# Research Papers — 2026-04 · bundle page 138 of 233 > Full-text markdown of papers #6851–6900 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/138 [← Previous bundle](https://aipod.dev/papers/archive/2026-04/page/137.md) [Next bundle →](https://aipod.dev/papers/archive/2026-04/page/139.md) ### RECIPER: A Dual-View Retrieval Pipeline for Procedure-Oriented Materials Question Answering Authors: Zhuoyu Wu, Wenhui Ou, Pei-Sze Tan, Wenqi Fang, Sailaja Rajanala, Raphaël C. -W. Phan Published: 2026-04-13 Categories: eess.SP, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2604.11229v1 Retrieving procedure-oriented evidence from materials science papers is difficult because key synthesis details are often scattered across long, context-heavy documents and are not well captured by paragraph-only dense retrieval. We present RECIPER, a dual-view retrieval pipeline that indexes both paragraph-level context and compact large language model-extracted procedural summaries, then combines the two candidate streams with lightweight lexical reranking. Across four dense retrieval backbones, RECIPER consistently improves early-rank retrieval over paragraph-only dense retrieval, achieving average gains of +3.73 in Recall@1, +2.85 in nDCG@10, and +3.13 in MRR. With BGE-large-en-v1.5, it reaches 86.82%, 97.07%, and 97.85% on Recall@1, Recall@5, and Recall@10, respectively. We further observe improved downstream question answering under automatic metrics, suggesting that procedural summaries can serve as a useful complementary retrieval signal for procedure-oriented materials question answering. Code and data are available at https://github.com/ReaganWu/RECIPER. --- ### Sign Language Recognition in the Age of LLMs Authors: Vaclav Javorek, Jakub Honzik, Ivan Gruber, Tomas Zelezny, Marek Hruz Published: 2026-04-13 Categories: cs.CV, cs.CL arXiv: https://arxiv.org/abs/2604.11225v1 Recent Vision Language Models (VLMs) have demonstrated strong performance across a wide range of multimodal reasoning tasks. This raises the question of whether such general-purpose models can also address specialized visual recognition problems such as isolated sign language recognition (ISLR) without task-specific training. In this work, we investigate the capability of modern VLMs to perform ISLR in a zero-shot setting. We evaluate several open-source and proprietary VLMs on the WLASL300 benchmark. Our experiments show that, under prompt-only zero-shot inference, current open-source VLMs remain far behind classic supervised ISLR classifiers by a wide margin. However, follow-up experiments reveal that these models capture partial visual-semantic alignment between signs and text descriptions. Larger proprietary models achieve substantially higher accuracy, highlighting the importance of model scale and training data diversity. All our code is publicly available on GitHub. --- ### Regional Explanations: Bridging Local and Global Variable Importance Authors: Salim I. Amoukou, Nicolas J-B. Brunel Published: 2026-04-13 Categories: stat.ML, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2604.11223v1 We analyze two widely used local attribution methods, Local Shapley Values and LIME, which aim to quantify the contribution of a feature value $x_i$ to a specific prediction $f(x_1, \dots, x_p)$. Despite their widespread use, we identify fundamental limitations in their ability to reliably detect locally important features, even under ideal conditions with exact computations and independent features. We argue that a sound local attribution method should not assign importance to features that neither influence the model output (e.g., features with zero coefficients in a linear model) nor exhibit statistical dependence with functionality-relevant features. We demonstrate that both Local SV and LIME violate this fundamental principle. To address this, we propose R-LOCO (Regional Leave Out COvariates), which bridges the gap between local and global explanations and provides more accurate attributions. R-LOCO segments the input space into regions with similar feature importance characteristics. It then applies global attribution methods within these regions, deriving an instance's feature contributions from its regional membership. This approach delivers more faithful local attributions while avoiding local explanation instability and preserving instance-specific detail often lost in global methods. --- ### H-SPAM: Hierarchical Superpixel Anything Model Authors: Julien Walther, Rémi Giraud, Michaël Clément Published: 2026-04-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.11218v1 Superpixels offer a compact image representation by grouping pixels into coherent regions. Recent methods have reached a plateau in terms of segmentation accuracy by generating noisy superpixel shapes. Moreover, most existing approaches produce a single fixed-scale partition that limits their use in vision pipelines that would benefit multi-scale representations. In this work, we introduce H-SPAM (Hierarchical Superpixel Anything Model), a unified framework for generating accurate, regular, and perfectly nested hierarchical superpixels. Starting from a fine partition, guided by deep features and external object priors, H-SPAM constructs the hierarchy through a two-phase region merging process that first preserves object consistency and then allows controlled inter-object grouping. The hierarchy can also be modulated using visual attention maps or user input to preserve important regions longer in the hierarchy. Experiments on standard benchmarks show that H-SPAM strongly outperforms existing hierarchical methods in both accuracy and regularity, while performing on par with most recent state-of-the-art non-hierarchical methods. Code and pretrained models are available: https://github.com/waldo-j/hspam. --- ### Measuring the Authority Stack of AI Systems: Empirical Analysis of 366,120 Forced-Choice Responses Across 8 AI Models Authors: Seulki Lee Published: 2026-04-13 Categories: cs.AI arXiv: https://arxiv.org/abs/2604.11216v1 What values, evidence preferences, and source trust hierarchies do AI systems actually exhibit when facing structured dilemmas? We present the first large-scale empirical mapping of AI decision-making across all three layers of the Authority Stack framework (S. Lee, 2026a): value priorities (L4), evidence-type preferences (L3), and source trust hierarchies (L2). Using the PRISM benchmark -- a forced-choice instrument of 14,175 unique scenarios per layer, spanning 7 professional domains, 3 severity levels, 3 decision timeframes, and 5 scenario variants -- we evaluated 8 major AI models at temperature 0, yielding 366,120 total responses. Key findings include: (1) a symmetric 4:4 split between Universalism-first and Security-first models at L4; (2) dramatic defense-domain value restructuring where Security surges to near-ceiling win-rates (95.1%-99.8%) in 6 of 8 models; (3) divergent evidence hierarchies at L3, with some models favoring empirical-scientific evidence while others prefer pattern-based or experiential evidence; (4) broad convergence on institutional source trust at L2; and (5) Paired Consistency Scores (PCS) ranging from 57.4% to 69.2%, revealing substantial framing sensitivity across scenario variants. Test-Retest Reliability (TRR) ranges from 91.7% to 98.6%, indicating that value instability stems primarily from variant sensitivity rather than stochastic noise. These findings demonstrate that AI models possess measurable -- if sometimes unstable -- Authority Stacks with consequential implications for deployment across professional domains. --- ### HiEdit: Lifelong Model Editing with Hierarchical Reinforcement Learning Authors: Yangfan Wang, Tianyang Sun, Chen Tang, Jie Liu, Wei Cai, Jingchi Jiang Published: 2026-04-13 Categories: cs.CL arXiv: https://arxiv.org/abs/2604.11214v1 Lifelong model editing (LME) aims to sequentially rectify outdated or inaccurate knowledge in deployed LLMs while minimizing side effects on unrelated inputs. However, existing approaches typically apply parameter perturbations to a static and dense set of LLM layers for all editing instances. This practice is counter-intuitive, as we hypothesize that different pieces of knowledge are stored in distinct layers of the model. Neglecting this layer-wise specificity can impede adaptability in integrating new knowledge and result in catastrophic forgetting for both general and previously edited knowledge. To address this, we propose HiEdit, a hierarchical reinforcement learning framework that adaptively identifies the most knowledge-relevant layers for each editing instance. By enabling dynamic, instance-aware layer selection and incorporating an intrinsic reward for sparsity, HiEdit achieves precise, localized updates. Experiments on various LLMs show that HiEdit boosts the performance of the competitive RLEdit by an average of 8.48% with perturbing only half of the layers per edit. Our code is available at: https://github.com/yangfanww/hiedit. --- ### 3DTV: A Feedforward Interpolation Network for Real-Time View Synthesis Authors: Stefan Schulz, Fernando Edelstein, Hannah Dröge, Matthias B. Hullin, Markus Plack Published: 2026-04-13 Categories: cs.CV, cs.LG, cs.MM arXiv: https://arxiv.org/abs/2604.11211v1 Real-time free-viewpoint rendering requires balancing multi-camera redundancy with the latency constraints of interactive applications. We address this challenge by combining lightweight geometry with learning and propose 3DTV, a feedforward network for real-time sparse-view interpolation. A Delaunay-based triplet selection ensures angular coverage for each target view. Building on this, we introduce a pose-aware depth module that estimates a coarse-to-fine depth pyramid, enabling efficient feature reprojection and occlusion-aware blending. Unlike methods that require scene-specific optimization, 3DTV runs feedforward without retraining, making it practical for AR/VR, telepresence, and interactive applications. Our experiments on challenging multi-view video datasets demonstrate that 3DTV consistently achieves a strong balance of quality and efficiency, outperforming recent real-time novel-view baselines. Crucially, 3DTV avoids explicit proxies, enabling robust rendering across diverse scenes. This makes it a practical solution for low-latency multi-view