# Research Papers — 2026-04 · bundle page 161 of 233 > Full-text markdown of papers #8001–8050 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/161 [← Previous bundle](https://aipod.dev/papers/archive/2026-04/page/160.md) [Next bundle →](https://aipod.dev/papers/archive/2026-04/page/162.md) ### Adam-HNAG: A Convergent Reformulation of Adam with Accelerated Rate Authors: Yaxin Yu, Long Chen, Zeyi Xu Published: 2026-04-09 Categories: math.OC, cs.LG arXiv: https://arxiv.org/abs/2604.08742v1 Adam has achieved strong empirical success, but its theory remains incomplete even in the deterministic full-batch setting, largely because adaptive preconditioning and momentum are tightly coupled. In this work, a convergent reformulation of full-batch Adam is developed by combining variable and operator splitting with a curvature-aware gradient correction. This leads to a continuous-time Adam-HNAG flow with an exponentially decaying Lyapunov function, as well as two discrete methods: Adam-HNAG, and Adam-HNAG-s, a synchronous variant closer in form to Adam. Within a unified Lyapunov analysis framework, convergence guarantees are established for both methods in the convex smooth setting, including accelerated convergence. Numerical experiments support the theory and illustrate the different empirical behavior of the two discretizations. To the best of our knowledge, this provides the first convergence proof for Adam-type methods in convex optimization. --- ### LPLCv2: An Expanded Dataset for Fine-Grained License Plate Legibility Classification Authors: Lucas Wojcik, Eduardo A. F. Machoski, Eduil Nascimento, Rayson Laroca, David Menotti Published: 2026-04-09 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.08741v1 Modern Automatic License Plate Recognition (ALPR) systems achieve outstanding performance in controlled, well-defined scenarios. However, large-scale real-world usage remains challenging due to low-quality imaging devices, compression artifacts, and suboptimal camera installation. Identifying illegible license plates (LPs) has recently become feasible through a dedicated benchmark; however, its impact has been limited by its small size and annotation errors. In this work, we expand the original benchmark to over three times the size with two extra capture days, revise its annotations and introduce novel labels. LP-level annotations include bounding boxes, text, and legibility level, while vehicle-level annotations comprise make, model, type, and color. Image-level annotations feature camera identity, capture conditions (e.g., rain and faulty cameras), acquisition time, and day ID. We present a novel training procedure featuring an Exponential Moving Average-based loss function and a refined learning rate scheduler, addressing common mistakes in testing. These improvements enable a baseline model to achieve an 89.5% F1-score on the test set, considerably surpassing the previous state of the art. We further introduce a novel protocol to explicitly addresses camera contamination between training and evaluation splits, where results show a small impact. Dataset and code are publicly available at https://github.com/lmlwojcik/LPLCv2-Dataset. --- ### RansomTrack: A Hybrid Behavioral Analysis Framework for Ransomware Detection Authors: Busra Caliskan, Ibrahim Gulatas, H. Hakan Kilinc, A. Halim Zaim Published: 2026-04-09 Categories: cs.CR, cs.LG arXiv: https://arxiv.org/abs/2604.08739v1 Ransomware poses a serious and fast-acting threat to critical systems, often encrypting files within seconds of execution. Research indicates that ransomware is the most reported cybercrime in terms of financial damage, highlighting the urgent need for early-stage detection before encryption is complete. In this paper, we present RansomTrack, a hybrid behavioral analysis framework to eliminate the limitations of using static and dynamic detection methods separately. Static features are extracted using the Radare2 sandbox, while dynamic behaviors such as memory protection changes, mutex creation, registry access and network activity are obtained using the Frida toolkit. Our dataset of 165 different ransomware and benign software families is publicly released, offering the highest family-to-sample ratio known in the literature. Experimental evaluation using machine learning models shows that ensemble classifiers such as XGBoost and Soft Voting achieve up to 96% accuracy and a ROC-AUC score of 0.99. Each sample analyzed in 9.1 seconds includes modular behavioral logging, runtime instrumentation, and SHAP-based interpretability to highlight the most influential features. Additionally, RansomTrack framework is able to detect ransomware under 9.2 seconds. Overall, RansomTrack offers a scalable, low-latency, and explainable solution for real-time ransomware detection. --- ### Wireless Communication Enhanced Value Decomposition for Multi-Agent Reinforcement Learning Authors: Diyi Hu, Bhaskar Krishnamachari Published: 2026-04-09 Categories: cs.LG arXiv: https://arxiv.org/abs/2604.08728v1 Cooperation in multi-agent reinforcement learning (MARL) benefits from inter-agent communication, yet most approaches assume idealized channels and existing value decomposition methods ignore who successfully shared information with whom. We propose CLOVER, a cooperative MARL framework whose centralized value mixer is conditioned on the communication graph realized under a realistic wireless channel. This graph introduces a relational inductive bias into value decomposition, constraining how individual utilities are mixed based on the realized communication structure. The mixer is a GNN with node-specific weights generated by a Permutation-Equivariant Hypernetwork: multi-hop propagation along communication edges reshapes credit assignment so that different topologies induce different mixing. We prove this mixer is permutation invariant, monotonic (preserving the IGM condition), and strictly more expressive than QMIX-style mixers. To handle realistic channels, we formulate an augmented MDP isolating stochastic channel effects from the agent computation graph, and employ a stochastic receptive field encoder for variable-size message sets, enabling end-to-end differentiable training. On Predator-Prey and Lumberjacks benchmarks under p-CSMA wireless channels, CLOVER consistently improves convergence speed and final performance over VDN, QMIX, TarMAC+VDN, and TarMAC+QMIX. Behavioral analysis confirms agents learn adaptive signaling and listening strategies, and ablations isolate the communication-graph inductive bias as the key source of improvement. --- ### Decomposing the Delta: What Do Models Actually Learn from Preference Pairs? Authors: Chia-Hsuan Lee, Mingyang Zhou, Renkun Ni, Zelei Cheng, Sihui Dai, Supriyo Chakraborty, Shixiong Zhang, Sambit Sahu, William Campbell Published: 2026-04-09 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2604.08723v1 Preference optimization methods such as DPO and KTO are widely used for aligning language models, yet little is understood about what properties of preference data drive downstream reasoning gains. We ask: what aspects of a preference pair improve a reasoning model's performance on general reasoning tasks? We investigate two distinct notions of quality delta in preference data: generator-level delta, arising from the differences in capability between models that generate chosen and rejected reasoning traces, and sample-level delta, arising from differences in judged quality differences within an individual preference pair. To study generator-level delta, we vary the generator's scale and model family, and to study sample-level delta, we employ an LLM-as-a-judge to rate the quality of generated traces along multiple reasoning-quality dimensions. We find that increasing generator-level delta steadily improves performance on out-of-domain reasoning tasks and filtering data by sample-level delta can enable more data-efficient training. Our results suggest a twofold recipe for improving reasoning performance through preference optimization: maximize generator-level delta when constructing preference pairs and exploit sample-level delta to select the most informative training examples. --- ### AI Driven Soccer Analysis Using Computer Vision Authors: Adrian Manchado, Tanner Cellio, Jonathan Keane, Yiyang Wang Published: 2026-04-09 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2604.08722v1 Sport analysis is crucial for team performance since it provides actionable data that can inform coaching decisions, improve player performance, and enhance team strategies. To analyze more complex features from game footage, a computer vision model can be used to identify and track key entities from the field. We propose the use of an object detection and tracking system to predict player positioning throughout the game. To translate this to positioning in relation to the field dimensions, we use a point prediction model to identify key points on the field and combine these with known field dimensions to extract actual distances. For the player-identification model, object detection models like YOLO and Faster R-CNN are evaluated on the accuracy of our custom video footage using multiple different evaluation metrics. The goal is to identify the best model for object identification to obtain the most accurate results when paired with SAM2 (Segment Anything Model 2) for segmentation and tracking. For the key point detection model, we use a CNN model to find consistent locations in the soccer field. Through homography, the positions of points and objects in the camera perspective will be transformed to a real-ground perspective. The segmented player masks from SAM2 are transformed from camera perspective to real-world field coordinates through homography, regardless of camera angle or movement. The transformed real-world coordinates can be used to calculate valuable tactical insights including player speed, distance covered, positioning