# Research Papers — 2026-03 · bundle page 18 of 243 > Full-text markdown of papers #851–900 of 12123 published in 2026-03, newest first. AI-readable mirrors of the full 12123-paper 2026-03 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2026-03/page/18 [← Previous bundle](https://aipod.dev/papers/archive/2026-03/page/17.md) [Next bundle →](https://aipod.dev/papers/archive/2026-03/page/19.md) ### Energy-Aware Imitation Learning for Steering Prediction Using Events and Frames Authors: Hu Cao, Jiong Liu, Xingzhuo Yan, Rui Song, Yan Xia, Walter Zimmer, Guang Chen, Alois Knoll Published: 2026-03-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.28008v1 In autonomous driving, relying solely on frame-based cameras can lead to inaccuracies caused by factors like long exposure times, high-speed motion, and challenging lighting conditions. To address these issues, we introduce a bio-inspired vision sensor known as the event camera. Unlike conventional cameras, event cameras capture sparse, asynchronous events that provide a complementary modality to mitigate these challenges. In this work, we propose an energy-aware imitation learning framework for steering prediction that leverages both events and frames. Specifically, we design an Energy-driven Cross-modality Fusion Module (ECFM) and an energy-aware decoder to produce reliable and safe predictions. Extensive experiments on two public real-world datasets, DDD20 and DRFuser, demonstrate that our method outperforms existing state-of-the-art (SOTA) approaches. The codes and trained models will be released upon acceptance. --- ### FedDES: Graph-Based Dynamic Ensemble Selection for Personalized Federated Learning Authors: Brianna Mueller, W. Nick Street Published: 2026-03-30 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.28006v1 Statistical heterogeneity in Federated Learning (FL) often leads to negative transfer, where a single global model fails to serve diverse client distributions. Personalized federated learning (pFL) aims to address this by tailoring models to individual clients. However, under most existing pFL approaches, clients integrate peer client contributions uniformly, which ignores the reality that not all peers are likely to be equally beneficial. Additionally, the potential for personalization at the instance level remains largely unexplored, even though the reliability of different peer models often varies across individual samples within the same client. We introduce FedDES (Federated Dynamic Ensemble Selection), a decentralized pFL framework that achieves instance-level personalization through dynamic ensemble selection. Central to our approach is a Graph Neural Network (GNN) meta-learner trained on a heterogeneous graph modeling interactions between data samples and candidate classifiers. For each test query, the GNN dynamically selects and weights peer client models, forming an ensemble of the most competent classifiers while effectively suppressing contributions from those that are irrelevant or potentially harmful for performance. Experiments on CIFAR-10 and real-world ICU healthcare data demonstrate that FedDES outperforms state-of-the-art pFL baselines in non-IID settings, offering robust protection against negative transfer. --- ### Rethinking Atomic Decomposition for LLM Judges: A Prompt-Controlled Study of Reference-Grounded QA Evaluation Authors: Xinran Zhang Published: 2026-03-30 Categories: cs.CL arXiv: https://arxiv.org/abs/2603.28005v1 Atomic decomposition -- breaking a candidate answer into claims before verifying each against a reference -- is a widely adopted design for LLM-based reference-grounded judges. However, atomic prompts are typically richer and longer, making it unclear whether any advantage comes from decomposition or from richer prompting. We study this for benchmark-style completeness-sensitive reference-support classification: classifying a candidate as fully supported, partially supported, or unsupported relative to a supplied reference. We compare a self-decomposing atomic judge (single-prompt decompose-and-verify) against a prompt-controlled holistic judge with the same inputs and a similarly detailed rubric. On 200 source examples per dataset across TruthfulQA, ASQA, and QAMPARI, with four model families, source-level paired tests, cluster bootstrap, and aggregation across three pre-frozen prompt variants per design family, we find the holistic judge matches or exceeds the atomic judge on two of three benchmarks: ASQA and QAMPARI favor holistic across all four families (statistically reliable in three of four), while TruthfulQA shows a small atomic edge. The holistic advantage is concentrated in partially\_supported cases -- incompleteness detection. A sensitivity check against human annotations confirms the ranking under both benchmark-completeness and human factual-correctness standards. Our finding is specific to the self-decomposing single-prompt pattern on three QA-style benchmarks with 200 source examples each; multi-stage atomic pipelines and non-QA tasks remain untested. Among perturbations examined, reference-quality degradation produced the largest accuracy drops for both judge families. --- ### DipGuava: Disentangling Personalized Gaussian Features for 3D Head Avatars from Monocular Video Authors: Jeonghaeng Lee, Seok Keun Choi, Zhixuan Li, Weisi Lin, Sanghoon Lee Published: 2026-03-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.28003v1 While recent 3D head avatar creation methods attempt to animate facial dynamics, they often fail to capture personalized details, limiting realism and expressiveness. To fill this gap, we present DipGuava (Disentangled and Personalized Gaussian UV Avatar), a novel 3D Gaussian head avatar creation method that successfully generates avatars with personalized attributes from monocular video. DipGuava is the first method to explicitly disentangle facial appearance into two complementary components, trained in a structured two-stage pipeline that significantly reduces learning ambiguity and enhances reconstruction fidelity. In the first stage, we learn a stable geometry-driven base appearance that captures global facial structure and coarse expression-dependent variations. In the second stage, the personalized residual details not captured in the first stage are predicted, including high-frequency components and nonlinearly varying features such as wrinkles and subtle skin deformations. These components are fused via dynamic appearance fusion that integrates residual details after deformation, ensuring spatial and semantic alignment. This disentangled design enables DipGuava to generate photorealistic, identity-preserving avatars, consistently outperforming prior methods in both visual quality and quantitativeperformance, as demonstrated in extensive experiments. --- ### CLIP-AUTT: Test-Time Personalization with Action Unit Prompting for Fine-Grained Video Emotion Recognition Authors: Muhammad Osama Zeeshan, Masoumeh Sharafi, Benoit Savary, Alessandro Lameiras Koerich, Marco Pedersoli, Eric Granger Published: 2026-03-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.27999v3 Personalization in emotion recognition (ER) is essential for accurate interpretation of subtle and subject-specific expressive patterns. Recent advances in vision-language models (VLMs), such as CLIP, demonstrate strong potential for leveraging joint image-text representations in ER. However, existing CLIP-based methods either rely on CLIP's contrastive pretraining or use LLMs to generate descriptive text prompts, which can be noisy, computationally expensive, and often fail to capture fine-grained expressions, leading to degraded performance. In this work, Action Units (AUs) are leveraged as structured textual prompts within CLIP to model fine-grained facial expressions. AUs encode the subtle muscle activations underlying expressions, providing localized and interpretable semantic cues for more robust facial expression recognition (FER). We introduce CLIP-AU, a lightweight AU-guided temporal learning method that integrates interpretable AU semantics into CLIP. It learns generic, subject-agnostic representations by aligning AU prompts with facial dynamics, enabling fine-grained FER without CLIP fine-tuning or LLM-generated text supervision. Although CLIP-AU models fine-grained AU semantics, it does not adapt to subject-specific variability in subtle expressions. To address this limitation, we propose CLIP-AUTT, a video-based test-time personalization method that dynamically adapts AU prompts to videos from unseen subjects. By combining entropy-guided temporal window selection with prompt tuning, CLIP-AUTT enables subject-specific adaptation while preserving temporal consistency. Our experiments on three challenging video-based datasets, BioVid, StressID, and BAH, indicate that CLIP-AU and CLIP-AUTT outperform state-of-the-art CLIP-based FER and TTA methods. --- ### HRIR-Former: Grid-Free Time-Domain Reconstruction of Head-Related Impulse Responses with a Spatially Encoded Transformer Authors: Shaoheng Xu, Chunyi Sun, Jihui Zhang, Amy Bastine, Prasanga N. Samarasinghe, Thushara D. Abhayapala, Hongdong Li Published: 2026-03-30 Categories: eess.AS, cs.LG arXiv: https://arxiv.org/abs/2603.27998v3 Individualized head-related impulse responses (HRIRs) enable binaural rendering, but dense per-listener measurements are costly. We address HRIR spatial up-sampling from sparse per-listener measurements: given a few measured HRIRs for a listener, predict HRIRs at unmeasured target directions. Prior learning methods often work in the frequency domain, rely on minimum-phase assumptions or separate timing models, and use a fixed direction grid, which can degrade temporal fidelity and spatial continuity. We propose HRIR-Former, a time-domain, grid-free binaural Transformer for reconstructing HRIRs at arbitrary directions from sparse inputs. It uses sinusoidal spatial features, a Conv1D refinement module, and auxiliary interaural time difference (ITD) and interaural level difference (ILD) heads. On SONICOM, it improves normalized mean squared error (NMSE), cosine distance, and ITD/ILD errors over prior methods; ablations validate modules and show minimum-phase preprocessing is unnecessary. --- ### HRIR-Former: Grid-Free Time-Domain Reconstruction of Head-Related Impulse Responses with a Spatially Encoded Transformer Authors: Shaoheng Xu, Chunyi Sun, Jihui Zhang, Amy