# Research Papers — 2026-03 · bundle page 113 of 243 > Full-text markdown of papers #5601–5650 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/113 [← Previous bundle](https://aipod.dev/papers/archive/2026-03/page/112.md) [Next bundle →](https://aipod.dev/papers/archive/2026-03/page/114.md) ### ProgressiveAvatars: Progressive Animatable 3D Gaussian Avatars Authors: Kaiwen Song, Jinkai Cui, Juyong Zhang Published: 2026-03-17 Categories: cs.CV, cs.GR arXiv: https://arxiv.org/abs/2603.16447v1 In practical real-time XR and telepresence applications, network and computing resources fluctuate frequently. Therefore, a progressive 3D representation is needed. To this end, we propose ProgressiveAvatars, a progressive avatar representation built on a hierarchy of 3D Gaussians grown by adaptive implicit subdivision on a template mesh. 3D Gaussians are defined in face-local coordinates to remain animatable under varying expressions and head motion across multiple detail levels. The hierarchy expands when screen-space signals indicate a lack of detail, allocating resources to important areas. Leveraging importance ranking, ProgressiveAvatars supports incremental loading and rendering, adding new Gaussians as they arrive while preserving previous content, thus achieving smooth quality improvements across varying bandwidths. ProgressiveAvatars enables progressive delivery and progressive rendering under fluctuating network bandwidth and varying compute and memory resources. --- ### Unified Removal of Raindrops and Reflections: A New Benchmark and A Novel Pipeline Authors: Xingyu Liu, Zewei He, Yu Chen, Chunyu Zhu, Zixuan Chen, Xing Luo, Zhe-Ming Lu Published: 2026-03-17 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.16446v4 When capturing images through glass surfaces or windshields on rainy days, raindrops and reflections frequently co-occur to significantly reduce the visibility of captured images. This practical problem lacks attention and needs to be resolved urgently. Prior de-raindrop, de-reflection, and all-in-one models have failed to address this composite degradation. To this end, we first formally define the unified removal of raindrops and reflections (UR$^3$) task for the first time and construct a real-shot dataset, namely RainDrop and ReFlection (RDRF), which provides a new benchmark with substantial, high-quality, diverse image pairs. Then, we propose a novel diffusion-based framework (i.e., DiffUR$^3$) with several target designs to address this challenging task. By leveraging the powerful generative prior, DiffUR$^3$ successfully removes both types of degradations. Extensive experiments demonstrate that our method achieves state-of-the-art performance on our benchmark and on challenging in-the-wild images. --- ### Visual Distraction Undermines Moral Reasoning in Vision-Language Models Authors: Xinyi Yang, Chenheng Xu, Weijun Hong, Ce Mo, Qian Wang, Fang Fang, Yixin Zhu Published: 2026-03-17 Categories: cs.AI arXiv: https://arxiv.org/abs/2603.16445v1 Moral reasoning is fundamental to safe Artificial Intelligence (AI), yet ensuring its consistency across modalities becomes critical as AI systems evolve from text-based assistants to embodied agents. Current safety techniques demonstrate success in textual contexts, but concerns remain about generalization to visual inputs. Existing moral evaluation benchmarks rely on textonly formats and lack systematic control over variables that influence moral decision-making. Here we show that visual inputs fundamentally alter moral decision-making in state-of-the-art (SOTA) Vision-Language Models (VLMs), bypassing text-based safety mechanisms. We introduce Moral Dilemma Simulation (MDS), a multimodal benchmark grounded in Moral Foundation Theory (MFT) that enables mechanistic analysis through orthogonal manipulation of visual and contextual variables. The evaluation reveals that the vision modality activates intuition-like pathways that override the more deliberate and safer reasoning patterns observed in text-only contexts. These findings expose critical fragilities where language-tuned safety filters fail to constrain visual processing, demonstrating the urgent need for multimodal safety alignment. --- ### Fast-HaMeR: Boosting Hand Mesh Reconstruction using Knowledge Distillation Authors: Hunain Ahmed Jillani, Ahmed Tawfik Aboukhadra, Ahmed Elhayek, Jameel Malik, Nadia Robertini, Didier Stricker Published: 2026-03-17 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.16444v1 Fast and accurate 3D hand reconstruction is essential for real-time applications in VR/AR, human-computer interaction, robotics, and healthcare. Most state-of-the-art methods rely on heavy models, limiting their use on resource-constrained devices like headsets, smartphones, and embedded systems. In this paper, we investigate how the use of lightweight neural networks, combined with Knowledge Distillation, can accelerate complex 3D hand reconstruction models by making them faster and lighter, while maintaining comparable reconstruction accuracy. While our approach is suited for various hand reconstruction frameworks, we focus primarily on boosting the HaMeR model, currently the leading method in terms of reconstruction accuracy. We replace its original ViT-H backbone with lighter alternatives, including MobileNet, MobileViT, ConvNeXt, and ResNet, and evaluate three knowledge distillation strategies: output-level, feature-level, and a hybrid of both. Our experiments show that using lightweight backbones that are only 35% the size of the original achieves 1.5x faster inference speed while preserving similar performance quality with only a minimal accuracy difference of 0.4mm. More specifically, we show how output-level distillation notably improves student performance, while feature-level distillation proves more effective for higher-capacity students. Overall, the findings pave the way for efficient real-world applications on low-power devices. The code and models are publicly available under https://github.com/hunainahmedj/Fast-HaMeR. --- ### Capability-Guided Compression: Toward Interpretability-Aware Budget Allocation for Large Language Models Authors: Rishaank Gupta Published: 2026-03-17 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2603.16440v1 Large language model compression has made substantial progress through pruning, quantization, and low-rank decomposition, yet a fundamental limitation persists across all existing methods: compression budgets are allocated without any representation of what individual model components functionally encode. We term this the capability-blind compression problem and argue it is a root cause of two well-documented failures -- the insensitivity of perplexity-based evaluation to reasoning capability loss, and the abrupt phase transitions in model performance recently characterized by Ma et al. (2026). We propose Capability-Guided Compression (CGC), a framework that addresses this by using Sparse Autoencoder (SAE)-derived capability density maps to allocate differential compression budgets across transformer components. Capability density is a formally defined scalar measure combining the feature breadth, activation entropy, and cross-input consistency of a component's SAE feature activation distribution. We prove theoretically that components with higher capability density exhibit lower structural redundancy and reach their individual phase transition points at lower compression ratios, providing the first pre-compression mechanism for component-level phase transition prediction. Experiments on GPT-2 Medium confirm that capability density is statistically independent of Wanda importance scores (Spearman rho = -0.054, n = 384 heads), establishing it as a genuinely novel compression signal orthogonal to all existing importance metrics. We report a negative result on PPL-based compression comparison and provide a principled diagnosis identifying GPT-2 Medium as an insufficient test bed for the full CGC hypothesis. The theoretical framework, density formalism, and orthogonality finding constitute a foundation for capability-aware compression research. --- ### CD-FKD: Cross-Domain Feature Knowledge Distillation for Robust Single-Domain Generalization in Object Detection Authors: Junseok Lee, Sungho Shin, Seongju Lee, Kyoobin Lee Published: 2026-03-17 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2603.16439v1 Single-domain generalization is essential for object detection, particularly when training models on a single source domain and evaluating them on unseen target domains. Domain shifts, such as changes in weather, lighting, or scene conditions, pose significant challenges to the generalization ability of existing models. To address this, we propose Cross-Domain Feature Knowledge Distillation (CD-FKD), which enhances the generalization capability of the student network by leveraging both global and instance-wise feature distillation. The proposed method uses diversified data through downscaling and corruption to train the student network, whereas the teacher network receives the original source domain data. The student network mimics the features of the teacher through both global and instance-wise distillation, enabling it to extract object-centric features effectively, even for objects that are difficult to detect owing to corruption. Extensive experiments on challenging scenes demonstrate that CD-FKD outperforms state-of-the-art methods in both target domain generalization and source domain performance, validating its effectiveness in improving object detection robustness to domain shifts. This approach is valuable in real-world applications, like autonomous driving and surveillance, where robust object detection in diverse environments is crucial. --- ### DISCOVER: A Solver for Distributional Counterfactual Explanations Authors: Yikai Gu, Lele Cao, Bo Zhao, Lei Lei, Lei You Published: 2026-03-17 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.16436v2 Counterfactual explanations (CE) explain model decisions