streaming and interactive rendering. Project Page: https://stefanmschulz.github.io/3DTV_webpage/ --- ### Exploring Knowledge Conflicts for Faithful LLM Reasoning: Benchmark and Method Authors: Tianzhe Zhao, Jiaoyan Chen, Shuxiu Zhang, Haiping Zhu, Qika Lin, Jun Liu Published: 2026-04-13 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2604.11209v1 Large language models (LLMs) have achieved remarkable success across a wide range of applications especially when augmented by external knowledge through retrieval-augmented generation (RAG). Despite their widespread adoption, recent studies have shown that LLMs often struggle to perform faithful reasoning when conflicting knowledge is retrieved. However, existing work primarily focuses on conflicts between external knowledge and the parametric knowledge of LLMs, leaving conflicts across external knowledge largely unexplored. Meanwhile, modern RAG systems increasingly emphasize the integration of unstructured text and (semi-)structured data like knowledge graphs (KGs) to improve knowledge completeness and reasoning faithfulness. To address this gap, we introduce ConflictQA, a novel benchmark that systematically instantiates conflicts between textual evidence and KG evidence. Extensive evaluations across representative LLMs reveal that, facing such cross-source conflicts, LLMs often fail to identify reliable evidence for correct reasoning. Instead, LLMs become more sensitive to prompting choices and tend to rely exclusively on either KG or textual evidence, resulting in incorrect responses. Based on these findings, we further propose XoT, a two-stage explanation-based thinking framework tailored for reasoning over heterogeneous conflicting evidence, and verify its effectiveness with extensive experiments. --- ### LoViF 2026 Challenge on Human-oriented Semantic Image Quality Assessment: Methods and Results Authors: Xin Li, Daoli Xu, Wei Luo, Guoqiang Xiang, Haoran Li, Chengyu Zhuang, Zhibo Chen, Jian Guan, Weiping Li, Weixia Zhang, Wei Sun, Zhihua Wang et al. Published: 2026-04-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.11207v2 This paper reviews the LoViF 2026 Challenge on Human-oriented Semantic Image Quality Assessment. This challenge aims to raise a new direction, i.e., how to evaluate the loss of semantic information from the human perspective, intending to promote the development of some new directions, like semantic coding, processing, and semantic-oriented optimization, etc. Unlike existing datasets of quality assessment, we form a dataset of human-oriented semantic quality assessment, termed the SeIQA dataset. This dataset is divided into three parts for this competition: (i) training data: 510 pairs of degraded images and their corresponding ground truth references; (ii) validation data: 80 pairs of degraded images and their corresponding ground-truth references; (iii) testing data: 160 pairs of degraded images and their corresponding ground-truth references. The primary objective of this challenge is to establish a new and powerful benchmark for human-oriented semantic image quality assessment. There are a total of 58 teams registered in this competition, and 6 teams submitted valid solutions and fact sheets for the final testing phase. These submissions achieved state-of-the-art (SOTA) performance on the SeIQA dataset. --- ### Designing Adaptive Digital Nudging Systems with LLM-Driven Reasoning Authors: Tiziano Santilli, Mina Alipour, Mahyar Tourchi Moghaddam Published: 2026-04-13 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2604.11206v1 Digital nudging systems lack architectural guidance for translating behavioral science into software design. While research identifies nudge strategies and quality attributes, existing architectures fail to integrate multi-dimensional user modeling with ethical compliance as architectural concerns. We present an architecture that uses behavioral theory through explicit architectural decisions, treating ethics and fairness as structural guardrails rather than implementation details. A literature review synthesized 68 nudging strategies, 11 quality attributes, and 3 user profiling dimensions into architectural requirements. The architecture implements sequential processing layers with cross-cutting evaluation modules enforcing regulatory compliance. Validation with 13 software architects confirmed requirements satisfaction and domain transferability. An LLM-powered proof-of-concept in residential energy sustainability demonstrated feasibility through evaluation with 15 users, achieving high perceived intervention quality and measurable positive emotional impact. This work bridges behavioral science and software architecture by providing reusable patterns for adaptive systems that balance effectiveness with ethical constraints. --- ### CapBench: A Multi-PDK Dataset for Machine-Learning-Based Post-Layout Capacitance Extraction Authors: Hector R. Rodriguez, Jiechen Huang, Wenjian Yu Published: 2026-04-13 Categories: cs.AR, cs.LG arXiv: https://arxiv.org/abs/2604.11202v1 We present CapBench, a fully reproducible, multi-PDK dataset for capacitance extraction. The dataset is derived from open-source designs, including single-core CPUs, systems-on-chip, and media accelerators. All designs are fully placed and routed using 14 independent OpenROAD flow runs spanning three technology nodes: ASAP7, NanGate45, and Sky130HD. From these layouts, we extract 61,855 3D windows across three size tiers to enable transfer learning and scalability studies. High-fidelity capacitance labels are generated using RWCap, a state-of-the-art random-walk solver, and validated against the industry-standard Raphael, achieving a mean absolute error of 0.64% for total capacitance. Each window is pre-processed into density maps, graph representations, and point clouds. We evaluate 10 machine learning architectures that illustrate dataset usage and serve as baselines, including convolutional neural networks (CNNs), point cloud transformers, and graph neural networks (GNNs). CNNs demonstrate the lowest errors (1.75%), while GNNs are up to 41.4x faster but exhibit larger errors (10.2%), illustrating a clear accuracy-speed trade-off. Code and dataset are available at https://github.com/THU-numbda/CapBench. --- ### CocoaBench: Evaluating Unified Digital Agents in the Wild Authors: CocoaBench Team, Shibo Hao, Zhining Zhang, Zhiqi Liang, Tianyang Liu, Yuheng Zha, Qiyue Gao, Jixuan Chen, Zilong Wang, Zhoujun Cheng, Haoxiang Zhang, Junli Wang et al. Published: 2026-04-13 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2604.11201v2 LLM agents now perform strongly in software engineering, deep research, GUI automation, and various other applications, while recent agent scaffolds and models are increasingly integrating these capabilities into unified systems. Yet, most evaluations still test these capabilities in isolation, which leaves a gap for more diverse use cases that require agents to combine different capabilities. We introduce CocoaBench, a benchmark for unified digital agents built from human-designed, long-horizon tasks that require flexible composition of vision, search, and coding. Tasks are specified only by an instruction and an automatic evaluation function over the final output, enabling reliable and scalable evaluation across diverse agent infrastructures. We also present CocoaAgent, a lightweight shared scaffold for controlled comparison across model backbones. Experiments show that current agents remain far from reliable on CocoaBench, with the best evaluated system achieving only 45.1% success rate. Our analysis further points to substantial room for improvement in reasoning and planning, tool use and execution, and visual grounding. --- ### ShapShift: Explaining Model Prediction Shifts with Subgroup Conditional Shapley Values Authors: Tom Bewley, Salim I. Amoukou, Emanuele Albini, Saumitra Mishra, Manuela Veloso Published: 2026-04-13 Categories: cs.LG, cs.AI, stat.ML arXiv: https://arxiv.org/abs/2604.11200v1 Changes in input distribution can induce shifts in the average predictions of machine learning models. Such prediction shifts may impact downstream business outcomes (e.g. a bank's loan approval rate), so understanding their causes can be crucial. We propose \ours{}: a Shapley value method for attributing prediction shifts to changes in the conditional probabilities of interpretable subgroups of data, where these subgroups are defined by the structure of decision trees. We initially apply this method to single decision trees, providing exact explanations based on conditional probability changes at split nodes. Next, we extend it to tree ensembles by selecting the most explanatory tree and accounting for residual effects. Finally, we propose a model-agnostic variant using surrogate trees grown with a novel objective function, allowing application to models like neural networks. While exact computation can be intensive, approximation techniques enable practical application. We show that \ours{} provides simple, faithful, and near-complete explanations of prediction shifts across model classes, aiding model monitoring in dynamic environments. --- ### From Time Series to State: Situation-Aware Modeling for Air Traffic Flow Prediction Authors: Anqi Liu, Jiangtao Zhao, Guiyuan Jiang, Feng Hong, Yanwei Yu, Bin Wang Published: 2026-04-13 Categories: cs.LG arXiv: https://arxiv.org/abs/2604.11198v3 Accurate air traffic prediction in the terminal airspace (TA) is pivotal for proactive air traffic management (ATM). However, existing data-driven approaches predominantly rely on time series-based forecasting paradigms, which inherently overlook critical aircraft state information, such as real-time kinematics and proximity to airspace boundaries. To address this limitation, we propose \textit{AeroSense}, a direct state-to-flow modeling framework for air traffic prediction. Unlike classical time series-based methods that first aggregate aircraft trajectories into macroscopic flow sequences before modeling, AeroSense explicitly represents the real-time airspace situation as \textit{a dynamic set of aircraft states}, enabling the direct processing of a variable number of aircraft instead of time series as inputs. Specifically, we introduce a situation-aware state representation that enables AeroSense to sense