# Research Papers — 2026-03 · bundle page 60 of 243

> Full-text markdown of papers #2951–3000 of 12123 published in 2026-03, newest first. AI-readable mirrors of the full 12123-paper 2026-03 archive (50 papers per file).

Canonical page: https://aipod.dev/papers/archive/2026-03/page/60
[← Previous bundle](https://aipod.dev/papers/archive/2026-03/page/59.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-03/page/61.md)

### UniQueR: Unified Query-based Feedforward 3D Reconstruction

Authors: Chensheng Peng, Quentin Herau, Jiezhi Yang, Yichen Xie, Yihan Hu, Wenzhao Zheng, Matthew Strong, Masayoshi Tomizuka, Wei Zhan
Published: 2026-03-24
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2603.22851v2

We present UniQueR, a unified query-based feedforward framework for efficient and accurate 3D reconstruction from unposed images. Existing feedforward models such as DUSt3R, VGGT, and AnySplat typically predict per-pixel point maps or pixel-aligned Gaussians, which remain fundamentally 2.5D and limited to visible surfaces. In contrast, UniQueR formulates reconstruction as a sparse 3D query inference problem. Our model learns a compact set of 3D anchor points that act as explicit geometric queries, enabling the network to infer scene structure, including geometry in occluded regions--in a single forward pass. Each query encodes spatial and appearance priors directly in global 3D space (instead of per-frame camera space) and spawns a set of 3D Gaussians for differentiable rendering. By leveraging unified query interactions across multi-view features and a decoupled cross-attention design, UniQueR achieves strong geometric expressiveness while substantially reducing memory and computational cost. Experiments on Mip-NeRF 360 and VR-NeRF demonstrate that UniQueR surpasses state-of-the-art feedforward methods in both rendering quality and geometric accuracy, using an order of magnitude fewer primitives than dense alternatives.

---

### UniQueR: Unified Query-based Feedforward 3D Reconstruction

Authors: Chensheng Peng, Quentin Herau, Jiezhi Yang, Yichen Xie, Yihan Hu, Wenzhao Zheng, Matthew Strong, Masayoshi Tomizuka, Wei Zhan
Published: 2026-03-24
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2603.22851v1

We present UniQueR, a unified query-based feedforward framework for efficient and accurate 3D reconstruction from unposed images. Existing feedforward models such as DUSt3R, VGGT, and AnySplat typically predict per-pixel point maps or pixel-aligned Gaussians, which remain fundamentally 2.5D and limited to visible surfaces. In contrast, UniQueR formulates reconstruction as a sparse 3D query inference problem. Our model learns a compact set of 3D anchor points that act as explicit geometric queries, enabling the network to infer scene structure, including geometry in occluded regions--in a single forward pass. Each query encodes spatial and appearance priors directly in global 3D space (instead of per-frame camera space) and spawns a set of 3D Gaussians for differentiable rendering. By leveraging unified query interactions across multi-view features and a decoupled cross-attention design, UniQueR achieves strong geometric expressiveness while substantially reducing memory and computational cost. Experiments on Mip-NeRF 360 and VR-NeRF demonstrate that UniQueR surpasses state-of-the-art feedforward methods in both rendering quality and geometric accuracy, using an order of magnitude fewer primitives than dense alternatives.

---

### Rethinking Token-Level Policy Optimization for Multimodal Chain-of-Thought

Authors: Yunheng Li, Hangyi Kuang, Hengrui Zhang, Jiangxia Cao, Zhaojie Liu, Qibin Hou, Ming-Ming Cheng
Published: 2026-03-24
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.22847v1

Multimodal Chain-of-Thought (CoT) reasoning requires large vision-language models to construct reasoning trajectories that interleave perceptual grounding with multi-step inference. However, existing Reinforcement Learning with Verifiable Rewards (RLVR) methods typically optimize reasoning at a coarse granularity, treating CoT uniformly without distinguishing their varying degrees of visual grounding. In this work, we conduct a token-level analysis of multimodal reasoning trajectories and show that successful reasoning is characterized by structured token dynamics reflecting both perceptual grounding and exploratory inference. Building upon this analysis, we propose Perception-Exploration Policy Optimization (PEPO), which derives a perception prior from hidden state similarity and integrates it with token entropy through a smooth gating mechanism to produce token-level advantages. PEPO integrates seamlessly with existing RLVR frameworks such as GRPO and DAPO, requiring neither additional supervision nor auxiliary branches. Extensive experiments across diverse multimodal benchmarks demonstrate consistent and robust improvements over strong RL baselines, spanning geometry reasoning, visual grounding, visual puzzle solving, and few-shot classification, while maintaining stable training dynamics. Code: https://github.com/xzxxntxdy/PEPO

---

### CoMaTrack: Competitive Multi-Agent Game-Theoretic Tracking with Vision-Language-Action Models

Authors: Youzhi Liu, Li Gao, Liu Liu, Mingyang Lv, Yang Cai
Published: 2026-03-24
Categories: cs.AI
arXiv: https://arxiv.org/abs/2603.22846v2

Embodied Visual Tracking (EVT), a core dynamic task in embodied intelligence, requires an agent to precisely follow a language-specified target. Yet most existing methods rely on single-agent imitation learning, suffering from costly expert data and limited generalization due to static training environments. Inspired by competition-driven capability evolution, we propose CoMaTrack, a competitive game-theoretic multi-agent reinforcement learning framework that trains agents in a dynamic adversarial setting with competitive subtasks, yielding stronger adaptive planning and interference-resilient strategies. We further introduce CoMaTrack-Bench, the first open-source Habitat-based benchmark protocol and episode set for language-conditioned competitive EVT featuring dynamic dueling, featuring game scenarios between a tracker and adaptive opponents across diverse environments and instructions, enabling standardized robustness evaluation under active adversarial interactions. Experiments show that CoMaTrack achieves state-of-the-art results on both standard benchmarks and CoMaTrack-Bench. Notably, a 3B VLM trained with our framework surpasses previous single-agent imitation learning methods based on 7B models on the challenging EVT-Bench, achieving 92.1% in STT, 74.2% in DT, and 57.5% in AT. The benchmark code will be available at https://github.com/wlqcode/CoMaTrack-Bench.

---

### PhySe-RPO: Physics and Semantics Guided Relative Policy Optimization for Diffusion-Based Surgical Smoke Removal

Authors: Zining Fang, Cheng Xue, Chunhui Liu, Bin Xu, Ming Chen, Xiaowei Hu
Published: 2026-03-24
Categories: cs.AI
arXiv: https://arxiv.org/abs/2603.22844v4

Surgical smoke severely degrades intraoperative video quality, obscuring anatomical structures and limiting surgical perception. Existing learning-based desmoking approaches rely on scarce paired supervision and deterministic restoration pipelines, making it difficult to perform exploration or reinforcement-driven refinement under real surgical conditions. We propose PhySe-RPO, a diffusion restoration framework optimized through Physics- and Semantics-Guided Relative Policy Optimization. The core idea is to transform deterministic restoration into a stochastic policy, enabling trajectory-level exploration and critic-free updates via group-relative optimization. A physics-guided reward imposes illumination and color consistency, while a visual-concept semantic reward learned from CLIP-based surgical concepts promotes smoke-free and anatomically coherent restoration. Together with a reference-free perceptual constraint, PhySe-RPO produces results that are physically consistent, semantically faithful, and clinically interpretable across synthetic and real robotic surgical datasets, providing a principled route to robust diffusion-based restoration under limited paired supervision.

---

### L-UNet: An LSTM Network for Remote Sensing Image Change Detection

Authors: Shuting Sun, Lin Mu, Lizhe Wang, Peng Liu
Published: 2026-03-24
Categories: eess.IV, cs.CV
arXiv: https://arxiv.org/abs/2603.22842v1

Change detection of high-resolution remote sensing images is an important task in earth observation and was extensively investigated. Recently, deep learning has shown to be very successful in plenty of remote sensing tasks. The current deep learning-based change detection method is mainly based on conventional long short-term memory (Conv-LSTM), which does not have spatial characteristics. Since change detection is a process with both spatiality and temporality, it is necessary to propose an end-to-end spatiotemporal network. To achieve this, Conv-LSTM, an extension of the Conv-LSTM structure, is introduced. Since it shares similar spatial characteristics with the convolutional layer, L-UNet, which substitutes partial convolution layers of UNet-to-Conv-LSTM and Atrous L-UNet (AL-UNet), which further using Atrous structure to multiscale spatial information is proposed. Experiments on two data sets are conducted and the proposed methods show the advantages both in quantity and quality when compared with some other methods.

