# Research Papers — 2026-04 · bundle page 140 of 233 > Full-text markdown of papers #6951–7000 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/140 [← Previous bundle](https://aipod.dev/papers/archive/2026-04/page/139.md) [Next bundle →](https://aipod.dev/papers/archive/2026-04/page/141.md) ### K-Way Energy Probes for Metacognition Reduce to Softmax in Discriminative Predictive Coding Networks Authors: Jon-Paul Cacioli Published: 2026-04-13 Categories: cs.LG, cs.CL, cs.NE arXiv: https://arxiv.org/abs/2604.11011v1 We present this as a negative result with an explanatory mechanism, not as a formal upper bound. Predictive coding networks (PCNs) admit a K-way energy probe in which each candidate class is fixed as a target, inference is run to settling, and the per-hypothesis settled energies are compared. The probe appears to read a richer signal source than softmax, since the per-hypothesis energy depends on the entire generative chain. We argue this appearance is misleading under the standard Pinchetti-style discriminative PC formulation. We present an approximate reduction showing that with target-clamped CE-energy training and effectively-feedforward latent dynamics, the K-way energy margin decomposes into a monotone function of the log-softmax margin plus a residual that is not trained to correlate with correctness. The decomposition predicts that the structural probe should track softmax from below. We test this across six conditions on CIFAR-10: extended deterministic training, direct measurement of latent movement during inference, a post-hoc decoder fairness control on a backpropagation network, a matched-budget PC vs BP comparison, a five-point Langevin temperature sweep, and trajectory-integrated MCPC training. In every condition the probe sat below softmax. The gap was stable across training procedures within the discriminative PC family. Final-state and trajectory-integrated training produced probes whose AUROC_2 values differed by less than 10^-3 at deterministic evaluation. The empirical regime is small: single seed, 2.1M-parameter network, 1280 test images. We frame the result as a preprint inviting replication. We discuss conditions under which the decomposition does not apply (bidirectional PC, prospective configuration, generative PC, non-CE energy formulations) and directions for productive structural probing the analysis does not foreclose. --- ### Byte-level generative predictions for forensics multimedia carving Authors: Jaewon Lee, Md Eimran Hossain Eimon, Avinash Srinivasan, Hari Kalva Published: 2026-04-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.11010v1 Digital forensic investigations often face significant challenges when recovering fragmented multimedia files that lack file system metadata. While traditional file carving relies on signatures and discriminative deep learning models for fragment classification, these methods cannot reconstruct or predict missing data. We propose a generative approach to multimedia carving using bGPT, a byte-level transformer designed for next-byte prediction. By feeding partial BMP image data into the model, we simulate the generation of likely fragment continuations. We evaluate the fidelity of these predictions using different metrics, namely, cosine similarity, structural similarity index (SSIM), chi-square distance, and Jensen-Shannon divergence (JSD). Our findings demonstrate that generative models can effectively predict byte-level patterns to support fragment matching in unallocated disk space. --- ### Data-Efficient Semantic Segmentation of 3D Point Clouds via Open-Vocabulary Image Segmentation-based Pseudo-Labeling Authors: Takahiko Furuya Published: 2026-04-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.11007v1 Semantic segmentation of 3D point cloud scenes is a crucial task for various applications. In real-world scenarios, training segmentation models often faces three concurrent forms of data insufficiency: scarcity of training scenes, scarcity of point-level annotations, and absence of 2D image sequences from which point clouds were reconstructed. Existing data-efficient algorithms typically address only one or two of these challenges, leaving the joint treatment of all three unexplored. This paper proposes a data-efficient training framework specifically designed to address the three forms of data insufficiency. Our proposed algorithm, called Point pseudo-Labeling via Open-Vocabulary Image Segmentation (PLOVIS), leverages an Open-Vocabulary Image Segmentation (OVIS) model as a pseudo label generator to compensate for the lack of training data. PLOVIS creates 2D images for pseudo-labeling directly from training 3D point clouds, eliminating the need for 2D image sequences. To mitigate the inherent noise and class imbalance in pseudo labels, we introduce a two-stage filtering of pseudo labels combined with a class-balanced memory bank for effective training. The two-stage filtering mechanism first removes low-confidence pseudo labels, then discards likely incorrect pseudo labels, thereby enhancing the quality of pseudo labels. Experiments on four benchmark datasets, i.e., ScanNet, S3DIS, Toronto3D, and Semantic3D, under realistic data-scarce conditions (a few tens of training 3D scenes, each annotated with only <100 3D points) demonstrate that PLOVIS consistently outperforms existing methods including standard fine-tuning strategies and state-of-the-art weakly supervised learning algorithms. Code will be made publicly available. --- ### Towards Realistic 3D Emission Materials: Dataset, Baseline, and Evaluation for Emission Texture Generation Authors: Zhiyuan Zhang, Zijian Zhou, Linjun Li, Long Chen, Hao Tang, Yichen Gong Published: 2026-04-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.11006v1 3D texture generation is receiving increasing attention, as it enables the creation of realistic and aesthetic texture materials for untextured 3D meshes. However, existing 3D texture generation methods are limited to producing only a few types of non-emissive PBR materials (e.g., albedo, metallic maps and roughness maps), making them difficult to replicate highly popular styles, such as cyberpunk, failing to achieve effects like realistic LED emissions. To address this limitation, we propose a novel task, emission texture generation, which enables the synthesized 3D objects to faithfully reproduce the emission materials from input reference images. Our key contributions include: first, We construct the Objaverse-Emission dataset, the first dataset that contains 40k 3D assets with high-quality emission materials. Second, we propose EmissionGen, a novel baseline for the emission texture generation task. Third, we define detailed evaluation metrics for the emission texture generation task. Our results demonstrate significant potential for future industrial applications. Dataset will be available at https://github.com/yx345kw/EmissionGen. --- ### Diffusion-CAM: Faithful Visual Explanations for dMLLMs Authors: Haomin Zuo, Yidi Li, Luoxiao Yang, Xiaofeng Zhang Published: 2026-04-13 Categories: cs.AI arXiv: https://arxiv.org/abs/2604.11005v1 While diffusion Multimodal Large Language Models (dMLLMs) have recently achieved remarkable strides in multimodal generation, the development of interpretability mechanisms has lagged behind their architectural evolution. Unlike traditional autoregressive models that produce sequential activations, diffusion-based architectures generate tokens via parallel denoising, resulting in smooth, distributed activation patterns across the entire sequence. Consequently, existing Class Activation Mapping (CAM) methods, which are tailored for local, sequential dependencies, are ill-suited for interpreting these non-autoregressive behaviors. To bridge this gap, we propose Diffusion-CAM, the first interpretability method specifically tailored for dMLLMs. We derive raw activation maps by differentiably probing intermediate representations in the transformer backbone, accordingly capturing both latent features and their class-specific gradients. To address the inherent stochasticity of these raw signals, we incorporate four key modules to resolve spatial ambiguity and mitigate intra-image confounders and redundant token correlations. Extensive experiments demonstrate that Diffusion-CAM significantly outperforms SoTA methods in both localization accuracy and visual fidelity, establishing a new standard for understanding the parallel generation process of diffusion multimodal systems. --- ### Panoptic Pairwise Distortion Graph Authors: Muhammad Kamran Janjua, Abdul Wahab, Bahador Rashidi Published: 2026-04-13 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2604.11004v1 In this work, we introduce a new perspective on comparative image assessment by representing an image pair as a structured composition of its regions. In contrast, existing methods focus on whole image analysis, while implicitly relying on region-level understanding. We extend the intra-image notion of a scene graph to inter-image, and propose a novel task of Distortion Graph (DG). DG treats paired images as a structured topology grounded in regions, and represents dense degradation information such as distortion type, severity, comparison and quality score in a compact interpretable graph structure. To realize the task of learning a distortion graph, we contribute (i) a region-level dataset, PandaSet, (ii) a benchmark suite, PandaBench, with varying region-level difficulty, and (iii) an efficient architecture, Panda, to generate distortion graphs. We demonstrate that PandaBench poses a significant challenge for state-of-the-art multimodal large language models (MLLMs) as they fail to understand region-level degradations even when fed with explicit region cues. We show that training on PandaSet or prompting with DG elicits region-wise distortion understanding, opening a new direction for fine-grained, structured pairwise image assessment. --- ### Sanity Checks for Agentic Data Science Authors: Zachary T. Rewolinski, Austin V. Zane, Hao Huang, Chandan Singh, Chenglong Wang, Jianfeng Gao, Bin Yu Published: 2026-04-13 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2604.11003v1 Agentic data science (ADS) pipelines have grown rapidly in both capability and adoption, with systems such as OpenAI Codex now able to directly analyze datasets and produce answers to statistical questions. However, these systems can reach falsely optimistic conclusions that are difficult for users to detect. To address this, we propose