# Research Papers — 2026-01 · bundle page 50 of 189

> Full-text markdown of papers #2451–2500 of 9403 published in 2026-01, newest first. AI-readable mirrors of the full 9403-paper 2026-01 archive (50 papers per file).

Canonical page: https://aipod.dev/papers/archive/2026-01/page/50
[← Previous bundle](https://aipod.dev/papers/archive/2026-01/page/49.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-01/page/51.md)

### Out-of-Distribution Radar Detection with Complex VAEs: Theory, Whitening, and ANMF Fusion

Authors: Yadang Alexis Rouzoumka, Jean Pinsolle, Eugénie Terreaux, Christèle Morisseau, Jean-Philippe Ovarlez, Chengfang Ren
Published: 2026-01-26
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2601.18677v1

We investigate the detection of weak complex-valued signals immersed in non-Gaussian, range-varying interference, with emphasis on maritime radar scenarios. The proposed methodology exploits a Complex-valued Variational AutoEncoder (CVAE) trained exclusively on clutter-plus-noise to perform Out-Of-Distribution detection. By operating directly on in-phase / quadrature samples, the CVAE preserves phase and Doppler structure and is assessed in two configurations: (i) using unprocessed range profiles and (ii) after local whitening, where per-range covariance estimates are obtained from neighboring profiles. Using extensive simulations together with real sea-clutter data from the CSIR maritime dataset, we benchmark performance against classical and adaptive detectors (MF, NMF, AMF-SCM, ANMF-SCM, ANMF-Tyler). In both configurations, the CVAE yields a higher detection probability Pd at matched false-alarm rate Pfa, with the most notable improvements observed under whitening. We further integrate the CVAE with the ANMF through a weighted log-p fusion rule at the decision level, attaining enhanced robustness in strongly non-Gaussian clutter and enabling empirically calibrated Pfa control under H0. Overall, the results demonstrate that statistical normalization combined with complex-valued generative modeling substantively improves detection in realistic sea-clutter conditions, and that the fused CVAE-ANMF scheme constitutes a competitive alternative to established model-based detectors.

---

### Quasi Monte Carlo methods enable extremely low-dimensional deep generative models

Authors: Miles Martinez, Alex H. Williams
Published: 2026-01-26
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.18676v1

This paper introduces quasi-Monte Carlo latent variable models (QLVMs): a class of deep generative models that are specialized for finding extremely low-dimensional and interpretable embeddings of high-dimensional datasets. Unlike standard approaches, which rely on a learned encoder and variational lower bounds, QLVMs directly approximate the marginal likelihood by randomized quasi-Monte Carlo integration. While this brute force approach has drawbacks in higher-dimensional spaces, we find that it excels in fitting one, two, and three dimensional deep latent variable models. Empirical results on a range of datasets show that QLVMs consistently outperform conventional variational autoencoders (VAEs) and importance weighted autoencoders (IWAEs) with matched latent dimensionality. The resulting embeddings enable transparent visualization and post hoc analyses such as nonparametric density estimation, clustering, and geodesic path computation, which are nontrivial to validate in higher-dimensional spaces. While our approach is compute-intensive and struggles to generate fine-scale details in complex datasets, it offers a compelling solution for applications prioritizing interpretability and latent space analysis.

---

### Learning temporal embeddings from electronic health records of chronic kidney disease patients

Authors: Aditya Kumar, Mario A. Cypko, Oliver Amft
Published: 2026-01-26
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2601.18675v2

We investigate whether temporal embedding models trained on longitudinal electronic health records can learn clinically meaningful representations without compromising predictive performance, and how architectural choices affect embedding quality. Model-guided medicine requires representations that capture disease dynamics while remaining transparent and task agnostic, whereas most clinical prediction models are optimised for a single task. Representation learning facilitates learning embeddings that generalise across downstream tasks, and recurrent architectures are well-suited for modelling temporal structure in observational clinical data. Using the MIMIC-IV dataset, we study patients with chronic kidney disease (CKD) and compare three recurrent architectures: a vanilla LSTM, an attention-augmented LSTM, and a time-aware LSTM (T-LSTM). All models are trained both as embedding models and as direct end-to-end predictors. Embedding quality is evaluated via CKD stage clustering and in-ICU mortality prediction. The T-LSTM produces more structured embeddings, achieving a lower Davies-Bouldin Index (DBI = 9.91) and higher CKD stage classification accuracy (0.74) than the vanilla LSTM (DBI = 15.85, accuracy = 0.63) and attention-augmented LSTM (DBI = 20.72, accuracy = 0.67). For in-ICU mortality prediction, embedding models consistently outperform end-to-end predictors, improving accuracy from 0.72-0.75 to 0.82-0.83, which indicates that learning embeddings as an intermediate step is more effective than direct end-to-end learning.

---

### A Dynamic Framework for Grid Adaptation in Kolmogorov-Arnold Networks

Authors: Spyros Rigas, Thanasis Papaioannou, Panagiotis Trakadas, Georgios Alexandridis
Published: 2026-01-26
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.18672v3

Kolmogorov-Arnold Networks (KANs) have recently demonstrated promising potential in scientific machine learning, partly due to their capacity for grid adaptation during training. However, existing adaptation strategies rely solely on input data density, failing to account for the geometric complexity of the target function or metrics calculated during network training. In this work, we propose a generalized framework that treats knot allocation as a density estimation task governed by Importance Density Functions (IDFs), allowing training dynamics to determine grid resolution. We introduce a curvature-based adaptation strategy and evaluate it across synthetic function fitting, regression on a subset of the Feynman dataset and different instances of the Helmholtz PDE, demonstrating that it significantly outperforms the standard input-based baseline. Specifically, our method yields average relative error reductions of 25.3% on synthetic functions, 9.4% on the Feynman dataset, and 23.3% on the PDE benchmark. Statistical significance is confirmed via Wilcoxon signed-rank tests, establishing curvature-based adaptation as a robust and computationally efficient alternative for KAN training.

---

### Uniform Computability of PAC Learning

Authors: Vasco Brattka, Guillaume Chirache
Published: 2026-01-26
Categories: math.LO, cs.LG, cs.LO
arXiv: https://arxiv.org/abs/2601.18663v1

We study uniform computability properties of PAC learning using Weihrauch complexity. We focus on closed concept classes, which are either represented by positive, by negative or by full information. Among other results, we prove that proper PAC learning from positive information is equivalent to the limit operation on Baire space, whereas improper PAC learning from positive information is closely related to Weak Kőnig's Lemma and even equivalent to it, when we have some negative information about the admissible hypotheses. If arbitrary hypotheses are allowed, then improper PAC learning from positive information is still in a finitary DNC range, which implies that it is non-deterministically computable, but does not allow for probabilistic algorithms. These results can also be seen as a classification of the degree of constructivity of the Fundamental Theorem of Statistical Learning. All the aforementioned results hold if an upper bound of the VC dimension is provided as an additional input information. We also study the question of how these results are affected if the VC dimension is not given, but only promised to be finite or if concept classes are represented by negative or full information. Finally, we also classify the complexity of the VC dimension operation itself, which is a problem that is of independent interest. For positive or full information it turns out to be equivalent to the binary sorting problem, for negative information it is equivalent to the jump of sorting. This classification allows also conclusions regarding the Borel complexity of PAC learnability.

---

### Contrasting Global and Patient-Specific Regression Models via a Neural Network Representation

Authors: Max Behrens, Daiana Stolz, Eleni Papakonstantinou, Janis M. Nolde, Gabriele Bellerino, Angelika Rohde, Moritz Hess, Harald Binder
Published: 2026-01-26
Categories: stat.ME, stat.ML
arXiv: https://arxiv.org/abs/2601.18658v1

When developing clinical prediction models, it can be challenging to balance between global models that are valid for all patients and personalized models tailored to individuals or potentially unknown subgroups. To aid such decisions, we propose a diagnostic tool for contrasting global regression models and patient-specific (local) regression models. The core utility of this tool is to identify where and for whom a global model may be inadequate. We focus on regression models and specifically suggest a localized regression approach that identifies regions in the predictor space where patients are not well represented by the global model. As localization becomes challenging when dealing with many predictors, we propose modeling in a dimension-reduced latent representation obtained from an autoencoder. Using such a neural network architecture for dimension reduction enables learning a latent representation simultaneously optimized for both good data reconstruction and for revealing local outcome-related associations suitable for robust localized regression. We illustrate the proposed approach with a clinical study involving patients with chronic obstructive pulmonary disease. Our findings indicate that the global model is adequate for most patients but that indeed specific subgroups benefit from personalized models. We also demonstrate how to map these subgroup models back to the original predictors, providing insight into why the global model falls short for these groups. Thus, the principal application and diagnostic yield of our tool is the identification and characterization of patients or subgroups whose outcome associations deviate from the global model.