---

### UAV-DETR: DETR for Anti-Drone Target Detection

Authors: Jun Yang, Dong Wang, Hongxu Yin, Hongpeng Li, Jianxiong Yu
Published: 2026-03-24
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2603.22841v1

Drone detection is pivotal in numerous security and counter-UAV applications. However, existing deep learning-based methods typically struggle to balance robust feature representation with computational efficiency. This challenge is particularly acute when detecting miniature drones against complex backgrounds under severe environmental interference. To address these issues, we introduce UAV-DETR, a novel framework that integrates a small-target-friendly architecture with real-time detection capabilities. Specifically, UAV-DETR features a WTConv-enhanced backbone and a Sliding Window Self-Attention (SWSA-IFI) encoder, capturing the high-frequency structural details of tiny targets while drastically reducing parameter overhead. Furthermore, we propose an Efficient Cross-Scale Feature Recalibration and Fusion Network (ECFRFN) to suppress background noise and aggregate multi-scale semantics. To further enhance accuracy, UAV-DETR incorporates a hybrid Inner-CIoU and NWD loss strategy, mitigating the extreme sensitivity of standard IoU metrics to minor positional deviations in small objects. Extensive experiments demonstrate that UAV-DETR significantly outperforms the baseline RT-DETR on our custom UAV dataset (+6.61% in mAP50:95, with a 39.8% reduction in parameters) and the public DUT-ANTI-UAV benchmark (+1.4% in Precision, +1.0% in F1-Score). These results establish UAV-DETR as a superior trade-off between efficiency and precision in counter-UAV object detection. The code is available at https://github.com/wd-sir/UAVDETR.

---

### URA-Net: Uncertainty-Integrated Anomaly Perception and Restoration Attention Network for Unsupervised Anomaly Detection

Authors: Wei Luo, Peng Xing, Yunkang Cao, Haiming Yao, Weiming Shen, Zechao Li
Published: 2026-03-24
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2603.22840v1

Unsupervised anomaly detection plays a pivotal role in industrial defect inspection and medical image analysis, with most methods relying on the reconstruction framework. However, these methods may suffer from over-generalization, enabling them to reconstruct anomalies well, which leads to poor detection performance. To address this issue, instead of focusing solely on normality reconstruction, we propose an innovative Uncertainty-Integrated Anomaly Perception and Restoration Attention Network (URA-Net), which explicitly restores abnormal patterns to their corresponding normality. First, unlike traditional image reconstruction methods, we utilize a pre-trained convolutional neural network to extract multi-level semantic features as the reconstruction target. To assist the URA-Net learning to restore anomalies, we introduce a novel feature-level artificial anomaly synthesis module to generate anomalous samples for training. Subsequently, a novel uncertainty-integrated anomaly perception module based on Bayesian neural networks is introduced to learn the distributions of anomalous and normal features. This facilitates the estimation of anomalous regions and ambiguous boundaries, laying the foundation for subsequent anomaly restoration. Then, we propose a novel restoration attention mechanism that leverages global normal semantic information to restore detected anomalous regions, thereby obtaining defect-free restored features. Finally, we employ residual maps between input features and restored features for anomaly detection and localization. The comprehensive experimental results on two industrial datasets, MVTec AD and BTAD, along with a medical image dataset, OCT-2017, unequivocally demonstrate the effectiveness and superiority of the proposed method.

---

### MultiCam: On-the-fly Multi-Camera Pose Estimation Using Spatiotemporal Overlaps of Known Objects

Authors: Shiyu Li, Hannah Schieber, Kristoffer Waldow, Benjamin Busam, Julian Kreimeier, Daniel Roth
Published: 2026-03-24
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.22839v1

Multi-camera dynamic Augmented Reality (AR) applications require a camera pose estimation to leverage individual information from each camera in one common system. This can be achieved by combining contextual information, such as markers or objects, across multiple views. While commonly cameras are calibrated in an initial step or updated through the constant use of markers, another option is to leverage information already present in the scene, like known objects. Another downside of marker-based tracking is that markers have to be tracked inside the field-of-view (FoV) of the cameras. To overcome these limitations, we propose a constant dynamic camera pose estimation leveraging spatiotemporal FoV overlaps of known objects on the fly. To achieve that, we enhance the state-of-the-art object pose estimator to update our spatiotemporal scene graph, enabling a relation even among non-overlapping FoV cameras. To evaluate our approach, we introduce a multi-camera, multi-object pose estimation dataset with temporal FoV overlap, including static and dynamic cameras. Furthermore, in FoV overlapping scenarios, we outperform the state-of-the-art on the widely used YCB-V and T-LESS dataset in camera pose accuracy. Our performance on both previous and our proposed datasets validates the effectiveness of our marker-less approach for AR applications. The code and dataset are available on https://github.com/roth-hex-lab/IEEE-VR-2026-MultiCam.

---

### Analysing LLM Persona Generation and Fairness Interpretation in Polarised Geopolitical Contexts

Authors: Maida Aizaz, Quang Minh Nguyen
Published: 2026-03-24
Categories: cs.CL
arXiv: https://arxiv.org/abs/2603.22837v1

Large language models (LLMs) are increasingly utilised for social simulation and persona generation, necessitating an understanding of how they represent geopolitical identities. In this paper, we analyse personas generated for Palestinian and Israeli identities by five popular LLMs across 640 experimental conditions, varying context (war vs non-war) and assigned roles. We observe significant distributional patterns in the generated attributes: Palestinian profiles in war contexts are frequently associated with lower socioeconomic status and survival-oriented roles, whereas Israeli profiles predominantly retain middle-class status and specialised professional attributes. When prompted with explicit instructions to avoid harmful assumptions, models exhibit diverse distributional changes, e.g., marked increases in non-binary gender inferences or a convergence toward generic occupational roles (e.g., "student"), while the underlying socioeconomic distinctions often remain. Furthermore, analysis of reasoning traces reveals an interesting dynamics between model reasoning and generation: while rationales consistently mention fairness-related concepts, the final generated personas follow the aforementioned diverse distributional changes. These findings illustrate a picture of how models interpret geopolitical contexts, while suggesting that they process fairness and adjust in varied ways; there is no consistent, direct translation of fairness concepts into representative outcomes.

---

### Improving Safety Alignment via Balanced Direct Preference Optimization

Authors: Shiji Zhao, Mengyang Wang, Shukun Xiong, Fangzhou Chen, Qihui Zhu, Shouwei Ruan, Yisong Xiao, Ranjie Duan, Xun Chen, XingXing Wei
Published: 2026-03-24
Categories: cs.AI
arXiv: https://arxiv.org/abs/2603.22829v1

With the rapid development and widespread application of Large Language Models (LLMs), their potential safety risks have attracted widespread attention. Reinforcement Learning from Human Feedback (RLHF) has been adopted to enhance the safety performance of LLMs. As a simple and effective alternative to RLHF, Direct Preference Optimization (DPO) is widely used for safety alignment. However, safety alignment still suffers from severe overfitting, which limits its actual performance. This paper revisits the overfitting phenomenon from the perspective of the model's comprehension of the training data. We find that the Imbalanced Preference Comprehension phenomenon exists between responses in preference pairs, which compromises the model's safety performance. To address this, we propose Balanced Direct Preference Optimization (B-DPO), which adaptively modulates optimization strength between preferred and dispreferred responses based on mutual information. A series of experimental results show that B-DPO can enhance the safety capability while maintaining the competitive general capabilities of LLMs on various mainstream benchmarks compared to state-of-the-art methods. \color{red}{Warning: This paper contains examples of harmful texts, and reader discretion is recommended.

---

### MVRD-Bench: Multi-View Learning and Benchmarking for Dynamic Remote Photoplethysmography under Occlusion

Authors: Zuxian He, Xu Cheng, Zhaodong Sun, Haoyu Chen, Jingang Shi, Xiaobai Li, Guoying Zhao
Published: 2026-03-24
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.22826v1

Remote photoplethysmography (rPPG) is a non-contact technique that estimates physiological signals by analyzing subtle skin color changes in facial videos. Existing rPPG methods often encounter performance degradation under facial motion and occlusion scenarios due to their reliance on static and single-view facial videos. Thus, this work focuses on tackling the motion-induced occlusion problem for rPPG measurement in unconstrained multi-view facial videos. Specifically, we introduce a Multi-View rPPG Dataset (MVRD), a high-quality benchmark dataset featuring synchronized facial videos from three viewpoints under stationary, speaking, and head movement scenarios to better match real-world conditions. We also propose MVRD-rPPG, a unified multi-view rPPG learning framework that fuses complementary visual cues to maintain robust facial skin coverage, especially under motion conditions. Our method integrates an Adaptive Temporal Optical Compensation (ATOC) module for motion artifact suppression, a Rhythm-Visual Dual-Stream Network to disentangle rhythmic and appearance-related features, and a Multi-View Correlation-Aware Attention (MVCA) for adaptive view-wise signal aggregation. Furthermore, we introduce a Correlation Frequency Adversarial (CFA) learning strategy, which jointly enforces temporal accuracy, spectral consistency, and perceptual realism in the predicted signals. Extensive experiments and ablation studies on the MVRD dataset demonstrate the superiority of our approach. In the MVRD movement scenario, MVRD-rPPG achieves an MAE of 0.90 and a Pearson correlation coefficient (R) of 0.99. The source code and dataset will be made available.