heatmaps, and more complex team statistics, providing coaches and players with actionable performance data previously unavailable from standard video analysis. --- ### Demystifying the Silence of Correctness Bugs in PyTorch Compiler Authors: Meiziniu Li, Dongze Li, Jianmeng Liu, Shing-Chi Cheung Published: 2026-04-09 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2604.08720v1 Performance optimization of AI infrastructure is key to the fast adoption of large language models (LLMs). The PyTorch compiler (torch.compile), a core optimization tool for deep learning (DL) models (including LLMs), has received due attention. However, torch.compile is prone to correctness bugs, which cause incorrect outputs of compiled DL models without triggering exceptions, crashes, or warnings. These bugs pose a serious threat to the reliability of downstream LLM applications. Data from the PyTorch community shows that 19.2% of high-priority issues are incorrect outputs of compiled DL models induced by torch.compile bugs, the second-most-common bug category (only behind program crashes at 19.57%). However, no systematic study has been conducted to specifically characterize and thereby detect these bugs. In this paper, we present the first empirical study of the correctness bugs in torch.compile, examine their characteristics, and assess the effectiveness of existing fuzzers in detecting them. Based on our findings, we propose a proof-of-concept testing technique named AlignGuard, tailored specifically for detecting correctness bugs in torch.compile. AlignGuard incorporates bug characteristics distilled from our empirical study, applying LLM-based test mutation to existing test cases for correctness bug detection. At the time of writing, AlignGuard has successfully detected 23 new correctness bugs in recent torch.compile. All these bugs have been confirmed or fixed by the PyTorch development team, and over half (14/23) of them are even marked as high-priority bugs, underscoring the usefulness of our technique. --- ### LMGenDrive: Bridging Multimodal Understanding and Generative World Modeling for End-to-End Driving Authors: Hao Shao, Letian Wang, Yang Zhou, Yuxuan Hu, Zhuofan Zong, Steven L. Waslander, Wei Zhan, Hongsheng Li Published: 2026-04-09 Categories: cs.CV, cs.AI, cs.RO arXiv: https://arxiv.org/abs/2604.08719v1 Recent years have seen remarkable progress in autonomous driving, yet generalization to long-tail and open-world scenarios remains a major bottleneck for large-scale deployment. To address this challenge, some works use LLMs and VLMs for vision-language understanding and reasoning, enabling vehicles to interpret rare and safety-critical situations when generating actions. Others study generative world models to capture the spatio-temporal evolution of driving scenes, allowing agents to imagine possible futures before acting. Inspired by human intelligence, which unifies understanding and imagination, we explore a unified model for autonomous driving. We present LMGenDrive, the first framework that combines LLM-based multimodal understanding with generative world models for end-to-end closed-loop driving. Given multi-view camera inputs and natural-language instructions, LMGenDrive generates both future driving videos and control signals. This design provides complementary benefits: video prediction improves spatio-temporal scene modeling, while the LLM contributes strong semantic priors and instruction grounding from large-scale pretraining. We further propose a progressive three-stage training strategy, from vision pretraining to multi-step long-horizon driving, to improve stability and performance. LMGenDrive supports both low-latency online planning and autoregressive offline video generation. Experiments show that it significantly outperforms prior methods on challenging closed-loop benchmarks, with clear gains in instruction following, spatio-temporal understanding, and robustness to rare scenarios. These results suggest that unifying multimodal understanding and generation is a promising direction for more generalizable and robust embodied decision-making systems. --- ### Accelerating Transformer-Based Monocular SLAM via Geometric Utility Scoring Authors: Xinmiao Xiong, Bangya Liu, Hao Wang, Dayou Li, Nuo Chen, Andrew Feng, Mingyu Ding, Suman Banerjee, Yang Zhou, Zhiwen Fan Published: 2026-04-09 Categories: cs.CV, cs.AI, cs.RO arXiv: https://arxiv.org/abs/2604.08718v2 Geometric Foundation Models (GFMs) have recently advanced monocular SLAM by providing robust, calibration-free 3D priors. However, deploying these models on dense video streams introduces significant computational redundancy. Current GFM-based SLAM systems typically rely on post hoc keyframe selection. Because of this, they must perform expensive dense geometric decoding simply to determine whether a frame contains novel geometry, resulting in late rejection and wasted computation. To mitigate this inefficiency, we propose LeanGate, a lightweight feed-forward frame-gating network. LeanGate predicts a geometric utility score to assess a frame's mapping value prior to the heavy GFM feature extraction and matching stages. As a predictive plug-and-play module, our approach bypasses over 90% of redundant frames. Evaluations on standard SLAM benchmarks demonstrate that LeanGate reduces tracking FLOPs by more than 85% and achieves a 5x end-to-end throughput speedup. Furthermore, it maintains the tracking and mapping accuracy of dense baselines. Project page: https://lean-gate.github.io/ --- ### What Matters in Virtual Try-Off? Dual-UNet Diffusion Model For Garment Reconstruction Authors: Loc-Phat Truong, Meysam Madadi, Sergio Escalera Published: 2026-04-09 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.08716v1 Virtual Try-On (VTON) has seen rapid advancements, providing a strong foundation for generative fashion tasks. However, the inverse problem, Virtual Try-Off (VTOFF)-aimed at reconstructing the canonical garment from a draped-on image-remains a less understood domain, distinct from the heavily researched field of VTON. In this work, we seek to establish a robust architectural foundation for VTOFF by studying and adapting various diffusion-based strategies from VTON and general Latent Diffusion Models (LDMs). We focus our investigation on the Dual-UNet Diffusion Model architecture and analyze three axes of design: (i) Generation Backbone: comparing Stable Diffusion variants; (ii) Conditioning: ablating different mask designs, masked/unmasked inputs for image conditioning, and the utility of high-level semantic features; and (iii) Losses and Training Strategies: evaluating the impact of the auxiliary attention-based loss, perceptual objectives and multi-stage curriculum schedules. Extensive experiments reveal trade-offs across various configuration options. Evaluated on VITON-HD and DressCode datasets, our framework achieves state-of-the-art performance with a drop of 9.5\% on the primary metric DISTS and competitive performance on LPIPS, FID, KID, and SSIM, providing both stronger baselines and insights to guide future Virtual Try-Off research. --- ### Model Space Reasoning as Search in Feedback Space for Planning Domain Generation Authors: James Oswald, Daniel Obolensky, Volodymyr Varha, Vasilije Dragovic, Kavitha Srinivas, Harsha Kokel, Michael Katz, Shirin Sohrabi Published: 2026-04-09 Categories: cs.AI arXiv: https://arxiv.org/abs/2604.08712v3 The generation of planning domains from natural language descriptions remains an open problem even with the advent of large language models and reasoning models. Recent work suggests that while LLMs have the ability to assist with domain generation, they are still far from producing high quality domains that can be deployed in practice. To this end, we investigate the ability of an agentic language model feedback framework to generate planning domains from natural language descriptions that have been augmented with a minimal amount of symbolic information. In particular, we evaluate the quality of the generated domains under various forms of symbolic feedback, including landmarks, and output from the VAL plan validator. Using these feedback mechanisms, we experiment using heuristic search over model space to optimize domain quality. --- ### Deep Learning-Based Tracking and Lineage Reconstruction of Ligament Breakup Authors: Vrushank Ahire, Vivek Kurumanghat, Mudasir Ganaie, Lipika Kabiraj Published: 2026-04-09 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2604.08711v1 The disintegration of liquid sheets into ligaments and droplets involves highly transient, multi-scale dynamics that are difficult to quantify from high-speed shadowgraphy images. Identifying droplets, ligaments, and blobs formed during breakup, along with tracking across frames, is essential for spray analysis. However, conventional multi-object tracking frameworks impose strict one-to-one temporal associations and cannot represent one-to-many fragmentation events. In this study, we present a two-stage deep learning framework for object detection and temporal relationship modeling across frames. The framework captures ligament deformation, fragmentation, and parent-child lineage during liquid sheet disintegration. In the first stage, a Faster R-CNN with a ResNet-50 backbone and Feature Pyramid Network detects and classifies ligaments and droplets in high-speed shadowgraphy recordings of an impinging Carbopol gel jet. A morphology-preserving synthetic data generation strategy augments the training set without introducing physically implausible configurations, achieving a held-out F1 score of up to 0.872 across fourteen original-to-synthetic configurations. In the second stage, a Transformer-augmented multilayer perceptron classifies inter-frame associations into continuation, fragmentation (one-to-many), and non-association using physics-informed geometric features. Despite severe class imbalance, the model achieves 86.1% accuracy, 93.2% precision, and