agentic Crawling and Graph Construction in Enterprise Documents Authors: Koushik Chakraborty, Koyel Guha Published: 2026-04-14 Categories: cs.IR, cs.AI arXiv: https://arxiv.org/abs/2604.14220v1 This research paper addresses the limitations of semantic search in complex enterprise document ecosystems. Traditional RAG pipelines often fail to capture hierarchical and interconnected information, leading to retrieval inaccuracies. We propose Agentic Knowledge Graphs featuring Recursive Crawling as a robust solution for navigating superseding logic and multi-hop references. Our benchmark evaluation using the Code of Federal Regulations (CFR) demonstrates that this Knowledge Graph-enhanced approach achieves a 70% accuracy improvement over standard vector-based RAG systems, providing exhaustive and precise answers for complex regulatory queries. --- ### BioTrain: Sub-MB, Sub-50mW On-Device Fine-Tuning for Edge-AI on Biosignals Authors: Run Wang, Victor J. B. Jung, Philip Wiese, Sebastian Frey, Giusy Spacone, Francesco Conti, Alessio Burrello, Luca Benini Published: 2026-04-14 Categories: cs.LG, cs.AR, eess.SP arXiv: https://arxiv.org/abs/2604.13359v2 Biosignals exhibit substantial cross-subject and cross-session variability, inducing severe domain shifts that degrade post-deployment performance for small, edge-oriented AI models. On-device adaptation is therefore essential to both preserve user privacy and ensure system reliability. However, existing sub-100 mW MCU-based wearable platforms can only support shallow or sparse adaptation schemes due to the prohibitive memory footprint and computational cost of full backpropagation (BP). In this paper, we propose BioTrain, a framework enabling full-network fine-tuning of state-of-the-art biosignal models under milliwatt-scale power and sub-megabyte memory constraints. We validate BioTrain using both offline and on-device benchmarks on EEG and EOG datasets, covering Day-1 new-subject calibration and longitudinal adaptation to signal drift. Experimental results show that full-network fine-tuning achieves accuracy improvements of up to 35% over non-adapted baselines and outperforms last-layer updates by approximately 7% during new-subject calibration. On the GAP9 MCU platform, BioTrain enables efficient on-device training throughput of 17 samples/s for EEG and 85 samples/s for EOG models within a power envelope below 50 mW. In addition, BioTrain's efficient memory allocator and network topology optimization enable the use of a large batch size, reducing peak memory usage. For fully on-chip BP on GAP9, BioTrain reduces the memory footprint by 8.1x, from 5.4 MB to 0.67 MB, compared to conventional full-network fine-tuning using batch normalization with batch size 8. --- ### Peer-Predictive Self-Training for Language Model Reasoning Authors: Shi Feng, Hanlin Zhang, Fan Nie, Sham Kakade, Yiling Chen Published: 2026-04-14 Categories: cs.CL, cs.AI, cs.GT arXiv: https://arxiv.org/abs/2604.13356v3 Mechanisms for continued self-improvement of language models without external supervision remain an open challenge. We propose Peer-Predictive Self-Training (PST), a label-free fine-tuning framework in which multiple language models improve collaboratively by using a cross-model aggregate response as an internal training signal. Given a prompt, models generate responses sequentially; the final aggregated answer, which is often more reliable than individual responses in practice, serves as an internal reference for learning. We measure how informative each intermediate response is about the aggregate using pointwise mutual information (PMI), and use this signal to scale self-training updates: responses already aligned with the aggregate receive smaller updates, while less informative or misaligned responses receive larger ones. On mathematical reasoning benchmarks, including SimulEq, MATH-500-Numeric, and MultiArith, PST improves exact-match accuracy by 2.2--4.3 percentage points across Gemma-2-2B, LLaMA-3.2-1B, and Qwen2.5-1.5B, and reduces the average generator--verifier gap (GV-Gap) by 26--40%, while requiring no external supervision, no teacher--student hierarchy, and only cross-model interactions. These results suggest that peer-predictive feedback from cross-model generations can provide an effective mechanism for self-supervised language-model improvement. --- ### Finetuning-Free Diffusion Model with Adaptive Constraint Guidance for Inorganic Crystal Structure Generation Authors: Auguste de Lambilly, Vladimir Baturin, David Portehault, Guillaume Lambard, Nataliya Sokolovska, Florence d'Alché-Buc, Jean-Claude Crivello Published: 2026-04-14 Categories: cond-mat.mtrl-sci, cs.AI arXiv: https://arxiv.org/abs/2604.13354v3 Generative diffusion models have emerged as powerful tools for the discovery of inorganic crystal structures, yet steering their sampling process toward user-defined physical and chemical objectives remains challenging. We present a computational framework that integrates adaptive constraint guidance into a pre-trained crystal diffusion model, enabling the generation of candidate structures that satisfy targeted structural and chemical requirements without model retraining. The approach incorporates differentiable constraint functions directly during sampling, providing an interpretable mechanism for expert-driven exploration of the crystal structure space. To assess the reliability of generated candidates, we introduce a multi-stage validation workflow combining descriptor-based analysis, duplicate removal, comparison with reference crystal databases, graph neural network energy prediction, and thermodynamic stability evaluation through convex-hull