---

### Towards The Implicit Bias on Multiclass Separable Data Under Norm Constraints

Authors: Shengping Xie, Zekun Wu, Quan Chen, Kaixu Tang
Published: 2026-03-24
Categories: cs.LG, math.OC, stat.ML
arXiv: https://arxiv.org/abs/2603.22824v1

Implicit bias induced by gradient-based algorithms is essential to the generalization of overparameterized models, yet its mechanisms can be subtle. This work leverages the Normalized Steepest Descent} (NSD) framework to investigate how optimization geometry shapes solutions on multiclass separable data. We introduce NucGD, a geometry-aware optimizer designed to enforce low rank structures through nuclear norm constraints. Beyond the algorithm itself, we connect NucGD with emerging low-rank projection methods, providing a unified perspective. To enable scalable training, we derive an efficient SVD-free update rule via asynchronous power iteration. Furthermore, we empirically dissect the impact of stochastic optimization dynamics, characterizing how varying levels of gradient noise induced by mini-batch sampling and momentum modulate the convergence toward the expected maximum margin solutions.Our code is accessible at: https://github.com/Tsokarsic/observing-the-implicit-bias-on-multiclass-seperable-data.

---

### Empirical Comparison of Agent Communication Protocols for Task Orchestration

Authors: Ivan Dobrovolskyi
Published: 2026-03-24
Categories: cs.AI
arXiv: https://arxiv.org/abs/2603.22823v3

Context. The problem of comparative evaluation of communication protocols for task orchestration by large language model (LLM) agents is considered. The object of study is the process of interaction between LLM agents and external tools, as well as between autonomous LLM agents, during task orchestration. Objective. The goal of this work is to develop a systematic pilot benchmark comparing tool integration, multi-agent dele-gation, and hybrid architectures for standardized queries at three levels of complexity, and to quantify the advantages and disadvantages in terms of response time, context window consumption, cost, error recovery, and implementation complexity.

---

### Cross-Slice Knowledge Transfer via Masked Multi-Modal Heterogeneous Graph Contrastive Learning for Spatial Gene Expression Inference

Authors: Zhiceng Shi, Changmiao Wang, Jun Wan, Wenwen Min
Published: 2026-03-24
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.22821v1

While spatial transcriptomics (ST) has advanced our understanding of gene expression in tissue context, its high experimental cost limits its large-scale application. Predicting ST from pathology images is a promising, cost-effective alternative, but existing methods struggle to capture complex cross-slide spatial relationships. To address the challenge, we propose SpaHGC, a multi-modal heterogeneous graph-based model that captures both intra-slice and inter-slice spot-spot relationships from histology images. It integrates local spatial context within the target slide and cross-slide similarities computed from image embeddings extracted by a pathology foundation model. These embeddings enable inter-slice knowledge transfer, and SpaHGC further incorporates Masked Graph Contrastive Learning to enhance feature representation and transfer spatial gene expression knowledge from reference to target slides, enabling it to model complex spatial dependencies and significantly improve prediction accuracy. We conducted comprehensive benchmarking on seven matched histology-ST datasets from different platforms, tissues, and cancer subtypes. The results demonstrate that SpaHGC significantly outperforms the existing nine state-of-the-art methods across all evaluation metrics. Additionally, the predictions are significantly enriched in multiple cancer-related pathways, thereby highlighting its strong biological relevance and application potential.

---

### RadTimeline: Timeline Summarization for Longitudinal Radiological Lung Findings

Authors: Sitong Zhou, Meliha Yetisgen, Mari Ostendorf
Published: 2026-03-24
Categories: cs.CL
arXiv: https://arxiv.org/abs/2603.22820v1

Tracking findings in longitudinal radiology reports is crucial for accurately identifying disease progression, and the time-consuming process would benefit from automatic summarization. This work introduces a structured summarization task, where we frame longitudinal report summarization as a timeline generation task, with dated findings organized in columns and temporally related findings grouped in rows. This structured summarization format enables straightforward comparison of findings across time and facilitates fact-checking against the associated reports. The timeline is generated using a 3-step LLM process of extracting findings, generating group names, and using the names to group the findings. To evaluate such systems, we create RadTimeline, a timeline dataset focused on tracking lung-related radiologic findings in chest-related imaging reports. Experiments on RadTimeline show tradeoffs of different-sized LLMs and prompting strategies. Our results highlight that group name generation as an intermediate step is critical for effective finding grouping. The best configuration has some irrelevant findings but very good recall, and grouping performance is comparable to human annotators.

---

### TDATR: Improving End-to-End Table Recognition via Table Detail-Aware Learning and Cell-Level Visual Alignment

Authors: Chunxia Qin, Chenyu Liu, Pengcheng Xia, Jun Du, Baocai Yin, Bing Yin, Cong Liu
Published: 2026-03-24
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2603.22819v1

Tables are pervasive in diverse documents, making table recognition (TR) a fundamental task in document analysis. Existing modular TR pipelines separately model table structure and content, leading to suboptimal integration and complex workflows. End-to-end approaches rely heavily on large-scale TR data and struggle in data-constrained scenarios. To address these issues, we propose TDATR (Table Detail-Aware Table Recognition) improves end-to-end TR through table detail-aware learning and cell-level visual alignment. TDATR adopts a ``perceive-then-fuse'' strategy. The model first performs table detail-aware learning to jointly perceive table structure and content through multiple structure understanding and content recognition tasks designed under a language modeling paradigm. These tasks can naturally leverage document data from diverse scenarios to enhance model robustness. The model then integrates implicit table details to generate structured HTML outputs, enabling more efficient TR modeling when trained with limited data. Furthermore, we design a structure-guided cell localization module integrated into the end-to-end TR framework, which efficiently locates cell and strengthens vision-language alignment. It enhances the interpretability and accuracy of TR. We achieve state-of-the-art or highly competitive performance on seven benchmarks without dataset-specific fine-tuning.

---

### Measuring and curing reasoning rigidity: from decorative chain-of-thought to genuine faithfulness

Authors: Abhinaba Basu, Pavan Chakraborty
Published: 2026-03-24
Categories: cs.CL, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2603.22816v3

Language models increasingly show their work by writing step-by-step reasoning before answering. But are these steps genuinely used, or is the answer rigid - fixed before reasoning begins? We introduce the Step-Level Reasoning Capacity (SLRC) metric and prove it is a consistent causal estimator (Theorem 1). We propose LC-CoSR, a training method with Lyapunov stability guarantees that directly reduces rigidity. Evaluating 16 frontier models (o4-mini, GPT-5.4, Claude Opus, Grok-4, DeepSeek-R1, Gemini 2.5 Pro, and others) across six domains at N=133-500, we find reasoning falls into three modes. OpenAI's o4-mini shows 74-88% step necessity on five of six tasks (73.8-88.3%) - the highest SLRC in our study. The critical differentiator is RL-based reasoning training, not thinking tokens: Grok-4's reasoning mode shows lower faithfulness than its non-reasoning mode (1.4% vs 7.2% necessity). We discover a faithfulness paradox - high-SLRC models are more susceptible to sycophancy - and propose the Reasoning Integrity Score (RIS = SLRC x (1-Sycophancy)), which significantly predicts error detection (rho=0.66, p=0.026). LC-CoSR achieves 2.6x less negative reward than FARL and CSR baselines without external model dependencies.

---

### Focus, Don't Prune: Identifying Instruction-Relevant Regions for Information-Rich Image Understanding

Authors: Mincheol Kwon, Minseung Lee, Seonga Choi, Miso Choi, Kyeong-Jin Oh, Hyunyoung Lee, Cheonyoung Park, Yongho Song, Seunghyun Park, Jinkyu Kim
Published: 2026-03-24
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2603.22815v1

Large Vision-Language Models (LVLMs) have shown strong performance across various multimodal tasks by leveraging the reasoning capabilities of Large Language Models (LLMs). However, processing visually complex and information-rich images, such as infographics or document layouts, requires these models to generate a large number of visual tokens, leading to significant computational overhead. To address this, we propose PinPoint, a novel two-stage framework that first identifies instruction-relevant image regions and then refines them to extract fine-grained visual features for improved reasoning and efficiency. Central to our approach is the Instruction-Region Alignment, which localizes relevant regions using both visual input and textual instructions. We further introduce new annotations that provide richer ground-truth supervision for instruction-relevant regions across challenging VQA benchmarks: InfographicVQA, MultiPageDocVQA, and SinglePageDocVQA. Experimental results show that PinPoint not only achieves superior accuracy compared to existing methods but also reduces computational overhead by minimizing irrelevant visual tokens.