by identifying input modifications that lead to different predictions. Most existing methods operate at the instance level. Distributional Counterfactual Explanations (DCE) extend this setting by optimizing an optimal transport objective that balances proximity to a factual input distribution and alignment to a target output distribution, with statistical certification via chance constrained bounds. However, DCE relies on gradient based optimization, while many real-world tabular pipelines are dominated by non-differentiable models. We propose DISCOVER, a model-agnostic solver for distributional counterfactual explanations. DISCOVER preserves the original DCE objective and certification while replacing gradient descent with a budgeted propose-and-select search paradigm. It exploits a sample-wise decomposition of the transport objective to compute per-row impact scores and enforce a top-k intervention budget, focusing edits on the most influential samples. To guide candidate generation without predictor gradients, DISCOVER introduces an OT-guided cone sampling primitive driven by input-side transport geometry. Experiments on multiple tabular datasets demonstrate strong joint alignment of input and output distributions, extending distributional counterfactual reasoning to modern black box learning pipelines. A code repository is available at: https://github.com/VALHALLA9/Discover. --- ### VQKV: High-Fidelity and High-Ratio Cache Compression via Vector-Quantization Authors: Yixuan Wang, Qingyu Shi, Jiayu Zhou, Dianbo Liu, Ziwei He, Zhouhan Lin Published: 2026-03-17 Categories: cs.CL arXiv: https://arxiv.org/abs/2603.16435v1 The growing context length of Large Language Models (LLMs) enlarges the Key-Value (KV) cache, limiting deployment in resource-limited environments. Prior training-free approaches for KV cache compression typically rely on low-rank approximation or scalar quantization, which fail to simultaneously achieve high compression ratios and high reconstruction fidelity. We propose VQKV, a novel, training-free method introducing vector quantization (VQ) to obtain highly compressed KV representations while preserving high model fidelity, allowing for the representation of thousands of floating-point values with just a few integer indices. As a result, VQKV achieves an 82.8\% compression ratio on LLaMA3.1-8B while retaining 98.6\% of the baseline performance on LongBench and enabling 4.3x longer generation length on the same memory footprint. --- ### From Natural Language to Executable Option Strategies via Large Language Models Authors: Haochen Luo, Zhengzhao Lai, Junjie Xu, Yifan Li, Tang Pok Hin, Yuan Zhang, Chen Liu Published: 2026-03-17 Categories: cs.AI, q-fin.TR arXiv: https://arxiv.org/abs/2603.16434v1 Large Language Models (LLMs) excel at general code generation, yet translating natural-language trading intents into correct option strategies remains challenging. Real-world option design requires reasoning over massive, multi-dimensional option chain data with strict constraints, which often overwhelms direct generation methods. We introduce the Option Query Language (OQL), a domain-specific intermediate representation that abstracts option markets into high-level primitives under grammatical rules, enabling LLMs to function as reliable semantic parsers rather than free-form programmers. OQL queries are then validated and executed deterministically by an engine to instantiate executable strategies. We also present a new dataset for this task and demonstrate that our neuro-symbolic pipeline significantly improves execution accuracy and logical consistency over direct baselines. --- ### IRIS: A Real-World Benchmark for Inverse Recovery and Identification of Physical Dynamic Systems from Monocular Video Authors: Rasul Khanbayov, Mohamed Rayan Barhdadi, Erchin Serpedin, Hasan Kurban Published: 2026-03-17 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2603.16432v3 Unsupervised physical parameter estimation from video lacks a common benchmark: existing methods evaluate on non-overlapping synthetic data, the sole real-world dataset is restricted to single-body systems, and no established protocol addresses governing-equation identification. This work introduces IRIS, a high-fidelity benchmark comprising 240 real-world videos captured at 4K resolution and 60fps, spanning both single- and multi-body dynamics with independently measured ground-truth parameters and uncertainty estimates. Each dynamical system is recorded under controlled laboratory conditions and paired with its governing equations, enabling principled evaluation. A standardized evaluation protocol is defined encompassing parameter accuracy, identifiability, extrapolation, robustness, and governing-equation selection. Multiple baselines are evaluated, including a multi-step physics loss formulation and four complementary equation-identification strategies (VLM temporal reasoning, describe-then-classify prompting, CNN-based classification, and path-based labelling), establishing reference performance across all IRIS scenarios and exposing systematic failure modes that motivate future research. The dataset, annotations, evaluation toolkit, and all baseline implementations are publicly released. --- ### EngGPT2: Sovereign, Efficient and Open Intelligence Authors: G. Ciarfaglia, A. Rosanova, S. Cipolla, J. Bartoli, A. Di Domenico, C. Fioroni, A. Fontana, M. R. Scoleri, M. I. Mone, D. Franchi, M. C. Del Gaudio, A. Leodori et al. Published: 2026-03-17 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2603.16430v3 EngGPT2-16B-A3B is the latest iteration of Engineering Group's Italian LLM and it's built to be a Sovereign, Efficient and Open model. EngGPT2 is trained on 2.5 trillion tokens - less than Qwen3's 36T or Llama3's 15T - and delivers performance on key benchmarks, including MMLU-Pro, GSM8K, IFEval and HumanEval, comparable to dense models in the 8B-16B range, while requiring one-fifth to half of the inference power, and between one-tenth to one-sixth of the training data and consequent needed training power. Designed as a trained-from-scratch Mixture-of-Experts (MoE) architecture, EngGPT2 features 16 billion parameters with 3 billion active per inference, with expert sizes positioned between those used in GPT-OSS and Qwen3. Approximately 25% of its training corpus consists of Italian-language data, to deliver strong capabilities for European and Italian NLP tasks among models of similar scale. This efficiency aims to position EngGPT2 as a key contributor to the growing portfolio of open-weight European models, combining performance and efficiency with full alignment to the EU AI Act. EngGPT2 is also a single model capable of multiple reasoning modes: non-reasoning, reasoning in Italian or English, and turbo-reasoning (a concise, bullet-point style reasoning available in both languages designed for real-time reasoning use cases). EngGPT2 aims to set a new standard for resource-conscious, high-performance LLMs tailored to European and Italian contexts. --- ### LenghuSky-8: An 8-Year All-Sky Cloud Dataset with Star-Aware Masks and Alt-Az Calibration for Segmentation and Nowcasting Authors: Yicheng Rui, Xiao-Wei Duan, Licai Deng, Fan Yang, Zhengming Dang, Zhengjun Du, Junhao Peng, Wenhao Chu, Umut Mahmut, Kexin Li, Yiyun Wu, Fabo Feng Published: 2026-03-17 Categories: astro-ph.IM, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2603.16429v1 Ground-based time-domain observatories require minute-by-minute, site-scale awareness of cloud cover, yet existing all-sky datasets are short, daylight-biased, or lack astrometric calibration. We present LenghuSky-8, an eight-year (2018-2025) all-sky imaging dataset from a premier astronomical site, comprising 429,620 $512 \times 512$ frames with 81.2% night-time coverage, star-aware cloud masks, background masks, and per-pixel altitude-azimuth (Alt-Az) calibration. For robust cloud segmentation across day, night, and lunar phases, we train a linear probe on DINOv3 local features and obtain 93.3% $\pm$ 1.1% overall accuracy on a balanced, manually labeled set of 1,111 images. Using stellar astrometry, we map each pixel to local alt-az coordinates and measure calibration uncertainties of approximately 0.37 deg at zenith and approximately 1.34 deg at 30 deg altitude, sufficient for integration with telescope schedulers. Beyond segmentation, we introduce a short-horizon nowcasting benchmark over per-pixel three-class logits (sky/cloud/contamination) with four baselines: persistence (copying the last frame), optical flow, ConvLSTM, and VideoGPT. ConvLSTM performs best but yields only limited gains over persistence, underscoring the difficulty of near-term cloud evolution. We release the dataset, calibrations, and an open-source toolkit for loading, evaluation, and scheduler-ready alt-az maps to boost research in segmentation, nowcasting, and autonomous observatory operations. --- ### An Efficient Heterogeneous Co-Design for Fine-Tuning on a Single GPU Authors: Ruijia Yang, Zeyi Wen Published: 2026-03-17 Categories: cs.DC, cs.AI arXiv: https://arxiv.org/abs/2603.16428v2 Fine-tuning Large Language Models (LLMs) has become essential for domain adaptation, but its memory-intensive property exceeds the capabilities of most GPUs. To address this challenge and democratize LLM fine-tuning, we present SlideFormer, a novel system designed for single-GPU environments. Our innovations are: (1) A lightweight asynchronous engine that treats the GPU as a sliding window and overlaps GPU computation with CPU updates and multi-tier I/O. (2) A highly efficient heterogeneous memory management scheme significantly reduces peak memory usage. (3) Optimized Triton kernels to solve key bottlenecks and integrated advanced I/O. This collaborative design enables fine-tuning of the latest 123B+ models on a single RTX 4090, supporting up to 8x larger batch sizes and 6x larger models. In evaluations, SlideFormer achieves 1.40x to 6.27x higher throughput while roughly halving CPU/GPU memory usage compared to