analysis. The framework is applied to several classes of inorganic compounds and to constraints involving atomic volume, local coordination environments, and near-neighbor structural motifs. Results demonstrate that adaptive guidance effectively redirects the sampling distribution toward structures exhibiting the desired characteristics while preserving chemical plausibility. Subsequent validation reveals which generated candidates remain viable after energetic and thermodynamic screening. The proposed methodology provides a practical and transparent strategy for incorporating expert knowledge into crystal generative models and establishes a general computational framework for constrained materials discovery. --- ### When Less Latent Leads to Better Relay: Information-Preserving Compression for Latent Multi-Agent LLM Collaboration Authors: Yiping Li, Zhiyu An, Wan Du Published: 2026-04-14 Categories: cs.LG arXiv: https://arxiv.org/abs/2604.13349v3 Multi-agent LLM systems are moving beyond discrete-token messages toward richer relays that preserve internal state. Recent work such as LatentMAS transmits full key-value (KV) caches between agents but pays a high memory and communication cost. We adapt KV-cache eviction to this setting and introduce \textbf{Orthogonal BackFill (OBF)}, which injects a low-rank residual from the discarded KV states back into the retained ones, orthogonal to what is already kept. With only $9.9\%$-$20.2\%$ of the prompt KV retained, compressed relay cuts bandwidth by $4.7\times$ and GPU memory by $8\%$ at under $5\%$ wall-clock overhead, and stays close to full relay in accuracy across nine benchmarks, ahead of it on several. OBF matches or improves over headwise eviction on all nine, and its gain is proportional to the accuracy gap eviction opens against full relay ($r{=}0.78$ across three model scales), so it gives back part of what eviction takes. Code is available at https://github.com/markli404/When-Less-Latent-Leads-to-Better-Relay. --- ### When Less Latent Leads to Better Relay: Information-Preserving Compression for Latent Multi-Agent LLM Collaboration Authors: Yiping Li, Zhiyu An, Wan Du Published: 2026-04-14 Categories: cs.LG arXiv: https://arxiv.org/abs/2604.13349v2 Communication in Large Language Model (LLM)-based multi-agent systems is moving beyond discrete tokens to preserve richer context. Recent work such as LatentMAS enables agents to exchange latent messages through full key-value (KV) caches. However, full KV relay incurs high memory and communication cost. We adapt KV-cache eviction methods to this setting and introduce \textbf{Orthogonal BackFill (OBF)} to mitigate information loss from hard eviction. OBF injects a low-rank orthogonal residual from discarded KV states into the retained KV states. We evaluate OBF against full KV relay on nine benchmarks spanning mathematical reasoning, expert and commonsense QA, and coding. With only 9.9%-20.2% of the prompt KV states retained, H-OBF delivers between $97%$ and $120%$ of full KV relay's per-benchmark accuracy across the nine benchmarks. This suggests that more information does not necessarily lead to better communication; preserving the most useful information matters more. Our codebase is included in the supplementary material. Our codebase is publicly available on https://github.com/markli404/When-Less-Latent-Leads-to-Better-Relay. --- ### Listening Alone, Understanding Together: Collaborative Context Recovery for Privacy-Aware AI Authors: Tanmay Srivastava, Amartya Basu, Shubham Jain, Vaishnavi Ranganathan Published: 2026-04-14 Categories: cs.AI, cs.CR arXiv: https://arxiv.org/abs/2604.13348v1 We introduce CONCORD, a privacy-aware asynchronous assistant-to-assistant (A2A) framework that leverages collaboration between proactive speech-based AI. As agents evolve from reactive to always-listening assistants, they face a core privacy risk (of capturing non-consenting speakers), which makes their social deployment a challenge. To overcome this, we implement CONCORD, which enforces owner-only speech capture via real-time speaker verification, producing a one-sided transcript that incurs missing context but preserves privacy. We demonstrate that CONCORD can safely recover necessary context through (1) spatio-temporal context resolution, (2) information gap detection, and (3) minimal A2A queries governed by a relationship-aware disclosure. Instead of hallucination-prone inferring, CONCORD treats context recovery as a negotiated safe exchange between assistants. Across a multi-domain dialogue dataset, CONCORD achieves 91.4% recall in gap detection, 96% relationship classification accuracy, and 97% true negative rate in privacy-sensitive disclosure decisions. By reframing always-listening AI as a coordination problem between privacy-preserving agents, CONCORD offers a practical path toward socially deployable proactive conversational agents. --- ### AgentSPEX: An Agent SPecification and EXecution Language Authors: Pengcheng Wang, Jerry Huang, Jiarui Yao, Rui Pan, Peizhi Niu, Yaowenqi Liu, Ruida Wang, Renhao Lu, Yuwei Guo, Tong Zhang Published: 2026-04-14 Categories: cs.CL arXiv: https://arxiv.org/abs/2604.13346v1 Language-model agent systems commonly rely on reactive prompting, in which a single instruction guides the model through an open-ended sequence of reasoning and tool-use steps, leaving control flow and intermediate state implicit and making agent behavior potentially difficult to control. Orchestration frameworks such as LangGraph, DSPy, and CrewAI impose greater structure through explicit workflow definitions, but tightly couple workflow logic with Python, making agents difficult to