the instantaneous terminal airspace situation directly from microscopic aircraft states. Furthermore, we design a model architecture that incorporates masked self-attention to capture inter-aircraft interactions, together with two decoupled prediction heads to model heterogeneous flow dynamics across two key functional areas of the TA. Extensive experiments on a large-scale real-world airport dataset demonstrate that AeroSense consistently achieves state-of-the-art performance, validating that direct modeling of microscopic aircraft states yields substantially higher predictive fidelity than time series-based baselines. Moreover, the proposed framework exhibits superior robustness during peak traffic periods, achieves Pareto-optimal performance under dayparting multi-object evaluation, and provides meaningful interpretability through attention-based visualizations. --- ### MedP-CLIP: Medical CLIP with Region-Aware Prompt Integration Authors: Jiahui Peng, He Yao, Jingwen Li, Yanzhou Su, Sibo Ju, Yujie Lu, Jin Ye, Hongchun Lu, Xue Li, Lincheng Jiang, Min Zhu, Junlong Cheng Published: 2026-04-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.11197v3 Contrastive Language-Image Pre-training (CLIP) has demonstrated outstanding performance in global image understanding and zero-shot transfer through large-scale text-image alignment. However, the core of medical image analysis often lies in the fine-grained understanding of specific anatomical structures or lesion regions. Therefore, precisely comprehending region-of-interest (RoI) information provided by medical professionals or perception models becomes crucial. To address this need, we propose MedP-CLIP, a region-aware medical vision-language model (VLM). MedP-CLIP innovatively integrates medical prior knowledge and designs a feature-level region prompt integration mechanism, enabling it to flexibly respond to various prompt forms (e.g., points, bounding boxes, masks) while maintaining global contextual awareness when focusing on local regions. We pre-train the model on a meticulously constructed large-scale dataset (containing over 6.4 million medical images and 97.3 million region-level annotations), equipping it with cross-disease and cross-modality fine-grained spatial semantic understanding capabilities. Experiments demonstrate that MedP-CLIP significantly outperforms baseline methods in various medical tasks, including zero-shot recognition, interactive segmentation, and empowering multimodal large language models. This model provides a scalable, plug-and-play visual backbone for medical AI, combining holistic image understanding with precise regional analysis. --- ### Towards Adaptive Open-Set Object Detection via Category-Level Collaboration Knowledge Mining Authors: Yuqi Ji, Junjie Ke, Lihuo He, Lizhi Wang, Xinbo Gao Published: 2026-04-13 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2604.11195v1 Existing object detectors often struggle to generalize across domains while adapting to emerging novel categories. Adaptive open-set object detection (AOOD) addresses this challenge by training on base categories in the source domain and adapting to both base and novel categories in the target domain without target annotations. However, current AOOD methods remain limited by weak cross-domain representations, ambiguity among novel categories, and source-domain feature bias. To address these issues, we propose a category-level collaboration knowledge mining strategy that exploits both inter-class and intra-class relationships across domains. Specifically, we construct a clustering-based memory bank to encode class prototypes, auxiliary features, and intra-class disparity information, and iteratively update it via unsupervised clustering to enhance category-level knowledge representation. We further design a base-to-novel selection metric to discover source-domain features related to novel categories and use them to initialize novel-category classifiers. In addition, an adaptive feature assignment strategy transfers the learned category-level knowledge to the target domain and asynchronously updates the memory bank to alleviate source-domain bias. Extensive experiments on multiple benchmarks show that our method consistently surpasses state-of-the-art AOOD methods by 1.1-5.5 mAP. --- ### TRACE: An Experiential Framework for Coherent Multi-hop Knowledge Graph Question Answering Authors: Yingxu Wang, Jiaxin Huang, Mengzhu Wang, Nan Yin Published: 2026-04-13 Categories: cs.CL arXiv: https://arxiv.org/abs/2604.11193v1 Multi-hop Knowledge Graph Question Answering (KGQA) requires coherent reasoning across relational paths, yet existing methods often treat each reasoning step independently and fail to effectively leverage experience from prior explorations, leading to fragmented reasoning and redundant exploration. To address these challenges, we propose Trajectoryaware Reasoning with Adaptive Context and Exploration priors (TRACE), an experiential framework that unifies LLM-driven contextual reasoning with exploration prior integration to enhance the coherence and robustness of multihop KGQA. Specifically, TRACE dynamically translates evolving reasoning paths into natural language narratives to maintain semantic continuity, while abstracting prior exploration trajectories into reusable experiential priors that capture recurring exploration patterns. A dualfeedback re-ranking mechanism further integrates contextual narratives with exploration priors to guide relation selection during reasoning. Extensive experiments on multiple KGQA benchmarks demonstrate that TRACE consistently outperforms state-of-the-art baselines. --- ### MathAgent: Adversarial Evolution of Constraint Graphs for Mathematical Reasoning Data Synthesis Authors: Zixiong Yu, Jun Rao, Guhan Chen, Songtao Tian, Bohan Li, Jiansheng Wei, Min Zhang, Xiaojun Meng Published: 2026-04-13 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2604.11188v1 Synthesizing high-quality mathematical reasoning data without human priors remains a significant challenge. Current approaches typically rely on seed data mutation or simple prompt engineering, often suffering from mode collapse and limited logical complexity. This paper proposes a hierarchical synthesis framework that formulates data synthesis as an unsupervised optimization problem over a constraint graph followed by semantic instantiation, rather than treating it as a direct text generation task. We introduce a Legislator-Executor paradigm: The Legislator adversarially evolves structured generation blueprints encoding the constraints of the problem, while the Executor instantiates these specifications into diverse natural language scenarios. This decoupling of skeleton design from linguistic realization enables a prioritized focus on constructing complex and diverse logical structures, thereby guiding high-quality data synthesis. Experiments conducted on a total of 10 models across the Qwen, Llama, Mistral, and Gemma series demonstrate that our method achieves notable results: models fine-tuned on 1K synthesized samples outperform widely-used datasets of comparable scale (LIMO, s1K) across eight mathematical benchmarks, exhibiting superior out-of-distribution generalization. --- ### Taking a Pulse on How Generative AI is Reshaping the Software Engineering Research Landscape Authors: Bianca Trinkenreich, Fabio Calefato, Kelly Blincoe, Viggo Tellefsen Wivestad, Antonio Pedro Santos Alves, Júlia Condé Araújo, Marina Condé Araújo, Paolo Tell, Marcos Kalinowski, Thomas Zimmermann, Margaret-Anne Storey Published: 2026-04-13 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2604.11184v1 Context: Software engineering (SE) researchers increasingly study Generative AI (GenAI) while also incorporating it into their own research practices. Despite rapid adoption, there is limited empirical evidence on how GenAI is used in SE research and its implications for research practices and governance. Aims: We conduct a large-scale survey of 457 SE researchers publishing in top venues between 2023 and 2025. Method: Using quantitative and qualitative analyses, we examine who uses GenAI and why, where it is used across research activities, and how researchers perceive its benefits, opportunities, challenges, risks, and governance. Results: GenAI use is widespread, with many researchers reporting pressure to adopt and align their work with it. Usage is concentrated in writing and early-stage activities, while methodological and analytical tasks remain largely human-driven. Although productivity gains are widely perceived, concerns about trust, correctness, and regulatory uncertainty persist. Researchers highlight risks such as inaccuracies and bias, emphasize mitigation through human oversight and verification, and call for clearer governance, including guidance on responsible use and peer review. Conclusion: We provide a fine-grained, SE-specific characterization of GenAI use across research activities, along with taxonomies of GenAI use cases for research and peer review, opportunities, risks, mitigation strategies, and governance needs. These findings establish an empirical baseline for the responsible integration of GenAI into academic practice. --- ### Evaluating Memory Capability in Continuous Lifelog Scenario Authors: Jianjie Zheng, Zhichen Liu, Zhanyu Shen, Jingxiang Qu, Guanhua Chen, Yile Wang, Yang Xu, Yang Liu, Sijie Cheng Published: 2026-04-13 Categories: cs.CL arXiv: https://arxiv.org/abs/2604.11182v2 Nowadays, wearable devices can continuously lifelog ambient conversations, creating substantial opportunities for memory systems. However, existing benchmarks primarily focus on online one-on-one chatting or human-AI interactions, thus neglecting the unique demands of real-world scenarios. Given the scarcity of public lifelogging audio datasets, we propose a hierarchical synthesis framework to curate \textbf{\textsc{LifeDialBench}}, a novel benchmark comprising two complementary subsets: \textbf{EgoMem}, built on real-world egocentric videos, and \textbf{LifeMem}, constructed using simulated virtual community. Crucially, to address the issue of temporal leakage in traditional offline settings, we propose an \textbf{Online Evaluation} protocol that strictly adheres to temporal causality, ensuring systems are evaluated in a realistic streaming