---

### FaLW: A Forgetting-aware Loss Reweighting for Long-tailed Unlearning

Authors: Liheng Yu, Zhe Zhao, Yuxuan Wang, Pengkun Wang, Xiaofeng Cao, Binwu Wang, Yang Wang
Published: 2026-01-26
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2601.18650v2

Machine unlearning, which aims to efficiently remove the influence of specific data from trained models, is crucial for upholding data privacy regulations like the ``right to be forgotten". However, existing research predominantly evaluates unlearning methods on relatively balanced forget sets. This overlooks a common real-world scenario where data to be forgotten, such as a user's activity records, follows a long-tailed distribution. Our work is the first to investigate this critical research gap. We find that in such long-tailed settings, existing methods suffer from two key issues: \textit{Heterogeneous Unlearning Deviation} and \textit{Skewed Unlearning Deviation}. To address these challenges, we propose FaLW, a plug-and-play, instance-wise dynamic loss reweighting method. FaLW innovatively assesses the unlearning state of each sample by comparing its predictive probability to the distribution of unseen data from the same class. Based on this, it uses a forgetting-aware reweighting scheme, modulated by a balancing factor, to adaptively adjust the unlearning intensity for each sample. Extensive experiments demonstrate that FaLW achieves superior performance.

---

### FadeMem: Biologically-Inspired Forgetting for Efficient Agent Memory

Authors: Lei Wei, Xiao Peng, Xu Dong, Niantao Xie, Bin Wang
Published: 2026-01-26
Categories: cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2601.18642v2

Large language models deployed as autonomous agents face critical memory limitations, lacking selective forgetting mechanisms that lead to either catastrophic forgetting at context boundaries or information overload within them. While human memory naturally balances retention and forgetting through adaptive decay processes, current AI systems employ binary retention strategies that preserve everything or lose it entirely. We propose FadeMem, a biologically-inspired agent memory architecture that incorporates active forgetting mechanisms mirroring human cognitive efficiency. FadeMem implements differential decay rates across a dual-layer memory hierarchy, where retention is governed by adaptive exponential decay functions modulated by semantic relevance, access frequency, and temporal patterns. Through LLM-guided conflict resolution and intelligent memory fusion, our system consolidates related information while allowing irrelevant details to fade. Experiments on Multi-Session Chat, LoCoMo, and LTI-Bench demonstrate superior multi-hop reasoning and retrieval with 45\% storage reduction, validating the effectiveness of biologically-inspired forgetting in agent memory systems.

---

### Unheard in the Digital Age: Rethinking AI Bias and Speech Diversity

Authors: Onyedikachi Hope Amaechi-Okorie, Branislav Radeljic
Published: 2026-01-26
Categories: cs.HC, cs.AI, cs.CY
arXiv: https://arxiv.org/abs/2601.18641v2

Speech remains one of the most visible yet overlooked vectors of inclusion and exclusion in contemporary society. While fluency is often equated with credibility and competence, individuals with atypical speech patterns are routinely marginalized. Given the current state of the debate, this article focuses on the structural biases that shape perceptions of atypical speech and are now being encoded into artificial intelligence. Automated speech recognition (ASR) systems and voice interfaces, trained predominantly on standardized speech, routinely fail to recognize or respond to diverse voices, compounding digital exclusion. As AI technologies increasingly mediate access to opportunity, the study calls for inclusive technological design, anti-bias training to minimize the impact of discriminatory algorithmic decisions, and enforceable policy reform that explicitly recognize speech diversity as a matter of equity, not merely accessibility. Drawing on interdisciplinary research, the article advocates for a cultural and institutional shift in how we value voice, urging co-created solutions that elevate the rights, representation, and realities of atypical speakers in the digital age. Ultimately, the article reframes speech inclusion as a matter of equity (not accommodation) and advocates for co-created AI systems that reflect the full spectrum of human voices.

---

### TwinPurify: Purifying gene expression data to reveal tumor-intrinsic transcriptional programs via self-supervised learning

Authors: Zhiwei Zheng, Kevin Bryson
Published: 2026-01-26
Categories: cs.LG, q-bio.MN
arXiv: https://arxiv.org/abs/2601.18640v2

Advances in single-cell and spatial transcriptomic technologies have transformed tumor ecosystem profiling at cellular resolution. However, large scale studies on patient cohorts continue to rely on bulk transcriptomic data, where variation in tumor purity obscures tumor-intrinsic transcriptional signals and constrains downstream discovery. Many deconvolution methods report strong performance on synthetic bulk mixtures but fail to generalize to real patient cohorts because of unmodeled biological and technical variation. Here, we introduce TwinPurify, a representation learning framework that adapts the Barlow Twins self-supervised objective, representing a fundamental departure from the deconvolution paradigm. Rather than resolving the bulk mixture into discrete cell-type fractions, TwinPurify instead learns continuous, high-dimensional tumor embeddings by leveraging adjacent-normal profiles within the same cohort as "background" guidance, enabling the disentanglement of tumor-specific signals without relying on any external reference. Benchmarked against multiple large cancer cohorts across RNA-seq and microarray platforms, TwinPurify outperforms conventional representation learning baselines like auto-encoders in recovering tumor-intrinsic and immune signals. The purified embeddings improve molecular subtype and grade classification, enhance survival model concordance, and uncover biologically meaningful pathway activities compared to raw bulk profiles. By providing a transferable framework for decontaminating bulk transcriptomics, TwinPurify extends the utility of existing clinical datasets for molecular discovery.

---

### Physics-Informed Uncertainty Enables Reliable AI-driven Design

Authors: Tingkai Xue, Chin Chun Ooi, Yang Jiang, Luu Trung Pham Duong, Pao-Hsiung Chiu, Weijiang Zhao, Nagarajan Raghavan, My Ha Dao
Published: 2026-01-26
Categories: cs.LG, physics.comp-ph
arXiv: https://arxiv.org/abs/2601.18638v1

Inverse design is a central goal in much of science and engineering, including frequency-selective surfaces (FSS) that are critical to microelectronics for telecommunications and optical metamaterials. Traditional surrogate-assisted optimization methods using deep learning can accelerate the design process but do not usually incorporate uncertainty quantification, leading to poorer optimization performance due to erroneous predictions in data-sparse regions. Here, we introduce and validate a fundamentally different paradigm of Physics-Informed Uncertainty, where the degree to which a model's prediction violates fundamental physical laws serves as a computationally-cheap and effective proxy for predictive uncertainty. By integrating physics-informed uncertainty into a multi-fidelity uncertainty-aware optimization workflow to design complex frequency-selective surfaces within the 20 - 30 GHz range, we increase the success rate of finding performant solutions from less than 10% to over 50%, while simultaneously reducing computational cost by an order of magnitude compared to the sole use of a high-fidelity solver. These results highlight the necessity of incorporating uncertainty quantification in machine-learning-driven inverse design for high-dimensional problems, and establish physics-informed uncertainty as a viable alternative to quantifying uncertainty in surrogate models for physical systems, thereby setting the stage for autonomous scientific discovery systems that can efficiently and robustly explore and evaluate candidate designs.

---

### Universality of Many-body Projected Ensemble for Learning Quantum Data Distribution

Authors: Quoc Hoan Tran, Koki Chinzei, Yasuhiro Endo, Hirotaka Oshima
Published: 2026-01-26
Categories: quant-ph, cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2601.18637v2

Generating quantum data by learning the underlying quantum distribution poses challenges in both theoretical and practical scenarios, yet it is a critical task for understanding quantum systems. A fundamental question in quantum machine learning (QML) is the universality of approximation: whether a parameterized QML model can approximate any quantum distribution. We address this question by proving a universality theorem for the Many-body Projected Ensemble (MPE) framework, a method for quantum state design that uses a single many-body wave function to prepare random states. This demonstrates that MPE can approximate any distribution of pure states within a 1-Wasserstein distance error. This theorem provides a rigorous guarantee of universal expressivity, addressing key theoretical gaps in QML. For practicality, we propose an Incremental MPE variant with layer-wise training to improve the trainability. Numerical experiments on clustered quantum states and quantum chemistry datasets validate MPE's efficacy in learning complex quantum data distributions.