---

### Learning What Matters Now: Dynamic Preference Inference under Contextual Shifts

Authors: Xianwei Cao, Dou Quan, Zhenliang Zhang, Shuang Wang
Published: 2026-03-24
Categories: cs.AI
arXiv: https://arxiv.org/abs/2603.22813v1

Humans often juggle multiple, sometimes conflicting objectives and shift their priorities as circumstances change, rather than following a fixed objective function. In contrast, most computational decision-making and multi-objective RL methods assume static preference weights or a known scalar reward. In this work, we study sequential decision-making problem when these preference weights are unobserved latent variables that drift with context. Specifically, we propose Dynamic Preference Inference (DPI), a cognitively inspired framework in which an agent maintains a probabilistic belief over preference weights, updates this belief from recent interaction, and conditions its policy on inferred preferences. We instantiate DPI as a variational preference inference module trained jointly with a preference-conditioned actor-critic, using vector-valued returns as evidence about latent trade-offs. In queueing, maze, and multi-objective continuous-control environments with event-driven changes in objectives, DPI adapts its inferred preferences to new regimes and achieves higher post-shift performance than fixed-weight and heuristic envelope baselines.

---

### Efficient Hallucination Detection: Adaptive Bayesian Estimation of Semantic Entropy with Guided Semantic Exploration

Authors: Qiyao Sun, Xingming Li, Xixiang He, Ao Cheng, Xuanyu Ji, Hailun Lu, Runke Huang, Qingyong Hu
Published: 2026-03-24
Categories: cs.CL
arXiv: https://arxiv.org/abs/2603.22812v1

Large language models (LLMs) have achieved remarkable success in various natural language processing tasks, yet they remain prone to generating factually incorrect outputs known as hallucinations. While recent approaches have shown promise for hallucination detection by repeatedly sampling from LLMs and quantifying the semantic inconsistency among the generated responses, they rely on fixed sampling budgets that fail to adapt to query complexity, resulting in computational inefficiency. We propose an Adaptive Bayesian Estimation framework for Semantic Entropy with Guided Semantic Exploration, which dynamically adjusts sampling requirements based on observed uncertainty. Our approach employs a hierarchical Bayesian framework to model the semantic distribution, enabling dynamic control of sampling iterations through variance-based thresholds that terminate generation once sufficient certainty is achieved. We also develop a perturbation-based importance sampling strategy to systematically explore the semantic space. Extensive experiments on four QA datasets demonstrate that our method achieves superior hallucination detection performance with significant efficiency gains. In low-budget scenarios, our approach requires about 50% fewer samples to achieve comparable detection performance to existing methods, while delivers an average AUROC improvement of 12.6% under the same sampling budget.

---

### Universal and efficient graph neural networks with dynamic attention for machine learning interatomic potentials

Authors: Shuyu Bi, Zhede Zhao, Qiangchao Sun, Tao Hu, Xionggang Lu, Hongwei Cheng
Published: 2026-03-24
Categories: cs.LG
arXiv: https://arxiv.org/abs/2603.22810v1

The core of molecular dynamics simulation fundamentally lies in the interatomic potential. Traditional empirical potentials lack accuracy, while first-principles methods are computationally prohibitive. Machine learning interatomic potentials (MLIPs) promise near-quantum accuracy at linear cost, but existing models still face challenges in efficiency and stability. We presents Machine Learning Advances Neural Network (MLANet), an efficient and robust graph neural network framework. MLANet introduces a dual-path dynamic attention mechanism for geometry-aware message passing and a multi-perspective pooling strategy to construct comprehensive system representations. This design enables highly accurate modeling of atomic environments while achieving exceptional computational efficiency, making high-fidelity simulations more accessible. Tested across a wide range of datasets spanning diverse systems, including organic molecules (e.g., QM7, MD17), periodic inorganic materials (e.g., Li-containing crystals), two-dimensional materials (e.g., bilayer graphene, black phosphorus), surface catalytic reactions (e.g., formate decomposition), and charged systems, MLANet maintains competitive prediction accuracy while its computational cost is markedly lower than mainstream equivariant models, and it enables stable long-time molecular dynamics simulations. MLANet provides an efficient and practical tool for large-scale, high-accuracy atomic simulations.

---

### Combinatorial Privacy: Private Multi-Party Bitstream Grand Sum by Hiding in Birkhoff Polytopes

Authors: Praneeth Vepakomma
Published: 2026-03-24
Categories: cs.CR, cs.LG
arXiv: https://arxiv.org/abs/2603.22808v4

We introduce PolyVeil, a protocol for private Boolean summation across $k$ clients that encodes private bits as permutation matrices in the Birkhoff polytope. A two-layer architecture gives the server perfect simulation-based security (statistical distance zero) while a separate aggregator faces \#P-hard likelihood inference via the permanent and mixed discriminant. Two variants (full and compressed) differ in what the aggregator observes. We develop a finite-sample $(\varepsilon,δ)$-DP analysis with explicit constants. In the full variant, where the aggregator sees a doubly stochastic matrix per client, the log-Lipschitz constant grows as $n^4 K_t$ and a signal-to-noise analysis shows the DP guarantee is non-vacuous only when the private signal is undetectable. In the compressed variant, where the aggregator sees a single scalar, the univariate density ratio yields non-vacuous $\varepsilon$ at moderate SNR, with the optimal decoy count balancing CLT accuracy against noise concentration. This exposes a fundamental tension. \#P-hardness requires the full matrix view (Birkhoff structure visible), while non-vacuous DP requires the scalar view (low dimensionality). Whether both hold simultaneously in one variant remains open. The protocol needs no PKI, has $O(k)$ communication, and outputs exact aggregates.

---

### Transformers Trained via Gradient Descent Can Provably Learn a Class of Teacher Models

Authors: Chenyang Zhang, Qingyue Zhao, Quanquan Gu, Yuan Cao
Published: 2026-03-24
Categories: cs.LG
arXiv: https://arxiv.org/abs/2603.22801v1

Transformers have achieved great success across a wide range of applications, yet the theoretical foundations underlying their success remain largely unexplored. To demystify the strong capacities of transformers applied to versatile scenarios and tasks, we theoretically investigate utilizing transformers as students to learn from a class of teacher models. Specifically, the teacher models covered in our analysis include convolution layers with average pooling, graph convolution layers, and various classic statistical learning models, including a variant of sparse token selection models (Sanford et al., 2023, Wang et al., 2024) and group-sparse linear predictors (Zhang et al., 2025). When learning from this class of teacher models, we prove that one-layer transformers with simplified "position-only'' attention can successfully recover all parameter blocks of the teacher models, thus achieving the optimal population loss. Building upon the efficient mimicry of trained transformers towards teacher models, we further demonstrate that they can generalize well to a broad class of out-of-distribution data under mild assumptions. The key in our analysis is to identify a fundamental bilinear structure shared by various learning tasks, which enables us to establish unified learning guarantees for these tasks when treating them as teachers for transformers.

---

### Span Modeling for Idiomaticity and Figurative Language Detection with Span Contrastive Loss

Authors: Blake Matheny, Phuong Minh Nguyen, Minh Le Nguyen
Published: 2026-03-24
Categories: cs.CL
arXiv: https://arxiv.org/abs/2603.22799v1

The category of figurative language contains many varieties, some of which are non-compositional in nature. This type of phrase or multi-word expression (MWE) includes idioms, which represent a single meaning that does not consist of the sum of its words. For language models, this presents a unique problem due to tokenization and adjacent contextual embeddings. Many large language models have overcome this issue with large phrase vocabulary, though immediate recognition frequently fails without one- or few-shot prompting or instruction finetuning. The best results have been achieved with BERT-based or LSTM finetuning approaches. The model in this paper contains one such variety. We propose BERT- and RoBERTa-based models finetuned with a combination of slot loss and span contrastive loss (SCL) with hard negative reweighting to improve idiomaticity detection, attaining state of the art sequence accuracy performance on existing datasets. Comparative ablation studies show the effectiveness of SCL and its generalizability. The geometric mean of F1 and sequence accuracy (SA) is also proposed to assess a model's span awareness and general performance together.

