# Research Papers — 2026-02 · bundle page 179 of 210 > Full-text markdown of papers #8901–8950 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/179 [← Previous bundle](https://aipod.dev/papers/archive/2026-02/page/178.md) [Next bundle →](https://aipod.dev/papers/archive/2026-02/page/180.md) ### Semantic-level Backdoor Attack against Text-to-Image Diffusion Models Authors: Tianxin Chen, Wenbo Jiang, Hongqiao Chen, Zhirun Zheng, Cheng Huang Published: 2026-02-03 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2602.04898v3 Text-to-image (T2I) diffusion models are widely adopted for their strong generative capabilities, yet remain vulnerable to backdoor attacks. Existing attacks typically rely on fixed textual triggers and single-entity backdoor targets, making them highly susceptible to enumeration-based input defenses and attention-consistency detection. In this work, we propose Semantic-level Backdoor Attack (SemBD), which introduces representation-level triggers based on continuous semantic regions rather than discrete textual patterns. SemBD implants such semantic backdoors by distillation-based editing of the key and value projection matrices in cross-attention layers, enabling semantically equivalent but textually diverse prompts to activate the backdoor. To further enhance stealthiness, SemBD incorporates a semantic regularization to prevent unintended activation under incomplete semantics, as well as multi-entity backdoor targets that avoid highly consistent cross-attention patterns. Extensive experiments demonstrate that SemBD achieves a 100% attack success rate while maintaining strong robustness against state-of-the-art input-level defenses. Our code is available at https://github.com/DPAS-Lab/SemBD/. --- ### Steering Externalities: Benign Activation Steering Unintentionally Increases Jailbreak Risk for Large Language Models Authors: Chen Xiong, Zhiyuan He, Pin-Yu Chen, Ching-Yun Ko, Tsung-Yi Ho Published: 2026-02-03 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2602.04896v1 Activation steering is a practical post-training model alignment technique to enhance the utility of Large Language Models (LLMs). Prior to deploying a model as a service, developers can steer a pre-trained model toward specific behavioral objectives, such as compliance or instruction adherence, without the need for retraining. This process is as simple as adding a steering vector to the model's internal representations. However, this capability unintentionally introduces critical and under-explored safety risks. We identify a phenomenon termed Steering Externalities, where steering vectors derived from entirely benign datasets-such as those enforcing strict compliance or specific output formats like JSON-inadvertently erode safety guardrails. Experiments reveal that these interventions act as a force multiplier, creating new vulnerabilities to jailbreaks and increasing attack success rates to over 80% on standard benchmarks by bypassing the initial safety alignment. Ultimately, our results expose a critical blind spot in deployment: benign activation steering systematically erodes the "safety margin," rendering models more vulnerable to black-box attacks and proving that inference-time utility improvements must be rigorously audited for unintended safety externalities. --- ### Privacy Amplification Persists under Unlimited Synthetic Data Release Authors: Clément Pierquin, Aurélien Bellet, Marc Tommasi, Matthieu Boussard Published: 2026-02-03 Categories: cs.CR, cs.DS, cs.LG, stat.ML arXiv: https://arxiv.org/abs/2602.04895v1 We study privacy amplification by synthetic data release, a phenomenon in which differential privacy guarantees are improved by releasing only synthetic data rather than the private generative model itself. Recent work by Pierquin et al. (2025) established the first formal amplification guarantees for a linear generator, but they apply only in asymptotic regimes where the model dimension far exceeds the number of released synthetic records, limiting their practical relevance. In this work, we show a surprising result: under a bounded-parameter assumption, privacy amplification persists even when releasing an unbounded number of synthetic records, thereby improving upon the bounds of Pierquin et al. (2025). Our analysis provides structural insights that may guide the development of tighter privacy guarantees for more complex release mechanisms. --- ### Scaling In-Context Online Learning Capability of LLMs via Cross-Episode Meta-RL Authors: Xiaofeng Lin, Sirou Zhu, Yilei Chen, Mingyu Chen, Hejian Sang, Ioannis Paschalidis, Zhipeng Wang, Aldo Pacchiano, Xuezhou Zhang Published: 2026-02-03 Categories: cs.AI, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2602.04089v1 Large language models (LLMs) achieve strong performance when all task-relevant information is available upfront, as in static prediction and instruction-following problems. However, many real-world decision-making tasks are inherently online: crucial information must be acquired through interaction, feedback is delayed, and effective behavior requires balancing information collection and exploitation over time. While in-context learning enables adaptation without weight updates, existing LLMs often struggle to reliably leverage in-context interaction experience in such settings. In this work, we show that this limitation can be addressed through training. We introduce ORBIT, a multi-task, multi-episode meta-reinforcement learning framework that trains LLMs to learn from interaction in context. After meta-training, a relatively small open-source model (Qwen3-14B) demonstrates substantially improved in-context online learning on entirely unseen environments, matching the performance of GPT-5.2 and outperforming standard RL fine-tuning by a large margin. Scaling experiments further reveal consistent gains with model size, suggesting significant headroom for learn-at-inference-time decision-making agents. Code reproducing the results in the paper can be found at https://github.com/XiaofengLin7/ORBIT. --- ### BASS: Benchmarking Audio LMs for Musical Structure and Semantic Reasoning Authors: Min Jang, Orevaoghene Ahia, Nazif Tamer, Sachin Kumar, Yulia Tsvetkov, Noah A. Smith Published: 2026-02-03 Categories: cs.SD, cs.CL arXiv: https://arxiv.org/abs/2602.04085v1 Music understanding is a complex task that often requires reasoning over both structural and semantic elements of audio. We introduce BASS, designed to evaluate music understanding and reasoning in audio language models across four broad categories: structural segmentation, lyric transcription, musicological analysis, and artist collaboration. BASS comprises 2658 questions spanning 12 tasks, 1993 unique songs and covering over 138 hours of music from a wide range of genres and tracks, crafted to assess musicological knowledge and reasoning in real-world scenarios. We evaluate 14 open-source and frontier multimodal LMs, finding that even state-of-the-art models struggle on higher-level reasoning tasks such as structural segmentation and artist collaboration, while performing best on lyric transcription. Our analysis reveals that current models leverage linguistic priors effectively but remain limited in reasoning over musical structure, vocal, and musicological attributes. BASS provides an evaluation framework with widespread applications in music recommendation and search and has the potential to guide the development of audio LMs. --- ### Structure-Informed Estimation for Pilot-Limited MIMO Channels via Tensor Decomposition Authors: Alexandre Barbosa de Lima Published: 2026-02-03 Categories: eess.SP, cs.AI arXiv: https://arxiv.org/abs/2602.04083v3 Accurate channel state information in wideband MIMO systems is constrained by pilot overhead, a challenge intensifying as bandwidths scale toward 6G. This paper proposes a structure-informed hybrid estimator formulating pilot-limited MIMO channel estimation as low-rank tensor completion from sparse pilot observations---an underdetermined inverse problem that prior approaches avoid by assuming fully observed tensors. Canonical polyadic~(CP) and Tucker decompositions are compared: CP excels for specular channels matching its rank-one parameterization exactly, while Tucker provides numerical stability at extreme pilot scarcity where CP exhibits heavy-tail divergence. A lightweight 3D U-Net learns residual components beyond the low-rank structure, compensating for diffuse scattering and hardware non-idealities. On synthetic specular channels, Tucker completion improves normalized mean-squared error (NMSE) by $10.88$~dB over least squares and $7.83$~dB over orthogonal matching pursuit at $10\%$ pilot density ($ρ$); CP outperforms Tucker by $13.11$~dB at SNR=20~dB. On DeepMIMO channels, the hybrid Tensor--NN estimator has two regimes: Tensor--NN(Tucker) remains stable at $ρ=2\%$ where CP diverges, while a CP-guided variant becomes best from $ρ\ge 4\%$, reaching $-16.44$~dB at $ρ=8\%$ and $-20.34$~dB at $ρ=20\%$. The Tucker-guided variant outperforms unconstrained deep learning across the full pilot range; the CP-guided variant widens this gap once stable. Empirical analysis confirms sample complexity scales with intrinsic channel dimensionality (dominant paths) rather than ambient tensor size. --- ### Structure-Informed Estimation for Pilot-Limited MIMO Channels via Tensor Decomposition Authors: Alexandre Barbosa de Lima Published: 2026-02-03 Categories: eess.SP, cs.AI arXiv: https://arxiv.org/abs/2602.04083v2 Accurate channel state information in wideband multiple-input multiple-output (MIMO) systems is fundamentally constrained by pilot overhead, a challenge that intensifies as antenna counts and bandwidths scale toward 6G. This paper proposes a structure-informed hybrid estimator that formulates pilot-limited MIMO channel estimation as low-rank tensor completion from sparse pilot observations -- a severely underdetermined inverse problem that prior tensor approaches avoid by assuming fully observed