perfect recall (1.00) for fragmentation events. Together, the framework enables automated reconstruction of fragmentation trees, preservation of parent-child lineage, and extraction of breakup statistics such as fragment multiplicity and droplet size distributions. By explicitly identifying children droplets formed from ligament fragmentation, the framework provides automated analysis of the primary atomization mode. --- ### Every Response Counts: Quantifying Uncertainty of LLM-based Multi-Agent Systems through Tensor Decomposition Authors: Tiejin Chen, Huaiyuan Yao, Jia Chen, Evangelos E. Papalexakis, Hua Wei Published: 2026-04-09 Categories: cs.LG, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2604.08708v1 While Large Language Model-based Multi-Agent Systems (MAS) consistently outperform single-agent systems on complex tasks, their intricate interactions introduce critical reliability challenges arising from communication dynamics and role dependencies. Existing Uncertainty Quantification methods, typically designed for single-turn outputs, fail to address the unique complexities of the MAS. Specifically, these methods struggle with three distinct challenges: the cascading uncertainty in multi-step reasoning, the variability of inter-agent communication paths, and the diversity of communication topologies. To bridge this gap, we introduce MATU, a novel framework that quantifies uncertainty through tensor decomposition. MATU moves beyond analyzing final text outputs by representing entire reasoning trajectories as embedding matrices and organizing multiple execution runs into a higher-order tensor. By applying tensor decomposition, we disentangle and quantify distinct sources of uncertainty, offering a comprehensive reliability measure that is generalizable across different agent structures. We provide comprehensive experiments to show that MATU effectively estimates holistic and robust uncertainty across diverse tasks and communication topologies. --- ### Parameterized Complexity Of Representing Models Of MSO Formulas Authors: Petr Kučera, Petr Martinek Published: 2026-04-09 Categories: cs.AI, cs.CC arXiv: https://arxiv.org/abs/2604.08707v1 Monadic second order logic (MSO2) plays an important role in parameterized complexity due to the Courcelle's theorem. This theorem states that the problem of checking if a given graph has a property specified by a given MSO2 formula can be solved by a parameterized linear time algorithm with respect to the treewidth of the graph and the size of the formula. We extend this result by showing that models of MSO2 formula with free variables can be represented with a decision diagram whose size is parameterized linear in the above mentioned parameter. In particular, we show a parameterized linear upper bound on the size of a sentential decision diagram (SDD) when treewidth is considered and a parameterized linear upper bound on the size of an ordered binary decision diagram (OBDD) when considering the pathwidth in the parameter. In addition, building on a lower bound on the size of OBDD by Razgon (2014), we show that there is an MSO2 formula and a class of graphs with bounded treewidth which do not admit an OBDD with the size parameterized by the treewidth. Our result offers a new perspective on the Courcelle's theorem and connects it to the area of knowledge representation. --- ### Efficient RL Training for LLMs with Experience Replay Authors: Charles Arnal, Vivien Cabannes, Taco Cohen, Julia Kempe, Remi Munos Published: 2026-04-09 Categories: cs.LG arXiv: https://arxiv.org/abs/2604.08706v1 While Experience Replay - the practice of storing rollouts and reusing them multiple times during training - is a foundational technique in general RL, it remains largely unexplored in LLM post-training due to the prevailing belief that fresh, on-policy data is essential for high performance. In this work, we challenge this assumption. We present a systematic study of replay buffers for LLM post-training, formalizing the optimal design as a trade-off between staleness-induced variance, sample diversity and the high computational cost of generation. We show that strict on-policy sampling is suboptimal when generation is expensive. Empirically, we show that a well-designed replay buffer can drastically reduce inference compute without degrading - and in some cases even improving - final model performance, while preserving policy entropy. --- ### RS-OVC: Open-Vocabulary Counting for Remote-Sensing Data Authors: Tamir Shor, George Leifman, Genady Beryozkin Published: 2026-04-09 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.08704v1 Object-Counting for remote-sensing (RS) imagery is attracting increasing research interest due to its crucial role in a wide and diverse set of applications. While several promising methods for RS object-counting have been proposed, existing methods focus on a closed, pre-defined set of object classes. This limitation necessitates costly re-annotation and model re-training to adapt current approaches for counting of novel objects that have not been seen during training, and severely inhibits their application in dynamic, real-world monitoring scenarios. To address this gap, in this work we propose RS-OVC - the first Open Vocabulary Counting (OVC) model for Remote-Sensing and aerial imagery. We show that our model is capable of accurate counting of novel object classes, that were unseen during training, based solely on textual and/or visual conditioning. --- ### QoS-QoE Translation with Large Language Model Authors: Yingjie Yu, Mingyuan Wu, Ahmadreza Eslaminia, Lingzhi Zhao, Kaizhuo Yan, Klara Nahrstedt Published: 2026-04-09 Categories: cs.MM, cs.DB, cs.LG arXiv: https://arxiv.org/abs/2604.08703v1 QoS-QoE translation is a fundamental problem in multimedia systems because it characterizes how measurable system and network conditions affect user-perceived experience. Although many prior studies have examined this relationship, their findings are often developed for specific setups and remain scattered across papers, experimental settings, and reporting formats, limiting systematic reuse, cross-scenario generalization, and large-scale analysis. To address this gap, we first introduce QoS-QoE Translation dataset, a source-grounded dataset of structured QoS-QoE relationships from the multimedia literature, with a focus on video streaming related tasks. We construct the dataset through an automated pipeline that combines paper curation, QoS-QoE relationship extraction, and iterative data evaluation. Each record preserves the extracted relationship together with parameter definitions, supporting evidence, and contextual metadata. We further evaluate the capability of large language models (LLMs) on QoS-QoE translation, both before and after supervised fine-tuning on our dataset, and show strong performance on both continuous-value and discrete-label prediction in bidirectional translation, from QoS-QoE and QoE-QoS. Our dataset provides a foundation for benchmarking LLMs in QoS-QoE translation and for supporting future LLM-based reasoning for multimedia quality prediction and optimization. The complete dataset and code are publicly available at https://yyu6969.github.io/qos-qoe-translation-page/, for full reproducibility and open access. --- ### Unified Multimodal Uncertain Inference Authors: Dengjia Zhang, Alexander Martin, William Jurayj, Kenton Murray, Benjamin Van Durme, Reno Kriz Published: 2026-04-09 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2604.08701v3 We introduce Unified Multimodal Uncertain Inference (UMUI), a multimodal inference task spanning text, audio, and video, where models must produce calibrated probability estimates of hypotheses conditioned on a premise in any modality or combination. While uncertain inference has been explored in text, extension to other modalities has been limited to single-modality binary entailment judgments, leaving no framework for fine-grained probabilistic reasoning in or across other modalities. To address this, we curate a human-annotated evaluation set with scalar probability judgments across audio, visual, and audiovisual settings, and additionally evaluate on existing text and audio benchmarks. We introduce CLUE (Calibrated Latent Uncertainty Estimation), which combines self-consistent teacher calibration and distribution-based confidence probing to produce calibrated predictions. We demonstrate that our 3B-parameter model achieves equivalent or stronger performance than zero-shot baselines up to 32B parameters across all modalities. --- ### Unified Multimodal Uncertain Inference Authors: Dengjia Zhang, Alexander Martin, William Jurayj, Kenton Murray, Benjamin Van Durme, Reno Kriz Published: 2026-04-09 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2604.08701v2 We introduce Unified Multimodal Uncertain Inference (UMUI), a multimodal inference task spanning text, audio, and video, where models must produce calibrated probability estimates of hypotheses conditioned on a premise in any modality or combination. While uncertain inference has been explored in text, extension to other modalities has been limited to single-modality binary entailment judgments, leaving no framework for fine-grained probabilistic reasoning in or across other modalities. To address this, we curate a human-annotated evaluation set with scalar probability judgments across audio, visual, and audiovisual settings, and additionally evaluate on existing text and audio benchmarks. We introduce CLUE (Calibrated Latent Uncertainty Estimation), which combines self-consistent teacher calibration and distribution-based confidence probing to produce calibrated predictions. We demonstrate that our 3B-parameter model achieves equivalent or stronger performance than baselines up to 32B parameters across all modalities. --- ### EvoLen: Evolution-Guided Tokenization for DNA Language Model Authors: Nan Huang, Xiaoxiao Zhou, Junxia Cui, Mario