fashion. Our experimental results reveal a counterintuitive finding: current sophisticated memory systems fail to outperform a simple RAG-based baseline. This highlights the detrimental impact of over-designed structures and lossy compression in current approaches, emphasizing the necessity of high-fidelity context preservation for lifelog scenarios. --- ### Probabilistic Prediction of Neural Dynamics via Autoregressive Flow Matching Authors: Nicole Rogalla, Yuzhen Qin, Mario Senden, Ahmed El-Gazzar, Marcel van Gerven Published: 2026-04-13 Categories: q-bio.NC, cs.LG arXiv: https://arxiv.org/abs/2604.11178v1 Forecasting neural activity in response to naturalistic stimuli remains a key challenge for understanding brain dynamics and enabling downstream neurotechnological applications. Here, we introduce a generative forecasting framework for modeling neural dynamics based on autoregressive flow matching (AFM). Building on recent advances in transport-based generative modeling, our approach probabilistically predicts neural responses at scale from multimodal sensory input. Specifically, we learn the conditional distribution of future neural activity given past neural dynamics and concurrent sensory input, explicitly modeling neural activity as a temporally evolving process in which future states depend on recent neural history. We evaluate our framework on the Algonauts project 2025 challenge functional magnetic resonance imaging dataset using subject-specific models. AFM significantly outperforms both a non-autoregressive flow-matching baseline and the official challenge general linear model baseline in predicting short-term parcel-wise blood oxygenation level-dependent (BOLD) activity, demonstrating improved generalization and widespread cortical prediction performance. Ablation analyses show that access to past BOLD dynamics is a dominant driver of performance, while autoregressive factorization yields consistent, modest gains under short-horizon, context-rich conditions. Together, these findings position autoregressive flow-based generative modeling as an effective approach for short-term probabilistic forecasting of neural dynamics with promising applications in closed-loop neurotechnology. --- ### Do Thought Streams Matter? Evaluating Reasoning in Gemini Vision-Language Models for Video Scene Understanding Authors: Shivam Sharma, Sankalp Nagaonkar, Ashish Choithani, Ashutosh Trivedi Published: 2026-04-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.11177v1 We benchmark how internal reasoning traces, which we call thought streams, affect video scene understanding in vision-language models. Using four configurations of Google's Gemini 2.5 Flash and Flash Lite across scenes extracted from 100 hours of video, we ask three questions: does more thinking lead to better outputs, where do the gains stop, and what do these models actually think about? We introduce three evaluation metrics. Contentfulness measures how much of the thought stream is useful scene content versus meta-commentary. Thought-Final Coverage measures how faithfully the thought stream translates into the final output. Dominant Entity Analysis identifies which subjects, actions, and settings the model focuses on. GPT-5 serves as an independent judge. We find that quality gains from additional thinking plateau quickly, with most improvement occurring in the first few hundred tokens. Flash Lite offers the best balance between quality and token usage. Tight reasoning budgets cause the model to add content in the final output that it never reasoned about, a form of compression-step hallucination. Despite being different model tiers, Flash and Flash Lite produce similar thought streams, though they differ in style: Flash discusses its reasoning process, while Lite focuses on describing the scene. --- ### Precision Synthesis of Multi-Tracer PET via VLM-Modulated Rectified Flow for Stratifying Mild Cognitive Impairment Authors: Tuo Liu, Shuijin Lin, Shaozhen Yan, Haifeng Wang, Jie Lu, Jianhua Ma, Chunfeng Lian Published: 2026-04-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.11176v2 The biological definition of Alzheimer's disease (AD) relies on multi-modal neuroimaging, yet the clinical utility of positron emission tomography (PET) is limited by cost and radiation exposure, hindering early screening at preclinical or prodromal stages. While generative models offer a promising alternative by synthesizing PET from magnetic resonance imaging (MRI), achieving subject-specific precision remains a primary challenge. Here, we introduce DIReCT$++$, a Domain-Informed ReCTified flow model for synthesizing multi-tracer PET from MRI combined with fundamental clinical information. Our approach integrates a 3D rectified flow architecture to capture complex cross-modal and cross-tracer relationships with a domain-adapted vision-language model (BiomedCLIP) that provides text-guided, personalized generation using clinical scores and imaging knowledge. Extensive evaluations on multi-center datasets demonstrate that DIReCT$++$ not only produces synthetic PET images ($^{18}$F-AV-45 and $^{18}$F-FDG) of superior fidelity and generalizability but also accurately recapitulates disease-specific patterns. Crucially, combining these synthesized PET images with MRI enables precise personalized stratification of mild cognitive impairment (MCI), advancing a scalable, data-efficient tool for the early diagnosis and prognostic prediction of AD. The source code will be released on https://github.com/ladderlab-xjtu/DIReCT-PLUS. --- ### EmbodiedGovBench: A Benchmark for Governance, Recovery, and Upgrade Safety in Embodied Agent Systems Authors: Xue Qin, Simin Luan, John See, Cong Yang, Zhijun Li Published: 2026-04-13 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2604.11174v1 Recent progress in embodied AI has produced a growing ecosystem of robot policies, foundation models, and modular runtimes. However, current evaluation remains dominated by task success metrics such as completion rate or manipulation accuracy. These metrics leave a critical gap: they do not measure whether embodied systems are governable -- whether they respect capability boundaries, enforce policies, recover safely, maintain audit trails, and respond to human oversight. We present EmbodiedGovBench, a benchmark for governance-oriented evaluation of embodied agent systems. Rather than asking only whether a robot can complete a task, EmbodiedGovBench evaluates whether the system remains controllable, policy-bounded, recoverable, auditable, and evolution-safe under realistic perturbations. The benchmark covers seven governance dimensions: unauthorized capability invocation, runtime drift robustness, recovery success, policy portability, version upgrade safety, human override responsiveness, and audit completeness. We define a benchmark structure spanning single-robot and fleet settings, with scenario templates, perturbation operators, governance metrics, and baseline evaluation protocols. We describe how the benchmark can be instantiated over embodied capability runtimes with modular interfaces and contract-aware upgrade workflows. Our analysis suggests that embodied governance should become a first-class evaluation target. EmbodiedGovBench provides the initial measurement framework for that shift. --- ### NeuVolEx: Implicit Neural Features for Volume Exploration Authors: Haill An, Suhyeon Kim, Donghyuk Choo, Younhyun Jung Published: 2026-04-13 Categories: cs.GR, cs.CV arXiv: https://arxiv.org/abs/2604.11172v1 Direct volume rendering (DVR) aims to help users identify and examine regions of interest (ROIs) within volumetric data, and feature representations that support effective ROI classification and clustering play a fundamental role in volume exploration. Existing approaches typically rely on either explicit local feature representations or implicit convolutional feature representations learned from raw volumes. However, explicit local feature representations are limited in capturing broader geometric patterns and spatial correlations, while implicit convolutional feature representations do not necessarily ensure robust performance in practice, where user supervision is typically limited. Meanwhile, implicit neural representations (INRs) have recently shown strong promise in DVR for volume compression, owing to their ability to compactly parameterize continuous volumetric fields. In this work, we propose NeuVolEx, a neural volume exploration approach that extends the role of INRs beyond volume compression. Unlike prior compression methods that focus on INR outputs, NeuVolEx leverages feature representations learned during INR training as a robust basis for volume exploration. To better adapt these feature representations to exploration tasks, we augment a base INR with a structural encoder and a multi-task learning scheme that improve spatial coherence for ROI characterization. We validate NeuVolEx on two fundamental volume exploration tasks: image-based transfer function (TF) design and viewpoint recommendation. NeuVolEx enables accurate ROI classification under sparse user supervision for image-based TF design and supports unsupervised clustering to identify compact complementary viewpoints that reveal different ROI clusters. Experiments on diverse volume datasets with varying modalities and ROI complexities demonstrate NeuVolEx improves both effectiveness and usability over prior methods --- ### Development and evaluation of CADe systems in low-prevalence setting: The RARE25 challenge for early detection of Barrett's neoplasia Authors: Tim J. M. Jaspers, Francisco Caetano, Cris H. B. Claessens, Carolus H. J. Kusters, Rixta A. H. van Eijck van Heslinga, Floor Slooter, Jacques J. Bergman, Peter H. N. De With, Martijn R. Jong, Albert J. de Groof, Fons van der Sommen Published: 2026-04-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.11171v1 Computer-aided detection (CADe) of early neoplasia in Barrett's esophagus is a low-prevalence surveillance problem in which clinically relevant findings are rare. Although many CADe systems report strong performance on balanced or enriched datasets, their behavior under realistic prevalence remains insufficiently characterized. The RARE25 challenge addresses this gap by introducing a large-scale, prevalence-aware benchmark for