received signal tensors. Canonical polyadic~(CP) and Tucker decompositions are comparatively analyzed: CP excels for specular channels whose rank-one multipath structure matches the CP parameterization exactly, while Tucker provides greater numerical stability at extreme pilot scarcity where CP exhibits heavy-tail divergence. A lightweight 3D U-Net learns residual components beyond the dominant low-rank structure, compensating for diffuse scattering and hardware non-idealities that algebraic priors alone cannot capture. On synthetic specular channels, Tucker completion achieves $10.88$~dB NMSE improvement over least squares and $7.83$~dB over orthogonal matching pursuit at $ρ= 10\%$ pilot density; CP outperforms Tucker by $13.11$~dB at SNR\,=\,20~dB under the specular multipath model. On DeepMIMO ray-tracing channels, the hybrid estimator surpasses CP by $2.26$~dB and Tucker by $4.80$~dB at $ρ= 8\%$, while remaining stable at $ρ= 2\%$ where CP diverges; algebraic structure consistently outperforms unconstrained deep learning across the full pilot-density range, with a margin growing from $1.53$~dB at $ρ= 2\%$ to $5.67$~dB at $ρ= 20\%$. Empirical recovery threshold analysis confirms that sample complexity scales with intrinsic channel dimensionality -- governed by the number of dominant propagation paths -- rather than with the ambient tensor size. --- ### A Probabilistic Framework for Solving High-Frequency Helmholtz Equations via Diffusion Models Authors: Yicheng Zou, Samuel Lanthaler, Hossein Salahshoor Published: 2026-02-03 Categories: cs.LG, math.NA arXiv: https://arxiv.org/abs/2602.04082v1 Deterministic neural operators perform well on many PDEs but can struggle with the approximation of high-frequency wave phenomena, where strong input-to-output sensitivity makes operator learning challenging, and spectral bias blurs oscillations. We argue for adopting a probabilistic approach for approximating waves in high-frequency regime, and develop our probabilistic framework using a score-based conditional diffusion operator. After demonstrating a stability analysis of the Helmholtz operator, we present our numerical experiments across a wide range of frequencies, benchmarked against other popular data-driven and machine learning approaches for waves. We show that our probabilistic neural operator consistently produces robust predictions with the lowest errors in $L^2$, $H^1$, and energy norms. Moreover, unlike all the other tested deterministic approaches, our framework remarkably captures uncertainties in the input sound speed map propagated to the solution field. We envision that our results position probabilistic operator learning as a principled and effective approach for solving complex PDEs such as Helmholtz in the challenging high-frequency regime. --- ### Abstraction Induces the Brain Alignment of Language and Speech Models Authors: Emily Cheng, Aditya R. Vaidya, Richard Antonello Published: 2026-02-03 Categories: cs.CL arXiv: https://arxiv.org/abs/2602.04081v2 Research has repeatedly demonstrated that intermediate hidden states extracted from large language models and speech audio models predict measured brain response to natural language stimuli. Yet, very little is known about the representation properties that enable this high prediction performance. Why is it the intermediate layers, and not the output layers, that are most effective for this unique and highly general transfer task? We give evidence that the correspondence between speech and language models and the brain derives from shared meaning abstraction and not their next-word prediction properties. In particular, models construct higher-order linguistic features in their middle layers, cued by a peak in the layerwise intrinsic dimension, a measure of feature complexity. We show that a layer's intrinsic dimension strongly predicts how well it explains fMRI and ECoG signals; that the relation between intrinsic dimension and brain predictivity arises over model pre-training; and finetuning models to better predict the brain causally increases both representations' intrinsic dimension and their semantic content. Results suggest that semantic richness, high intrinsic dimension, and brain predictivity mirror each other, and that the key driver of model-brain similarity is rich meaning abstraction of the inputs, where language modeling is a task complex enough (but perhaps not the only) to require it. --- ### Principles of Lipschitz continuity in neural networks Authors: Róisín Luo Published: 2026-02-03 Categories: cs.LG, cs.AI, stat.ML arXiv: https://arxiv.org/abs/2602.04078v2 Deep learning has achieved remarkable success across a wide range of domains, significantly expanding the frontiers of what is achievable in artificial intelligence. Yet, despite these advances, critical challenges remain -- most notably, ensuring robustness to small input perturbations and generalization to out-of-distribution data. These critical challenges underscore the need to understand the underlying fundamental principles that govern robustness and generalization. Among the theoretical tools available, Lipschitz continuity plays a pivotal role in governing the fundamental properties of neural networks related to robustness and generalization. It quantifies the worst-case sensitivity of network's outputs to small input perturbations. While its importance is widely acknowledged, prior research has predominantly focused on empirical regularization approaches based on Lipschitz constraints, leaving the underlying principles less explored. This thesis seeks to advance a principled understanding of the principles of Lipschitz continuity in neural networks within the paradigm of machine learning, examined from two complementary perspectives: an internal perspective -- focusing on the temporal evolution of Lipschitz continuity in neural networks during training (i.e., training dynamics); and an external perspective -- investigating how Lipschitz continuity modulates the behavior of neural networks with respect to features in the input data, particularly its role in governing frequency signal propagation (i.e., modulation of frequency signal propagation). --- ### Efficient Subgroup Analysis via Optimal Trees with Global Parameter Fusion Authors: Zhongming Xie, Joseph Giorgio, Jingshen Wang Published: 2026-02-03 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2602.04077v1 Identifying and making statistical inferences on differential treatment effects (commonly known as subgroup analysis in clinical research) is central to precision health. Subgroup analysis allows practitioners to pinpoint populations for whom a treatment is especially beneficial or protective, thereby advancing targeted interventions. Tree based recursive partitioning methods are widely used for subgroup analysis due to their interpretability. Nevertheless, these approaches encounter significant limitations, including suboptimal partitions induced by greedy heuristics and overfitting from locally estimated splits, especially under limited sample sizes. To address these limitations, we propose a fused optimal causal tree method that leverages mixed integer optimization (MIO) to facilitate precise subgroup identification. Our approach ensures globally optimal partitions and introduces a parameter fusion constraint to facilitate information sharing across related subgroups. This design substantially improves subgroup discovery accuracy and enhances statistical efficiency. We provide theoretical guarantees by rigorously establishing out of sample risk bounds and comparing them with those of classical tree based methods. Empirically, our method consistently outperforms popular baselines in simulations. Finally, we demonstrate its practical utility through a case study on the Health and Aging Brain Study Health Disparities (HABS-HD) dataset, where our approach yields clinically meaningful insights. --- ### Thermodynamic assessment of machine learning models for solid-state synthesis prediction Authors: Jane Schlesinger, Simon Hjaltason, Nathan J. Szymanski, Christopher J. Bartel Published: 2026-02-03 Categories: cond-mat.mtrl-sci, cs.LG arXiv: https://arxiv.org/abs/2602.04075v2 Machine learning models have recently emerged to predict whether hypothetical solid-state materials can be synthesized. These models aim to circumvent direct first-principles modeling of solid-state phase transformations, instead learning from large databases of successfully synthesized materials. Here, we assess the alignment of several recently introduced synthesis prediction models with material and reaction thermodynamics, quantified by the energy with respect to the convex hull and a metric accounting for thermodynamic selectivity of enumerated synthesis reactions. A dataset of successful synthesis recipes was used to determine the likely bounds on both quantities beyond which materials can be deemed unlikely to be synthesized. With these bounds as context, thermodynamic quantities were computed using the CHGNet foundation potential for thousands of new hypothetical materials generated using the Chemeleon generative model. Four recently published machine learning models for synthesizability prediction were applied to this same dataset, and the resultant predictions were considered against computed thermodynamics. We find these models generally overpredict the likelihood of synthesis, but some model scores do trend with thermodynamic heuristics, assigning lower scores to materials that are less stable or do not have an available synthesis recipe that is calculated to be thermodynamically selective. In total, this work identifies existing gaps in machine learning models for materials synthesis and introduces a new approach to assess their quality in the absence of extensive negative examples (failed syntheses). --- ### Stroke Lesions as a Rosetta Stone for Language Model Interpretability Authors: Julius Fridriksson, Roger D. Newman-Norlund, Saeed Ahmadi, Regan Willis, Nadra Salman, Kalil Warren, Xiang