a pair of lightweight sanity checks grounded in the Predictability-Computability-Stability (PCS) framework for veridical data science. These checks use reasonable perturbations to screen whether an agent can reliably distinguish signal from noise, acting as a falsifiability constraint that can expose affirmative conclusions as unsupported. Together, the two checks characterize the trustworthiness of an ADS output, e.g. whether it has found stable signal, is responding to noise, or is sensitive to incidental aspects of the input. We validate the approach on synthetic data with controlled signal-to-noise ratios, confirming that the sanity checks track ground-truth signal strength. We then demonstrate the checks on 11 real-world datasets using OpenAI Codex, characterizing the trustworthiness of each conclusion and finding that in 6 of the datasets an affirmative conclusion is not well-supported, even though a single ADS run may support one. We further analyze failure modes of ADS systems and find that ADS self-reported confidence is poorly calibrated to the empirical stability of its conclusions. --- ### Flow-Controlled Scheduling for LLM Inference with Provable Stability Guarantees Authors: Zhuolun Dong, Junyu Cao Published: 2026-04-13 Categories: cs.LG arXiv: https://arxiv.org/abs/2604.11001v1 Large language models (LLMs) have been widely adopted due to their great performance across a wide range of applications. ChatGPT and Gemini now serve hundreds of millions of active users and handle billions of user requests per day, which puts optimizing LLM inference into the spotlight. A key challenge in LLM inference is that decode lengths are unknown. The memory usage for each request grows with generated tokens, which may lead to overflow and cause system instability. To address this concern, we propose a simple flow-control framework that controls the rate at which prompts join the active set. We derive a necessary condition that any stable system must satisfy and establish sufficient conditions under which our algorithm provably achieves stability. Experiments show that, compared to commonly used strategies in practice, our approach achieves higher token and request throughput, lower average and tail latency, and more stable KV cache utilization. --- ### TraversalBench: Challenging Paths to Follow for Vision Language Models Authors: Clara Petrova, Zhuo Chen, Marin Soljačić Published: 2026-04-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.10999v2 Vision-language models (VLMs) perform strongly on multimodal benchmarks, but their ability to follow complex visual paths remains under-tested. We introduce TraversalBench, a controlled benchmark for exact visual path traversal. Each instance contains a continuous polyline with a unique start marker and labeled vertices; models must recover the ordered sequence encountered from start to finish. The benchmark balances self-intersection count, tortuosity, vertex count, and nearby confounding lines while limiting reliance on OCR, world knowledge, or open-ended planning. We find that self-intersections are the dominant source of difficulty. A first-crossing analysis localizes failures to crossing points: performance is stable before the first crossing, then drops sharply when the model must resolve the correct continuation. Nearby confounders have weaker but compounding effects, and an auxiliary reading-order benchmark reveals a consistent left-to-right bias. Together, these results characterize how VLMs perceive and fail on visual paths. Finally, we position TraversalBench as a new contribution to the growing line of sustained and precise visual grounding benchmarks for VLMs. Code, benchmark data, and rendered examples are available at https://github.com/clarapetrova/traversalbench. --- ### When Valid Signals Fail: Regime Boundaries Between LLM Features and RL Trading Policies Authors: Zhengzhe Yang Published: 2026-04-13 Categories: cs.CL, cs.AI, cs.CE arXiv: https://arxiv.org/abs/2604.10996v1 Can large language models (LLMs) generate continuous numerical features that improve reinforcement learning (RL) trading agents? We build a modular pipeline where a frozen LLM serves as a stateless feature extractor, transforming unstructured daily news and filings into a fixed-dimensional vector consumed by a downstream PPO agent. We introduce an automated prompt-optimization loop that treats the extraction prompt as a discrete hyperparameter and tunes it directly against the Information Coefficient - the Spearman rank correlation between predicted and realized returns - rather than NLP losses. The optimized prompt discovers genuinely predictive features (IC above 0.15 on held-out data). However, these valid intermediate representations do not automatically translate into downstream task performance: during a distribution shift caused by a macroeconomic shock, LLM-derived features add noise, and the augmented agent under-performs a price-only baseline. In a calmer test regime the agent recovers, yet macroeconomic state variables remain the most robust driver of policy improvement. Our findings highlight a gap between feature-level validity and policy-level robustness that parallels known challenges in transfer learning under distribution shift. --- ### LumiMotion: Improving Gaussian Relighting with Scene Dynamics Authors: Joanna Kaleta, Piotr Wójcik, Kacper Marzol, Tomasz Trzciński, Kacper Kania, Marek Kowalski Published: 2026-04-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.10994v1 In 3D reconstruction, the problem of inverse rendering, namely recovering the illumination of the scene and the material properties, is fundamental. Existing Gaussian Splatting-based methods primarily target static scenes and often assume simplified or moderate lighting to avoid entangling shadows with surface appearance. This limits their ability to accurately separate lighting effects from material properties, particularly in real-world conditions. We address this limitation by leveraging dynamic elements - regions of the scene that undergo motion - as a supervisory signal for inverse rendering. Motion reveals the same surfaces under varying lighting conditions, providing stronger cues for disentangling material and illumination. This thesis is supported by our experimental results which show we improve LPIPS by 23% for albedo estimation and by 15% for scene relighting relative to next-best baseline. To this end, we introduce LumiMotion, the first Gaussian-based approach that leverages dynamics for inverse rendering and operates in arbitrary dynamic scenes. Our method learns a dynamic 2D Gaussian Splatting representation that employs a set of novel constraints which encourage the dynamic regions of the scene to deform, while keeping static regions stable. As we demonstrate, this separation is crucial for correct optimization of the albedo. Finally, we release a new synthetic benchmark comprising five scenes under four lighting conditions, each in both static and dynamic variants, for the first time enabling systematic evaluation of inverse rendering methods in dynamic environments and challenging lighting. Link to project page: https://joaxkal.github.io/LumiMotion/ --- ### ArtiCAD: Articulated CAD Assembly Design via Multi-Agent Code Generation Authors: Yuan Shui, Yandong Guan, Zhanwei Zhang, Juncheng Hu, Jing Zhang, Dong Xu, Qian Yu Published: 2026-04-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.10992v2 Parametric Computer-Aided Design (CAD) of articulated assemblies is essential for product development, yet generating these multi-part, movable models from high-level descriptions remains unexplored. To address this, we propose ArtiCAD, the first training-free multi-agent system capable of generating editable, articulated CAD assemblies directly from text or images. Our system divides this complex task among four specialized agents: Design, Generation, Assembly, and Review. One of our key insights is to predict assembly relationships during the initial design stage rather than the assembly stage. By utilizing a Connector that explicitly defines attachment points and joint parameters, ArtiCAD determines these relationships before geometry generation, effectively bypassing the limited spatial reasoning capabilities of current LLMs and VLMs. To further ensure high-quality outputs, we introduce validation steps in the generation and assembly stages, accompanied by a cross-stage rollback mechanism that accurately isolates and corrects design- and code-level errors. Additionally, a self-evolving experience store accumulates design knowledge to continuously improve performance on future tasks. Extensive evaluations on three datasets (ArtiCAD-Bench, CADPrompt, and ACD) validate the effectiveness of our approach. We further demonstrate the applicability of ArtiCAD in requirement-driven conceptual design, physical prototyping, and the generation of embodied AI training assets through URDF export. --- ### Examining EAP Students' AI Disclosure Intention: A Cognition-Affect-Conation Perspective Authors: Yiran Du, Huimin He Published: 2026-04-13 Categories: cs.HC, cs.AI arXiv: https://arxiv.org/abs/2604.10991v1 The growing use of generative artificial intelligence (AI) in academic writing has raised increasing concerns regarding transparency and academic integrity in higher education. This study examines the psychological factors influencing English for Academic Purposes (EAP) students' intention to disclose their use of AI tools. Drawing on the cognition-affect-conation framework, the study proposes a model integrating both enabling and inhibiting factors shaping disclosure intention. A sequential explanatory mixed-methods design was employed. Quantitative data from 324 EAP students at an English-medium instruction university in China were analysed using structural equation modelling, followed by semi-structured interviews with 15 students to further interpret the findings. The quantitative results indicate that psychological safety positively predicts AI disclosure intention, whereas fear of negative evaluation negatively predicts it. The qualitative findings further reveal that supportive teacher practices and clear guidance foster psychological safety, while policy ambiguity and reputational concerns intensify fear of negative evaluation and discourage disclosure. These findings highlight the importance of clear institutional policies and supportive pedagogical environments in promoting transparent AI use. --- ### When Verification Fails: How Compositionally