Tapia-Pacheco, Tiffany Amariuta, Yang Li, Jingbo Shang Published: 2026-04-09 Categories: cs.LG, q-bio.GN arXiv: https://arxiv.org/abs/2604.08698v3 Tokens serve as the basic units of representation in DNA language models (DNALMs), yet their design remains underexplored. Unlike natural language, DNA lacks inherent token boundaries or predefined compositional rules, making tokenization a fundamental modeling decision rather than a naturally specified one. While existing approaches like byte-pair encoding (BPE) excel at capturing token structures that reflect human-generated linguistic regularities, DNA is organized by biological function and evolutionary constraint rather than linguistic convention. We argue that DNA tokenization should prioritize functional sequence patterns like regulatory motifs-short, recurring segments under evolutionary constraint and typically preserved across species. We incorporate evolutionary information directly into the tokenization process through EvoLen, a tokenizer that combines evolutionary stratification with length-aware decoding to better preserve motif-scale functional sequence units. EvoLen uses cross-species evolutionary signals to group DNA sequences, trains separate BPE tokenizers on each group, merges the resulting vocabularies via a rule prioritizing preserved patterns, and applies length-aware decoding with dynamic programming. Through controlled experiments, EvoLen improves the preservation of functional sequence patterns, differentiation across genomic contexts, and alignment with evolutionary constraint, while matching or outperforming standard BPE across diverse DNALM benchmarks. These results demonstrate that tokenization introduces a critical inductive bias and that incorporating evolutionary information yields more biologically meaningful and interpretable sequence representations. Code, pretrained and fine-tuned checkpoints, and tokenizer files are available at https://github.com/HN020719/EvoLen and https://huggingface.co/EvoLenTokenizer. --- ### EvoLen: Evolution-Guided Tokenization for DNA Language Model Authors: Nan Huang, Xiaoxiao Zhou, Junxia Cui, Mario Tapia-Pacheco, Tiffany Amariuta, Yang Li, Jingbo Shang Published: 2026-04-09 Categories: cs.LG, q-bio.GN arXiv: https://arxiv.org/abs/2604.08698v1 Tokens serve as the basic units of representation in DNA language models (DNALMs), yet their design remains underexplored. Unlike natural language, DNA lacks inherent token boundaries or predefined compositional rules, making tokenization a fundamental modeling decision rather than a naturally specified one. While existing approaches like byte-pair encoding (BPE) excel at capturing token structures that reflect human-generated linguistic regularities, DNA is organized by biological function and evolutionary constraint rather than linguistic convention. We argue that DNA tokenization should prioritize functional sequence patterns like regulatory motifs-short, recurring segments under evolutionary constraint and typically preserved across species. We incorporate evolutionary information directly into the tokenization process through EvoLen, a tokenizer that combines evolutionary stratification with length-aware decoding to better preserve motif-scale functional sequence units. EvoLen uses cross-species evolutionary signals to group DNA sequences, trains separate BPE tokenizers on each group, merges the resulting vocabularies via a rule prioritizing preserved patterns, and applies length-aware decoding with dynamic programming. Through controlled experiments, EvoLen improves the preservation of functional sequence patterns, differentiation across genomic contexts, and alignment with evolutionary constraint, while matching or outperforming standard BPE across diverse DNALM benchmarks. These results demonstrate that tokenization introduces a critical inductive bias and that incorporating evolutionary information yields more biologically meaningful and interpretable sequence representations. --- ### EfficientSign: An Attention-Enhanced Lightweight Architecture for Indian Sign Language Recognition Authors: Rishabh Gupta, Shravya R. Nalla Published: 2026-04-09 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2604.08694v1 How do you build a sign language recognizer that works on a phone? That question drove this work. We built EfficientSign, a lightweight model which takes EfficientNet-B0 and focuses on two attention modules (Squeeze-and-Excitation for channel focus, and a spatial attention layer that focuses on the hand gestures). We tested it against five other approaches on 12,637 images of Indian Sign Language alphabets, all 26 classes, using 5-fold cross-validation. EfficientSign achieves the accuracy of 99.94% (+/-0.05%), which matches the performance of ResNet18's 99.97% accuracy, but with 62% fewer parameters (4.2M vs 11.2M). We also experimented with feeding deep features (1,280-dimensional vectors pulled from EfficientNet-B0's pooling layer) into classical classifiers. SVM achieved the accuracy of 99.63%, Logistic Regression achieved the accuracy of 99.03% and KNN achieved accuracy of 96.33%. All of these blow past the 92% that SURF-based methods managed on a similar dataset back in 2015. Our results show that attention-enhanced learning model provides an efficient and deployable solution for ISL recognition without requiring a massive model or hand-tuned feature pipelines anymore. --- ### Skip-Connected Policy Optimization for Implicit Advantage Authors: Fengwei Teng, Jinyi Bai, Xinhao Yao, Demi Ruohan Wang, Jiahao Zhao, Zhijiang Guo Published: 2026-04-09 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2604.08690v1 Group Relative Policy Optimization (GRPO) has proven effective in RLVR by using outcome-based rewards. While fine-grained dense rewards can theoretically improve performance, we reveal that under practical sampling budgets, Monte Carlo estimation yields high-variance and sign-inconsistent advantages for early reasoning tokens, paradoxically underperforming outcome-only GRPO. We propose Skip-Connected Optimization (SKPO), which decomposes reasoning into upstream and downstream phases: upstream receives dense rewards from downstream Monte Carlo sampling with single-stream optimization; downstream maintains group-relative optimization, where a skip connection concatenates the upstream segment with the original problem, enabling the model to leverage helpful upstream reasoning while preserving the freedom to bypass flawed reasoning through direct problem access. Experiments demonstrate improvements of 3.91% and 6.17% relative gains over the strongest baselines on Qwen2.5-Math-7B and Llama-3.2-3B respectively across mathematical benchmarks and out-of-domain tasks including general reasoning and code generation. Further analysis reveals an implicit advantage: SKPO generates trajectories with higher intermediate-step quality even when matched for final correctness. --- ### RAMP: Hybrid DRL for Online Learning of Numeric Action Models Authors: Yarin Benyamin, Argaman Mordoch, Shahaf S. Shperberg, Roni Stern Published: 2026-04-09 Categories: cs.AI arXiv: https://arxiv.org/abs/2604.08685v1 Automated planning algorithms require an action model specifying the preconditions and effects of each action, but obtaining such a model is often hard. Learning action models from observations is feasible, but existing algorithms for numeric domains are offline, requiring expert traces as input. We propose the Reinforcement learning, Action Model learning, and Planning (RAMP) strategy for learning numeric planning action models online via interactions with the environment. RAMP simultaneously trains a Deep Reinforcement Learning (DRL) policy, learns a numeric action model from past interactions, and uses that model to plan future actions when possible. These components form a positive feedback loop: the RL policy gathers data to refine the action model, while the planner generates plans to continue training the RL policy. To facilitate this integration of RL and numeric planning, we developed Numeric PDDLGym, an automated framework for converting numeric planning problems to Gym environments. Experimental results on standard IPC numeric domains show that RAMP significantly outperforms PPO, a well-known DRL algorithm, in terms of solvability and plan quality. --- ### An Algorithm for Fast Assembling Large-Scale Defect-Free Atom Arrays Authors: Tao Zhang, Xiaodi Li, Hui Zhai, Linghui Chen Published: 2026-04-09 Categories: cond-mat.quant-gas, cs.LG, quant-ph arXiv: https://arxiv.org/abs/2604.08669v1 It is widely believed that tens of thousands of physical qubits are needed to build a practically useful quantum computer. Atom arrays formed by optical tweezers are among the most promising platforms for achieving this goal, owing to the excellent scalability and mobility of atomic qubits. However, assembling a defect-free atom array with ~ 10^4 qubits remains algorithmically challenging, alongside other hardware limitations. This is due to the computationally hard path-planning problems and the time-consuming generation of suffciently smooth trajectories for optical tweezer potentials by spatial light modulators (SLM). Here, we present a unified framework comprising two innovative components to fully address these algorithmic challenges: (1) a path-planning module that employs a supervised learning approach using a graph neural network combined with a modified auction decoder, and (2) a potential-generation module called the phase and profile-aware Weighted Gerchberg-Saxton algorithm. The inference time for the first module is nearly a size-independent constant overhead of ~ 5 ms, and the second module generates a potential frame with about 0.5 ms, a timescale shorter than the current commercial SLM refresh time. Altogether, our algorithm enables the assembly of an atom array with 10^4 qubits on a timescale much shorter than the typical vacuum lifetime of the trapped atoms. --- ### Geometry-Induced