# Research Papers — 2026-02 · bundle page 50 of 210 > Full-text markdown of papers #2451–2500 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/50 [← Previous bundle](https://aipod.dev/papers/archive/2026-02/page/49.md) [Next bundle →](https://aipod.dev/papers/archive/2026-02/page/51.md) ### Test-Time Learning of Causal Structure from Interventional Data Authors: Wei Chen, Rui Ding, Bojun Huang, Yang Zhang, Qiang Fu, Yuxuan Liang, Han Shi, Dongmei Zhang Published: 2026-02-22 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2602.19131v1 Supervised causal learning has shown promise in causal discovery, yet it often struggles with generalization across diverse interventional settings, particularly when intervention targets are unknown. To address this, we propose TICL (Test-time Interventional Causal Learning), a novel method that synergizes Test-Time Training with Joint Causal Inference. Specifically, we design a self-augmentation strategy to generate instance-specific training data at test time, effectively avoiding distribution shifts. Furthermore, by integrating joint causal inference, we developed a PC-inspired two-phase supervised learning scheme, which effectively leverages self-augmented training data while ensuring theoretical identifiability. Extensive experiments on bnlearn benchmarks demonstrate TICL's superiority in multiple aspects of causal discovery and intervention target detection. --- ### Detecting labeling bias using influence functions Authors: Frida Jørgensen, Nina Weng, Siavash Bigdeli Published: 2026-02-22 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2602.19130v1 Labeling bias arises during data collection due to resource limitations or unconscious bias, leading to unequal label error rates across subgroups or misrepresentation of subgroup prevalence. Most fairness constraints assume training labels reflect the true distribution, rendering them ineffective when labeling bias is present; leaving a challenging question, that \textit{how can we detect such labeling bias?} In this work, we investigate whether influence functions can be used to detect labeling bias. Influence functions estimate how much each training sample affects a model's predictions by leveraging the gradient and Hessian of the loss function -- when labeling errors occur, influence functions can identify wrongly labeled samples in the training set, revealing the underlying failure mode. We develop a sample valuation pipeline and test it first on the MNIST dataset, then scaled to the more complex CheXpert medical imaging dataset. To examine label noise, we introduced controlled errors by flipping 20\% of the labels for one class in the dataset. Using a diagonal Hessian approximation, we demonstrated promising results, successfully detecting nearly 90\% of mislabeled samples in MNIST. On CheXpert, mislabeled samples consistently exhibit higher influence scores. These results highlight the potential of influence functions for identifying label errors. --- ### K-Search: LLM Kernel Generation via Co-Evolving Intrinsic World Model Authors: Shiyi Cao, Ziming Mao, Joseph E. Gonzalez, Ion Stoica Published: 2026-02-22 Categories: cs.AI arXiv: https://arxiv.org/abs/2602.19128v2 Optimizing GPU kernels is critical for efficient modern machine learning systems yet remains challenging due to the complex interplay of design factors and rapid hardware evolution. Existing automated approaches typically treat Large Language Models (LLMs) merely as stochastic code generators within heuristic-guided evolutionary loops. These methods often struggle with complex kernels requiring coordinated, multi-step structural transformations, as they lack explicit planning capabilities and frequently discard promising strategies due to inefficient or incorrect intermediate implementations. To address this, we propose Search via Co-Evolving World Model and build K-Search based on this method. By replacing static search heuristics with a co-evolving world model, our framework leverages LLMs' prior domain knowledge to guide the search, actively exploring the optimization space. This approach explicitly decouples high-level algorithmic planning from low-level program instantiation, enabling the system to navigate non-monotonic optimization paths while remaining resilient to temporary implementation defects. We evaluate K-Search on diverse, complex kernels from FlashInfer, including GQA, MLA, and MoE kernels. Our results show that K-Search significantly outperforms state-of-the-art evolutionary search methods, achieving an average 2.10x improvement and up to a 14.3x gain on complex MoE kernels. On the GPUMode TriMul task, K-Search achieves state-of-the-art performance on H100, reaching 1030us and surpassing both prior evolution and human-designed solutions. --- ### AgenticRAGTracer: A Hop-Aware Benchmark for Diagnosing Multi-Step Retrieval Reasoning in Agentic RAG Authors: Qijie You, Wenkai Yu, Wentao Zhang Published: 2026-02-22 Categories: cs.CL arXiv: https://arxiv.org/abs/2602.19127v2 With the rapid advancement of agent-based methods in recent years, Agentic RAG has undoubtedly become an important research direction. Multi-hop reasoning, which requires models to engage in deliberate thinking and multi-step interaction, serves as a critical testbed for assessing such capabilities. However, existing benchmarks typically provide only final questions and answers, while lacking the intermediate hop-level questions that gradually connect atomic questions to the final multi-hop query. This limitation prevents researchers from analyzing at which step an agent fails and restricts more fine-grained evaluation of model capabilities. Moreover, most current benchmarks are manually constructed, which is both time-consuming and labor-intensive, while also limiting scalability and generalization. To address these challenges, we introduce AgenticRAGTracer, the first Agentic RAG benchmark that is primarily constructed automatically by large language models and designed to support step-by-step validation. Our benchmark spans multiple domains, contains 1,305 data points, and has no overlap with existing mainstream benchmarks. Extensive experiments demonstrate that even the best large language models perform poorly on our dataset. For instance, GPT-5 attains merely 22.6\% EM accuracy on the hardest portion of our dataset. Hop-aware diagnosis reveals that failures are primarily driven by distorted reasoning chains -- either collapsing prematurely or wandering into over-extension. This highlights a critical inability to allocate steps consistent with the task's logical structure, providing a diagnostic dimension missing in traditional evaluations. We believe our work will facilitate research in Agentic RAG and inspire further meaningful progress in this area. Our code and data are available at https://github.com/YqjMartin/AgenticRAGTracer. --- ### Robust Predictive Uncertainty and Double Descent in Contaminated Bayesian Random Features Authors: Michele Caprio, Katerina Papagiannouli, Siu Lun Chau, Sayan Mukherjee Published: 2026-02-22 Categories: cs.LG, math.PR, math.ST arXiv: https://arxiv.org/abs/2602.19126v2 We propose a robust Bayesian formulation of random feature (RF) regression that accounts explicitly for prior and likelihood misspecification via Huber-style contamination sets. Starting from the classical equivalence between ridge-regularized RF training and Bayesian inference with Gaussian priors and likelihoods, we replace the single prior and likelihood with $ε$- and $η$-contaminated credal sets, respectively, and perform inference using pessimistic generalized Bayesian updating. We derive explicit and tractable bounds for the resulting lower and upper posterior predictive densities. These bounds show that, when contamination is moderate, prior and likelihood ambiguity effectively acts as a direct contamination of the posterior predictive distribution, yielding uncertainty envelopes around the classical Gaussian predictive. We introduce an Imprecise Highest Density Region (IHDR) for robust predictive uncertainty quantification and show that it admits an efficient approximation via an adjusted Gaussian credible interval. We further obtain predictive variance bounds (under a mild truncation approximation for the upper bound) and prove that they preserve the leading-order proportional-growth asymptotics known for RF models. Together, these results establish a robustness theory for Bayesian random features: predictive uncertainty remains computationally tractable, inherits the classical double-descent phase structure, and is improved by explicit worst-case guarantees under bounded prior and likelihood misspecification. --- ### StreetTree: A Large-Scale Global Benchmark for Fine-Grained Tree Species Classification Authors: Jiapeng Li, Yingjing Huang, Fan Zhang, Yu liu Published: 2026-02-22 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.19123v2 The fine grained classification of street trees is a crucial task for urban planning, streetscape management, and the assessment of urban ecosystem services. However, progress in this field has been hindered by the lack of large scale, geographically diverse, and publicly available benchmark datasets specifically designed for street trees. To address this critical gap, we introduce StreetTree, the world's first large scale benchmark dataset dedicated to fine grained street tree classification. The dataset contains over 12 million images covering more than 8,300 common street tree species, collected from urban streetscapes across 133 countries spanning five continents, and supplemented with expert verified observational data. StreetTree poses challenges for pretrained vision models under complex urban environments including high inter species visual similarity, long tailed natural distributions, significant intra class variations caused by seasonal changes, and diverse imaging conditions such as lighting, occlusions from buildings, and varying camera