# Research Papers — 2026-02 · bundle page 44 of 210 > Full-text markdown of papers #2151–2200 of 10493 published in 2026-02, newest first. AI-readable mirrors of the full 10493-paper 2026-02 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2026-02/page/44 [← Previous bundle](https://aipod.dev/papers/archive/2026-02/page/43.md) [Next bundle →](https://aipod.dev/papers/archive/2026-02/page/45.md) ### SAMAS: A Spectrum-Guided Multi-Agent System for Achieving Style Fidelity in Literary Translation Authors: Jingzhuo Wu, Jiajun Zhang, Keyan Jin, Dehua Ma, Junbo Wang Published: 2026-02-23 Categories: cs.CL arXiv: https://arxiv.org/abs/2602.19840v1 Modern large language models (LLMs) excel at generating fluent and faithful translations. However, they struggle to preserve an author's unique literary style, often producing semantically correct but generic outputs. This limitation stems from the inability of current single-model and static multi-agent systems to perceive and adapt to stylistic variations. To address this, we introduce the Style-Adaptive Multi-Agent System (SAMAS), a novel framework that treats style preservation as a signal processing task. Specifically, our method quantifies literary style into a Stylistic Feature Spectrum (SFS) using the wavelet packet transform. This SFS serves as a control signal to dynamically assemble a tailored workflow of specialized translation agents based on the source text's structural patterns. Extensive experiments on translation benchmarks show that SAMAS achieves competitive semantic accuracy against strong baselines, primarily by leveraging its statistically significant advantage in style fidelity. --- ### Meta-Learning and Meta-Reinforcement Learning -- Tracing the Path towards DeepMind's Adaptive Agent Authors: Björn Hoppmann, Christoph Scholz Published: 2026-02-23 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2602.19837v3 Humans are highly effective at utilizing prior knowledge to adapt to novel tasks, a capability that standard machine learning models struggle to replicate due to their reliance on task-specific training. Meta-learning overcomes this limitation by allowing models to acquire transferable knowledge from various tasks, enabling rapid adaptation to new challenges with minimal data. This survey provides a rigorous, task-based formalization of meta-learning and meta-reinforcement learning and uses that paradigm to chronicle the landmark algorithms that paved the way for DeepMind's Adaptive Agent, consolidating the essential concepts needed to understand the Adaptive Agent and other generalist approaches. --- ### M3S-Net: Multimodal Feature Fusion Network Based on Multi-scale Data for Ultra-short-term PV Power Forecasting Authors: Penghui Niu, Taotao Cai, Suqi Zhang, Junhua Gu, Ping Zhang, Qiqi Liu, Jianxin Li Published: 2026-02-23 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.19832v1 The inherent intermittency and high-frequency variability of solar irradiance, particularly during rapid cloud advection, present significant stability challenges to high-penetration photovoltaic grids. Although multimodal forecasting has emerged as a viable mitigation strategy, existing architectures predominantly rely on shallow feature concatenation and binary cloud segmentation, thereby failing to capture the fine-grained optical features of clouds and the complex spatiotemporal coupling between visual and meteorological modalities. To bridge this gap, this paper proposes M3S-Net, a novel multimodal feature fusion network based on multi-scale data for ultra-short-term PV power forecasting. First, a multi-scale partial channel selection network leverages partial convolutions to explicitly isolate the boundary features of optically thin clouds, effectively transcending the precision limitations of coarse-grained binary masking. Second, a multi-scale sequence to image analysis network employs Fast Fourier Transform (FFT)-based time-frequency representation to disentangle the complex periodicity of meteorological data across varying time horizons. Crucially, the model incorporates a cross-modal Mamba interaction module featuring a novel dynamic C-matrix swapping mechanism. By exchanging state-space parameters between visual and temporal streams, this design conditions the state evolution of one modality on the context of the other, enabling deep structural coupling with linear computational complexity, thus overcoming the limitations of shallow concatenation. Experimental validation on the newly constructed fine-grained PV power dataset demonstrates that M3S-Net achieves a mean absolute error reduction of 6.2% in 10-minute forecasts compared to state-of-the-art baselines. The dataset and source code will be available at https://github.com/she1110/FGPD. --- ### TextShield-R1: Reinforced Reasoning for Tampered Text Detection Authors: Chenfan Qu, Yiwu Zhong, Jian Liu, Xuekang Zhu, Bohan Yu, Lianwen Jin Published: 2026-02-23 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.19828v1 The growing prevalence of tampered images poses serious security threats, highlighting the urgent need for reliable detection methods. Multimodal large language models (MLLMs) demonstrate strong potential in analyzing tampered images and generating interpretations. However, they still struggle with identifying micro-level artifacts, exhibit low accuracy in localizing tampered text regions, and heavily rely on expensive annotations for forgery interpretation. To this end, we introduce TextShield-R1, the first reinforcement learning based MLLM solution for tampered text detection and reasoning. Specifically, our approach introduces Forensic Continual Pre-training, an easy-to-hard curriculum that well prepares the MLLM for tampered text detection by harnessing the large-scale cheap data from natural image forensic and OCR tasks. During fine-tuning, we perform Group Relative Policy Optimization with novel reward functions to reduce annotation dependency and improve reasoning capabilities. At inference time, we enhance localization accuracy via OCR Rectification, a method that leverages the MLLM's strong text recognition abilities to refine its predictions. Furthermore, to support rigorous evaluation, we introduce the Text Forensics Reasoning (TFR) benchmark, comprising over 45k real and tampered images across 16 languages, 10 tampering techniques, and diverse domains. Rich reasoning-style annotations are included, allowing for comprehensive assessment. Our TFR benchmark simultaneously addresses seven major limitations of existing benchmarks and enables robust evaluation under cross-style, cross-method, and cross-language conditions. Extensive experiments demonstrate that TextShield-R1 significantly advances the state of the art in interpretable tampered text detection. --- ### Open-vocabulary 3D scene perception in industrial environments Authors: Keno Moenck, Adrian Philip Florea, Julian Koch, Thorsten Schüppstuhl Published: 2026-02-23 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.19823v1 Autonomous vision applications in production, intralogistics, or manufacturing environments require perception capabilities beyond a small, fixed set of classes. Recent open-vocabulary methods, leveraging 2D Vision-Language Foundation Models (VLFMs), target this task but often rely on class-agnostic segmentation models pre-trained on non-industrial datasets (e.g., household scenes). In this work, we first demonstrate that such models fail to generalize, performing poorly on common industrial objects. Therefore, we propose a training-free, open-vocabulary 3D perception pipeline that overcomes this limitation. Instead of using a pre-trained model to generate instance proposals, our method simply generates masks by merging pre-computed superpoints based on their semantic features. Following, we evaluate the domain-adapted VLFM "IndustrialCLIP" on a representative 3D industrial workshop scene for open-vocabulary querying. Our qualitative results demonstrate successful segmentation of industrial objects. --- ### Efficient endometrial carcinoma screening via cross-modal synthesis and gradient distillation Authors: Dongjing Shan, Yamei Luo, Jiqing Xuan, Lu Huang, Jin Li, Mengchu Yang, Zeyu Chen, Fajin Lv, Yong Tang, Chunxiang Zhang Published: 2026-02-23 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2602.19822v1 Early detection of myometrial invasion is critical for the staging and life-saving management of endometrial carcinoma (EC), a prevalent global malignancy. Transvaginal ultrasound serves as the primary, accessible screening modality in resource-constrained primary care settings; however, its diagnostic reliability is severely hindered by low tissue contrast, high operator dependence, and a pronounced scarcity of positive pathological samples. Existing artificial intelligence solutions struggle to overcome this severe class imbalance and the subtle imaging features of invasion, particularly under the strict computational limits of primary care clinics. Here we present an automated, highly efficient two-stage deep learning framework that resolves both data and computational bottlenecks in EC screening. To mitigate pathological data scarcity, we develop a structure-guided cross-modal generation network that synthesizes diverse, high-fidelity ultrasound images from unpaired magnetic resonance imaging (MRI) data, strictly preserving clinically essential anatomical junctions. Furthermore, we introduce a lightweight screening network utilizing gradient distillation, which transfers discriminative knowledge from a high-capacity teacher model to dynamically guide sparse attention towards task-critical regions. Evaluated on a large, multicenter cohort of 7,951 participants, our model achieves a sensitivity of 99.5\%, a specificity of 97.2\%, and an area under the curve of 0.987 at a minimal computational cost (0.289 GFLOPs), substantially outperforming the average diagnostic accuracy of expert sonographers. Our approach demonstrates that combining cross-modal synthetic