---

### Splat-Portrait: Generalizing Talking Heads with Gaussian Splatting

Authors: Tong Shi, Melonie de Almeida, Daniela Ivanova, Nicolas Pugeault, Paul Henderson
Published: 2026-01-26
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.18633v1

Talking Head Generation aims at synthesizing natural-looking talking videos from speech and a single portrait image. Previous 3D talking head generation methods have relied on domain-specific heuristics such as warping-based facial motion representation priors to animate talking motions, yet still produce inaccurate 3D avatar reconstructions, thus undermining the realism of generated animations. We introduce Splat-Portrait, a Gaussian-splatting-based method that addresses the challenges of 3D head reconstruction and lip motion synthesis. Our approach automatically learns to disentangle a single portrait image into a static 3D reconstruction represented as static Gaussian Splatting, and a predicted whole-image 2D background. It then generates natural lip motion conditioned on input audio, without any motion driven priors. Training is driven purely by 2D reconstruction and score-distillation losses, without 3D supervision nor landmarks. Experimental results demonstrate that Splat-Portrait exhibits superior performance on talking head generation and novel view synthesis, achieving better visual quality compared to previous works. Our project code and supplementary documents are public available at https://github.com/stonewalking/Splat-portrait.

---

### AdaReasoner: Dynamic Tool Orchestration for Iterative Visual Reasoning

Authors: Mingyang Song, Haoyu Sun, Jiawei Gu, Linjie Li, Luxin Xu, Ranjay Krishna, Yu Cheng
Published: 2026-01-26
Categories: cs.AI, cs.CL, cs.CV, cs.MA
arXiv: https://arxiv.org/abs/2601.18631v2

When humans face problems beyond their immediate capabilities, they rely on tools, providing a promising paradigm for improving visual reasoning in multimodal large language models (MLLMs). Effective reasoning, therefore, hinges on knowing which tools to use, when to invoke them, and how to compose them over multiple steps, even when faced with new tools or new tasks. We introduce \textbf{AdaReasoner}, a family of multimodal models that learn tool use as a general reasoning skill rather than as tool-specific or explicitly supervised behavior. AdaReasoner is enabled by (i) a scalable data curation pipeline exposing models to long-horizon, multi-step tool interactions; (ii) Tool-GRPO, a reinforcement learning algorithm that optimizes tool selection and sequencing based on end-task success; and (iii) an adaptive learning mechanism that dynamically regulates tool usage. Together, these components allow models to infer tool utility from task context and intermediate outcomes, enabling coordination of multiple tools and generalization to unseen tools. Empirically, AdaReasoner exhibits strong tool-adaptive and generalization behaviors: it autonomously adopts beneficial tools, suppresses irrelevant ones, and adjusts tool usage frequency based on task demands, despite never being explicitly trained to do so. These capabilities translate into state-of-the-art performance across challenging benchmarks, improving the 7B base model by +24.9\% on average and surpassing strong proprietary systems such as GPT-5 on multiple tasks, including VSP and Jigsaw.

---

### Assessing the Quality of Mental Health Support in LLM Responses through Multi-Attribute Human Evaluation

Authors: Abeer Badawi, Md Tahmid Rahman Laskar, Elahe Rahimi, Sheri Grach, Lindsay Bertrand, Lames Danok, Frank Rudzicz, Jimmy Huang, Elham Dolatabadi
Published: 2026-01-26
Categories: cs.AI, cs.HC
arXiv: https://arxiv.org/abs/2601.18630v1

The escalating global mental health crisis, marked by persistent treatment gaps, availability, and a shortage of qualified therapists, positions Large Language Models (LLMs) as a promising avenue for scalable support. While LLMs offer potential for accessible emotional assistance, their reliability, therapeutic relevance, and alignment with human standards remain challenging to address. This paper introduces a human-grounded evaluation methodology designed to assess LLM generated responses in therapeutic dialogue. Our approach involved curating a dataset of 500 mental health conversations from datasets with real-world scenario questions and evaluating the responses generated by nine diverse LLMs, including closed source and open source models. More specifically, these responses were evaluated by two psychiatric trained experts, who independently rated each on a 5 point Likert scale across a comprehensive 6 attribute rubric. This rubric captures Cognitive Support and Affective Resonance, providing a multidimensional perspective on therapeutic quality. Our analysis reveals that LLMs provide strong cognitive reliability by producing safe, coherent, and clinically appropriate information, but they demonstrate unstable affective alignment. Although closed source models (e.g., GPT-4o) offer balanced therapeutic responses, open source models show greater variability and emotional flatness. We reveal a persistent cognitive-affective gap and highlight the need for failure aware, clinically grounded evaluation frameworks that prioritize relational sensitivity alongside informational accuracy in mental health oriented LLMs. We advocate for balanced evaluation protocols with human in the loop that center on therapeutic sensitivity and provide a framework to guide the responsible design and clinical oversight of mental health oriented conversational AI.

---

### Rank-1 Approximation of Inverse Fisher for Natural Policy Gradients in Deep Reinforcement Learning

Authors: Yingxiao Huo, Satya Prakash Dash, Radu Stoican, Samuel Kaski, Mingfei Sun
Published: 2026-01-26
Categories: cs.LG, cs.AI, stat.ML
arXiv: https://arxiv.org/abs/2601.18626v3

Natural gradients have long been studied in deep reinforcement learning due to their fast convergence properties and covariant weight updates. However, computing natural gradients requires inversion of the Fisher Information Matrix (FIM) at each iteration, which is computationally prohibitive in nature. In this paper, we present an efficient and scalable natural policy optimization technique that leverages a rank-1 approximation to full inverse-FIM. We theoretically show that under certain conditions, a rank-1 approximation to inverse-FIM converges faster than policy gradients and, under some conditions, enjoys the same sample complexity as stochastic policy gradient methods. We benchmark our method on a diverse set of environments and show that it achieves superior performance to standard actor-critic and trust-region baselines.

---

### CONQUER: Context-Aware Representation with Query Enhancement for Text-Based Person Search

Authors: Zequn Xie
Published: 2026-01-26
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.18625v1

Text-Based Person Search (TBPS) aims to retrieve pedestrian images from large galleries using natural language descriptions. This task, essential for public safety applications, is hindered by cross-modal discrepancies and ambiguous user queries. We introduce CONQUER, a two-stage framework designed to address these challenges by enhancing cross-modal alignment during training and adaptively refining queries at inference. During training, CONQUER employs multi-granularity encoding, complementary pair mining, and context-guided optimal matching based on Optimal Transport to learn robust embeddings. At inference, a plug-and-play query enhancement module refines vague or incomplete queries via anchor selection and attribute-driven enrichment, without requiring retraining of the backbone. Extensive experiments on CUHK-PEDES, ICFG-PEDES, and RSTPReid demonstrate that CONQUER consistently outperforms strong baselines in both Rank-1 accuracy and mAP, yielding notable improvements in cross-domain and incomplete-query scenarios. These results highlight CONQUER as a practical and effective solution for real-world TBPS deployment. Source code is available at https://github.com/zqxie77/CONQUER.

---

### Adaptive Domain Shift in Diffusion Models for Cross-Modality Image Translation

Authors: Zihao Wang, Yuzhou Chen, Shaogang Ren
Published: 2026-01-26
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.18623v2

Cross-modal image translation remains brittle and inefficient. Standard diffusion approaches often rely on a single, global linear transfer between domains. We find that this shortcut forces the sampler to traverse off-manifold, high-cost regions, inflating the correction burden and inviting semantic drift. We refer to this shared failure mode as fixed-schedule domain transfer. In this paper, we embed domain-shift dynamics directly into the generative process. Our model predicts a spatially varying mixing field at every reverse step and injects an explicit, target-consistent restoration term into the drift. This in-step guidance keeps large updates on-manifold and shifts the model's role from global alignment to local residual correction. We provide a continuous-time formulation with an exact solution form and derive a practical first-order sampler that preserves marginal consistency. Empirically, across translation tasks in medical imaging, remote sensing, and electroluminescence semantic mapping, our framework improves structural fidelity and semantic consistency while converging in fewer denoising steps.