Infeasible Claims Escape Rejection Authors: Muxin Liu, Delip Rao, Grace Kim, Chris Callison-Burch Published: 2026-04-13 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2604.10990v1 Scientific claim verification, the task of determining whether claims are entailed by scientific evidence, is fundamental to establishing discoveries in evidence while preventing misinformation. This process involves evaluating each asserted constraint against validated evidence. Under the Closed-World Assumption (CWA), a claim is accepted if and only if all asserted constraints are positively supported. We show that existing verification benchmarks cannot distinguish models enforcing this standard from models applying a simpler shortcut called salient-constraint checking, which applies CWA's rejection criterion only to the most salient constraint and accepts when that constraint is supported. Because existing benchmarks construct infeasible claims by perturbing a single salient element they are insufficient at distinguishing between rigorous claim verification and simple salient-constraint reliance. To separate the two, we construct compositionally infeasible claims where the salient constraint is supported but a non-salient constraint is contradicted. Across model families and modalities, models that otherwise saturate existing benchmarks consistently over-accept these claims, confirming the prevalence of such shortcut reasoning. Via model context interventions, we show that different models and prompting strategies occupy distinct positions on a shared ROC curve, indicating that the gap between model families reflects differences in verification threshold rather than underlying reasoning ability, and that the compositional inference bottleneck is a structural property of current verification behavior that strategy guidance alone cannot overcome. --- ### MAFIG: Multi-agent Driven Formal Instruction Generation Framework Authors: Shixing Zhao, Zheng Si, Pengpeng Ouyang, Zhengqing Hu, Wanqi Zhu, Dong Chen, Yibo Guo, Mingliang Xu Published: 2026-04-13 Categories: cs.AI arXiv: https://arxiv.org/abs/2604.10989v1 Emergency situations in scheduling systems often trigger local functional failures that undermine system stability and even cause system collapse. Existing methods primarily rely on robust scheduling or reactive scheduling, handling emergencies through predefined rules or rescheduling strategies. However, the diversity and unpredictability of real-world emergencies make them difficult to anticipate, which limits the adaptability of these methods in complex scenarios. Recent studies have shown that Large Language Models (LLMs) possess strong potential for complex scheduling tasks because of their extensive prior knowledge and strong reasoning capabilities. Nevertheless, the high inference latency of LLMs and the lengthy contextual information of scheduling systems significantly hinder their application for emergency handling. To mitigate these issues, we propose the Multi-agent Driven Formal Instruction Generation Framework (MAFIG). The framework constrains the decision scope to local functional modules affected by emergency situations and repairs scheduling logic rapidly by generating formal instructions. MAFIG contains a Perception Agent and an Emergency Decision Agent, which mitigates the adverse impact of lengthy system contexts on emergency decision-making. We further introduce span-focused loss-driven local distillation mechanism (SFL) to transfer the decision-making capability of powerful Cloud Large Language Models (C-LLMs) to lightweight local models, reducing inference latency while preserving decision-making effectiveness. Experiments in the Port, Warehousing, and Deck scheduling datasets show success rates of 98.49\%, 94.97\%, and 97.50\%, with average processing times of 0.33 s, 0.23 s, and 0.19 s. These results demonstrate that MAFIG effectively mitigates the impact of emergencies and improves the robustness and adaptability of scheduling systems. --- ### WebForge: Breaking the Realism-Reproducibility-Scalability Trilemma in Browser Agent Benchmark Authors: Peng Yuan, Yuyang Yin, Yuxuan Cai, Zheng Wei Published: 2026-04-13 Categories: cs.AI, cs.CV arXiv: https://arxiv.org/abs/2604.10988v1 Existing browser agent benchmarks face a fundamental trilemma: real-website benchmarks lack reproducibility due to content drift, controlled environments sacrifice realism by omitting real-web noise, and both require costly manual curation that limits scalability. We present WebForge, the first fully automated framework that resolves this trilemma through a four-agent pipeline -- Plan, Generate, Refine, and Validate -- that produces interactive, self-contained web environments end-to-end without human annotation. A seven-dimensional difficulty control framework structures task design along navigation depth, visual complexity, reasoning difficulty, and more, enabling systematic capability profiling beyond single aggregate scores. Using WebForge, we construct WebForge-Bench, a benchmark of 934 tasks spanning 7 domains and 3 difficulty levels. Multi-model experiments show that difficulty stratification effectively differentiates model capabilities, while cross-domain analysis exposes capability biases invisible to aggregate metrics. Together, these results confirm that multi-dimensional evaluation reveals distinct capability profiles that a single aggregate score cannot capture. Code and benchmark are publicly available at https://github.com/yuandaxia2001/WebForge. --- ### Back to the Barn with LLAMAs: Evolving Pretrained LLM Backbones in Finetuning Vision Language Models Authors: Sameera Horawalavithana, Lauren Phillips, Ian Stewart, Sai Munikoti, Karl Pazdernik Published: 2026-04-13 Categories: cs.AI, cs.CL, cs.CV arXiv: https://arxiv.org/abs/2604.10985v1 Vision-Language Models (VLMs) have rapidly advanced by leveraging powerful pre-trained Large Language Models (LLMs) as core reasoning backbones. As new and more capable LLMs emerge with improved reasoning, instruction-following, and generalization, there is a pressing need to efficiently update existing VLMs to incorporate these advancements. However, the integration of new LLMs into VLMs, particularly how the evolving LLMs contribute to multimodal reasoning, alignment, and task-specific performance remains underexplored. Addressing this gap is important for VLM development, given the rapid evolution of pretrained LLM backbones. This study presents a controlled and systematic investigation of how changes in the pretrained LLM backbone affect downstream VLM task performance. By having the vision encoder, training data, and post-training algorithm remain same across LLAMA-1, LLAMA-2, and LLAMA-3 based VLMs, we find that newer LLM backbones do not always lead to better VLMs, but the performance depends on the downstream VLM task. For example, in visual question and answering tasks, newer LLM backbones tend to solve different questions rather than just more questions, and our analysis shows this is driven by differences in how the models process information, including better calibrated confidence and more stable internal representations. We also find that some VLM capabilities appear only in the newest LLM generation, while tasks that depend mainly on visual understanding see little benefit from a newer LLM backbone. --- ### Energy-oriented Diffusion Bridge for Image Restoration with Foundational Diffusion Models Authors: Jinhui Hou, Zhiyu Zhu, Junhui Hou Published: 2026-04-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.10983v1 Diffusion bridge models have shown great promise in image restoration by explicitly connecting clean and degraded image distributions. However, they often rely on complex and high-cost trajectories, which limit both sampling efficiency and final restoration quality. To address this, we propose an Energy-oriented diffusion Bridge (E-Bridge) framework to approximate a set of low-cost manifold geodesic trajectories to boost the performance of the proposed method. We achieve this by designing a novel bridge process that evolves over a shorter time horizon and makes the reverse process start from an entropy-regularized point that mixes the degraded image and Gaussian noise, which theoretically reduces the required trajectory energy. To solve this process efficiently, we draw inspiration from consistency models to learn a single-step mapping function, optimized via a continuous-time consistency objective tailored for our trajectory, so as to analytically map any state on the trajectory to the target image. Notably, the trajectory length in our framework becomes a tunable task-adaptive knob, allowing the model to adaptively balance information preservation against generative power for tasks of varying degradation, such as denoising versus super-resolution. Extensive experiments demonstrate that our E-Bridge achieves state-of-the-art performance across various image restoration tasks while enabling high-quality recovery with a single or fewer sampling steps. Our project page is https://jinnh.github.io/E-Bridge/. --- ### ATANT v1.1: Positioning Continuity Evaluation Against Memory, Long-Context, and Agentic-Memory Benchmarks Authors: Samuel Sameer Tanguturi Published: 2026-04-13 Categories: cs.AI, cs.IR arXiv: https://arxiv.org/abs/2604.10981v2 ATANT v1.0 (arXiv:2604.06710) defined continuity as a system property with 7 required properties and introduced a 10-checkpoint, LLM-free evaluation methodology validated on a 250-story corpus. Since publication, a recurring reviewer and practitioner question has concerned not the framework itself but its relationship to a wider set of memory evaluations: LOCOMO, LongMemEval, BEAM, MemoryBench, Zep's evaluation suite, Letta/MemGPT's evaluations, and RULER. This companion paper, v1.1, does not modify the v1.0 standard. It closes a related-work gap that v1.0 left brief under page limits. We show by structural analysis that none of these benchmarks measures continuity as defined in v1.0: of the 7 required properties, the median existing eval covers 1 property, the mean covers 0.43 when partial credit is scored at 0.5, and no eval covers more than 2. We provide a cell-by-cell property-coverage matrix, identify methodological defects specific to each benchmark (including an empty-gold scoring bug in the LOCOMO reference implementation that renders 23% of its corpus unscorable by construction), and publish our reference implementation's LOCOMO score (8.8%) alongside the structural reason that number