angles. In addition, we provide a hierarchical taxonomy (order, family, genus, and species) to support research in hierarchical classification and representation learning. Through extensive experiments with various vision models, we establish solid baselines and reveal the limitations of existing methods in handling such real world complexities. We believe that StreetTree will serve as a key resource for driving new advancements at the intersection of computer vision and urban science. --- ### Keep it SymPL: Symbolic Projective Layout for Allocentric Spatial Reasoning in Vision-Language Models Authors: Jaeyun Jang, Seunghui Shin, Taeho Park, Hyoseok Hwang Published: 2026-02-22 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.19117v2 Perspective-aware spatial reasoning involves understanding spatial relationships from specific viewpoints-either egocentric (observer-centered) or allocentric (object-centered). While vision-language models (VLMs) perform well in egocentric settings, their performance deteriorates when reasoning from allocentric viewpoints, where spatial relations must be inferred from the perspective of objects within the scene. In this study, we address this underexplored challenge by introducing Symbolic Projective Layout (SymPL), a framework that reformulates allocentric reasoning into symbolic-layout forms that VLMs inherently handle well. By leveraging four key factors-projection, abstraction, bipartition, and localization-SymPL converts allocentric questions into structured symbolic-layout representations. Extensive experiments demonstrate that this reformulation substantially improves performance in both allocentric and egocentric tasks, enhances robustness under visual illusions and multi-view scenarios, and that each component contributes critically to these gains. These results show that SymPL provides an effective and principled approach for addressing complex perspective-aware spatial reasoning. --- ### Event-Triggered Gossip for Distributed Learning Authors: Zhiyuan Zhai, Xiaojun Yuan, Wei Ni, Xin Wang, Rui Zhang, Geoffrey Ye Li Published: 2026-02-22 Categories: eess.SP, cs.LG arXiv: https://arxiv.org/abs/2602.19116v1 While distributed learning offers a new learning paradigm for distributed network with no central coordination, it is constrained by communication bottleneck between nodes. We develop a new event-triggered gossip framework for distributed learning to reduce inter-node communication overhead. The framework introduces an adaptive communication control mechanism that enables each node to autonomously decide in a fully decentralized fashion when to exchange model information with its neighbors based on local model deviations. We analyze the ergodic convergence of the proposed framework under noconvex objectives and interpret the convergence guarantees under different triggering conditions. Simulation results show that the proposed framework achieves substantially lower communication overhead than the state-of-the-art distributed learning methods, reducing cumulative point-to-point transmissions by \textbf{71.61\%} with only a marginal performance loss, compared with the conventional full-communication baseline. --- ### How Do LLMs Encode Scientific Quality? An Empirical Study Using Monosemantic Features from Sparse Autoencoders Authors: Michael McCoubrey, Angelo Salatino, Francesco Osborne, Enrico Motta Published: 2026-02-22 Categories: cs.CL, cs.AI, cs.DL arXiv: https://arxiv.org/abs/2602.19115v1 In recent years, there has been a growing use of generative AI, and large language models (LLMs) in particular, to support both the assessment and generation of scientific work. Although some studies have shown that LLMs can, to a certain extent, evaluate research according to perceived quality, our understanding of the internal mechanisms that enable this capability remains limited. This paper presents the first study that investigates how LLMs encode the concept of scientific quality through relevant monosemantic features extracted using sparse autoencoders. We derive such features under different experimental settings and assess their ability to serve as predictors across three tasks related to research quality: predicting citation count, journal SJR, and journal h-index. The results indicate that LLMs encode features associated with multiple dimensions of scientific quality. In particular, we identify four recurring types of features that capture key aspects of how research quality is represented: 1) features reflecting research methodologies; 2) features related to publication type, with literature reviews typically exhibiting higher impact; 3) features associated with high-impact research fields and technologies; and 4) features corresponding to specific scientific jargons. These findings represent an important step toward understanding how LLMs encapsulate concepts related to research quality. --- ### Kaiwu-PyTorch-Plugin: Bridging Deep Learning and Photonic Quantum Computing for Energy-Based Models and Active Sample Selection Authors: Hongdong Zhu, Qi Gao, Yin Ma, Shaobo Chen, Haixu Liu, Fengao Wang, Tinglan Wang, Chang Wu, Kai Wen Published: 2026-02-22 Categories: quant-ph, cs.AI arXiv: https://arxiv.org/abs/2602.19114v1 This paper introduces the Kaiwu-PyTorch-Plugin (KPP) to bridge Deep Learning and Photonic Quantum Computing across multiple dimensions. KPP integrates the Coherent Ising Machine into the PyTorch ecosystem, addressing classical inefficiencies in Energy-Based Models. The framework facilitates quantum integration in three key aspects: accelerating Boltzmann sampling, optimizing training data via Active Sampling, and constructing hybrid architectures like QBM-VAE and Q-Diffusion. Empirical results on single-cell and OpenWebText datasets demonstrate KPPs ability to achieve SOTA performance, validating a comprehensive quantum-classical paradigm. --- ### Learning from Complexity: Exploring Dynamic Sample Pruning of Spatio-Temporal Training Authors: Wei Chen, Junle Chen, Yuqian Wu, Yuxuan Liang, Xiaofang Zhou Published: 2026-02-22 Categories: cs.LG, cs.AI, stat.ML arXiv: https://arxiv.org/abs/2602.19113v2 Spatio-temporal forecasting is fundamental to intelligent systems in transportation, climate science, and urban planning. However, training deep learning models on the massive, often redundant, datasets from these domains presents a significant computational bottleneck. Existing solutions typically focus on optimizing model architectures or optimizers, while overlooking the inherent inefficiency of the training data itself. This conventional approach of iterating over the entire static dataset each epoch wastes considerable resources on easy-to-learn or repetitive samples. In this paper, we explore a novel training-efficiency techniques, namely learning from complexity with dynamic sample pruning, ST-Prune, for spatio-temporal forecasting. Through dynamic sample pruning, we aim to intelligently identify the most informative samples based on the model's real-time learning state, thereby accelerating convergence and improving training efficiency. Extensive experiments conducted on real-world spatio-temporal datasets show that ST-Prune significantly accelerates the training speed while maintaining or even improving the model performance, and it also has scalability and universality. --- ### Universal 3D Shape Matching via Coarse-to-Fine Language Guidance Authors: Qinfeng Xiao, Guofeng Mei, Bo Yang, Liying Zhang, Jian Zhang, Kit-lun Yick Published: 2026-02-22 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.19112v3 Establishing dense correspondences between shapes is a crucial task in computer vision and graphics, while prior approaches depend on near-isometric assumptions and homogeneous subject types (i.e., only operate for human shapes). However, building semantic correspondences for cross-category objects remains challenging and has received relatively little attention. To achieve this, we propose UniMatch, a semantic-aware, coarse-to-fine framework for constructing dense semantic correspondences between strongly non-isometric shapes without restricting object categories. The key insight is to lift "coarse" semantic cues into "fine" correspondence, which is achieved through two stages. In the "coarse" stage, we perform class-agnostic 3D segmentation to obtain non-overlapping semantic parts and prompt multimodal large language models (MLLMs) to identify part names. Then, we employ pretrained vision language models (VLMs) to extract text embeddings, enabling the construction of matched semantic parts. In the "fine" stage, we leverage these coarse correspondences to guide the learning of dense correspondences through a dedicated rank-based contrastive scheme. Thanks to class-agnostic segmentation, language guiding, and rank-based contrastive learning, our method is versatile for universal object categories and requires no predefined part proposals, enabling universal matching for inter-class and non-isometric shapes. Extensive experiments demonstrate UniMatch consistently outperforms competing methods in various challenging scenarios. --- ### Astra: Activation-Space Tail-Eigenvector Low-Rank Adaptation of Large Language Models Authors: Kainan Liu, Yong Zhang, Ning Cheng, Yun Zhu, Yanmeng Wang, Shaojun Wang, Jing Xiao Published: 2026-02-22 Categories: cs.CL arXiv: https://arxiv.org/abs/2602.19111v1 Parameter-Efficient Fine-Tuning (PEFT) methods, especially LoRA, are widely used for adapting pre-trained models to downstream tasks due to their computational and storage efficiency. However, in the context of LoRA and its variants, the potential of activation subspaces corresponding to tail eigenvectors remains substantially under-exploited, which may lead to suboptimal fine-tuning performance. In this work, we propose Astra (Activation-Space Tail-Eigenvector Low-Rank Adaptation), a novel PEFT method that leverages the tail eigenvectors of the model output activations-estimated from a small task-specific