neoplasia detection. It includes a public training set and a hidden test set reflecting real-world incidence. Methods were evaluated using operating-point-specific metrics emphasizing high sensitivity and accounting for prevalence. Eleven teams from seven countries submitted approaches using diverse architectures, pretraining, ensembling, and calibration strategies. While several methods achieved strong discriminative performance, positive predictive values remained low, highlighting the difficulty of low-prevalence detection and the risk of overestimating clinical utility when prevalence is ignored. All methods relied on fully supervised classification despite the dominance of normal findings, indicating a lack of prevalence-agnostic approaches such as anomaly detection or one-class learning. By releasing a public dataset and a reproducible evaluation framework, RARE25 aims to support the development of CADe systems robust to prevalence shift and suitable for clinical surveillance workflows. --- ### Do Instance Priors Help Weakly Supervised Semantic Segmentation? Authors: Anurag Das, Anna Kukleva, Xinting Hu, Yuki M. Asano, Bernt Schiele Published: 2026-04-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.11170v1 Semantic segmentation requires dense pixel-level annotations, which are costly and time-consuming to acquire. To address this, we present SeSAM, a framework that uses a foundational segmentation model, i.e. Segment Anything Model (SAM), with weak labels, including coarse masks, scribbles, and points. SAM, originally designed for instance-based segmentation, cannot be directly used for semantic segmentation tasks. In this work, we identify specific challenges faced by SAM and determine appropriate components to adapt it for class-based segmentation using weak labels. Specifically, SeSAM decomposes class masks into connected components, samples point prompts along object skeletons, selects SAM masks using weak-label coverage, and iteratively refines labels using pseudo-labels, enabling SAM-generated masks to be effectively used for semantic segmentation. Integrated with a semi-supervised learning framework, SeSAM balances ground-truth labels, SAM-based pseudo-labels, and high-confidence pseudo-labels, significantly improving segmentation quality. Extensive experiments across multiple benchmarks and weak annotation types show that SeSAM consistently outperforms weakly supervised baselines while substantially reducing annotation cost relative to fine supervision. --- ### Cost-optimal Sequential Testing via Doubly Robust Q-learning Authors: Doudou Zhou, Yiran Zhang, Dian Jin, Yingye Zheng, Lu Tian, Tianxi Cai Published: 2026-04-13 Categories: stat.ML, cs.AI, cs.LG, math.ST arXiv: https://arxiv.org/abs/2604.11165v2 Clinical decision-making often involves selecting tests that are costly, invasive, or time-consuming, motivating individualized, sequential strategies for what to measure and when to stop ascertaining. We study the problem of learning cost-optimal sequential decision policies from retrospective data, where test availability depends on prior results, inducing informative missingness. Under a sequential missing-at-random mechanism, we develop a doubly robust Q-learning framework for estimating optimal policies. The method introduces path-specific inverse probability weights that account for heterogeneous test trajectories and satisfy a normalization property conditional on the observed history. By combining these weights with auxiliary contrast models, we construct orthogonal pseudo-outcomes that enable unbiased policy learning when either the acquisition model or the contrast model is correctly specified. We establish oracle inequalities for the stage-wise contrast estimators, along with convergence rates, regret bounds, and misclassification rates for the learned policy. Simulations demonstrate improved cost-adjusted performance over weighted and complete-case baselines, and an application to a prostate cancer cohort study illustrates how the method reduces testing cost without compromising predictive accuracy. --- ### RADA: Region-Aware Dual-encoder Auxiliary learning for Barely-supervised Medical Image Segmentation Authors: Shuang Zeng, Boxu Xie, Lei Zhu, Xinliang Zhang, Jiakui Hu, Zhengjian Yao, Yuanwei Li, Yuxing Lu, Yanye Lu Published: 2026-04-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.11164v1 Deep learning has greatly advanced medical image segmentation, but its success relies heavily on fully supervised learning, which requires dense annotations that are costly and time-consuming for 3D volumetric scans. Barely-supervised learning reduces annotation burden by using only a few labeled slices per volume. Existing methods typically propagate sparse annotations to unlabeled slices through geometric continuity to generate pseudo-labels, but this strategy lacks semantic understanding, often resulting in low-quality pseudo-labels. Furthermore, medical image segmentation is inherently a pixel-level visual understanding task, where accuracy fundamentally depends on the quality of local, fine-grained visual features. Inspired by this, we propose RADA, a novel Region-Aware Dual-encoder Auxiliary learning pipeline which introduces a dual-encoder framework pre-trained on Alpha-CLIP to extract fine-grained, region-specific visual features from the original images and limited annotations. The framework combines image-level fine-grained visual features with text-level semantic guidance, providing region-aware semantic supervision that bridges image-level semantics and pixel-level segmentation. Integrated into a triple-view training framework, RADA achieves SOTA performance under extremely sparse annotation settings on LA2018, KiTS19 and LiTS, demonstrating robust generalization across diverse datasets. --- ### Boxes2Pixels: Learning Defect Segmentation from Noisy SAM Masks Authors: Camile Lendering, Erkut Akdag, Egor Bondarev Published: 2026-04-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.11162v1 Accurate defect segmentation is critical for industrial inspection, yet dense pixel-level annotations are rarely available. A common workaround is to convert inexpensive bounding boxes into pseudo-masks using foundation segmentation models such as the Segment Anything Model (SAM). However, these pseudo-labels are systematically noisy on industrial surfaces, often hallucinating background structure while missing sparse defects. To address this limitation, a noise-robust box-to-pixel distillation framework, Boxes2Pixels, is proposed that treats SAM as a noisy teacher rather than a source of ground-truth supervision. Bounding boxes are converted into pseudo-masks offline by SAM, and a compact student is trained with (i) a hierarchical decoder over frozen DINOv2 features for semantic stability, (ii) an auxiliary binary localization head to decouple sparse foreground discovery from class prediction, and (iii) a one-sided online self-correction mechanism that relaxes background supervision when the student is confident, targeting teacher false negatives. On a manually annotated wind turbine inspection benchmark, the proposed Boxes2Pixels improves anomaly mIoU by +6.97 and binary IoU by +9.71 over the strongest baseline trained under identical weak supervision. Moreover, online self-correction increases the binary recall by +18.56, while the model employs 80\% fewer trainable parameters. Code is available at https://github.com/CLendering/Boxes2Pixels. --- ### rPPG-VQA: A Video Quality Assessment Framework for Unsupervised rPPG Training Authors: Tianyang Dai, Ming Chang, Yan Chen, Yang Hu Published: 2026-04-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.11156v1 Unsupervised remote photoplethysmography (rPPG) promises to leverage unlabeled video data, but its potential is hindered by a critical challenge: training on low-quality "in-the-wild" videos severely degrades model performance. An essential step missing here is to assess the suitability of the videos for rPPG model learning before using them for the task. Existing video quality assessment (VQA) methods are mainly designed for human perception and not directly applicable to the above purpose. In this work, we propose rPPG-VQA, a novel framework for assessing video suitability for rPPG. We integrate signal-level and scene-level analyses and design a dual-branch assessment architecture. The signal-level branch evaluates the physiological signal quality of the videos via robust signal-to-noise ratio (SNR) estimation with a multi-method consensus mechanism, and the scene-level branch uses a multimodal large language model (MLLM) to identify interferences like motion and unstable lighting. Furthermore, we propose a two-stage adaptive sampling (TAS) strategy that utilizes the quality score to curate optimal training datasets. Experiments show that by training on large-scale, "in-the-wild" videos filtered by our framework, we can develop unsupervised rPPG models that achieve a substantial improvement in accuracy on standard benchmarks. Our code is available at https://github.com/Tianyang-Dai/rPPG-VQA. --- ### Environmental Footprint of GenAI Research: Insights from the Moshi Foundation Model Authors: Marta López-Rauhut, Loic Landrieu, Mathieu Aubry, Anne-Laure Ligozat Published: 2026-04-13 Categories: cs.AI arXiv: https://arxiv.org/abs/2604.11154v1 New multi-modal large language models (MLLMs) are continuously being trained and deployed, following rapid development cycles. This generative AI frenzy is driving steady increases in energy consumption, greenhouse gas emissions, and a plethora of other environmental impacts linked to datacenter construction and hardware manufacturing. Mitigating the environmental consequences of GenAI remains challenging due to an overall lack of transparency by the main actors in the field. Even when the environmental impacts of specific models are mentioned, they are typically restricted to the carbon footprint of the final training run, omitting the research and development stages. In this work, we explore the impact of GenAI research through a fine-grained analysis of the compute spent to create Moshi, a 7B-parameter speech-text foundation model for real-time dialogue developed by Kyutai, a leading privately funded open science AI lab. For the first time, our study dives into the anatomy