Long-Range Correlations in Recurrent Neural Network Quantum States Authors: Asif Bin Ayub, Amine Mohamed Aboussalah, Mohamed Hibat-Allah Published: 2026-04-09 Categories: quant-ph, cond-mat.dis-nn, cs.LG, physics.comp-ph arXiv: https://arxiv.org/abs/2604.08661v1 Neural Quantum States based on autoregressive recurrent neural network (RNN) wave functions enable efficient sampling without Markov-chain autocorrelation, but standard RNN architectures are biased toward finite-length correlations and can fail on states with long-range dependencies. A common response is to adopt transformer-style self-attention, but this typically comes with substantially higher computational and memory overhead. Here we introduce dilated RNN wave functions, where recurrent units access distant sites through dilated connections, injecting an explicit long-range inductive bias while retaining a favorable $\mathcal{O}(N \log N)$ forward pass scaling. We show analytically that dilation changes the correlation geometry and can induce power-law correlation scaling in a simplified linearized and perturbative setting. Numerically, for the critical 1D transverse-field Ising model, dilated RNNs reproduce the expected power-law connected two-point correlations in contrast to the exponential decay typical of conventional RNN ansätze. We further show that the dilated RNN accurately approximates the one-dimensional Cluster state, a paradigmatic example with long-range conditional correlations that has previously been reported to be challenging for RNN-based wave functions. These results highlight dilation as a simple geometric mechanism for building correlation-aware autoregressive neural quantum states. --- ### PRAGMA: Revolut Foundation Model Authors: Maxim Ostroukhov, Ruslan Mikhailov, Vladimir Iashin, Artem Sokolov, Andrei Akshonov, Vitaly Protasov, Andrey Goncharov, Dmitrii Beloborodov, Vince Mullin, Roman Yokunda Enzmann, Georgios Kolovos, Jason Renders et al. Published: 2026-04-09 Categories: cs.LG, cs.CE, cs.CL, cs.IR, q-fin.CP arXiv: https://arxiv.org/abs/2604.08649v2 Modern financial systems generate vast quantities of transactional and event-level data that encode rich economic signals. This paper presents PRAGMA, a family of foundation models for banking event sequences. Our approach pre-trains a Transformer-based architecture with masked modelling on a large-scale, heterogeneous banking event corpus using a self-supervised objective tailored to the discrete, variable-length nature of financial records. The resulting model supports a wide range of downstream tasks such as credit scoring, fraud detection, and lifetime value prediction: strong performance can be achieved by training a simple linear model on top of the extracted embeddings and can be further improved with lightweight fine-tuning. Through extensive evaluation on downstream tasks, we demonstrate that PRAGMA achieves superior performance across multiple domains directly from raw event sequences, providing a general-purpose representation layer for financial applications. --- ### PRAGMA: Revolut Foundation Model Authors: Maxim Ostroukhov, Ruslan Mikhailov, Vladimir Iashin, Artem Sokolov, Andrei Akshonov, Vitaly Protasov, Dmitrii Beloborodov, Vince Mullin, Roman Yokunda Enzmann, Georgios Kolovos, Jason Renders, Pavel Nesterov et al. Published: 2026-04-09 Categories: cs.LG, cs.CE, cs.CL, cs.IR, q-fin.CP arXiv: https://arxiv.org/abs/2604.08649v1 Modern financial systems generate vast quantities of transactional and event-level data that encode rich economic signals. This paper presents PRAGMA, a family of foundation models for multi-source banking event sequences. Our approach pre-trains a Transformer-based architecture with masked modelling on a large-scale, heterogeneous banking event corpus using a self-supervised objective tailored to the discrete, variable-length nature of financial records. The resulting model supports a wide range of downstream tasks such as credit scoring, fraud detection, and lifetime value prediction: strong performance can be achieved by training a simple linear model on top of the extracted embeddings and can be further improved with lightweight fine-tuning. Through extensive evaluation on downstream tasks, we demonstrate that PRAGMA achieves superior performance across multiple domains directly from raw event sequences, providing a general-purpose representation layer for financial applications. --- ### High-dimensional inference for the $γ$-ray sky with differentiable programming Authors: Siddharth Mishra-Sharma, Tracy R. Slatyer, Yitian Sun, Yuqing Wu Published: 2026-04-09 Categories: astro-ph.HE, astro-ph.IM, cs.LG, hep-ph arXiv: https://arxiv.org/abs/2604.08648v2 We motivate the use of differentiable probabilistic programming techniques in order to account for the large model-space inherent to astrophysical $γ$-ray analyses. Targeting the longstanding Galactic Center $γ$-ray Excess (GCE) puzzle, we construct differentiable forward model and likelihood that make liberal use of GPU acceleration and vectorization in order to simultaneously account for a continuum of possible spatial morphologies consistent with the GCE emission in a fully probabilistic manner. Our setup allows for efficient inference over the large model space using variational methods. Beyond application to $γ$-ray data, a goal of this work is to showcase how differentiable probabilistic programming can be used as a tool to enable flexible analyses of astrophysical datasets. --- ### InsEdit: Towards Instruction-based Visual Editing via Data-Efficient Video Diffusion Models Adaptation Authors: Zhefan Rao, Bin Zou, Haoxuan Che, Xuanhua He, Chong Hou Choi, Yanheng Li, Rui Liu, Qifeng Chen Published: 2026-04-09 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.08646v1 Instruction-based video editing is a natural way to control video content with text, but adapting a video generation model into an editor usually appears data-hungry. At the same time, high-quality video editing data remains scarce. In this paper, we show that a video generation backbone can become a strong video editor without large scale video editing data. We present InsEdit, an instruction-based editing model built on HunyuanVideo-1.5. InsEdit combines a visual editing architecture with a video data pipeline based on Mutual Context Attention (MCA), which creates aligned video pairs where edits can begin in the middle of a clip rather than only from the first frame. With only O(100)K video editing data, InsEdit achieves state-of-the-art results among open-source methods on our video instruction editing benchmarks. In addition, because our training recipe also includes image editing data, the final model supports image editing without any modification. --- ### 3D-VCD: Hallucination Mitigation in 3D-LLM Embodied Agents through Visual Contrastive Decoding Authors: Makanjuola Ogunleye, Eman Abdelrahman, Ismini Lourentzou Published: 2026-04-09 Categories: cs.CV, cs.AI, cs.LG, cs.RO arXiv: https://arxiv.org/abs/2604.08645v1 Large multimodal models are increasingly used as the reasoning core of embodied agents operating in 3D environments, yet they remain prone to hallucinations that can produce unsafe and ungrounded decisions. Existing inference-time hallucination mitigation methods largely target 2D vision-language settings and do not transfer to embodied 3D reasoning, where failures arise from object presence, spatial layout, and geometric grounding rather than pixel-level inconsistencies. We introduce 3D-VCD, the first inference-time visual contrastive decoding framework for hallucination mitigation in 3D embodied agents. 3D-VCD constructs a distorted 3D scene graph by applying semantic and geometric perturbations to object-centric representations, such as category substitutions and coordinate or extent corruption. By contrasting predictions under the original and distorted 3D contexts, our method suppresses tokens that are insensitive to grounded scene evidence and are therefore likely driven by language priors. We evaluate 3D-VCD on the 3D-POPE and HEAL benchmarks and show that it consistently improves grounded reasoning without any retraining, establishing inference-time contrastive decoding over structured 3D representations as an effective and practical route to more reliable embodied intelligence. --- ### EXAONE 4.5 Technical Report Authors: Eunbi Choi, Kibong Choi, Sehyun Chun, Seokhee Hong, Junwon Hwang, Hyojin Jeon, Ahra Jo, Hyunjik Jo, Yeonsik Jo, Joonkee Kim, Seonghwan Kim, Soyeon Kim et al. Published: 2026-04-09 Categories: cs.CL arXiv: https://arxiv.org/abs/2604.08644v1 This technical report introduces EXAONE 4.5, the first open-weight vision language model released by LG AI Research. EXAONE 4.5 is architected by integrating a dedicated visual encoder into the existing EXAONE 4.0 framework, enabling native multimodal pretraining over both visual and textual modalities. The model is trained on large-scale data with careful curation, particularly emphasizing document-centric corpora that align with LG's strategic application domains. This targeted data design enables substantial performance gains in document understanding and related tasks, while also delivering broad improvements across general language capabilities. EXAONE 4.5 extends context length up to 256K tokens, facilitating long-context reasoning and enterprise-scale use cases. Comparative evaluations demonstrate that EXAONE 4.5 achieves competitive performance in general benchmarks while outperforming state-of-the-art models of similar scale in document understanding and Korean contextual reasoning. As part of LG's ongoing effort toward practical industrial deployment, EXAONE 4.5 is designed to be continuously extended with additional domains and application scenarios to advance AI for a better life. --- ### Creator Incentives in Recommender Systems: A Cooperative Game-Theoretic Approach for Stable and Fair Collaboration in Multi-Agent Bandits Authors: Ramakrishnan Krishnamurthy, Arpit Agarwal, Lakshminarayanan Subramanian, Maximilian Nickel Published: 2026-04-09 Categories: cs.LG, cs.CY, cs.GT, cs.SI arXiv: https://arxiv.org/abs/2604.08643v1 User interactions in online recommendation platforms create interdependencies among content creators: feedback on one creator's content influences the system's learning and, in turn, the exposure of other creators' contents. To analyze incentives in such settings, we model collaboration as a multi-agent stochastic linear bandit problem with a transferable utility (TU) cooperative game formulation, where a coalition's value equals the negative sum of its members' cumulative regrets. We show that, for identical (homogenous) agents with fixed action sets, the induced TU game is convex under mild algorithmic conditions, implying a non-empty core that contains the Shapley value and ensures both stability and fairness. For heterogeneous agents, the game still admits a non-empty core, though convexity and Shapley value core-membership are no longer guaranteed. To address this, we propose a simple regret-based payout rule that satisfies three out of the four Shapley axioms and also lies in the core. Experiments on MovieLens-100k dataset illustrate when the empirical payout aligns with -- and diverges from -- the Shapley fairness across different settings and algorithms. --- ### On Semiotic-Grounded Interpretive Evaluation of Generative Art Authors: Ruixiang Jiang, Changwen Chen Published: 2026-04-09 Categories: cs.CV, cs.AI, cs.HC, cs.MM arXiv: https://arxiv.org/abs/2604.08641v1 Interpretation is essential to deciphering the language of art: audiences communicate with artists by recovering meaning from visual artifacts. However, current Generative Art (GenArt) evaluators remain fixated on surface-level image quality or literal prompt adherence, failing to assess the deeper symbolic or abstract meaning intended by the creator. We address this gap by formalizing a Peircean computational semiotic theory that models Human-GenArt Interaction (HGI) as cascaded semiosis. This framework reveals that artistic meaning is conveyed through three modes - iconic, symbolic, and indexical - yet existing evaluators operate heavily within the iconic mode, remaining structurally blind to the latter two. To overcome this structural blindness, we propose SemJudge. This evaluator explicitly assesses symbolic and indexical meaning in HGI via a Hierarchical Semiosis Graph (HSG) that reconstructs the meaning-making process from prompt to generated artifact. Extensive quantitative experiments show that SemJudge aligns more closely with human judgments than prior evaluators on an interpretation-intensive fine-art benchmark. User studies further demonstrate that SemJudge produces deeper, more insightful artistic interpretations, thereby paving the way for GenArt to move beyond the generation of "pretty" images toward a medium capable of expressing complex human experience. Project page: https://github.com/songrise/SemJudge. --- ### VOLTA: The Surprising Ineffectiveness of Auxiliary Losses for Calibrated Deep Learning Authors: Rahul D Ray, Utkarsh Srivastava Published: 2026-04-09 Categories: cs.LG, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2604.08639v1 Uncertainty quantification (UQ) is essential for deploying deep learning models in safety critical applications, yet no consensus exists on which UQ method performs best across different data modalities and distribution shifts. This paper presents a comprehensive benchmark of ten widely used UQ baselines including MC Dropout, SWAG, ensemble methods, temperature scaling, energy based OOD, Mahalanobis, hyperbolic classifiers, ENN, Taylor Sensus, and split conformal prediction against a simplified yet highly effective variant of VOLTA that retains only a deep encoder, learnable prototypes, cross entropy loss, and post hoc temperature scaling. We evaluate all methods on CIFAR 10 (in distribution), CIFAR 100, SVHN, uniform noise (out of distribution), CIFAR 10 C (corruptions), and Tiny ImageNet features (tabular). VOLTA achieves competitive or superior accuracy (up to 0.864 on CIFAR 10), significantly lower expected calibration error (0.010 vs. 0.044 to 0.102 for baselines), and strong OOD detection (AUROC 0.802). Statistical testing over three random seeds shows that VOLTA matches or outperforms most baselines, with ablation studies confirming the importance of adaptive temperature and deep encoders. Our results establish VOLTA as a lightweight, deterministic, and well calibrated alternative to more complex UQ approaches. --- ### LEGO: Latent-space Exploration for Geometry-aware Optimization of Humanoid Kinematic Design Authors: Jihwan Yoon, Taemoon Jeong, Jeongeun Park, Chanwoo Kim, Jaewoon Kwon, Yonghyeon Lee, Kyungjae Lee, Sungjoon Choi Published: 2026-04-09 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2604.08636v1 Designing robot morphologies and kinematics has traditionally relied on human intuition, with little systematic foundation. Motion-design co-optimization offers a promising path toward automation, but two major challenges remain: (i) the vast, unstructured design space and (ii) the difficulty of constructing task-specific loss functions. We propose a new paradigm that minimizes human involvement by (i) learning the design search space from existing mechanical designs, rather than hand-crafting it, and (ii) defining the loss directly from human motion data via motion retargeting and Procrustes analysis. Using screw-theory-based joint axis representation and isometric manifold learning, we construct a compact, geometry-preserving latent space of humanoid upper body designs in which optimization is tractable. We then solve design optimization in this latent space using gradient-free optimization. Our approach establishes a principled framework for data-driven robot design and demonstrates that leveraging existing designs and human motion can effectively guide the automated discovery of novel robot design. --- ### Retrieval Augmented Classification for Confidential Documents Authors: Yeseul E. Chang, Rahul Kailasa, Simon Shim, Byunghoon Oh, Jaewoo Lee Published: 2026-04-09 Categories: cs.CR, cs.AI, cs.IR arXiv: https://arxiv.org/abs/2604.08628v1 Unauthorized disclosure of confidential documents demands robust, low-leakage classification. In real work environments, there is a lot of inflow and outflow of documents. To continuously update knowledge, we propose a methodology for classifying confidential documents using Retrieval Augmented Classification (RAC). To confirm this effectiveness, we compare RAC and supervised fine tuning (FT) on the WikiLeaks US Diplomacy corpus under realistic sequence-length constraints. On balanced data, RAC matches FT. On unbalanced data, RAC is more stable while delivering comparable performance--about 96% Accuracy on both the original (unbalanced) and augmented (balanced) sets, and up to 94% F1 with proper prompting--whereas FT attains 90% F1 trained on the augmented, balanced set but drops to 88% F1 trained on the original, unbalanced set. When robust augmentation is infeasible, RAC provides a practical, security-preserving path to strong classification by keeping sensitive content out of model weights and under your control, and it remains robust as real-world conditions change in class balance, data, context length, or governance requirements. Because RAC grounds decisions in an external vector store with similarity matching, it is less sensitive to label skew, reduces parameter-level leakage, and can incorporate new data immediately via reindexing--a difficult step for FT, which typically requires retraining. The contributions of this paper are threefold: first, a RAC-based classification pipeline and evaluation recipe; second, a controlled study that isolates class imbalance and context-length effects for FT versus RAC in confidential-document grading; and third, actionable guidance on RAC design patterns for governed deployments. --- ### Evidential Transformation Network: Turning Pretrained Models into Evidential Models for Post-hoc Uncertainty Estimation Authors: Yongchan Chun, Chanhee Park, Jeongho Yoon, Jaehyung Seo, Heuiseok Lim Published: 2026-04-09 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2604.08627v1 Pretrained models have become standard in both vision and language, yet they typically do not provide reliable measures of confidence. Existing uncertainty estimation methods, such as deep ensembles and MC dropout, are often too computationally expensive to deploy in practice. Evidential Deep Learning (EDL) offers a more efficient alternative, but it requires models to be trained to output evidential quantities from the start, which is rarely true for pretrained networks. To enable EDL-style uncertainty estimation in pretrained models, we propose the Evidential Transformation Network (ETN), a lightweight post-hoc module that converts a pretrained predictor into an evidential model. ETN operates in logit space: it learns a sample-dependent affine transformation of the logits and interprets the transformed outputs as parameters of a Dirichlet distribution for uncertainty estimation. We evaluate ETN on image classification and large language model question-answering benchmarks under both in-distribution and out-of-distribution settings. ETN consistently improves uncertainty estimation over post-hoc baselines while preserving accuracy and adding only minimal computational overhead. --- ### WildDet3D: Scaling Promptable 3D Detection in the Wild Authors: Weikai Huang, Jieyu Zhang, Sijun Li, Taoyang Jia, Jiafei Duan, Yunqian Cheng, Jaemin Cho, Matthew Wallingford, Rustin Soraki, Chris Dongjoo Kim, Shuo Liu, Donovan Clay et al. Published: 2026-04-09 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.08626v2 Understanding objects in 3D from a single image is a cornerstone of spatial intelligence. A key step toward this goal is monocular 3D object