---

### PhotoAgent: A Robotic Photographer with Spatial and Aesthetic Understanding

Authors: Lirong Che, Zhenfeng Gan, Yanbo Chen, Junbo Tan, Xueqian Wang
Published: 2026-03-24
Categories: cs.CV, cs.AI, cs.RO
arXiv: https://arxiv.org/abs/2603.22796v1

Embodied agents for creative tasks like photography must bridge the semantic gap between high-level language commands and geometric control. We introduce PhotoAgent, an agent that achieves this by integrating Large Multimodal Models (LMMs) reasoning with a novel control paradigm. PhotoAgent first translates subjective aesthetic goals into solvable geometric constraints via LMM-driven, chain-of-thought (CoT) reasoning, allowing an analytical solver to compute a high-quality initial viewpoint. This initial pose is then iteratively refined through visual reflection within a photorealistic internal world model built with 3D Gaussian Splatting (3DGS). This ``mental simulation'' replaces costly and slow physical trial-and-error, enabling rapid convergence to aesthetically superior results. Evaluations confirm that PhotoAgent excels in spatial reasoning and achieves superior final image quality.

---

### It Takes Two: A Duet of Periodicity and Directionality for Burst Flicker Removal

Authors: Lishen Qu, Shihao Zhou, Jie Liang, Hui Zeng, Lei Zhang, Jufeng Yang
Published: 2026-03-24
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.22794v1

Flicker artifacts, arising from unstable illumination and row-wise exposure inconsistencies, pose a significant challenge in short-exposure photography, severely degrading image quality. Unlike typical artifacts, e.g., noise and low-light, flicker is a structured degradation with specific spatial-temporal patterns, which are not accounted for in current generic restoration frameworks, leading to suboptimal flicker suppression and ghosting artifacts. In this work, we reveal that flicker artifacts exhibit two intrinsic characteristics, periodicity and directionality, and propose Flickerformer, a transformer-based architecture that effectively removes flicker without introducing ghosting. Specifically, Flickerformer comprises three key components: a phase-based fusion module (PFM), an autocorrelation feed-forward network (AFFN), and a wavelet-based directional attention module (WDAM). Based on the periodicity, PFM performs inter-frame phase correlation to adaptively aggregate burst features, while AFFN exploits intra-frame structural regularities through autocorrelation, jointly enhancing the network's ability to perceive spatially recurring patterns. Moreover, motivated by the directionality of flicker artifacts, WDAM leverages high-frequency variations in the wavelet domain to guide the restoration of low-frequency dark regions, yielding precise localization of flicker artifacts. Extensive experiments demonstrate that Flickerformer outperforms state-of-the-art approaches in both quantitative metrics and visual quality. The source code is available at https://github.com/qulishen/Flickerformer.

---

### Signals Are Not States: Neuro-Symbolic Safeguards for Culturally Aware Classroom AI

Authors: Sina Bagheri Nezhad
Published: 2026-03-24
Categories: cs.AI
arXiv: https://arxiv.org/abs/2603.22793v2

Classroom AI systems increasingly infer high-level educational states such as engagement, confusion, collaboration, participation, and instructional quality from multimodal and linguistic signals. In multicultural and multilingual classrooms, such inferences can translate culturally situated behavior into stereotyped claims: silence may be read as disengagement, gaze aversion as inattention, code-switching as low proficiency, or indirect help-seeking as confusion. We argue that stereotype-aware classroom AI should separate observable evidence from culturally loaded interpretation and should treat unsupported construct-level claims as safety risks. We introduce NSCR, a culturally grounded neuro-symbolic framework that converts video, audio, ASR, lesson artifacts, and contextual metadata into typed facts with uncertainty, provenance, and cultural scope, then composes them through executable reasoning and policy constraints. We define a taxonomy of stereotype-prone classroom inferences and propose a benchmark agenda covering culture-conditioned state inference, evidence-grounded claim verification, multilingual and code-switched reasoning, collaboration analysis, counterfactual cultural robustness, and culture-conditioned red-teaming. We further specify metrics for stereotype leakage, unsupported attribution, cultural calibration gaps, abstention under cultural ambiguity, and evidence faithfulness. The contribution is methodological: a concrete framework and evaluation agenda for mitigating stereotyped reasoning in classroom AI, with education as a high-stakes, culturally variable deployment setting.

---

### ABSTRAL: Automatic Design of Multi-Agent Systems Through Iterative Refinement and Topology Optimization

Authors: Weijia Song, Jiashu Yue, Zhe Pang
Published: 2026-03-24
Categories: cs.AI
arXiv: https://arxiv.org/abs/2603.22791v1

How should multi-agent systems be designed, and can that design knowledge be captured in a form that is inspectable, revisable, and transferable? We introduce ABSTRAL, a framework that treats MAS architecture as an evolving natural-language document, an artifact refined through contrastive trace analysis. Three findings emerge. First, we provide a precise measurement of the multi-agent coordination tax: under fixed turn budgets, ensembles achieve only 26% turn efficiency, with 66% of tasks exhausting the limit, yet still improve over single-agent baselines by discovering parallelizable task decompositions. Second, design knowledge encoded in documents transfers: topology reasoning and role templates learned on one domain provide a head start on new domains, with transferred seeds matching coldstart iteration 3 performance in a single iteration. Third, contrastive trace analysis discovers specialist roles absent from any initial design, a capability no prior system demonstrates. On SOPBench (134 bank tasks, deterministic oracle), ABSTRAL reaches 70% validation / 65.96% test pass rate with a GPT-4o backbone. We release the converged documents as inspectable design rationale.

---

### Quantum Random Forest for the Regression Problem

Authors: Kamil Khadiev, Liliya Safina
Published: 2026-03-24
Categories: quant-ph, cs.AI
arXiv: https://arxiv.org/abs/2603.22790v1

The Random Forest model is one of the popular models of Machine learning. We present a quantum algorithm for testing (forecasting) process of the Random Forest machine learning model for the Regression problem. The presented algorithm is more efficient (in terms of query complexity or running time) than the classical counterpart.

---

### Predictive Photometric Uncertainty in Gaussian Splatting for Novel View Synthesis

Authors: Chamuditha Jayanga Galappaththige, Thomas Gottwald, Peter Stehr, Edgar Heinert, Niko Suenderhauf, Dimity Miller, Matthias Rottmann
Published: 2026-03-24
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.22786v2

Recent advances in 3D Gaussian Splatting have enabled impressive photorealistic novel view synthesis. However, to transition from a pure rendering engine to a reliable spatial map for autonomous agents and safety-critical applications, knowing where the representation is uncertain is as important as the rendering fidelity itself. We bridge this critical gap by introducing a lightweight, plug-and-play framework for pixel-wise, view-dependent predictive uncertainty estimation. Our post-hoc method formulates uncertainty as a Bayesian-regularized linear least-squares optimization over reconstruction residuals. This architecture-agnostic approach extracts a per-primitive uncertainty channel without modifying the underlying scene representation or degrading baseline visual fidelity. Crucially, we demonstrate that providing this actionable reliability signal successfully translates 3D Gaussian splatting into a trustworthy spatial map, further improving state-of-the-art performance across three critical downstream perception tasks: active view selection, pose-agnostic scene change detection, and pose-agnostic anomaly detection.

---

### Exposure-Normalized Bed and Chair Fall Rates via Continuous AI Monitoring

Authors: Paolo Gabriel, Peter Rehani, Zack Drumm, Tyler Troy, Tiffany Wyatt, Narinder Singh
Published: 2026-03-24
Categories: cs.CV, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2603.22785v1

This retrospective cohort study used continuous AI monitoring to estimate fall rates by exposure time rather than occupied bed-days. From August 2024 to December 2025, 3,980 eligible monitoring units contributed 292,914 hourly rows, yielding probability-weighted rates of 17.8 falls per 1,000 chair exposure-hours and 4.3 per 1,000 bed exposure-hours. Within the study window, 43 adjudicated falls matched the monitoring pipeline, and 40 linked to eligible exposure hours for the primary Poisson model, producing an adjusted chair-versus-bed rate ratio of 2.35 (95% confidence interval 0.87 to 6.33; p=0.0907). In a separate broader observation cohort (n=32 deduplicated events), 6 of 7 direct chair falls involved footrest-positioning failures. Because this was an observational study in a single health system, these findings remain hypothesis-generating and support testing safer chair setups rather than using chairs less.