Bastine, Prasanga N. Samarasinghe, Thushara D. Abhayapala, Hongdong Li Published: 2026-03-30 Categories: eess.AS, cs.LG arXiv: https://arxiv.org/abs/2603.27998v2 Individualized head-related impulse responses (HRIRs) enable binaural rendering, but dense per-listener measurements are costly. We address HRIR spatial up-sampling from sparse per-listener measurements: given a few measured HRIRs for a listener, predict HRIRs at unmeasured target directions. Prior learning methods often work in the frequency domain, rely on minimum-phase assumptions or separate timing models, and use a fixed direction grid, which can degrade temporal fidelity and spatial continuity. We propose HRIR-Former, a time-domain, grid-free binaural Transformer for reconstructing HRIRs at arbitrary directions from sparse inputs. It uses sinusoidal spatial features, a Conv1D refinement module, and auxiliary interaural time difference (ITD) and interaural level difference (ILD) heads. On SONICOM, it improves normalized mean squared error (NMSE), cosine distance, and ITD/ILD errors over prior methods; ablations validate modules and show minimum-phase preprocessing is unnecessary. --- ### From Independent to Correlated Diffusion: Generalized Generative Modeling with Probabilistic Computers Authors: Nihal Sanjay Singh, Mazdak Mohseni-Rajaee, Shaila Niazi, Kerem Y. Camsari Published: 2026-03-30 Categories: cs.LG, cs.ET arXiv: https://arxiv.org/abs/2603.27996v2 Diffusion models have emerged as a powerful framework for generative tasks in deep learning. They decompose generative modeling into two computational primitives: deterministic neural-network evaluation and stochastic sampling. Current implementations usually place most computation in the neural network, but diffusion as a framework allows a broader range of choices for the stochastic transition kernel. Here, we generalize the stochastic sampling component by replacing independent noise injection with Markov chain Monte Carlo (MCMC) dynamics that incorporate known interaction structure. Standard independent diffusion is recovered as a special case when couplings are set to zero. By explicitly incorporating Ising couplings into the diffusion dynamics, the noising and denoising processes exploit spatial correlations representative of the target system. The resulting framework maps naturally onto probabilistic computers (p-computers) built from probabilistic bits (p-bits), which provide orders-of-magnitude advantages in sampling throughput and energy efficiency over GPUs. We demonstrate the approach on equilibrium states of the 2D ferromagnetic Ising model and the 3D Edwards-Anderson spin glass, showing that correlated diffusion produces samples in closer agreement with MCMC reference distributions than independent diffusion. More broadly, the framework shows that p-computers can enable new classes of diffusion algorithms that exploit structured probabilistic sampling for generative modeling. --- ### From Independent to Correlated Diffusion: Generalized Generative Modeling with Probabilistic Computers Authors: Nihal Sanjay Singh, Mazdak Mohseni-Rajaee, Shaila Niazi, Kerem Y. Camsari Published: 2026-03-30 Categories: cs.LG, cs.ET arXiv: https://arxiv.org/abs/2603.27996v1 Diffusion models have emerged as a powerful framework for generative tasks in deep learning. They decompose generative modeling into two computational primitives: deterministic neural-network evaluation and stochastic sampling. Current implementations usually place most computation in the neural network, but diffusion as a framework allows a broader range of choices for the stochastic transition kernel. Here, we generalize the stochastic sampling component by replacing independent noise injection with Markov chain Monte Carlo (MCMC) dynamics that incorporate known interaction structure. Standard independent diffusion is recovered as a special case when couplings are set to zero. By explicitly incorporating Ising couplings into the diffusion dynamics, the noising and denoising processes exploit spatial correlations representative of the target system. The resulting framework maps naturally onto probabilistic computers (p-computers) built from probabilistic bits (p-bits), which provide orders-of-magnitude advantages in sampling throughput and energy efficiency over GPUs. We demonstrate the approach on equilibrium states of the 2D ferromagnetic Ising model and the 3D Edwards-Anderson spin glass, showing that correlated diffusion produces samples in closer agreement with MCMC reference distributions than independent diffusion. More broadly, the framework shows that p-computers can enable new classes of diffusion algorithms that exploit structured probabilistic sampling for generative modeling. --- ### UniDA3D: A Unified Domain-Adaptive Framework for Multi-View 3D Object Detection Authors: Hongjing Wu, Cheng Chi, Jinlin Wu, Yanzhao Su, Zhen Lei, Wenqi Ren Published: 2026-03-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.27995v1 Camera-only 3D object detection is critical for autonomous driving, offering a cost-effective alternative to LiDAR based methods. In particular, multi-view 3D object detection has emerged as a promising direction due to its balanced trade-off between performance and cost. However, existing methods often suffer significant performance degradation under complex environmental conditions such as nighttime, fog, and rain, primarily due to their reliance on training data collected mostly in ideal conditions. To address this challenge, we propose UniDA3D, a unified domain-adaptive multi-view 3D object detector designed for robust perception under diverse adverse conditions. UniDA3D formulates nighttime, rainy, and foggy scenes as a unified multi target domain adaptation problem and leverages a novel query guided domain discrepancy mitigation (QDDM) module to align object features between source and target domains at both batch and global levels via query-centric adversarial and contrastive learning. Furthermore, we introduce a domain-adaptive teacher student training pipeline with an exponential-moving-average teacher and dynamically updated high-quality pseudo labels to enhance consistency learning and suppress background noise in unlabeled target domains. In contrast to prior approaches that require separate training for each condition, UniDA3D performs a single unified training process across multiple domains, enabling robust all-weather 3D perception. On a synthesized multi-view 3D benchmark constructed by generating nighttime, rainy, and foggy counterparts from nuScenes (nuScenes-Night, nuScenes-Rain, and nuScenes-Haze), UniDA3D consistently outperforms state of-the-art camera-only multi-view 3D detectors under extreme conditions, achieving substantial gains in mAP and NDS while maintaining real-time inference efficiency. --- ### Progressive Prompt-Guided Cross-Modal Reasoning for Referring Image Segmentation Authors: Jiachen Li, Hongyun Wang, Jinyu Xu, Wenbo Jiang, Yanchun Ma, Yongjian Liu, Qing Xie, Bolong Zheng Published: 2026-03-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.27993v1 Referring image segmentation aims to localize and segment a target object in an image based on a free-form referring expression. The core challenge lies in effectively bridging linguistic descriptions with object-level visual representations, especially when referring expressions involve detailed attributes and complex inter-object relationships. Existing methods either rely on cross-modal alignment or employ Semantic Segmentation Prompts, but they often lack explicit reasoning mechanisms for grounding language descriptions to target regions in the image. To address these limitations, we propose PPCR, a Progressive Prompt-guided Cross-modal Reasoning framework for referring image segmentation. PPCR explicitly structures the reasoning process as a Semantic Understanding-Spatial Grounding-Instance Segmentation pipeline. Specifically, PPCR first employs multimodal large language models (MLLMs) to generate Semantic Segmentation Prompt that capture key semantic cues of the target object. Based on this semantic context, Spatial Segmentation Prompt are further generated to reason about object location and spatial extent, enabling a progressive transition from semantic understanding to spatial grounding. The Semantic and Spatial Segmentation prompts are then jointly integrated into the segmentation module to guide accurate target localization and segmentation. Extensive experiments on standard referring image segmentation benchmarks demonstrate that PPCR consistently outperforms existing methods. The code will be publicly released to facilitate reproducibility. --- ### ViviDoc: Generating Interactive Documents through Human-Agent Collaboration Authors: Yinghao Tang, Yupeng Xie, Yingchaojie Feng, Tingfeng Lan, Jiale Lao, Yue Cheng, Wei Chen Published: 2026-03-30 Categories: cs.HC, cs.AI arXiv: https://arxiv.org/abs/2603.27991v1 Interactive documents help readers engage with complex ideas through dynamic visualization, interactive animations, and exploratory interfaces. However, creating such documents remains costly, as it requires both domain expertise and web development skills. Recent Large Language Model (LLM)-based agents can automate content creation, but directly applying them to interactive document generation often produces outputs that are difficult to control. To address this, we present ViviDoc, to the best of our knowledge the first work to systematically address interactive document generation. ViviDoc introduces a multi-agent pipeline (Planner, Styler, Executor, Evaluator). To make the generation process controllable, we provide three levels of human control: (1) the Document Specification (DocSpec) with SRTC Interaction Specifications (State, Render, Transition, Constraint) for structured planning, (2) a content-aware Style Palette for customizing writing and interaction styles, and (3) chat-based editing for iterative refinement. We also construct ViviBench, a benchmark of 101 topics derived from real-world interactive documents across 11 domains, along with a taxonomy of 8 interaction types and a 4-dimensional automated evaluation framework validated against human ratings (Pearson r > 0.84). Experiments show that ViviDoc achieves the highest content richness and interaction quality in both automated and human evaluation. A 12-person user study confirms that the system is easy to