augmentation with knowledge-driven efficient modeling can democratize expert-level, real-time cancer screening for resource-constrained primary care settings. --- ### SafePickle: Robust and Generic ML Detection of Malicious Pickle-based ML Models Authors: Hillel Ohayon, Daniel Gilkarov, Ran Dubin Published: 2026-02-23 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2602.19818v1 Model repositories such as Hugging Face increasingly distribute machine learning artifacts serialized with Python's pickle format, exposing users to remote code execution (RCE) risks during model loading. Recent defenses, such as PickleBall, rely on per-library policy synthesis that requires complex system setups and verified benign models, which limits scalability and generalization. In this work, we propose a lightweight, machine-learning-based scanner that detects malicious Pickle-based files without policy generation or code instrumentation. Our approach statically extracts structural and semantic features from Pickle bytecode and applies supervised and unsupervised models to classify files as benign or malicious. We construct and release a labeled dataset of 727 Pickle-based files from Hugging Face and evaluate our models on four datasets: our own, PickleBall (out-of-distribution), Hide-and-Seek (9 advanced evasive malicious models), and synthetic joblib files. Our method achieves 90.01% F1-score compared with 7.23%-62.75% achieved by the SOTA scanners (Modelscan, Fickling, ClamAV, VirusTotal) on our dataset. Furthermore, on the PickleBall data (OOD), it achieves 81.22% F1-score compared with 76.09% achieved by the PickleBall method, while remaining fully library-agnostic. Finally, we show that our method is the only one to correctly parse and classify 9/9 evasive Hide-and-Seek malicious models specially crafted to evade scanners. This demonstrates that data-driven detection can effectively and generically mitigate Pickle-based model file attacks. --- ### Whole-Piece Training for Symbolic Music Language Models via Full-Horizon Compressed Recurrence Authors: Yungang Yi, Weihua Li, Matthew Kuo, Catherine Shi, Quan Bai Published: 2026-02-23 Categories: cs.SD, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2602.19816v3 For computational efficiency, modern language models are typically trained on independently sampled fixed-length sequences. Symbolic music language models largely inherit this paradigm, despite musical structure naturally unfolding over complete compositions rather than isolated excerpts. Fragmenting compositions into independent training instances therefore prevents continuous conditioning over the complete work. We present a practical framework for whole-piece training of symbolic music language models via Full-Horizon Compressed Recurrence (FHCR). FHCR preserves the full temporal horizon of recurrent memory while reducing the dimensionality of its key-value (KV) representation, making continuous whole-piece training practical under limited GPU memory. To directly assess functional long-range dependence, we introduce KV-Reset Context Utilization (KRCU), an evaluation-time diagnostic. On the MAESTRO symbolic piano dataset, KRCU shows that full-horizon models utilize context far beyond the local segment window, whereas reducing the temporal extent of recurrent memory substantially weakens this measurable long-range dependence. FHCR preserves long-range context utilization while substantially reducing recurrent memory cost. These findings show that preserving the temporal extent of recurrent history is important for efficient whole-piece modeling, and that memory cost can instead be reduced through KV representation compression. The project demos and generated music samples are available at https://wholemusic.github.io. --- ### Depth-Structured Music Recurrence: Budgeted Recurrent Attention for Full-Piece Symbolic Music Modeling Authors: Yungang Yi, Weihua Li, Matthew Kuo, Catherine Shi, Quan Bai Published: 2026-02-23 Categories: cs.SD, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2602.19816v2 Long-context modeling is essential for symbolic music generation, since motif repetition and developmental variation can span thousands of musical events, yet practical workflows frequently rely on resource-limited hardware. We introduce Depth-Structured Music Recurrence (DSMR), a training-time design that learns from complete compositions end to end by streaming each piece left-to-right with stateful recurrent attention and distributing layer-wise memory horizons under a fixed recurrent-state budget. Our main instantiation, two-scale DSMR, assigns long history windows to lower layers and a uniform short window to the remaining layers. On the MAESTRO piano performance dataset, two-scale DSMR matches a full-memory recurrent reference in perplexity (5.96 vs. 5.98) while using approximately 59% less GPU memory and achieving roughly 36% higher throughput. Variant analyses further show strong layer substitutability under binary-horizon schedules: performance depends primarily on total allocated memory rather than which layers carry it. --- ### Keyboards for the Endangered Idu Mishmi Language Authors: Akhilesh Kakolu Ramarao Published: 2026-02-23 Categories: cs.CL arXiv: https://arxiv.org/abs/2602.19815v1 We present a mobile and desktop keyboard suite for Idu Mishmi, an endangered Trans-Himalayan language spoken by approximately 11,000 people in Arunachal Pradesh, India. Although a Latin-based orthography was developed in 2018, no digital input tools existed to use it, forcing speakers into ad-hoc romanizations that cannot represent the full writing system. Our keyboards comprise two tools: (1) an Android mobile keyboard, published on the Google Play Store and actively used in teacher training programs, and (2) a Windows desktop keyboard currently undergoing community testing. Both tools support the complete Idu Mishmi character inventory, including schwa, retracted schwa, nasalized vowels, and accented forms. Both operate fully offline with zero network permissions, addressing connectivity constraints and data sovereignty concerns. We describe the design, implementation, and deployment as a replicable model for other endangered language communities. --- ### From Agent-Only Social Networks to Autonomous Scientific Research: Lessons from OpenClaw and Moltbook, and the Architecture of ClawdLab and Beach.Science Authors: Lukas Weidener, Marko Brkić, Phillip Lee, Martin Karlsson, Kevin Noessler, Paul Kohlhaas Published: 2026-02-23 Categories: cs.AI arXiv: https://arxiv.org/abs/2602.19810v3 In January 2026, the open-source agent framework OpenClaw and the agent-only social network Moltbook produced a large-scale dataset of autonomous AI-to-AI interaction, attracting six academic publications within fourteen days. This study conducts a multivocal literature review of that ecosystem and presents two complementary platforms for autonomous scientific research as a design science response to the architectural failure modes identified. ClawdLab, an open-source platform for structured laboratory collaboration, addresses these failure modes through hard role restrictions, structured adversarial critique, PI-led governance, multi-model orchestration, and evidence requirements enforced through external tool verification, in which the principal investigator validates submitted work using available API calls, computational services, and model context protocol integrations rather than relying on social consensus. Beach.science, a public research commons, complements ClawdLab's structured laboratory model by providing a free-form environment in which heterogeneous agent configurations interact, discover research opportunities, and autonomously contribute computational analyses, supported by template-based role specialisation, extensible skill registries, and programmatic reward mechanisms that distribute inference resources to agents demonstrating scientific progress. A three-tier taxonomy distinguishes single-agent pipelines, predetermined multi-agent workflows, and fully decentralised systems, analysing why leading AI co-scientist platforms remain confined to the first two tiers. The composable third-tier architecture instantiated across ClawdLab and beach.science, in which foundation models, capabilities, governance, verification tooling, and inter-lab coordination are independently modifiable, enables compounding improvement as the broader AI ecosystem advances. --- ### Decision MetaMamba: Enhancing Selective SSM in Offline RL with Heterogeneous Sequence Mixing Authors: Wall Kim, Chaeyoung Song, Hanul Kim Published: 2026-02-23 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2602.19805v2 Mamba-based models have drawn much attention in offline RL. However, their selective mechanism often detrimental when key steps in RL sequences are omitted. To address these issues, we propose a simple yet effective structure, called Decision MetaMamba (DMM), which replaces Mamba's token mixer with a dense layer-based sequence mixer and modifies positional structure to preserve local information. By performing sequence mixing that considers all channels simultaneously before Mamba, DMM prevents information loss due to selective scanning and residual gating. Extensive experiments demonstrate that our DMM delivers the state-of-the-art performance across diverse RL tasks. Furthermore, DMM achieves these results with a compact parameter footprint, demonstrating strong potential for real-world applications. --- ### Fast Linear Reservoirs via Diagonalization Authors: Romain de Coudenhove, Yannis Bendi-Ouis, Anthony Strock, Xavier Hinaut Published: 2026-02-23 Categories: cs.DC, cs.NE, math.CV, math.DS arXiv: https://arxiv.org/abs/2602.19802v3 We introduce a diagonalization-based optimization for Linear Echo State Networks (ESNs) that reduces the per-step computational complexity of reservoir state updates from quadratic to linear. By reformulating reservoir dynamics in the eigenbasis of the recurrent matrix, the recurrent