---

### Caterpillar of Thoughts: The Optimal Test-Time Algorithm for Large Language Models

Authors: Amir Azarmehr, Soheil Behnezhad, Alma Ghafari
Published: 2026-03-24
Categories: cs.LG
arXiv: https://arxiv.org/abs/2603.22784v1

Large language models (LLMs) can often produce substantially better outputs when allowed to use additional test-time computation, such as sampling, chain of thought, backtracking, or revising partial solutions. Despite the growing empirical success of such techniques, there is limited theoretical understanding of how inference time computation should be structured, or what constitutes an optimal use of a fixed computation budget. We model test-time computation as an algorithm interacting with a Markov chain: at any point, the algorithm may resume generation from any previously observed state. That is, unlike standard Markov chains where the states are drawn passively, we allow the algorithm to backtrack to any previously observed state of the Markov chain at any time. Many of the existing test-time algorithms, such as Chain-of-Thought (CoT) (Wei et al., 2023), Tree-of-Thoughts (ToT) (Yao et al., 2023), or Best-of-$k$ (Brown et al., 2024) could be seen as specific algorithms in this model. We prove that while backtracking can reduce the number of generations exponentially, a very limited form of backtracking is theoretically sufficient. Namely, we show that the optimal algorithm always generates a caterpillar tree. That is, if we remove the leaves of the state tree generated by the optimal algorithm, we obtain a path. Motivated by our characterization of the optimal algorithm, we present Caterpillar of Thoughts (CaT), a new test-time computation algorithm, reducing the number of token/state generations. Our empirical evaluation shows that CaT, compared to ToT, achieves a better success rate while also reducing the number of token generations.

---

### Know3D: Prompting 3D Generation with Knowledge from Vision-Language Models

Authors: Wenyue Chen, Wenjue Chen, Peng Li, Qinghe Wang, Xu Jia, Heliang Zheng, Rongfei Jia, Yuan Liu, Ronggang Wang
Published: 2026-03-24
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.22782v2

Recent advances in 3D generation have improved the fidelity and geometric details of synthesized 3D assets. However, due to the inherent ambiguity of single-view observations and the lack of robust global structural priors caused by limited 3D training data, the unseen regions generated by existing models are often stochastic and difficult to control, which may sometimes fail to align with user intentions or produce implausible geometries. In this paper, we propose Know3D, a novel framework that incorporates rich knowledge from multimodal large language models into 3D generative processes via latent hidden-state injection, enabling language-controllable generation of the back-view for 3D assets. We utilize a VLM-diffusion-based model, where the VLM is responsible for semantic understanding and guidance. The diffusion model acts as a bridge that transfers semantic knowledge from the VLM to the 3D generation model. In this way, we successfully bridge the gap between abstract textual instructions and the geometric reconstruction of unobserved regions, transforming the traditionally stochastic back-view hallucination into a semantically controllable process, demonstrating a promising direction for future 3D generation models.

---

### Know3D: Prompting 3D Generation with Knowledge from Vision-Language Models

Authors: Wenyue Chen, Wenjue Chen, Peng Li, Qinghe Wang, Xu Jia, Heliang Zheng, Rongfei Jia, Yuan Liu, Ronggang Wang
Published: 2026-03-24
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.22782v1

Recent advances in 3D generation have improved the fidelity and geometric details of synthesized 3D assets. However, due to the inherent ambiguity of single-view observations and the lack of robust global structural priors caused by limited 3D training data, the unseen regions generated by existing models are often stochastic and difficult to control, which may sometimes fail to align with user intentions or produce implausible geometries. In this paper, we propose Know3D, a novel framework that incorporates rich knowledge from multimodal large language models into 3D generative processes via latent hidden-state injection, enabling language-controllable generation of the back-view for 3D assets. We utilize a VLM-diffusion-based model, where the VLM is responsible for semantic understanding and guidance. The diffusion model acts as a bridge that transfers semantic knowledge from the VLM to the 3D generation model. In this way, we successfully bridge the gap between abstract textual instructions and the geometric reconstruction of unobserved regions, transforming the traditionally stochastic back-view hallucination into a semantically controllable process, demonstrating a promising direction for future 3D generation models.

---

### Typography-Based Monocular Distance Estimation Framework for Vehicle Safety Systems

Authors: Manognya Lokesh Reddy, Zheng Liu
Published: 2026-03-24
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.22781v1

Accurate inter-vehicle distance estimation is a cornerstone of advanced driver assistance systems and autonomous driving. While LiDAR and radar provide high precision, their cost prohibits widespread adoption in mass-market vehicles. Monocular vision offers a low-cost alternative but suffers from scale ambiguity and sensitivity to environmental disturbances. This paper introduces a typography-based monocular distance estimation framework, which exploits the standardized typography of license plates as passive fiducial markers for metric distance estimation. The core geometric module uses robust plate detection and character segmentation to measure character height and computes distance via the pinhole camera model. The system incorporates interactive calibration, adaptive detection with strict and permissive modes, and multi-method character segmentation leveraging both adaptive and global thresholding. To enhance robustness, the framework further includes camera pose compensation using lane-based horizon estimation, hybrid deep-learning fusion, temporal Kalman filtering for velocity estimation, and multi-feature fusion that exploits additional typographic cues such as stroke width, character spacing, and plate border thickness. Experimental validation with a calibrated monocular camera in a controlled indoor setup achieved a coefficient of variation of 2.3% in character height across consecutive frames and a mean absolute error of 7.7%. The framework operates without GPU acceleration, demonstrating real-time feasibility. A comprehensive comparison with a plate-width based method shows that character-based ranging reduces the standard deviation of estimates by 35%, translating to smoother, more consistent distance readings in practice, where erratic estimates could trigger unnecessary braking or acceleration.

---

### KARMA: Knowledge-Action Regularized Multimodal Alignment for Personalized Search at Taobao

Authors: Zhi Sun, Wenming Zhang, Yi Wei, Liren Yu, Zhixuan Zhang, Dan Ou, Haihong Tang
Published: 2026-03-24
Categories: cs.IR, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2603.22779v2

Large Language Models (LLMs) are equipped with profound semantic knowledge, making them a natural choice for injecting semantic generalization into personalized search systems. However, in practice we find that directly fine-tuning LLMs on industrial personalized tasks (e.g. next item prediction) often yields suboptimal results. We attribute this bottleneck to a critical Knowledge--Action Gap: the inherent conflict between preserving pre-trained semantic knowledge and aligning with specific personalized actions by discriminative objectives. Empirically, action-only training objectives induce Semantic Collapse, such as attention "sinks". This degradation severely cripples the LLM's generalization, failing to bring improvements to personalized search systems. We propose KARMA (Knowledge--Action Regularized Multimodal Alignment), a unified framework that treats semantic reconstruction as a train-only regularizer. KARMA optimizes a next-interest embedding for retrieval (Action) while enforcing semantic decodability (Knowledge) through two complementary objectives: (i) history-conditioned semantic generation, which anchors optimization to the LLM's native next-token distribution, and (ii) embedding-conditioned semantic reconstruction, which constrains the interest embedding to remain semantically recoverable. On Taobao search system, KARMA mitigates semantic collapse (attention-sink analysis) and improves both action metrics and semantic fidelity. In ablations, semantic decodability yields up to +22.5 HR@200. With KARMA, we achieve +0.25 CTR AUC in ranking, +1.86 HR in pre-ranking and +2.51 HR in recalling. Deployed online with low inference overhead at ranking & pre-ranking stage, KARMA drives +0.9% increase in GMV.

---

### AgriPestDatabase-v1.0: A Structured Insect Dataset for Training Agricultural Large Language Model

Authors: Yagizhan Bilal Durak, Ahsan Ul Islam, Shahidul Islam, Ashley Morgan-Olvera, Iftekhar Ibne Basith, Syed Hasib Akhter Faruqui
Published: 2026-03-24
Categories: cs.AI
arXiv: https://arxiv.org/abs/2603.22777v1

Agricultural pest management increasingly relies on timely and accurate access to expert knowledge, yet high quality labeled data and continuous expert support remain limited, particularly for farmers operating in rural regions with unstable/no internet connectivity. At the same time, the rapid growth of AI and LLMs has created new opportunities to deliver practical decision support tools directly to end users in agriculture through compact and deployable systems. This work addresses (i) generating a structured insect information dataset, and (ii) adapting a lightweight LLM model ($\leq$ 7B) by fine tuning it for edge device uses in agricultural pest management. The textual data collection was done by reviewing and collecting information from available pest databases and published manuscripts on nine selected pest species. These structured reports were then reviewed and validated by a domain expert. From these reports, we constructed Q/A pairs to support model training and evaluation. A LoRA-based fine-tuning approach was applied to multiple lightweight LLMs and evaluated. Initial evaluation shows that Mistral 7B achieves an 88.9\% pass rate on the domain-specific Q/A task, substantially outperforming Qwen 2.5 7B (63.9\%), and LLaMA 3.1 8B (58.7\%). Notably, Mistral demonstrates higher semantic alignment (embedding similarity: 0.865) despite lower lexical overlap (BLEU: 0.097), indicating that semantic understanding and robust reasoning are more predictive of task success than surface-level conformity in specialized domains. By combining expert organized data, well-structured Q/A pairs, semantic quality control, and efficient model adaptation, this work contributes towards providing support for farmer facing agricultural decision support tools and demonstrates the feasibility of deploying compact, high-performing language models for practical field-level pest management guidance.