baselines, sustaining >95% peak performance on both NVIDIA and AMD GPUs.The code is available at https://github.com/RegiaYoung/SlideFormer. --- ### Cross-modal learning for plankton recognition Authors: Joona Kareinen, Veikka Immonen, Tuomas Eerola, Lumi Haraguchi, Lasse Lensu, Kaisa Kraft, Sanna Suikkanen, Heikki Kälviäinen Published: 2026-03-17 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.16427v2 This paper considers self-supervised cross-modal coordination as a strategy enabling utilization of multiple modalities and large volumes of unlabeled plankton data to build models for plankton recognition. Automated imaging instruments facilitate the continuous collection of plankton image data on a large scale. Current methods for automatic plankton image recognition rely primarily on supervised approaches, which require labeled training sets that are labor-intensive to collect. On the other hand, some modern plankton imaging instruments complement image information with optical measurement data, such as scatter and fluorescence profiles, which currently are not widely utilized in plankton recognition. In this work, we explore the possibility of using such measurement data to guide the learning process without requiring manual labeling. Inspired by the concepts behind Contrastive Language-Image Pre-training, we train encoders for both modalities using only binary supervisory information indicating whether a given image and profile originate from the same particle or from different particles. For plankton recognition, we employ a small labeled gallery of known plankton species combined with a $k$-NN classifier. This approach yields a recognition model that is inherently multimodal, i.e., capable of utilizing information extracted from both image and profile data. We demonstrate that the proposed method achieves high recognition accuracy while requiring only a minimal number of labeled images. Furthermore, we show that the approach outperforms an image-only self-supervised baseline. Code available at https://github.com/Jookare/cross-modal-plankton. --- ### 3D Fourier-based Global Feature Extraction for Hyperspectral Image Classification Authors: Muhammad Ahmad Published: 2026-03-17 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.16426v1 Hyperspectral image classification (HSIC) has been significantly advanced by deep learning methods that exploit rich spatial-spectral correlations. However, existing approaches still face fundamental limitations: transformer-based models suffer from poor scalability due to the quadratic complexity of self-attention, while recent Fourier transform-based methods typically rely on 2D spatial FFTs and largely ignore critical inter-band spectral dependencies inherent to hyperspectral data. To address these challenges, we propose Hybrid GFNet (HGFNet), a novel architecture that integrates localized 3D convolutional feature extraction with frequency-domain global filtering via GFNet-style blocks for efficient and robust spatial-spectral representation learning. HGFNet introduces three complementary frequency transforms tailored to hyperspectral imagery: Spectral Fourier Transform (a 1D FFT along the spectral axis), Spatial Fourier Transform (a 2D FFT over spatial dimensions), and Spatial-Spatial Fourier Transform (a 3D FFT jointly over spectral and spatial dimensions), enabling comprehensive and high-dimensional frequency modeling. The 3D convolutional layers capture fine-grained local spatial-spectral structures, while the Fourier-based global filtering modules efficiently model long-range dependencies and suppress noise. To further mitigate the severe class imbalance commonly observed in HSIC, HGFNet incorporates an Adaptive Focal Loss (AFL) that dynamically adjusts class-wise focusing and weighting, improving discrimination for underrepresented classes. --- ### SF-Mamba: Rethinking State Space Model for Vision Authors: Masakazu Yoshimura, Teruaki Hayashi, Yuki Hoshino, Wei-Yao Wang, Takeshi Ohashi Published: 2026-03-17 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2603.16423v1 The realm of Mamba for vision has been advanced in recent years to strike for the alternatives of Vision Transformers (ViTs) that suffer from the quadratic complexity. While the recurrent scanning mechanism of Mamba offers computational efficiency, it inherently limits non-causal interactions between image patches. Prior works have attempted to address this limitation through various multi-scan strategies; however, these approaches suffer from inefficiencies due to suboptimal scan designs and frequent data rearrangement. Moreover, Mamba exhibits relatively slow computational speed under short token lengths, commonly used in visual tasks. In pursuit of a truly efficient vision encoder, we rethink the scan operation for vision and the computational efficiency of Mamba. To this end, we propose SF-Mamba, a novel visual Mamba with two key proposals: auxiliary patch swapping for encoding bidirectional information flow under an unidirectional scan and batch folding with periodic state reset for advanced GPU parallelism. Extensive experiments on image classification, object detection, and instance and semantic segmentation consistently demonstrate that our proposed SF-Mamba significantly outperforms state-of-the-art baselines while improving throughput across different model sizes. We will release the source code after publication. --- ### HGP-Mamba: Integrating Histology and Generated Protein Features for Mamba-based Multimodal Survival Risk Prediction Authors: Jing Dai, Chen Wu, Ming Wu, Qibin Zhang, Zexi Wu, Jingdong Zhang, Hongming Xu Published: 2026-03-17 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.16421v2 Recent advances in multimodal learning have significantly improved cancer survival risk prediction. However, the joint prognostic potential of protein markers and histopathology images remains underexplored, largely due to the high cost and limited availability of protein expression profiling. To address this challenge, we propose HGP-Mamba, a Mamba-based multimodal framework that efficiently integrates histological with generated protein features for survival risk prediction. Specifically, we introduce a protein feature extractor (PFE) that leverages pretrained foundation models to derive high-throughput protein embeddings directly from Whole Slide Images (WSIs), enabling data-efficient incorporation of molecular information. Together with histology embeddings that capture morphological patterns, we further introduce the Local Interaction-aware Mamba (LiAM) for fine-grained feature interaction and the Global Interaction-enhanced Mamba (GiEM) to promote holistic modality fusion at the slide level, thus capture complex cross-modal dependencies. Experiments on four public cancer datasets demonstrate that HGP-Mamba achieves state-of-the-art performance while maintaining superior computational efficiency compared with existing methods. Our source code is publicly available at https://github.com/Daijing-ai/HGP-Mamba.git. --- ### Via Negativa for AI Alignment: Why Negative Constraints Are Structurally Superior to Positive Preferences Authors: Quan Cheng Published: 2026-03-17 Categories: cs.AI arXiv: https://arxiv.org/abs/2603.16417v1 Recent empirical results have demonstrated that training large language models (LLMs) with negative-only feedback can match or exceed standard reinforcement learning from human feedback (RLHF). Negative Sample Reinforcement achieves parity with PPO on mathematical reasoning; Distributional Dispreference Optimization trains effectively using only dispreferred samples; and Constitutional AI outperforms pure RLHF on harmlessness benchmarks. Yet no unified theoretical account explains why negative signals are so effective. This paper proposes such an account: positive preferences and negative constraints are structurally asymmetric. Positive preferences ("which is better") encode continuously coupled, context-dependent human values that cannot be exhaustively specified -- leading models to learn surface correlates such as agreement with the user (sycophancy). Negative constraints ("what is wrong") encode discrete, finite, independently verifiable prohibitions that can converge to a stable boundary. This asymmetry -- rooted in Popper's falsification logic and the epistemology of negative knowledge -- explains both the sycophancy failure of preference-based RLHF and the surprising effectiveness of negative-signal methods. We argue that alignment research should shift its center of gravity from "learning what humans prefer" to "learning what humans reject," and offer testable predictions for this framework. --- ### IndexRAG: Index-Time Reasoning for Multi-Hop Retrieval-Augmented Generation Authors: Zhenghua Bao, Yi Shi Published: 2026-03-17 Categories: cs.CL, cs.AI, cs.IR arXiv: https://arxiv.org/abs/2603.16415v2 Multi-hop question answering (QA) requires reasoning across multiple documents, yet existing retrieval-augmented generation (RAG) approaches address this either through graph-based methods requiring additional online processing or iterative multi-step reasoning. We present IndexRAG, a novel approach that shifts cross-document reasoning from online inference to offline indexing. IndexRAG identifies bridge entities shared across documents and generates bridging facts as independently retrievable units, requiring no additional training or fine-tuning. Experiments on three widely-used multi-hop QA benchmarks (HotpotQA, 2WikiMultiHopQA, MuSiQue) show that IndexRAG improves F1 over Naive RAG by 4.6 points on average, while requiring only single-pass retrieval and a single LLM call at inference time. When combined with IRCoT, IndexRAG achieves the best average performance among all evaluated methods, including graph-based baselines such as HippoRAG2 and FastGraphRAG, while relying on a flat vector index. Our code is available at https://github.com/Continuum-AI-Corp/IndexRAG . --- ### IndexRAG: Bridging Facts for Cross-Document Reasoning at Index Time