of compute-intensive MLLM research, quantifying the GPU-time invested in specific model components and training phases, as well as early experimental stages, failed training runs, debugging, and ablation studies. Additionally, we assess the environmental impacts of creating Moshi from beginning to end using a life cycle assessment methodology: we quantify energy and water consumption, greenhouse gas emissions, and mineral resource depletion associated with the production and use of datacenter hardware. Our detailed analysis allows us to provide actionable guidelines to reduce compute usage and environmental impacts of MLLM research, paving the way for more sustainable AI research. --- ### SHARE: Social-Humanities AI for Research and Education Authors: João Gonçalves, Sonia de Jager, Petr Knoth, David Pride, Nick Jelicic Published: 2026-04-13 Categories: cs.CL arXiv: https://arxiv.org/abs/2604.11152v1 This intermediate technical report introduces the SHARE family of base models and the MIRROR user interface. The SHARE models are the first causal language models fully pretrained by and for the social sciences and humanities (SSH). Their performance in modelling SSH texts is close to that of general purpose models (Phi-4) which use 100 times more tokens, as shown by our custom SSH Cloze benchmark. The MIRROR user interface is designed for reviewing text inputs from the SSH disciplines while preserving critical engagement. By prototyping a generative AI interface that does not generate any text, we propose a way to harness the capabilities of the SHARE models without compromising the integrity of SSH principles and norms. --- ### Gradient-Variation Regret Bounds for Unconstrained Online Learning Authors: Yuheng Zhao, Andrew Jacobsen, Nicolò Cesa-Bianchi, Peng Zhao Published: 2026-04-13 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2604.11151v2 We develop parameter-free algorithms for unconstrained online learning with regret guarantees that scale with the gradient variation $V_T(u) = \sum_{t=2}^T \|\nabla f_t(u)-\nabla f_{t-1}(u)\|^2$. For $L$-smooth convex losses, we provide fully-adaptive algorithms achieving regret of $\widetilde{O}(\|u\|\sqrt{V_T(u)} + L\|u\|^2+G^4)$ without requiring prior knowledge of comparator norm $\|u\|$, Lipschitz constant $G$, or smoothness $L$. The update in each round can be computed efficiently via a closed-form expression. Our results extend to dynamic regret and find immediate implications for the stochastically-extended adversarial (SEA) model, which significantly improves upon the previous best-known result (Wang et al., 2025). --- ### A Full Compression Pipeline for Green Federated Learning in Communication-Constrained Environments Authors: Elouan Colybes, Shirin Salehi, Anke Schmeink Published: 2026-04-13 Categories: cs.LG, cs.DC arXiv: https://arxiv.org/abs/2604.11146v2 Federated Learning (FL) enables collaborative model training across distributed clients without sharing raw data, thereby preserving privacy. However, FL often suffers from significant communication and computational overhead, limiting its scalability and sustainability. In this work, we introduce a Full Compression Pipeline (FCP) for FL in communication-constrained environments. FCP integrates three complementary deep compression techniques (pruning, quantization, and Huffman encoding) into a unified end-to-end framework. By compressing local models and communication payloads, FCP substantially reduces transmission costs and resource consumption while maintaining competitive accuracy. To quantify its impact, we develop an evaluation framework that captures both communication and computation overheads as a unified model cost, allowing a holistic assessment of efficiency trade-offs. The pipeline is evaluated in an independent and identically distributed (IID) and non-IID data setting. In one representative scenario, training a ResNet-12 model on the CIFAR-10 dataset with ten clients and a 2 Mbps bandwidth, the FCP achieves more than 11$\times$ reduction in model size, with only a 2% drop in accuracy compared to the uncompressed baseline. This results in an FL training that is more than 60% faster. --- ### Hierarchical Textual Knowledge for Enhanced Image Clustering Authors: Yijie Zhong, Yunfan Gao, Weipeng Jiang, Haofen Wang Published: 2026-04-13 Categories: cs.CV, cs.CL, cs.MM arXiv: https://arxiv.org/abs/2604.11144v1 Image clustering aims to group images in an unsupervised fashion. Traditional methods focus on knowledge from visual space, making it difficult to distinguish between visually similar but semantically different classes. Recent advances in vision-language models enable the use of textual knowledge to enhance image clustering. However, most existing methods rely on coarse class labels or simple nouns, overlooking the rich conceptual and attribute-level semantics embedded in textual space. In this paper, we propose a knowledge-enhanced clustering (KEC) method that constructs a hierarchical concept-attribute structured knowledge with the help of large language models (LLMs) to guide clustering. Specifically, we first condense redundant textual labels into abstract concepts and then automatically extract discriminative attributes for each single concept and similar concept pairs, via structured prompts to LLMs. This knowledge is instantiated for each input image to achieve the knowledge-enhanced features. The knowledge-enhanced features with original visual features are adapted to various downstream clustering algorithms. We evaluate KEC on 20 diverse datasets, showing consistent improvements across existing methods using additional textual knowledge. KEC without training outperforms zero-shot CLIP on 14 out of 20 datasets. Furthermore, the naive use of textual knowledge may harm clustering performance, while KEC provides both accuracy and robustness. --- ### Naka-GS: A Bionics-inspired Dual-Branch Naka Correction and Progressive Point Pruning for Low-Light 3DGS Authors: Runyu Zhu, SiXun Dong, Zhiqiang Zhang, Qingxia Ye, Zhihua Xu Published: 2026-04-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.11142v1 Low-light conditions severely hinder 3D restoration and reconstruction by degrading image visibility, introducing color distortions, and contaminating geometric priors for downstream optimization. We present NAKA-GS, a bionics-inspired framework for low-light 3D Gaussian Splatting that jointly improves photometric restoration and geometric initialization. Our method starts with a Naka-guided chroma-correction network, which combines physics-prior low-light enhancement, dual-branch input modeling, frequency-decoupled correction, and mask-guided optimization to suppress bright-region chromatic artifacts and edge-structure errors. The enhanced images are then fed into a feed-forward multi-view reconstruction model to produce dense scene priors. To further improve Gaussian initialization, we introduce a lightweight Point Preprocessing Module (PPM) that performs coordinate alignment, voxel pooling, and distance-adaptive progressive pruning to remove noisy and redundant points while preserving representative structures. Without introducing heavy inference overhead, NAKA-GS improves restoration quality, training stability, and optimization efficiency for low-light 3D reconstruction. The proposed method was presented in the NTIRE 3D Restoration and Reconstruction (3DRR) Challenge, and outperformed the baseline methods by a large margin. The code is available at https://github.com/RunyuZhu/Naka-GS --- ### Reducing Hallucination in Enterprise AI Workflows via Hybrid Utility Minimum Bayes Risk (HUMBR) Authors: Chenhao Fang, Jordi Mola, Mark Harman, Jason Nawrocki, Vaibhav Shrivastava, Yue Cheng, Jay Minesh Shah, Katayoun Zand, Mansi Tripathi, Arya Pudota, Matthew Becker, Hervé Robert et al. Published: 2026-04-13 Categories: cs.LG, cs.CR arXiv: https://arxiv.org/abs/2604.11141v1 Although LLMs drive automation, it is critical to ensure immense consideration for high-stakes enterprise workflows such as those involving legal matters, risk management, and privacy compliance. For Meta, and other organizations like ours, a single hallucinated clause in such high stakes workflows risks material consequences. We show that by framing hallucination mitigation as a Minimum Bayes Risk (MBR) problem, we can dramatically reduce this risk. Specifically, we introduce a Hybrid Utility MBR (HUMBR) framework that synthesizes semantic embedding similarity with lexical precision to identify consensus without ground-truth references, for which we derive rigorous error bounds. We complement this theoretical analysis with a comprehensive empirical evaluation on widely-used public benchmark suites (TruthfulQA and LegalBench) and also real world data from Meta production deployment. The results from our empirical study show that MBR significantly outperforms standard Universal Self-Consistency. Notably, 81% of the pipeline's suggestions were preferred over human-crafted ground truth, and critical recall failures were virtually eliminated. --- ### Hyper-FEOD: Sparse Hypergraph-Enhanced Frame-Event Object Detection with Fine-Grained MoE Authors: Wei Bao, Yuehan Wang, Tianhang Zhou, Siqi Li Published: 2026-04-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.11140v2 The integration of frame-based RGB cameras with event streams constitutes a promising paradigm for robust object detection under challenging dynamic conditions. Nevertheless, effectively modeling intricate multi-modal interactions and reconciling the semantic heterogeneity between RGB and event data remain formidable challenges for high-precision detection. In this paper, we present Hyper-FEOD, a novel high-performance detection framework that synergistically strengthens cross-modal representation learning through two core hypergraph-driven components. Specifically, we first design a Sparse Hypergraph-enhanced Cross-Modal Fusion (SHCF) module that exploits event activity cues to identify motion-critical sparse tokens and performs high-order relational reasoning through hypergraph modeling. This design effectively captures intricate high-order dependencies and rich contextual correlations across modalities. Second, we develop a Fine-Grained Mixture-of-Experts (FG-MoE) module tailored to handle the heterogeneous semantic demands arising from