detection--recovering the extent, location, and orientation of objects from an input RGB image. To be practical in the open world, such a detector must generalize beyond closed-set categories, support diverse prompt modalities, and leverage geometric cues when available. Progress is hampered by two bottlenecks: existing methods are designed for a single prompt type and lack a mechanism to incorporate additional geometric cues, and current 3D datasets cover only narrow categories in controlled environments, limiting open-world transfer. In this work we address both gaps. First, we introduce WildDet3D, a unified geometry-aware architecture that natively accepts text, point, and box prompts and can incorporate auxiliary depth signals at inference time. Second, we present WildDet3D-Data, the largest open 3D detection dataset to date, constructed by generating candidate 3D boxes from existing 2D annotations and retaining only human-verified ones, yielding over 1M images across 13.5K categories in diverse real-world scenes. WildDet3D establishes a new state-of-the-art across multiple benchmarks and settings. In the open-world setting, it achieves 22.6/24.8 AP3D on our newly introduced WildDet3D-Bench with text and box prompts. On Omni3D, it reaches 34.2/36.4 AP3D with text and box prompts, respectively. In zero-shot evaluation, it achieves 40.3/48.9 ODS on Argoverse 2 and ScanNet. Notably, incorporating depth cues at inference time yields substantial additional gains (+20.7 AP on average across settings). --- ### Spectral-transport stability and benign overfitting for minimum norm interpolation Authors: Gustav Olaf Yunus Laitinen-Fredriksson Lundström-Imanov Published: 2026-04-09 Categories: stat.ML, cs.LG, math.ST arXiv: https://arxiv.org/abs/2604.08625v3 Benign overfitting describes the ability of minimum norm interpolating estimators to generalize despite fitting noisy data exactly. Existing characterizations depend on delicate spectral functionals of the population covariance operator, namely the effective ranks of its eigenvalue tail. We study the stability of these characterizations when the covariance spectrum is perturbed, and we quantify perturbations with the Wasserstein distance between spectral measures, a viewpoint we call spectral transport. We prove that eigenvalue tail sums, tail second moments, and the two effective ranks that govern benign overfitting are Lipschitz stable with respect to the spectral-transport distance, with explicit constants driven by an eigenvalue gap. As consequences we obtain three results: a risk transfer theorem for the minimum norm interpolator under aligned spectral perturbations, a stability theorem showing that the benign overfitting classification is preserved under vanishing spectral-transport perturbations, and an empirical certification result in which sample covariance spectra certify benignity through operator norm concentration. The framework connects benign overfitting to harmonic analysis constructions such as diffusion maps and scattering representations, where covariance spectra are perturbed by deformations of the data representation, and to linearized optimal transport, where Wasserstein geometry is the natural metric on perturbations. Numerical experiments with three spectral families confirm the theory: the ordering of the effective rank indices predicts the ordering of the empirical excess risks, and the observed risk change scales at a near Lipschitz rate in the Wasserstein distance between spectra. --- ### Practical Bayesian Inference for Speech SNNs: Uncertainty and Loss-Landscape Smoothing Authors: Yesmine Abdennadher, Philip N. Garner Published: 2026-04-09 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2604.08624v1 Spiking Neural Networks (SNNs) are naturally suited for speech processing tasks due to their specific dynamics, which allows them to handle temporal data. However, the threshold-based generation of spikes in SNNs intuitively causes an angular or irregular predictive landscape. We explore the effect of using the Bayesian learning approach for the weights on the irregular predictive landscape. For the surrogate-gradient SNNs, we also explore the application of the Improved Variational Online Newton (IVON) approach, which is an efficient variational approach. The performance of the proposed approach is evaluated on the Heidelberg Digits and Speech Commands datasets. The hypothesis is that the Bayesian approach will result in a smoother and more regular predictive landscape, given the angular nature of the deterministic predictive landscape. The experimental evaluation of the proposed approach shows improved performance on the negative log-likelihood and Brier score. Furthermore, the proposed approach has resulted in a smoother and more regular predictive landscape compared to the deterministic approach, based on the one-dimensional slices of the weight space --- ### Sustained Impact of Agentic Personalisation in Marketing: A Longitudinal Case Study Authors: Olivier Jeunen, Eleanor Hanna, Schaun Wheeler Published: 2026-04-09 Categories: cs.AI, cs.HC, cs.LG arXiv: https://arxiv.org/abs/2604.08621v1 In consumer applications, Customer Relationship Management (CRM) has traditionally relied on the manual optimisation of static, rule-based messaging strategies. While adaptive and autonomous learning systems offer the promise of scalable personalisation, it remains unclear to what extent ``human-in-the-loop'' oversight is required to sustain performance uplift over time. This paper presents a longitudinal case study analysing a real-world consumer application that leverages agentic infrastructure to personalise marketing messaging for a large-scale user base over an 11-month period. We compare two distinct periods: an active phase where marketers directly curated content, audiences, and strategies -- followed immediately by a passive phase where agents operated autonomously from a fixed library of components. Our results demonstrate that whilst active human management generates the highest relative lift in engagement metrics, the autonomous agents successfully sustained a positive lift during the passive period. These findings suggest a symbiotic model where human intervention drives strategic initialisation and discovery, yet autonomous agents can ensure the scalable retention and preservation of performance gains. --- ### StructRL: Recovering Dynamic Programming Structure from Learning Dynamics in Distributional Reinforcement Learning Authors: Ivo Nowak Published: 2026-04-09 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2604.08620v2 Reinforcement learning is typically treated as a uniform, data-driven optimization process, where updates are guided by rewards and temporal-difference errors without explicitly exploiting global structure. In contrast, dynamic programming methods rely on structured information propagation, enabling efficient and stable learning. In this paper, we provide evidence that such structure can be recovered from the learning dynamics of distributional reinforcement learning. By analyzing the temporal evolution of return distributions, we identify signals that capture when and where learning occurs in the state space. In particular, we introduce a temporal learning indicator t*(s) that reflects when a state undergoes its strongest learning update during training. Empirically, this signal induces an ordering over states that is consistent with a dynamic programming-style propagation of information. Building on this observation, we propose StructRL, a framework that exploits these signals to guide sampling in alignment with the emerging propagation structure. Our preliminary results suggest that distributional learning dynamics provide a mechanism to recover and exploit dynamic programming-like structure without requiring an explicit model. This offers a new perspective on reinforcement learning, where learning can be interpreted as a structured propagation process rather than a purely uniform optimization procedure. --- ### SkillForge: Forging Domain-Specific, Self-Evolving Agent Skills in Cloud Technical Support Authors: Xingyan Liu, Xiyue Luo, Linyu Li, Ganghong Huang, Jianfeng Liu, Honglin Qiao Published: 2026-04-09 Categories: cs.IR, cs.AI, cs.SE arXiv: https://arxiv.org/abs/2604.08618v2 Deploying LLM-powered agents in enterprise scenarios such as cloud technical support demands high-quality, domain-specific skills. However, existing skill creators lack domain grounding, producing skills poorly aligned with real-world task requirements. Moreover, once deployed, there is no systematic mechanism to trace execution failures back to skill deficiencies and drive targeted refinements, leaving skill quality stagnant despite accumulating operational evidence. We introduce SkillForge, a self-evolving framework that closes an end-to-end creation-evaluation-refinement loop. To produce well-aligned initial skills, a Domain-Contextualized Skill Creator grounds skill synthesis in knowledge bases and historical support tickets. To enable continuous self-optimization, a three-stage pipeline -- Failure Analyzer, Skill Diagnostician, and Skill Optimizer -- automatically diagnoses execution failures in batch, pinpoints the underlying skill deficiencies, and rewrites the skill to eliminate them. This cycle runs iteratively, allowing skills to self-improve with every round of deployment feedback. Evaluated on five real-world cloud support scenarios spanning 1,883 tickets and 3,737 tasks, experiments show that: (1) the Domain-Contextualized Skill Creator produces substantially better initial skills than the generic skill creator, as measured by consistency with expert-authored reference responses from historical tickets; and (2) the self-evolution loop progressively improves skill quality from diverse starting points (including expert-authored, domain-created, and generic skills) across successive rounds, demonstrating that automated evolution can surpass