Authors: Zhenghua Bao, Yi Shi Published: 2026-03-17 Categories: cs.CL, cs.AI, cs.IR arXiv: https://arxiv.org/abs/2603.16415v1 Multi-hop question answering (QA) requires reasoning across multiple documents, yet existing retrieval-augmented generation (RAG) approaches address this either through graph-based methods requiring additional online processing or iterative multi-step reasoning. We present IndexRAG, a novel approach that shifts cross-document reasoning from online inference to offline indexing. IndexRAG identifies bridge entities shared across documents and generates bridging facts as independently retrievable units, requiring no additional training or fine-tuning. Experiments on three widely-used multi-hop QA benchmarks (HotpotQA, 2WikiMultiHopQA, MuSiQue) show that IndexRAG improves F1 over Naive RAG by 4.6 points on average, while requiring only single-pass retrieval and a single LLM call at inference time. When combined with IRCoT, IndexRAG outperforms all graph-based baselines on average, including HippoRAG and FastGraphRAG, while relying solely on flat retrieval. Our code will be released upon acceptance. --- ### Trained Persistent Memory for Frozen Encoder--Decoder LLMs: Six Architectural Methods Authors: Hong Jeong Published: 2026-03-17 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2603.16413v1 Frozen encoder--decoder language models are stateless: the latent representation is discarded after every forward pass, so no information persists across sessions. This paper presents a \textbf{proof-of-concept pilot study} showing that persistent memory in the \emph{continuous latent space} of a frozen LLM is feasible -- even under severe resource constraints (a single frozen Flan-T5-XL backbone, small trainable adapters, a single dataset). We implement six architectural methods spanning three injection points and four write mechanisms; unlike text-level memory systems, every write and read is a differentiable operation on dense vectors. After training only the adapter, the memory bank continues to accumulate at inference time without gradients, enabling \emph{conversational learning}. Under a forgetting-curve evaluation on LoCoMo at two capacity scales (1$\times$ and 10$\times$), the stateless baseline scores exactly zero; at 10$\times$ all six trained adapters produce positive memory-recall curves; at 1$\times$ three methods collapse, revealing capacity as a critical design parameter. Because the memory bank is a compact numerical array, it can be scaled to arbitrarily large capacity without altering the backbone. We argue that full end-to-end training with larger models, larger data, and orders-of-magnitude larger memory will yield substantially stronger results; this pilot study establishes the feasibility baseline and design-space taxonomy that such efforts require. --- ### RECOVER: Robust Entity Correction via agentic Orchestration of hypothesis Variants for Evidence-based Recovery Authors: Abhishek Kumar, Aashraya Sachdeva Published: 2026-03-17 Categories: cs.CL, eess.AS arXiv: https://arxiv.org/abs/2603.16411v1 Entity recognition in Automatic Speech Recognition (ASR) is challenging for rare and domain-specific terms. In domains such as finance, medicine, and air traffic control, these errors are costly. If the entities are entirely absent from the ASR output, post-ASR correction becomes difficult. To address this, we introduce RECOVER, an agentic correction framework that serves as a tool-using agent. It leverages multiple hypotheses as evidence from ASR, retrieves relevant entities, and applies Large Language Model (LLM) correction under constraints. The hypotheses are used using different strategies, namely, 1-Best, Entity-Aware Select, Recognizer Output Voting Error Reduction (ROVER) Ensemble, and LLM-Select. Evaluated across five diverse datasets, it achieves 8-46% relative reductions in entity-phrase word error rate (E-WER) and increases recall by up to 22 percentage points. The LLM-Select achieves the best overall performance in entity correction while maintaining overall WER. --- ### PlotTwist: A Creative Plot Generation Framework with Small Language Models Authors: Abhinav Thorat, Ravi Kolla, Jyotin Goel, Madhav Kataria, Niranjan Pedanekar Published: 2026-03-17 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2603.16410v2 Creative plot generation presents a fundamental challenge for language models: transforming a concise premise into a coherent narrative that sustains global coherence, character development, pacing, tone consistency, and emotional progression. Although recent Large Language Models (LLMs) demonstrate strong fluency on general-purpose tasks, they require preference alignment to perform well on domain-specific tasks such as creative plot generation. However, conducting such alignment at the scale of frontier LLMs is computationally prohibitive, significantly limiting accessibility and practical deployment. To address this, we present PlotTwist, a structured framework that enables Small Language Models (SLMs) with $\leq$3B active parameters to generate high-quality, premise-conditioned plots competitive with frontier systems of vastly greater parameter scale. Our approach decomposes generation into three specialized components: (1) an Aspect Rating Reward Model, trained via a novel Positive-Negative prompting strategy; (2) a Mixture-of-Experts (MoE) plot generator aligned via Direct Preference Optimization (DPO); and (3) an Agentic Evaluation module using a cross-family jury for unbiased, independent post-hoc assessment. Extensive experiments demonstrate that PlotTwist consistently outperforms all baselines, including frontier models, across multiple Narrative Quality Dimensions (NQDs), achieving higher win rates against every baseline except the strongest, with which it remains competitive. Further validation confirms strong sensitivity to narrative quality, as the framework reliably distinguishes plots derived from critically acclaimed versus widely panned screenplays. Together, these results establish structured, preference-based alignment as a resource-efficient approach to high-quality creative plot generation. Project page: https://abhinavthorat.github.io/plottwist/ --- ### Who Benchmarks the Benchmarks? A Case Study of LLM Evaluation in Icelandic Authors: Finnur Ágúst Ingimundarson, Steinunn Rut Friðriksdóttir, Bjarki Ármannsson, Iris Edda Nowenstein, Steinþór Steingrímsson Published: 2026-03-17 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2603.16406v1 This paper evaluates current Large Language Model (LLM) benchmarking for Icelandic, identifies problems, and calls for improved evaluation methods in low/medium-resource languages in particular. We show that benchmarks that include synthetic or machine-translated data that have not been verified in any way, commonly contain severely flawed test examples that are likely to skew the results and undermine the tests' validity. We warn against the use of such methods without verification in low/medium-resource settings as the translation quality can, at best, only be as good as MT quality for a given language at any given time. Indeed, the results of our quantitative error analysis on existing benchmarks for Icelandic show clear differences between human-authored/-translated benchmarks vs. synthetic or machine-translated benchmarks. --- ### Near-light Photometric Stereo with Symmetric Lights Authors: Lilika Makabe, Heng Guo, Hiroaki Santo, Fumio Okura, Yasuyuki Matsushita Published: 2026-03-17 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.16404v1 This paper describes a linear solution method for near-light photometric stereo by exploiting symmetric light source arrangements. Unlike conventional non-convex optimization approaches, by arranging multiple sets of symmetric nearby light source pairs, our method derives a closed-form solution for surface normal and depth without requiring initialization. In addition, our method works as long as the light sources are symmetrically distributed about an arbitrary point even when the entire spatial offset is uncalibrated. Experiments showcase the accuracy of shape recovery accuracy of our method, achieving comparable results to the state-of-the-art calibrated near-light photometric stereo method while significantly reducing requirements of careful depth initialization and light calibration. --- ### Deep Reinforcement Learning-Assisted Automated Operator Portfolio for Constrained Multi-objective Optimization Authors: Shuai Shao, Ye Tian, Shangshang Yang, Xingyi Zhang Published: 2026-03-17 Categories: cs.NE arXiv: https://arxiv.org/abs/2603.16401v1 Constrained multi-objective optimization problems (CMOPs) are of great significance in the context of practical applications, ranging from scientific to engineering domains. Most existing constrained multi-objective evolutionary algorithms (CMOEAs) usually employ fixed operators all the time, which exhibit poor versatility in handling various CMOPs. Therefore, some recent studies have focused on adaptively selecting the best operators for the current population states during the search process. The evolutionary algorithms proposed in these studies learn the value of each operator and recommend the operator with the highest value for the current population, resulting in only a single operator being recommended at each generation, which can potentially lead to local optima and inefficient utilization of function evaluations. To address the dilemma in operator adaptation, this paper proposes a reinforcement learning-based automated operator portfolio approach to learn an allocation scheme of operators at each generation. This approach considers the optimization-related and constraint-related features of the current population as states, the overall improvement in population convergence and diversity as rewards, and different operator portfolios as actions. By utilizing deep neural networks to establish a mapping model between the population states and the expected cumulative rewards, the proposed