Guan, Yong Yang, Srihari Nelakuditi, Rutvik Desai, Leonardo Bonilha, Jeff Charney et al. Published: 2026-02-03 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2602.04074v1 Large language models (LLMs) have achieved remarkable capabilities, yet methods to verify which model components are truly necessary for language function remain limited. Current interpretability approaches rely on internal metrics and lack external validation. Here we present the Brain-LLM Unified Model (BLUM), a framework that leverages lesion-symptom mapping, the gold standard for establishing causal brain-behavior relationships for over a century, as an external reference structure for evaluating LLM perturbation effects. Using data from individuals with chronic post-stroke aphasia (N = 410), we trained symptom-to-lesion models that predict brain damage location from behavioral error profiles, applied systematic perturbations to transformer layers, administered identical clinical assessments to perturbed LLMs and human patients, and projected LLM error profiles into human lesion space. LLM error profiles were sufficiently similar to human error profiles that predicted lesions corresponded to actual lesions in error-matched humans above chance in 67% of picture naming conditions (p < 10^{-23}) and 68.3% of sentence completion conditions (p < 10^{-61}), with semantic-dominant errors mapping onto ventral-stream lesion patterns and phonemic-dominant errors onto dorsal-stream patterns. These findings open a new methodological avenue for LLM interpretability in which clinical neuroscience provides external validation, establishing human lesion-symptom mapping as a reference framework for evaluating artificial language systems and motivating direct investigation of whether behavioral alignment reflects shared computational principles. --- ### Agentic AI-Empowered Dynamic Survey Framework Authors: Furkan Mumcu, Lokman Bekit, Michael J. Jones, Anoop Cherian, Yasin Yilmaz Published: 2026-02-03 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.04071v1 Survey papers play a central role in synthesizing and organizing scientific knowledge, yet they are increasingly strained by the rapid growth of research output. As new work continues to appear after publication, surveys quickly become outdated, contributing to redundancy and fragmentation in the literature. We reframe survey writing as a long-horizon maintenance problem rather than a one-time generation task, treating surveys as living documents that evolve alongside the research they describe. We propose an agentic Dynamic Survey Framework that supports the continuous updating of existing survey papers by incrementally integrating new work while preserving survey structure and minimizing unnecessary disruption. Using a retrospective experimental setup, we demonstrate that the proposed framework effectively identifies and incorporates emerging research while preserving the coherence and structure of existing surveys. --- ### An Empirical Survey and Benchmark of Learned Distance Indexes for Road Networks Authors: Gautam Choudhary, Libin Zhou, Yeasir Rayhan, Walid G. Aref Published: 2026-02-03 Categories: cs.LG, cs.DB arXiv: https://arxiv.org/abs/2602.04068v2 The calculation of shortest-path distances in road networks is a core operation in navigation systems, location-based services, and spatial analytics. Although classical algorithms, e.g., Dijkstra's algorithm, provide exact answers, their latency is prohibitive for modern real-time, large-scale deployments. Over the past two decades, numerous distance indexes have been proposed to speed up query processing for shortest distance queries. More recently, with advances in machine learning (ML), researchers have designed and proposed ML-based distance indexes to answer approximate shortest path and distance queries efficiently. However, a comprehensive and systematic evaluation of these ML-based approaches is lacking. This paper presents the first empirical survey of ML-based distance indexes on road networks, evaluating them along four key dimensions: training time, query latency, storage, and accuracy. Using 13 real-world road networks (7 with workload-driven queries, derived from trajectory data, and 6 with synthetically generated queries), we benchmark ten representative ML techniques and compare them against classical non-ML baselines, highlighting key insights and practical trade-offs. We release a unified open-source codebase to support reproducibility and future research on learned indexes. --- ### An Empirical Survey and Benchmark of Learned Distance Indexes for Road Networks Authors: Gautam Choudhary, Libin Zhou, Yeasir Rayhan, Walid G. Aref Published: 2026-02-03 Categories: cs.LG, cs.DB arXiv: https://arxiv.org/abs/2602.04068v1 The calculation of shortest-path distances in road networks is a core operation in navigation systems, location-based services, and spatial analytics. Although classical algorithms, e.g., Dijkstra's algorithm, provide exact answers, their latency is prohibitive for modern real-time, large-scale deployments. Over the past two decades, numerous distance indexes have been proposed to speed up query processing for shortest distance queries. More recently, with the advancement in machine learning (ML), researchers have designed and proposed ML-based distance indexes to answer approximate shortest path and distance queries efficiently. However, a comprehensive and systematic evaluation of these ML-based approaches is lacking. This paper presents the first empirical survey of ML-based distance indexes on road networks, evaluating them along four key dimensions: Training time, query latency, storage, and accuracy. Using seven real-world road networks and workload-driven query datasets derived from trajectory data, we benchmark ten representative ML techniques and compare them against strong classical non-ML baselines, highlighting key insights and practical trade-offs. We release a unified open-source codebase to support reproducibility and future research on learned distance indexes. --- ### iSight: Towards expert-AI co-assessment for improved immunohistochemistry staining interpretation Authors: Jacob S. Leiby, Jialu Yao, Pan Lu, George Hu, Anna Davidian, Shunsuke Koga, Olivia Leung, Pravin Patel, Isabella Tondi Resta, Rebecca Rojansky, Derek Sung, Eric Yang et al. Published: 2026-02-03 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.04063v1 Immunohistochemistry (IHC) provides information on protein expression in tissue sections and is commonly used to support pathology diagnosis and disease triage. While AI models for H\&E-stained slides show promise, their applicability to IHC is limited due to domain-specific variations. Here we introduce HPA10M, a dataset that contains 10,495,672 IHC images from the Human Protein Atlas with comprehensive metadata included, and encompasses 45 normal tissue types and 20 major cancer types. Based on HPA10M, we trained iSight, a multi-task learning framework for automated IHC staining assessment. iSight combines visual features from whole-slide images with tissue metadata through a token-level attention mechanism, simultaneously predicting staining intensity, location, quantity, tissue type, and malignancy status. On held-out data, iSight achieved 85.5\% accuracy for location, 76.6\% for intensity, and 75.7\% for quantity, outperforming fine-tuned foundation models (PLIP, CONCH) by 2.5--10.2\%. In addition, iSight demonstrates well-calibrated predictions with expected calibration errors of 0.0150-0.0408. Furthermore, in a user study with eight pathologists evaluating 200 images from two datasets, iSight outperformed initial pathologist assessments on the held-out HPA dataset (79\% vs 68\% for location, 70\% vs 57\% for intensity, 68\% vs 52\% for quantity). Inter-pathologist agreement also improved after AI assistance in both held-out HPA (Cohen's $κ$ increased from 0.63 to 0.70) and Stanford TMAD datasets (from 0.74 to 0.76), suggesting expert--AI co-assessment can improve IHC interpretation. This work establishes a foundation for AI systems that can improve IHC diagnostic accuracy and highlights the potential for integrating iSight into clinical workflows to enhance the consistency and reliability of IHC assessment. --- ### SEIS: Subspace-based Equivariance and Invariance Scores for Neural Representations Authors: Huahua Lin, Katayoun Farrahi, Xiaohao Cai Published: 2026-02-03 Categories: cs.LG, cs.CV arXiv: https://arxiv.org/abs/2602.04054v2 Understanding how neural representations respond to geometric transformations is essential for evaluating whether learned features preserve meaningful spatial structure. Existing approaches primarily assess robustness primarily by comparing model outputs under transformed inputs, offering limited insight into how geometric information is organized within internal representations and failing to distinguish between information loss and re-encoding. In this work, we introduce SEIS (Subspace-based Equivariance and Invariance Scores), a subspace metric for analyzing layer-wise feature representations under geometric transformations, disentangling equivariance from invariance without requiring labels or explicit knowledge of the transformation. Through controlled experiments across diverse architectures, we uncover several consistent patterns. First, convolutional encoders exhibit a depth-wise transition from strong equivariance to increasing invariance, with both properties stabilizing within the first few training epochs. In segmentation decoders, however, equivariance tends to recover in later layers. Second, this trade-off is not intrinsic but is shaped by training decisions: data augmentation actively strengthens both equivariance and invariance simultaneously, and multi-task learning induces synergistic gains in both properties beyond what either task achieves alone. Extending our analysis beyond convolutional networks, we find that transformer-based models exhibit distinct geometric behaviors, while