update becomes a set of independent element-wise operations, eliminating the matrix multiplication. We further propose three methods to use our optimization depending on the situation: (i) Eigenbasis Weight Transformation (EWT), which preserves the dynamics of standard and trained Linear ESNs, (ii) End-to-End Eigenbasis Training (EET), which directly optimizes readout weights in the transformed space and (iii) Direct Parameter Generation (DPG), that bypasses matrix diagonalization by directly sampling eigenvalues and eigenvectors, achieving comparable performance to standard Linear ESNs. Across all experiments, both our methods preserve predictive accuracy while offering significant computational speedups, making them a replacement for standard Linear ESNs computations and training, and suggesting a shift of paradigm in linear ESN towards the direct selection of eigenvalues. --- ### Path-conditioned training: a principled way to rescale ReLU neural networks Authors: Arthur Lebeurrier, Titouan Vayer, Rémi Gribonval Published: 2026-02-23 Categories: stat.ML, cs.LG, math.OC arXiv: https://arxiv.org/abs/2602.19799v2 Despite recent algorithmic advances, we still lack principled ways to leverage the well-documented rescaling symmetries in ReLU neural network parameters. While two properly rescaled weights implement the same function, the training dynamics can be dramatically different. To offer a fresh perspective on exploiting this phenomenon, we build on the recent path-lifting framework, which provides a compact factorization of ReLU networks. We introduce a geometrically motivated criterion to rescale neural network parameters which minimization leads to a conditioning strategy that aligns a kernel in the path-lifting space with a chosen reference. We derive an efficient algorithm to perform this alignment. In the context of random network initialization, we analyze how the architecture and the initialization scale jointly impact the output of the proposed method. Numerical experiments illustrate its potential to speed up training. --- ### Drift Localization using Conformal Predictions Authors: Fabian Hinder, Valerie Vaquet, Johannes Brinkrolf, Barbara Hammer Published: 2026-02-23 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2602.19790v2 Concept drift -- the change of the distribution over time -- poses significant challenges for learning systems and is of central interest for monitoring. Understanding drift is thus paramount, and drift localization -- determining which samples are affected by the drift -- is essential. While several approaches exist, most rely on local testing schemes, which tend to fail in high-dimensional, low-signal settings. In this work, we consider a fundamentally different approach based on conformal predictions. We discuss and show the shortcomings of common approaches and demonstrate the performance of our approach on state-of-the-art image datasets. --- ### Position: Stop Preaching and Start Practising Data Frugality for Responsible Development of AI Authors: Sophia N. Wilson, Andrew Millard, Guðrún Fjóla Guðmundsdóttir, Raghavendra Selvan, Sebastian Mair Published: 2026-02-23 Categories: cs.LG, cs.CY arXiv: https://arxiv.org/abs/2602.19789v2 This position paper argues that the machine learning community must move from preaching to practising data frugality for responsible artificial intelligence (AI) development. For too long, progress has been equated with ever-larger datasets, driving remarkable advances but now yielding increasingly diminishing performance gains alongside rising energy use and carbon emissions. While awareness of data frugal approaches has grown, their adoption has remained rhetorical, and data scaling continues to dominate development practice. We argue that this gap between preach and practice must be closed, as continued data scaling entails substantial and under-accounted environmental impacts. To ground our position, we provide indicative estimates of the energy use and carbon emissions associated with the downstream use of ImageNet-1K. We then present empirical evidence that data frugality is both practical and beneficial, demonstrating that subset selection methods can substantially reduce training energy consumption with little loss in accuracy, while also mitigating dataset bias. Finally, we outline actionable recommendations for moving data frugality from rhetorical preaching to concrete practice for responsible development of AI. --- ### Bayesian Meta-Learning with Expert Feedback for Task-Shift Adaptation through Causal Embeddings Authors: Lotta Mäkinen, Jorge Loría, Samuel Kaski Published: 2026-02-23 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.19788v1 Meta-learning methods perform well on new within-distribution tasks but often fail when adapting to out-of-distribution target tasks, where transfer from source tasks can induce negative transfer. We propose a causally-aware Bayesian meta-learning method, by conditioning task-specific priors on precomputed latent causal task embeddings, enabling transfer based on mechanistic similarity rather than spurious correlations. Our approach explicitly considers realistic deployment settings where access to target-task data is limited, and adaptation relies on noisy (expert-provided) pairwise judgments of causal similarity between source and target tasks. We provide a theoretical analysis showing that conditioning on causal embeddings controls prior mismatch and mitigates negative transfer under task shift. Empirically, we demonstrate reductions in negative transfer and improved out-of-distribution adaptation in both controlled simulations and a large-scale real-world clinical prediction setting for cross-disease transfer, where causal embeddings align with underlying clinical mechanisms. --- ### The Climate Change Knowledge Graph: Supporting Climate Services Authors: Miguel Ceriani, Fiorela Ciroku, Alessandro Russo, Massimiliano Schembri, Fai Fung, Neha Mittal, Vito Trianni, Andrea Giovanni Nuzzolese Published: 2026-02-23 Categories: cs.DB, cs.AI, cs.CY arXiv: https://arxiv.org/abs/2602.19786v1 Climate change impacts a broad spectrum of human resources and activities, necessitating the use of climate models to project long-term effects and inform mitigation and adaptation strategies. These models generate multiple datasets by running simulations across various scenarios and configurations, thereby covering a range of potential future outcomes. Currently, researchers rely on traditional search interfaces and APIs to retrieve such datasets, often piecing together information from metadata and community vocabularies. The Climate Change Knowledge Graph is designed to address these challenges by integrating diverse data sources related to climate simulations into a coherent and interoperable knowledge graph. This innovative resource allows for executing complex queries involving climate models, simulations, variables, spatio-temporal domains, and granularities. Developed with input from domain experts, the knowledge graph and its underlying ontology are published with open access license and provide a comprehensive framework that enhances the exploration of climate data, facilitating more informed decision-making in addressing climate change issues. --- ### Unsupervised Anomaly Detection in NSL-KDD Using $β$-VAE: A Latent Space and Reconstruction Error Approach Authors: Dylan Baptiste, Ramla Saddem, Alexandre Philippot, François Foyer Published: 2026-02-23 Categories: cs.LG, cs.NE, stat.ML arXiv: https://arxiv.org/abs/2602.19785v1 As Operational Technology increasingly integrates with Information Technology, the need for Intrusion Detection Systems becomes more important. This paper explores an unsupervised approach to anomaly detection in network traffic using $β$-Variational Autoencoders on the NSL-KDD dataset. We investigate two methods: leveraging the latent space structure by measuring distances from test samples to the training data projections, and using the reconstruction error as a conventional anomaly detection metric. By comparing these approaches, we provide insights into their respective advantages and limitations in an unsupervised setting. Experimental results highlight the effectiveness of latent space exploitation for classification tasks. --- ### Addressing Instrument-Outcome Confounding in Mendelian Randomization through Representation Learning Authors: Shimeng Huang, Matthew Robinson, Francesco Locatello Published: 2026-02-23 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.19782v1 Mendelian Randomization (MR) is a prominent observational epidemiological research method designed to address unobserved confounding when estimating causal effects. However, core assumptions -- particularly the independence between instruments and unobserved confounders -- are often violated due to population stratification or assortative mating. Leveraging the increasing availability of multi-environment data, we propose a representation learning framework that exploits cross-environment invariance to recover latent exogenous components of genetic instruments. We provide theoretical guarantees for identifying these latent instruments under various mixing mechanisms and demonstrate the effectiveness of our approach through simulations and semi-synthetic experiments using data from the All of Us Research Hub. --- ### Enhancing Automatic Chord Recognition via Pseudo-Labeling and Knowledge Distillation Authors: Nghia Phan, Rong Jin, Gang Liu, Xiao Dong Published: 2026-02-23 Categories: cs.SD, cs.IR, cs.LG, cs.MM arXiv: https://arxiv.org/abs/2602.19778v5 Automatic Chord Recognition (ACR) is constrained by the scarcity of aligned chord annotations, which are costly to acquire. At the same time, open-weight pre-trained models are more accessible than their proprietary training data. In this work, we present a two-stage training pipeline that leverages pre-trained models together with unlabeled audio. The proposed method decouples training into two stages. In the first stage, we