use, provides effective control over the generation process, and produces documents that satisfy users. --- ### Beyond Dataset Distillation: Lossless Dataset Concentration via Diffusion-Assisted Distribution Alignment Authors: Tongfei Liu, Yufan Liu, Bing Li, Weiming Hu Published: 2026-03-30 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2603.27987v1 The high cost and accessibility problem associated with large datasets hinder the development of large-scale visual recognition systems. Dataset Distillation addresses these problems by synthesizing compact surrogate datasets for efficient training, storage, transfer, and privacy preservation. The existing state-of-the-art diffusion-based dataset distillation methods face three issues: lack of theoretical justification, poor efficiency in scaling to high data volumes, and failure in data-free scenarios. To address these issues, we establish a theoretical framework that justifies the use of diffusion models by proving the equivalence between dataset distillation and distribution matching, and reveals an inherent efficiency limit in the dataset distillation paradigm. We then propose a Dataset Concentration (DsCo) framework that uses a diffusion-based Noise-Optimization (NOpt) method to synthesize a small yet representative set of samples, and optionally augments the synthetic data via "Doping", which mixes selected samples from the original dataset with the synthetic samples to overcome the efficiency limit of dataset distillation. DsCo is applicable in both data-accessible and data-free scenarios, achieving SOTA performances for low data volumes, and it extends well to high data volumes, where it nearly reduces the dataset size by half with no performance degradation. --- ### FedFG: Privacy-Preserving and Robust Federated Learning via Flow-Matching Generation Authors: Ruiyang Wang, Rong Pan, Zhengan Yao Published: 2026-03-30 Categories: cs.CR, cs.AI, cs.CV, cs.LG arXiv: https://arxiv.org/abs/2603.27986v1 Federated learning (FL) enables distributed clients to collaboratively train a global model using local private data. Nevertheless, recent studies show that conventional FL algorithms still exhibit deficiencies in privacy protection, and the server lacks a reliable and stable aggregation rule for updating the global model. This situation creates opportunities for adversaries: on the one hand, they may eavesdrop on uploaded gradients or model parameters, potentially leaking benign clients' private data; on the other hand, they may compromise clients to launch poisoning attacks that corrupt the global model. To balance accuracy and security, we propose FedFG, a robust FL framework based on flow-matching generation that simultaneously preserves client privacy and resists sophisticated poisoning attacks. On the client side, each local network is decoupled into a private feature extractor and a public classifier. Each client is further equipped with a flow-matching generator that replaces the extractor when interacting with the server, thereby protecting private features while learning an approximation of the underlying data distribution. Complementing the client-side design, the server employs a client-update verification scheme and a novel robust aggregation mechanism driven by synthetic samples produced by the flow-matching generator. Experiments on MNIST, FMNIST, and CIFAR-10 demonstrate that, compared with prior work, our approach adapts to multiple attack strategies and achieves higher accuracy while maintaining strong privacy protection. --- ### CDH-Bench: A Commonsense-Driven Hallucination Benchmark for Evaluating Visual Fidelity in Vision-Language Models Authors: Kesheng Chen, Yamin Hu, Qi Zhou, Zhenqian Zhu, Wenjian Luo Published: 2026-03-30 Categories: cs.CV, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2603.27982v2 Vision-language models (VLMs) achieve strong performance on many benchmarks, yet a basic reliability question remains underexplored: when visual evidence conflicts with commonsense, do models follow what is shown or what commonsense suggests? A characteristic failure in this setting is that the model overrides visual evidence and outputs the commonsense alternative. We term this phenomenon \textbf{commonsense-driven hallucination} (CDH). To evaluate it, we introduce \textbf{CDH-Bench}, a benchmark designed to create explicit \textbf{visual evidence--commonsense conflicts}. CDH-Bench covers three dimensions: \textit{counting anomalies}, \textit{relational anomalies}, and \textit{attribute anomalies}. We evaluate frontier VLMs under \textit{binary Question Answering (QA)} and \textit{multiple-choice QA}, and report metrics including \textit{Counterfactual Accuracy} (CF-Acc), \textit{Commonsense Accuracy} (CS-Acc), \textit{Counterfactual Accuracy Drop} (CFAD), \textit{Commonsense Collapse Rate} (CCR), and \textit{Relative Prior Dependency} (RPD). Results show that even strong models remain vulnerable to prior-driven normalization under visual evidence--commonsense conflict. CDH-Bench provides a controlled diagnostic of visual fidelity under visual evidence--commonsense conflict. --- ### On the Role of Encoder Depth: Pruning Whisper and LoRA Fine-Tuning in SLAM-ASR Authors: Ganesh Pavan Kartikeya Bharadwaj Kolluri, Michael Kampouridis, Ravi Shekhar Published: 2026-03-30 Categories: cs.CL, cs.SD arXiv: https://arxiv.org/abs/2603.27981v1 Automatic speech recognition (ASR) has advanced rapidly in recent years, driven by large-scale pretrained models and end-to-end architectures such as SLAM-ASR. A key component of SLAM-ASR systems is the Whisper speech encoder, which provides robust acoustic representations. While model pruning has been explored for the full Whisper encoder-decoder architecture, its impact within the SLAM-ASR setting remains under-investigated. In this work, we analyze the effects of layer pruning in the Whisper encoder when used as the acoustic backbone of SLAM-ASR. We further examine the extent to which LoRA-based fine-tuning can recover performance degradation caused by pruning. Experiments conducted across three Whisper variants (Small, Medium, Large-v2), three languages representing distinct resource levels (Danish, Dutch, English), and over 200 training runs demonstrate that pruning two encoder layers causes only 2-4% WER degradation, and that combining this pruning with LoRA adaptation consistently outperforms the unpruned baseline while reducing total parameters by 7-14%. Moreover, our error analysis reveals that LoRA primarily compensates through the language model's linguistic priors, reducing total word errors by 11-21% for Dutch and English, with substitutions and deletions showing the largest reductions. However, for low-resource Danish, the reduction is smaller (4-7%), and LoRA introduces increased insertion errors, indicating that compensation effectiveness depends on the LLM's pre-existing language proficiency and available training data. --- ### RetinexDualV2: Physically-Grounded Dual Retinex for Generalized UHD Image Restoration Authors: Mohab Kishawy, Jun Chen Published: 2026-03-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.27979v2 We propose RetinexDualV2, a unified, physically grounded dual-branch framework for diverse Ultra-High-Definition (UHD) image restoration. Unlike generic models, our method employs a Task-Specific Physical Grounding Module (TS-PGM) to extract degradation-aware priors (e.g., rain masks and dark channels). These explicitly guide a Retinex decomposition network via a novel Physical-Conditioned Multi-head Self-Attention (PC-MSA) mechanism, enabling robust reflection and illumination correction. This physical conditioning allows a single architecture to handle various complex degradations seamlessly, without task-specific structural modifications. RetinexDualV2 demonstrates exceptional generalizability, securing 4th place in the NTIRE 2026 Day and Night Raindrop Removal Challenge and 5th place in the Joint Noise Low-light Enhancement (JNLLIE) Challenge. Extensive experiments confirm the state-of-the-art performance and efficiency of our physically motivated approach. Code is available at https://github.com/ErrorLogic1211/RetinexDual/tree/master/RetinexDualV2 --- ### SARL: Label-Free Reinforcement Learning by Rewarding Reasoning Topology Authors: Yifan Wang, Bolian Li, David Cho, Ruqi Zhang, Fanping Sui, Ananth Grama Published: 2026-03-30 Categories: cs.AI arXiv: https://arxiv.org/abs/2603.27977v2 Reinforcement learning is critical to improving large reasoning models, but its success relies heavily on verifiable rewards (RLVR), making it hard to use in open-ended domains where correctness is ambiguous and cannot be verified. Moreover, reasoning trajectories remain largely unconstrained, and optimizing solely toward the final answer can favor early exploitation over generalization. In this work, we ask whether general reasoning ability can be improved by teaching models how to think (the structure of reasoning) rather than what to produce (the outcome of reasoning), and we extend traditional RLVR to open-ended settings. We introduce Structure-Aware Reinforcement Learning (SARL), a label-free framework that constructs per-response reasoning maps from intermediate thinking steps and rewards their reasoning topology. SARL shifts supervision from destination to path, encouraging reasoning trajectories that are both locally coherent and globally efficient. On verifiable math tasks, SARL outperforms prior label-free RL baselines and even exceeds RL methods with ground truth supervision, with average gains of +9.1% under PPO and +11.6% under GRPO across four math benchmarks, with particularly large improvements on AIME25 (+35.5% with PPO and +44.7% with GRPO). On non-verifiable open-ended tasks, SARL achieves average gains of +34.6% under PPO and +30.4% under GRPO on WildBench across five task categories, outperforming prior label-free RL methods and DPO, which relies on additional preference labels. Beyond strong performance, SARL exhibits substantially lower KL divergence and higher policy entropy, indicating more stable and exploratory training dynamics. Code and data are available at \href{https://github.com/cacayaya/SARL}{Code Link}. --- ### Principal Prototype Analysis on Manifold for Interpretable Reinforcement Learning Authors: Bodla Krishna Vamshi, Haizhao Yang Published: 2026-03-30 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.27971v2 Recent