is uninformative about continuity. We publish our 8.8% LOCOMO score alongside our 96% ATANT cumulative-scale score as a calibration pair: the 87-point divergence is evidence that the two benchmarks measure different properties, not that one system is an order of magnitude better than another. The position v1.1 takes is not adversarial: each benchmark measures a real capability. The claim is that none of them can adjudicate continuity, and conflating them with continuity evaluation has led the field to under-invest in the properties v1.0 names. --- ### Tracking High-order Evolutions via Cascading Low-rank Fitting Authors: Zhao Song Published: 2026-04-13 Categories: cs.LG arXiv: https://arxiv.org/abs/2604.10980v1 Diffusion models have become the de facto standard for modern visual generation, including well-established frameworks such as latent diffusion and flow matching. Recently, modeling high-order dynamics has emerged as a promising frontier in generative modeling. Rather than only learning the first-order velocity field that transports random noise to a target data distribution, these approaches simultaneously learn higher-order derivatives, such as acceleration and jerk, yielding a diverse family of higher-order diffusion variants. To represent higher-order derivatives, naive approaches instantiate separate neural networks for each order, which scales the parameter space linearly with the derivative order. To overcome this computational bottleneck, we introduce cascading low-rank fitting, an ordinary differential equation inspired method that approximates successive derivatives by applying a shared base function augmented with sequentially accumulated low-rank components. Theoretically, we analyze the rank dynamics of these successive matrix differences. We prove that if the initial difference is linearly decomposable, the generic ranks of high-order derivatives are guaranteed to be monotonically non-increasing. Conversely, we demonstrate that without this structural assumption, the General Leibniz Rule allows ranks to strictly increase. Furthermore, we establish that under specific conditions, the sequence of derivative ranks can be designed to form any arbitrary permutation. Finally, we present a straightforward algorithm to efficiently compute the proposed cascading low-rank fitting. --- ### Enabling and Inhibitory Pathways of Students' AI Use Concealment Intention in Higher Education: Evidence from SEM and fsQCA Authors: Yiran Du, Huimin He Published: 2026-04-13 Categories: cs.HC, cs.AI arXiv: https://arxiv.org/abs/2604.10978v1 This study investigates students' AI use concealment intention in higher education by integrating the cognition-affect-conation (CAC) framework with a dual-method approach combining structural equation modelling (SEM) and fuzzy-set qualitative comparative analysis (fsQCA). Drawing on data from 1346 university students, the findings reveal two opposing mechanisms shaping concealment intention. The enabling pathway shows that perceived stigma, perceived risk, and perceived policy uncertainty increase fear of negative evaluation, which in turn promotes concealment. In contrast, the inhibitory pathway demonstrates that AI self-efficacy, perceived fairness, and perceived social support enhance psychological safety, thereby reducing concealment intention. SEM results confirm the hypothesised relationships and mediation effects, while fsQCA identifies multiple configurational pathways, highlighting equifinality and the central role of fear of negative evaluation across conditions. The study contributes to the literature by conceptualising concealment as a distinct behavioural outcome and by providing a nuanced explanation that integrates both net-effect and configurational perspectives. Practical implications emphasise the need for clear institutional policies, destigmatisation of appropriate AI use, and the cultivation of supportive learning environments to promote transparency. --- ### Neural Generalized Mixed-Effects Models Authors: Yuli Slavutsky, Sebastian Salazar, David M. Blei Published: 2026-04-13 Categories: stat.ML, cs.LG, stat.CO, stat.ME arXiv: https://arxiv.org/abs/2604.10976v1 Generalized linear mixed-effects models (GLMMs) are widely used to analyze grouped and hierarchical data. In a GLMM, each response is assumed to follow an exponential-family distribution where the natural parameter is given by a linear function of observed covariates and a latent group-specific random effect. Since exact marginalization over the random effects is typically intractable, model parameters are estimated by maximizing an approximate marginal likelihood. In this paper, we replace the linear function with neural networks. The result is a more flexible model, the neural generalized mixed-effects model (NGMM), which captures complex relationships between covariates and responses. To fit NGMM to data, we introduce an efficient optimization procedure that maximizes the approximate marginal likelihood and is differentiable with respect to network parameters. We show that the approximation error of our objective decays at a Gaussian-tail rate in a user-chosen parameter. On synthetic data, NGMM improves over GLMMs when covariate-response relationships are nonlinear, and on real-world datasets it outperforms prior methods. Finally, we analyze a large dataset of student proficiency to demonstrate how NGMM can be extended to more complex latent-variable models. --- ### Robust Adversarial Policy Optimization Under Dynamics Uncertainty Authors: Mintae Kim, Koushil Sreenath Published: 2026-04-13 Categories: cs.LG, cs.RO arXiv: https://arxiv.org/abs/2604.10974v2 Reinforcement learning (RL) policies often fail under dynamics that differ from training, a gap not fully addressed by domain randomization or existing adversarial RL methods. Distributionally robust RL provides a formal remedy but still relies on surrogate adversaries to approximate intractable primal problems, leaving blind spots that potentially cause instability and over-conservatism. We propose a dual formulation that directly exposes the robustness-performance trade-off. At the trajectory level, a temperature parameter from the dual problem is approximated with an adversarial network, yielding efficient and stable worst-case rollouts within a divergence bound. At the model level, we employ Boltzmann reweighting over dynamics ensembles, focusing on more adverse environments to the current policy rather than uniform sampling. The two components act independently and complement each other: trajectory-level steering ensures robust rollouts, while model-level sampling provides policy-sensitive coverage of adverse dynamics. The resulting framework, robust adversarial policy optimization (RAPO) outperforms robust RL baselines, improving resilience to uncertainty and generalization to out-of-distribution dynamics while maintaining dual tractability. --- ### CFMS: A Coarse-to-Fine Multimodal Synthesis Framework for Enhanced Tabular Reasoning Authors: Qixian Huang, Hongqiang Lin, Tong Fu, Yingsen Wang, Zhenghui Fu, Qirui Wang, Yiding Sun, Dongxu Zhang Published: 2026-04-13 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2604.10973v1 Reasoning over tabular data is a crucial capability for tasks like question answering and fact verification, as it requires models to comprehend both free-form questions and semi-structured tables. However, while methods like Chain-of-Thought (CoT) introduce reasoning chains, purely symbolic methodes are inherently limited by their blindness to holistic visual patterns. To address this, we propose the Coarse-to-Fine Multimodal Synthesis framework (CFMS), a novel two-stage paradigm that hierarchically decouples high-level visual perception from granular symbolic reasoning. In the Coarse Stage, CFMS leverages the Multimodal Large Language Models (MLLMs) to perform a one-time synthesis of a multi-perspective knowledge tuple. This tuple subsequently serves as a dynamic reasoning map to guide the fine stage, where a symbolic engine executes a targeted and efficient sequence of iterative operations over the table. Extensive experiments on the WikiTQ and TabFact benchmarks demonstrate that CFMS achieves competitive accuracy. The framework exhibits particular robustness when handling large tables and when instantiated with smaller backbone models, validating its effectiveness and generalizability. --- ### MMR-AD: A Large-Scale Multimodal Dataset for Benchmarking General Anomaly Detection with Multimodal Large Language Models Authors: Xincheng Yao, Zefeng Qian, Chao Shi, Jiayang Song, Chongyang Zhang Published: 2026-04-13 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2604.10971v1 In the progress of industrial anomaly detection, general anomaly detection (GAD) is an emerging trend and also the ultimate goal. Unlike the conventional single- and multi-class AD, general AD aims to train a general AD model that can directly detect anomalies in diverse novel classes without any retraining or fine-tuning on the target data. Recently, Multimodal Large Language Models (MLLMs) have shown great promise in achieving general anomaly detection due to their revolutionary visual understanding and language reasoning capabilities. However, MLLM's general AD ability remains underexplored due to: (1) MLLMs are pretrained on amounts of data sourced from the Web, these data still have significant gaps with the data in AD scenarios. Moreover, the image-text pairs during pretraining are also not specifically for AD tasks. (2) The current mainstream AD datasets are image-based and not yet suitable for post-training MLLMs. To facilitate MLLM-based general AD research, we present MMR-AD, which is a comprehensive benchmark for both training and evaluating MLLM-based AD models. With MMR-AD, we reveal that the AD performance of current SOTA generalist MLLMs still falls far behind the industrial requirements. Based on MMR-AD, we also propose a baseline model, Anomaly-R1, which is a reasoning-based AD model that learns from the CoT data in MMR-AD and is further enhanced by reinforcement learning. Extensive experiments show that our Anomaly-R1 achieves remarkable improvements over generalist MLLMs in both anomaly detection and localization. --- ### Using Deep Learning Models Pretrained by Self-Supervised Learning for Protein Localization Authors: Ben Isselmann, Dilara Göksu, Heinz Neumann, Andreas Weinmann Published: 2026-04-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.10970v2 Background: Task-specific microscopy