use the pre-trained BTC model as a teacher to generate pseudo-labels for over 1,000 hours of diverse unlabeled audio and train a student model solely on these pseudo-labels. In the second stage, the student is continually trained on ground-truth labels as they become available. To prevent catastrophic forgetting of the representations learned in the first stage, we apply selective knowledge distillation (KD) from the teacher as a regularizer. In our experiments, two models (BTC, 2E1D) were used as students. In Stage 1, using only pseudo-labels, the BTC student achieves about 99% of the teacher's performance, while the 2E1D model achieves about 97% of the teacher's performance across seven standard mir_eval metrics. After continual training with labeled data in Stage 2, the resulting BTC student model consistently surpasses both the traditional supervised learning baseline and the original pre-trained teacher model across all metrics. The resulting 2E1D student model also outperforms the supervised baseline and approaches teacher-level performance, with both models demonstrating substantial gains on rare chord qualities. --- ### Exact Discrete Stochastic Simulation with Deep-Learning-Scale Gradient Optimization Authors: Jose M. G. Vilar, Leonor Saiz Published: 2026-02-23 Categories: q-bio.QM, cond-mat.stat-mech, cs.LG, physics.comp-ph, q-bio.MN arXiv: https://arxiv.org/abs/2602.19775v1 Exact stochastic simulation of continuous-time Markov chains (CTMCs) is essential when discreteness and noise drive system behavior, but the hard categorical event selection in Gillespie-type algorithms blocks gradient-based learning. We eliminate this constraint by decoupling forward simulation from backward differentiation, with hard categorical sampling generating exact trajectories and gradients propagating through a continuous massively-parallel Gumbel-Softmax straight-through surrogate. Our approach enables accurate optimization at parameter scales over four orders of magnitude beyond existing simulators. We validate for accuracy, scalability, and reliability on a reversible dimerization model (0.09% error), a genetic oscillator (1.2% error), a 203,796-parameter gene regulatory network achieving 98.4% MNIST accuracy (a prototypical deep-learning multilayer perceptron benchmark), and experimental patch-clamp recordings of ion channel gating (R^2 = 0.987) in the single-channel regime. Our GPU implementation delivers 1.9 billion steps per second, matching the scale of non-differentiable simulators. By making exact stochastic simulation massively parallel and autodiff-compatible, our results enable high-dimensional parameter inference and inverse design across systems biology, chemical kinetics, physics, and related CTMC-governed domains. --- ### The Confusion is Real: GRAPHIC -- A Network Science Approach to Confusion Matrices in Deep Learning Authors: Johanna S. Fröhlich, Bastian Heinlein, Jan U. Claar, Hans Rosenberger, Vasileios Belagiannis, Ralf R. Müller Published: 2026-02-23 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2602.19770v2 Explainable artificial intelligence has emerged as a promising field of research to address reliability concerns in artificial intelligence. Despite significant progress in explainable artificial intelligence, few methods provide a systematic way to visualize and understand how classes are confused and how their relationships evolve as training progresses. In this work, we present GRAPHIC, an architecture-agnostic approach that analyzes neural networks on a class level. It leverages confusion matrices derived from intermediate layers using linear classifiers. We interpret these as adjacency matrices of directed graphs, allowing tools from network science to visualize and quantify learning dynamics across training epochs and intermediate layers. GRAPHIC provides insights into linear class separability, dataset issues, and architectural behavior, revealing, for example, similarities between flatfish and man and labeling ambiguities validated in a human study. In summary, by uncovering real confusions, GRAPHIC offers new perspectives on how neural networks learn. The code is available at https://github.com/Johanna-S-Froehlich/GRAPHIC. --- ### TraceVision: Trajectory-Aware Vision-Language Model for Human-Like Spatial Understanding Authors: Fan Yang, Shurong Zheng, Hongyin Zhao, Yufei Zhan, Xin Li, Yousong Zhu, Chaoyang Zhao Ming Tang, Jinqiao Wang Published: 2026-02-23 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.19768v2 Recent Large Vision-Language Models (LVLMs) demonstrate remarkable capabilities in image understanding and natural language generation. However, current approaches focus predominantly on global image understanding, struggling to simulate human visual attention trajectories and explain associations between descriptions and specific regions. We propose TraceVision, a unified vision-language model integrating trajectory-aware spatial understanding in an end-to-end framework. TraceVision employs a Trajectory-aware Visual Perception (TVP) module for bidirectional fusion of visual features and trajectory information. We design geometric simplification to extract semantic keypoints from raw trajectories and propose a three-stage training pipeline where trajectories guide description generation and region localization. We extend TraceVision to trajectory-guided segmentation and video scene understanding, enabling cross-frame tracking and temporal attention analysis. We construct the Reasoning-based Interactive Localized Narratives (RILN) dataset to enhance logical reasoning and interpretability. Extensive experiments on trajectory-guided captioning, text-guided trajectory prediction, understanding, and segmentation demonstrate that TraceVision achieves state-of-the-art performance, establishing a foundation for intuitive spatial interaction and interpretable visual understanding. --- ### One2Scene: Geometric Consistent Explorable 3D Scene Generation from a Single Image Authors: Pengfei Wang, Liyi Chen, Zhiyuan Ma, Yanjun Guo, Guowen Zhang, Lei Zhang Published: 2026-02-23 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.19766v2 Generating explorable 3D scenes from a single image is a highly challenging problem in 3D vision. Existing methods struggle to support free exploration, often producing severe geometric distortions and noisy artifacts when the viewpoint moves far from the original perspective. We introduce \textbf{One2Scene}, an effective framework that decomposes this ill-posed problem into three tractable sub-tasks to enable immersive explorable scene generation. We first use a panorama generator to produce anchor views from a single input image as initialization. Then, we lift these 2D anchors into an explicit 3D geometric scaffold via a generalizable, feed-forward Gaussian Splatting network. Instead of treating the panorama as a single image for reconstruction, we project it into multiple sparse anchor views and reformulate the reconstruction task as multi-view stereo matching, which allows us to leverage robust geometric priors learned from large-scale multi-view datasets. A bidirectional feature fusion module is used to enforce cross-view consistency, yielding an efficient and geometrically reliable scaffold. Finally, the scaffold serves as a strong prior for a novel view generator to produce photorealistic and geometrically accurate views at arbitrary cameras. By explicitly conditioning on a 3D-consistent scaffold to perform reconstruction, One2Scene works stably under large camera motions, supporting immersive scene exploration. Extensive experiments show that One2Scene substantially outperforms state-of-the-art methods in panorama depth estimation, feed-forward 360° reconstruction, and explorable 3D scene generation. Project page: https://one2scene5406.github.io/ --- ### Training Deep Stereo Matching Networks on Tree Branch Imagery: A Benchmark Study for Real-Time UAV Forestry Applications Authors: Yida Lin, Bing Xue, Mengjie Zhang, Sam Schofield, Richard Green Published: 2026-02-23 Categories: cs.CV, eess.IV arXiv: https://arxiv.org/abs/2602.19763v1 Autonomous drone-based tree pruning needs accurate, real-time depth estimation from stereo cameras. Depth is computed from disparity maps using $Z = f B/d$, so even small disparity errors cause noticeable depth mistakes at working distances. Building on our earlier work that identified DEFOM-Stereo as the best reference disparity generator for vegetation scenes, we present the first study to train and test ten deep stereo matching networks on real tree branch images. We use the Canterbury Tree Branches dataset -- 5,313 stereo pairs from a ZED Mini camera at 1080P and 720P -- with DEFOM-generated disparity maps as training targets. The ten methods cover step-by-step refinement, 3D convolution, edge-aware attention, and lightweight designs. Using perceptual metrics (SSIM, LPIPS, ViTScore) and structural metrics (SIFT/ORB feature matching), we find that BANet-3D produces the best overall quality (SSIM = 0.883, LPIPS = 0.157), while RAFT-Stereo scores highest on scene-level understanding (ViTScore = 0.799). Testing on an NVIDIA Jetson Orin Super (16 GB, independently powered) mounted on our drone shows that AnyNet reaches 6.99 FPS at 1080P -- the only near-real-time option -- while BANet-2D gives the best quality-speed balance at 1.21 FPS. We also compare 720P and 1080P processing times to guide resolution choices for forestry drone systems. --- ### Hexagon-MLIR: An AI Compilation Stack For Qualcomm's Neural Processing Units (NPUs) Authors: Mohammed Javed Absar, Muthu Baskaran, Abhikrant Sharma, Abhilash Bhandari, Ankit Aggarwal, Arun Rangasamy, Dibyendu Das, Fateme Hosseini, Franck Slama, Iulian Brumar, Jyotsna Verma, Krishnaprasad Bindumadhavan et al. Published: 2026-02-23 Categories: cs.PL, cs.AI arXiv: https://arxiv.org/abs/2602.19762v1 In this paper, we present Hexagon-MLIR,an open-source compilation stack that targets Qualcomm Hexagon Neural Processing Unit (NPU) and