---

### CASSANDRA: Programmatic and Probabilistic Learning and Inference for Stochastic World Modeling

Authors: Panagiotis Lymperopoulos, Abhiramon Rajasekharan, Ian Berlot-Attwell, Stéphane Aroca-Ouellette, Kaheer Suleman
Published: 2026-01-26
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.18620v1

Building world models is essential for planning in real-world domains such as businesses. Since such domains have rich semantics, we can leverage world knowledge to effectively model complex action effects and causal relationships from limited data. In this work, we propose CASSANDRA, a neurosymbolic world modeling approach that leverages an LLM as a knowledge prior to construct lightweight transition models for planning. CASSANDRA integrates two components: (1) LLM-synthesized code to model deterministic features, and (2) LLM-guided structure learning of a probabilistic graphical model to capture causal relationships among stochastic variables. We evaluate CASSANDRA in (i) a small-scale coffee-shop simulator and (ii) a complex theme park business simulator, where we demonstrate significant improvements in transition prediction and planning over baselines.

---

### Scale-Aware Self-Supervised Learning for Segmentation of Small and Sparse Structures

Authors: Jorge Quesada, Ghassan AlRegib
Published: 2026-01-26
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.18619v1

Self-supervised learning (SSL) has emerged as a powerful strategy for representation learning under limited annotation regimes, yet its effectiveness remains highly sensitive to many factors, especially the nature of the target task. In segmentation, existing pipelines are typically tuned to large, homogeneous regions, but their performance drops when objects are small, sparse, or locally irregular. In this work, we propose a scale-aware SSL adaptation that integrates small-window cropping into the augmentation pipeline, zooming in on fine-scale structures during pretraining. We evaluate this approach across two domains with markedly different data modalities: seismic imaging, where the goal is to segment sparse faults, and neuroimaging, where the task is to delineate small cellular structures. In both settings, our method yields consistent improvements over standard and state-of-the-art baselines under label constraints, improving accuracy by up to 13% for fault segmentation and 5% for cell delineation. In contrast, large-scale features such as seismic facies or tissue regions see little benefit, underscoring that the value of SSL depends critically on the scale of the target objects. Our findings highlight the need to align SSL design with object size and sparsity, offering a general principle for buil ding more effective representation learning pipelines across scientific imaging domains.

---

### Emergence of Phonemic, Syntactic, and Semantic Representations in Artificial Neural Networks

Authors: Pierre Orhan, Pablo Diego-Simón, Emmnanuel Chemla, Yair Lakretz, Yves Boubenec, Jean-Rémi King
Published: 2026-01-26
Categories: cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2601.18617v1

During language acquisition, children successively learn to categorize phonemes, identify words, and combine them with syntax to form new meaning. While the development of this behavior is well characterized, we still lack a unifying computational framework to explain its underlying neural representations. Here, we investigate whether and when phonemic, lexical, and syntactic representations emerge in the activations of artificial neural networks during their training. Our results show that both speech- and text-based models follow a sequence of learning stages: during training, their neural activations successively build subspaces, where the geometry of the neural activations represents phonemic, lexical, and syntactic structure. While this developmental trajectory qualitatively relates to children's, it is quantitatively different: These algorithms indeed require two to four orders of magnitude more data for these neural representations to emerge. Together, these results show conditions under which major stages of language acquisition spontaneously emerge, and hence delineate a promising path to understand the computations underpinning language acquisition.

---

### Geometry-Free Conditional Diffusion Modeling for Solving the Inverse Electrocardiography Problem

Authors: Ramiro Valdes Jara, Adam Meyers
Published: 2026-01-26
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.18615v1

This paper proposes a data-driven model for solving the inverse problem of electrocardiography, the mathematical problem that forms the basis of electrocardiographic imaging (ECGI). We present a conditional diffusion framework that learns a probabilistic mapping from noisy body surface signals to heart surface electric potentials. The proposed approach leverages the generative nature of diffusion models to capture the non-unique and underdetermined nature of the ECGI inverse problem, enabling probabilistic sampling of multiple reconstructions rather than a single deterministic estimate. Unlike traditional methods, the proposed framework is geometry-free and purely data-driven, alleviating the need for patient-specific mesh construction. We evaluate the method on a real ECGI dataset and compare it against strong deterministic baselines, including a convolutional neural network, long short-term memory network, and transformer-based model. The results demonstrate that the proposed diffusion approach achieves improved reconstruction accuracy, highlighting the potential of diffusion models as a robust tool for noninvasive cardiac electrophysiology imaging.

---

### Multimodal Privacy-Preserving Entity Resolution with Fully Homomorphic Encryption

Authors: Susim Roy, Nalini Ratha
Published: 2026-01-26
Categories: cs.CR, cs.CV
arXiv: https://arxiv.org/abs/2601.18612v1

The canonical challenge of entity resolution within high-compliance sectors, where secure identity reconciliation is frequently confounded by significant data heterogeneity, including syntactic variations in personal identifiers, is a longstanding and complex problem. To this end, we introduce a novel multimodal framework operating with the voluminous data sets typical of government and financial institutions. Specifically, our methodology is designed to address the tripartite challenge of data volume, matching fidelity, and privacy. Consequently, the underlying plaintext of personally identifiable information remains computationally inaccessible throughout the matching lifecycle, empowering institutions to rigorously satisfy stringent regulatory mandates with cryptographic assurances of client confidentiality while achieving a demonstrably low equal error rate and maintaining computational tractability at scale.

---

### PolySHAP: Extending KernelSHAP with Interaction-Informed Polynomial Regression

Authors: Fabian Fumagalli, R. Teal Witter, Christopher Musco
Published: 2026-01-26
Categories: cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2601.18608v3

Shapley values have emerged as a central game-theoretic tool in explainable AI (XAI). However, computing Shapley values exactly requires $2^d$ game evaluations for a model with $d$ features. Lundberg and Lee's KernelSHAP algorithm has emerged as a leading method for avoiding this exponential cost. KernelSHAP approximates Shapley values by approximating the game as a linear function, which is fit using a small number of game evaluations for random feature subsets. In this work, we extend KernelSHAP by approximating the game via higher degree polynomials, which capture non-linear interactions between features. Our resulting PolySHAP method yields empirically better Shapley value estimates for various benchmark datasets, and we prove that these estimates are consistent. Moreover, we connect our approach to paired sampling (antithetic sampling), a ubiquitous modification to KernelSHAP that improves empirical accuracy. We prove that paired sampling outputs exactly the same Shapley value approximations as second-order PolySHAP, without ever fitting a degree 2 polynomial. To the best of our knowledge, this finding provides the first strong theoretical justification for the excellent practical performance of the paired sampling heuristic.

---

### LaCoGSEA: Unsupervised deep learning for pathway analysis via latent correlation

Authors: Zhiwei Zheng, Kevin Bryson
Published: 2026-01-26
Categories: cs.LG, q-bio.GN
arXiv: https://arxiv.org/abs/2601.18604v2

Motivation: Pathway enrichment analysis is widely used to interpret gene expression data. Standard approaches, such as GSEA, rely on predefined phenotypic labels and pairwise comparisons, which limits their applicability in unsupervised settings. Existing unsupervised extensions, including single-sample methods, provide pathway-level summaries but primarily capture linear relationships and do not explicitly model gene-pathway associations. More recently, deep learning models have been explored to capture non-linear transcriptomic structure. However, their interpretation has typically relied on generic explainable AI (XAI) techniques designed for feature-level attribution. As these methods are not designed for pathway-level interpretation in unsupervised transcriptomic analyses, their effectiveness in this setting remains limited. Results: To bridge this gap, we introduce LaCoGSEA (Latent Correlation GSEA), an unsupervised framework that integrates deep representation learning with robust pathway statistics. LaCoGSEA employs an autoencoder to capture non-linear manifolds and proposes a global gene-latent correlation metric as a proxy for differential expression, generating dense gene rankings without prior labels. We demonstrate that LaCoGSEA offers three key advantages: (i) it achieves improved clustering performance in distinguishing cancer subtypes compared to existing unsupervised baselines; (ii) it recovers a broader range of biologically meaningful pathways at higher ranks compared with linear dimensionality reduction and gradient-based XAI methods; and (iii) it maintains high robustness and consistency across varying experimental protocols and dataset sizes. Overall, LaCoGSEA provides state-of-the-art performance in unsupervised pathway enrichment analysis. Availability and implementation: https://github.com/willyzzz/LaCoGSEA