years have witnessed the widespread adoption of reinforcement learning (RL), from solving real-time games to fine-tuning large language models using human preference data significantly improving alignment with user expectations. However, as model complexity grows exponentially, the interpretability of these systems becomes increasingly challenging. While numerous explainability methods have been developed for computer vision and natural language processing to elucidate both local and global reasoning patterns, their application to RL remains limited. Direct extensions of these methods often struggle to maintain the delicate balance between interpretability and performance within RL settings. Prototype-Wrapper Networks (PW-Nets) have recently shown promise in bridging this gap by enhancing explainability in RL domains without sacrificing the efficiency of the original black-box models. However, these methods typically require manually defined reference prototypes, which often necessitate expert domain knowledge. In this work, we propose a method that removes this dependency by automatically selecting optimal prototypes from the available data. Preliminary experiments on standard Gym environments demonstrate that our approach matches the performance of existing PW-Nets, while remaining competitive with the original black-box models. --- ### AffordMatcher: Affordance Learning in 3D Scenes from Visual Signifiers Authors: Nghia Vu, Tuong Do, Khang Nguyen, Baoru Huang, Nhat Le, Binh Xuan Nguyen, Erman Tjiputra, Quang D. Tran, Ravi Prakash, Te-Chuan Chiu, Anh Nguyen Published: 2026-03-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.27970v1 Affordance learning is a complex challenge in many applications, where existing approaches primarily focus on the geometric structures, visual knowledge, and affordance labels of objects to determine interactable regions. However, extending this learning capability to a scene is significantly more complicated, as incorporating object- and scene-level semantics is not straightforward. In this work, we introduce AffordBridge, a large-scale dataset with 291,637 functional interaction annotations across 685 high-resolution indoor scenes in the form of point clouds. Our affordance annotations are complemented by RGB images that are linked to the same instances within the scenes. Building upon our dataset, we propose AffordMatcher, an affordance learning method that establishes coherent semantic correspondences between image-based and point cloud-based instances for keypoint matching, enabling a more precise identification of affordance regions based on cues, so-called visual signifiers. Experimental results on our dataset demonstrate the effectiveness of our approach compared to other methods. --- ### Hg-I2P: Bridging Modalities for Generalizable Image-to-Point-Cloud Registration via Heterogeneous Graphs Authors: Pei An, Junfeng Ding, Jiaqi Yang, Yulong Wang, Jie Ma, Liangliang Nan Published: 2026-03-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.27969v1 Image-to-point-cloud (I2P) registration aims to align 2D images with 3D point clouds by establishing reliable 2D-3D correspondences. The drastic modality gap between images and point clouds makes it challenging to learn features that are both discriminative and generalizable, leading to severe performance drops in unseen scenarios. We address this challenge by introducing a heterogeneous graph that enables refining both cross-modal features and correspondences within a unified architecture. The proposed graph represents a mapping between segmented 2D and 3D regions, which enhances cross-modal feature interaction and thus improves feature discriminability. In addition, modeling the consistency among vertices and edges within the graph enables pruning of unreliable correspondences. Building on these insights, we propose a heterogeneous graph embedded I2P registration method, termed Hg-I2P. It learns a heterogeneous graph by mining multi-path feature relationships, adapts features under the guidance of heterogeneous edges, and prunes correspondences using graph-based projection consistency. Experiments on six indoor and outdoor benchmarks under cross-domain setups demonstrate that Hg-I2P significantly outperforms existing methods in both generalization and accuracy. Code is released on https://github.com/anpei96/hg-i2p-demo. --- ### Learning Multi-View Spatial Reasoning from Cross-View Relations Authors: Suchae Jeong, Jaehwi Song, Haeone Lee, Hanna Kim, Jian Kim, Dongjun Lee, Dong Kyu Shin, Changyeon Kim, Dongyoon Hahm, Woogyeol Jin, Juheon Choi, Kimin Lee Published: 2026-03-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.27967v1 Vision-language models (VLMs) have achieved impressive results on single-view vision tasks, but lack the multi-view spatial reasoning capabilities essential for embodied AI systems to understand 3D environments and manipulate objects across different viewpoints. In this work, we introduce Cross-View Relations (XVR), a large-scale dataset designed to teach VLMs spatial reasoning across multiple views. XVR comprises 100K vision-question-answer samples derived from 18K diverse 3D scenes and 70K robotic manipulation trajectories, spanning three fundamental spatial reasoning tasks: Correspondence (matching objects across views), Verification (validating spatial relationships), and Localization (identifying object positions). VLMs fine-tuned on XVR achieve substantial improvements on established multi-view and robotic spatial reasoning benchmarks (MindCube and RoboSpatial). When integrated as backbones in Vision-Language-Action models, XVR-trained representations improve success rates on RoboCasa. Our results demonstrate that explicit training on cross-view spatial relations significantly enhances multi-view reasoning and transfers effectively to real-world robotic manipulation. --- ### ExFusion: Efficient Transformer Training via Multi-Experts Fusion Authors: Jiacheng Ruan, Daize Dong, Xiaoye Qu, Tong Zhu, Ting Liu, Yuzhuo Fu, Yu Cheng, Suncheng Xiang Published: 2026-03-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.27965v2 Mixture-of-Experts (MoE) models substantially improve performance by increasing the capacity of dense architectures. However, directly training MoE models requires considerable computational resources and introduces extra overhead in parameter storage and deployment. Therefore, it is critical to develop an approach that leverages the multi-expert capability of MoE to enhance performance while incurring minimal additional cost. To this end, we propose a novel pre-training approach, termed ExFusion, which improves the efficiency of Transformer training through multi-expert fusion. Specifically, during the initialization phase, ExFusion upcycles the feed-forward network (FFN) of the Transformer into a multi-expert configuration, where each expert is assigned a weight for later parameter fusion. During training, these weights allow multiple experts to be fused into a single unified expert equivalent to the original FFN, which is subsequently used for forward computation. As a result, ExFusion introduces multi-expert characteristics into the training process while incurring only marginal computational cost compared to standard dense training. After training, the learned weights are used to integrate multi-experts into a single unified expert, thereby eliminating additional overhead in storage and deployment. Extensive experiments on a variety of computer vision and natural language processing tasks demonstrate the effectiveness of the proposed method. --- ### Gradient Manipulation in Distributed Stochastic Gradient Descent with Strategic Agents: Truthful Incentives with Convergence Guarantees Authors: Ziqin Chen, Yongqiang Wang Published: 2026-03-30 Categories: cs.LG, cs.GT arXiv: https://arxiv.org/abs/2603.27962v1 Distributed learning has gained significant attention due to its advantages in scalability, privacy, and fault tolerance.In this paradigm, multiple agents collaboratively train a global model by exchanging parameters only with their neighbors. However, a key vulnerability of existing distributed learning approaches is their implicit assumption that all agents behave honestly during gradient updates. In real-world scenarios, this assumption often breaks down, as selfish or strategic agents may be incentivized to manipulate gradients for personal gain, ultimately compromising the final learning outcome. In this work, we propose a fully distributed payment mechanism that, for the first time, guarantees both truthful behaviors and accurate convergence in distributed stochastic gradient descent. This represents a significant advancement, as it overcomes two major limitations of existing truthfulness mechanisms for collaborative learning:(1) reliance on a centralized server for payment collection, and (2) sacrificing convergence accuracy to guarantee truthfulness. In addition to characterizing the convergence rate under general convex and strongly convex conditions, we also prove that our approach guarantees the cumulative gain that an agent can obtain through strategic behavior remains finite, even as the number of iterations approaches infinity--a property unattainable by most existing truthfulness mechanisms. Our experimental results on standard machine learning tasks, evaluated on benchmark datasets, confirm the effectiveness of the proposed approach. --- ### Towards Efficient Large Vision-Language Models: A Comprehensive Survey on Inference Strategies Authors: Surendra Pathak, Bo Han Published: 2026-03-30 Categories: cs.LG, cs.CL, cs.CV arXiv: https://arxiv.org/abs/2603.27960v2 Although Large Vision Language Models (LVLMs) have demonstrated impressive multimodal reasoning capabilities, their scalability and deployment are constrained by massive computational requirements. In particular, the massive amount of visual tokens from high-resolution input data aggravates the situation due to the quadratic complexity of attention mechanisms. To address these issues, the research community has developed several optimization frameworks. This paper presents a comprehensive survey of the current state-of-the-art techniques for accelerating LVLM inference. We introduce a systematic taxonomy that categorizes existing optimization frameworks into four primary dimensions: visual token compression, memory management and serving, efficient architectural