approach determines the optimal operator portfolio during the evolutionary process. By embedding the proposed approach into existing CMOEAs, a deep reinforcement learning-assisted automated operator portfolio based evolutionary algorithm for solving CMOPs, abbreviated as CMOEA-AOP, is developed. Empirical studies on 33 benchmark problems demonstrate that the proposed algorithm significantly enhances the performance of CMOEAs and exhibits more stable performance across different CMOPs. --- ### Fanar 2.0: Arabic Generative AI Stack Authors: FANAR TEAM, Ummar Abbas, Mohammad Shahmeer Ahmad, Minhaj Ahmad, Abdulaziz Al-Homaid, Anas Al-Nuaimi, Enes Altinisik, Ehsaneddin Asgari, Sanjay Chawla, Shammur Chowdhury, Fahim Dalvi, Kareem Darwish et al. Published: 2026-03-17 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2603.16397v1 We present Fanar 2.0, the second generation of Qatar's Arabic-centric Generative AI platform. Sovereignty is a first-class design principle: every component, from data pipelines to deployment infrastructure, was designed and operated entirely at QCRI, Hamad Bin Khalifa University. Fanar 2.0 is a story of resource-constrained excellence: the effort ran on 256 NVIDIA H100 GPUs, with Arabic having only ~0.5% of web data despite 400 million native speakers. Fanar 2.0 adopts a disciplined strategy of data quality over quantity, targeted continual pre-training, and model merging to achieve substantial gains within these constraints. At the core is Fanar-27B, continually pre-trained from a Gemma-3-27B backbone on a curated corpus of 120 billion high-quality tokens across three data recipes. Despite using 8x fewer pre-training tokens than Fanar 1.0, it delivers substantial benchmark improvements: Arabic knowledge (+9.1 pts), language (+7.3 pts), dialects (+3.5 pts), and English capability (+7.6 pts). Beyond the core LLM, Fanar 2.0 introduces a rich stack of new capabilities. FanarGuard is a state-of-the-art 4B bilingual moderation filter for Arabic safety and cultural alignment. The speech family Aura gains a long-form ASR model for hours-long audio. Oryx vision family adds Arabic-aware image and video understanding alongside culturally grounded image generation. An agentic tool-calling framework enables multi-step workflows. Fanar-Sadiq utilizes a multi-agent architecture for Islamic content. Fanar-Diwan provides classical Arabic poetry generation. FanarShaheen delivers LLM-powered bilingual translation. A redesigned multi-layer orchestrator coordinates all components through intent-aware routing and defense-in-depth safety validation. Taken together, Fanar 2.0 demonstrates that sovereign, resource-constrained AI development can produce systems competitive with those built at far greater scale. --- ### Robust Physics-Guided Diffusion for Full-Waveform Inversion Authors: Jishen Peng, Enze Jiang, Zheng Ma, Xiongbin Yan Published: 2026-03-17 Categories: math.NA, cs.AI arXiv: https://arxiv.org/abs/2603.16393v1 We develop a robust physics-guided diffusion framework for full-waveform inversion that combines a score-based generative prior with likelihood guidance computed through wave-equation simulations. We adopt a transport-based data-consistency potential (Wasserstein-2), incorporating wavefield enhancement via bounded weighting and observation-dependent normalization, thereby improving robustness to amplitude imbalance and time/phase misalignment. On the inference side, we introduce a preconditioned guided reverse-diffusion scheme that adapts the guidance strength and spatial scaling throughout the reverse-time dynamics, yielding a more stable and effective data-consistency guidance step than standard diffusion posterior sampling (DPS). Numerical experiments on OpenFWI datasets demonstrate improved reconstruction quality over deterministic optimization baselines and standard DPS under comparable computational budgets. --- ### DermaFlux: Synthetic Skin Lesion Generation with Rectified Flows for Enhanced Image Classification Authors: Stathis Galanakis, Alexandros Koliousis, Stefanos Zafeiriou Published: 2026-03-17 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.16392v1 Despite recent advances in deep generative modeling, skin lesion classification systems remain constrained by the limited availability of large, diverse, and well-annotated clinical datasets, resulting in class imbalance between benign and malignant lesions and consequently reduced generalization performance. We introduce DermaFlux, a rectified flow-based text-to-image generative framework that synthesizes clinically grounded skin lesion images from natural language descriptions of dermatological attributes. Built upon Flux.1, DermaFlux is fine-tuned using parameter-efficient Low-Rank Adaptation (LoRA) on a large curated collection of publicly available clinical image datasets. We construct image-text pairs using synthetic textual captions generated by Llama 3.2, following established dermatological criteria including lesion asymmetry, border irregularity, and color variation. Extensive experiments demonstrate that DermaFlux generates diverse and clinically meaningful dermatology images that improve binary classification performance by up to 6% when augmenting small real-world datasets, and by up to 9% when classifiers are trained on DermaFlux-generated synthetic images rather than diffusion-based synthetic images. Our ImageNet-pretrained ViT fine-tuned with only 2,500 real images and 4,375 DermaFlux-generated samples achieves 78.04% binary classification accuracy and an AUC of 0.859, surpassing the next best dermatology model by 8%. --- ### Unpaired Cross-Domain Calibration of DMSP to VIIRS Nighttime Light Data Based on CUT Network Authors: Zhan Tong, ChenXu Zhou, Fei Tang, Yiming Tu, Tianyu Qin, Kaihao Fang Published: 2026-03-17 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.16385v1 Defense Meteorological Satellite Program (DMSP-OLS) and Suomi National Polar-orbiting Partnership (SNPP-VIIRS) nighttime light (NTL) data are vital for monitoring urbanization, yet sensor incompatibilities hinder long-term analysis. This study proposes a cross-sensor calibration method using Contrastive Unpaired Translation (CUT) network to transform DMSP data into VIIRS-like format, correcting DMSP defects. The method employs multilayer patch-wise contrastive learning to maximize mutual information between corresponding patches, preserving content consistency while learning cross-domain similarity. Utilizing 2012-2013 overlapping data for training, the network processes 1992-2013 DMSP imagery to generate enhanced VIIRS-style raster data. Validation results demonstrate that generated VIIRS-like data exhibits high consistency with actual VIIRS observations (R-squared greater than 0.87) and socioeconomic indicators. This approach effectively resolves cross-sensor data fusion issues and calibrates DMSP defects, providing reliable attempt for extended NTL time-series. --- ### Controlling Fish Schools via Reinforcement Learning of Virtual Fish Movement Authors: Yusuke Nishii, Hiroaki Kawashima Published: 2026-03-17 Categories: cs.RO, cs.LG, q-bio.PE arXiv: https://arxiv.org/abs/2603.16384v1 This study investigates a method to guide and control fish schools using virtual fish trained with reinforcement learning. We utilize 2D virtual fish displayed on a screen to overcome technical challenges such as durability and movement constraints inherent in physical robotic agents. To address the lack of detailed behavioral models for real fish, we adopt a model-free reinforcement learning approach. First, simulation results show that reinforcement learning can acquire effective movement policies even when simulated real fish frequently ignore the virtual stimulus. Second, real-world experiments with live fish confirm that the learned policy successfully guides fish schools toward specified target directions. Statistical analysis reveals that the proposed method significantly outperforms baseline conditions, including the absence of stimulus and a heuristic "stay-at-edge" strategy. This study provides an early demonstration of how reinforcement learning can be used to influence collective animal behavior through artificial agents. --- ### Age Predictors Through the Lens of Generalization, Bias Mitigation, and Interpretability: Reflections on Causal Implications Authors: Debdas Paul, Elisa Ferrari, Irene Gravili, Alessandro Cellerino Published: 2026-03-17 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2603.16377v1 Chronological age predictors often fail to achieve out-of-distribution (OOD) gen- eralization due to exogenous attributes such as race, gender, or tissue. Learning an invariant representation with respect to those attributes is therefore essential to improve OOD generalization and prevent overly optimistic results. In predic- tive settings, these attributes motivate bias mitigation; in causal analyses, they appear as confounders; and when protected, their suppression leads to fairness. We coherently explore these concepts with theoretical rigor and discuss the scope of an interpretable neural network model based on adversarial representation learning. Using publicly available mouse transcriptomic datasets, we illustrate the behavior of this model relative to conventional machine learning models. We observe that the outcome of this model is consistent with the predictive results of a published study demonstrating the effects of Elamipretide on mouse skeletal and cardiac muscle. We conclude by discussing the limitations of deriving causal interpretation from such purely predictive models. --- ### Prior-Informed Neural Network Initialization: A Spectral Approach for Function Parameterizing Architectures Authors: David Orlando Salazar Torres, Diyar Altinses, Andreas Schwung Published: 2026-03-17 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.16376v1 Neural network architectures designed for function parameterization, such as the Bag-of-Functions (BoF) framework, bridge the gap between the expressivity of deep learning and