---

### Viewport-based Neural 360° Image Compression

Authors: Jingwei Liao, Bo Chen, Klara Nahrstedt, Zhisheng Yan
Published: 2026-03-24
Categories: eess.IV, cs.CV
arXiv: https://arxiv.org/abs/2603.22776v1

Given the popularity of 360° images on social media platforms, 360° image compression becomes a critical technology for media storage and transmission. Conventional 360° image compression pipeline projects the spherical image into a single 2D plane, leading to issues of oversampling and distortion. In this paper, we propose a novel viewport-based neural compression pipeline for 360° images. By replacing the image projection in conventional 360° image compression pipelines with viewport extraction and efficiently compressing multiple viewports, the proposed pipeline minimizes the inherent oversampling and distortion issues. However, viewport extraction impedes information sharing between multiple viewports during compression, causing the loss of global information about the spherical image. To tackle this global information loss, we design a neural viewport codec to capture global prior information across multiple viewports and maximally compress the viewport data. The viewport codec is empowered by a transformer-based ViewPort ConText (VPCT) module that can be integrated with canonical learning-based 2D image compression structures. We compare the proposed pipeline with existing 360° image compression models and conventional 360° image compression pipelines building on learning-based 2D image codecs and standard hand-crafted codecs. Results show that our pipeline saves an average of $14.01\%$ bit consumption compared to the best-performing 360° image compression methods without compromising quality. The proposed VPCT-based codec also outperforms existing 2D image codecs in the viewport-based neural compression pipeline. Our code can be found at: https://github.com/Jingwei-Liao/VPCT.

---

### Explainable Threat Attribution for IoT Networks Using Conditional SHAP and Flow Behavior Modelling

Authors: Samuel Ozechi, Jennifer Okonkwoabutu
Published: 2026-03-24
Categories: cs.CR, cs.LG
arXiv: https://arxiv.org/abs/2603.22771v1

As the Internet of Things (IoT) continues to expand across critical infrastructure, smart environments, and consumer devices, securing them against cyber threats has become increasingly vital. Traditional intrusion detection models often treat IoT threats as binary classification problems or rely on opaque models, thereby limiting trust. This work studies multiclass threat attribution in IoT environments using the CICIoT2023 dataset, grouping over 30 attack variants into 8 semantically meaningful classes. We utilize a combination of a gradient boosting model and SHAP (SHapley Additive exPlanations) to deliver both global and class-specific explanations, enabling detailed insight into the features driving each attack classification. The results show that the model distinguishes distinct behavioral signatures of the attacks using flow timing, packet size uniformity, TCP flag dynamics, and statistical variance. Additional analysis that exposes both feature attribution and the decision trajectory per class further validates these observed patterns. Our findings contribute to the development of more accurate and explainable intrusion detection systems, bridging the gap between high-performance machine learning and the need for trust and accountability in AI-driven cybersecurity for IoT environments.

---

### From Arithmetic to Logic: The Resilience of Logic and Lookup-Based Neural Networks Under Parameter Bit-Flips

Authors: Alan T. L. Bacellar, Sathvik Chemudupati, Shashank Nag, Allison Seigler, Priscila M. V. Lima, Felipe M. G. França, Lizy K. John
Published: 2026-03-24
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2603.22770v2

The deployment of deep neural networks (DNNs) in safety-critical edge environments necessitates robustness against hardware-induced bit-flip errors. While empirical studies indicate that reducing numerical precision can improve fault tolerance, the theoretical basis of this phenomenon remains underexplored. In this work, we study resilience as a structural property of neural architectures rather than solely as a property of a dataset-specific trained solution. By deriving the expected squared error (MSE) under independent parameter bit flips across multiple numerical formats and layer primitives, we show that lower precision, higher sparsity, bounded activations, and shallow depth are consistently favored under this corruption model. We then argue that logic and lookup-based neural networks realize the joint limit of these design trends. Through ablation studies on the MLPerf Tiny benchmark suite, we show that the observed empirical trends are consistent with the theoretical predictions, and that LUT-based models remain highly stable in corruption regimes where standard floating-point models fail sharply. Furthermore, we identify a novel even-layer recovery effect unique to logic-based architectures and analyze the structural conditions under which it emerges. Overall, our results suggest that shifting from continuous arithmetic weights to discrete Boolean lookups can provide a favorable accuracy-resilience trade-off for hardware fault tolerance.

---

### From Pixels to Semantics: A Multi-Stage AI Framework for Structural Damage Detection in Satellite Imagery

Authors: Bijay Shakya, Catherine Hoier, Khandaker Mamun Ahmed
Published: 2026-03-24
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.22768v1

Rapid and accurate structural damage assessment following natural disasters is critical for effective emergency response and recovery. However, remote sensing imagery often suffers from low spatial resolution, contextual ambiguity, and limited semantic interpretability, reducing the reliability of traditional detection pipelines. In this work, we propose a novel hybrid framework that integrates AI-based super-resolution, deep learning object detection, and Vision-Language Models (VLMs) for comprehensive post-disaster building damage assessment. First, we enhance pre- and post-disaster satellite imagery using a Video Restoration Transformer (VRT) to upscale images from 1024x1024 to 4096x4096 resolution, improving structural detail visibility. Next, a YOLOv11-based detector localizes buildings in pre-disaster imagery, and cropped building regions are analyzed using VLMs to semantically assess structural damage across four severity levels. To ensure robust evaluation in the absence of ground-truth captions, we employ CLIPScore for reference-free semantic alignment and introduce a multi-model VLM-as-a-Jury strategy to reduce individual model bias in safety-critical decision making. Experiments on subsets of the xBD dataset, including the Moore Tornado and Hurricane Matthew events, demonstrate that the proposed framework enhances the semantic interpretation of damaged buildings. In addition, our framework provides helpful recommendations to first responders for recovery based on damage analysis.

---

### Can LLM Agents Generate Real-World Evidence? Evaluating Observational Studies in Medical Databases

Authors: Dubai Li, Yuxiang He, Yan Hu, Yu Tian, Jingsong Li
Published: 2026-03-24
Categories: cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2603.22767v1

Observational studies can yield clinically actionable evidence at scale, but executing them on real-world databases is open-ended and requires coherent decisions across cohort construction, analysis, and reporting. Prior evaluations of LLM agents emphasize isolated steps or single answers, missing the integrity and internal structure of the resulting evidence bundle. To address this gap, we introduce RWE-bench, a benchmark grounded in MIMIC-IV and derived from peer-reviewed observational studies. Each task provides the corresponding study protocol as the reference standard, requiring agents to execute experiments in a real database and iteratively generate tree-structured evidence bundles. We evaluate six LLMs (three open-source, three closed-source) under three agent scaffolds using both question-level correctness and end-to-end task metrics. Across 162 tasks, task success is low: the best agent reaches 39.9%, and the best open-source model reaches 30.4%. Agent scaffolds also matter substantially, causing over 30% variation in performance metrics. Furthermore, we implement an automated cohort evaluation method to rapidly localize errors and identify agent failure modes. Overall, the results highlight persistent limitations in agents' ability to produce end-to-end evidence bundles, and efficient validation remains an important direction for future work. Code and data are available at https://github.com/somewordstoolate/RWE-bench.

---

### From Overload to Convergence: Supporting Multi-Issue Human-AI Negotiation with Bayesian Visualization

Authors: Mehul Parmar, Chaklam Silpasuwanchai
Published: 2026-03-24
Categories: cs.HC, cs.AI
arXiv: https://arxiv.org/abs/2603.22766v2

As AI systems increasingly mediate negotiations, understanding how the number of negotiated issues impacts human performance is crucial for maintaining human agency. We designed a human-AI negotiation case study in a realistic property rental scenario, varying the number of negotiated issues; empirical findings show that without support, performance stays stable up to three issues but declines as additional issues increase cognitive load. To address this, we introduce a novel uncertainty-based visualization driven by Bayesian estimation of agreement probability. It shows how the space of mutually acceptable agreements narrows as negotiation progresses, helping users identify promising options. In a within-subjects experiment (N=32), it improved human outcomes and efficiency, preserved human control, and avoided redistributing value. Our findings surface practical limits on the complexity people can manage in human-AI negotiation, advance theory on human performance in complex negotiations, and offer validated design guidance for interactive systems.