design, and advanced decoding strategies. Furthermore, we critically examine the limitations of these current methodologies and identify critical open problems to inspire future research directions in efficient multimodal systems. --- ### MathGen: Revealing the Illusion of Mathematical Competence through Text-to-Image Generation Authors: Ruiyao Liu, Hui Shen, Ping Zhang, Yunta Hsieh, Yifan Zhang, Jing Xu, Qi Han, Junchen Li, Jiawei Lu, Jianing Ma, Jiaqi Mo, Sicheng Chen et al. Published: 2026-03-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.27959v3 Modern generative models have demonstrated the ability to solve challenging mathematical problems. In many real-world settings, however, mathematical solutions must be expressed visually through diagrams, plots, geometric constructions, and structured symbolic layouts, where correctness depends on precise visual composition. This naturally raises the question of whether generative models can still do so when the answer must be rendered visually rather than written in text? To study this problem, we introduce MathGen, a rigorous benchmark of 420 problems spanning seven core domains, including 350 Clean-Scene problems and 70 paired Open-Scene problems. Each problem is evaluated under a Script-as-a-Judge protocol with problem-specific verification criteria implemented through reusable executable scripts for deterministic and reproducible evaluation. Experiments on representative open-source and proprietary text-to-image models show that mathematical fidelity remains a major bottleneck: even the best closed-source model reaches only 53.7% overall accuracy, while open-source models achieve just 1--11%, often near 0% on structured tasks, particularly those requiring precise geometric and functional rendering. Overall, current T2I models remain far from reliable at even elementary mathematical visual generation. --- ### MathGen: Revealing the Illusion of Mathematical Competence through Text-to-Image Generation Authors: Ruiyao Liu, Hui Shen, Ping Zhang, Yunta Hsieh, Yifan Zhang, Jing Xu, Sicheng Chen, Junchen Li, Jiawei Lu, Jianing Ma, Jiaqi Mo, Qi Han et al. Published: 2026-03-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.27959v2 Modern generative models have demonstrated the ability to solve challenging mathematical problems. In many real-world settings, however, mathematical solutions must be expressed visually through diagrams, plots, geometric constructions, and structured symbolic layouts, where correctness depends on precise visual composition. This naturally raises the question of whether generative models can still do so when the answer must be rendered visually rather than written in text? To study this problem, we introduce MathGen, a rigorous benchmark of 900 problems spanning seven core domains, each paired with an executable verifier under a Script-as-a-Judge protocol for deterministic and objective evaluation. Experiments on representative open-source and proprietary text-to-image models show that mathematical fidelity remains a major bottleneck: even the best closed-source model reaches only 42.0% overall accuracy, while open-source models achieve just ~ 1-11%, often near 0% on structured tasks. Overall, current T2I models remain far from competent at even elementary mathematical visual generation. --- ### CARV: A Diagnostic Benchmark for Compositional Analogical Reasoning in Multimodal LLMs Authors: Yongkang Du, Xiaohan Zou, Minhao Cheng, Lu Lin Published: 2026-03-30 Categories: cs.AI arXiv: https://arxiv.org/abs/2603.27958v2 Analogical reasoning tests a fundamental aspect of human cognition: mapping the relation from one pair of objects to another. Existing evaluations of this ability in multimodal large language models (MLLMs) overlook the ability to compose rules from multiple sources, a critical component of higher-order intelligence. To close this gap, we introduce CARV (Compositional Analogical Reasoning in Vision), a novel task together with a 5,500-sample dataset as the first diagnostic benchmark. We extend the analogy from a single pair to multiple pairs, which requires MLLMs to extract symbolic rules from each pair and compose new transformations. Evaluation on the state-of-the-art MLLMs reveals a striking performance gap: even Gemini-2.5 Pro achieving only 40.4% accuracy, far below human-level performance of 100%. Diagnostic analysis shows two consistent failure modes: (1) decomposing visual changes into symbolic rules, and (2) maintaining robustness under diverse or complex settings, highlighting the limitations of current MLLMs on this task. --- ### Symbolic Density Estimation: A Decompositional Approach Authors: Angelo Rajendram, Xieting Chu, Vijay Ganesh, Max Fieg, Aishik Ghosh Published: 2026-03-30 Categories: cs.LG, hep-ph arXiv: https://arxiv.org/abs/2603.27955v1 We introduce AI-Kolmogorov, a novel framework for Symbolic Density Estimation (SymDE). Symbolic regression (SR) has been effectively used to produce interpretable models in standard regression settings but its applicability to density estimation tasks has largely been unexplored. To address the SymDE task we introduce a multi-stage pipeline: (i) problem decomposition through clustering and/or probabilistic graphical model structure learning; (ii) nonparametric density estimation; (iii) support estimation; and finally (iv) SR on the density estimate. We demonstrate the efficacy of AI-Kolmogorov on synthetic mixture models, multivariate normal distributions, and three exotic distributions, two of which are motivated by applications in high-energy physics. We show that AI-Kolmogorov can discover underlying distributions or otherwise provide valuable insight into the mathematical expressions describing them. --- ### Scaling Atomistic Protein Binder Design with Generative Pretraining and Test-Time Compute Authors: Kieran Didi, Zuobai Zhang, Guoqing Zhou, Danny Reidenbach, Zhonglin Cao, Sooyoung Cha, Tomas Geffner, Christian Dallago, Jian Tang, Michael M. Bronstein, Martin Steinegger, Emine Kucukbenli et al. Published: 2026-03-30 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.27950v1 Protein interaction modeling is central to protein design, which has been transformed by machine learning with applications in drug discovery and beyond. In this landscape, structure-based de novo binder design is cast as either conditional generative modeling or sequence optimization via structure predictors ("hallucination"). We argue that this is a false dichotomy and propose Proteina-Complexa, a novel fully atomistic binder generation method unifying both paradigms. We extend recent flow-based latent protein generation architectures and leverage the domain-domain interactions of monomeric computationally predicted protein structures to construct Teddymer, a new large-scale dataset of synthetic binder-target pairs for pretraining. Combined with high-quality experimental multimers, this enables training a strong base model. We then perform inference-time optimization with this generative prior, unifying the strengths of previously distinct generative and hallucination methods. Proteina-Complexa sets a new state of the art in computational binder design benchmarks: it delivers markedly higher in-silico success rates than existing generative approaches, and our novel test-time optimization strategies greatly outperform previous hallucination methods under normalized compute budgets. We also demonstrate interface hydrogen bond optimization, fold class-guided binder generation, and extensions to small molecule targets and enzyme design tasks, again surpassing prior methods. Code, models and new data will be publicly released. --- ### EnsemJudge: Enhancing Reliability in Chinese LLM-Generated Text Detection through Diverse Model Ensembles Authors: Zhuoshang Wang, Yubing Ren, Guoyu Zhao, Xiaowei Zhu, Hao Li, Yanan Cao Published: 2026-03-30 Categories: cs.CL arXiv: https://arxiv.org/abs/2603.27949v1 Large Language Models (LLMs) are widely applied across various domains due to their powerful text generation capabilities. While LLM-generated texts often resemble human-written ones, their misuse can lead to significant societal risks. Detecting such texts is an essential technique for mitigating LLM misuse, and many detection methods have shown promising results across different datasets. However, real-world scenarios often involve out-of-domain inputs or adversarial samples, which can affect the performance of detection methods to varying degrees. Furthermore, most existing research has focused on English texts, with limited work addressing Chinese text detection. In this study, we propose EnsemJudge, a robust framework for detecting Chinese LLM-generated text by incorporating tailored strategies and ensemble voting mechanisms. We trained and evaluated our system on a carefully constructed Chinese dataset provided by NLPCC2025 Shared Task 1. Our approach outperformed all baseline methods and achieved first place in the task, demonstrating its effectiveness and reliability in Chinese LLM-generated text detection. Our code is available at https://github.com/johnsonwangzs/MGT-Mini. --- ### RehearsalNeRF: Decoupling Intrinsic Neural Fields of Dynamic Illuminations for Scene Editing Authors: Changyeon Won, Hyunjun Jung, Jungu Cho, Seonmi Park, Chi-Hoon Lee, Hae-Gon Jeon Published: 2026-03-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.27948v3 Although there has been significant progress in neural radiance fields, an issue on dynamic illumination changes still remains unsolved. Different from relevant works that parameterize time-variant/-invariant components in scenes, subjects' radiance is highly entangled with their own emitted radiance and lighting colors in spatio-temporal domain. In this paper, we present a new effective method to learn disentangled neural fields under the severe illumination changes, named RehearsalNeRF. Our key idea is to leverage scenes captured under stable lighting like rehearsal stages, easily taken before dynamic illumination occurs, to enforce geometric consistency between the different lighting conditions. In particular, RehearsalNeRF employs a learnable vector for lighting effects which represents illumination colors in a temporal dimension and is used to disentangle projected light colors from scene radiance. Furthermore, our RehearsalNeRF is also able to reconstruct the neural fields of dynamic objects by simply adopting off-the-shelf