MLP-Mixers display intermediate characteristics. --- ### Seeing Through Clutter: Structured 3D Scene Reconstruction via Iterative Object Removal Authors: Rio Aguina-Kang, Kevin James Blackburn-Matzen, Thibault Groueix, Vladimir Kim, Matheus Gadelha Published: 2026-02-03 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.04053v2 We present SeeingThroughClutter, a method for reconstructing structured 3D representations from single images by segmenting and modeling objects individually. Prior approaches rely on intermediate tasks such as semantic segmentation and depth estimation, which often underperform in complex scenes, particularly in the presence of occlusion and clutter. We address this by introducing an iterative object removal and reconstruction pipeline that decomposes complex scenes into a sequence of simpler subtasks. Using VLMs as orchestrators, foreground objects are removed one at a time via detection, segmentation, object removal, and 3D fitting. We show that removing objects allows for cleaner segmentations of subsequent objects, even in highly occluded scenes. Our method requires no task-specific training and benefits directly from ongoing advances in foundation models. We demonstrate stateof-the-art robustness on 3D-Front and ADE20K datasets. Project Page: https://rioak.github.io/seeingthroughclutter/ --- ### Artifact Removal and Image Restoration in AFM:A Structured Mask-Guided Directional Inpainting Approach Authors: Juntao Zhang, Angona Biswas, Jaydeep Rade, Charchit Shukla, Juan Ren, Anwesha Sarkar, Adarsh Krishnamurthy, Aditya Balu Published: 2026-02-03 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.04051v1 Atomic Force Microscopy (AFM) enables high-resolution surface imaging at the nanoscale, yet the output is often degraded by artifacts introduced by environmental noise, scanning imperfections, and tip-sample interactions. To address this challenge, a lightweight and fully automated framework for artifact detection and restoration in AFM image analysis is presented. The pipeline begins with a classification model that determines whether an AFM image contains artifacts. If necessary, a lightweight semantic segmentation network, custom-designed and trained on AFM data, is applied to generate precise artifact masks. These masks are adaptively expanded based on their structural orientation and then inpainted using a directional neighbor-based interpolation strategy to preserve 3D surface continuity. A localized Gaussian smoothing operation is then applied for seamless restoration. The system is integrated into a user-friendly GUI that supports real-time parameter adjustments and batch processing. Experimental results demonstrate the effective artifact removal while preserving nanoscale structural details, providing a robust, geometry-aware solution for high-fidelity AFM data interpretation. --- ### Fast, Unsupervised Framework for Registration Quality Assessment of Multi-stain Histological Whole Slide Pairs Authors: Shikha Dubey, Patricia Raciti, Kristopher Standish, Albert Juan Ramon, Erik Ames Burlingame Published: 2026-02-03 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.04046v1 High-fidelity registration of histopathological whole slide images (WSIs), such as hematoxylin & eosin (H&E) and immunohistochemistry (IHC), is vital for integrated molecular analysis but challenging to evaluate without ground-truth (GT) annotations. Existing WSI-level assessments -- using annotated landmarks or intensity-based similarity metrics -- are often time-consuming, unreliable, and computationally intensive, limiting large-scale applicability. This study proposes a fast, unsupervised framework that jointly employs down-sampled tissue masks- and deformations-based metrics for registration quality assessment (RQA) of registered H&E and IHC WSI pairs. The masks-based metrics measure global structural correspondence, while the deformations-based metrics evaluate local smoothness, continuity, and transformation realism. Validation across multiple IHC markers and multi-expert assessments demonstrate a strong correlation between automated metrics and human evaluations. In the absence of GT, this framework offers reliable, real-time RQA with high fidelity and minimal computational resources, making it suitable for large-scale quality control in digital pathology. --- ### A Parameterizable Convolution Accelerator for Embedded Deep Learning Applications Authors: Panagiotis Mousouliotis, Georgios Keramidas Published: 2026-02-03 Categories: cs.CV, cs.AR arXiv: https://arxiv.org/abs/2602.04044v1 Convolutional neural network (CNN) accelerators implemented on Field-Programmable Gate Arrays (FPGAs) are typically designed with a primary focus on maximizing performance, often measured in giga-operations per second (GOPS). However, real-life embedded deep learning (DL) applications impose multiple constraints related to latency, power consumption, area, and cost. This work presents a hardware-software (HW/SW) co-design methodology in which a CNN accelerator is described using high-level synthesis (HLS) tools that ease the parameterization of the design, facilitating more effective optimizations across multiple design constraints. Our experimental results demonstrate that the proposed design methodology is able to outperform non-parameterized design approaches, and it can be easily extended to other types of DL applications. --- ### AnyStyle: Single-Pass Multimodal Stylization for 3D Gaussian Splatting Authors: Joanna Kaleta, Bartosz Świrta, Kacper Kania, Tomasz Trzciński, Przemysław Spurek, Marek Kowalski Published: 2026-02-03 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.04043v2 The growing demand for rapid and scalable 3D asset creation has driven interest in feed-forward 3D reconstruction methods, with 3D Gaussian Splatting (3DGS) emerging as an effective scene representation. While recent approaches have demonstrated pose-free reconstruction from unposed image collections, integrating stylization or appearance control into such pipelines remains underexplored. Existing attempts largely rely on image-based conditioning, which limits both controllability and flexibility. In this work, we introduce AnyStyle, a feed-forward 3D reconstruction and stylization framework that enables pose-free, zero-shot stylization through multimodal conditioning. Our method supports both textual and visual style inputs, allowing users to control the scene appearance using natural language descriptions or reference images. We propose a modular stylization architecture that requires only minimal architectural modifications and can be integrated into existing feed-forward 3D reconstruction backbones. Experiments demonstrate that AnyStyle improves style controllability over prior feed-forward stylization methods while preserving high-quality geometric reconstruction. A user study further confirms that AnyStyle achieves superior stylization quality compared to an existing state-of-the-art approach. Repository: https://github.com/joaxkal/AnyStyle. --- ### Partition Tree: Conditional Density Estimation over General Outcome Spaces Authors: Felipe Angelim, Alessandro Leite Published: 2026-02-03 Categories: cs.LG, stat.ME, stat.ML arXiv: https://arxiv.org/abs/2602.04042v2 We propose Partition Tree, a novel tree-based framework for conditional density estimation over general outcome spaces that supports both continuous and categorical variables within a unified formulation. Our approach models conditional distributions as piecewise-constant densities on data-adaptive partitions and learns trees by directly minimizing conditional negative log-likelihood. This yields a scalable, nonparametric alternative to existing probabilistic trees that does not make parametric assumptions about the target distribution. We further introduce Partition Forest, a bagging extension obtained by averaging conditional densities. Empirically, we demonstrate improved probabilistic prediction over CART-style trees and competitive performance compared to state-of-the-art probabilistic tree methods and Random Forests. --- ### DADP: Domain Adaptive Diffusion Policy Authors: Pengcheng Wang, Qinghang Liu, Haotian Lin, Yiheng Li, Guojian Zhan, Masayoshi Tomizuka, Yixiao Wang Published: 2026-02-03 Categories: cs.LG, cs.RO arXiv: https://arxiv.org/abs/2602.04037v3 Learning domain adaptive policies that can generalize to unseen transition dynamics, remains a fundamental challenge in learning-based control. Substantial progress has been made through domain representation learning to capture domain-specific information, thus enabling domain-aware decision making. We analyze the process of learning domain representations through dynamical prediction and find that selecting contexts adjacent to the current step causes the learned representations to entangle static domain information with varying dynamical properties. Such mixture can confuse the conditioned policy, thereby constraining zero-shot adaptation. To tackle the challenge, we propose DADP (Domain Adaptive Diffusion Policy), which achieves robust adaptation through unsupervised disentanglement and domain-aware diffusion injection. First, we introduce Lagged Context Dynamical Prediction, a strategy that conditions future state estimation on a historical offset context; by increasing this temporal gap, we unsupervisedly disentangle static domain representations by filtering out transient properties. Second, we integrate the learned domain representations directly into the generative process by biasing the prior distribution and reformulating the diffusion target. Extensive experiments on challenging benchmarks across locomotion and manipulation demonstrate the superior performance, and the generalizability of DADP over prior methods. More visualization results are available on the https://outsider86.github.io/DomainAdaptiveDiffusionPolicy/. --- ### On the Credibility of Evaluating LLMs using Survey Questions Authors: Jindřich Libovický Published: 2026-02-03 Categories: cs.CL, cs.AI, cs.CY arXiv: https://arxiv.org/abs/2602.04033v1 Recent studies evaluate the value orientation of large language models (LLMs) using adapted social surveys, typically by prompting models with survey questions and comparing their responses to average human responses. This paper identifies limitations in this methodology that, depending on the exact setup, can lead to both underestimating and overestimating the similarity of value orientation. Using the World Value Survey in three languages across five countries, we demonstrate that prompting methods (direct vs. chain-of-thought) and decoding strategies (greedy vs. sampling) significantly affect results. To assess the interaction between answers, we introduce a novel metric, self-correlation distance. This metric measures whether LLMs maintain consistent relationships between answers across different questions, as humans do. This indicates that even a high average agreement with human data, when considering LLM responses independently, does not guarantee structural alignment in responses. Additionally, we reveal a weak correlation between two common evaluation metrics, mean-squared distance and KL divergence, which assume that survey answers are independent of each other. For future research, we recommend CoT prompting, sampling-based decoding with dozens of samples, and robust analysis using multiple metrics, including self-correlation distance. --- ### MS-SCANet: A Multiscale Transformer-Based Architecture with Dual Attention for No-Reference Image Quality Assessment Authors: Mayesha Maliha R. Mithila, Mylene C. Q. Farias Published: 2026-02-03 Categories: eess.IV, cs.CV, cs.MM arXiv: https://arxiv.org/abs/2602.04032v1 We present the Multi-Scale Spatial Channel Attention Network (MS-SCANet), a transformer-based architecture designed for no-reference image quality assessment (IQA). MS-SCANet features a dual-branch structure that processes images at multiple scales, effectively capturing both fine and coarse details, an improvement over traditional single-scale methods. By integrating tailored spatial and channel attention mechanisms, our model emphasizes essential features while minimizing computational complexity. A key component of MS-SCANet is its cross-branch attention mechanism, which enhances the integration of features across different scales, addressing limitations in previous approaches. We also introduce two new consistency loss functions, Cross-Branch Consistency Loss and Adaptive Pooling Consistency Loss, which maintain spatial integrity during feature scaling, outperforming conventional linear and bilinear techniques. Extensive evaluations on datasets like KonIQ-10k, LIVE, LIVE Challenge, and CSIQ show that MS-SCANet consistently surpasses state-of-the-art methods, offering a robust framework with stronger correlations with subjective human scores. --- ### The Illusion of Generalization in Tabular Language Models Authors: Aditya Gorla, Ratish Puduppully Published: 2026-02-03 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.04031v2 Tabular Language Models (TLMs) have been claimed to achieve strong generalization for tabular prediction. We conduct a systematic re-evaluation of Tabula-8B as a representative TLM, utilizing 165 datasets from the UniPredict benchmark. Our investigation reveals three findings. First, binary and categorical classification achieve near-zero median lift over majority-class baselines and strong aggregate performance is driven entirely by quartile classification tasks. Second, top-performing datasets exhibit pervasive contamination, including complete train-test overlap and task-level leakage that evades standard deduplication. Third, instruction-tuning without tabular exposure recovers 92.2% of standard classification performance and on quartile classification, format familiarity closes 71.3% of the gap with the residual attributable to contaminated datasets. These findings suggest claimed generalization likely reflects evaluation artifacts rather than learned tabular reasoning. We conclude with recommendations for strengthening TLM evaluation. --- ### TiCLS : Tightly Coupled Language Text Spotter Authors: Leeje Jang, Yijun Lin, Yao-Yi Chiang, Jerod Weinman Published: 2026-02-03 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.04030v1 Scene text spotting aims to detect and recognize text in real-world images, where instances are often short, fragmented, or visually ambiguous. Existing methods primarily rely on visual cues and implicitly capture local character dependencies, but they overlook the benefits of external linguistic knowledge. Prior attempts to integrate language models either adapt language modeling objectives without external knowledge or apply pretrained models that are misaligned with the word-level granularity of scene text. We propose TiCLS, an end-to-end text spotter that explicitly incorporates external linguistic knowledge from a character-level pretrained language model. TiCLS introduces a linguistic decoder that fuses visual and linguistic features, yet can be initialized by a pretrained language model, enabling robust recognition of ambiguous or fragmented text. Experiments on ICDAR 2015 and Total-Text demonstrate that TiCLS achieves state-of-the-art performance, validating the effectiveness of PLM-guided linguistic integration for scene text spotting. --- ### PluRel: Synthetic Data unlocks Scaling Laws for Relational Foundation Models Authors: Vignesh Kothapalli, Rishabh Ranjan, Valter Hudovernik, Vijay Prakash Dwivedi, Johannes Hoffart, Carlos Guestrin, Jure Leskovec Published: 2026-02-03 Categories: cs.DB, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2602.04029v2 Relational Foundation Models (RFMs) facilitate data-driven decision-making by learning from complex multi-table databases. However, the diverse relational databases needed to train such models are rarely public due to privacy constraints. While there are methods to generate synthetic tabular data of arbitrary size, incorporating schema structure and primary-foreign key connectivity for multi-table generation remains challenging. Here we introduce PLUREL, a framework to synthesize multi-tabular relational databases from scratch. In a step-by-step fashion, PLUREL models (1) schemas with directed graphs, (2) inter-table primary-foreign key connectivity with bipartite graphs, and, (3) feature distributions in tables via conditional causal mechanisms. The design space across these stages supports the synthesis of a wide range of diverse databases, while being computationally lightweight. Using PLUREL, we observe for the first time that (1) RFM pretraining loss exhibits power-law scaling with the number of synthetic databases and total pretraining tokens, (2) scaling the number of synthetic databases improves generalization to real databases, and (3) synthetic pretraining yields strong base models for continued pretraining on real databases. Overall, our framework and results position synthetic data scaling as a promising paradigm for RFMs. --- ### Axiomatic Foundations of Counterfactual Explanations Authors: Leila Amgoud, Martin Cooper Published: 2026-02-03 Categories: cs.AI, cs.LG, stat.ME arXiv: https://arxiv.org/abs/2602.04028v1 Explaining autonomous and intelligent systems is critical in order to improve trust in their decisions. Counterfactuals have emerged as one of the most compelling forms of explanation. They address ``why not'' questions by revealing how decisions could be altered. Despite the growing literature, most existing explainers focus on a single type of counterfactual and are restricted to local explanations, focusing on individual instances. There has been no systematic study of alternative counterfactual types, nor of global counterfactuals that shed light on a system's overall reasoning process. This paper addresses the two gaps by introducing an axiomatic framework built on a set of desirable properties for counterfactual explainers. It proves impossibility theorems showing that no single explainer can satisfy certain axiom combinations simultaneously, and fully characterizes all compatible sets. Representation theorems then establish five one-to-one correspondences between specific subsets of axioms and the families of explainers that satisfy them. Each family gives rise to a distinct type of counterfactual explanation, uncovering five fundamentally different types of counterfactuals. Some of these correspond to local explanations, while others capture global explanations. Finally, the framework situates existing explainers within this taxonomy, formally characterizes their behavior, and analyzes the computational complexity of generating such explanations. --- ### A Consensus-Bayesian Framework for Detecting Malicious Activity in Enterprise Directory Access Graphs Authors: Pratyush Uppuluri, Shilpa Noushad, Sajan Kumar Published: 2026-02-03 Categories: cs.LG, cs.CR arXiv: https://arxiv.org/abs/2602.04027v2 This work presents a consensus-based Bayesian framework to detect malicious user behavior in enterprise directory access graphs. By modeling directories as topics and users as agents within a multi-level interaction graph, we simulate access evolution using influence-weighted opinion dynamics. Logical dependencies between users are encoded in dynamic matrices Ci, and directory similarity is captured via a shared influence matrix W. Malicious behavior is injected as cross-component logical perturbations that violate structural norms of strongly connected components(SCCs). We apply theoretical guarantees from opinion dynamics literature to determine topic convergence and detect anomaly via scaled opinion variance. To quantify uncertainty, we introduce a Bayesian anomaly scoring mechanism that evolves over time, using both static and online priors. Simulations over synthetic access graphs validate our method, demonstrating its sensitivity to logical inconsistencies and robustness under dynamic perturbation. --- ### Group Contrastive Learning for Weakly Paired