---

### DALDALL: Data Augmentation for Lexical and Semantic Diverse in Legal Domain by leveraging LLM-Persona

Authors: Janghyeok Choi, Jaewon Lee, Sungzoon Cho
Published: 2026-03-24
Categories: cs.CL, cs.AI, cs.IR
arXiv: https://arxiv.org/abs/2603.22765v1

Data scarcity remains a persistent challenge in low-resource domains. While existing data augmentation methods leverage the generative capabilities of large language models (LLMs) to produce large volumes of synthetic data, these approaches often prioritize quantity over quality and lack domain-specific strategies. In this work, we introduce DALDALL, a persona-based data augmentation framework tailored for legal information retrieval (IR). Our method employs domain-specific professional personas--such as attorneys, prosecutors, and judges--to generate synthetic queries that exhibit substantially greater lexical and semantic diversity than vanilla prompting approaches. Experiments on the CLERC and COLIEE benchmarks demonstrate that persona-based augmentation achieves improvement in lexical diversity as measured by Self-BLEU scores, while preserving semantic fidelity to the original queries. Furthermore, dense retrievers fine-tuned on persona-augmented data consistently achieve competitive or superior recall performance compared to those trained on original data or generic augmentations. These findings establish persona-based prompting as an effective strategy for generating high-quality training data in specialized, low-resource domains.

---

### ENC-Bench: A Benchmark for Evaluating Multimodal Large Language Models in Electronic Navigational Chart Understanding

Authors: Ao Cheng, Xingming Li, Xuanyu Ji, Xixiang He, Qiyao Sun, Chunping Qiu, Runke Huang, Qingyong Hu
Published: 2026-03-24
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.22763v1

Electronic Navigational Charts (ENCs) are the safety-critical backbone of modern maritime navigation, yet it remains unclear whether multimodal large language models (MLLMs) can reliably interpret them. Unlike natural images or conventional charts, ENCs encode regulations, bathymetry, and route constraints via standardized vector symbols, scale-dependent rendering, and precise geometric structure -- requiring specialized maritime expertise for interpretation. We introduce ENC-Bench, the first benchmark dedicated to professional ENC understanding. ENC-Bench contains 20,490 expert-validated samples from 840 authentic National Oceanic and Atmospheric Administration (NOAA) ENCs, organized into a three-level hierarchy: Perception (symbol and feature recognition), Spatial Reasoning (coordinate localization, bearing, distance), and Maritime Decision-Making (route legality, safety assessment, emergency planning under multiple constraints). All samples are generated from raw S-57 data through a calibrated vector-to-image pipeline with automated consistency checks and expert review. We evaluate 10 state-of-the-art MLLMs such as GPT-4o, Gemini 2.5, Qwen3-VL, InternVL-3, and GLM-4.5V, under a unified zero-shot protocol. The best model achieves only 47.88% accuracy, with systematic challenges in symbolic grounding, spatial computation, multi-constraint reasoning, and robustness to lighting and scale variations. By establishing the first rigorous ENC benchmark, we open a new research frontier at the intersection of specialized symbolic reasoning and safety-critical AI, providing essential infrastructure for advancing MLLMs toward professional maritime applications.

---

### Reconstruction-Guided Slot Curriculum: Addressing Object Over-Fragmentation in Video Object-Centric Learning

Authors: WonJun Moon, Hyun Seok Seong, Jae-Pil Heo
Published: 2026-03-24
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2603.22758v1

Video Object-Centric Learning seeks to decompose raw videos into a small set of object slots, but existing slot-attention models often suffer from severe over-fragmentation. This is because the model is implicitly encouraged to occupy all slots to minimize the reconstruction objective, thereby representing a single object with multiple redundant slots. We tackle this limitation with a reconstruction-guided slot curriculum (SlotCurri). Training starts with only a few coarse slots and progressively allocates new slots where reconstruction error remains high, thus expanding capacity only where it is needed and preventing fragmentation from the outset. Yet, during slot expansion, meaningful sub-parts can emerge only if coarse-level semantics are already well separated; however, with a small initial slot budget and an MSE objective, semantic boundaries remain blurry. Therefore, we augment MSE with a structure-aware loss that preserves local contrast and edge information to encourage each slot to sharpen its semantic boundaries. Lastly, we propose a cyclic inference that rolls slots forward and then backward through the frame sequence, producing temporally consistent object representations even in the earliest frames. All combined, SlotCurri addresses object over-fragmentation by allocating representational capacity where reconstruction fails, further enhanced by structural cues and cyclic inference. Notable FG-ARI gains of +6.8 on YouTube-VIS and +8.3 on MOVi-C validate the effectiveness of SlotCurri. Our code is available at github.com/wjun0830/SlotCurri.

---

### Multimodal Industrial Anomaly Detection via Geometric Prior

Authors: Min Li, Jinghui He, Gang Li, Jiachen Li, Jin Wan, Delong Han
Published: 2026-03-24
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.22757v1

The purpose of multimodal industrial anomaly detection is to detect complex geometric shape defects such as subtle surface deformations and irregular contours that are difficult to detect in 2D-based methods. However, current multimodal industrial anomaly detection lacks the effective use of crucial geometric information like surface normal vectors and 3D shape topology, resulting in low detection accuracy. In this paper, we propose a novel Geometric Prior-based Anomaly Detection network (GPAD). Firstly, we propose a point cloud expert model to perform fine-grained geometric feature extraction, employing differential normal vector computation to enhance the geometric details of the extracted features and generate geometric prior. Secondly, we propose a two-stage fusion strategy to efficiently leverage the complementarity of multimodal data as well as the geometric prior inherent in 3D points. We further propose attention fusion and anomaly regions segmentation based on geometric prior, which enhance the model's ability to perceive geometric defects. Extensive experiments show that our multimodal industrial anomaly detection model outperforms the State-of-the-art (SOTA) methods in detection accuracy on both MVTec-3D AD and Eyecandies datasets.

---

### MVPBench: A Multi-Video Perception Evaluation Benchmark for Multi-Modal Video Understanding

Authors: Purui Bai, Tao Wu, Jiayang Sun, Xinyue Liu, Huaibo Huang, Ran He
Published: 2026-03-24
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.22756v1

The rapid progress of Large Language Models (LLMs) has spurred growing interest in Multi-modal LLMs (MLLMs) and motivated the development of benchmarks to evaluate their perceptual and comprehension abilities. Existing benchmarks, however, are limited to static images or single videos, overlooking the complex interactions across multiple videos. To address this gap, we introduce the Multi-Video Perception Evaluation Benchmark (MVPBench), a new benchmark featuring 14 subtasks across diverse visual domains designed to evaluate models on extracting relevant information from video sequences to make informed decisions. MVPBench includes 5K question-answering tests involving 2.7K video clips sourced from existing datasets and manually annotated clips. Extensive evaluations reveal that current models struggle to process multi-video inputs effectively, underscoring substantial limitations in their multi-video comprehension. We anticipate MVPBench will drive advancements in multi-video perception.

---

### KALAVAI: Predicting When Independent Specialist Fusion Works -- A Quantitative Model for Post-Hoc Cooperative LLM Training

Authors: Ramchand Kumaresan
Published: 2026-03-24
Categories: cs.CL, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2603.22755v2

Independently trained domain specialists can be fused post-hoc into a single model that outperforms any individual specialist, and the gain is predictable: gain = 0.82 x divergence - 2.72 (R^2 = 0.856, n=6, 3-26% divergence). This enables practitioners to estimate cooperative value before committing compute. Below ~3.3% divergence, gains approach zero.In the KALAVAI protocol, contributors fine-tune copies of a shared checkpoint independently, then submit for lightweight MoE routing (500 steps). Gains are consistent: +7.72% at 410M (+/-0.02%, 3 seeds), +7.49% at 1B (+/-0.01%, 3 seeds), +6.53% at 6.9B, each over the best specialist. The router matches domain-oracle routing within <10^{-5} nats. Cross-lingual fusion (Tamil/Yoruba/Welsh/Code) achieves +21.76%, with Yoruba perplexity falling 41.9 to 7.7. A 20-contributor federation achieves +16.71% (+/-0.07pp, 3 seeds).Three requirements bound the protocol. Shared initialisation is necessary: checkpoint mismatch degrades routing. Frozen layers are optional below ~10,000 steps and beneficial beyond. Learned routing is essential: uniform averaging degrades by -1.2% vs. best specialist, while any trained router achieves oracle-optimal assignment.

---