datasets are often small, making it difficult to train deep learning models that learn robust features. While self-supervised learning (SSL) has shown promise through pretraining on large, domain-specific datasets, generalizability across datasets with differing staining protocols and channel configurations remains underexplored. We investigated the generalizability of SSL models pretrained on ImageNet-1k and HPA FOV, evaluating their embeddings on OpenCell with and without fine-tuning, two channel-mismatch strategies, and varying fine-tuning data fractions. We additionally analyzed single-cell embeddings on a labeled OpenCell subset. Result: DINO-based ViT backbones pretrained on HPA FOV or ImageNet-1k transfer well to OpenCell even without fine-tuning. Fine-tuning further improved performance to 0.704 $\pm$ 0.027 (17 classes, multi-class labels). At the single-cell level, the HPA single-cell-pretrained model achieved the highest k-nearest neighbor performance across all neighborhood sizes (macro $F_1$ $\geq$ 0.515). Conclusion: SSL methods like DINO, pretrained on large domain-relevant datasets, enable effective use of deep learning features for fine-tuning on small, task-specific microscopy datasets. --- ### Using Deep Learning Models Pretrained by Self-Supervised Learning for Protein Localization Authors: Ben Isselmann, Dilara Göksu, Heinz Neumann, Andreas Weinmann Published: 2026-04-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.10970v1 Background: Task-specific microscopy datasets are often small, making it difficult to train deep learning models that learn robust features. While self-supervised learning (SSL) has shown promise through pretraining on large, domain-specific datasets, generalizability across datasets with differing staining protocols and channel configurations remains underexplored. We investigated the generalizability of SSL models pretrained on ImageNet-1k and HPA FOV, evaluating their embeddings on OpenCell with and without fine-tuning, two channel-mismatch strategies, and varying fine-tuning data fractions. We additionally analyzed single-cell embeddings on a labeled OpenCell subset. Result: DINO-based ViT backbones pretrained on HPA FOV or ImageNet-1k transfer well to OpenCell even without fine-tuning. The HPA FOV-pretrained model achieved the highest zero-shot performance (macro $F_1$ 0.822 $\pm$ 0.007). Fine-tuning further improved performance to 0.860 $\pm$ 0.013. At the single-cell level, the HPA single-cell-pretrained model achieved the highest k-nearest neighbor performance across all neighborhood sizes (macro $F_1$ $\geq$ 0.796). Conclusion: SSL methods like DINO, pretrained on large domain-relevant datasets, enable effective use of deep learning features for fine-tuning on small, task-specific microscopy datasets. --- ### Towards Automated Solar Panel Integrity: Hybrid Deep Feature Extraction for Advanced Surface Defect Identification Authors: Muhammad Junaid Asif, Muhammad Saad Rafaqat, Usman Nazakat, Uzair Khan, Rana Fayyaz Ahmad Published: 2026-04-13 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2604.10969v2 To ensure energy efficiency and reliable operations, it is essential to monitor solar panels in generation plants to detect defects. It is quite labor-intensive, time consuming and costly to manually monitor large-scale solar plants and those installed in remote areas. Manual inspection may also be susceptible to human errors. Consequently, it is necessary to create an automated, intelligent defect-detection system, that ensures continuous monitoring, early fault detection, and maximum power generation. We proposed a novel hybrid method for defect detection in SOLAR plates by combining both handcrafted and deep learning features. Local Binary Pattern (LBP), Histogram of Gradients (HoG) and Gabor Filters were used for the extraction of handcrafted features. Deep features extracted by leveraging the use of DenseNet-169. Both handcrafted and deep features were concatenated and then fed to three distinct types of classifiers, including Support Vector Machines (SVM), Extreme Gradient Boost (XGBoost) and Light Gradient-Boosting Machine (LGBM). Experimental results evaluated on the augmented dataset show the superior performance, especially DenseNet-169 + Gabor (SVM), had the highest scores with 99.17% accuracy which was higher than all the other systems. In general, the proposed hybrid framework offers better defect-detection accuracy, resistance, and flexibility that has a solid basis on the real-life use of the automated PV panels monitoring system. --- ### Towards Automated Solar Panel Integrity: Hybrid Deep Feature Extraction for Advanced Surface Defect Identification Authors: Muhammad Junaid Asif, Muhammad Saad Rafaqat, Usman Nazakat, Uzair Khan, Rana Fayyaz Ahmad Published: 2026-04-13 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2604.10969v1 To ensure energy efficiency and reliable operations, it is essential to monitor solar panels in generation plants to detect defects. It is quite labor-intensive, time consuming and costly to manually monitor large-scale solar plants and those installed in remote areas. Manual inspection may also be susceptible to human errors. Consequently, it is necessary to create an automated, intelligent defect-detection system, that ensures continuous monitoring, early fault detection, and maximum power generation. We proposed a novel hybrid method for defect detection in SOLAR plates by combining both handcrafted and deep learning features. Local Binary Pattern (LBP), Histogram of Gradients (HoG) and Gabor Filters were used for the extraction of handcrafted features. Deep features extracted by leveraging the use of DenseNet-169. Both handcrafted and deep features were concatenated and then fed to three distinct types of classifiers, including Support Vector Machines (SVM), Extreme Gradient Boost (XGBoost) and Light Gradient-Boosting Machine (LGBM). Experimental results evaluated on the augmented dataset show the superior performance, especially DenseNet-169 + Gabor (SVM), had the highest scores with 99.17% accuracy which was higher than all the other systems. In general, the proposed hybrid framework offers better defect-detection accuracy, resistance, and flexibility that has a solid basis on the real-life use of the automated PV panels monitoring system. --- ### YIELD: A Large-Scale Dataset and Evaluation Framework for Information Elicitation Agents Authors: Victor De Lima, Grace Hui Yang Published: 2026-04-13 Categories: cs.CL arXiv: https://arxiv.org/abs/2604.10968v1 Most conversational agents (CAs) are designed to satisfy user needs through user-driven interactions. However, many real-world settings, such as academic interviewing, judicial proceedings, and journalistic investigations, involve broader institutional decision-making processes and require agents that can elicit information from users. In this paper, we introduce Information Elicitation Agents (IEAs) in which the agent's goal is to elicit information from users to support the agent's institutional or task-oriented objectives. To enable systematic research on this setting, we present YIELD, a 26M-token dataset of 2,281 ethically sourced, human-to-human dialogues. Moreover, we formalize information elicitation as a finite-horizon POMDP and propose novel metrics tailored to IEAs. Pilot experiments on multiple foundation LLMs show that training on YIELD improves their alignment with real elicitation behavior and findings are corroborated by human evaluation. We release YIELD under CC BY 4.0. The dataset, project code, evaluation tools, and fine-tuned model adapters are available at: https://github.com/infosenselab/yield. --- ### Learning to Test: Physics-Informed Representation for Dynamical Instability Detection Authors: Minxing Zheng, Zewei Deng, Liyan Xie, Shixiang Zhu Published: 2026-04-13 Categories: cs.LG arXiv: https://arxiv.org/abs/2604.10967v1 Many safety-critical scientific and engineering systems evolve according to differential-algebraic equations (DAEs), where dynamical behavior is constrained by physical laws and admissibility conditions. In practice, these systems operate under stochastically varying environmental inputs, so stability is not a static property but must be reassessed as the context distribution shifts. Repeated large-scale DAE simulation, however, is computationally prohibitive in high-dimensional or real-time settings. This paper proposes a test-oriented learning framework for stability assessment under distribution shift. Rather than re-estimating physical parameters or repeatedly solving the underlying DAE, we learn a physics-informed latent representation of contextual variables that captures stability-relevant structure and is regularized toward a tractable reference distribution. Trained on baseline data from a certified safe regime, the learned representation enables deployment-time safety monitoring to be formulated as a distributional hypothesis test in latent space, with controlled Type I error. By integrating neural dynamical surrogates, uncertainty-aware calibration, and uniformity-based testing, our approach provides a scalable and statistically grounded method for detecting instability risk in stochastic constrained dynamical systems without repeated simulation. --- ### You Only Judge Once: Multi-response Reward Modeling in a Single Forward Pass Authors: Yinuo Yang, Zixian Ma, Manasi Ganti, Jieyu Zhang, Ranjay Krishna Published: 2026-04-13 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2604.10966v2 We present a discriminative multimodal reward model that scores all candidate responses in a single forward pass. Conventional discriminative reward models evaluate each response independently, requiring multiple forward passes, one for each potential response. Our approach concatenates multiple responses with separator tokens and applies cross-entropy over their scalar scores, enabling direct comparative reasoning and efficient $N$-way preference learning. The multi-response design also yields up to $N\times$ wall-clock speedup and FLOPs reduction over conventional single-response scoring. To enable $N$-way reward evaluation beyond existing pairwise benchmarks, we construct two new benchmarks: (1) MR$^2$Bench-Image contains human-annotated rankings over responses from 8 diverse models; (2) MR$^2$Bench-Video is a large-scale video-based reward benchmark derived from 94K crowdsourced pairwise human judgments over video question-answering spanning 19 models, denoised via preference