Multimodal Data Authors: Aditya Gorla, Hugues Van Assel, Jan-Christian Huetter, Heming Yao, Kyunghyun Cho, Aviv Regev, Russell Littman Published: 2026-02-03 Categories: cs.LG, q-bio.QM, stat.ML arXiv: https://arxiv.org/abs/2602.04021v1 We present GROOVE, a semi-supervised multi-modal representation learning approach for high-content perturbation data where samples across modalities are weakly paired through shared perturbation labels but lack direct correspondence. Our primary contribution is GroupCLIP, a novel group-level contrastive loss that bridges the gap between CLIP for paired cross-modal data and SupCon for uni-modal supervised contrastive learning, addressing a fundamental gap in contrastive learning for weakly-paired settings. We integrate GroupCLIP with an on-the-fly backtranslating autoencoder framework to encourage cross-modally entangled representations while maintaining group-level coherence within a shared latent space. Critically, we introduce a comprehensive combinatorial evaluation framework that systematically assesses representation learners across multiple optimal transport aligners, addressing key limitations in existing evaluation strategies. This framework includes novel simulations that systematically vary shared versus modality-specific perturbation effects enabling principled assessment of method robustness. Our combinatorial benchmarking reveals that there is not yet an aligner that uniformly dominates across settings or modality pairs. Across simulations and two real single-cell genetic perturbation datasets, GROOVE performs on par with or outperforms existing approaches for downstream cross-modal matching and imputation tasks. Our ablation studies demonstrate that GroupCLIP is the key component driving performance gains. These results highlight the importance of leveraging group-level constraints for effective multi-modal representation learning in scenarios where only weak pairing is available. --- ### Understanding and Guiding Layer Placement in Parameter-Efficient Fine-Tuning of Large Language Models Authors: Yichen Xu, Yuyang Liang, Shan Dai, Tianyang Hu, Tsz Nam Chan, Chenhao Ma Published: 2026-02-03 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2602.04019v2 As large language models (LLMs) continue to grow, the cost of full-parameter fine-tuning has made parameter-efficient fine-tuning (PEFT) the default strategy for downstream adaptation. Constraints from inference latency in scalable serving and fine-tuning cost in edge or rapid-deployment settings make the choice of which layers to fine-tune unavoidable. Yet current practice typically applies PEFT uniformly across all layers, with limited understanding or leverage of layer selection. This paper develops a unified projected residual view of PEFT on top of a frozen base model. Under a local quadratic approximation, layerwise adaptation is governed by three quantities: (i) the projected residual norm (resnorm), which measures how much correctable bias a layer can capture; (ii) the activation energy, which determines feature conditioning; and (iii) layer coupling, which quantifies how strongly residuals interact across layers. We show that, for squared loss and linear adapters, the resnorm equals a normalized gradient norm, activation energy controls ill-conditioning and noise amplification, and weak coupling yields approximately additive layerwise contributions. Building on these insights, we introduce the Layer Card, a reusable diagnostic that summarizes residual signal strength, compute cost, and performance for each layer of a given model. With an identical model and LoRA configuration, Layer Card-guided placement refines the choice of adapted layers to flexibly prioritize different objectives, such as maximizing performance or reducing fine-tuning cost. Moreover, on Qwen3-8B, we show that selectively adapting a subset of layers can achieve performance close to full-layer LoRA while substantially reducing fine-tuning cost and the number of adapter-augmented layers during inference, offering a more cost-performance-aware alternative to full-layer insertion. --- ### Chaplains' Reflections on the Design and Usage of AI for Conversational Care Authors: Joel Wester, Samuel Rhys Cox, Henning Pohl, Niels van Berkel Published: 2026-02-03 Categories: cs.HC, cs.CL arXiv: https://arxiv.org/abs/2602.04017v1 Despite growing recognition that responsible AI requires domain knowledge, current work on conversational AI primarily draws on clinical expertise that prioritises diagnosis and intervention. However, much of everyday emotional support needs occur in non-clinical contexts, and therefore requires different conversational approaches. We examine how chaplains, who guide individuals through personal crises, grief, and reflection, perceive and engage with conversational AI. We recruited eighteen chaplains to build AI chatbots. While some chaplains viewed chatbots with cautious optimism, the majority expressed limitations of chatbots' ability to support everyday well-being. Our analysis reveals how chaplains perceive their pastoral care duties and areas where AI chatbots fall short, along the themes of Listening, Connecting, Carrying, and Wanting. These themes resonate with the idea of attunement, recently highlighted as a relational lens for understanding the delicate experiences care technologies provide. This perspective informs chatbot design aimed at supporting well-being in non-clinical contexts. --- ### A Multi-Modal Foundational Model for Wireless Communication and Sensing Authors: Vahid Yazdnian, Yasaman Ghasempour Published: 2026-02-03 Categories: eess.SP, cs.LG arXiv: https://arxiv.org/abs/2602.04016v1 Artificial intelligence is a key enabler for next-generation wireless communication and sensing. Yet, today's learning-based wireless techniques do not generalize well: most models are task-specific, environment-dependent, and limited to narrow sensing modalities, requiring costly retraining when deployed in new scenarios. This work introduces a task-agnostic, multi-modal foundational model for physical-layer wireless systems that learns transferable, physics-aware representations across heterogeneous modalities, enabling robust generalization across tasks and environments. Our framework employs a physics-guided self-supervised pretraining strategy incorporating a dedicated physical token to capture cross-modal physical correspondences governed by electromagnetic propagation. The learned representations enable efficient adaptation to diverse downstream tasks, including massive multi-antenna optimization, wireless channel estimation, and device localization, using limited labeled data. Our extensive evaluations demonstrate superior generalization, robustness to deployment shifts, and reduced data requirements compared to task-specific baselines. --- ### PromptSplit: Revealing Prompt-Level Disagreement in Generative Models Authors: Mehdi Lotfian, Mohammad Jalali, Farzan Farnia Published: 2026-02-03 Categories: cs.LG, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2602.04009v2 Prompt-guided generative AI models have rapidly expanded across vision and language domains, producing realistic and diverse outputs from textual inputs. The growing variety of such models, trained with different data and architectures, calls for principled methods to identify which types of prompts lead to distinct model behaviors. In this work, we propose PromptSplit, a kernel-based framework for detecting and analyzing prompt-dependent disagreement between generative models. For each compared model pair, PromptSplit constructs a joint prompt--output representation by forming tensor-product embeddings of the prompt and image (or text) features, and then computes the corresponding kernel covariance matrix. We utilize the eigenspace of the weighted difference between these matrices to identify the main directions of behavioral difference across prompts. To ensure scalability, we employ a random-projection approximation that reduces computational complexity to $O(nr^2 + r^3)$ for projection dimension $r$. We further provide a theoretical analysis showing that this approximation yields an eigenstructure estimate whose expected deviation from the full-dimensional result is bounded by $O(1/r^2)$. Experiments across text-to-image, text-to-text, and image-captioning settings demonstrate that PromptSplit accurately detects ground-truth behavioral differences and isolates the prompts responsible, offering an interpretable tool for detecting where generative models disagree. --- ### Rational ANOVA Networks Authors: Jusheng Zhang, Ningyuan Liu, Qinhan Lyu, Jing Yang, Keze Wang Published: 2026-02-03 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2602.04006v1 Deep neural networks typically treat nonlinearities as fixed primitives (e.g., ReLU), limiting both interpretability and the granularity of control over the induced function class. While recent additive models (like KANs) attempt to address this using splines, they often suffer from computational inefficiency and boundary instability. We propose the Rational-ANOVA Network (RAN), a foundational architecture grounded in functional ANOVA decomposition and Padé-style rational approximation. RAN models f(x) as a composition of main effects and sparse pairwise interactions, where each component is parameterized by a stable, learnable rational unit. Crucially, we enforce a strictly positive denominator, which avoids poles and numerical instability while capturing sharp transitions and near-singular behaviors more efficiently than polynomial bases. This ANOVA structure provides an explicit low-order interaction bias for data efficiency and interpretability, while the rational parameterization significantly improves extrapolation. Across controlled function benchmarks and vision classification tasks (e.g., CIFAR-10) under matched parameter and compute budgets, RAN matches or surpasses parameter-matched MLPs and learnable-activation baselines, with better stability and