manually curated expert knowledge. --- ### From Selection to Scheduling: Federated Geometry-Aware Correction Makes Exemplar Replay Work Better under Continual Dynamic Heterogeneity Authors: Zhuang Qi, Ying-Peng Tang, Lei Meng, Guoqing Chao, Lei Wu, Han Yu, Xiangxu Meng Published: 2026-04-09 Categories: cs.LG, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2604.08617v1 Exemplar replay has become an effective strategy for mitigating catastrophic forgetting in federated continual learning (FCL) by retaining representative samples from past tasks. Existing studies focus on designing sample-importance estimation mechanisms to identify information-rich samples. However, they typically overlook strategies for effectively utilizing the selected exemplars, which limits their performance under continual dynamic heterogeneity across clients and tasks. To address this issue, this paper proposes a Federated gEometry-Aware correcTion method, termed FEAT, which alleviates imbalance-induced representation collapse that drags rare-class features toward frequent classes across clients. Specifically, it consists of two key modules: 1) the Geometric Structure Alignment module performs structural knowledge distillation by aligning the pairwise angular similarities between feature representations and their corresponding Equiangular Tight Frame prototypes, which are fixed and shared across clients to serve as a class-discriminative reference structure. This encourages geometric consistency across tasks and helps mitigate representation drift; 2) the Energy-based Geometric Correction module removes task-irrelevant directional components from feature embeddings, which reduces prediction bias toward majority classes. This improves sensitivity to minority classes and enhances the model's robustness under class-imbalanced distributions. --- ### MARINER: A 3E-Driven Benchmark for Fine-Grained Perception and Complex Reasoning in Open-Water Environments Authors: Xingming Liao, Ning Chen, Muying Shu, Yunpeng Yin, Peijian Zeng, Zhuowei Wang, Nankai Lin, Lianglun Cheng Published: 2026-04-09 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2604.08615v1 Fine-grained visual understanding and high-level reasoning in real-world open-water environments remain under-explored due to the lack of dedicated benchmarks. We introduce MARINER, a comprehensive benchmark built under the novel Entity-Environment-Event (3E) paradigm. MARINER contains 16,629 multi-source maritime images with 63 fine-grained vessel categories, diverse adverse environments, and 5 typical dynamic maritime incidents, covering fine-grained classification, object detection, and visual question answering tasks. We conduct extensive evaluations on mainstream Multimodal Large language models (MLLMs) and establish baselines, revealing that even advanced models struggle with fine-grained discrimination and causal reasoning in complex marine scenes. As a dedicated maritime benchmark, MARINER fills the gap of realistic and cognitive-level evaluation for maritime multimodal understanding, and promotes future research on robust vision-language models for open-water applications. Appendix and supplementary materials are available at https://lxixim.github.io/MARINER. --- ### ViSAGE @ NTIRE 2026 Challenge on Video Saliency Prediction Authors: Kun Wang, Yupeng Hu, Zhiran Li, Hao Liu, Qianlong Xiang, Liqiang Nie Published: 2026-04-09 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.08613v1 In this report, we present our champion solution for the NTIRE 2026 Challenge on Video Saliency Prediction held in conjunction with CVPR 2026. To exploit complementary inductive biases for video saliency, we propose Video Saliency with Adaptive Gated Experts (ViSAGE), a multi-expert ensemble framework. Each specialized decoder performs adaptive gating and modulation to refine spatio-temporal features. The complementary predictions from different experts are then fused at inference. ViSAGE thereby aggregates diverse inductive biases to capture complex spatio-temporal saliency cues in videos. On the Private Test set, ViSAGE ranked first on two out of four evaluation metrics, and outperformed most competing solutions on the other two metrics, demonstrating its effectiveness and generalization ability. Our code has been released at https://github.com/iLearn-Lab/CVPRW26-ViSAGE. --- ### ETCH-X: Robustify Expressive Body Fitting to Clothed Humans with Composable Datasets Authors: Xiaoben Li, Jingyi Wu, Zeyu Cai, Siyuan Yu, Boqian Li, Yuliang Xiu Published: 2026-04-09 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.08548v3 Human body fitting, which aligns parametric body models such as SMPL to raw 3D point clouds of clothed humans, serves as a crucial first step for downstream tasks like animation and texturing. An effective fitting method should be both locally expressive-capturing fine details such as hands and facial features-and globally robust to handle real-world challenges, including clothing dynamics, pose variations, and noisy or partial inputs. Existing approaches typically excel in only one aspect, lacking an all-in-one solution. We upgrade ETCH to ETCH-X, which leverages a tightness-aware fitting paradigm to filter out clothing dynamics ("undress"), extends expressiveness with SMPL-X, and replaces explicit sparse markers (which are highly sensitive to partial data) with implicit dense correspondences ("dense fit") for more robust and fine-grained body fitting. Our disentangled "undress" and "dense fit" modular stages enable separate and scalable training on composable data sources, including diverse simulated garments (CLOTH3D), large-scale full-body motions (AMASS), and fine-grained hand gestures (InterHand2.6M), improving outfit generalization and pose robustness of both bodies and hands. Our approach achieves robust and expressive fitting across diverse clothing, poses, and levels of input completeness, delivering a substantial performance improvement over ETCH on both: 1) seen data, such as 4D-Dress (MPJPE-All, 33.0% ) and CAPE (V2V-Hands, 35.8% ), and 2) unseen data, such as BEDLAM2.0 (MPJPE-All, 80.8% ; V2V-All, 80.5% ). Code and models will be released at https://xiaobenli00.github.io/ETCH-X/. --- ### GaussiAnimate: Rig Animatable Categories with Level of Dynamics Authors: Jiaxin Wang, Dongxin Lyu, Zeyu Cai, Zhiyang Dou, Cheng Lin, Anpei Chen, Yuliang Xiu Published: 2026-04-09 Categories: cs.CV, cs.GR arXiv: https://arxiv.org/abs/2604.08547v2 We propose Skelebones, a Scaffold-Skin Rigging System built on three steps: (1) Bones compress temporally consistent Gaussian or mesh sequences into free-form bones with smooth skinning weights, approximating non-rigid deformations via linear blend skinning (LBS); (2) Skeleton extracts the Mean Curvature Skeleton (MCS) from the canonical shape and temporally refines its topology and kinematics into a compact skeletal structure; and (3) Binding connects the skeleton and bones through non-parametric Partwise Motion Matching (PartMM), which synthesizes novel bone motions by matching, retrieving, and blending existing ones. Together, these steps compress the dynamics of 4D shapes into compact skelebones that are simultaneously controllable and expressive. The resulting representation is category-agnostic, meaning template-free; motion-adaptive, with dynamic topology; and topology-correct, with a skeleton consistent with the surface geometry. PartMM requires no learning. We validate our method on both synthetic and real-world datasets, achieving substantial reanimation improvements on unseen poses: a 17.3 dB PSNR gain over LBS on DNA-Rendering and a 45.6 dB gain over Bag-of-Bones on ActorsHQ, while preserving high rendering fidelity for characters with complex non-rigid dynamics. PartMM generalizes robustly to both Gaussian and mesh representations, excelling in low-data regimes of approximately 1,000 frames, with a 48.4 RMSE improvement over LBS and improvements of more than 20 over GRU- and MLP-based methods. Code will be publicly released at https://cookmaker.cn/gaussianimate/. --- ### GaussiAnimate: Reconstruct and Rig Animatable Categories with Level of Dynamics Authors: Jiaxin Wang, Dongxin Lyu, Zeyu Cai, Zhiyang Dou, Cheng Lin, Anpei Chen, Yuliang Xiu Published: 2026-04-09 Categories: cs.CV, cs.GR arXiv: https://arxiv.org/abs/2604.08547v1 Free-form bones, that conform closely to the surface, can effectively capture non-rigid deformations, but lack a kinematic structure necessary for intuitive control. Thus, we propose a Scaffold-Skin Rigging System, termed "Skelebones", with three key steps: (1) Bones: compress temporally-consistent deformable Gaussians into free-form bones, approximating non-rigid surface deformations; (2) Skeleton: extract a Mean Curvature Skeleton from canonical Gaussians and refine it temporally, ensuring a category-agnostic, motion-adaptive, and topology-correct kinematic structure; (3) Binding: bind the skeleton and bones via non-parametric partwise motion matching (PartMM), synthesizing novel bone motions by matching, retrieving, and blending existing ones. Collectively, these three steps enable us to compress the Level of Dynamics of 4D shapes into compact skelebones that are both controllable and expressive. We validate our approach on both synthetic and real-world datasets, achieving significant improvements in reanimation performance across unseen poses-with 17.3% PSNR gains over Linear Blend Skinning (LBS) and 21.7% over Bag-of-Bones (BoB)-while maintaining excellent reconstruction fidelity, particularly for characters exhibiting complex non-rigid surface dynamics. Our Partwise Motion Matching algorithm demonstrates strong generalization to both Gaussian and mesh representations, especially under low-data regime (~1000 frames), achieving 48.4% RMSE improvement over robust LBS and outperforming GRU- and MLP-based learning methods by >20%. Code will be made publicly available for research purposes at cookmaker.cn/gaussianimate. ---