graph ensemble. Both benchmarks provide 4-response evaluation variants sampled from the full rankings. Built on a 4B vision-language backbone with LoRA fine-tuning and a lightweight MLP value head, our model achieves state-of-the-art results on six multimodal reward benchmarks, including MR$^2$Bench-Image, MR$^2$Bench-Video, and four other existing benchmarks. Our model outperforms existing larger generative and discriminative reward models. We further demonstrate that our reward model, when used in reinforcement learning with GRPO, produces improved policy models that maintain performance across standard multimodal benchmarks while substantially improving open-ended generation quality, outperforming a single-response discriminative reward model (RM) baseline by a large margin in both training stability and open-ended generation quality. --- ### bioLeak: Leakage-Aware Modeling and Diagnostics for Machine Learning in R Authors: Selçuk Korkmaz Published: 2026-04-13 Categories: stat.CO, cs.LG, stat.AP, stat.ML arXiv: https://arxiv.org/abs/2604.10965v1 Data leakage remains a recurrent source of optimistic bias in biomedical machine learning studies. Standard row-wise cross-validation and globally estimated preprocessing steps are often inappropriate for data with repeated measurements, study-level heterogeneity, batch effects, or temporal dependencies. This paper describes bioLeak, an R package for constructing leakage-aware resampling workflows and for auditing fitted models for common leakage mechanisms. The package provides leakage-aware split construction, train-fold-only preprocessing, cross-validated model fitting, nested hyperparameter tuning, post hoc leakage audits, and HTML reporting. The implementation supports binary classification, multiclass classification, regression, and survival analysis, with task-specific metrics and S4 containers for splits, fits, audits, and inflation summaries. The simulation artifacts show how apparent performance changes under controlled leakage mechanisms, and the case study illustrates how guarded and leaky pipelines can yield materially different conclusions on multi-study transcriptomic data. The emphasis throughout is on software design, reproducible workflows, and interpretation of diagnostic output. --- ### Delving Aleatoric Uncertainty in Medical Image Segmentation via Vision Foundation Models Authors: Ruiyang Li, Fang Liu, Licheng Jiao, Xinglin Xie, Jiayao Hao, Shuo Li, Xu Liu, Jingyi Yang, Lingling Li, Puhua Chen, Wenping Ma Published: 2026-04-13 Categories: cs.AI arXiv: https://arxiv.org/abs/2604.10963v1 Medical image segmentation supports clinical workflows by precisely delineating anatomical structures and lesions. However, medical image datasets medical image datasets suffer from acquisition noise and annotation ambiguity, causing pervasive data uncertainty that substantially undermines model robustness. Existing research focuses primarily on model architectural improvements and predictive reliability estimation, while systematic exploration of the intrinsic data uncertainty remains insufficient. To address this gap, this work proposes leveraging the universal representation capabilities of visual foundation models to estimate inherent data uncertainty. Specifically, we analyze the feature diversity of the model's decoded representations and quantify their singular value energy to define the semantic perception scale for each class, thereby measuring sample difficulty and aleatoric uncertainty. Based on this foundation, we design two uncertainty-driven application strategies: (1) the aleatoric uncertainty-aware data filtering mechanism to eliminate potentially noisy samples and enhance model learning quality; (2) the dynamic uncertainty-aware optimization strategy that adaptively adjusts class-specific loss weights during training based on the semantic perception scale, combined with a label denoising mechanism to improve training stability. Experimental results on five public datasets encompassing CT and MRI modalities and involving multi-organ and tumor segmentation tasks demonstrate that our method achieves significant and robust performance improvements across various mainstream network architectures, revealing the broad application potential of aleatoric uncertainty in medical image understanding and segmentation tasks. --- ### RAG-KT: Cross-platform Explainable Knowledge Tracing with Multi-view Fusion Retrieval Generation Authors: Zhiyi Duan, Hongyu Yuan, Rui Liu Published: 2026-04-13 Categories: cs.AI arXiv: https://arxiv.org/abs/2604.10960v2 Knowledge Tracing (KT) infers a student's knowledge state from past interactions to predict future performance. Conventional Deep Learning (DL)-based KT models are typically tied to platform-specific identifiers and latent representations, making them hard to transfer and interpret. Large Language Model (LLM)-based methods can be either ungrounded under prompting or overly domain-dependent under fine-tuning. In addition, most existing KT methods are developed and evaluated under a same-distribution assumption. In real deployments, educational data often arise from heterogeneous platforms with substantial distribution shift, which often degrades generalization. To this end, we propose RAG-KT, a retrieval-augmented paradigm that frames cross-platform KT as reliable context constrained inference with LLMs. It builds a unified multi-source structured context with cross-source alignment via Question Group abstractions and retrieves complementary rich and reliable context for each prediction, enabling grounded prediction and interpretable diagnosis. Experiments on three public KT benchmarks demonstrate consistent gains in accuracy and robustness, including strong performance under cross-platform conditions. --- ### Continuous-time Online Learning via Mean-Field Neural Networks: Regret Analysis in Diffusion Environments Authors: Erhan Bayraktar, Bingyan Han, Ziqing Zhang Published: 2026-04-13 Categories: cs.LG, cs.AI, math.OC arXiv: https://arxiv.org/abs/2604.10958v1 We study continuous-time online learning where data are generated by a diffusion process with unknown coefficients. The learner employs a two-layer neural network, continuously updating its parameters in a non-anticipative manner. The mean-field limit of the learning dynamics corresponds to a stochastic Wasserstein gradient flow adapted to the data filtration. We establish regret bounds for both the mean-field limit and finite-particle system. Our analysis leverages the logarithmic Sobolev inequality, Polyak-Lojasiewicz condition, Malliavin calculus, and uniform-in-time propagation of chaos. Under displacement convexity, we obtain a constant static regret bound. In the general non-convex setting, we derive explicit linear regret bounds characterizing the effects of data variation, entropic exploration, and quadratic regularization. Finally, our simulations demonstrate the outperformance of the online approach and the impact of network width and regularization parameters. --- ### A molecular clock for writing systems reveals the quantitative impact of imperial power on cultural evolution Authors: Hiroki Fukui Published: 2026-04-13 Categories: q-bio.PE, cs.AI, cs.CL, cs.CY arXiv: https://arxiv.org/abs/2604.10957v1 Writing systems are cultural replicators whose evolution has never been studied quantitatively at global scale. We compile the Global Script Database (GSD): 300 writing and notation systems, 50 binary structural characters, and 259 phylogenetic edges spanning 5,400 years. Applying four methods -- phenetics, cladistics, Bayesian inference, and neural network clustering -- we find that scripts exhibit a detectable molecular clock. The best-fitting model (Mk+Gamma strict clock) yields a substitution rate of q = 0.226 substitutions/character/millennium (95% CI: 0.034-1.22; Delta BIC = -4.1 versus relaxed clock; Delta BIC = -1,364.7 versus Mk without rate variation). Political interventions break this clock: deviation from expected divergence times correlates with intervention intensity (Spearman rho = 0.556, p < 10^{-4}), and per-character rate analysis reveals that intervention selectively rewrites deep structural features rather than merely accelerating change (rate profile correlation rho = 0.320). We identify 30 major script replacement events and rank their destructive impact. A ceiling effect suppresses independent invention wherever writing already exists (Fisher's exact OR = 0.054, p < 10^{-6}), and colonial contact predicts script extinction (Cox HR = 5.25, p = 0.0006). The Spanish Empire extinguished the most scripts (6 of 12 contacted, 50%), followed by the Empire of Japan (3 of 9, 33.3%). Feature coding was validated by inter-rater reliability testing with two independent human coders (Cohen's kappa = 0.877; human-LLM kappa = 0.929; Fleiss' kappa = 0.911). --- ### Hypergraph Neural Diffusion: A PDE-Inspired Framework for Hypergraph Message Passing Authors: Zhiheng Zhou, Mengyao Zhou, Xixun Lin, Xingqin Qi, Guiying Yan Published: 2026-04-13 Categories: cs.LG arXiv: https://arxiv.org/abs/2604.10955v1 Hypergraph neural networks (HGNNs) have shown remarkable potential in modeling high-order relationships that naturally arise in many real-world data domains. However, existing HGNNs often suffer from shallow propagation, oversmoothing, and limited adaptability to complex hypergraph structures. In this paper, we propose Hypergraph Neural Diffusion (HND), a novel framework that unifies nonlinear diffusion equations with neural message passing on hypergraphs. HND is grounded in a continuous-time hypergraph diffusion equation, formulated via hypergraph gradient and divergence operators, and modulated by a learnable, structure-aware coefficient matrix over hyperedge-node pairs. This partial differential equation (PDE) based formulation provides a physically interpretable view of hypergraph learning, where feature propagation is understood as an anisotropic diffusion process governed by local inconsistency and adaptive diffusion coefficient. From this perspective, neural message passing becomes a discretized gradient flow that progressively minimizes a diffusion energy functional. We derive rigorous theoretical guarantees, including energy dissipation, solution boundedness via a discrete maximum principle, and stability under explicit and implicit numerical schemes. The HND framework supports a variety of integration strategies such as non-adaptive-step (like Runge-Kutta) and adaptive-step solvers, enabling the construction of