calibration set-to construct task-adaptive low-rank adapters. By constraining updates to the subspace spanned by these tail eigenvectors, Astra achieves faster convergence and improved downstream performance with a significantly reduced parameter budget. Extensive experiments across natural language understanding (NLU) and natural language generation (NLG) tasks demonstrate that Astra consistently outperforms existing PEFT baselines across 16 benchmarks and even surpasses full fine-tuning (FFT) in certain scenarios. --- ### Post-Routing Arithmetic in Llama-3: Last-Token Result Writing and Rotation-Structured Digit Directions Authors: Yao Yan Published: 2026-02-22 Categories: cs.AI arXiv: https://arxiv.org/abs/2602.19109v1 We study three-digit addition in Meta-Llama-3-8B (base) under a one-token readout to characterize how arithmetic answers are finalized after cross-token routing becomes causally irrelevant. Causal residual patching and cumulative attention ablations localize a sharp boundary near layer~17: beyond it, the decoded sum is controlled almost entirely by the last input token and late-layer self-attention is largely dispensable. In this post-routing regime, digit(-sum) direction dictionaries vary with a next-higher-digit context but are well-related by an approximately orthogonal map inside a shared low-rank subspace (low-rank Procrustes alignment). Causal digit editing matches this geometry: naive cross-context transfer fails, while rotating directions through the learned map restores strict counterfactual edits; negative controls do not recover. --- ### Value Entanglement: Conflation Between Different Kinds of Good In (Some) Large Language Models Authors: Seong Hah Cho, Junyi Li, Anna Leshinskaya Published: 2026-02-22 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2602.19101v2 Value alignment of Large Language Models (LLMs) requires us to empirically measure these models' actual, acquired representation of value. Among the characteristics of value representation in humans is that they distinguish among value of different kinds. We investigate whether LLMs likewise distinguish three different kinds of good: moral, grammatical, and economic. By probing model behavior, embeddings, and residual stream activations, we report pervasive cases of value entanglement: a conflation between these distinct representations of value. Specifically, both grammatical and economic valuation was found to be overly influenced by moral value, relative to human norms. This conflation was repaired by selective ablation of the activation vectors associated with morality. --- ### The Power of Decaying Steps: Enhancing Attack Stability and Transferability for Sign-based Optimizers Authors: Wei Tao, Yang Dai, Jincai Huang, Qing Tao Published: 2026-02-22 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.19096v2 Crafting adversarial examples can be formulated as an optimization problem. While sign-based optimizers such as I-FGSM and MI-FGSM have become the de facto standard for the induced optimization problems, there still exist several unsolved problems in theoretical grounding and practical reliability especially in non-convergence and instability, which inevitably influences their transferability. Contrary to the expectation, we observe that the attack success rate may degrade sharply when more number of iterations are conducted. In this paper, we address these issues from an optimization perspective. By reformulating the sign-based optimizer as a specific coordinate-wise gradient descent, we argue that one cause for non-convergence and instability is their non-decaying step-size scheduling. Based upon this viewpoint, we propose a series of new attack algorithms that enforce Monotonically Decreasing Coordinate-wise Step-sizes (MDCS) within sign-based optimizers. Typically, we further provide theoretical guarantees proving that MDCS-MI attains an optimal convergence rate of $O(1/\sqrt{T})$, where $T$ is the number of iterations. Extensive experiments on image classification and cross-modal retrieval tasks demonstrate that our approach not only significantly improves transferability but also enhances attack stability compared to state-of-the-art sign-based methods. --- ### RKHS Representation of Algebraic Convolutional Filters with Integral Operators Authors: Alejandro Parada-Mayorga, Alejandro Ribeiro, Juan Bazerque Published: 2026-02-22 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.19094v1 Integral operators play a central role in signal processing, underpinning classical convolution, and filtering on continuous network models such as graphons. While these operators are traditionally analyzed through spectral decompositions, their connection to reproducing kernel Hilbert spaces (RKHS) has not been systematically explored within the algebraic signal processing framework. In this paper, we develop a comprehensive theory showing that the range of integral operators naturally induces RKHS convolutional signal models whose reproducing kernels are determined by a box product of the operator symbols. We characterize the algebraic and spectral properties of these induced RKHS and show that polynomial filtering with integral operators corresponds to iterated box products, giving rise to a unital kernel algebra. This perspective yields pointwise RKHS representations of filters via the reproducing property, providing an alternative to operator-based implementations. Our results establish precise connections between eigendecompositions and RKHS representations in graphon signal processing, extend naturally to directed graphons, and enable novel spatial--spectral localization results. Furthermore, we show that when the spectral domain is a subset of the original domain of the signals, optimal filters for regularized learning problems admit finite-dimensional RKHS representations, providing a principled foundation for learnable filters in integral-operator-based neural architectures. --- ### CREM: Compression-Driven Representation Enhancement for Multimodal Retrieval and Comprehension Authors: Lihao Liu, Yan Wang, Biao Yang, Da Li, Jiangxia Cao, Yuxiao Luo, Xiang Chen, Xiangyu Wu, Wei Yuan, Fan Yang, Guiguang Ding, Tingting Gao et al. Published: 2026-02-22 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.19091v1 Multimodal Large Language Models (MLLMs) have shown remarkable success in comprehension tasks such as visual description and visual question answering. However, their direct application to embedding-based tasks like retrieval remains challenging due to the discrepancy between output formats and optimization objectives. Previous approaches often employ contrastive fine-tuning to adapt MLLMs for retrieval, but at the cost of losing their generative capabilities. We argue that both generative and embedding tasks fundamentally rely on shared cognitive mechanisms, specifically cross-modal representation alignment and contextual comprehension. To this end, we propose CREM (Compression-driven Representation Enhanced Model), with a unified framework that enhances multimodal representations for retrieval while preserving generative ability. Specifically, we introduce a compression-based prompt design with learnable chorus tokens to aggregate multimodal semantics and a compression-driven training strategy that integrates contrastive and generative objectives through compression-aware attention. Extensive experiments demonstrate that CREM achieves state-of-the-art retrieval performance on MMEB while maintaining strong generative performance on multiple comprehension benchmarks. Our findings highlight that generative supervision can further improve the representational quality of MLLMs under the proposed compression-driven paradigm. --- ### Ani3DHuman: Photorealistic 3D Human Animation with Self-guided Stochastic Sampling Authors: Qi Sun, Can Wang, Jiaxiang Shang, Yingchun Liu, Jing Liao Published: 2026-02-22 Categories: cs.CV, cs.GR, cs.LG arXiv: https://arxiv.org/abs/2602.19089v1 Current 3D human animation methods struggle to achieve photorealism: kinematics-based approaches lack non-rigid dynamics (e.g., clothing dynamics), while methods that leverage video diffusion priors can synthesize non-rigid motion but suffer from quality artifacts and identity loss. To overcome these limitations, we present Ani3DHuman, a framework that marries kinematics-based animation with video diffusion priors. We first introduce a layered motion representation that disentangles rigid motion from residual non-rigid motion. Rigid motion is generated by a kinematic method, which then produces a coarse rendering to guide the video diffusion model in generating video sequences that restore the residual non-rigid motion. However, this restoration task, based on diffusion sampling, is highly challenging, as the initial renderings are out-of-distribution, causing standard deterministic ODE samplers to fail. Therefore, we propose a novel self-guided stochastic sampling method, which effectively addresses the out-of-distribution problem by combining stochastic sampling (for photorealistic quality) with self-guidance (for identity fidelity). These restored videos provide high-quality supervision, enabling the optimization of the residual non-rigid motion field. Extensive experiments demonstrate that \MethodName can generate photorealistic 3D human animation, outperforming existing methods. Code is available in https://github.com/qiisun/ani3dhuman. --- ### Detecting Cybersecurity Threats by Integrating Explainable AI with SHAP Interpretability and Strategic Data Sampling Authors: Norrakith Srisumrith, Sunantha Sodsee Published: 2026-02-22 Categories: cs.CR, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2602.19087v1 The critical need for transparent and trustworthy machine learning in cybersecurity operations drives the development of this integrated Explainable AI (XAI) framework. Our methodology addresses three fundamental challenges in deploying AI for threat detection: handling massive datasets through Strategic Sampling Methodology that preserves class distributions while enabling efficient model development; ensuring experimental rigor via Automated Data Leakage Prevention that systematically identifies and removes contaminated features; and providing operational transparency through Integrated XAI Implementation using SHAP analysis for model-agnostic interpretability across algorithms. Applied to the CIC-IDS2017 dataset, our approach maintains detection efficacy while reducing computational overhead and delivering actionable explanations for security analysts. The framework demonstrates that explainability, computational efficiency, and experimental integrity can be simultaneously achieved, providing a robust foundation for deploying trustworthy AI systems in security operations centers where decision transparency is paramount. --- ### A Multi-Stage Framework for Kuzushiji Character Recognition in Japanese Historical Documents Authors: Rui-Yang Ju, Kohei Yamashita, Hirotaka Kameko, Shinsuke Mori Published: 2026-02-22 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.19086v3 Kuzushiji was a widely used cursive writing system in pre-modern Japan. Due to simplification and glyph variation, most modern Japanese readers cannot read Kuzushiji characters. Consequently, recent studies have developed optical character recognition (OCR) systems for Kuzushiji. Despite recent progress, Kuzushiji character recognition (KCR) in Japanese historical documents remains challenging because of seal-character overlap and complex layouts, which interfere with character recognition and hinder accurate reconstruction of the reading order. To address these challenges, we propose a multi-stage KCR framework comprising character detection, cropping, classification, ordering, and large language model (LLM)-based post-OCR correction. Specifically, we employ a synthetic data augmentation strategy to improve character detection robustness against seal interference and introduce an adaptive column clustering algorithm to reconstruct the reading order. Finally, we leverage the contextual capabilities of the LLM to correct OCR errors. In addition, we correct annotation omissions, reconstruct the benchmark dataset, and introduce a synthetic test set with simulated seal interference and an out-of-domain (OOD) test set for evaluation. Compared with the conventional character-level OCR baseline, our framework achieves relative CER reductions of 43.48%, 46.02%, and 39.11% on the real, synthetic, and OOD test sets, respectively. --- ### Seal-Robust KCR: A Robust Kuzushiji Character Recognition Framework under Seal Interference Authors: Rui-Yang Ju, Kohei Yamashita, Hirotaka Kameko, Shinsuke Mori Published: 2026-02-22 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.19086v2 Kuzushiji was one of the most widely used cursive writing systems in pre-modern Japan. Due to its highly cursive forms and extensive glyph variations, most modern Japanese readers are unable to read Kuzushiji characters. Consequently, recent studies have focused on developing automated Kuzushiji character recognition (KCR) methods, which have achieved strong performance on relatively clean Japanese historical document images. Although seals frequently appear in Japanese historical documents, existing methods often fail to maintain recognition accuracy under seal interference, particularly when seals overlap with characters. To address this challenge, we propose a seal-robust KCR framework. Based on character detection, classification, and ordering, the proposed framework additionally incorporates document restoration to mitigate seal interference, thereby improving overall recognition performance. In addition, we introduce a novel synthetic data augmentation strategy to enhance the performance of character detection models. We further correct annotation errors, reconstruct the dataset, and create a synthetic test set to simulate severe seal interference. Experimental results demonstrate the effectiveness of the proposed framework in mitigating the impact of seal interference on KCR. Compared with a conventional baseline and NDLkotenOCR, it achieves relative character error rate (CER) reductions of 39.7% and 5.9%, respectively, on the real test set, and 50.1% and 41.7%, respectively, on the synthetic test set. --- ### ChordEdit: One-Step Low-Energy Transport for Image Editing Authors: Liangsi Lu, Xuhang Chen, Minzhe Guo, Shichu Li, Jingchao Wang, Yang Shi Published: 2026-02-22 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.19083v2 The advent of one-step text-to-image (T2I) models offers unprecedented synthesis speed. However, their application to text-guided image editing remains severely hampered, as forcing existing training-free editors into a single inference step fails. This failure manifests as severe object distortion and a critical loss of consistency in non-edited regions, resulting from the high-energy, erratic trajectories produced by naive vector arithmetic on the models' structured fields. To address this problem, we introduce ChordEdit, a model agnostic, training-free, and inversion-free method that facilitates high-fidelity one-step editing. We recast editing as a transport problem between the source and target distributions defined by the source and target text prompts. Leveraging dynamic optimal transport theory, we derive a principled, low-energy control strategy. This strategy yields a smoothed, variance-reduced editing field that is inherently stable, facilitating the field to be traversed in a single, large integration step. A theoretically grounded and experimentally validated approach allows ChordEdit to deliver fast, lightweight and precise edits, finally achieving true real-time editing on these challenging models. --- ### TriTopic: Tri-Modal Graph-Based Topic Modeling with Iterative Refinement and Archetypes Authors: Roman Egger Published: 2026-02-22 Categories: cs.CL arXiv: https://arxiv.org/abs/2602.19079v1 Topic modeling extracts latent themes from large text collections, but leading approaches like BERTopic face critical limitations: stochastic instability, loss of lexical precision ("Embedding Blur"), and reliance on a single data perspective. We present TriTopic, a framework that addresses these weaknesses through a tri-modal graph fusing semantic embeddings, TF-IDF, and metadata. Three core innovations drive its performance: hybrid graph construction via Mutual kNN and Shared Nearest Neighbors to eliminate noise and combat the curse of dimensionality; Consensus Leiden Clustering for reproducible, stable partitions; and Iterative Refinement that sharpens embeddings through dynamic centroid-pulling. TriTopic also replaces the "average document" concept with archetype-based topic representations defined by boundary cases rather than centers alone. In benchmarks across 20 Newsgroups, BBC News, AG News, and Arxiv, TriTopic achieves the highest NMI on every dataset (mean NMI 0.575 vs. 0.513 for BERTopic, 0.416 for NMF, 0.299 for LDA), guarantees 100% corpus coverage with 0% outliers, and is available as an open-source PyPI library. --- ### Defining Explainable AI for Requirements Analysis Authors: Raymond Sheh, Isaac Monteath Published: 2026-02-22 Categories: cs.AI arXiv: https://arxiv.org/abs/2602.19071v1 Explainable Artificial Intelligence (XAI) has become popular in the last few years. The Artificial Intelligence (AI) community in general, and the Machine Learning (ML) community in particular, is coming to the realisation that in many applications, for AI to be trusted, it must not only demonstrate good performance in its decisionmaking, but it also must explain these decisions and convince us that it is making the decisions for the right reasons. However, different applications have different requirements on the information required of the underlying AI system in order to convince us that it is worthy of our trust. How do we define these requirements? In this paper, we present three dimensions for categorising the explanatory requirements of different applications. These are Source, Depth and Scope. We focus on the problem of matching up the explanatory requirements of different applications with the capabilities of underlying ML techniques to provide them. We deliberately avoid including aspects of explanation that are already well-covered by the existing literature and we focus our discussion on ML although the principles apply to AI more broadly. --- ### Asking the Right Questions: Improving Reasoning with Generated Stepping Stones Authors: Hengyuan Hu, Tingchen Fu, Minqi Jiang, Alexander H Miller, Yoram Bachrach, Jakob Nicolaus Foerster Published: 2026-02-22 Categories: cs.AI arXiv: https://arxiv.org/abs/2602.19069v2 Recent years have witnessed tremendous progress in enabling LLMs to solve complex reasoning tasks such as math and coding. As we start to apply LLMs to harder tasks that they may not be able to solve in one shot, it is worth paying attention to their ability to construct intermediate stepping stones that prepare them to better solve the tasks. Examples of stepping stones include simplifications, alternative framings, or subproblems. We study properties and benefits of stepping stones in the context of modern reasoning LLMs via ARQ (Asking the Right Questions), a simple framework that introduces a question generator to the default reasoning pipeline. We first show that good stepping stone questions exist and are transferrable, meaning that good questions can be generated, and they substantially help LLMs of various capabilities in solving the target tasks. We next frame stepping stone generation as a post-training task and show that we can fine-tune LLMs to generate more useful stepping stones by SFT and RL on synthetic data. --- ### TimeRadar: A Domain-Rotatable Foundation Model for Time Series Anomaly Detection Authors: Hui He, Hezhe Qiao, Yutong Chen, Kun Yi, Guansong Pang Published: 2026-02-22 