throughput. Code is available at https://github.com/jushengzhang/Rational-ANOVA-Networks.git. --- ### When AI Persuades: Adversarial Explanation Attacks on Human Trust in AI-Assisted Decision Making Authors: Shutong Fan, Lan Zhang, Xiaoyong Yuan Published: 2026-02-03 Categories: cs.AI arXiv: https://arxiv.org/abs/2602.04003v3 Most adversarial threats in artificial intelligence (AI) target the computational behavior of models rather than the humans who rely on them. Yet modern AI systems increasingly operate within human decision loops, where users interpret and act on model recommendations. Large Language Models (LLMs) generate fluent natural-language explanations that shape how users perceive and trust AI outputs, revealing a new attack surface at the cognitive layer: the communication channel between AI and its users. We introduce adversarial explanation attacks (AEAs), where an attacker manipulates the framing of LLM-generated explanations to modulate human trust in incorrect outputs. We formalize this behavioral threat through the trust miscalibration gap, a metric that captures the difference in human trust between benign and adversarial explanations. Using this metric as a lens, we highlight a behavioral risk where persuasive explanation framing can preserve user trust even when the underlying AI prediction is wrong. To characterize this threat, we conducted a human study with over 200 participants, systematically varying four dimensions of explanation framing: reasoning mode, evidence type, communication style, and presentation format. Our findings show that users report nearly identical trust for adversarial and benign explanations, with adversarial explanations preserving the vast majority of benign trust despite being incorrect. The most vulnerable cases arise when AEAs closely resemble expert communication, combining authoritative evidence, neutral tone, and domain-appropriate reasoning. Vulnerability is highest on hard tasks, in fact-driven domains, and among participants who are less formally educated, younger, or highly trusting of AI. --- ### Functional Stochastic Localization Authors: Anming Gu, Bobby Shi, Kevin Tian Published: 2026-02-03 Categories: math.PR, cs.DS, cs.LG, math.ST, stat.ML arXiv: https://arxiv.org/abs/2602.03999v2 Eldan's stochastic localization is a probabilistic construction that has proved instrumental to modern breakthroughs in high-dimensional geometry and the design of sampling algorithms. Motivated by sampling under non-Euclidean geometries and the mirror descent algorithm in optimization, we develop a functional generalization of Eldan's process that replaces Gaussian regularization with regularization by any positive integer multiple of a log-Laplace transform. We further give a mixing time bound on the Markov chain induced by our localization process, which holds if our target distribution satisfies a functional Poincaré inequality. Finally, we apply our framework to differentially private convex optimization in $\ell_p$ norms for $p \in (1, 2)$, where we improve state-of-the-art query complexities in a zeroth-order model. --- ### AtlasPatch: Scalable Foundation Model-based Tissue Detection and Patch Extraction for Computational Pathology Authors: Ahmed Alagha, Christopher Leclerc, Yousef Kotp, Omar Metwally, Calvin Moras, Peter Rentopoulos, Ghodsiyeh Rostami, Bich Ngoc Nguyen, Jumanah Baig, Abdelhakim Khellaf, Vincent Quoc-Huy Trinh, Rabeb Mizouni et al. Published: 2026-02-03 Categories: eess.IV, cs.CV, q-bio.QM arXiv: https://arxiv.org/abs/2602.03998v3 Whole-slide image (WSI) preprocessing, including tissue detection and patch extraction, is critical computational pathology, yet remains a major bottleneck for large-scale workflows. Existing methods often rely either on threshold-based heuristics that are sensitive to staining variations, tissue fragmentation, and artifacts, or on patch-wise deep learning pipelines with substantially higher computational cost. We present AtlasPatch, a scalable high-throughput WSI preprocessing method built around a foundation-model-based tissue detector that operates at thumbnail resolution: a single thumbnail-level forward pass yields a tissue mask that directly guides patch coordinate generation at the target desired magnification, avoiding repeated patch-level inference. The proposed detector's robustness and efficiency is driven by two coupled contributions: (i) a parameter-efficient adaptation of the SAM2 foundation model that updates only its layer-normalization parameters (0.076% of model weights), and (ii) a curated and semi-manually annotated multi-cohort dataset of 30,000 WSI thumbnail-mask pairs deliberately spanning multiple organs, scanners, tissue appearances, and artifacts. The detector is coupled with pyramid-aware contour mapping from thumbnail to full-resolution slide coordinates, enabling direct patch coordinate generation at the target magnification and parallelized high-throughput patch extraction. AtlasPatch's tissue detection achieves a precision of 0.986 and remains robust across slide variations. Compared with widely used deep-learning preprocessing methods, AtlasPatch is up to 16x faster while preserving downstream multiple-instance learning performance across six slide-level classification tasks. These results position AtlasPatch as a frontier of efficient preprocessing in large-scale computational pathology and pathology foundation models. --- ### AtlasPatch: Efficient Tissue Detection and High-throughput Patch Extraction for Computational Pathology at Scale Authors: Ahmed Alagha, Christopher Leclerc, Yousef Kotp, Omar Metwally, Calvin Moras, Peter Rentopoulos, Ghodsiyeh Rostami, Bich Ngoc Nguyen, Jumanah Baig, Abdelhakim Khellaf, Vincent Quoc-Huy Trinh, Rabeb Mizouni et al. Published: 2026-02-03 Categories: eess.IV, cs.CV, q-bio.QM arXiv: https://arxiv.org/abs/2602.03998v2 Whole-slide image (WSI) preprocessing, comprising tissue detection followed by patch extraction, is foundational to AI-driven computational pathology but remains a major bottleneck for scaling to large and heterogeneous cohorts. We present AtlasPatch, a scalable framework that couples foundation-model tissue detection with high-throughput patch extraction at minimal computational overhead. Our tissue detector achieves high precision (0.986) and remains robust across varying tissue conditions (e.g., brightness, fragmentation, boundary definition, tissue heterogeneity) and common artifacts (e.g., pen/ink markings, scanner streaks). This robustness is enabled by our annotated, heterogeneous multi-cohort training set of ~30,000 WSI thumbnails combined with efficient adaptation of the Segment-Anything (SAM) model. AtlasPatch also reduces end-to-end WSI preprocessing time by up to 16$\times$ versus widely used deep-learning pipelines, without degrading downstream task performance. The AtlasPatch tool is open-source, efficiently parallelized for practical deployment, and supports options to save extracted patches or stream them into common feature-extraction models for on-the-fly embedding, making it adaptable to both pathology departments (tissue detection and quality control) and AI researchers (dataset creation and model training). AtlasPatch software package is available at https://github.com/AtlasAnalyticsLab/AtlasPatch. --- ### Bypassing the Rationale: Causal Auditing of Implicit Reasoning in Language Models Authors: Anish Sathyanarayanan, Aditya Nagarsekar, Aarush Rathore Published: 2026-02-03 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2602.03994v3 Chain-of-thought (CoT) prompting is widely used as a reasoning aid and is often treated as a transparency mechanism. Yet behavioral gains under CoT do not imply that the model's internal computation causally depends on the emitted reasoning text, i.e. models may produce fluent rationales while routing decision-critical computation through latent pathways. We introduce a causal, layerwise audit of CoT faithfulness based on activation patching. Our key metric, the CoT Mediation Index (CMI), isolates CoT-specific causal influence by comparing performance degradation from patching CoT-token hidden states against matched control patches. Across multiple model families (Phi, Qwen, DialoGPT) and scales, we find that CoT-specific influence is typically depth-localized into narrow ''reasoning windows,'' and we identify bypass regimes where CMI is near-zero despite plausible CoT text. We further observe that models tuned explicitly for reasoning tend to exhibit stronger and more structured mediation than larger untuned counterparts, while Mixture-of-Experts models show more distributed mediation consistent with routing-based computation. Overall, our results show that CoT faithfulness varies substantially across models and tasks and cannot be inferred from behavior alone, motivating causal, layerwise audits when using CoT as a transparency signal. --- ### Bypassing the Rationale: Causal Auditing of Implicit Reasoning in Language Models Authors: Anish Sathyanarayanan, Aditya Nagarsekar, Aarush Rathore Published: 2026-02-03 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2602.03994v2 Chain-of-thought (CoT) prompting is widely used as a reasoning aid and is often treated as a transparency mechanism. Yet behavioral gains under CoT do not imply that the model's internal computation causally depends on the emitted reasoning text, i.e., models may produce fluent rationales while routing decision-critical computation through latent pathways. We introduce a causal, layerwise audit of CoT faithfulness based on activation patching. Our key metric, the CoT Mediation Index (CMI), isolates CoT-specific causal influence by comparing performance degradation from patching CoT-token hidden states against matched control patches. Across multiple model families (Phi, Qwen, DialoGPT) and scales, we find that CoT-specific influence is typically depth-localized into narrow "reasoning windows," and we identify bypass regimes where CMI is near-zero despite plausible CoT