maintain and modify. In this paper, we introduce AgentSPEX, an Agent SPecification and EXecution Language for specifying LLM-agent workflows with explicit control flow and modular structure, along with a customizable agent harness. AgentSPEX supports typed steps, branching and loops, parallel execution, reusable submodules, and explicit state management, and these workflows execute within an agent harness that provides tool access, a sandboxed virtual environment, and support for checkpointing, verification, and logging. Furthermore, we provide a visual editor with synchronized graph and workflow views for authoring and inspection. We include ready-to-use agents for deep research and scientific research, and we evaluate AgentSPEX on 7 benchmarks. Finally, we show through a user study that AgentSPEX provides a more interpretable and accessible workflow-authoring paradigm than a popular existing agent framework. --- ### Multi-Agent Object Detection Framework Based on Raspberry Pi YOLO Detector and Slack-Ollama Natural Language Interface Authors: Vladimir Kalušev, Branko Brkljač, Milan Brkljač Published: 2026-04-14 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.13345v1 The paper presents design and prototype implementation of an edge based object detection system within the new paradigm of AI agents orchestration. It goes beyond traditional design approaches by leveraging on LLM based natural language interface for system control and communication and practically demonstrates integration of all system components into a single resource constrained hardware platform. The method is based on the proposed multi-agent object detection framework which tightly integrates different AI agents within the same task of providing object detection and tracking capabilities. The proposed design principles highlight the fast prototyping approach that is characteristic for transformational potential of generative AI systems, which are applied during both development and implementation stages. Instead of specialized communication and control interface, the system is made by using Slack channel chatbot agent and accompanying Ollama LLM reporting agent, which are both run locally on the same Raspberry Pi platform, alongside the dedicated YOLO based computer vision agent performing real time object detection and tracking. Agent orchestration is implemented through a specially designed event based message exchange subsystem, which represents an alternative to completely autonomous agent orchestration and control characteristic for contemporary LLM based frameworks like the recently proposed OpenClaw. Conducted experimental investigation provides valuable insights into limitations of the low cost testbed platforms in the design of completely centralized multi-agent AI systems. The paper also discusses comparative differences between presented approach and the solution that would require additional cloud based external resources. --- ### MSGS: Multispectral 3D Gaussian Splatting Authors: Iris Zheng, Guojun Tang, Alexander Doronin, Paul Teal, Fang-Lue Zhang Published: 2026-04-14 Categories: cs.CV, cs.GR arXiv: https://arxiv.org/abs/2604.13340v1 We present a multispectral extension to 3D Gaussian Splatting (3DGS) for wavelength-aware view synthesis. Each Gaussian is augmented with spectral radiance, represented via per-band spherical harmonics, and optimized under a dual-loss supervision scheme combining RGB and multispectral signals. To improve rendering fidelity, we perform spectral-to-RGB conversion at the pixel level, allowing richer spectral cues to be retained during optimization. Our method is evaluated on both public and self-captured real-world datasets, demonstrating consistent improvements over the RGB-only 3DGS baseline in terms of image quality and spectral consistency. Notably, it excels in challenging scenes involving translucent materials and anisotropic reflections. The proposed approach maintains the compactness and real-time efficiency of 3DGS while laying the foundation for future integration with physically based shading models. --- ### SEDTalker: Emotion-Aware 3D Facial Animation Using Frame-Level Speech Emotion Diarization Authors: Farzaneh Jafari, Stefano Berretti, Anup Basu Published: 2026-04-14 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.13335v1 We introduce SEDTalker, an emotion-aware framework for speech-driven 3D facial animation that leverages frame-level speech emotion diarization to achieve fine-grained expressive control. Unlike prior approaches that rely on utterance-level or manually specified emotion labels, our method predicts temporally dense emotion categories and intensities directly from speech, enabling continuous modulation of facial expressions over time. The diarized emotion signals are encoded as learned embeddings and used to condition a speech-driven 3D animation model based on a hybrid Transformer-Mamba architecture. This design allows effective disentanglement of linguistic content and emotional style while preserving identity and temporal coherence. We evaluate our approach on a large-scale multi-corpus dataset for speech emotion diarization and on the EmoVOCA dataset for emotional 3D facial animation. Quantitative results demonstrate strong frame-level emotion recognition performance and low geometric and temporal reconstruction errors, while qualitative results show smooth emotion transitions and consistent expression control. These findings highlight the effectiveness of frame-level emotion diarization for expressive and controllable 3D talking head generation. --- ### SSD-GS: Scattering and Shadow Decomposition for Relightable 3D Gaussian