provides unified support for lowering Triton kernels and PyTorch models . Built using the MLIR framework, our compiler applies a structured sequence of passes to exploit NPU architectural features to accelerate AI workloads. It enables faster deployment of new Triton kernels (hand-written or subgraphs from PyTorch 2.0), for our target by providing automated compilation from kernel to binary. By ingesting Triton kernels, we generate mega-kernels that maximize data locality in the NPU's Tightly Coupled Memory (TCM), reducing the bandwidth bottlenecks inherent in library-based approaches. This initiative complements our commercial toolchains by providing developers with an open-source MLIR-based compilation stack that gives them a path to advance AI compilation capabilities through a more flexible approach. Hexagon-MLIR is a work-in-progress, and we are continuing to add many more optimizations and capabilities in this effort. --- ### Ensemble Machine Learning and Statistical Procedures for Dynamic Predictions of Time-to-Event Outcomes Authors: Nina van Gerwen, Sten Willemsen, Bettina E. Hansen, Christophe Corpechot, Marco Carbone, Cynthia Levy, Maria-Carlota Londõno, Atsushi Tanaka, Palak Trivedi, Alejandra Villamil, Gideon Hirschfield, Dimitris Rizopoulos Published: 2026-02-23 Categories: stat.ML, cs.LG, stat.AP arXiv: https://arxiv.org/abs/2602.19761v1 Dynamic predictions for longitudinal and time-to-event outcomes have become a versatile tool in precision medicine. Our work is motivated by the application of dynamic predictions in the decision-making process for primary biliary cholangitis patients. For these patients, serial biomarker measurements (e.g., bilirubin and alkaline phosphatase levels) are routinely collected to inform treating physicians of the risk of liver failure and guide clinical decision-making. Two popular statistical approaches to derive dynamic predictions are joint modelling and landmarking. However, recently, machine learning techniques have also been proposed. Each approach has its merits, and no single method exists to outperform all others. Consequently, obtaining the best possible survival estimates is challenging. Therefore, we extend the Super Learner framework to combine dynamic predictions from different models and procedures. Super Learner is an ensemble learning technique that allows users to combine different prediction algorithms to improve predictive accuracy and flexibility. It uses cross-validation and different objective functions of performance (e.g., squared loss) that suit specific applications to build the optimally weighted combination of predictions from a library of candidate algorithms. In our work, we pay special attention to appropriate objective functions for Super Learner to obtain the most optimal weighted combination of dynamic predictions. In our primary biliary cholangitis application, Super Learner presented unique benefits due to its ability to flexibly combine outputs from a diverse set of models with varying assumptions for equal or better predictive performance than any model fit separately. --- ### Multimodal Dataset Distillation Made Simple by Prototype-Guided Data Synthesis Authors: Junhyeok Choi, Sangwoo Mo, Minwoo Chae Published: 2026-02-23 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.19756v2 Recent advances in multimodal learning have achieved remarkable success across diverse vision-language tasks. However, such progress heavily relies on large-scale image-text datasets, making training costly and inefficient. Prior efforts in dataset filtering and pruning attempt to mitigate this issue, but still require relatively large subsets to maintain performance and fail under very small subsets. Dataset distillation offers a promising alternative, yet existing multimodal dataset distillation methods require full-dataset training and joint optimization of image pixels and text features, making them architecture-dependent and limiting cross-architecture generalization. To overcome this, we propose a learning-free dataset distillation framework that eliminates the need for large-scale training and optimization while enhancing generalization across architectures. Our method uses CLIP to extract aligned image-text embeddings, obtains prototypes, and employs an unCLIP decoder to synthesize images, enabling efficient and scalable multimodal dataset distillation. Extensive experiments demonstrate that our approach consistently outperforms optimization-based dataset distillation and subset selection methods, achieving state-of-the-art cross-architecture generalization. --- ### RAP: Fast Feedforward Rendering-Free Attribute-Guided Primitive Importance Score Prediction for Efficient 3D Gaussian Splatting Processing Authors: Kaifa Yang, Qi Yang, Yiling Xu, Zhu Li Published: 2026-02-23 Categories: cs.CV, cs.GR arXiv: https://arxiv.org/abs/2602.19753v1 3D Gaussian Splatting (3DGS) has emerged as a leading technology for high-quality 3D scene reconstruction. However, the iterative refinement and densification process leads to the generation of a large number of primitives, each contributing to the reconstruction to a substantially different extent. Estimating primitive importance is thus crucial, both for removing redundancy during reconstruction and for enabling efficient compression and transmission. Existing methods typically rely on rendering-based analyses, where each primitive is evaluated through its contribution across multiple camera viewpoints. However, such methods are sensitive to the number and selection of views, rely on specialized differentiable rasterizers, and have long calculation times that grow linearly with view count, making them difficult to integrate as plug-and-play modules and limiting scalability and generalization. To address these issues, we propose RAP, a fast feedforward rendering-free attribute-guided method for efficient importance score prediction in 3DGS. RAP infers primitive significance directly from intrinsic Gaussian attributes and local neighborhood statistics, avoiding rendering-based or visibility-dependent computations. A compact MLP predicts per-primitive importance scores using rendering loss, pruning-aware loss, and significance distribution regularization. After training on a small set of scenes, RAP generalizes effectively to unseen data and can be seamlessly integrated into reconstruction, compression, and transmission pipelines. Our code is publicly available at https://github.com/yyyykf/RAP. --- ### NILE: Formalizing Natural-Language Descriptions of Formal Languages Authors: Tristan Kneisel, Marko Schmellenkamp, Fabian Vehlken, Thomas Zeume Published: 2026-02-23 Categories: cs.FL, cs.CL, cs.LO arXiv: https://arxiv.org/abs/2602.19743v1 This paper explores how natural-language descriptions of formal languages can be compared to their formal representations and how semantic differences can be explained. This is motivated from educational scenarios where learners describe a formal language (presented, e.g., by a finite state automaton, regular expression, pushdown automaton, context-free grammar or in set notation) in natural language, and an educational support system has to (1) judge whether the natural-language description accurately describes the formal language, and to (2) provide explanations why descriptions are not accurate. To address this question, we introduce a representation language for formal languages, Nile, which is designed so that Nile expressions can mirror the syntactic structure of natural-language descriptions of formal languages. Nile is sufficiently expressive to cover a broad variety of formal languages, including all regular languages and fragments of context-free languages typically used in educational contexts. Generating Nile expressions that are syntactically close to natural-language descriptions then allows to provide explanations for inaccuracies in the descriptions algorithmically. In experiments on an educational data set, we show that LLMs can translate natural-language descriptions into equivalent, syntactically close Nile expressions with high accuracy - allowing to algorithmically provide explanations for incorrect natural-language descriptions. Our experiments also show that while natural-language descriptions can also be translated into regular expressions (but not context-free grammars), the expressions are often not syntactically close and thus not suitable for providing explanations. --- ### InfScene-SR: Seamless Super-Resolution of Arbitrarily Large Remote-Sensing Scenes via Variance-Preserving Joint Denoising Authors: Shoukun Sun, Zhe Wang, Xiang Que, Jiyin Zhang, Xiaogang Ma Published: 2026-02-23 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.19736v3 Diffusion models now give the best perceptual quality in super-resolution (SR), but their architecture and training confine them to small fixed crops. Operational remote sensing needs seamless scenes orders of magnitude larger. Joint denoising fuses overlapping tiles at every reverse step and lets text-to-image diffusion generate beyond its training crop, but it assumes deterministic ODE samplers. With the stochastic sampler of SR models such as SR3, the averaging also partly cancels independent per-tile noise. This known variance erosion blurs the detail SR should recover and must be corrected. We carry variance-corrected fusion to conditional SR and derive Spatially-Decoupled Variance Correction (SDVC), an exact reformulation that replaces per-step global normalization with independent per-tile contributions accumulated in one additive pass. SDVC turns the coupled per-step computation into independent tile-local work, so the resulting pipeline, InfScene-SR, runs in parallel across GPUs and makes SR of arbitrarily large scenes feasible. On a 5$\times$ SR task built from NAIP aerial imagery, we evaluate whole scenes with fidelity, perceptual, seam-continuity, and faithfulness metrics. Under one backbone, InfScene-SR is the only fusion strategy that is seamless and sharp at once, the