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.19068v1 Current time series foundation models (TSFMs) primarily focus on learning prevalent and regular patterns within a predefined time or frequency domain to enable supervised downstream tasks (e.g., forecasting). Consequently, they are often ineffective for inherently unsupervised downstream tasks-such as time series anomaly detection (TSAD), which aims to identify rare, irregular patterns. This limitation arises because such abnormal patterns can closely resemble the regular patterns when presented in the same time/frequency domain. To address this issue, we introduce TimeRadar, an innovative TSFM built in a fractional time-frequency domain to support generalist TSAD across diverse unseen datasets. Our key insight is that rotating a time series into a data-dependent fractional time-frequency representation can adaptively differentiate the normal and abnormal signals across different datasets. To this end, a novel component, namely Fractionally modulated Time-Frequency Reconstruction (FTFRecon), is proposed in TimeRadar to leverage a learnable fractional order to rotate the time series to the most pronounced angle between a continuous time and frequency domain for accurate data reconstruction. This provides adaptive data reconstruction in an optimal time-frequency domain for each data input, enabling effective differentiation of the unbounded abnormal patterns from the regular ones across datasets, including unseen datasets. To allow TimeRadar to model local abnormality that is not captured by the global data reconstruction, we further introduce a Contextual Deviation Learning (CDL) component to model the local deviation of the input relative to its contextual time series data in the rotatable domain. --- ### IDLM: Inverse-distilled Diffusion Language Models Authors: David Li, Nikita Gushchin, Dmitry Abulkhanov, Eric Moulines, Ivan Oseledets, Maxim Panov, Alexander Korotin Published: 2026-02-22 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2602.19066v2 Diffusion Language Models (DLMs) have recently achieved strong results in text generation. However, their multi-step sampling leads to slow inference, limiting practical use. To address this, we extend Inverse Distillation, a technique originally developed to accelerate continuous diffusion models, to the discrete setting. Nonetheless, this extension introduces both theoretical and practical challenges. From a theoretical perspective, the inverse distillation objective lacks uniqueness guarantees, which may lead to suboptimal solutions. From a practical standpoint, backpropagation in the discrete space is non-trivial and often unstable. To overcome these challenges, we first provide a theoretical result demonstrating that our inverse formulation admits a unique solution, thereby ensuring valid optimization. We then introduce gradient-stable relaxations to support effective training. As a result, experiments on multiple DLMs show that our method, Inverse-distilled Diffusion Language Models (IDLM), reduces the number of inference steps by 4x-64x, while preserving the teacher model's generation quality. We provide the code, model checkpoints, and video tutorials on the project page: https://david-cripto.github.io/idlm-project-page --- ### Agentic Problem Frames: A Systematic Approach to Engineering Reliable Domain Agents Authors: Chanjin Park Published: 2026-02-22 Categories: cs.AI arXiv: https://arxiv.org/abs/2602.19065v1 Large Language Models (LLMs) are evolving into autonomous agents, yet current "frameless" development--relying on ambiguous natural language without engineering blueprints--leads to critical risks such as scope creep and open-loop failures. To ensure industrial-grade reliability, this study proposes Agentic Problem Frames (APF), a systematic engineering framework that shifts focus from internal model intelligence to the structured interaction between the agent and its environment. The APF establishes a dynamic specification paradigm where intent is concretized at runtime through domain knowledge injection. At its core, the Act-Verify-Refine (AVR) loop functions as a closed-loop control system that transforms execution results into verified knowledge assets, driving system behavior toward asymptotic convergence to mission requirements (R). To operationalize this, this study introduces the Agentic Job Description (AJD), a formal specification tool that defines jurisdictional boundaries, operational contexts, and epistemic evaluation criteria. The efficacy of this framework is validated through two contrasting case studies: a delegated proxy model for business travel and an autonomous supervisor model for industrial equipment management. By applying AJD-based specification and APF modeling to these scenarios, the analysis demonstrates how operational scenarios are systematically controlled within defined boundaries. These cases provide a conceptual proof that agent reliability stems not from a model's internal reasoning alone, but from the rigorous engineering structures that anchor stochastic AI within deterministic business processes, thereby enabling the development of verifiable and dependable domain agents. --- ### L3DR: 3D-aware LiDAR Diffusion and Rectification Authors: Quan Liu, Xiaoqin Zhang, Ling Shao, Shijian Lu Published: 2026-02-22 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.19064v1 Range-view (RV) based LiDAR diffusion has recently made huge strides towards 2D photo-realism. However, it neglects 3D geometry realism and often generates various RV artifacts such as depth bleeding and wavy surfaces. We design L3DR, a 3D-aware LiDAR Diffusion and Rectification framework that can regress and cancel RV artifacts in 3D space and restore local geometry accurately. Our theoretical and empirical analysis reveals that 3D models are inherently superior to 2D models in generating sharp and authentic boundaries. Leveraging such analysis, we design a 3D residual regression network that rectifies RV artifacts and achieves superb geometry realism by predicting point-level offsets in 3D space. On top of that, we design a Welsch Loss that helps focus on local geometry and ignore anomalous regions effectively. Extensive experiments over multiple benchmarks including KITTI, KITTI360, nuScenes and Waymo show that the proposed L3DR achieves state-of-the-art generation and superior geometry-realism consistently. In addition, L3DR is generally applicable to different LiDAR diffusion models with little computational overhead. --- ### Direction-aware 3D Large Multimodal Models Authors: Quan Liu, Weihao Xuan, Junjue Wang, Naoto Yokoya, Ling Shao, Shijian Lu Published: 2026-02-22 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.19063v1 3D large multimodal models (3D LMMs) rely heavily on ego poses for enabling directional question-answering and spatial reasoning. However, most existing point cloud benchmarks contain rich directional queries but lack the corresponding ego poses, making them inherently ill-posed in 3D large multimodal modelling. In this work, we redefine a new and rigorous paradigm that enables direction-aware 3D LMMs by identifying and supplementing ego poses into point cloud benchmarks and transforming the corresponding point cloud data according to the identified ego poses. We enable direction-aware 3D LMMs with two novel designs. The first is PoseRecover, a fully automatic pose recovery pipeline that matches questions with ego poses from RGB-D video extrinsics via object-frustum intersection and visibility check with Z-buffers. The second is PoseAlign that transforms the point cloud data to be aligned with the identified ego poses instead of either injecting ego poses into textual prompts or introducing pose-encoded features in the projection layers. Extensive experiments show that our designs yield consistent improvements across multiple 3D LMM backbones such as LL3DA, LL3DA-SONATA, Chat-Scene, and 3D-LLAVA, improving ScanRefer mIoU by 30.0% and Scan2Cap LLM-as-judge accuracy by 11.7%. In addition, our approach is simple, generic, and training-efficient, requiring only instruction tuning while establishing a strong baseline for direction-aware 3D-LMMs. --- ### Do LLMs and VLMs Share Neurons for Inference? Evidence and Mechanisms of Cross-Modal Transfer Authors: Chenhang Cui, An Zhang, Yuxin Chen, Gelei Deng, Jingnan Zheng, Zhenkai Liang, Xiang Wang, Tat-Seng Chua Published: 2026-02-22 Categories: cs.CL arXiv: https://arxiv.org/abs/2602.19058v1 Large vision-language models (LVLMs) have rapidly advanced across various domains, yet they still lag behind strong text-only large language models (LLMs) on tasks that require multi-step inference and compositional decision-making. Motivated by their shared transformer architectures, we investigate whether the two model families rely on common internal computation for such inference. At the neuron level, we uncover a surprisingly large overlap: more than half of the top-activated units during multi-step inference are shared between representative LLMs and LVLMs, revealing a modality-invariant inference subspace. Through causal probing via activation amplification, we further show that these shared neurons encode consistent and interpretable concept-level effects, demonstrating their functional contribution to inference. Building on this insight, we propose Shared Neuron Low-Rank Fusion (SNRF), a parameter-efficient framework that transfers mature inference circuitry from LLMs to LVLMs. SNRF profiles cross-model activations to identify shared neurons, computes a low-rank approximation of inter-model weight differences, and injects these updates selectively within the shared-neuron subspace. This mechanism strengthens multimodal inference performance with minimal parameter changes and requires no large-scale multimodal fine-tuning. Across diverse mathematics and perception benchmarks, SNRF consistently enhances LVLM inference performance while preserving perceptual capabilities. Our results