Splatting Authors: Iris Zheng, Guojun Tang, Alexander Doronin, Paul Teal, Fang-Lue Zhang Published: 2026-04-14 Categories: cs.CV, cs.GR arXiv: https://arxiv.org/abs/2604.13333v1 We present SSD-GS, a physically-based relighting framework built upon 3D Gaussian Splatting (3DGS) that achieves high-quality reconstruction and photorealistic relighting under novel lighting conditions. In physically-based relighting, accurately modeling light-material interactions is essential for faithful appearance reproduction. However, existing 3DGS-based relighting methods adopt coarse shading decompositions, either modeling only diffuse and specular reflections or relying on neural networks to approximate shadows and scattering. This leads to limited fidelity and poor physical interpretability, particularly for anisotropic metals and translucent materials. To address these limitations, SSD-GS decomposes reflectance into four components: diffuse, specular, shadow, and subsurface scattering. We introduce a learnable dipole-based scattering module for subsurface transport, an occlusion-aware shadow formulation that integrates visibility estimates with a refinement network, and an enhanced specular component with an anisotropic Fresnel-based model. Through progressive integration of all components during training, SSD-GS effectively disentangles lighting and material properties, even for unseen illumination conditions, as demonstrated on the challenging OLAT dataset. Experiments demonstrate superior quantitative and perceptual relighting quality compared to prior methods and pave the way for downstream tasks, including controllable light source editing and interactive scene relighting. The source code is available at: https://github.com/irisfreesiri/SSD-GS. --- ### Selecting Feature Interactions for Generalized Additive Models by Distilling Foundation Models Authors: Jingyun Jia, Chandan Singh, Rich Caruana, Ben Lengerich Published: 2026-04-14 Categories: cs.LG arXiv: https://arxiv.org/abs/2604.13332v1 Identifying meaningful feature interactions is a central challenge in building accurate and interpretable models for tabular data. Generalized additive models (GAMs) have shown great success at modeling tabular data, but often rely on heuristic procedures to select interactions, potentially missing higher-order or context-dependent effects. To meet this challenge, we propose TabDistill, a method that leverages tabular foundation models and post-hoc distillation methods. Our key intuition is that tabular foundation models implicitly learn rich, adaptive feature dependencies through large-scale representation learning. Given a dataset, TabDistill first fits a tabular foundation model to the dataset, and then applies a post-hoc interaction attribution method to extract salient feature interactions from it. We evaluate these interactions by then using them as terms in a GAM. Across tasks, we find that interactions identified by TabDistill lead to consistent improvements in downstream GAMs' predictive performance. Our results suggest that tabular foundation models can serve as effective, data-driven guides for interaction discovery, bridging high-capacity models and interpretable additive frameworks. --- ### Text-Attributed Knowledge Graph Enrichment with Large Language Models for Medical Concept Representation Authors: Mohsen Nayebi Kerdabadi, Arya Hadizadeh Moghaddam, Chen Chen, Dongjie Wang, Zijun Yao Published: 2026-04-14 Categories: cs.LG arXiv: https://arxiv.org/abs/2604.13331v2 In electronic health record (EHR) mining, learning high-quality representations of medical concepts (e.g., standardized diagnosis, medication, and procedure codes) is fundamental for downstream clinical prediction. However, ro bust concept representation learning is hindered by two key challenges: (i) clinically important cross-type dependencies (e.g., diagnosis medication and medication-procedure relations) are often missing or incomplete in existing ontology resources, limiting the ability to model complex EHR patterns; and (ii) rich clinical semantics are often missing from structured resources, and even when available as text, are difficult to integrate with KG structure for representation learning. To address these challenges, we present MedCo, an LLM empowered graph learning framework for medical concept representation. MedCo first builds a global knowledge graph (KG) over medical codes by combining statistically reliable associations mined from EHRs with type-constrained LLM prompting to infer semantic relations. It then utilizes LLMs to enrich the KG into a text-attributed graph by generating node descriptions and edge rationales, providing semantic signals for both concepts and their relationships. Finally, MedCo jointly trains a LoRA-tuned LLaMA text encoder with a heterogeneous GNN, fusing text semantics and graph structure into unified concept embeddings. Extensive experiments on MIMIC-III and MIMIC-IV show that MedCo consistently improves prediction performance and serves as an effective plug-in concept encoder for standard EHR pipelines. --- ### Multi-Task LLM with LoRA Fine-Tuning for Automated Cancer Staging and Biomarker Extraction Authors: Jiahao Shao, Anam Nawaz Khan, Christopher Brett, Tom Berg, Xueping Li, Bing Yao Published: 2026-04-14 Categories: cs.LG arXiv: https://arxiv.org/abs/2604.13328v1 Pathology reports serve as the definitive record for breast cancer staging, yet their unstructured format impedes large-scale data curation. While Large Language Models (LLMs) offer semantic reasoning, their deployment is often limited by high computational costs and hallucination risks. This study introduces a