---

### EFSI-DETR: Efficient Frequency-Semantic Integration for Real-Time Small Object Detection in UAV Imagery

Authors: Yu Xia, Chang Liu, Tianqi Xiang, Zhigang Tu
Published: 2026-01-26
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.18597v2

Real-time small object detection in Unmanned Aerial Vehicle (UAV) imagery remains challenging due to limited feature representation and ineffective multi-scale fusion. Existing methods underutilize frequency information and rely on static convolutional operations, which constrain the capacity to obtain rich feature representations and hinder the effective exploitation of deep semantic features. To address these issues, we propose EFSI-DETR, a novel detection framework that integrates efficient semantic feature enhancement with dynamic frequency-spatial guidance. EFSI-DETR comprises two main components: (1) a Dynamic Frequency-Spatial Unified Synergy Network (DyFusNet) that jointly exploits frequency and spatial cues for robust multi-scale feature fusion, (2) an Efficient Semantic Feature Concentrator (ESFC) that enables deep semantic extraction with minimal computational cost. Furthermore, a Fine-grained Feature Retention (FFR) strategy is adopted to incorporate spatially rich shallow features during fusion to preserve fine-grained details, crucial for small object detection in UAV imagery. Extensive experiments on VisDrone and CODrone benchmarks demonstrate that our EFSI-DETR achieves the state-of-the-art performance with real-time efficiency, yielding improvement of \textbf{1.6}\% and \textbf{5.8}\% in AP and AP$_{s}$ on VisDrone, while obtaining \textbf{188} FPS inference speed on a single RTX 4090 GPU.

---

### A Balanced Neuro-Symbolic Approach for Commonsense Abductive Logic

Authors: Joseph Cotnareanu, Didier Chetelat, Yingxue Zhang, Mark Coates
Published: 2026-01-26
Categories: cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2601.18595v1

Although Large Language Models (LLMs) have demonstrated impressive formal reasoning abilities, they often break down when problems require complex proof planning. One promising approach for improving LLM reasoning abilities involves translating problems into formal logic and using a logic solver. Although off-the-shelf logic solvers are in principle substantially more efficient than LLMs at logical reasoning, they assume that all relevant facts are provided in a question and are unable to deal with missing commonsense relations. In this work, we propose a novel method that uses feedback from the logic solver to augment a logic problem with commonsense relations provided by the LLM, in an iterative manner. This involves a search procedure through potential commonsense assumptions to maximize the chance of finding useful facts while keeping cost tractable. On a collection of pure-logical reasoning datasets, from which some commonsense information has been removed, our method consistently achieves considerable improvements over existing techniques, demonstrating the value in balancing neural and symbolic elements when working in human contexts.

---

### Global Optimization of Atomic Clusters via Physically-Constrained Tensor Train Decomposition

Authors: Konstantin Sozykin, Nikita Rybin, Andrei Chertkov, Anh-Huy Phan, Ivan Oseledets, Alexander Shapeev, Ivan Novikov, Gleb Ryzhakov
Published: 2026-01-26
Categories: math.OC, cond-mat.mtrl-sci, cs.NE
arXiv: https://arxiv.org/abs/2601.18592v1

The global optimization of atomic clusters represents a fundamental challenge in computational chemistry and materials science due to the exponential growth of local minima with system size (i.e., the curse of dimensionality). We introduce a novel framework that overcomes this limitation by exploiting the low-rank structure of potential energy surfaces through Tensor Train (TT) decomposition. Our approach combines two complementary TT-based strategies: the algebraic TTOpt method, which utilizes maximum volume sampling, and the probabilistic PROTES method, which employs generative sampling. A key innovation is the development of physically-constrained encoding schemes that incorporate molecular constraints directly into the discretization process. We demonstrate the efficacy of our method by identifying global minima of Lennard-Jones clusters containing up to 45 atoms. Furthermore, we establish its practical applicability to real-world systems by optimizing 20-atom carbon clusters using a machine-learned Moment Tensor Potential, achieving geometries consistent with quantum-accurate simulations. This work establishes TT-decomposition as a powerful tool for molecular structure prediction and provides a general framework adaptable to a wide range of high-dimensional optimization problems in computational material science.

---

### AGSP-DSA: An Adaptive Graph Signal Processing Framework for Robust Multimodal Fusion with Dynamic Semantic Alignment

Authors: KV Karthikeya, Ashok Kumar Das, Shantanu Pal, Vivekananda Bhat K, Arun Sekar Rajasekaran
Published: 2026-01-26
Categories: cs.CV, cs.MM
arXiv: https://arxiv.org/abs/2601.18589v1

In this paper, we introduce an Adaptive Graph Signal Processing with Dynamic Semantic Alignment (AGSP DSA) framework to perform robust multimodal data fusion over heterogeneous sources, including text, audio, and images. The requested approach uses a dual-graph construction to learn both intra-modal and inter-modal relations, spectral graph filtering to boost the informative signals, and effective node embedding with Multi-scale Graph Convolutional Networks (GCNs). Semantic aware attention mechanism: each modality may dynamically contribute to the context with respect to contextual relevance. The experimental outcomes on three benchmark datasets, including CMU-MOSEI, AVE, and MM-IMDB, show that AGSP-DSA performs as the state of the art. More precisely, it achieves 95.3% accuracy, 0.936 F1-score, and 0.924 mAP on CMU-MOSEI, improving MM-GNN by 2.6 percent in accuracy. It gets 93.4% accuracy and 0.911 F1-score on AVE and 91.8% accuracy and 0.886 F1-score on MM-IMDB, which demonstrate good generalization and robustness in the missing modality setting. These findings verify the efficiency of AGSP-DSA in promoting multimodal learning in sentiment analysis, event recognition and multimedia classification.

---

### Stability as a Liability:Systematic Breakdown of Linguistic Structure in LLMs

Authors: Xianzhe Meng, Qiangsheng Zeng, Ling Luo, Qinghan Yang, Jiarui Hao, Wenbo Wu, Qinyu Wang, Rui Yin, Lin Qi, Renzhi Lu
Published: 2026-01-26
Categories: cs.AI, cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2601.18588v2

Training stability is typically regarded as a prerequisite for reliable optimization in large language models. In this work, we analyze how stabilizing training dynamics affects the induced generation distribution. We show that under standard maximum likelihood training, stable parameter trajectories lead stationary solutions to approximately minimize the forward KL divergence to the empirical distribution, while implicitly reducing generative entropy. As a consequence, the learned model can concentrate probability mass on a limited subset of empirical modes, exhibiting systematic degeneration despite smooth loss convergence. We empirically validate this effect using a controlled feedback-based training framework that stabilizes internal generation statistics, observing consistent low-entropy outputs and repetitive behavior across architectures and random seeds. It indicates that optimization stability and generative expressivity are not inherently aligned, and that stability alone is an insufficient indicator of generative quality.

---

### Learning long term climate-resilient transport adaptation pathways under direct and indirect flood impacts using reinforcement learning

Authors: Miguel Costa, Arthur Vandervoort, Carolin Schmidt, Morten W. Petersen, Martin Drews, Karyn Morrissey, Francisco C. Pereira
Published: 2026-01-26
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2601.18586v1

Climate change is expected to intensify rainfall and other hazards, increasing disruptions in urban transportation systems. Designing effective adaptation strategies is challenging due to the long-term, sequential nature of infrastructure investments, deep uncertainty, and complex cross-sector interactions. We propose a generic decision-support framework that couples an integrated assessment model (IAM) with reinforcement learning (RL) to learn adaptive, multi-decade investment pathways under uncertainty. The framework combines long-term climate projections (e.g., IPCC scenario pathways) with models that map projected extreme-weather drivers (e.g. rain) into hazard likelihoods (e.g. flooding), propagate hazards into urban infrastructure impacts (e.g. transport disruption), and value direct and indirect consequences for service performance and societal costs. Embedded in a reinforcement-learning loop, it learns adaptive climate adaptation policies that trade off investment and maintenance expenditures against avoided impacts. In collaboration with Copenhagen Municipality, we demonstrate the approach on pluvial flooding in the inner city for the horizon of 2024 to 2100. The learned strategies yield coordinated spatial-temporal pathways and improved robustness relative to conventional optimization baselines, namely inaction and random action, illustrating the framework's transferability to other hazards and cities.