demonstrate that shared neurons form an interpretable bridge between LLMs and LVLMs, enabling low-cost transfer of inference ability into multimodal models. Our code is available at (https://github.com/chenhangcuisg-code/Do-LLMs-VLMs-Share-Neurons)(https://github.com/chenhangcuisg-code/Do-LLMs-VLMs-Share-Neurons). --- ### Automated Disentangling Analysis of Skin Colour for Lesion Images Authors: Wenbo Yang, Eman Rezk, Walaa M. Moursi, Zhou Wang Published: 2026-02-22 Categories: eess.IV, cs.CV arXiv: https://arxiv.org/abs/2602.19055v2 Machine-learning models applied to skin images often have degraded performance when the skin colour captured in images (SCCI) differs between training and deployment. These discrepancies arise from a combination of entangled environmental factors (e.g., illumination, camera settings) and intrinsic factors (e.g., skin tone) that cannot be accurately described by a single "skin tone" scalar -- a simplification commonly adopted by prior work. To mitigate such colour mismatches, we propose a skin-colour disentangling framework that adapts disentanglement-by-compression to learn a structured, manipulable latent space for SCCI from unlabelled dermatology images. To prevent information leakage that hinders proper learning of dark colour features, we introduce a randomized, mostly monotonic decolourization mapping. To suppress unintended colour shifts of localized patterns (e.g., ink marks, scars) during colour manipulation, we further propose a geometry-aligned post-processing step. Together, these components enable faithful counterfactual editing and answering an essential question: "What would this skin condition look like under a different SCCI?", as well as direct colour transfer between images and controlled traversal along physically meaningful directions (e.g., blood perfusion, camera white balance), enabling educational visualization of skin conditions under varying SCCI. We demonstrate that dataset-level augmentation and colour normalization based on our framework achieve competitive lesion classification performance. Ultimately, our work promotes equitable diagnosis through creating diverse training datasets that include different skin tones and image-capturing conditions. --- ### TeFlow: Enabling Multi-frame Supervision for Self-Supervised Feed-forward Scene Flow Estimation Authors: Qingwen Zhang, Chenhan Jiang, Xiaomeng Zhu, Yunqi Miao, Yushan Zhang, Olov Andersson, Patric Jensfelt Published: 2026-02-22 Categories: cs.CV, cs.RO arXiv: https://arxiv.org/abs/2602.19053v2 Self-supervised feed-forward methods for scene flow estimation offer real-time efficiency, but their supervision from two-frame point correspondences is unreliable and often breaks down under occlusions. Multi-frame supervision has the potential to provide more stable guidance by incorporating motion cues from past frames, yet naive extensions of two-frame objectives are ineffective because point correspondences vary abruptly across frames, producing inconsistent signals. In the paper, we present TeFlow, enabling multi-frame supervision for feed-forward models by mining temporally consistent supervision. TeFlow introduces a temporal ensembling strategy that forms reliable supervisory signals by aggregating the most temporally consistent motion cues from a candidate pool built across multiple frames. Extensive evaluations demonstrate that TeFlow establishes a new state-of-the-art for self-supervised feed-forward methods, achieving performance gains of up to 33\% on the challenging Argoverse 2 and nuScenes datasets. Our method performs on par with leading optimization-based methods, yet speeds up 150 times. The code is open-sourced at https://github.com/Kin-Zhang/TeFlow along with trained model weights. --- ### IAPO: Information-Aware Policy Optimization for Token-Efficient Reasoning Authors: Yinhan He, Yaochen Zhu, Mingjia Shi, Wendy Zheng, Lin Su, Xiaoqing Wang, Qi Guo, Jundong Li Published: 2026-02-22 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2602.19049v2 Large language models increasingly rely on long chains of thought to improve accuracy, yet such gains come with substantial inference-time costs. We revisit token-efficient post-training and argue that existing sequence-level reward-shaping methods offer limited control over how reasoning effort is allocated across tokens. To bridge the gap, we propose IAPO, an information-theoretic post-training framework that assigns token-wise advantages based on each token's conditional mutual information (MI) with the final answer. This yields an explicit, principled mechanism for identifying informative reasoning steps and suppressing low-utility exploration. We provide a theoretical analysis showing that our IAPO can induce monotonic reductions in reasoning verbosity without harming correctness. Empirically, IAPO consistently improves reasoning accuracy while reducing reasoning length by up to 36%, outperforming existing token-efficient RL methods across various reasoning datasets. Extensive empirical evaluations demonstrate that information-aware advantage shaping is a powerful and general direction for token-efficient post-training. The code is available at https://github.com/YinhanHe123/IAPO. --- ### Uncovering Context Reliance in Unstructured Knowledge Editing Authors: Zisheng Zhou, Mengqi Zhang, Shiguang Wu, Xiaotian Ye, Chi Zhang, Zhumin Chen, Pengjie Ren Published: 2026-02-22 Categories: cs.CL arXiv: https://arxiv.org/abs/2602.19043v1 Editing Large language models (LLMs) with real-world, unstructured knowledge is essential for correcting and updating their internal parametric knowledge. In this work, we revisit the fundamental next-token prediction (NTP) as a candidate paradigm for unstructured editing. We identify Context Reliance as a critical failure mode of NTP-based approaches, where knowledge acquired from edited text becomes highly dependent on its preceding context, leading to recall failures when that context is absent during inference. This hypothesis is supported by our empirical validation that prepending context during inference recovers knowledge recall. We further theoretically demonstrate that Context Reliance is an inherent consequence of gradient-based optimization, which tends to bind acquired knowledge to a specific aggregated contextual representation. To address this, we propose a simple yet effective COntext-INdependent editing framework (COIN), encouraging model to focus on knowledge within local scope rather than memorizing contextual patterns. Evaluations show that COIN reduces Context Reliance by 45.2% and outperforms strong baselines by 23.6% in editing success rate, highlighting the vital role of mitigating Context Reliance for robust editing. --- ### Back to Blackwell: Closing the Loop on Intransitivity in Multi-Objective Preference Fine-Tuning Authors: Jiahao Zhang, Lujing Zhang, Keltin Grimes, Zhuohao Yu, Gokul Swamy, Zhiwei Steven Wu Published: 2026-02-22 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.19041v2 A recurring challenge in preference fine-tuning (PFT) is handling $\textit{intransitive}$ (i.e., cyclic) preferences. Intransitive preferences often stem from either $\textit{(i)}$ inconsistent rankings along a single objective or $\textit{(ii)}$ scalarizing multiple objectives into a single metric. Regardless of their source, the downstream implication of intransitive preferences is the same: there is no well-defined optimal policy, breaking a core assumption of the standard PFT pipeline. In response, we propose a novel, game-theoretic solution concept, the $\textit{Maximum Entropy Blackwell Winner}$ ($\textit{MaxEntBW}$), that is well-defined under multi-objective intransitive preferences. To enable computing MaxEntBWs at scale, we derive $\texttt{PROSPER}$: a provably efficient PFT algorithm. Unlike prior self-play techniques, $\texttt{PROSPER}$ directly handles multiple objectives without requiring scalarization. We then apply $\texttt{PROSPER}$ to the problem of fine-tuning large language models (LLMs) from multi-objective LLM-as-a-Judge feedback (e.g., rubric-based judges), a setting where both sources of intransitivity arise. We find that $\texttt{PROSPER}$ outperforms all baselines considered across both instruction following and general chat benchmarks, releasing trained model checkpoints at the 7B and 3B parameter scales. --- ### OpenVO: Open-World Visual Odometry with Temporal Dynamics Awareness Authors: Phuc D. A. Nguyen, Anh N. Nhu, Ming C. Lin Published: 2026-02-22 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.19035v2 We introduce OpenVO, a novel framework for Open-world Visual Odometry (VO) with temporal awareness under limited input conditions. OpenVO effectively estimates real-world-scale ego-motion from monocular dashcam footage with varying observation rates and uncalibrated cameras, enabling robust trajectory dataset construction from rare driving events recorded in dashcam. Existing VO methods are trained on fixed observation frequency (e.g., 10Hz or 12Hz), completely overlooking temporal dynamics information. Many prior methods also require calibrated cameras with known intrinsic parameters. Consequently, their performance degrades when (1) deployed under unseen observation frequencies or (2) applied to uncalibrated cameras. These significantly limit their generalizability to many downstream tasks, such as extracting trajectories from dashcam footage. To address these challenges, OpenVO (1) explicitly encodes temporal dynamics information within a two-frame pose regression framework and (2) leverages 3D geometric priors derived from foundation models. We validate our method on three major autonomous-driving benchmarks - KITTI, nuScenes, and Argoverse 2 - achieving more than 20 performance improvement over state-of-the-art approaches. Under varying observation rate settings, our method is significantly more robust, achieving 46%-92% lower errors across all metrics. These results demonstrate the versatility of OpenVO