interactive masks. To decouple the dynamic objects, we propose a new regularization leveraging optical flow, which provides coarse supervision for the color disentanglement. We demonstrate the effectiveness of RehearsalNeRF by showing robust performances on novel view synthesis and scene editing under dynamic illumination conditions. Our source code and video datasets will be publicly available. --- ### JaWildText: A Benchmark for Vision-Language Models on Japanese Scene Text Understanding Authors: Koki Maeda, Naoaki Okazaki Published: 2026-03-30 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2603.27942v2 Japanese scene text poses challenges that multilingual benchmarks often fail to capture, including mixed scripts, frequent vertical writing, and a character inventory far larger than the Latin alphabet. Although Japanese is included in several multilingual benchmarks, these resources do not adequately capture the language-specific complexities. Meanwhile, existing Japanese visual text datasets have primarily focused on scanned documents, leaving in-the-wild scene text underexplored. To fill this gap, we introduce JaWildText, a diagnostic benchmark for evaluating vision-language models (VLMs) on Japanese scene text understanding. JaWildText contains 3,241 instances from 2,961 images newly captured in Japan, with 1.12 million annotated characters spanning 3,643 unique character types. It comprises three complementary tasks that vary in visual organization, output format, and writing style: (i) Dense Scene Text Visual Question Answering (STVQA), which requires reasoning over multiple pieces of visual text evidence; (ii) Receipt Key Information Extraction (KIE), which tests layout-aware structured extraction from mobile-captured receipts; and (iii) Handwriting OCR, which evaluates page-level transcription across various media and writing directions. We evaluate 14 open-weight VLMs and find that the best model achieves an average score of 0.64 across the three tasks. Error analyses show recognition remains the dominant bottleneck, especially for kanji. JaWildText enables fine-grained, script-aware diagnosis of Japanese scene text capabilities, and will be released with evaluation code. --- ### Top-down string-to-dependency Neural Machine Translation Authors: Shuhei Kondo, Katsuhito Sudoh, Yuji Matsumoto Published: 2026-03-30 Categories: cs.CL arXiv: https://arxiv.org/abs/2603.27938v1 Most of modern neural machine translation (NMT) models are based on an encoder-decoder framework with an attention mechanism. While they perform well on standard datasets, they can have trouble in translation of long inputs that are rare or unseen during training. Incorporating target syntax is one approach to dealing with such length-related problems. We propose a novel syntactic decoder that generates a target-language dependency tree in a top-down, left-to-right order. Experiments show that the proposed top-down string-to-tree decoding generalizes better than conventional sequence-to-sequence decoding in translating long inputs that are not observed in the training data. --- ### Deflation-PINNs: Learning Multiple Solutions for PDEs and Landau-de Gennes Authors: Sean Disarò, Ruma Rani Maity, Aras Bacho Published: 2026-03-30 Categories: math.NA, cs.LG arXiv: https://arxiv.org/abs/2603.27936v3 Nonlinear Partial Differential Equations (PDEs) are ubiquitous in mathematical physics and engineering. Although Physics-Informed Neural Networks (PINNs) have emerged as a powerful tool for solving PDE problems, they typically struggle to identify multiple distinct solutions, since they are designed to find one solution at a time. To address this limitation, we introduce Deflation-PINNs, a novel framework that integrates a deflation loss with an architecture based on PINNs and Deep Operator Networks (DeepONets). By incorporating a deflation term into the loss function, our method systematically forces the Deflation-PINN to seek and converge upon distinct finitely many solution branches. We provide theoretical results on the approximation capabilities of our model and demonstrate the efficacy of Deflation-PINNs through numerical experiments on the Landau-de Gennes model of liquid crystals, a system renowned for its complex energy landscape and multiple equilibrium states, and on an Allen--Cahn benchmark whose solution set is provably known. Our results show that Deflation-PINNs can successfully identify and characterize multiple distinct crystal structures: a single unsupervised run recovers all six stable states of the benchmark, each branch certified to lie in the basin of attraction of a different equilibrium, and the discovered branches are refined to percent-level accuracy by a purely neural Deflation--Deep-Ritz stage and to the accuracy of a mesh-converged reference by a classical solver that they initialize. --- ### Deflation-PINNs: Learning Multiple Solutions for PDEs and Landau-de Gennes Authors: Sean Disarò, Ruma Rani Maity, Aras Bacho Published: 2026-03-30 Categories: math.NA, cs.LG arXiv: https://arxiv.org/abs/2603.27936v2 Nonlinear Partial Differential Equations (PDEs) are ubiquitous in mathematical physics and engineering. Although Physics-Informed Neural Networks (PINNs) have emerged as a powerful tool for solving PDE problems, they typically struggle to identify multiple distinct solutions, since they are designed to find one solution at a time. To address this limitation, we introduce Deflation-PINNs, a novel framework that integrates a deflation loss with an architecture based on PINNs and Deep Operator Networks (DeepONets). By incorporating a deflation term into the loss function, our method systematically forces the Deflation-PINN to seek and converge upon distinct finitely many solution branches. We provide theoretical evidence on the convergence of our model and demonstrate the efficacy of Deflation-PINNs through numerical experiments on the Landau-de Gennes model of liquid crystals, a system renowned for its complex energy landscape and multiple equilibrium states. Our results show that Deflation-PINNs can successfully identify and characterize multiple distinct crystal structures. --- ### A Cross-Scale Decoder with Token Refinement for Off-Road Semantic Segmentation Authors: Seongkyu Choi Jhonghyun An Published: 2026-03-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.27931v1 Off-road semantic segmentation is fundamentally challenged by irregular terrain, vegetation clutter, and inherent annotation ambiguity. Unlike urban scenes with crisp object boundaries, off-road environments exhibit strong class-level similarity among terrain categories, resulting in thick and uncertain transition regions that degrade boundary coherence and destabilize training. Rare or thin structures, such as narrow traversable gaps or isolated obstacles, further receive sparse and unreliable supervision and are easily overwhelmed by dominant background textures. Existing decoder designs either rely on low-scale bottlenecks that oversmooth fine structural details, or repeatedly fuse high-detail features, which tends to amplify annotation noise and incur substantial computational cost. We present a cross-scale decoder that explicitly addresses these challenges through three complementary mechanisms. First, a global--local token refinement module consolidates semantic context on a compact bottleneck lattice, guided by boundary-aware regularization to remain robust under ambiguous supervision. Second, a gated detail bridge selectively injects fine-scale structural cues only once through cross-scale attention, preserving boundary and texture information while avoiding noise accumulation. Third, an uncertainty-guided class-aware point refinement selectively updates the least reliable pixels, improving rare and ambiguous structures with minimal computational overhead. The resulting framework achieves noise-robust and boundary-preserving segmentation tailored to off-road environments, recovering fine structural details while maintaining deployment-friendly efficiency. Experimental results on standard off-road benchmarks demonstrate consistent improvements over prior approaches without resorting to heavy dense feature fusion. --- ### Physics-Guided Transformer (PGT): Physics-Aware Attention Mechanism for PINNs Authors: Ehsan Zeraatkar, Rodion Podorozhny, Jelena Tešić Published: 2026-03-30 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2603.27929v1 Reconstructing continuous physical fields from sparse, irregular observations is a central challenge in scientific machine learning, particularly for systems governed by partial differential equations (PDEs). Existing physics-informed methods typically enforce governing equations as soft penalty terms during optimization, often leading to gradient imbalance, instability, and degraded physical consistency under limited data. We introduce the Physics-Guided Transformer (PGT), a neural architecture that embeds physical structure directly into the self-attention mechanism. Specifically, PGT incorporates a heat-kernel-derived additive bias into attention logits, encoding diffusion dynamics and temporal causality within the representation. Query coordinates attend to these physics-conditioned context tokens, and the resulting features are decoded using a FiLM-modulated sinusoidal implicit network that adaptively controls spectral response. We evaluate PGT on the one-dimensional heat equation and two-dimensional incompressible Navier-Stokes systems. In sparse 1D reconstruction with 100 observations, PGT achieves a relative L2 error of 5.9e-3, significantly outperforming both PINNs and sinusoidal representations. In the 2D cylinder wake problem, PGT uniquely achieves both low PDE residual (8.3e-4) and competitive relative error (0.034), outperforming methods that optimize only one objective. These results demonstrate that embedding physics within attention improves stability, generalization, and physical fidelity under data-scarce conditions. --- ### ForestSim: A Synthetic Benchmark for Intelligent Vehicle Perception in Unstructured Forest Environments Authors: Pragat Wagle, Zheng Chen, Lantao Liu Published: 2026-03-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.27923v1 Robust scene understanding is essential for intelligent vehicles operating in natural, unstructured environments. While semantic segmentation datasets for structured urban driving are abundant, the