closest to the low-resolution observation among those that synthesize detail, and within 0.003 IoU of native high-resolution imagery on downstream invasive-plant segmentation. Code is available at https://github.com/TitorX/infscene-sr. --- ### InfScene-SR: Arbitrary-Size Image Super-Resolution via Iterative Joint-Denoising Authors: Shoukun Sun, Zhe Wang, Xiang Que, Jiyin Zhang, Xiaogang Ma Published: 2026-02-23 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.19736v2 While diffusion models have achieved state-of-the-art performance in Image Super-Resolution (SR), their prohibitive computational and memory demands restrict their training and inference to fixed-size inputs. The standard workaround to super-resolve larger images relies on partitioning the image, super-resolving patches independently, and stitching them together -- a process that inevitably introduces severe boundary artifacts and spatial inconsistencies in large-scale scenes. To achieve spatially continuous, arbitrary-size image super-resolution, we propose InfScene-SR, a diffusion-based SR approach. Building upon SR3, our approach leverages Variance-Corrected Fusion (VCF) to perform joint-denoising across overlapping patches. VCF guarantees continuous transitions while preserving the stochastic variance crucial for high-fidelity texture reconstruction. To overcome the prohibitive synchronization overhead of scaling joint-denoising to gigapixel imagery, we introduce Spatially-Decoupled Variance Correction (SDVC). SDVC reformulates the global fusion process into independent, atomic patch operations, drastically reducing memory complexity to $\mathcal{O}(1)$ and naturally enabling fully distributed, parallelized inference. Extensive experiments on large-scale remote sensing datasets demonstrate that InfScene-SR strictly eliminates boundary seams, achieves superior perceptual quality, and significantly boosts performance in downstream semantic segmentation task. --- ### VGGT-MPR: VGGT-Enhanced Multimodal Place Recognition in Autonomous Driving Environments Authors: Jingyi Xu, Zhangshuo Qi, Zhongmiao Yan, Xuyu Gao, Qianyun Jiao, Songpengcheng Xia, Xieyuanli Chen, Ling Pei Published: 2026-02-23 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.19735v1 In autonomous driving, robust place recognition is critical for global localization and loop closure detection. While inter-modality fusion of camera and LiDAR data in multimodal place recognition (MPR) has shown promise in overcoming the limitations of unimodal counterparts, existing MPR methods basically attend to hand-crafted fusion strategies and heavily parameterized backbones that require costly retraining. To address this, we propose VGGT-MPR, a multimodal place recognition framework that adopts the Visual Geometry Grounded Transformer (VGGT) as a unified geometric engine for both global retrieval and re-ranking. In the global retrieval stage, VGGT extracts geometrically-rich visual embeddings through prior depth-aware and point map supervision, and densifies sparse LiDAR point clouds with predicted depth maps to improve structural representation. This enhances the discriminative ability of fused multimodal features and produces global descriptors for fast retrieval. Beyond global retrieval, we design a training-free re-ranking mechanism that exploits VGGT's cross-view keypoint-tracking capability. By combining mask-guided keypoint extraction with confidence-aware correspondence scoring, our proposed re-ranking mechanism effectively refines retrieval results without additional parameter optimization. Extensive experiments on large-scale autonomous driving benchmarks and our self-collected data demonstrate that VGGT-MPR achieves state-of-the-art performance, exhibiting strong robustness to severe environmental changes, viewpoint shifts, and occlusions. Our code and data will be made publicly available. --- ### Understanding the Curse of Unrolling Authors: Sheheryar Mehmood, Florian Knoll, Peter Ochs Published: 2026-02-23 Categories: cs.LG, math.OC arXiv: https://arxiv.org/abs/2602.19733v1 Algorithm unrolling is ubiquitous in machine learning, particularly in hyperparameter optimization and meta-learning, where Jacobians of solution mappings are computed by differentiating through iterative algorithms. Although unrolling is known to yield asymptotically correct Jacobians under suitable conditions, recent work has shown that the derivative iterates may initially diverge from the true Jacobian, a phenomenon known as the curse of unrolling. In this work, we provide a non-asymptotic analysis that explains the origin of this behavior and identifies the algorithmic factors that govern it. We show that truncating early iterations of the derivative computation mitigates the curse while simultaneously reducing memory requirements. Finally, we demonstrate that warm-starting in bilevel optimization naturally induces an implicit form of truncation, providing a practical remedy. Our theoretical findings are supported by numerical experiments on representative examples. --- ### Towards Personalized Multi-Modal MRI Synthesis across Heterogeneous Datasets Authors: Yue Zhang, Zhizheng Zhuo, Siyao Xu, Shan Lv, Zhaoxi Liu, Jun Qiu, Qiuli Wang, Yaou Liu, S. Kevin Zhou Published: 2026-02-23 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.19723v1 Synthesizing missing modalities in multi-modal magnetic resonance imaging (MRI) is vital for ensuring diagnostic completeness, particularly when full acquisitions are infeasible due to time constraints, motion artifacts, and patient tolerance. Recent unified synthesis models have enabled flexible synthesis tasks by accommodating various input-output configurations. However, their training and evaluation are typically restricted to a single dataset, limiting their generalizability across diverse clinical datasets and impeding practical deployment. To address this limitation, we propose PMM-Synth, a personalized MRI synthesis framework that not only supports various synthesis tasks but also generalizes effectively across heterogeneous datasets. PMM-Synth is jointly trained on multiple multi-modal MRI datasets that differ in modality coverage, disease types, and intensity distributions. It achieves cross-dataset generalization through three core innovations: a Personalized Feature Modulation module that dynamically adapts feature representations based on dataset identifier to mitigate the impact of distributional shifts; a Modality-Consistent Batch Scheduler that facilitates stable and efficient batch training under inconsistent modality conditions; and a selective supervision loss to ensure effective learning when ground truth modalities are partially missing. Evaluated on four clinical multi-modal MRI datasets, PMM-Synth consistently outperforms state-of-the-art methods in both one-to-one and many-to-one synthesis tasks, achieving superior PSNR and SSIM scores. Qualitative results further demonstrate improved preservation of anatomical structures and pathological details. Additionally, downstream tumor segmentation and radiological reporting studies suggest that PMM-Synth holds potential for supporting reliable diagnosis under real-world modality-missing scenarios. --- ### Generative 6D Pose Estimation via Conditional Flow Matching Authors: Amir Hamza, Davide Boscaini, Weihang Li, Benjamin Busam, Fabio Poiesi Published: 2026-02-23 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.19719v1 Existing methods for instance-level 6D pose estimation typically rely on neural networks that either directly regress the pose in $\mathrm{SE}(3)$ or estimate it indirectly via local feature matching. The former struggle with object symmetries, while the latter fail in the absence of distinctive local features. To overcome these limitations, we propose a novel formulation of 6D pose estimation as a conditional flow matching problem in $\mathbb{R}^3$. We introduce Flose, a generative method that infers object poses via a denoising process conditioned on local features. While prior approaches based on conditional flow matching perform denoising solely based on geometric guidance, Flose integrates appearance-based semantic features to mitigate ambiguities caused by object symmetries. We further incorporate RANSAC-based registration to handle outliers. We validate Flose on five datasets from the established BOP benchmark. Flose outperforms prior methods with an average improvement of +4.5 Average Recall. Project Website : https://tev-fbk.github.io/Flose/ --- ### Carbon-Aware Governance Gates: An Architecture for Sustainable GenAI Development Authors: Mateen A. Abbasi, Tommi J. Mikkonen, Petri J. Ihantola, Muhammad Waseem, Pekka Abrahamsson, Niko K. Mäkitalo Published: 2026-02-23 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2602.19718v2 The rapid adoption of Generative AI (GenAI) in the software development life cycle (SDLC) increases computational demand, which can raise the carbon footprint of development activities. At the same time, organizations are increasingly embedding governance mechanisms into GenAI-assisted development to support trust, transparency, and accountability. However, these governance mechanisms introduce additional computational workloads, including repeated inference, regeneration cycles, and expanded validation pipelines, increasing energy use and the carbon footprint of GenAI-assisted development. This paper proposes Carbon-Aware Governance Gates (CAGG), an architectural extension that embeds carbon budgets, energy provenance, and sustainability-aware validation orchestration into human-AI governance layers. CAGG comprises three components: (i) an Energy and Carbon Provenance Ledger, (ii) a Carbon Budget Manager, and (iii) a Green Validation Orchestrator, operationalized through governance policies and reusable design patterns. --- ### Pixels Don't Lie (But Your Detector Might): Bootstrapping MLLM-as-a-Judge for Trustworthy Deepfake Detection and Reasoning Supervision Authors: Kartik Kuckreja, Parul Gupta, Muhammad Haris