the interpretability of classical signal processing. However, these models are inherently sensitive to parameter initialization, as traditional data-agnostic schemes fail to capture the structural properties of the target signals, often leading to suboptimal convergence. In this work, we propose a prior-informed design strategy that leverages the intrinsic spectral and temporal structure of the data to guide both network initialization and architectural configuration. A principled methodology is introduced that uses the Fast Fourier Transform to extract dominant seasonal priors, informing model depth and initial states, and a residual-based regression approach to parameterize trend components. Crucially, this structural alignment enables a substantial reduction in encoder dimensionality without compromising reconstruction fidelity. A supporting theoretical analysis provides guidance on trend estimation under finite-sample regimes. Extensive experiments on synthetic and real-world benchmarks demonstrate that embedding data-driven priors significantly accelerates convergence, reduces performance variability across trials, and improves computational efficiency. Overall, the proposed framework enables more compact and interpretable architectures while outperforming standard initialization baselines, without altering the core training procedure. --- ### Semantic One-Dimensional Tokenizer for Image Reconstruction and Generation Authors: Yunpeng Qu, Kaidong Zhang, Yukang Ding, Ying Chen, Jian Wang Published: 2026-03-17 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.16373v1 Visual generative models based on latent space have achieved great success, underscoring the significance of visual tokenization. Mapping images to latents boosts efficiency and enables multimodal alignment for scaling up in downstream tasks. Existing visual tokenizers primarily map images into fixed 2D spatial grids and focus on pixel-level restoration, which hinders the capture of representations with compact global semantics. To address these issues, we propose \textbf{SemTok}, a semantic one-dimensional tokenizer that compresses 2D images into 1D discrete tokens with high-level semantics. SemTok sets a new state-of-the-art in image reconstruction, achieving superior fidelity with a remarkably compact token representation. This is achieved via a synergistic framework with three key innovations: a 2D-to-1D tokenization scheme, a semantic alignment constraint, and a two-stage generative training strategy. Building on SemTok, we construct a masked autoregressive generation framework, which yields notable improvements in downstream image generation tasks. Experiments confirm the effectiveness of our semantic 1D tokenization. Our code will be open-sourced. --- ### InViC: Intent-aware Visual Cues for Medical Visual Question Answering Authors: Zhisong Wang, Ziyang Chen, Zanting Ye, Hongze Zhu, Yefeng Zheng, Yong Xia Published: 2026-03-17 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.16372v1 Medical visual question answering (Med-VQA) aims to answer clinically relevant questions grounded in medical images. However, existing multimodal large language models (MLLMs) often exhibit shortcut answering, producing plausible responses by exploiting language priors or dataset biases while insufficiently attending to visual evidence. This behavior undermines clinical reliability, especially when subtle imaging findings are decisive. We propose a lightweight plug-in framework, termed Intent-aware Visual Cues (InViC), to explicitly enhance image-based answer generation in medical VQA. InViC introduces a Cue Tokens Extraction (CTE) module that distills dense visual tokens into a compact set of K question-conditioned cue tokens, which serve as structured visual intermediaries injected into the LLM decoder to promote intent-aligned visual evidence. To discourage bypassing of visual information, we further design a two-stage fine-tuning strategy with a cue-bottleneck attention mask. In Stage I, we employ an attention mask to block the LLM's direct view of raw visual features, thereby funneling all visual evidence through the cue pathway. In Stage II, standard causal attention is restored to train the LLM to jointly exploit the visual and cue tokens. We evaluate InViC on three public Med-VQA benchmarks (VQA-RAD, SLAKE, and ImageCLEF VQA-Med 2019) across multiple representative MLLMs. InViC consistently improves over zero-shot inference and standard LoRA fine-tuning, demonstrating that intent-aware visual cues with bottlenecked training is a practical and effective strategy for improving trustworthy Med-VQA. --- ### FederatedFactory: Generative One-Shot Learning for Extremely Non-IID Distributed Scenarios Authors: Andrea Moleri, Christian Internò, Ali Raza, Markus Olhofer, David Klindt, Fabio Stella, Barbara Hammer Published: 2026-03-17 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2603.16370v1 Federated Learning (FL) enables distributed optimization without compromising data sovereignty. Yet, where local label distributions are mutually exclusive, standard weight aggregation fails due to conflicting optimization trajectories. Often, FL methods rely on pretrained foundation models, introducing unrealistic assumptions. We introduce FederatedFactory, a zero-dependency framework that inverts the unit of federation from discriminative parameters to generative priors. By exchanging generative modules in a single communication round, our architecture supports ex nihilo synthesis of universally class balanced datasets, eliminating gradient conflict and external prior bias entirely. Evaluations across diverse medical imagery benchmarks, including MedMNIST and ISIC2019, demonstrate that our approach recovers centralized upper-bound performance. Under pathological heterogeneity, it lifts baseline accuracy from a collapsed 11.36% to 90.57% on CIFAR-10 and restores ISIC2019 AUROC to 90.57%. Additionally, this framework facilitates exact modular unlearning through the deterministic deletion of specific generative modules. --- ### Encoding Predictability and Legibility for Style-Conditioned Diffusion Policy Authors: Adrien Jacquet Crétides, Mouad Abrini, Hamed Rahimi, Mohamed Chetouani Published: 2026-03-17 Categories: cs.RO, cs.LG arXiv: https://arxiv.org/abs/2603.16368v2 Striking a balance between efficiency and transparent motion is a core challenge in human-robot collaboration, as highly expressive movements often incur unnecessary time and energy costs. In collaborative environments, legibility allows a human observer a better understanding of the robot's actions, increasing safety and trust. However, these behaviors result in sub-optimal and exaggerated trajectories that are redundant in low-ambiguity scenarios where the robot's goal is already obvious. To address this trade-off, we propose Style-Conditioned Diffusion Policy (SCDP), a modular framework that constrains the trajectory generation of a pre-trained diffusion model toward either legibility or efficiency based on the environment's configuration. Our method utilizes a post-training pipeline that freezes the base policy and trains a lightweight scene encoder and conditioning predictor to modulate the diffusion process. At inference time, an ambiguity detection module activates the appropriate conditioning, prioritizing expressive motion only for ambiguous goals and reverting to efficient paths otherwise. We evaluate SCDP on manipulation and navigation tasks, and results show that it enhances legibility in ambiguous settings while preserving optimal efficiency when legibility is unnecessary, all without retraining the base policy. --- ### DynamicGate MLP Conditional Computation via Learned Structural Dropout and Input Dependent Gating for Functional Plasticity Authors: Yong Il Choi Published: 2026-03-17 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2603.16367v1 Dropout is a representative regularization technique that stochastically deactivates hidden units during training to mitigate overfitting. In contrast, standard inference executes the full network with dense computation, so its goal and mechanism differ from conditional computation, where the executed operations depend on the input. This paper organizes DynamicGate-MLP into a single framework that simultaneously satisfies both the regularization view and the conditional-computation view. Instead of a random mask, the proposed model learns gates that decide whether to use each unit (or block), suppressing unnecessary computation while implementing sample-dependent execution that concentrates computation on the parts needed for each input. To this end, we define continuous gate probabilities and, at inference time, generate a discrete execution mask from them to select an execution path. Training controls the compute budget via a penalty on expected gate usage and uses a Straight-Through Estimator (STE) to optimize the discrete mask. We evaluate DynamicGate-MLP on MNIST, CIFAR-10, Tiny-ImageNet, Speech Commands, and PBMC3k, and compare it with various MLP baselines and MoE-style variants. Compute efficiency is compared under a consistent criterion using gate activation ratios and a layerweighted relative MAC metric, rather than wall-clock latency that depends on hardware and backend kernels. --- ### FactorEngine: A Program-level Knowledge-Infused Factor Mining Framework for Quantitative Investment Authors: Qinhong Lin, Ruitao Feng, Yinglun Feng, Zhenxin Huang, Yukun Chen, Zhongliang Yang, Linna Zhou, Binjie Fei, Jiaqi Liu, Yu Li Published: 2026-03-17 Categories: cs.AI arXiv: https://arxiv.org/abs/2603.16365v3 We study alpha factor mining, the automated discovery of predictive signals from noisy, non-stationary market data-under a practical requirement that mined factors be directly executable and auditable, and that the discovery process remain computationally tractable at scale. Existing symbolic approaches are limited by bounded expressiveness, while neural forecasters often trade interpretability for performance and