---

### GimmBO: Interactive Generative Image Model Merging via Bayesian Optimization

Authors: Chenxi Liu, Selena Ling, Alec Jacobson
Published: 2026-01-26
Categories: cs.CV, cs.GR
arXiv: https://arxiv.org/abs/2601.18585v2

Fine-tuning-based adaptation is widely used to customize diffusion-based image generation, leading to large collections of community-created adapters that capture diverse subjects and styles. Adapters derived from the same base model can be merged with weights, enabling the synthesis of new visual results within a vast and continuous design space. To explore this space, current workflows rely on manual slider-based tuning, an approach that scales poorly and makes weight selection difficult, even when the candidate set is limited to 20-30 adapters. We propose GimmBO to support interactive exploration of adapter merging for image generation through Preferential Bayesian Optimization (PBO). Motivated by observations from real-world usage, including sparsity and constrained weight ranges, we introduce a two-stage BO backend that improves sampling efficiency and convergence in high-dimensional spaces. We evaluate our approach with simulated users and a user study, demonstrating improved convergence, high success rates, and consistent gains over BO and line-search baselines, and further show the flexibility of the framework through several extensions.

---

### From Classification to Ranking: Enhancing LLM Reasoning Capabilities for MBTI Personality Detection

Authors: Yuan Cao, Feixiang Liu, Xinyue Wang, Yihan Zhu, Hui Xu, Zheng Wang, Qiang Qiu
Published: 2026-01-26
Categories: cs.CL
arXiv: https://arxiv.org/abs/2601.18582v1

Personality detection aims to measure an individual's corresponding personality traits through their social media posts. The advancements in Large Language Models (LLMs) offer novel perspectives for personality detection tasks. Existing approaches enhance personality trait analysis by leveraging LLMs to extract semantic information from textual posts as prompts, followed by training classifiers for categorization. However, accurately classifying personality traits remains challenging due to the inherent complexity of human personality and subtle inter-trait distinctions. Moreover, prompt-based methods often exhibit excessive dependency on expert-crafted knowledge without autonomous pattern-learning capacity. To address these limitations, we view personality detection as a ranking task rather than a classification and propose a corresponding reinforcement learning training paradigm. First, we employ supervised fine-tuning (SFT) to establish personality trait ranking capabilities while enforcing standardized output formats, creating a robust initialization. Subsequently, we introduce Group Relative Policy Optimization (GRPO) with a specialized ranking-based reward function. Unlike verification tasks with definitive solutions, personality assessment involves subjective interpretations and blurred boundaries between trait categories. Our reward function explicitly addresses this challenge by training LLMs to learn optimal answer rankings. Comprehensive experiments have demonstrated that our method achieves state-of-the-art performance across multiple personality detection benchmarks.

---

### K-Myriad: Jump-starting reinforcement learning with unsupervised parallel agents

Authors: Vincenzo De Paola, Mirco Mutti, Riccardo Zamboni, Marcello Restelli
Published: 2026-01-26
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.18580v1

Parallelization in Reinforcement Learning is typically employed to speed up the training of a single policy, where multiple workers collect experience from an identical sampling distribution. This common design limits the potential of parallelization by neglecting the advantages of diverse exploration strategies. We propose K-Myriad, a scalable and unsupervised method that maximizes the collective state entropy induced by a population of parallel policies. By cultivating a portfolio of specialized exploration strategies, K-Myriad provides a robust initialization for Reinforcement Learning, leading to both higher training efficiency and the discovery of heterogeneous solutions. Experiments on high-dimensional continuous control tasks, with large-scale parallelization, demonstrate that K-Myriad can learn a broad set of distinct policies, highlighting its effectiveness for collective exploration and paving the way towards novel parallelization strategies.

---

### GraFine: Retrieval-Time Refinement for Efficient Graph RAG over Corpus Graphs

Authors: Seonho An, Chaejeong Hyun, Min-Soo Kim
Published: 2026-01-26
Categories: cs.IR, cs.AI
arXiv: https://arxiv.org/abs/2601.18579v2

Graph RAG on corpus graphs enhances retrieval by leveraging intermediate node content as contextual clues to uncover unretrieved oracle nodes. However, existing methods suffer from two critical blind spots, namely semantically blind graph expansion and topology blind pruning, or else rely on prohibitively slow retrieval and generation interleaving. To address this, we formalize these limitations through an operational taxonomy and propose a retriever design that couples semantics-aware adding with graph-aware pruning under efficiency constraints. We instantiate this design as GraFine, which alternates between two refinement stages: Semantic Proximity eXpansion (SPX) for semantics-aware node addition, and a Graph Smoothing Reranker (GSR) for graph-aware pruning. Experiments on reference networks and text-rich knowledge graphs show that GraFine improves retrieval accuracy and generation quality while maintaining time-efficiency. Furthermore, we introduce Topological Recall (TR), a metric that quantifies the topological proximity between retrieved and oracle nodes. Our analysis using TR confirms that GraFine more effectively steers refinement toward undiscovered oracle nodes by leveraging intermediate contextual clues. Our code is available at this link: https://github.com/asmath472/GraFine.

---

### Self-Refining Video Sampling

Authors: Sangwon Jang, Taekyung Ki, Jaehyeong Jo, Saining Xie, Jaehong Yoon, Sung Ju Hwang
Published: 2026-01-26
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2601.18577v2

Modern video generators still struggle with complex physical dynamics, often falling short of physical realism. Existing approaches address this using external verifiers or additional training on augmented data, which is computationally expensive and still limited in capturing fine-grained motion. In this work, we present self-refining video sampling, a simple method that uses a pre-trained video generator trained on large-scale datasets as its own self-refiner. By interpreting the generator as a denoising autoencoder, we enable iterative inner-loop refinement at inference time without any external verifier or additional training. We further introduce an uncertainty-aware refinement strategy that selectively refines regions based on self-consistency, which prevents artifacts caused by over-refinement. Experiments on state-of-the-art video generators demonstrate significant improvements in motion coherence and physics alignment, achieving over 70% human preference compared to the default sampler and guidance-based sampler.

---

### One Persona, Many Cues, Different Results: How Sociodemographic Cues Impact LLM Personalization

Authors: Franziska Weeber, Vera Neplenbroek, Jan Batzner, Sebastian Padó
Published: 2026-01-26
Categories: cs.CL
arXiv: https://arxiv.org/abs/2601.18572v3

Personalization of LLMs by sociodemographic subgroup often improves user experience, but can also introduce or amplify biases and unfair outcomes across groups. Prior work has employed so-called personas, sociodemographic user attributes conveyed to a model, to study bias in LLMs by relying on a single cue to prompt a persona, such as user names or explicit attribute mentions. This disregards LLM sensitivity to prompt variation and the rarity of some cues in real interactions (external validity). We compare six commonly used persona cues across seven open and proprietary LLMs on four writing and advice tasks. While cues are overall highly correlated, they produce substantial variance in responses across personas that can change findings on persona-induced differences and bias. We therefore caution against claims based on single persona cues, especially when they are overly explicit and have low external validity.

---

### Attention-Based Neural-Augmented Kalman Filter for Legged Robot State Estimation

Authors: Seokju Lee, Kyung-Soo Kim
Published: 2026-01-26
Categories: cs.RO, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2601.18569v2

In this letter, we propose an Attention-Based Neural-Augmented Kalman Filter (AttenNKF) for state estimation in legged robots. Foot slip is a major source of estimation error: when slip occurs, kinematic measurements violate the no-slip assumption and inject bias during the update step. Our objective is to estimate this slip-induced error and compensate for it. To this end, we augment an Invariant Extended Kalman Filter (InEKF) with a neural compensator that uses an attention mechanism to infer error conditioned on foot-slip severity and then applies this estimate as a post-update compensation to the InEKF state (i.e., after the filter update). The compensator is trained in a latent space, which aims to reduce sensitivity to raw input scales and encourages structured slip-conditioned compensations, while preserving the InEKF recursion. Experiments demonstrate improved performance compared to existing legged-robot state estimators, particularly under slip-prone conditions.