datasets for extremely unstructured wild environments remain scarce due to the difficulty and cost of generating pixel-accurate annotations. These limitations hinder the development of perception systems needed for intelligent ground vehicles tasked with forestry automation, agricultural robotics, disaster response, and all-terrain mobility. To address this gap, we present ForestSim, a high-fidelity synthetic dataset designed for training and evaluating semantic segmentation models for intelligent vehicles in forested off-road and no-road environments. ForestSim contains 2094 photorealistic images across 25 diverse environments, covering multiple seasons, terrain types, and foliage densities. Using Unreal Engine environments integrated with Microsoft AirSim, we generate consistent, pixel-accurate labels across 20 classes relevant to autonomous navigation. We benchmark ForestSim using state-of-the-art architectures and report strong performance despite the inherent challenges of unstructured scenes. ForestSim provides a scalable and accessible foundation for perception research supporting the next generation of intelligent off-road vehicles. The dataset and code are publicly available: Dataset: https://vailforestsim.github.io Code: https://github.com/pragatwagle/ForestSim --- ### Transferable knowledge graphs with executable learned operators for algorithm design Authors: Camilo Chacón Sartori, José H. García, Andrei Voicu Tomut, Christian Blum Published: 2026-03-30 Categories: cs.AI, cs.IR arXiv: https://arxiv.org/abs/2603.27922v2 Procedural knowledge in algorithm design is embedded in source code and rebuilt for each new domain. We introduce Generative Executable Algorithm Knowledge Graphs (GEAKG), a representation in which this knowledge is stored as a generative, executable, transferable graph: typed nodes hold validated operators, edges encode admissible compositions, and learned edge weights record effective sequences. The same engine instantiates the structure across domains by changing only a role ontology (RoleSchema) and a binding. We study GEAKG as a representation mechanism rather than a state-of-the-art optimizer, asking what transfers and when. Layer ablations localize transfer by granularity: within a neural-architecture-search family the learned snapshot transfers across 70 dataset pairs - its weights stay correlated across datasets and one frozen snapshot remains competitive with Regularized Evolution at zero deployment-token cost; across combinatorial domains only the ontology-constrained executable structure transfers, not the learned weights. That structure pays off where target-side search is expensive - a Traveling Salesman snapshot beats an equally untuned from-scratch search on large scheduling instances even at one-fifth its budget - but does not improve on an effective local search where one is cheap, as in assignment and linear ordering. Executable procedural knowledge can thus be acquired offline, compacted, inspected, and reused without runtime language-model calls. --- ### GEAKG: Generative Executable Algorithm Knowledge Graphs Authors: Camilo Chacón Sartori, José H. García, Andrei Voicu Tomut, Christian Blum Published: 2026-03-30 Categories: cs.AI, cs.IR arXiv: https://arxiv.org/abs/2603.27922v1 In the context of algorithms for problem solving, procedural knowledge -- the know-how of algorithm design and operator composition -- remains implicit in code, lost between runs, and must be re-engineered for each new domain. Knowledge graphs (KGs) have proven effective for organizing declarative knowledge, yet current KG paradigms provide limited support for representing procedural knowledge as executable, learnable graph structures. We introduce \textit{Generative Executable Algorithm Knowledge Graphs} (GEAKG), a class of KGs whose nodes store executable operators, whose edges encode learned composition patterns, and whose traversal generates solutions. A GEAKG is \emph{generative} (topology and operators are synthesized by a Large Language Model), \emph{executable} (every node is runnable code), and \emph{transferable} (learned patterns generalize zero-shot across domains). The framework is domain-agnostic at the engine level: the same three-layer architecture and Ant Colony Optimization (ACO)-based learning engine can be instantiated across domains, parameterized by a pluggable ontology (\texttt{RoleSchema}). Two case studies -- sharing no domain-specific framework code -- provide concrete evidence for this framework hypothesis: (1)~Neural Architecture Search across 70 cross-dataset transfer pairs on two tabular benchmarks, and (2)~Combinatorial Optimization, where knowledge learned on the Traveling Salesman Problem transfers zero-shot to scheduling and assignment domains. Taken together, the results support that algorithmic expertise can be explicitly represented, learned, and transferred as executable knowledge graphs. --- ### Adversarial Attacks on Multimodal Large Language Models: A Comprehensive Survey Authors: Bhavuk Jain, Sercan Ö. Arık, Hardeo K. Thakur Published: 2026-03-30 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2603.27918v1 Multimodal large language models (MLLMs) integrate information from multiple modalities such as text, images, audio, and video, enabling complex capabilities such as visual question answering and audio translation. While powerful, this increased expressiveness introduces new and amplified vulnerabilities to adversarial manipulation. This survey provides a comprehensive and systematic analysis of adversarial threats to MLLMs, moving beyond enumerating attack techniques to explain the underlying causes of model susceptibility. We introduce a taxonomy that organizes adversarial attacks according to attacker objectives, unifying diverse attack surfaces across modalities and deployment settings. Additionally, we also present a vulnerability-centric analysis that links integrity attacks, safety and jailbreak failures, control and instruction hijacking, and training-time poisoning to shared architectural and representational weaknesses in multimodal systems. Together, this framework provides an explanatory foundation for understanding adversarial behavior in MLLMs and informs the development of more robust and secure multimodal language systems. --- ### FlashSign: Pose-Free Guidance for Efficient Sign Language Video Generation Authors: Liuzhou Zhang, Zeyu Zhang, Biao Wu, Luyao Tang, Zirui Song, Hongyang He, Renda Han, Guangzhen Yao, Huacan Wang, Ronghao Chen, Xiuying Chen, Guan Huang et al. Published: 2026-03-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.27915v1 Sign language plays a crucial role in bridging communication gaps between the deaf and hard-of-hearing communities. However, existing sign language video generation models often rely on complex intermediate representations, which limits their flexibility and efficiency. In this work, we propose a novel pose-free framework for real-time sign language video generation. Our method eliminates the need for intermediate pose representations by directly mapping natural language text to sign language videos using a diffusion-based approach. We introduce two key innovations: (1) a pose-free generative model based on the a state-of-the-art diffusion backbone, which learns implicit text-to-gesture alignments without pose estimation, and (2) a Trainable Sliding Tile Attention (T-STA) mechanism that accelerates inference by exploiting spatio-temporal locality patterns. Unlike previous training-free sparsity approaches, T-STA integrates trainable sparsity into both training and inference, ensuring consistency and eliminating the train-test gap. This approach significantly reduces computational overhead while maintaining high generation quality, making real-time deployment feasible. Our method increases video generation speed by 3.07x without compromising video quality. Our contributions open new avenues for real-time, high-quality, pose-free sign language synthesis, with potential applications in inclusive communication tools for diverse communities. Code: https://github.com/AIGeeksGroup/FlashSign. --- ### ITQ3_S: High-Fidelity 3-bit LLM Inference via Interleaved Ternary Quantization with Rotation-Domain Smoothing Authors: Edward J. Yoon Published: 2026-03-30 Categories: cs.LG, cs.AI, cs.DC arXiv: https://arxiv.org/abs/2603.27914v2 We present ITQ3_S (Interleaved Ternary Quantization -- Specialized), a novel 3-bit weight quantization format for LLMs integrating TurboQuant (TQ), a rotation-domain strategy based on the Fast Walsh-Hadamard Transform (FWHT). Conventional 3-bit methods suffer precision loss from heavy-tailed weight distributions and inter-channel outliers. ITQ3_S pre-rotates the weight space via FWHT before quantization, spreading outlier energy across the vector and inducing a near-Gaussian distribution amenable to uniform ternary coding. We derive a rigorous dequantization procedure fusing a 256-point Inverse FWHT into the CUDA shared-memory loading stage, ensuring reconstruction error is bounded exclusively by the ternary quantization grid with no additional error from the transform inversion. For any weight vector $\mathbf{w} \in \mathbb{R}^{256}$, the reconstruction satisfies $\|\hat{\mathbf{w}} - \mathbf{w}\|_2 \leq ε_q$, strictly smaller than uniform 3-bit baselines that do not exploit rotation-induced distribution normalization. TurboQuant lacks a native CUDA kernel, precluding direct deployment; naively composing TQ with existing weight quantizers introduces domain mismatch errors that accumulate across layers, degrading quality below standard 3-bit baselines. ITQ3_S resolves this by co-designing the FWHT rotation and quantization kernel as a unified pipeline grounded in the IQ3_S weight format, with the inverse transform fused into the CUDA MMQ kernel. Empirically, on the NVIDIA RTX 5090 (Blackwell), ITQ3_S achieves perplexity competitive with FP16 while delivering throughput exceeding 1.5x that of 4-bit alternatives via optimized DP4A and Tensor Core scheduling. Our results establish ITQ3_S as a practical, mathematically grounded solution for high-fidelity LLM deployment on consumer hardware. --- ### LUMEN: Cost-Transparent Multi-Agent Pipeline for Automated Systematic Review and Meta-Analysis Authors: Yen-Hsun Huang, Yu-Shiou Lin Published: 2026-03-29 Categories: cs.IR, cs.AI, cs.CL, cs.CY, cs.DL arXiv: https://arxiv.org/abs/2606.28362v1 Systematic