Khan, Abhinav Dhall Published: 2026-02-23 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.19715v1 Deepfake detection models often generate natural-language explanations, yet their reasoning is frequently ungrounded in visual evidence, limiting reliability. Existing evaluations measure classification accuracy but overlook reasoning fidelity. We propose DeepfakeJudge, a framework for scalable reasoning supervision and evaluation, that integrates an out-of-distribution benchmark containing recent generative and editing forgeries, a human-annotated subset with visual reasoning labels, and a suite of evaluation models, that specialize in evaluating reasoning rationales without the need for explicit ground truth reasoning rationales. The Judge is optimized through a bootstrapped generator-evaluator process that scales human feedback into structured reasoning supervision and supports both pointwise and pairwise evaluation. On the proposed meta-evaluation benchmark, our reasoning-bootstrapped model achieves an accuracy of 96.2\%, outperforming \texttt{30x} larger baselines. The reasoning judge attains very high correlation with human ratings and 98.9\% percent pairwise agreement on the human-annotated meta-evaluation subset. These results establish reasoning fidelity as a quantifiable dimension of deepfake detection and demonstrate scalable supervision for interpretable deepfake reasoning. Our user study shows that participants preferred the reasonings generated by our framework 70\% of the time, in terms of faithfulness, groundedness, and usefulness, compared to those produced by other models and datasets. All of our datasets, models, and codebase are \href{https://github.com/KjAeRsTuIsK/DeepfakeJudge}{open-sourced}. --- ### Universal Pose Pretraining for Generalizable Vision-Language-Action Policies Authors: Haitao Lin, Hanyang Yu, Jingshun Huang, He Zhang, Yonggen Ling, Ping Tan, Xiangyang Xue, Yanwei Fu Published: 2026-02-23 Categories: cs.CV, cs.LG, cs.RO arXiv: https://arxiv.org/abs/2602.19710v4 Existing Vision-Language-Action (VLA) models often suffer from feature collapse and low training efficiency because they entangle high-level perception with sparse, embodiment-specific action supervision. Since these models typically rely on VLM backbones optimized for Visual Question Answering (VQA), they excel at semantic identification but often overlook subtle 3D state variations that dictate distinct action patterns. To resolve these misalignments, we propose Pose-VLA, a decoupled paradigm that separates VLA training into a pre-training phase for extracting universal 3D spatial priors in a unified camera-centric space, and a post-training phase for efficient embodiment alignment within robot-specific action space. By introducing discrete pose tokens as a universal representation, Pose-VLA seamlessly integrates spatial grounding from diverse 3D datasets with geometry-level trajectories from robotic demonstrations. Our framework follows a two-stage pre-training pipeline, establishing fundamental spatial grounding via poses followed by motion alignment through trajectory supervision. Extensive evaluations demonstrate that Pose-VLA achieves state-of-the-art results on RoboTwin 2.0 with a 79.5% average success rate and competitive performance on LIBERO at 96.0%. Real-world experiments further showcase robust generalization across diverse objects using only 100 demonstrations per task, validating the efficiency of our pre-training paradigm. --- ### PoseVLA: Universal Pose Pretraining for Generalizable Vision-Language-Action Policies Authors: Haitao Lin, Hanyang Yu, Jingshun Huang, He Zhang, Yonggen Ling, Ping Tan, Xiangyang Xue, Yanwei Fu Published: 2026-02-23 Categories: cs.CV, cs.LG, cs.RO arXiv: https://arxiv.org/abs/2602.19710v3 Existing Vision-Language-Action (VLA) models often suffer from feature collapse and low training efficiency because they entangle high-level perception with sparse, embodiment-specific action supervision. Since these models typically rely on VLM backbones optimized for Visual Question Answering (VQA), they excel at semantic identification but often overlook subtle 3D state variations that dictate distinct action patterns. To resolve these misalignments, we propose Pose-VLA, a decoupled paradigm that separates VLA training into a pre-training phase for extracting universal 3D spatial priors in a unified camera-centric space, and a post-training phase for efficient embodiment alignment within robot-specific action space. By introducing discrete pose tokens as a universal representation, Pose-VLA seamlessly integrates spatial grounding from diverse 3D datasets with geometry-level trajectories from robotic demonstrations. Our framework follows a two-stage pre-training pipeline, establishing fundamental spatial grounding via poses followed by motion alignment through trajectory supervision. Extensive evaluations demonstrate that Pose-VLA achieves state-of-the-art results on RoboTwin 2.0 with a 79.5% average success rate and competitive performance on LIBERO at 96.0%. Real-world experiments further showcase robust generalization across diverse objects using only 100 demonstrations per task, validating the efficiency of our pre-training paradigm. --- ### ChimeraLoRA: Multi-Head LoRA-Guided Synthetic Datasets Authors: Hoyoung Kim, Minwoo Jang, Jabin Koo, Sangdoo Yun, Jungseul Ok Published: 2026-02-23 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.19708v2 Beyond general recognition tasks, specialized domains and fine-grained settings often encounter data scarcity, especially for tail classes. To obtain less biased and more reliable models under such scarcity, practitioners leverage diffusion models to supplement underrepresented regions of real data. Specifically, recent studies fine-tune pretrained diffusion models with LoRA on few-shot real sets to synthesize additional images. While an image-wise LoRA trained on a single image captures fine-grained details yet offers limited diversity, a class-wise LoRA trained over all shots produces diverse images as it encodes class priors yet tends to overlook fine details. To combine both benefits, we separate the adapter into a class-shared LoRA~$A$ for class priors and per-image LoRAs~$\mathcal{B}$ for image-specific characteristics. To expose coherent class semantics in the shared LoRA~$A$, we propose a semantic boosting by preserving class bounding boxes during training. For generation, we compose $A$ with a mixture of $\mathcal{B}$ using coefficients drawn from a Dirichlet distribution. Across diverse datasets, our synthesized images are both diverse and detail-rich while closely aligning with the few-shot real distribution, yielding robust gains in downstream classification accuracy. --- ### HDR Reconstruction Boosting with Training-Free and Exposure-Consistent Diffusion Authors: Yo-Tin Lin, Su-Kai Chen, Hou-Ning Hu, Yen-Yu Lin, Yu-Lun Liu Published: 2026-02-23 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.19706v1 Single LDR to HDR reconstruction remains challenging for over-exposed regions where traditional methods often fail due to complete information loss. We present a training-free approach that enhances existing indirect and direct HDR reconstruction methods through diffusion-based inpainting. Our method combines text-guided diffusion models with SDEdit refinement to generate plausible content in over-exposed areas while maintaining consistency across multi-exposure LDR images. Unlike previous approaches requiring extensive training, our method seamlessly integrates with existing HDR reconstruction techniques through an iterative compensation mechanism that ensures luminance coherence across multiple exposures. We demonstrate significant improvements in both perceptual quality and quantitative metrics on standard HDR datasets and in-the-wild captures. Results show that our method effectively recovers natural details in challenging scenarios while preserving the advantages of existing HDR reconstruction pipelines. Project page: https://github.com/EusdenLin/HDR-Reconstruction-Boosting --- ### Testing Effect Homogeneity and Confounding in High-Dimensional Experimental and Observational Studies Authors: Ana Armendariz, Martin Huber Published: 2026-02-23 Categories: econ.EM, stat.ML arXiv: https://arxiv.org/abs/2602.19703v1 We propose a framework for testing the homogeneity of conditional average treatment effects (CATEs) across multiple experimental and observational studies. Our approach leverages multiple randomized trials to assess whether treatment effects vary with unobserved heterogeneity that differs across trials: if CATEs are homogeneous, this indicates the absence of interactions between treatment and unobservables in the mean effect. Comparing CATEs between experimental and observational data further allows evaluation of potential confounding: if the estimands coincide, there is no unobserved confounding; if they differ, deviations may arise from unobserved confounding, effect heterogeneity, or both. We extend the framework to settings with alternative identification strategies, namely instrumental variable settings and panel data with parallel trends assumptions based on differences in differences, where effects are identified only locally for subpopulations such as compliers or treated units. In these contexts, testing homogeneity is useful for assessing whether local effects can be extrapolated to the total population. We suggest a test based on double machine learning that accommodates high-dimensional covariates in a data-driven way and investigate its finite-sample performance through a simulation study. Finally, we apply the test to the International Stroke Trial (IST), a large multi-country randomized controlled trial in patients with acute ischaemic stroke that evaluated whether early treatment with aspirin altered subsequent clinical outcomes. Our methodology provides a flexible tool for both validating identification assumptions and understanding the generalizability of estimated