distinct visual regions. By deploying specialized hypergraph experts with varying hyperedge connectivity pattern and incorporating a spatial gating mechanism, FG-MoE adaptively routes features to enable precise enhancement at target regions. Coupled with an auxiliary router loss, the proposed framework ensures stable end-to-end training and optimal feature refinement. Comprehensive experiments conducted on widely-adopted RGB-Event benchmarks show that Hyper-FEOD delivers superior detection performance and consistently outperforms existing state-of-the-art approaches by a notable margin. --- ### ViserDex: Visual Sim-to-Real for Robust Dexterous In-hand Reorientation Authors: Arjun Bhardwaj, Maximum Wilder-Smith, Mayank Mittal, Vaishakh Patil, Marco Hutter Published: 2026-04-13 Categories: cs.RO, cs.CV arXiv: https://arxiv.org/abs/2604.11138v1 In-hand object reorientation requires precise estimation of the object pose to handle complex task dynamics. While RGB sensing offers rich semantic cues for pose tracking, existing solutions rely on multi-camera setups or costly ray tracing. We present a sim-to-real framework for monocular RGB in-hand reorientation that integrates 3D Gaussian Splatting (3DGS) to bridge the visual sim-to-real gap. Our key insight is performing domain randomization in the Gaussian representation space: by applying physically consistent, pre-rendering augmentations to 3D Gaussians, we generate photorealistic, randomized visual data for object pose estimation. The manipulation policy is trained using curriculum-based reinforcement learning with teacher-student distillation, enabling efficient learning of complex behaviors. Importantly, both perception and control models can be trained independently on consumer-grade hardware, eliminating the need for large compute clusters. Experiments show that the pose estimator trained with 3DGS data outperforms those trained using conventional rendering data in challenging visual environments. We validate the system on a physical multi-fingered hand equipped with an RGB camera, demonstrating robust reorientation of five diverse objects even under challenging lighting conditions. Our results highlight Gaussian splatting as a practical path for RGB-only dexterous manipulation. For videos of the hardware deployments and additional supplementary materials, please refer to the project website: https://rffr.leggedrobotics.com/works/viserdex/ --- ### From Answers to Arguments: Toward Trustworthy Clinical Diagnostic Reasoning with Toulmin-Guided Curriculum Goal-Conditioned Learning Authors: Chen Zhan, Xiaoyu Tan, Gengchen Ma, Yu-Jie Xiong, Xiaoyan Jiang, Xihe Qiu Published: 2026-04-13 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2604.11137v2 The integration of Large Language Models (LLMs) into clinical decision support is critically obstructed by their opaque and often unreliable reasoning. In the high-stakes domain of healthcare, correct answers alone are insufficient; clinical practice demands full transparency to ensure patient safety and enable professional accountability. A pervasive and dangerous weakness of current LLMs is their tendency to produce "correct answers through flawed reasoning." This issue is far more than a minor academic flaw; such process errors signal a fundamental lack of robust understanding, making the model prone to broader hallucinations and unpredictable failures when faced with real-world clinical complexity. In this paper, we establish a framework for trustworthy clinical argumentation by adapting the Toulmin model to the diagnostic process. We propose a novel training pipeline: Curriculum Goal-Conditioned Learning (CGCL), designed to progressively train LLM to generate diagnostic arguments that explicitly follow this Toulmin structure. CGCL's progressive three-stage curriculum systematically builds a solid clinical argument: (1) extracting facts and generating differential diagnoses; (2) justifying a core hypothesis while rebutting alternatives; and (3) synthesizing the analysis into a final, qualified conclusion. We validate CGCL using T-Eval, a quantitative framework measuring the integrity of the diagnosis reasoning. Experiments show that our method achieves diagnostic accuracy and reasoning quality comparable to resource-intensive Reinforcement Learning (RL) methods, while offering a more stable and efficient training pipeline. --- ### BoxTuning: Directly Injecting the Object Box for Multimodal Model Fine-Tuning Authors: Zekun Qian, Ruize Han, Wei Feng Published: 2026-04-13 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2604.11136v1 Object-level spatial-temporal understanding is essential for video question answering, yet existing multimodal large language models (MLLMs) encode frames holistically and lack explicit mechanisms for fine-grained object grounding. Recent work addresses this by serializing bounding box coordinates as text tokens, but this text-coordinate paradigm suffers from a fundamental modality mismatch: object information is inherently visual, yet encoding it as text incurs a high token cost that forces aggressive temporal downsampling. We propose BoxTuning, which resolves this mismatch by injecting object spatial-temporal information directly into the visual modality. Colored bounding boxes and trajectory trails are rendered onto video frames as visual prompts, with only a concise color-to-object legend retained as text. This reduces the token cost significantly, achieving 87-93% text token reduction in practice. It also preserves full temporal resolution, where the trajectory trails further encode inter-frame motion direction and speed within each keyframe, recovering fine-grained dynamics that text-coordinate methods are forced to discard. Experimental results on five video QA benchmarks (CLEVRER, Perception Test, STAR, NExT-QA, IntentQA) show that BoxTuning surpasses text-coordinate baselines on spatially oriented tasks and nearly eliminates the accuracy degradation observed on reasoning-centric tasks, establishing visual prompting as a more natural and efficient paradigm for conveying object information to video MLLMs. --- ### AIM: Intent-Aware Unified world action Modeling with Spatial Value Maps Authors: Liaoyuan Fan, Zetian Xu, Chen Cao, Wenyao Zhang, Mingqi Yuan, Jiayu Chen Published: 2026-04-13 Categories: cs.RO, cs.LG arXiv: https://arxiv.org/abs/2604.11135v1 Pretrained video generation models provide strong priors for robot control, but existing unified world action models still struggle to decode reliable actions without substantial robot-specific training. We attribute this limitation to a structural mismatch: while video models capture how scenes evolve, action generation requires explicit reasoning about where to interact and the underlying manipulation intent. We introduce AIM, an intent-aware unified world action model that bridges this gap via an explicit spatial interface. Instead of decoding actions directly from future visual representations, AIM predicts an aligned spatial value map that encodes task-relevant interaction structure, enabling a control-oriented abstraction of future dynamics. Built on a pretrained video generation model, AIM jointly models future observations and value maps within a shared mixture-of-transformers architecture. It employs intent-causal attention to route future information to the action branch exclusively through the value representation. We further propose a self-distillation reinforcement learning stage that freezes the video and value branches and optimizes only the action head using dense rewards derived from projected value-map responses together with sparse task-level signals. To support training and evaluation, we construct a simulation dataset of 30K manipulation trajectories with synchronized multi-view observations, actions, and value-map annotations. Experiments on RoboTwin 2.0 benchmark show that AIM achieves a 94.0% average success rate, significantly outperforming prior unified world action baselines. Notably, the improvement is more pronounced in long-horizon and contact-sensitive manipulation tasks, demonstrating the effectiveness of explicit spatial-intent modeling as a bridge between visual world modeling and robot control. --- ### How Robust Are Large Language Models for Clinical Numeracy? An Empirical Study on Numerical Reasoning Abilities in Clinical Contexts Authors: Minh-Vuong Nguyen, Fatemeh Shiri, Zhuang Li, Karin Verspoor Published: 2026-04-13 Categories: cs.CL arXiv: https://arxiv.org/abs/2604.11133v2 Large Language Models (LLMs) are increasingly being explored for clinical question answering and decision support, yet safe deployment critically requires reliable handling of patient measurements in heterogeneous clinical notes. Existing evaluations of LLMs for clinical numerical reasoning provide limited operation-level coverage, restricted primarily to arithmetic computation, and rarely assess the robustness of numerical understanding across clinical note formats. We introduce ClinicNumRobBench, a benchmark of 1,624 context-question instances with ground-truth answers that evaluates four main types of clinical numeracy: value retrieval, arithmetic computation, relational comparison, and aggregation. To stress-test robustness, ClinicNumRobBench presents longitudinal MIMIC-IV vital-sign records in three semantically equivalent representations, including a real-world note-style variant derived from the Open Patients dataset, and instantiates queries using 42 question templates. Experiments on 17 LLMs show that value retrieval is generally strong, with most models exceeding 85% accuracy, while relational comparison and aggregation remain challenging, with some models scoring below 15%. Fine-tuning on medical data can reduce numeracy relative to base models by over 30%, and performance drops under note-style variation indicate LLM sensitivity to format. ClinicNumRobBench offers a rigorous testbed for clinically reliable numerical reasoning. Code and data URL are available on https://github.com/MinhVuong2000/ClinicNumRobBench. --- ### MADQRL: Distributed Quantum Reinforcement Learning Framework for Multi-Agent Environments Authors: Abhishek Sawaika, Samuel Yen-Chi Chen, Udaya Parampalli, Rajkumar Buyya Published: 2026-04-13 Categories: cs.AI, cs.LG, cs.MA arXiv: https://arxiv.org/abs/2604.11131v1 