---

### An Unsupervised Tensor-Based Domain Alignment

Authors: Chong Hyun Lee, Kibae Lee, Hyun Hee Yim
Published: 2026-01-26
Categories: cs.LG, cs.CV, eess.SP
arXiv: https://arxiv.org/abs/2601.18564v1

We propose a tensor-based domain alignment (DA) algorithm designed to align source and target tensors within an invariant subspace through the use of alignment matrices. These matrices along with the subspace undergo iterative optimization of which constraint is on oblique manifold, which offers greater flexibility and adaptability compared to the traditional Stiefel manifold. Moreover, regularization terms defined to preserve the variance of both source and target tensors, ensures robust performance. Our framework is versatile, effectively generalizing existing tensor-based DA methods as special cases. Through extensive experiments, we demonstrate that our approach not only enhances DA conversion speed but also significantly boosts classification accuracy. This positions our method as superior to current state-of-the-art techniques, making it a preferable choice for complex domain adaptation tasks.

---

### AI-enabled Satellite Edge Computing: A Single-Pixel Feature based Shallow Classification Model for Hyperspectral Imaging

Authors: Li Fang, Tianyu Li, Yanghong Lin, Shudong Zhou, Wei Yao
Published: 2026-01-26
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.18560v1

As the important component of the Earth observation system, hyperspectral imaging satellites provide high-fidelity and enriched information for the formulation of related policies due to the powerful spectral measurement capabilities. However, the transmission speed of the satellite downlink has become a major bottleneck in certain applications, such as disaster monitoring and emergency mapping, which demand a fast response ability. We propose an efficient AI-enabled Satellite Edge Computing paradigm for hyperspectral image classification, facilitating the satellites to attain autonomous decision-making. To accommodate the resource constraints of satellite platforms, the proposed method adopts a lightweight, non-deep learning framework integrated with a few-shot learning strategy. Moreover, onboard processing on satellites could be faced with sensor failure and scan pattern errors, which result in degraded image quality with bad/misaligned pixels and mixed noise. To address these challenges, we develop a novel two-stage pixel-wise label propagation scheme that utilizes only intrinsic spectral features at the single pixel level without the necessity to consider spatial structural information as requested by deep neural networks. In the first stage, initial pixel labels are obtained by propagating selected anchor labels through the constructed anchor-pixel affinity matrix. Subsequently, a top-k pruned sparse graph is generated by directly computing pixel-level similarities. In the second stage, a closed-form solution derived from the sparse graph is employed to replace iterative computations. Furthermore, we developed a rank constraint-based graph clustering algorithm to determine the anchor labels.

---

### Generative Diffusion Augmentation with Quantum-Enhanced Discrimination for Medical Image Diagnosis

Authors: Jingsong Xia, Siqi Wang
Published: 2026-01-26
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2601.18556v1

In biomedical engineering, artificial intelligence has become a pivotal tool for enhancing medical diagnostics, particularly in medical image classification tasks such as detecting pneumonia from chest X-rays and breast cancer screening. However, real-world medical datasets frequently exhibit severe class imbalance, where positive samples substantially outnumber negative samples, leading to biased models with low recall rates for minority classes. This imbalance not only compromises diagnostic accuracy but also poses clinical misdiagnosis risks. To address this challenge, we propose SDA-QEC (Simplified Diffusion Augmentation with Quantum-Enhanced Classification), an innovative framework that integrates simplified diffusion-based data augmentation with quantum-enhanced feature discrimination. Our approach employs a lightweight diffusion augmentor to generate high-quality synthetic samples for minority classes, rebalancing the training distribution. Subsequently, a quantum feature layer embedded within MobileNetV2 architecture enhances the model's discriminative capability through high-dimensional feature mapping in Hilbert space. Comprehensive experiments on coronary angiography image classification demonstrate that SDA-QEC achieves 98.33% accuracy, 98.78% AUC, and 98.33% F1-score, significantly outperforming classical baselines including ResNet18, MobileNetV2, DenseNet121, and VGG16. Notably, our framework simultaneously attains 98.33% sensitivity and 98.33% specificity, achieving a balanced performance critical for clinical deployment. The proposed method validates the feasibility of integrating generative augmentation with quantum-enhanced modeling in real-world medical imaging tasks, offering a novel research pathway for developing highly reliable medical AI systems in small-sample, highly imbalanced, and high-risk diagnostic scenarios.

---

### Automated Landmark Detection for assessing hip conditions: A Cross-Modality Validation of MRI versus X-ray

Authors: Roberto Di Via, Vito Paolo Pastore, Francesca Odone, Siôn Glyn-Jones, Irina Voiculescu
Published: 2026-01-26
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.18555v1

Many clinical screening decisions are based on angle measurements. In particular, FemoroAcetabular Impingement (FAI) screening relies on angles traditionally measured on X-rays. However, assessing the height and span of the impingement area requires also a 3D view through an MRI scan. The two modalities inform the surgeon on different aspects of the condition. In this work, we conduct a matched-cohort validation study (89 patients, paired MRI/X-ray) using standard heatmap regression architectures to assess cross-modality clinical equivalence. Seen that landmark detection has been proven effective on X-rays, we show that MRI also achieves equivalent localisation and diagnostic accuracy for cam-type impingement. Our method demonstrates clinical feasibility for FAI assessment in coronal views of 3D MRI volumes, opening the possibility for volumetric analysis through placing further landmarks. These results support integrating automated FAI assessment into routine MRI workflows. Code is released at https://github.com/Malga-Vision/Landmarks-Hip-Conditions

---

### Deconstructing Instruction-Following: A New Benchmark for Granular Evaluation of Large Language Model Instruction Compliance Abilities

Authors: Alberto Purpura, Li Wang, Sahil Badyal, Eugenio Beaufrand, Adam Faulkner
Published: 2026-01-26
Categories: cs.AI
arXiv: https://arxiv.org/abs/2601.18554v1

Reliably ensuring Large Language Models (LLMs) follow complex instructions is a critical challenge, as existing benchmarks often fail to reflect real-world use or isolate compliance from task success. We introduce MOSAIC (MOdular Synthetic Assessment of Instruction Compliance), a modular framework that uses a dynamically generated dataset with up to 20 application-oriented generation constraints to enable a granular and independent analysis of this capability. Our evaluation of five LLMs from different families based on this new benchmark demonstrates that compliance is not a monolithic capability but varies significantly with constraint type, quantity, and position. The analysis reveals model-specific weaknesses, uncovers synergistic and conflicting interactions between instructions, and identifies distinct positional biases such as primacy and recency effects. These granular insights are critical for diagnosing model failures and developing more reliable LLMs for systems that demand strict adherence to complex instructions.

---

### Unknown Unknowns: Do Hidden Intentions in LLMs Evade Detection?

Authors: Devansh Srivastav, David Pape, Lea Schönherr
Published: 2026-01-26
Categories: cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2601.18552v2

LLMs expand accessibility and provide wide-reaching access to information. Yet these interactions also create opportunities to embed subtle, goal-oriented behaviours that shape what users think and how they behave, a concern reflected in governance frameworks that prohibit manipulative AI. We refer to these behaviours as hidden intentions: covert agendas embedded in a model's outputs that can manipulate users' beliefs and actions. In this work, we examine whether hidden intentions can be identified and characterised, and assess whether detection can serve as a mitigation strategy. To operationalise this, we introduce a social-science-grounded set of ten hidden intention categories and show that they are trivially inducible. A case study further confirms that all ten categories manifest in deployed LLMs. We then evaluate static classifiers and LLM judges on these categories, providing the first systematic analysis of why hidden intentions are difficult to detect. Our stress tests show that, unless false-positive rates are vanishingly small, auditing is dominated by precision-prevalence trade-offs. Capability scaling and reasoning models do not close this gap, suggesting a fundamental challenge for open-world detection. These findings expose a core gap of current AI governance: without new auditing paradigms for open-world, low-prevalence risks, bans on manipulative AI remain difficult to enforce.