text. We further observe that models tuned explicitly for reasoning tend to exhibit stronger and more structured mediation than larger untuned counterparts, while Mixture-of-Experts models show more distributed mediation consistent with routing-based computation. Overall, our results show that CoT faithfulness varies substantially across models and tasks and cannot be inferred from behavior alone, motivating causal, layerwise audits when using CoT as a transparency signal. --- ### eCP: Equivariant Conformal Prediction with pre-trained models Authors: Nikolaos Bousias, Lars Lindemann, George Pappas Published: 2026-02-03 Categories: cs.LG, cs.RO, eess.SY arXiv: https://arxiv.org/abs/2602.03986v2 Conformal prediction, a post-hoc, distribution-free, finite-sample method of uncertainty quantification that offers formal coverage guarantees under the assumption of data exchangeability. Unfortunately, the resulting uncertainty regions can grow significantly in long horizon missions, rendering the statistical guarantees uninformative. To that end, we propose infusing CP with geometric information via group-averaging of the pretrained predictor to distribute the non-conformity mass across the orbits. Each sample now is treated as a representative of an orbit, thus uncertainty can be mitigated by other samples entangled to it via the orbit inducing elements of the symmetry group. Our approach provably yields contracted non-conformity scores in increasing convex order, implying improved exponential-tail bounds and sharper conformal prediction sets in expectation, especially at high confidence levels. We then propose an experimental design to test these theoretical claims in pedestrian trajectory prediction. --- ### Efficient Long-Horizon Vision-Language-Action Models via Static-Dynamic Disentanglement Authors: Weikang Qiu, Huashuo Lei, Tinglin Huang, Rex Ying Published: 2026-02-03 Categories: cs.RO, cs.CV arXiv: https://arxiv.org/abs/2602.03983v3 Vision-Language-Action (VLA) models have recently emerged as a promising paradigm for generalist robotic control. Built upon vision-language model (VLM) architectures, VLAs predict actions conditioned on visual observations and language instructions, achieving strong performance and generalization across tasks. However, VLAs face two major challenges: a limited context window for input frames and inefficient inference due to the quadratic attention complexity and large parameter counts. To this end, we propose DySta, a framework that disentangles visual inputs into multi-level static and dynamic tokens, which enables (1) retaining a single copy of static tokens across frames to significantly reduce context length, and (2) reusing the key-value (KV) cache of static tokens through a lightweight recache gate that updates only when necessary. This design enables efficient multi-frame integration and efficient inference. In addition, we introduce a new benchmark that more effectively evaluates the multi-frame integration ability of VLAs. Experiments show that Dysta improves multi-frame integration by 24.5% across metrics on our benchmark and 23.3% in absolute success rate on real-world memory-dependent tasks, while accelerating inference by 2.0x (with +2.3% success rate) on simulation benchmarks and 2.2x (with +10.6% success rate) on real-world general tasks. --- ### DeXposure-FM: A Time-series, Graph Foundation Model for Credit Exposures and Stability on Decentralized Financial Networks Authors: Aijie Shu, Wenbin Wu, Gbenga Ibikunle, Fengxiang He Published: 2026-02-03 Categories: cs.LG, cs.AI, econ.EM arXiv: https://arxiv.org/abs/2602.03981v2 Credit exposure in Decentralized Finance (DeFi) is often implicit and token-mediated, creating a dense web of inter-protocol dependencies. Thus, a shock to one token may result in significant and uncontrolled contagion effects. As the DeFi ecosystem becomes increasingly linked with traditional financial infrastructure through instruments, such as stablecoins, the risk posed by this dynamic demands more powerful quantification tools. We introduce DeXposure-FM, the first time-series, graph foundation model for measuring and forecasting inter-protocol credit exposure on DeFi networks, to the best of our knowledge. Employing a graph-tabular encoder, with pre-trained weight initialization, and multiple task-specific heads, DeXposure-FM is trained on the DeXposure dataset that has 43.7 million data entries, across 4,300+ protocols on 602 blockchains, covering 24,300+ unique tokens. The training is operationalized for credit-exposure forecasting, predicting the joint dynamics of (1) protocol-level flows, and (2) the topology and weights of credit-exposure links. The DeXposure-FM is empirically validated on two machine learning benchmarks; it consistently outperforms the state-of-the-art approaches, including a graph foundation model and temporal graph neural networks. DeXposure-FM further produces financial economics tools that support macroprudential monitoring and scenario-based DeFi stress testing, by enabling protocol-level systemic-importance scores, sector-level spillover and concentration measures via a forecast-then-measure pipeline. Empirical verification fully supports our financial economics tools. The model and code have been publicly available. Model: https://huggingface.co/EVIEHub/DeXposure-FM. Code: https://github.com/EVIEHub/DeXposure-FM. --- ### Transformers perform adaptive partial pooling Authors: Vsevolod Kapatsinski Published: 2026-02-03 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2602.03980v2 Any language model must decide what to say in novel contexts based on information from similar contexts. But what about contexts that are not novel but merely infrequent? In hierarchical regression, the model's predictions for behavior in a context are affected by observations from similar contexts to the extent that 1) the current context is infrequent and 2) different contexts behave similarly. This is called adaptive partial pooling. This paper shows that next-word predictions of a transformer (GPT2) are affected by observations from outside the current context, but this pooling reduces with more training. Pooling is affected by context frequency, context number (type frequency) and context variability in a qualitatively similar way to hierarchical regression. However, there is a "sweet spot" in training at which the transformer best matches the behavior of hierarchical regression. This is the point at which the effect of context frequency on pooling is at maximum. --- ### Likelihood-Based Reward Designs for General LLM Reasoning Authors: Ariel Kwiatkowski, Natasha Butt, Ismail Labiad, Julia Kempe, Yann Ollivier Published: 2026-02-03 Categories: cs.CL arXiv: https://arxiv.org/abs/2602.03979v1 Fine-tuning large language models (LLMs) on reasoning benchmarks via reinforcement learning requires a specific reward function, often binary, for each benchmark. This comes with two potential limitations: the need to design the reward, and the potentially sparse nature of binary rewards. Here, we systematically investigate rewards derived from the probability or log-probability of emitting the reference answer (or any other prompt continuation present in the data), which have the advantage of not relying on specific verifiers and being available at scale. Several recent works have advocated for the use of similar rewards (e.g., VeriFree, JEPO, RLPR, NOVER). We systematically compare variants of likelihood-based rewards with standard baselines, testing performance both on standard mathematical reasoning benchmarks, and on long-form answers where no external verifier is available. We find that using the log-probability of the reference answer as the reward for chain-of-thought (CoT) learning is the only option that performs well in all setups. This reward is also consistent with the next-token log-likelihood loss used during pretraining. In verifiable settings, log-probability rewards bring comparable or better success rates than reinforcing with standard binary rewards, and yield much better perplexity. In non-verifiable settings, they perform on par with SFT. On the other hand, methods based on probability, such as VeriFree, flatline on non-verifiable settings due to vanishing probabilities of getting the correct answer. Overall, this establishes log-probability rewards as a viable method for CoT fine-tuning, bridging the short, verifiable and long, non-verifiable answer settings. --- ### Monitorability as a Free Gift: How RLVR Spontaneously Aligns Reasoning Authors: Zidi Xiong, Shan Chen, Himabindu Lakkaraju Published: 2026-02-03 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2602.03978v1 As Large Reasoning Models (LRMs) are increasingly deployed, auditing their chain-of-thought (CoT) traces for safety becomes critical. Recent work has reported that monitorability--the degree to which CoT faithfully and informatively reflects internal computation--can appear as a "free gift" during the early stages of Reinforcement Learning with Verifiable Rewards (RLVR). We make this observation concrete through a systematic evaluation across model families and training domains. Our results show that this effect is not universal: monitorability improvements are strongly data-dependent. In particular, we demonstrate the critical role of data diversity and instruction-following data during RLVR training. We further show that monitorability is orthogonal to capability--improvements in reasoning performance do not imply increased transparency. Through mechanistic analysis, we attribute monitorability gains primarily to response distribution sharpening (entropy reduction) and increased attention to the prompt, rather than stronger causal reliance on reasoning traces. We also reveal how monitorability dynamics vary with controlled training and evaluation difficulty. Together, these findings provide a holistic view of how monitorability emerges under RLVR, clarifying when gains are likely to occur and when they are not. ---