remain vulnerable to regime shifts and overfitting. We introduce FactorEngine (FE), a program-level factor discovery framework that casts factors as Turing-complete code and improves both effectiveness and efficiency via three separations: (i) logic revision vs. parameter optimization, (ii) LLM-guided directional search vs. Bayesian hyperparameter search, and (iii) LLM usage vs. local computation. FE further incorporates a knowledge-infused bootstrapping module that transforms unstructured financial reports into executable factor programs through a closed-loop multi-agent extraction-verification-code-generation pipeline, and an experience knowledge base that supports trajectory-aware refinement (including learning from failures). Across extensive backtests on real-world OHLCV data, FE produces factors with substantially stronger predictive stability and portfolio impact-for example, higher IC/ICIR (and Rank IC/ICIR) and improved AR/Sharpe, than baseline methods, achieving state-of-the-art predictive and portfolio performance. --- ### FactorEngine: A Program-level Knowledge-Infused Factor Mining Framework for Quantitative Investment Authors: Qinhong Lin, Ruitao Feng, Yinglun Feng, Zhenxin Huang, Yukun Chen, Zhongliang Yang, Linna Zhou, Binjie Fei, Jiaqi Liu, Yu Li Published: 2026-03-17 Categories: cs.AI arXiv: https://arxiv.org/abs/2603.16365v2 We study alpha factor mining, the automated discovery of predictive signals from noisy, non-stationary market data-under a practical requirement that mined factors be directly executable and auditable, and that the discovery process remain computationally tractable at scale. Existing symbolic approaches are limited by bounded expressiveness, while neural forecasters often trade interpretability for performance and remain vulnerable to regime shifts and overfitting. We introduce FactorEngine (FE), a program-level factor discovery framework that casts factors as Turing-complete code and improves both effectiveness and efficiency via three separations: (i) logic revision vs. parameter optimization, (ii) LLM-guided directional search vs. Bayesian hyperparameter search, and (iii) LLM usage vs. local computation. FE further incorporates a knowledge-infused bootstrapping module that transforms unstructured financial reports into executable factor programs through a closed-loop multi-agent extraction-verification-code-generation pipeline, and an experience knowledge base that supports trajectory-aware refinement (including learning from failures). Across extensive backtests on real-world OHLCV data, FE produces factors with substantially stronger predictive stability and portfolio impact-for example, higher IC/ICIR (and Rank IC/ICIR) and improved AR/Sharpe, than baseline methods, achieving state-of-the-art predictive and portfolio performance. --- ### Advancing Visual Reliability: Color-Accurate Underwater Image Enhancement for Real-Time Underwater Missions Authors: Yiqiang Zhou, Yifan Chen, Zhe Sun, Jijun Lu, Ye Zheng, Xuelong Li Published: 2026-03-17 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.16363v1 Underwater image enhancement plays a crucial role in providing reliable visual information for underwater platforms, since strong absorption and scattering in water-related environments generally lead to image quality degradation. Existing high-performance methods often rely on complex architectures, which hinder deployment on underwater devices. Lightweight methods often sacrifice quality for speed and struggle to handle severely degraded underwater images. To address this limitation, we present a real-time underwater image enhancement framework with accurate color restoration. First, an Adaptive Weighted Channel Compensation module is introduced to achieve dynamic color recovery of the red and blue channels using the green channel as a reference anchor. Second, we design a Multi-branch Re-parameterized Dilated Convolution that employs multi-branch fusion during training and structural re-parameterization during inference, enabling large receptive field representation with low computational overhead. Finally, a Statistical Global Color Adjustment module is employed to optimize overall color performance based on statistical priors. Extensive experiments on eight datasets demonstrate that the proposed method achieves state-of-the-art performance across seven evaluation metrics. The model contains only 3,880 inference parameters and achieves an inference speed of 409 FPS. Our method improves the UCIQE score by 29.7% under diverse environmental conditions, and the deployment on ROV platforms and performance gains in downstream tasks further validate its superiority for real-time underwater missions. --- ### $D^3$-RSMDE: 40$\times$ Faster and High-Fidelity Remote Sensing Monocular Depth Estimation Authors: Ruizhi Wang, Weihan Li, Zunlei Feng, Haofei Zhang, Mingli Song, Jiayu Wang, Jie Song, Li Sun Published: 2026-03-17 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2603.16362v1 Real-time, high-fidelity monocular depth estimation from remote sensing imagery is crucial for numerous applications, yet existing methods face a stark trade-off between accuracy and efficiency. Although using Vision Transformer (ViT) backbones for dense prediction is fast, they often exhibit poor perceptual quality. Conversely, diffusion models offer high fidelity but at a prohibitive computational cost. To overcome these limitations, we propose Depth Detail Diffusion for Remote Sensing Monocular Depth Estimation ($D^3$-RSMDE), an efficient framework designed to achieve an optimal balance between speed and quality. Our framework first leverages a ViT-based module to rapidly generate a high-quality preliminary depth map construction, which serves as a structural prior, effectively replacing the time-consuming initial structure generation stage of diffusion models. Based on this prior, we propose a Progressive Linear Blending Refinement (PLBR) strategy, which uses a lightweight U-Net to refine the details in only a few iterations. The entire refinement step operates efficiently in a compact latent space supported by a Variational Autoencoder (VAE). Extensive experiments demonstrate that $D^3$-RSMDE achieves a notable 11.85% reduction in the Learned Perceptual Image Patch Similarity (LPIPS) perceptual metric over leading models like Marigold, while also achieving over a 40x speedup in inference and maintaining VRAM usage comparable to lightweight ViT models. --- ### Toward Experimentation-as-a-Service in 5G/6G: The Plaza6G Prototype for AI-Assisted Trials Authors: Sergio Barrachina-Muñoz, Marc Carrascosa-Zamacois, Horacio Bleda, Umair Riaz, Yasir Maqsood, Xavier Calle, Selva Vía, Miquel Payaró, Josep Mangues-Bafalluy Published: 2026-03-17 Categories: cs.NI, cs.AI arXiv: https://arxiv.org/abs/2603.16356v1 This paper presents Plaza6G, the first operational Experiment-as-a-Service (ExaS) platform unifying cloud resources with next-generation wireless infrastructure. Developed at CTTC in Barcelona, Plaza6G integrates GPU-accelerated compute clusters, multiple 5G cores, both open-source (e.g., Free5GC) and commercial (e.g., Cumucore), programmable RANs, and physical or emulated user equipment under unified orchestration. In Plaza6G, the experiment design requires minimal expertise as it is expressed in natural language via a web portal or a REST API. The web portal and REST API are enhanced with a Large Language Model (LLM)-based assistant, which employs retrieval-augmented generation (RAG) for up-to-date experiment knowledge and Low-Rank Adaptation (LoRA) for continuous domain fine-tuning. Over-the-air (OTA) trials leverage a four-chamber anechoic facility and a dual-site outdoor 5G network operating in sub-6~GHz and mmWave bands. Demonstrations include automated CI/CD integration with sub-ten-minute setup and interactive OTA testing under programmable propagation conditions. Machine-readable experiment descriptors ensure reproducibility, while future work targets policy-aware orchestration, safety validation, and federated testbed integration toward open, reproducible wireless experimentation. --- ### PashtoCorp: A 1.25-Billion-Word Corpus, Evaluation Suite, and Reproducible Pipeline for Low-Resource Language Development Authors: Hanif Rahman Published: 2026-03-17 Categories: cs.CL, cs.IR, cs.LG arXiv: https://arxiv.org/abs/2603.16354v1 We present PashtoCorp, a 1.25-billion-word corpus for Pashto, a language spoken by 60 million people that remains severely underrepresented in NLP. The corpus is assembled from 39 sources spanning seven HuggingFace datasets and 32 purpose-built web scrapers, processed through a reproducible pipeline with Arabic-script tokenization, SHA-256 deduplication, and quality filtering. At 1.25B words across 2.81 million documents, PashtoCorp is 40x larger than the OSCAR Pashto subset and 83x larger than the previously largest dedicated Pashto corpus. Continued MLM pretraining of XLM-R-base on PashtoCorp reduces held-out perplexity by 25.1% (8.08->6.06). On WikiANN Pashto NER, the pretrained model improves entity F1 by 10% relative (19.0%->21.0%) and reduces training variance nearly 7x; the largest gain appears at 50 training sentences (+27%), with PashtoCorp covering 97.9% of WikiANN entity vocabulary. On Belebele Pashto reading comprehension, Gemma-3n achieves 64.6% accuracy, the first published LLM baseline for Pashto on this benchmark. A leave-one-out source ablation shows that Wikipedia (0.7% of documents) is the most critical source for NER: removing it alone reduces entity F1 by 47%. Corpus data, trained model, and code are available at https://huggingface.co/datasets/ihanif/pashto-corpus, https://huggingface.co/ihanif/xlmr-pashto, and https://github.com/ihanif/pashto-corpus. --- ### Automated identification of Ichneumonoidea wasps via YOLO-based deep learning: Integrating HiresCam for Explainable AI Authors: Joao Manoel Herrera Pinheiro, Gabriela Do Nascimento Herrera, Alvaro Doria Dos Santos, Luciana Bueno Dos Reis Fernandes, Ricardo V. Godoy, Eduardo