---

### REMAC: Reference-Based Martian Asymmetrical Image Compression

Authors: Qing Ding, Mai Xu, Shengxi Li, Xin Deng, Xin Zou
Published: 2026-01-26
Categories: cs.CV, cs.MM
arXiv: https://arxiv.org/abs/2601.18547v1

To expedite space exploration on Mars, it is indispensable to develop an efficient Martian image compression method for transmitting images through the constrained Mars-to-Earth communication channel. Although the existing learned compression methods have achieved promising results for natural images from earth, there remain two critical issues that hinder their effectiveness for Martian image compression: 1) They overlook the highly-limited computational resources on Mars; 2) They do not utilize the strong \textit{inter-image} similarities across Martian images to advance image compression performance. Motivated by our empirical analysis of the strong \textit{intra-} and \textit{inter-image} similarities from the perspective of texture, color, and semantics, we propose a reference-based Martian asymmetrical image compression (REMAC) approach, which shifts computational complexity from the encoder to the resource-rich decoder and simultaneously improves compression performance. To leverage \textit{inter-image} similarities, we propose a reference-guided entropy module and a ref-decoder that utilize useful information from reference images, reducing redundant operations at the encoder and achieving superior compression performance. To exploit \textit{intra-image} similarities, the ref-decoder adopts a deep, multi-scale architecture with enlarged receptive field size to model long-range spatial dependencies. Additionally, we develop a latent feature recycling mechanism to further alleviate the extreme computational constraints on Mars. Experimental results show that REMAC reduces encoder complexity by 43.51\% compared to the state-of-the-art method, while achieving a BD-PSNR gain of 0.2664 dB.

---

### Information Hidden in Gradients of Regression with Target Noise

Authors: Arash Jamshidi, Katsiaryna Haitsiukevich, Kai Puolamäki
Published: 2026-01-26
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.18546v2

Second-order information -- such as curvature or data covariance -- is critical for optimisation, diagnostics, and robustness. However, in many modern settings, only the gradients are observable. We show that the gradients alone can reveal the Hessian, equalling the data covariance $Σ$ for the linear regression. Our key insight is a simple variance calibration: injecting Gaussian noise so that the total target noise variance equals the batch size ensures that the empirical gradient covariance closely approximates the Hessian, even when evaluated far from the optimum. We provide non-asymptotic operator-norm guarantees under sub-Gaussian inputs. We also show that without such calibration, recovery can fail by an $Ω(1)$ factor. The proposed method is practical (a "set target-noise variance to $n$" rule) and robust (variance $\mathcal{O}(n)$ suffices to recover $Σ$ up to scale). Applications include preconditioning for faster optimisation, adversarial risk estimation, and gradient-only training, for example, in distributed systems. We support our theoretical results with experiments on synthetic and real data.

---

### GenAgent: Scaling Text-to-Image Generation via Agentic Multimodal Reasoning

Authors: Kaixun Jiang, Yuzheng Wang, Junjie Zhou, Pandeng Li, Zhihang Liu, Chen-Wei Xie, Zhaoyu Chen, Yun Zheng, Wenqiang Zhang
Published: 2026-01-26
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.18543v2

We introduce GenAgent, unifying visual understanding and generation through an agentic multimodal model. Unlike unified models that face expensive training costs and understanding-generation trade-offs, GenAgent decouples these capabilities through an agentic framework: understanding is handled by the multimodal model itself, while generation is achieved by treating image generation models as invokable tools. Crucially, unlike existing modular systems constrained by static pipelines, this design enables autonomous multi-turn interactions where the agent generates multimodal chains-of-thought encompassing reasoning, tool invocation, judgment, and reflection to iteratively refine outputs. We employ a two-stage training strategy: first, cold-start with supervised fine-tuning on high-quality tool invocation and reflection data to bootstrap agent behaviors; second, end-to-end agentic reinforcement learning combining pointwise rewards (final image quality) and pairwise rewards (reflection accuracy), with trajectory resampling for enhanced multi-turn exploration. GenAgent significantly boosts base generator(FLUX.1-dev) performance on GenEval++ (+23.6\%) and WISE (+14\%). Beyond performance gains, our framework demonstrates three key properties: 1) cross-tool generalization to generators with varying capabilities, 2) test-time scaling with consistent improvements across interaction rounds, and 3) task-adaptive reasoning that automatically adjusts to different tasks. Our code will be available at \href{https://github.com/deep-kaixun/GenAgent}{this url}.

---

### SKETCH: Semantic Key-Point Conditioning for Long-Horizon Vessel Trajectory Prediction

Authors: Linyong Gan, Zimo Li, Wenxin Xu, Xingjian Li, Jianhua Z. Huang, Enmei Tu, Shuhang Chen
Published: 2026-01-26
Categories: cs.RO, cs.AI
arXiv: https://arxiv.org/abs/2601.18537v4

Accurate long-horizon vessel trajectory prediction remains challenging due to compounded uncertainty from complex navigation behaviors and environmental factors. Existing methods often struggle to maintain global directional consistency, leading to drifting or implausible trajectories when extrapolated over long time horizons. To address this issue, we propose a semantic-key-point-conditioned trajectory modeling framework, in which future trajectories are predicted by conditioning on a high-level Next Key Point (NKP) that captures navigational intent. This formulation decomposes long-horizon prediction into global semantic decision-making and local motion modeling, effectively restricting the support of future trajectories to semantically feasible subsets. To efficiently estimate the NKP prior from historical observations, we adopt a pretrain-finetune strategy. Extensive experiments on real-world AIS data demonstrate that the proposed method consistently outperforms state-of-the-art approaches, particularly for long travel durations, directional accuracy, and fine-grained trajectory prediction.

---

### Evaluating Morphological Plausibility of Subword Tokenization via Statistical Alignment with Morpho-Syntactic Features

Authors: Abishek Stephen, Jindřich Libovický
Published: 2026-01-26
Categories: cs.CL
arXiv: https://arxiv.org/abs/2601.18536v1

We present a novel metric for the evaluation of the morphological plausibility of subword segmentation. Unlike the typically used morpheme boundary or retrieval F-score, which requires gold segmentation data that is either unavailable or of inconsistent quality across many languages, our approach utilizes morpho-syntactic features. These are available in resources such as Universal Dependencies or UniMorph for a much wider range of languages. The metric works by probabilistically aligning subwords with morphological features through an IBM Model 1. Our experiments show that the metric correlates well with traditional morpheme boundary recall while being more broadly applicable across languages with different morphological systems.

---

### From Verifiable Dot to Reward Chain: Harnessing Verifiable Reference-based Rewards for Reinforcement Learning of Open-ended Generation

Authors: Yuxin Jiang, Yufei Wang, Qiyuan Zhang, Xingshan Zeng, Liangyou Li, Jierun Chen, Chaofan Tao, Haoli Bai, Lifeng Shang
Published: 2026-01-26
Categories: cs.CL
arXiv: https://arxiv.org/abs/2601.18533v1

Reinforcement learning with verifiable rewards (RLVR) succeeds in reasoning tasks (e.g., math and code) by checking the final verifiable answer (i.e., a verifiable dot signal). However, extending this paradigm to open-ended generation is challenging because there is no unambiguous ground truth. Relying on single-dot supervision often leads to inefficiency and reward hacking. To address these issues, we propose reinforcement learning with verifiable reference-based rewards (RLVRR). Instead of checking the final answer, RLVRR extracts an ordered linguistic signal from high-quality references (i.e, reward chain). Specifically, RLVRR decomposes rewards into two dimensions: content, which preserves deterministic core concepts (e.g., keywords), and style, which evaluates adherence to stylistic properties through LLM-based verification. In this way, RLVRR combines the exploratory strength of RL with the efficiency and reliability of supervised fine-tuning (SFT). Extensive experiments on more than 10 benchmarks with Qwen and Llama models confirm the advantages of our approach. RLVRR (1) substantially outperforms SFT trained with ten times more data and advanced reward models, (2) unifies the training of structured reasoning and open-ended generation, and (3) generalizes more effectively while preserving output diversity. These results establish RLVRR as a principled and efficient path toward verifiable reinforcement learning for general-purpose LLM alignment. We release our code and data at https://github.com/YJiangcm/RLVRR.

---