parameter-efficient, multi-task framework for automating the extraction of Tumor-Node-Metastasis (TNM) staging, histologic grade, and biomarkers. We fine-tune a Llama-3-8B-Instruct encoder using Low-Rank Adaptation (LoRA) on a curated, expert-verified dataset of 10,677 reports. Unlike generative approaches, our architecture utilizes parallel classification heads to enforce consistent schema adherence. Experimental results demonstrate that the model achieves a Macro F1 score of 0.976, successfully resolving complex contextual ambiguities and heterogeneous reporting formats that challenge traditional extraction methods including rule-based natural language processing (NLP) pipelines, zero-shot LLMs, and single-task LLM baselines. The proposed adapter-efficient, multi-task architecture enables reliable, scalable pathology-derived cancer staging and biomarker profiling, with the potential to enhance clinical decision support and accelerate data-driven oncology research. --- ### Event Tensor: A Unified Abstraction for Compiling Dynamic Megakernel Authors: Hongyi Jin, Bohan Hou, Guanjie Wang, Ruihang Lai, Jinqi Chen, Zihao Ye, Yaxing Cai, Yixin Dong, Xinhao Cheng, Zhihao Zhang, Yilong Zhao, Yingyi Huang et al. Published: 2026-04-14 Categories: cs.DC, cs.LG, cs.PL arXiv: https://arxiv.org/abs/2604.13327v2 Modern GPU workloads, especially large language model (LLM) inference, suffer from kernel launch overheads and coarse synchronization that limit inter-kernel parallelism. Recent megakernel techniques fuse multiple operators into a single persistent kernel to eliminate launch gaps and expose inter-kernel parallelism, but struggle to handle dynamic shapes and data-dependent computation in real workloads. We present Event Tensor, a unified compiler abstraction for dynamic megakernels. Event Tensor encodes dependencies between tiled tasks, and enables first-class support for both shape and data-dependent dynamism. Built atop this abstraction, our Event Tensor Compiler (ETC) applies static and dynamic scheduling transformations to generate high-performance persistent kernels. Evaluations show that ETC achieves state-of-the-art LLM serving latency while significantly reducing system warmup overhead. --- ### Right Regions, Wrong Labels: Semantic Label Flips in Segmentation under Correlation Shift Authors: Akshit Achara, Yovin Yahathugoda, Nick Byrne, Michela Antonelli, Esther Puyol Anton, Alexander Hammers, Andrew P. King Published: 2026-04-14 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.13326v2 The robustness of machine learning models can be compromised by spurious correlations between non-causal features in the input data and target labels. A common way to test for such correlations is to train on data where the label is strongly tied to some non-causal cue, then evaluate on examples where that tie no longer holds. This idea is well established for classification tasks, but for semantic segmentation the specific failure modes are not well understood. We show that a model may achieve reasonable overlap while assigning the wrong semantic label, swapping one plausible foreground class for another, even when object boundaries are largely correct. We focus on this semantic label-flip behaviour and quantify it with a simple diagnostic (Flip) that counts how often ground truth foreground pixels are assigned the wrong foreground identity while remaining predicted as foreground. In a setting where category and scene are correlated during training, increasing the correlation consistently widens the gap between common and rare test conditions and increases these within-object label swaps on counterfactual groups. Overall, our results motivate assessing segmentation robustness under distribution shift beyond overlap by decomposing foreground errors into correct pixels, flipped-identity pixels, and missed-to-background pixels. We also propose an entropy-based, ground truth label-free `flip-risk' score, which is computed from foreground identity uncertainty, and show that it can flag flip-prone cases at inference time. Code is available at https://github.com/acharaakshit/label-flips. --- ### Towards Successful Implementation of Automated Raveling Detection: Effects of Training Data Size, Illumination Difference, and Spatial Shift Authors: Xinan Zhang, Haolin Wang, Zhongyu Yang, Yi-Chang, Tsai Published: 2026-04-14 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.13322v1 Raveling, the loss of aggregates, is a major form of asphalt pavement surface distress, especially on highways. While research has shown that machine learning and deep learning-based methods yield promising results for raveling detection by classification on range images, their performance often degrades in large-scale deployments where more diverse inference data may originate from different runs, sensors, and environmental conditions. This degradation highlights the need of a more generalizable and robust solution for real-world implementation. Thus, the objectives of this study are to 1) identify and assess potential variations that impact model robustness, such as the quantity of training data, illumination difference, and spatial shift; and 2) leverage findings to enhance model robustness under real-world conditions. To this end, we propose RavelingArena, a benchmark designed to evaluate model robustness to variations in raveling detection. Instead of collecting extensive new data, it is built by augmenting an existing dataset with diverse, controlled variations, thereby enabling variation-controlled experiments to quantify the impact of each variation. Results demonstrate that both the quantity and diversity of training data are critical