deep, stable, and interpretable architectures. Extensive experiments on benchmark datasets demonstrate that HND achieves competitive performance. Our results highlight the power of PDE-inspired design in enhancing the stability, expressivity, and interpretability of hypergraph learning. --- ### FineEdit: Fine-Grained Image Edit with Bounding Box Guidance Authors: Haohang Xu, Lin Liu, Zhibo Zhang, Rong Cong, Xiaopeng Zhang, Qi Tian Published: 2026-04-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.10954v1 Diffusion-based image editing models have achieved significant progress in real world applications. However, conventional models typically rely on natural language prompts, which often lack the precision required to localize target objects. Consequently, these models struggle to maintain background consistency due to their global image regeneration paradigm. Recognizing that visual cues provide an intuitive means for users to highlight specific areas of interest, we utilize bounding boxes as guidance to explicitly define the editing target. This approach ensures that the diffusion model can accurately localize the target while preserving background consistency. To achieve this, we propose FineEdit, a multi-level bounding box injection method that enables the model to utilize spatial conditions more effectively. To support this high precision guidance, we present FineEdit-1.2M, a large scale, fine-grained dataset comprising 1.2 million image editing pairs with precise bounding box annotations. Furthermore, we construct a comprehensive benchmark, termed FineEdit-Bench, which includes 1,000 images across 10 subjects to effectively evaluate region based editing capabilities. Evaluations on FineEdit-Bench demonstrate that our model significantly outperforms state-of-the-art open-source models (e.g., Qwen-Image-Edit and LongCat-Image-Edit) in instruction compliance and background preservation. Further assessments on open benchmarks (GEdit and ImgEdit Bench) confirm its superior generalization and robustness. --- ### UniPROT: Uniform Prototype Selection via Partial Optimal Transport with Submodular Guarantees Authors: Prateek Chanda, Prayas Agrawal, Karthik S. Gurumoorthy, Ganesh Ramakrishnan, Bamdev Mishra, Pratik Jawanpuria Published: 2026-04-13 Categories: cs.LG arXiv: https://arxiv.org/abs/2604.10952v1 Selecting prototypical examples from a source distribution to represent a target data distribution is a fundamental problem in machine learning. Existing subset selection methods often rely on implicit importance scores, which can be skewed towards majority classes and lead to low-quality prototypes for minority classes. We present $\methodprop$, a novel subset selection framework that minimizes the optimal transport (OT) distance between a uniformly weighted prototypical distribution and the target distribution. While intuitive, this formulation leads to a cardinality-constrained maximization of a \emph{super-additive} objective, which is generally intractable to approximate efficiently. To address this, we propose a principled reformulation of the OT marginal constraints, yielding a partial optimal transport-based submodular objective. We prove that this reformulation enables a greedy algorithm with a $(1-1/e)$ approximation guarantee relative to the original super-additive maximization problem. Empirically, we showcase that enforcing uniform prototype weights in UniPROT consistently improves minority-class representation in imbalanced classification benchmarks without compromising majority-class accuracy. In both finetuning and pretraining regimes for large language models under domain imbalance, UniPROT enforces uniform source contributions, yielding robust performance gains. Our results establish UniPROT as a scalable, theoretically grounded solution for uniform-weighted prototype selection. Our code is publicly available at GitHub\footnote{Code: https://github.com/efficiency-learning/UniPROT} --- ### Bootstrapping Video Semantic Segmentation Model via Distillation-assisted Test-Time Adaptation Authors: Jihun Kim, Hoyong Kwon, Hyeokjun Kweon, Kuk-Jin Yoon Published: 2026-04-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.10950v2 Fully supervised Video Semantic Segmentation (VSS) relies heavily on densely annotated video data, limiting practical applicability. Alternatively, applying pre-trained Image Semantic Segmentation (ISS) models frame-by-frame avoids annotation costs but ignores crucial temporal coherence. Recent foundation models such as SAM2 enable high-quality mask propagation yet remain impractical for direct VSS due to limited semantic understanding and computational overhead. In this paper, we propose DiTTA (Distillation-assisted Test-Time Adaptation), a novel framework that converts an ISS model into a temporally-aware VSS model through efficient test-time adaptation (TTA), without annotated videos. DiTTA distills SAM2's temporal segmentation knowledge into the ISS model during a brief, single-pass initialization phase, complemented by a lightweight temporal fusion module to aggregate cross-frame context. Crucially, DiTTA achieves robust generalization even when adapting with highly limited partial video snippets (e.g., initial 10%), significantly outperforming zero-shot refinement approaches that repeatedly invoke SAM2 during inference. Extensive experiments on VSPW and Cityscapes demonstrate DiTTA's effectiveness, achieving competitive or superior performance relative to fully-supervised VSS methods, thus providing a practical and annotation-free solution for real-world VSS tasks. --- ### Pseudo-Unification: Entropy Probing Reveals Divergent Information Patterns in Unified Multimodal Models Authors: Songlin Yang, Xianghao Kong, Anyi Rao Published: 2026-04-13 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2604.10949v1 Unified multimodal models (UMMs) were designed to combine the reasoning ability of large language models (LLMs) with the generation capability of vision models. In practice, however, this synergy remains elusive: UMMs fail to transfer LLM-like reasoning to image synthesis and exhibit divergent response behaviors. We term this phenomenon pseudo-unification. Diagnosing its internal causes is important, but existing probing methods either lack model-internal insight or ignore prompt-response dependencies. To address these limitations, we propose an information-theoretic probing framework that jointly analyzes how UMMs encode inputs and generate outputs. Applied to ten representative UMMs, our framework reveals that pseudo-unification stems from a dual divergence: (i) Modality-Asymmetric Encoding, where vision and language follow different entropy trajectories, and (ii) Pattern-Split Response, where text generation exhibits high-entropy creativity while image synthesis enforces low-entropy fidelity. Only models that unify both sides (e.g., via contextual prediction) achieve more genuine unification, enabling stronger reasoning-based text-to-image generation even with fewer parameters. Our work provides the first model-internal probing of unification, demonstrating that real multimodal synergy requires consistency in information flow, not just shared parameters. --- ### Learning to Adapt: In-Context Learning Beyond Stationarity Authors: Zhen Qin, Jiachen Jiang, Zhihui Zhu Published: 2026-04-13 Categories: cs.LG, math.OC arXiv: https://arxiv.org/abs/2604.10946v1 Transformer models have become foundational across a wide range of scientific and engineering domains due to their strong empirical performance. A key capability underlying their success is in-context learning (ICL): when presented with a short prompt from an unseen task, transformers can perform per-token and next-token predictions without any parameter updates. Recent theoretical efforts have begun to uncover the mechanisms behind this phenomenon, particularly in supervised regression settings. However, these analyses predominantly assume stationary task distributions, which overlook a broad class of real-world scenarios where the target function varies over time. In this work, we bridge this gap by providing a theoretical analysis of ICL under non-stationary regression problems. We study how the gated linear attention (GLA) mechanism adapts to evolving input-output relationships and rigorously characterize its advantages over standard linear attention in this dynamic setting. To model non-stationarity, we adopt a first-order autoregressive process and show that GLA achieves lower training and testing errors by adaptively modulating the influence of past inputs -- effectively implementing a learnable recency bias. Our theoretical findings are further supported by empirical results, which validate the benefits of gating mechanisms in non-stationary ICL tasks. --- ### Progressive Deep Learning for Automated Spheno-Occipital Synchondrosis Maturation Assessment Authors: Omid Halimi Milani, Amanda Nikho, Marouane Tliba, Lauren Mills, Emadeldeen Hamdan, Ahmet Enis Cetin, Mohammed H. Elnagar Published: 2026-04-13 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2604.10945v1 Accurate assessment of spheno-occipital synchondrosis (SOS) maturation is a key indicator of craniofacial growth and a critical determinant for orthodontic and surgical timing. However, SOS staging from cone-beam CT (CBCT) relies on subtle, continuously evolving morphological cues, leading to high inter-observer variability and poor reproducibility, especially at transitional fusion stages. We frame SOS assessment as a fine-grained visual recognition problem and propose a progressive representation-learning framework that explicitly mirrors how expert clinicians reason about synchondral fusion: from coarse anatomical structure to increasingly subtle patterns of closure. Rather than training a full-capacity network end-to-end, we sequentially grow the model by activating deeper blocks over time, allowing early layers to first encode stable cranial base morphology before higher-level layers specialize in discriminating adjacent maturation stages. This yields a curriculum over network depth that aligns deep feature learning with the biological continuum of SOS fusion. Extensive experiments across convolutional and transformer-based architectures show that this expert-inspired training strategy produces more stable optimization and consistently higher accuracy than standard training, particularly for ambiguous intermediate stages. Importantly, these gains are achieved without changing network architectures or loss