reviews and meta-analyses (SR/MA) remain the gold standard for evidence synthesis, yet completing one typically requires 67 weeks and substantial expert effort. Recent large language model (LLM) systems have demonstrated strong performance on individual SR phases - screening (otto-SR: 96.7% sensitivity), extraction (Gartlehner et al.: 91.0% accuracy), and search (TrialMind: 0.83 recall) - but no study has reported what it actually costs to run an end-to-end pipeline, how cost distributes across phases, or how architectural choices affect the cost-quality trade-off. We present LUMEN, an open-source multi-agent pipeline that automates six SR/MA phases using 11 specialized LLM agents with deliberate model routing. We evaluate LUMEN on seven datasets: five self-conducted domain reviews (psychiatry, psychology, surgery, vaccinology, cardiology) and two SYNERGY screening benchmarks. Across 13 ground-truth-comparable outcomes, LUMEN achieves 100% directional agreement with published meta-analyses, with effect sizes within 1% for homogeneous study designs. The primary contribution is the first empirical cost and operational characterization of such a pipeline: a complete review costs 19 to 29 USD (median 22.65 USD), with title-abstract screening and data extraction together dominating expenditure. A three-arm extraction ablation reveals a phase-dependent architecture reversal: multi-agent design hurts screening but is essential for extraction, producing 5.7x more poolable analyses than single-model alternatives while eliminating clinically dangerous direction errors. A two-dataset screening benchmark demonstrates that model ranking is domain-dependent and not transferable across review topics. All code and cost logs are publicly available. --- ### RAINO: Anchoring Agents in Reality, A Systematic Review and Conceptual Framework for Realism in Agent-Based Modelling Authors: Loïs Vanhée, Melania Borit Published: 2026-03-29 Categories: cs.MA, cs.AI arXiv: https://arxiv.org/abs/2606.05167v1 Realism is a central yet seemingly under-theorized concept in Agent-Based Modelling. This paper presents a Systematic Literature Review, aiming to identify how realism is currently operationalized and demonstrated. The results show that realism is often poorly defined and lacks a consistent conceptual framework. A wide variety of methods are used to achieve and demonstrate realism, but explanations of whether and why these methods are appropriate for their intended purposes are generally limited. Building on this review, we introduce the Reality Anchor, Input, Output (RAINO) framework. RAINO identifies the key structures used to argue for realism in Agent-Based Models, consisting of Reality Anchors (e.g., empirical data, formal theory, expert knowledge, common-sense expectations) and their application as model Input or Output. RAINO broadens existing perspectives on how realism is framed. It explains why different assessors may evaluate the realism of a model in different ways, and it shows how this broader framing can lead to significantly different approaches to model development. --- ### Evaluating Prompt Injection Defenses for Educational LLM Tutors: Security-Usability-Latency Trade-offs Authors: Alexandre Cristovão Maiorano Published: 2026-03-29 Categories: cs.CR, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2605.06669v2 Educational LLM tutors face a core AI alignment challenge: they must follow user intent while preserving pedagogical constraints and safety policies. We present an evaluation methodology for prompt-injection defenses in this setting, showing that guardrail design entails explicit trade-offs among adversarial robustness, benign-task usability, and response latency. We evaluate a domain-specific multi-layer safeguard pipeline combining deterministic pattern filters, structural validation, contextual sandboxing, and session-level behavioral checks. On a controlled holdout benchmark, the pipeline reaches low bypass and false positive rates with optimized average latency - an operating point that prioritizes pedagogical usability (zero false positives) while maintaining measurable attack resistance. We provide a reproducible benchmark protocol for head-to-head comparison under identical conditions, including stratified bootstrap confidence intervals, paired McNemar significance tests, multi-seed sensitivity sweeps, and direct evaluation of Prompt Guard and NeMo Guardrails on the same split with unified instrumentation. Results expose operational trade-offs: NeMo reaches 0 percent bypass at 16.22 percent FPR and roughly 1.5s latency, while Prompt Guard yields 38.48 percent bypass with 3.60 percent FPR. The framework supports evidence-based guardrail selection for AI tutoring systems under different institutional risk and usability requirements. --- ### The Randomness Floor: Measuring Intrinsic Non-Randomness in Language Model Token Distributions Authors: Jarosław Hryszko Published: 2026-03-29 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2604.22771v1 Language models cannot be random. This paper introduces Entropic Deviation (ED), the normalised KL divergence between a model's token distribution and the uniform distribution, and measures it systematically across 31,200 generations spanning seven models, two architectures (transformer and state space), nine prompt categories, three temperatures, and five languages. Under semantically neutral prompts (empty strings, random characters, nonsense syllables) transformers still exhibit ED of approximately 0.30, meaning that 88-93% of the non-randomness observed under semantic prompts is intrinsic to the learned weights rather than induced by context. Three transformer families (Gemma, Llama, Qwen) converge on nearly identical ED values despite different training data and vocabularies. A state space model (Mamba2) reveals a qualitatively different regime: twice the ED, three times lower within-sequence variance, and massive sensitivity to temperature (r = -0.78) where transformers are nearly immune (r < 0.05). Cross-lingual experiments with Qwen-32B show a stable gradient across five languages (English, Japanese, Chinese, Polish, Arabic) that does not correlate with token fertility and persists when two languages sharing an identical tokeniser subset are compared. These findings establish a structural lower bound on randomness in pretrained language models, characterise how this bound differs across architectures, and demonstrate that language itself modulates the bound independently of tokenisation. --- ### Learning in Blocks: A Multi Agent Debate Assisted Personalized Adaptive Learning Framework for Language Learning Authors: Nicy Scaria, Silvester John Joseph Kennedy, Deepak Subramani Published: 2026-03-29 Categories: cs.CY, cs.AI, cs.CL, cs.HC arXiv: https://arxiv.org/abs/2604.22770v2 Most digital language learning curricula rely on discrete-item quizzes that test recall rather than applied conversational proficiency. When progression is driven by quiz performance, learners can advance despite persistent gaps in using grammar and vocabulary during interaction. Recent work on LLM-based judging suggests a path toward scoring open-ended conversations, but using interaction evidence to drive progression and review requires scoring protocols that are reliable and validated. We introduce Learning in Blocks, a framework that grounds progression in demonstrated conversational competence evaluated using CEFR-aligned rubrics. The framework employs heterogeneous multi-agent debate (HeteroMAD) in two stages: a scoring stage where role-specialized agents independently evaluate Grammar, Vocabulary, and Interactive Communication, engage in debate to address conflicting judgments, and a judge synthesizes consensus scores; and a recommendation stage that identifies specific grammar skills and vocabulary topics for targeted review. Progression requires demonstrating 70% mastery, and spaced review targets identified weaknesses to counter skill decay. We benchmark four scoring and recommendation methods on CEFR A2 conversations annotated by ESL experts. HeteroMAD achieves a superior score agreement with a 0.23 degree of variation and recommendation acceptability of 90.91%. An 8-week study with 180 CEFR A2 learners demonstrates that combining rubric-aligned scoring and recommendation with spaced review and mastery-based progression produces better learning outcomes than feedback alone. --- ### The Root Theorem of Context Engineering Authors: Borja Odriozola Schick Published: 2026-03-29 Categories: cs.CC, cs.CL, cs.HC, cs.IT arXiv: https://arxiv.org/abs/2604.20874v1 Every system that maintains a large language model conversation beyond a single session faces two inescapable constraints: the context window is finite, and information quality degrades with accumulated volume. We formalize these constraints as axioms and derive a single governing principle -- the Root Theorem of Context Engineering: \emph{maximize signal-to-token ratio within bounded, lossy channels.} From this principle, we derive five consequences without additional assumptions: (1)~a quality function $F(P)$ that degrades monotonically with injected token volume, independent of window size; (2)~the independence of signal and token count as optimization variables; (3)~a necessary gate mechanism triggered by fidelity thresholds, not capacity limits; (4)~the inevitability of homeostatic persistence -- accumulate, compress, rewrite, shed -- as the only architecture that sustains understanding indefinitely; and (5)~the self-referential property that the compression mechanism operates inside the channel it compresses, requiring an external verification gate. We show that append-only systems necessarily exceed their effective window in finite time, that retrieval-augmented generation solves search but not continuity, and that the theorem's constraint structure converges with biological memory architecture through independent derivation from shared principles. Engineering proof is provided through a 60+-session persistent architecture demonstrating stable memory footprint under continuous operation -- the divergence prediction made concrete. The Root Theorem establishes context engineering as an information-theoretic discipline with formal foundations, distinct from prompt engineering in both scope and method. Shannon solved point-to-point transmission. Context engineering solves continuity. ---