to the accuracy of models, achieving at least a 9.2% gain in accuracy under the most diverse conditions in experiments. Additionally, a case study applying these findings to a multi-year test section in Georgia, U.S., shows significant improvements in year-to-year consistency, laying foundations for future studies on temporal deterioration modeling. These insights provide guidance for more reliable model deployment in raveling detection and other real-world tasks that require adaptability to diverse conditions. --- ### Why MLLMs Struggle to Determine Object Orientations Authors: Anju Gopinath, Nikhil Krishnaswamy, Bruce Draper Published: 2026-04-14 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.13321v1 Multimodal Large Language Models (MLLMs) struggle with tasks that require reasoning about 2D object orientation in images, as documented in prior work. Tong et al. and Nichols et al. hypothesize that these failures originate in the visual encoder, since commonly used encoders such as CLIP and SigLIP are trained for image-text semantic alignment rather than geometric reasoning. We design a controlled empirical protocol to test this claim by measuring whether rotations can be recovered from encoder representations. In particular, we examine SigLIP and ViT features from LLaVA OneVision and Qwen2.5-VL-7B-Instruct models, respectively, using full images, and examine CLIP representations in LLaVA 1.5 and 1.6 using rotated foreground patches against natural background images. Our null hypothesis is that orientation information is not preserved in the encoder embeddings and we test this by training linear regressors to predict object orientation from encoded features. Contrary to the hypothesis, we find that orientation information is recoverable from encoder representations: simple linear models accurately predict object orientations from embeddings. This contradicts the assumption that MLLM orientation failures originate in the visual encoder. Having rejected the accepted hypothesis that MLLMs struggle with 2D orientation tasks because of visual encoder limitations, we still don't know why they fail. Although a full explanation is beyond the scope of this paper, we show that although present, orientation information is spread diffusely across tens of thousands of features. This may or may not be while MLLMs fail to exploit the available orientation information. --- ### WebXSkill: Skill Learning for Autonomous Web Agents Authors: Zhaoyang Wang, Qianhui Wu, Xuchao Zhang, Chaoyun Zhang, Wenlin Yao, Fazle Elahi Faisal, Baolin Peng, Si Qin, Suman Nath, Qingwei Lin, Chetan Bansal, Dongmei Zhang et al. Published: 2026-04-14 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2604.13318v2 Autonomous web agents powered by large language models (LLMs) remain brittle on long-horizon browser workflows. A key bottleneck is a grounding gap in existing skill formulations: textual workflow skills provide natural language guidance but cannot be directly executed, while code-based skills execute without giving the agent step-level guidance for adaptation or recovery. We introduce WebXSkill, a framework that bridges this gap with executable skills, each pairing a parameterized action program with step-level natural-language guidance. WebXSkill operates in three stages: skill extraction mines reusable action subsequences from readily available synthetic agent trajectories and abstracts them into parameterized skills, skill organization indexes them into a URL-based graph for context-aware retrieval, and skill deployment exposes two complementary modes, grounded mode for fully automated execution and guided mode where skills serve as step-by-step instructions the agent follows with its native planning. WebXSkill demonstrates consistent improvements on WebArena, WebVoyager, and Online-Mind2Web. We further find that better skill deployment mode depends on a model's plan and execution capability. The code is available at https://github.com/aiming-lab/WebXSkill. --- ### WebXSkill: Skill Learning for Autonomous Web Agents Authors: Zhaoyang Wang, Qianhui Wu, Xuchao Zhang, Chaoyun Zhang, Wenlin Yao, Fazle Elahi Faisal, Baolin Peng, Si Qin, Suman Nath, Qingwei Lin, Chetan Bansal, Dongmei Zhang et al. Published: 2026-04-14 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2604.13318v1 Autonomous web agents powered by large language models (LLMs) have shown promise in completing complex browser tasks, yet they still struggle with long-horizon workflows. A key bottleneck is the grounding gap in existing skill formulations: textual workflow skills provide natural language guidance but cannot be directly executed, while code-based skills are executable but opaque to the agent, offering no step-level understanding for error recovery or adaptation. We introduce WebXSkill, a framework that bridges this gap with executable skills, each pairing a parameterized action program with step-level natural language guidance, enabling both direct execution and agent-driven adaptation. WebXSkill operates in three stages: skill extraction mines reusable action subsequences from readily available synthetic agent trajectories and abstracts them into parameterized skills, skill organization indexes skills into a URL-based graph for context-aware retrieval, and skill deployment exposes two complementary modes, grounded mode for fully automated multi-step execution and guided mode where skills serve as step-by-step instructions that the agent follows with its native planning. On WebArena and WebVoyager, WebXSkill improves task success rate by up to 9.8 and 12.9 points over the baseline, respectively, demonstrating the effectiveness of