for real-world 3D reconstruction and diverse downstream applications. --- ### A Markovian View of Iterative-Feedback Loops in Image Generative Models: Neural Resonance and Model Collapse Authors: Vibhas Kumar Vats, David J. Crandall, Samuel Goree Published: 2026-02-22 Categories: cs.LG, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2602.19033v1 AI training datasets will inevitably contain AI-generated examples, leading to ``feedback'' in which the output of one model impacts the training of another. It is known that such iterative feedback can lead to model collapse, yet the mechanisms underlying this degeneration remain poorly understood. Here we show that a broad class of feedback processes converges to a low-dimensional invariant structure in latent space, a phenomenon we call neural resonance. By modeling iterative feedback as a Markov Chain, we show that two conditions are needed for this resonance to occur: ergodicity of the feedback process and directional contraction of the latent representation. By studying diffusion models on MNIST and ImageNet, as well as CycleGAN and an audio feedback experiment, we map how local and global manifold geometry evolve, and we introduce an eight-pattern taxonomy of collapse behaviors. Neural resonance provides a unified explanation for long-term degenerate behavior in generative models and provides practical diagnostics for identifying, characterizing, and eventually mitigating collapse. --- ### Pushing the Limits of Inverse Lithography with Generative Reinforcement Learning Authors: Haoyu Yang, Haoxing Ren Published: 2026-02-22 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2602.19027v1 Inverse lithography (ILT) is critical for modern semiconductor manufacturing but suffers from highly non-convex objectives that often trap optimization in poor local minima. Generative AI has been explored to warm-start ILT, yet most approaches train deterministic image-to-image translators to mimic sub-optimal datasets, providing limited guidance for escaping non-convex traps during refinement. We reformulate mask synthesis as conditional sampling: a generator learns a distribution over masks conditioned on the design and proposes multiple candidates. The generator is first pretrained with WGAN plus a reconstruction loss, then fine-tuned using Group Relative Policy Optimization (GRPO) with an ILT-guided imitation loss. At inference, we sample a small batch of masks, run fast batched ILT refinement, evaluate lithography metrics (e.g., EPE, process window), and select the best candidate. On \texttt{LithoBench} dataset, the proposed hybrid framework reduces EPE violations under a 3\,nm tolerance and roughly doubles throughput versus a strong numerical ILT baseline, while improving final mask quality. We also present over 20\% EPE improvement on \texttt{ICCAD13} contest cases with 3$\times$ speedup over the SOTA numerical ILT solver. By learning to propose ILT-friendly initializations, our approach mitigates non-convexity and advances beyond what traditional solvers or GenAI can achieve. --- ### Routing-Aware Explanations for Mixture of Experts Graph Models in Malware Detection Authors: Hossein Shokouhinejad, Roozbeh Razavi-Far, Griffin Higgins, Ali. A Ghorbani Published: 2026-02-22 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2602.19025v1 Mixture-of-Experts (MoE) offers flexible graph reasoning by combining multiple views of a graph through a learned router. We investigate routing-aware explanations for MoE graph models in malware detection using control flow graphs (CFGs). Our architecture builds diversity at two levels. At the node level, each layer computes multiple neighborhood statistics and fuses them with an MLP, guided by a degree reweighting factor rho and a pooling choice lambda in {mean, std, max}, producing distinct node representations that capture complementary structural cues in CFGs. At the readout level, six experts, each tied to a specific (rho, lambda) view, output graph-level logits that the router weights into a final prediction. Post-hoc explanations are generated with edge-level attributions per expert and aggregated using the router gates so the rationale reflects both what each expert highlights and how strongly it is selected. Evaluated against single-expert GNN baselines such as GCN, GIN, and GAT on the same CFG dataset, the proposed MoE achieves strong detection accuracy while yielding stable, faithful attributions under sparsity-based perturbations. The results indicate that making the router explicit and combining multi-statistic node encoding with expert-level diversity can improve the transparency of MoE decisions for malware analysis. --- ### Towards Calibrating Prompt Tuning of Vision-Language Models Authors: Ashshak Sharifdeen, Fahad Shamshad, Muhammad Akhtar Munir, Abhishek Basu, Mohamed Insaf Ismithdeen, Jeyapriyan Jeyamohan, Chathurika Sewwandi Silva, Karthik Nandakumar, Muhammad Haris Khan Published: 2026-02-22 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.19024v1 Prompt tuning of large-scale vision-language models such as CLIP enables efficient task adaptation without updating model weights. However, it often leads to poor confidence calibration and unreliable predictive uncertainty. We address this problem by proposing a calibration framework that enhances predictive reliability while preserving the geometry of the pretrained CLIP embedding space, which is required for robust generalization. Our approach extends the standard cross-entropy loss with two complementary regularizers: (1) a mean-variance margin penalty that stabilizes inter-class logit margins by maximizing their average while minimizing dispersion, mitigating underconfidence and overconfidence spikes; and (2) a text moment-matching loss that aligns the first and second moments of tuned text embeddings with their frozen CLIP counterparts, preserving semantic dispersion crucial for generalization. Through extensive experiments across 7 prompt-tuning methods and 11 diverse datasets, we demonstrate that our approach significantly reduces the Expected Calibration Error (ECE) compared to competitive calibration techniques on both base and novel classes --- ### An interpretable framework using foundation models for fish sex identification Authors: Zheng Miao, Tien-Chieh Hung Published: 2026-02-22 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2602.19022v1 Accurate sex identification in fish is vital for optimizing breeding and management strategies in aquaculture, particularly for species at the risk of extinction. However, most existing methods are invasive or stressful and may cause additional mortality, posing severe risks to threatened or endangered fish populations. To address these challenges, we propose FishProtoNet, a robust, non-invasive computer vision-based framework for sex identification of delta smelt (Hypomesus transpacificus), an endangered fish species native to California, across its full life cycle. Unlike the traditional deep learning methods, FishProtoNet provides interpretability through learned prototype representations while improving robustness by leveraging foundation models to reduce the influence of background noise. Specifically, the FishProtoNet framework consists of three key components: fish regions of interest (ROIs) extraction using visual foundation model, feature extraction from fish ROIs and fish sex identification based on an interpretable prototype network. FishProtoNet demonstrates strong performance in delta smelt sex identification during early spawning and post-spawning stages, achieving the accuracies of 74.40% and 81.16% and corresponding F1 scores of 74.27% and 79.43% respectively. In contrast, delta smelt sex identification at the subadult stage remains challenging for current computer vision methods, likely due to less pronounced morphological differences in immature fish. The source code of FishProtoNet is publicly available at: https://github.com/zhengmiao1/Fish_sex_identification --- ### Learning to Detect Language Model Training Data via Active Reconstruction Authors: Junjie Oscar Yin, John X. Morris, Vitaly Shmatikov, Sewon Min, Hannaneh Hajishirzi Published: 2026-02-22 Categories: cs.LG, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2602.19020v1 Detecting LLM training data is generally framed as a membership inference attack (MIA) problem. However, conventional MIAs operate passively on fixed model weights, using log-likelihoods or text generations. In this work, we introduce \textbf{Active Data Reconstruction Attack} (ADRA), a family of MIA that actively induces a model to reconstruct a given text through training. We hypothesize that training data are \textit{more reconstructible} than non-members, and the difference in their reconstructibility can be exploited for membership inference. Motivated by findings that reinforcement learning (RL) sharpens behaviors already encoded in weights, we leverage on-policy RL to actively elicit data reconstruction by finetuning a policy initialized from the target model. To effectively use RL for MIA, we design reconstruction metrics and contrastive rewards. The resulting algorithms, \textsc{ADRA} and its adaptive variant \textsc{ADRA+}, improve both reconstruction and detection given a pool of candidate data. Experiments show that our methods consistently outperform existing MIAs in detecting pre-training, post-training, and distillation data, with an average improvement of 10.7\% over the previous runner-up. In particular, \MethodPlus~improves over Min-K\%++ by 18.8\% on BookMIA for pre-training detection and by 7.6\% on AIME for post-training detection. --- ### TokenTrace: Multi-Concept Attribution through Watermarked Token Recovery Authors: Li Zhang, Shruti Agarwal, John Collomosse, Pengtao Xie, Vishal Asnani Published: 2026-02-22 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.19019v2 Generative AI models pose a significant challenge to intellectual property (IP), as they can replicate