Reinforcement learning (RL) is one of the most practical ways to learn from real-life use-cases. Motivated from the cognitive methods used by humans makes it a widely acceptable strategy in the field of artificial intelligence. Most of the environments used for RL are often high-dimensional, and traditional RL algorithms becomes computationally expensive and challenging to effectively learn from such systems. Recent advancements in practical demonstration of quantum computing (QC) theories, such as compact encoding, enhanced representation and learning algorithms, random sampling, or the inherent stochastic nature of quantum systems, have opened up new directions to tackle these challenges. Quantum reinforcement learning (QRL) is seeking significant traction over the past few years. However, the current state of quantum hardware is not enough to cater for such high-dimensional environments with complex multi-agent setup. To tackle this issue, we propose a distributed framework for QRL where multiple agents learn independently, distributing the load of joint training from individual machines. Our method works well for environments with disjoint sets of action and observation spaces, but can also be extended to other systems with reasonable approximations. We analyze the proposed method on cooperative-pong environment and our results indicate ~10% improvement from other distribution strategies, and ~5% improvement from classical models of policy representation. --- ### DeCoVec: Building Decoding Space based Task Vector for Large Language Models via In-Context Learning Authors: Feiyang Li, Yile Wang Published: 2026-04-13 Categories: cs.CL arXiv: https://arxiv.org/abs/2604.11129v1 Task vectors, representing directions in model or activation spaces that encode task-specific behaviors, have emerged as a promising tool for steering large language models (LLMs). However, existing approaches typically require fine-tuning or invasive manipulation of internal states, limiting their flexibility and scalability. We propose \textsc{DeCoVec} (Decoding Space based Task Vector), a training-free and non-invasive framework that constructs task vectors directly in the \textit{decoding space} by leveraging in-context learning (ICL). Specifically, \textsc{DeCoVec} captures the task essence as the difference between the output logit distributions of few-shot and zero-shot prompts, then steers generation by injecting this vector into the decoding process. Experiments across seven LLMs (0.5B--9B) on TruthfulQA, Math-500, and AQUA-RAT show that \textsc{DeCoVec} consistently outperforms standard few-shot baselines, with gains up to +5.50 average accuracy. Further analysis demonstrates that \textsc{DeCoVec} effectively suppresses generation degeneration and logical flaws while exhibiting strong robustness to demonstration ordering, all without incurring additional input token costs. Our method offers a training-free and non-invasive solution for LLM steering without requiring weight updates or auxiliary models. --- ### A Proposed Biomedical Data Policy Framework to Reduce Fragmentation, Improve Quality, and Incentivize Sharing in Indian Healthcare in the era of Artificial Intelligence and Digital Health Authors: Nikhil Mehta, Sachin Gupta, Gouri RP Anand Published: 2026-04-13 Categories: cs.AI arXiv: https://arxiv.org/abs/2604.11125v1 India generates vast biomedical data through postgraduate research, government hospital services and audits, government schemes, private hospitals and their electronic medical record (EMR) systems, insurance programs and standalone clinics. Unfortunately, these resources remain fragmented across institutional silos and vendor-locked EMR systems. The fundamental bottleneck is not technological but economic and academic. There is a systemic misalignment of incentives that renders data sharing a high-risk, low-reward activity for individual researchers and institutions. Until India's academic promotion criteria, institutional rankings, and funding mechanisms explicitly recognize and reward data curation as professional work, the nation's AI ambitions will remain constrained by fragmented, non-interoperable datasets. We propose a multi-layered incentive architecture integrating recognition of data papers in National Medical Commission (NMC) promotion criteria, incorporation of open data metrics into the National Institutional Ranking Framework (NIRF), adoption of Shapley Value-based revenue sharing in federated learning consortia, and establishment of institutional data stewardship as a mainstream professional role. Critical barriers to data sharing, including fear of data quality scrutiny, concerns about misinterpretation, and selective reporting bias, are addressed through mandatory data quality assessment, structured peer review, and academic credit for auditing roles. The proposed framework directly addresses regulatory constraints introduced by the Digital Personal Data Protection Act 2023 (DPDPA), while constructively engaging with the National Data Sharing and Accessibility Policy (NDSAP), Biotech-PRIDE Guidelines, and the Anusandhan National Research Foundation (ANRF) guidelines. --- ### Semantic-Geometric Dual Compression: Training-Free Visual Token Reduction for Ultra-High-Resolution Remote Sensing Understanding Authors: Yueying Li, Fengxiang Wang, Yan Li, Mingshuo Chen, Mengying Zhao, Long Lan Published: 2026-04-13 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2604.11122v1 Multimodal Large Language Models (MLLMs) have demonstrated immense potential in Earth observation. However, the massive visual tokens generated when processing Ultra-High-Resolution (UHR) imagery introduce prohibitive computational overhead, severely bottlenecking their inference efficiency. Existing visual token compression methods predominantly adopt static and uniform compression strategies, neglecting the inherent "Semantic-Geometric Duality" in remote sensing interpretation tasks. Specifically, object semantic tasks focus on the abstract semantics of objects and benefit from aggressive background pruning, whereas scene geometric tasks critically rely on the integrity of spatial topology. To address this challenge, we propose DualComp, a task-adaptive dual-stream token compression framework. Dynamically guided by a lightweight pre-trained router, DualComp decouples feature processing into two dedicated pathways. In the object semantic stream, the Spatially-Contiguous Semantic Aggregator (SCSA) utilizes size-adaptive clustering to aggregates redundant background while protecting small object. In the scene geometric stream, the Instruction-Guided Structure Recoverer (IGSR) introduces a greedy path-tracing topology completion mechanism to reconstruct spatial skeletons. Experiments on the UHR remote sensing benchmark XLRS-Bench demonstrate that DualComp accomplishes high-fidelity remote sensing interpretation at an exceptionally low computational cost, achieving simultaneous improvements in both efficiency and accuracy. --- ### BITS Pilani at SemEval-2026 Task 9: Structured Supervised Fine-Tuning with DPO Refinement for Polarization Detection Authors: Atharva Gupta, Dhruv Kumar, Yash Sinha Published: 2026-04-13 Categories: cs.CL arXiv: https://arxiv.org/abs/2604.11121v2 The POLAR SemEval-2026 Shared Task aims to detect online polarization and focuses on the classification and identification of multilingual, multicultural, and multi-event polarization. Accurate computational detection of online polarization is challenging due to nuanced rhetoric, implicit framing, and the high cost of human-in-the-loop annotation. Building on recent findings that contextual prompting enables large language models to function as strong polarization detectors, we present a two-stage approach for detecting polarization in social media text that combines structured supervised fine tuning with Direct Preference Optimization (DPO) refinement. We fine tune Qwen 2.5-7B-Instruct with LoRA using an interpretable slot-filling template (target, claim type, manifestation checklist, and justification). We then apply DPO with automatically generated preference pairs to reduce costly false negatives. Our submitted system achieves 0.7664 Macro-F1 on the English test set. Post-submission experiments with Mistral-Nemo-Instruct-2407 and LLM-judge-filtered preference pairs further improve to 0.8162 Macro-F1 (not submitted to CodaBench), surpassing the organiser baseline of 0.7802. --- ### Persona Non Grata: Single-Method Safety Evaluation Is Incomplete for Persona-Imbued LLMs Authors: Wenkai Li, Fan Yang, Shaunak A. Mehta, Koichi Onoue Published: 2026-04-13 Categories: cs.AI arXiv: https://arxiv.org/abs/2604.11120v2 Personality imbuing customizes LLM behavior, but safety evaluations almost always study prompt-based personas alone. We show this is incomplete: prompting and activation steering expose *different*, architecture-dependent vulnerability profiles, and testing with only one method can miss a model's dominant failure mode. Across 5,568 judged conditions on four standard models from three architecture families, persona danger rankings under system prompting are preserved across all architectures ($ρ= 0.71$--$0.96$), but activation-steering vulnerability diverges sharply and cannot be predicted from prompt-side rankings: Llama-3.1-8B is substantially more AS-vulnerable, whereas Gemma-3-27B and Qwen3.5 are more vulnerable to prompting. The most striking illustration of this divergence is the *prosocial persona paradox*: on Llama-3.1-8B, P12 (high conscientiousness + high agreeableness) is among the safest personas under prompting yet becomes the highest-ASR activation-steered persona (ASR ~0.818). This is an inversion robust to coefficient ablation and matched-strength calibration, and replicated on DeepSeek-R1-Distill-Qwen-32B. A trait refusal alignment framework, in which conscientiousness is strongly anti-aligned with refusal on Llama-3.1-8B, offers a partial geometric account. Reasoning provides only partial protection: two 32B reasoning models reach 15--18% prompt-side ASR, and activation steering separates them sharply in both baseline susceptibility and persona-specific vulnerability. Heuristic trace diagnostics suggest that the safer model retains stronger policy recall and self-correction behavior, not merely longer reasoning. ---