executable skills for web agents. The code is publicly available at https://github.com/aiming-lab/WebXSkill. --- ### Beyond Uniform Sampling: Synergistic Active Learning and Input Denoising for Robust Neural Operators Authors: Samrendra Roy, Souvik Chakraborty, Syed Bahauddin Alam Published: 2026-04-14 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2604.13316v1 Neural operators have emerged as fast surrogate models for physics simulations, yet they remain acutely vulnerable to adversarial perturbations, a critical liability for safety-critical digital twin deployments. We present a synergistic defense that combines active learning-based data generation with an input denoising architecture. The active learning component adaptively probes model weaknesses using differential evolution attacks, then generates targeted training data at discovered vulnerability locations while an adaptive smooth-ratio safeguard preserves baseline accuracy. The input denoising component augments the operator architecture with a learnable bottleneck that filters adversarial noise while retaining physics-relevant features. On the viscous Burgers' equation benchmark, the combined approach achieves a 2.04% combined error (1.21% baseline + 0.83% robustness), representing an 87% reduction relative to standard training (15.42% combined) and outperforming both active learning alone (3.42%) and input denoising alone (5.22%). More broadly, our results, combined with cross-architecture vulnerability analysis from prior work, suggest that optimal training data for neural operators is architecture-dependent: because different architectures concentrate sensitivity in distinct input subspaces, uniform sampling cannot adequately cover the vulnerability landscape of all models. These findings have potential implications for the deployment of neural operators in safety-critical energy systems including nuclear reactor monitoring. --- ### The Spectrascapes Dataset: Street-view imagery beyond the visible captured using a mobile platform Authors: Akshit Gupta, Joris Timmermans, Filip Biljecki, Remko Uijlenhoet Published: 2026-04-14 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2604.13315v2 High-resolution data in spatial and temporal contexts is imperative for developing climate resilient cities. Current datasets for monitoring urban parameters are developed primarily using manual inspections, embedded-sensing, remote sensing, or standard street-view imagery (RGB). These methods and datasets are often constrained respectively by poor scalability, inconsistent spatio-temporal resolutions, overhead views or low spectral information. We present a novel method and its open implementation: a multi-spectral terrestrial-view dataset that circumvents these limitations. This dataset consists of 17,718 street level multi-spectral images captured with RGB, Near-infrared, and Thermal imaging sensors on bikes, across diverse urban morphologies (village, town, small city, and big urban area) in the Netherlands. Strict emphasis is put on data calibration and quality while also providing the details of our data collection methodology (including the hardware and software details). To the best of our knowledge, Spectrascapes is the first open-access dataset of its kind. Finally, we demonstrate two downstream use-cases enabled using this dataset and provide potential research directions in the machine learning, urban planning and remote sensing domains. --- ### Concrete Jungle: Towards Concreteness Paved Contrastive Negative Mining for Compositional Understanding Authors: Eun Woo Im, Dhruv Madhwal, Vivek Gupta Published: 2026-04-14 Categories: cs.LG arXiv: https://arxiv.org/abs/2604.13313v1 Vision-Language Models demonstrate remarkable capabilities but often struggle with compositional reasoning, exhibiting vulnerabilities regarding word order and attribute binding. This limitation arises from a scarcity of informative samples needed to differentiate subtle semantic variations during contrastive pretraining. Although hard negative mining offers a promising remedy, existing methods lack explicit mechanisms to dictate which linguistic elements undergo modification. Instead of engineering generative architectures, this study establishes lexical concreteness as a fundamental determinant of negative sample efficacy. Modifying highly concrete terms generates more pronounced structural and visual discrepancies, providing a substantially stronger learning signal. Leveraging this principle, ConcretePlant is proposed to systematically isolate and manipulate perceptually grounded concepts. Analyses of the InfoNCE further reveals a severe gradient imbalance, where easily distinguishable pairs disproportionately overwhelm the optimization process and restrict the bandwidth available for nuanced learning. To resolve this degradation, the Cement loss is formulated utilizing a margin-based approach. By correlating psycholinguistic scores with sample difficulty, this objective dynamically calibrates the penalization applied to individual training pairs. Comprehensive evaluations substantiate these theoretical claims. The integrated framework, designated as Slipform, achieves state-of-the-art accuracy across diverse compositional evaluation benchmarks, general cross-modal retrieval, single and multi label linear probing. --- ### Deep Spatially-Regularized and Superpixel-Based Diffusion Learning for Unsupervised Hyperspectral Image Clustering Authors: Vutichart Buranasiri, James M. Murphy Published: 2026-04-14 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2604.13307v1 An unsupervised framework for hyperspectral image (HSI) clustering is proposed