unique artistic styles and concepts without attribution. While watermarking offers a potential solution, existing methods often fail in complex scenarios where multiple concepts (e.g., an object and an artistic style) are composed within a single image. These methods struggle to disentangle and attribute each concept individually. In this work, we introduce TokenTrace, a novel proactive watermarking framework for robust, multi-concept attribution. Our method embeds secret signatures into the semantic domain by simultaneously perturbing the text prompt embedding and the initial latent noise that guide the diffusion model's generation process. For retrieval, we propose a query-based TokenTrace module that takes the generated image and a textual query specifying which concepts need to be retrieved (e.g., a specific object or style) as inputs. This query-based mechanism allows the module to disentangle and independently verify the presence of multiple concepts from a single generated image. Extensive experiments show that our method achieves state-of-the-art performance on both single-concept (object and style) and multi-concept attribution tasks, significantly outperforming existing baselines while maintaining high visual quality and robustness to common transformations. --- ### Why ReLU? A Bit-Model Dichotomy for Deep Network Training Authors: Ilan Doron-Arad, Elchanan Mossel Published: 2026-02-22 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.19017v1 Theoretical analyses of Empirical Risk Minimization (ERM) are standardly framed within the Real-RAM model of computation. In this setting, training even simple neural networks is known to be $\exists \mathbb{R}$-complete -- a complexity class believed to be harder than NP, that characterizes the difficulty of solving systems of polynomial inequalities over the real numbers. However, this algebraic framework diverges from the reality of digital computation with finite-precision hardware. In this work, we analyze the theoretical complexity of ERM under a realistic bit-level model ($\mathsf{ERM}_{\text{bit}}$), where network parameters and inputs are constrained to be rational numbers with polynomially bounded bit-lengths. Under this model, we reveal a sharp dichotomy in tractability governed by the network's activation function. We prove that for deep networks with {\em any} polynomial activations with rational coefficients and degree at least $2$, the bit-complexity of training is severe: deciding $\mathsf{ERM}_{\text{bit}}$ is $\#P$-Hard, hence believed to be strictly harder than NP-complete problems. Furthermore, we show that determining the sign of a single partial derivative of the empirical loss function is intractable (unlikely in BPP), and deciding a specific bit in the gradient is $\#P$-Hard. This provides a complexity-theoretic perspective for the phenomenon of exploding and vanishing gradients. In contrast, we show that for piecewise-linear activations such as ReLU, the precision requirements remain manageable: $\mathsf{ERM}_{\text{bit}}$ is contained within NP (specifically NP-complete), and standard backpropagation runs in polynomial time. Our results demonstrate that finite-precision constraints are not merely implementation details but fundamental determinants of learnability. --- ### Capable but Unreliable: Canonical Path Deviation as a Causal Mechanism of Agent Failure in Long-Horizon Tasks Authors: Wilson Y. Lee Published: 2026-02-22 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2602.19008v1 Why do language agents fail on tasks they are capable of solving? We argue that many such failures are reliability failures caused by stochastic drift from a task's latent solution structure, not capability failures. Every well-defined tool-use task imposes a canonical solution path (i.e., a convergent set of tool invocations shared across successful runs) and agent success depends critically on whether a trajectory stays within this path's operating envelope. We establish this causally using a natural experiment that holds model capability and task difficulty fixed by construction. We analyze trajectories from the Toolathlon benchmark: 22 frontier models each attempt 108 real-world tool-use tasks across 3 independent runs, yielding 515 model$\times$task units where the same model succeeds on some runs and fails on others due to LLM sampling stochasticity alone. Within these units, successful runs adhere significantly more closely to the canonical solution path than failed runs ($+$0.060 Jaccard, $p<0.0001$, $n=488$ units, 95% CI (+0.043, +0.077)). This result survives six robustness checks including cross-model-family leave-one-out validation. Critically, the causal mechanism is gradual and self-reinforcing: the adherence gap is statistically indistinguishable from zero through the first 50% of the trajectory, ruling out early-branching selection bias, and each off-canonical tool call raises the probability that the next call is also off-canonical by 22.7 percentage points ($\hatβ=+0.227$, $p<0.0001$), more than doubling the baseline rate. These findings imply that agent reliability cannot be improved by capability scaling alone, but offer a highly actionable intervention: a simple monitor that restarts the bottom tercile of runs based on mid-trajectory canonical adherence lifts success rates by $+$8.8 percentage points among intervened runs. --- ### GUIDE-US: Grade-Informed Unpaired Distillation of Encoder Knowledge from Histopathology to Micro-UltraSound Authors: Emma Willis, Tarek Elghareb, Paul F. R. Wilson, Minh Nguyen Nhat To, Mohammad Mahdi Abootorabi, Amoon Jamzad, Brian Wodlinger, Parvin Mousavi, Purang Abolmaesumi Published: 2026-02-22 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2602.19005v1 Purpose: Non-invasive grading of prostate cancer (PCa) from micro-ultrasound (micro-US) could expedite triage and guide biopsies toward the most aggressive regions, yet current models struggle to infer tissue micro-structure at coarse imaging resolutions. Methods: We introduce an unpaired histopathology knowledge-distillation strategy that trains a micro-US encoder to emulate the embedding distribution of a pretrained histopathology foundation model, conditioned on International Society of Urological Pathology (ISUP) grades. Training requires no patient-level pairing or image registration, and histopathology inputs are not used at inference. Results: Compared to the current state of the art, our approach increases sensitivity to clinically significant PCa (csPCa) at 60% specificity by 3.5% and improves overall sensitivity at 60% specificity by 1.2%. Conclusion: By enabling earlier and more dependable cancer risk stratification solely from imaging, our method advances clinical feasibility. Source code will be publicly released upon publication. --- ### MoBind: Motion Binding for Fine-Grained IMU-Video Pose Alignment Authors: Duc Duy Nguyen, Tat-Jun Chin, Minh Hoai Published: 2026-02-22 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.19004v1 We aim to learn a joint representation between inertial measurement unit (IMU) signals and 2D pose sequences extracted from video, enabling accurate cross-modal retrieval, temporal synchronization, subject and body-part localization, and action recognition. To this end, we introduce MoBind, a hierarchical contrastive learning framework designed to address three challenges: (1) filtering out irrelevant visual background, (2) modeling structured multi-sensor IMU configurations, and (3) achieving fine-grained, sub-second temporal alignment. To isolate motion-relevant cues, MoBind aligns IMU signals with skeletal motion sequences rather than raw pixels. We further decompose full-body motion into local body-part trajectories, pairing each with its corresponding IMU to enable semantically grounded multi-sensor alignment. To capture detailed temporal correspondence, MoBind employs a hierarchical contrastive strategy that first aligns token-level temporal segments, then fuses local (body-part) alignment with global (body-wide) motion aggregation. Evaluated on mRi, TotalCapture, and EgoHumans, MoBind consistently outperforms strong baselines across all four tasks, demonstrating robust fine-grained temporal alignment while preserving coarse semantic consistency across modalities. Code is available at https://github.com/bbvisual/ MoBind. --- ### Life-Bench: A Benchmark and Knowledge Graph Framework for Multimodal Personalization Beyond Concept Recognition Authors: Xia Hu, Honglei Zhuang, Brian Potetz, Alireza Fathi, Bo Hu, Babak Samari, Howard Zhou Published: 2026-02-22 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.19001v2 As large language models increasingly power personal assistants, users expect them to reason over multimodal life histories, from recognizing people to understanding events to aggregating patterns, yet existing benchmarks primarily target concept-level recognition. We introduce Life-Bench, a fully synthetic, human-verified multimodal benchmark of over 11,800 question-answer pairs across 10 tasks, organized by required evidence scope: concept identification, event understanding, and aggregated reasoning. The benchmark's photo-centric personal histories are distributionally aligned with real user accounts under embedding statistic. The interconnected structure of personal data invites graph-based solutions; we propose LifeGraph, a personal knowledge graph framework providing structured retrieval with on-demand access to source visual evidence, showing particular promise on event and aggregated tasks. Systematic evaluation of four retrieval paradigms on Life-Bench demonstrates that accuracy degrades sharply with evidence scope, falling below 0.40 on aggregated tasks, and that no single paradigm dominates across categories. Performance beyond concept recognition remains modest for all evaluated methods, establishing personalization over multimodal histories as an open challenge and Life-Bench as a testbed for future progress. ---