functions, demonstrating that training dynamics alone can substantially improve anatomical representation learning. The proposed framework establishes a principled link between expert dental intuition and deep visual representations, enabling robust, data-efficient SOS staging from CBCT and offering a general strategy for modeling other continuous biological processes in medical imaging. --- ### Generative Design for Direct-to-Chip Liquid Cooling for Data Centers Authors: Zheng Liu Published: 2026-04-13 Categories: eess.SY, cs.LG arXiv: https://arxiv.org/abs/2604.10941v1 Rapid growth in artificial intelligence (AI) workloads is driving up data center power densities, increasing the need for advanced thermal management. Direct-to-chip liquid cooling can remove heat efficiently at the source, but many cold plate channel layouts remain heuristic and are not optimized for the strongly non-uniform temperature distribution of modern heterogeneous packages. This work presents a generative design framework for synthesizing cooling channel geometries for the NVIDIA GB200 Grace Blackwell Superchip. A physics-based finite-difference thermal model provides rapid steady-state temperature predictions and supplies spatial thermal feedback to a constrained reaction-diffusion process that generates novel channel topologies while enforcing inlet/outlet and component constraints. By iterating channel generation and thermal evaluation in a closed loop, the method naturally redistributes cooling capacity toward high-power regions and suppresses hot-spot formation. Compared with a baseline parallel channel design, the resulting channels achieve more than a 5 degree Celsius reduction in average temperature and over 35 degree Celsius reduction in maximum temperature. Overall, the results demonstrate that coupling generative algorithms with lightweight physics-based modeling can significantly enhance direct-to-chip liquid cooling performance, supporting more sustainable scaling of AI computing. --- ### AmodalSVG: Amodal Image Vectorization via Semantic Layer Peeling Authors: Juncheng Hu, Ziteng Xue, Guotao Liang, Anran Qi, Buyu Li, Sheng Wang, Dong Xu, Qian Yu Published: 2026-04-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.10940v1 We introduce AmodalSVG, a new framework for amodal image vectorization that produces semantically organized and geometrically complete SVG representations from natural images. Existing vectorization methods operate under a modal paradigm: tracing only visible pixels and disregarding occlusion. Consequently, the resulting SVGs are semantically entangled and geometrically incomplete, limiting SVG's structural editability. In contrast, AmodalSVG reconstructs full object geometries, including occluded regions, into independent, editable vector layers. To achieve this, AmodalSVG reformulates image vectorization as a two-stage framework, performing semantic decoupling and completion in the raster domain to produce amodally complete semantic layers, which are then independently vectorized. In the first stage, we introduce Semantic Layer Peeling (SLP), a VLM-guided strategy that progressively decomposes an image into semantically coherent layers. By hybrid inpainting, SLP recovers complete object appearances under occlusions, enabling explicit semantic decoupling. To vectorize these layers efficiently, we propose Adaptive Layered Vectorization (ALV), which dynamically modulates the primitive budget via an error-budget-driven adjustment mechanism. Extensive experiments demonstrate that AmodalSVG significantly outperforms prior methods in visual fidelity. Moreover, the resulting amodal layers enable object-level editing directly in the vector domain, capabilities not supported by existing vectorization approaches. Code will be released upon acceptance. --- ### QShield: Securing Neural Networks Against Adversarial Attacks using Quantum Circuits Authors: Navid Azimi, Aditya Prakash, Yao Wang, Li Xiong Published: 2026-04-13 Categories: cs.CR, cs.AI, cs.CV, cs.LG, quant-ph arXiv: https://arxiv.org/abs/2604.10933v2 Deep neural networks remain highly vulnerable to adversarial perturbations, limiting their reliability in security- and safety-critical applications. To address this challenge, we introduce QShield, a modular hybrid quantum-classical neural network (HQCNN) architecture designed to enhance the adversarial robustness of classical deep learning models. QShield integrates a conventional convolutional neural network (CNN) backbone for feature extraction with a quantum processing module that encodes the extracted features into quantum states, applies structured entanglement operations under realistic noise models, and outputs a hybrid prediction through a dynamically weighted fusion mechanism implemented via a lightweight multilayer perceptron (MLP). We systematically evaluate both classical and hybrid quantum-classical models on the MNIST, OrganAMNIST, and CIFAR-10 datasets, using a comprehensive set of robustness, efficiency, and computational performance metrics. Our results demonstrate that classical models are highly vulnerable to adversarial attacks, whereas the proposed hybrid models with entanglement patterns maintain high predictive accuracy while substantially reducing attack success rates across a wide range of adversarial attacks. Furthermore, the proposed hybrid architecture significantly increased the computational cost required to generate adversarial examples, thereby introducing an additional layer of defense. These findings indicate that the proposed modular hybrid architecture achieves a practical balance between predictive accuracy and adversarial robustness, positioning it as a promising approach for secure and reliable machine learning in sensitive and safety-critical applications. --- ### On the Use of Bi-Objective Evolutionary Algorithms for the Stochastic MKP under Dynamic Constraints Authors: Ishara Hewa Pathiranage, Aneta Neumann Published: 2026-04-13 Categories: cs.NE arXiv: https://arxiv.org/abs/2604.10930v1 The multiple knapsack problem (MKP) generalizes the classical knapsack problem by assigning items to multiple knapsacks subject to capacity constraints. It is used to model many real-world resource allocation and scheduling problems. In practice, these optimization problems often involve stochastic and dynamic components. Evolutionary algorithms provide a flexible framework for addressing such problems under uncertainty and dynamic changes. In this paper, we investigate a stochastic and dynamic variant of MKP with chance constraints, where the item weights are modeled as independent normally distributed random variables and knapsack capacities change during the optimization process. We formulate the problem as a bi-objective optimization formulation that balances profit maximization and probabilistic capacity satisfaction at a given confidence level. We conduct an empirical comparison of four widely used multi-objective evolutionary algorithms (MOEAs), representing both decomposition- and dominance-based search paradigms. The algorithms are evaluated under varying uncertainty levels, confidence thresholds, and dynamic change settings. The results provide comparative insights into the behavior of decomposition-based and dominance-based MOEAs for stochastic MKP under dynamic constraints. --- ### LiveGesture Streamable Co-Speech Gesture Generation Model Authors: Muhammad Usama Saleem, Mayur Jagdishbhai Patel, Ekkasit Pinyoanuntapong, Zhongxing Qin, Li Yang, Hongfei Xue, Ahmed Helmy, Chen Chen, Pu Wang Published: 2026-04-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.10927v1 We propose LiveGesture, the first fully streamable, speech-driven full-body gesture generation framework that operates with zero look-ahead and supports arbitrary sequence length. Unlike existing co-speech gesture methods, which are designed for offline generation and either treat body regions independently or entangle all joints within a single model, LiveGesture is built from the ground up for causal, region-coordinated motion generation. LiveGesture consists of two main modules: the Streamable Vector Quantized Motion Tokenizer (SVQ) and the Hierarchical Autoregressive Transformer (HAR). The SVQ tokenizer converts the motion sequence of each body region into causal, discrete motion tokens, enabling real-time, streamable token decoding. On top of SVQ, HAR employs region-expert autoregressive (xAR) transformers to model expressive, fine-grained motion dynamics for each body region. A causal spatio-temporal fusion module (xAR Fusion) then captures and integrates correlated motion dynamics across regions. Both xAR and xAR Fusion are conditioned on live, continuously arriving audio signals encoded by a streamable causal audio encoder. To enhance robustness under streaming noise and prediction errors, we introduce autoregressive masking training, which leverages uncertainty-guided token masking and random region masking to expose the model to imperfect, partially erroneous histories during training. Experiments on the BEAT2 dataset demonstrate that LiveGesture produces coherent, diverse, and beat-synchronous full-body gestures in real time, matching or surpassing state-of-the-art offline methods under true zero look-ahead conditions. --- ### From Words to Widgets for Controllable LLM Generation Authors: Chao Zhang, Yiren Liu, Lunyiu Nie, Jeffrey M. Rzeszotarski, Yun Huang, Tal August Published: 2026-04-13 Categories: cs.HC, cs.CL arXiv: https://arxiv.org/abs/2604.10925v3 Natural language remains the predominant way people interact with large language models (LLMs). However, users often struggle to precisely express and control subjective preferences (e.g., tone, style, and emphasis) through prompting. We propose Malleable Prompting, a new interactive prompting technique for controllable LLM generation. It reifies preference expressions in natural language prompts into GUI widgets (e.g., sliders, dropdowns, and toggles) that users can directly configure to steer generation, while visualizing each control's influence on the output to support attribution and comparison across iterations. To enable this interaction, we introduce an LLM decoding algorithm that modulates the token probability distribution during generation based on preference expressions and their widget values. Through a user study, we show that Malleable Prompting helps participants achieve target preferences more precisely and is perceived as more controllable and transparent than natural language prompting alone. ---