that incorporates masked deep representation learning with diffusion-based clustering, extending the Spatially-Regularized Superpixel-based Diffusion Learning ($S^2DL$) algorithm. Initially, a denoised latent representation of the original HSI is learned via an unsupervised masked autoencoder (UMAE) model with a Vision Transformer backbone. The UMAE takes spatial context and long-range spectral correlations into account and incorporates an efficient pretraining process via masking that utilizes only a small subset of training pixels. In the next stage, the entropy rate superpixel (ERS) algorithm is used to segment the image into superpixels, and a spatially regularized diffusion graph is constructed using Euclidean and diffusion distances within the compressed latent space instead of the HSI space. The proposed algorithm, Deep Spatially-Regularized Superpixel-based Diffusion Learning ($DS^2DL$), leverages more faithful diffusion distances and subsequent diffusion graph construction that better reflect the intrinsic geometry of the underlying data manifold, improving labeling accuracy and clustering quality. Experiments on Botswana and KSC datasets demonstrate the efficacy of $DS^2DL$. --- ### Bias at the End of the Score Authors: Salma Abdel Magid, Grace Guo, Esin Tureci, Amaya Dharmasiri, Vikram V. Ramaswamy, Hanspeter Pfister, Olga Russakovsky Published: 2026-04-14 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.13305v1 Reward models (RMs) are inherently non-neutral value functions designed and trained to encode specific objectives, such as human preferences or text-image alignment. RMs have become crucial components of text-to-image (T2I) generation systems where they are used at various stages for dataset filtering, as evaluation metrics, as a supervisory signal during optimization of parameters, and for post-generation safety and quality filtering of T2I outputs. While specific problems with the integration of RMs into the T2I pipeline have been studied (e.g. reward hacking or mode collapse), their robustness and fairness as scoring functions remains largely unknown. We conduct a large scale audit of RM robustness with respect to demographic biases during T2I model training and generation. We provide quantitative and qualitative evidence that while originally developed as quality measures, RMs encode demographic biases, which cause reward-guided optimization to disproportionately sexualize female image subjects reinforce gender/racial stereotypes, and collapse demographic diversity. These findings highlight shortcomings in current reward models, challenge their reliability as quality metrics, and underscore the need for improved data collection and training procedures to enable more robust scoring. --- ### Can Cross-Layer Transcoders Replace Vision Transformer Activations? An Interpretable Perspective on Vision Authors: Gerasimos Chatzoudis, Konstantinos D. Polyzos, Zhuowei Li, Difei Gu, Gemma E. Moran, Hao Wang, Dimitris N. Metaxas Published: 2026-04-14 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2604.13304v1 Understanding the internal activations of Vision Transformers (ViTs) is critical for building interpretable and trustworthy models. While Sparse Autoencoders (SAEs) have been used to extract human-interpretable features, they operate on individual layers and fail to capture the cross-layer computational structure of Transformers, as well as the relative significance of each layer in forming the last-layer representation. Alternatively, we introduce the adoption of Cross-Layer Transcoders (CLTs) as reliable, sparse, and depth-aware proxy models for MLP blocks in ViTs. CLTs use an encoder-decoder scheme to reconstruct each post-MLP activation from learned sparse embeddings of preceding layers, yielding a linear decomposition that transforms the final representation of ViTs from an opaque embedding into an additive, layer-resolved construction that enables faithful attribution and process-level interpretability. We train CLTs on CLIP ViT-B/32 and ViT-B/16 across CIFAR-100, COCO, and ImageNet-100. We show that CLTs achieve high reconstruction fidelity with post-MLP activations while preserving and even improving, in some cases, CLIP zero-shot classification accuracy. In terms of interpretability, we show that the cross-layer contribution scores provide faithful attribution, revealing that the final representation is concentrated in a smaller set of dominant layer-wise terms whose removal degrades performance and whose retention largely preserves it. These results showcase the significance of adopting CLTs as an alternative interpretable proxy of ViTs in the vision domain. --- ### Honeypot Protocol Authors: Najmul Hasan Published: 2026-04-14 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2604.13301v1 Trusted monitoring, the standard defense in AI control, is vulnerable to adaptive attacks, collusion, and strategic attack selection. All of these exploit the fact that monitoring is passive: it observes model behavior but never probes whether the model would behave differently under different perceived conditions. We introduce the honeypot protocol, which tests for context-dependent behavior by varying only the system prompt across three conditions (evaluation, synthetic deployment, explicit no-monitoring) while holding the task, environment, and scoring identical. We evaluate Claude Opus 4.6 in BashArena across all three conditions in both honest and attack modes. The model achieved 100% main task success and triggered zero side tasks uniformly across conditions, providing a baseline for future comparisons with stronger attack policies and additional models. ---