treatment effects. --- ### DReX: An Explainable Deep Learning-based Multimodal Recommendation Framework Authors: Adamya Shyam, Venkateswara Rao Kagita, Bharti Rana, Vikas Kumar Published: 2026-02-23 Categories: cs.IR, cs.AI arXiv: https://arxiv.org/abs/2602.19702v1 Multimodal recommender systems leverage diverse data sources, such as user interactions, content features, and contextual information, to address challenges like cold-start and data sparsity. However, existing methods often suffer from one or more key limitations: processing different modalities in isolation, requiring complete multimodal data for each interaction during training, or independent learning of user and item representations. These factors contribute to increased complexity and potential misalignment between user and item embeddings. To address these challenges, we propose DReX, a unified multimodal recommendation framework that incrementally refines user and item representations by leveraging interaction-level features from multimodal feedback. Our model employs gated recurrent units to selectively integrate these fine-grained features into global representations. This incremental update mechanism provides three key advantages: (1) simultaneous modeling of both nuanced interaction details and broader preference patterns, (2) eliminates the need for separate user and item feature extraction processes, leading to enhanced alignment in their learned representation, and (3) inherent robustness to varying or missing modalities. We evaluate the performance of the proposed approach on three real-world datasets containing reviews and ratings as interaction modalities. By considering review text as a modality, our approach automatically generates interpretable keyword profiles for both users and items, which supplement the recommendation process with interpretable preference indicators. Experiment results demonstrate that our approach outperforms state-of-the-art methods across all evaluated datasets. --- ### Iconographic Classification and Content-Based Recommendation for Digitized Artworks Authors: Krzysztof Kutt, Maciej Baczyński Published: 2026-02-23 Categories: cs.DL, cs.AI, cs.CV, cs.IR arXiv: https://arxiv.org/abs/2602.19698v1 We present a proof-of-concept system that automates iconographic classification and content-based recommendation of digitized artworks using the Iconclass vocabulary and selected artificial intelligence methods. The prototype implements a four-stage workflow for classification and recommendation, which integrates YOLOv8 object detection with algorithmic mappings to Iconclass codes, rule-based inference for abstract meanings, and three complementary recommenders (hierarchical proximity, IDF-weighted overlap, and Jaccard similarity). Although more engineering is still needed, the evaluation demonstrates the potential of this solution: Iconclass-aware computer vision and recommendation methods can accelerate cataloging and enhance navigation in large heritage repositories. The key insight is to let computer vision propose visible elements and to use symbolic structures (Iconclass hierarchy) to reach meaning. --- ### BayesFusion-SDF: Probabilistic Signed Distance Fusion with View Planning on CPU Authors: Soumya Mazumdar, Vineet Kumar Rakesh, Tapas Samanta Published: 2026-02-23 Categories: cs.CV, cs.GR, cs.RO arXiv: https://arxiv.org/abs/2602.19697v1 Key part of robotics, augmented reality, and digital inspection is dense 3D reconstruction from depth observations. Traditional volumetric fusion techniques, including truncated signed distance functions (TSDF), enable efficient and deterministic geometry reconstruction; however, they depend on heuristic weighting and fail to transparently convey uncertainty in a systematic way. Recent neural implicit methods, on the other hand, get very high fidelity but usually need a lot of GPU power for optimization and aren't very easy to understand for making decisions later on. This work presents BayesFusion-SDF, a CPU-centric probabilistic signed distance fusion framework that conceptualizes geometry as a sparse Gaussian random field with a defined posterior distribution over voxel distances. First, a rough TSDF reconstruction is used to create an adaptive narrow-band domain. Then, depth observations are combined using a heteroscedastic Bayesian formulation that is solved using sparse linear algebra and preconditioned conjugate gradients. Randomized diagonal estimators are a quick way to get an idea of posterior uncertainty. This makes it possible to extract surfaces and plan the next best view while taking into account uncertainty. Tests on a controlled ablation scene and a CO3D object sequence show that the new method is more accurate geometrically than TSDF baselines and gives useful estimates of uncertainty for active sensing. The proposed formulation provides a clear and easy-to-use alternative to GPU-heavy neural reconstruction methods while still being able to be understood in a probabilistic way and acting in a predictable way. GitHub: https://mazumdarsoumya.github.io/BayesFusionSDF --- ### Smoothness Adaptivity in Constant-Depth Neural Networks: Optimal Rates via Smooth Activations Authors: Yuhao Liu, Zilin Wang, Lei Wu, Shaobo Zhang Published: 2026-02-23 Categories: stat.ML, cs.LG, math.NA arXiv: https://arxiv.org/abs/2602.19691v2 Smooth activation functions are ubiquitous in modern deep learning, yet their theoretical advantages over non-smooth counterparts remain poorly understood. In this work, we study both approximation and statistical properties of neural networks with smooth activations for learning functions in the Sobolev space $W^{s,\infty}((0,1)^d)$ with $s>0$. We prove that constant-depth networks equipped with smooth activations achieve smoothness adaptivity: increasing width alone suffices to attain the minimax-optimal approximation and estimation error rates (up to logarithmic factors). In contrast, for non-smooth activations such as ReLU, smoothness adaptivity is fundamentally limited by depth: the attainable approximation order is bounded by depth, and higher-order smoothness requires proportional depth growth. These results identify activation smoothness as a fundamental mechanism, complementary to depth, for achieving optimal rates over Sobolev function classes. Technically, our analysis is based on a multi-scale approximation framework that yields explicit neural network approximators with controlled parameter norms and model size. This complexity control ensures statistical learnability under empirical risk minimization (ERM) and avoids the impractical $\ell^0$-sparsity constraints commonly required in prior analyses. --- ### PerturbDiff: Functional Diffusion for Single-Cell Perturbation Modeling Authors: Xinyu Yuan, Xixian Liu, Ya Shi Zhang, Zuobai Zhang, Hongyu Guo, Jian Tang Published: 2026-02-23 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2602.19685v1 Building Virtual Cells that can accurately simulate cellular responses to perturbations is a long-standing goal in systems biology. A fundamental challenge is that high-throughput single-cell sequencing is destructive: the same cell cannot be observed both before and after a perturbation. Thus, perturbation prediction requires mapping unpaired control and perturbed populations. Existing models address this by learning maps between distributions, but typically assume a single fixed response distribution when conditioned on observed cellular context (e.g., cell type) and the perturbation type. In reality, responses vary systematically due to unobservable latent factors such as microenvironmental fluctuations and complex batch effects, forming a manifold of possible distributions for the same observed conditions. To account for this variability, we introduce PerturbDiff, which shifts modeling from individual cells to entire distributions. By embedding distributions as points in a Hilbert space, we define a diffusion-based generative process operating directly over probability distributions. This allows PerturbDiff to capture population-level response shifts across hidden factors. Benchmarks on established datasets show that PerturbDiff achieves state-of-the-art performance in single-cell response prediction and generalizes substantially better to unseen perturbations. See our project page (https://katarinayuan.github.io/PerturbDiff-ProjectPage/), where code and data will be made publicly available (https://github.com/DeepGraphLearning/PerturbDiff). --- ### TeHOR: Text-Guided 3D Human and Object Reconstruction with Textures Authors: Hyeongjin Nam, Daniel Sungho Jung, Kyoung Mu Lee Published: 2026-02-23 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2602.19679v1 Joint reconstruction of 3D human and object from a single image is an active research area, with pivotal applications in robotics and digital content creation. Despite recent advances, existing approaches suffer from two fundamental limitations. First, their reconstructions rely heavily on physical contact information, which inherently cannot capture non-contact human-object interactions, such as gazing at or pointing toward an object. Second, the reconstruction process is primarily driven by local geometric proximity, neglecting the human and object appearances that provide global context crucial for understanding holistic interactions. To address these issues, we introduce TeHOR, a framework built upon two core designs. First, beyond contact information, our framework leverages text descriptions of human-object interactions to enforce semantic alignment between the 3D reconstruction and its textual cues, enabling reasoning over a wider spectrum of interactions, including non-contact cases. Second, we incorporate appearance cues of the 3D human and object into the alignment process to capture holistic contextual information, thereby ensuring visually plausible reconstructions. As a result, our framework produces accurate and semantically coherent reconstructions, achieving state-of-the-art performance. ---