A. B. Almeida, Helena Carolina Onody, Marcelo Andrade Da Costa Vieira, Angelica Maria Penteado-Dias, Marcelo Becker Published: 2026-03-17 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2603.16351v2 Accurate taxonomic identification of parasitoid wasps within the superfamily Ichneumonoidea is essential for biodiversity assessment, ecological monitoring, and biological control programs. However, morphological similarity, small body size, and fine-grained interspecific variation make manual identification labor-intensive and expertise-dependent. This study proposes a deep learning-based framework for the automated identification of Ichneumonoidea wasps using a YOLO-based architecture integrated with High-Resolution Class Activation Mapping (HiResCAM) to enhance interpretability. The proposed system simultaneously identifies wasp families from high-resolution images. The dataset comprises 3556 high-resolution images of Hymenoptera specimens. The taxonomic distribution is primarily concentrated among the families Ichneumonidae (n = 786), Braconidae (n = 648), Apidae (n = 466), and Vespidae (n = 460). Extensive experiments were conducted using a curated dataset, with model performance evaluated through precision, recall, F1 score, and accuracy. The results demonstrate high accuracy of over 96 % and robust generalization across morphological variations. HiResCAM visualizations confirm that the model focuses on taxonomically relevant anatomical regions, such as wing venation, antennae segmentation, and metasomal structures, thereby validating the biological plausibility of the learned features. The integration of explainable AI techniques improves transparency and trustworthiness, making the system suitable for entomological research to accelerate biodiversity characterization in an under-described parasitoid superfamily. --- ### Explainable machine learning workflows for radio astronomical data processing Authors: S. Yatawatta, A. Ahmadi, B. Asabere, M. Iacobelli, N. Peters, M. Veldhuis Published: 2026-03-17 Categories: astro-ph.IM, cs.AI arXiv: https://arxiv.org/abs/2603.16350v1 Radio astronomy relies heavily on efficient and accurate processing pipelines to deliver science ready data. With the increasing data flow of modern radio telescopes, manual configuration of such data processing pipelines is infeasible. Machine learning (ML) is already emerging as a viable solution for automating data processing pipelines. However, almost all existing ML enabled pipelines are of black-box type, where the decisions made by the automating agents are not easily deciphered by astronomers. In order to improve the explainability of the ML aided data processing pipelines in radio astronomy, we propose the joint use of fuzzy rule based inference and deep learning. We consider one application in radio astronomy, i.e., calibration, to showcase the proposed approach of ML aided decision making using a Takagi-Sugeno-Kang (TSK) fuzzy system. We provide results based on simulations to illustrate the increased explainability of the proposed approach, not compromising on the quality or accuracy. --- ### Learning Human-Object Interaction for 3D Human Pose Estimation from LiDAR Point Clouds Authors: Daniel Sungho Jung, Dohee Cho, Kyoung Mu Lee Published: 2026-03-17 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.16343v1 Understanding humans from LiDAR point clouds is one of the most critical tasks in autonomous driving due to its close relationships with pedestrian safety, yet it remains challenging in the presence of diverse human-object interactions and cluttered backgrounds. Nevertheless, existing methods largely overlook the potential of leveraging human-object interactions to build robust 3D human pose estimation frameworks. There are two major challenges that motivate the incorporation of human-object interaction. First, human-object interactions introduce spatial ambiguity between human and object points, which often leads to erroneous 3D human keypoint predictions in interaction regions. Second, there exists severe class imbalance in the number of points between interacting and non-interacting body parts, with the interaction-frequent regions such as hand and foot being sparsely observed in LiDAR data. To address these challenges, we propose a Human-Object Interaction Learning (HOIL) framework for robust 3D human pose estimation from LiDAR point clouds. To mitigate the spatial ambiguity issue, we present human-object interaction-aware contrastive learning (HOICL) that effectively enhances feature discrimination between human and object points, particularly in interaction regions. To alleviate the class imbalance issue, we introduce contact-aware part-guided pooling (CPPool) that adaptively reallocates representational capacity by compressing overrepresented points while preserving informative points from interacting body parts. In addition, we present an optional contact-based temporal refinement that refines erroneous per-frame keypoint estimates using contact cues over time. As a result, our HOIL effectively leverages human-object interaction to resolve spatial ambiguity and class imbalance in interaction regions. Codes will be released. --- ### Deep learning based intelligent IDS for Large-scale IoT networks Authors: Isha Andrade, Shalaka S Mahadik, Mithun Mukherjee, Pranav M Pawar, Raja Muthalagu Published: 2026-03-17 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2603.16342v2 The proliferation of large-scale IoT networks has been both a blessing and a curse. Not only has it revolutionized the way organizations operate by increasing the efficiency of automated procedures, but it has also simplified our daily lives. However, while IoT networks have improved convenience and connectivity, they have also increased security risk due to unauthorized devices gaining access to these networks and exploiting existing weaknesses with specific attack types. The research proposes two lightweight deep learning (DL)-based intelligent intrusion detection systems (IDS). to enhance the security of IoT networks: the proposed convolutional neural network (CNN)-based IDS and the proposed long short-term memory (LSTM)-based IDS. The research evaluated the performance of both intelligent IDSs based on DL using the CICIoT2023 dataset. DL-based intelligent IDSs successfully identify and classify various cyber threats using binary, grouped, and multi-class classification. The proposed CNN-based IDS achieves an accuracy of 99.34%, 99.02% and 98.6%, while the proposed LSTM-based IDS achieves an accuracy of 99.42%, 99.13%, and 98.68% for binary, grouped, and multi-class classification, respectively. --- ### PKINet-v2: Towards Powerful and Efficient Poly-Kernel Remote Sensing Object Detection Authors: Xinhao Cai, Liulei Li, Gensheng Pei, Zeren Sun, Yazhou Yao, Wenguan Wang Published: 2026-03-17 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.16341v1 Object detection in remote sensing images (RSIs) is challenged by the coexistence of geometric and spatial complexity: targets may appear with diverse aspect ratios, while spanning a wide range of object sizes under varied contexts. Existing RSI backbones address the two challenges separately, either by adopting anisotropic strip kernels to model slender targets or by using isotropic large kernels to capture broader context. However, such isolated treatments lead to complementary drawbacks: the strip-only design can disrupt spatial coherence for regular-shaped objects and weaken tiny details, whereas isotropic large kernels often introduce severe background noise and geometric mismatch for slender structures. In this paper, we extend PKINet, and present a powerful and efficient backbone that jointly handles both challenges within a unified paradigm named Poly Kernel Inception Network v2 (PKINet-v2). PKINet-v2 synergizes anisotropic axial-strip convolutions with isotropic square kernels and builds a multi-scope receptive field, preserving fine-grained local textures while progressively aggregating long-range context across scales. To enable efficient deployment, we further introduce a Heterogeneous Kernel Re-parameterization (HKR) Strategy that fuses all heterogeneous branches into a single depth-wise convolution for inference, eliminating fragmented kernel launches without accuracy loss. Extensive experiments on four widely-used benchmarks, including DOTA-v1.0, DOTA-v1.5, HRSC2016, and DIOR-R, demonstrate that PKINet-v2 achieves state-of-the-art accuracy while delivering a $\textbf{3.9}\times$ FPS acceleration compared to PKINet-v1, surpassing previous remote sensing backbones in both effectiveness and efficiency. --- ### Iris: Bringing Real-World Priors into Diffusion Model for Monocular Depth Estimation Authors: Xinhao Cai, Gensheng Pei, Zeren Sun, Yazhou Yao, Fumin Shen, Wenguan Wang Published: 2026-03-17 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.16340v2 In this paper, we propose \textbf{Iris}, a deterministic framework for Monocular Depth Estimation (MDE) that integrates real-world priors into the diffusion model. Conventional feed-forward methods rely on massive training data, yet still miss details. Previous diffusion-based methods leverage rich generative priors yet struggle with synthetic-to-real domain transfer. Iris, in contrast, preserves fine details, generalizes strongly from synthetic to real scenes, and remains efficient with limited training data. To this end, we introduce a two-stage Priors-to-Geometry Deterministic (PGD) schedule: the prior stage uses Spectral-Gated Distillation (SGD) to transfer low-frequency real priors while leaving high-frequency details unconstrained, and the geometry stage applies Spectral-Gated Consistency (SGC) to enforce high-frequency fidelity while refining with synthetic ground truth. The two stages share weights and are executed with a high-to-low timestep schedule. Extensive experimental results confirm that Iris achieves significant improvements in MDE performance with strong in-the-wild generalization. ---