# Research Papers — 2026-01 · bundle page 55 of 189 > Full-text markdown of papers #2701–2750 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/55 [← Previous bundle](https://aipod.dev/papers/archive/2026-01/page/54.md) [Next bundle →](https://aipod.dev/papers/archive/2026-01/page/56.md) ### Memory-Efficient FPGA Implementation of Stochastic Simulated Annealing Authors: Duckgyu Shin, Naoya Onizawa, Warren J. Gross, Takahiro Hanyu Published: 2026-01-25 Categories: cs.AR, cs.LG arXiv: https://arxiv.org/abs/2601.18007v1 Simulated annealing (SA) is a well-known algorithm for solving combinatorial optimization problems. However, the computation time of SA increases rapidly, as the size of the problem grows. Recently, a stochastic simulated annealing (SSA) algorithm that converges faster than conventional SA has been reported. In this paper, we present a hardware-aware SSA (HA- SSA) algorithm for memory-efficient FPGA implementations. HA-SSA can reduce the memory usage of storing intermediate results while maintaining the computing speed of SSA. For evaluation purposes, the proposed algorithm is compared with the conventional SSA and SA approaches on maximum cut combinatorial optimization problems. HA-SSA achieves a convergence speed that is up to 114-times faster than that of the conventional SA algorithm depending on the maximum cut problem selected from the G-set which is a dataset of the maximum cut problems. HA-SSA is implemented on a field-programmable gate array (FPGA) (Xilinx Kintex-7), and it achieves up to 6-times the memory efficiency of conventional SSA while maintaining high solution quality for optimization problems. --- ### PEAR: Pairwise Evaluation for Automatic Relative Scoring in Machine Translation Authors: Lorenzo Proietti, Roman Grundkiewicz, Matt Post Published: 2026-01-25 Categories: cs.CL arXiv: https://arxiv.org/abs/2601.18006v2 We present PEAR (Pairwise Evaluation for Automatic Relative Scoring), a supervised quality estimation (QE) metric family that reframes reference-free machine translation (MT) evaluation as a graded pairwise comparison. Given a source segment and two candidate translations, PEAR predicts the direction and magnitude of their quality difference. The metrics are trained using pairwise supervision derived from differences in human judgments, with an additional regularization term that encourages sign inversion under candidate order reversal. On the WMT24 meta-evaluation benchmark, PEAR outperforms strictly matched single-candidate QE baselines trained with the same data and backbones, isolating the benefit of the proposed pairwise formulation. Despite using substantially fewer parameters than recent large metrics, PEAR surpasses far larger QE models and reference-based metrics. Our analysis further indicates that PEAR yields a less redundant evaluation signal relative to other top metrics. Finally, we show that PEAR is an effective utility function for minimum Bayes risk (MBR) decoding, reducing pairwise scoring cost at negligible impact. --- ### Flow-based Extremal Mathematical Structure Discovery Authors: Gergely Bérczi, Baran Hashemi, Jonas Klüver Published: 2026-01-25 Categories: math.CO, cs.LG arXiv: https://arxiv.org/abs/2601.18005v1 The discovery of extremal structures in mathematics requires navigating vast and nonconvex landscapes where analytical methods offer little guidance and brute-force search becomes intractable. We introduce FlowBoost, a closed-loop generative framework that learns to discover rare and extremal geometric structures by combining three components: (i) a geometry-aware conditional flow-matching model that learns to sample high-quality configurations, (ii) reward-guided policy optimization with action exploration that directly optimizes the generation process toward the objective while maintaining diversity, and (iii) stochastic local search for both training-data generation and final refinement. Unlike prior open-loop approaches, such as PatternBoost that retrains on filtered discrete samples, or AlphaEvolve which relies on frozen Large Language Models (LLMs) as evolutionary mutation operators, FlowBoost enforces geometric feasibility during sampling, and propagates reward signal directly into the generative model, closing the optimization loop and requiring much smaller training sets and shorter training times, and reducing the required outer-loop iterations by orders of magnitude, while eliminating dependence on LLMs. We demonstrate the framework on four geometric optimization problems: sphere packing in hypercubes, circle packing maximizing sum of radii, the Heilbronn triangle problem, and star discrepancy minimization. In several cases, FlowBoost discovers configurations that match or exceed the best known results. For circle packings, we improve the best known lower bounds, surpassing the LLM-based system AlphaEvolve while using substantially fewer computational resources. --- ### MorphXAI: An Explainable Framework for Morphological Analysis of Parasites in Blood Smear Images Authors: Aqsa Yousaf, Sint Sint Win, Megan Coffee, Habeeb Olufowobi Published: 2026-01-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.18001v1 Parasitic infections remain a pressing global health challenge, particularly in low-resource settings where diagnosis still depends on labor-intensive manual inspection of blood smears and the availability of expert domain knowledge. While deep learning models have shown strong performance in automating parasite detection, their clinical usefulness is constrained by limited interpretability. Existing explainability methods are largely restricted to visual heatmaps or attention maps, which highlight regions of interest but fail to capture the morphological traits that clinicians rely on for diagnosis. In this work, we present MorphXAI, an explainable framework that unifies parasite detection with fine-grained morphological analysis. MorphXAI integrates morphological supervision directly into the prediction pipeline, enabling the model to localize parasites while simultaneously characterizing clinically relevant attributes such as shape, curvature, visible dot count, flagellum presence, and developmental stage. To support this task, we curate a clinician-annotated dataset of three parasite species (Leishmania, Trypanosoma brucei, and Trypanosoma cruzi) with detailed morphological labels, establishing a new benchmark for interpretable parasite analysis. Experimental results show that MorphXAI not only improves detection performance over the baseline but also provides structured, biologically meaningful explanations. --- ### Coding-Enforced Resilient and Secure Aggregation for Hierarchical Federated Learning Authors: Shudi Weng, Ming Xiao, Mikael Skoglund Published: 2026-01-25 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2601.17995v1 Hierarchical federated learning (HFL) has emerged as an effective paradigm to enhance link quality between clients and the server. However, ensuring model accuracy while preserving privacy under unreliable communication remains a key challenge in HFL, as the coordination among privacy noise can be randomly disrupted. To address this limitation, we propose a robust hierarchical secure aggregation scheme, termed H-SecCoGC, which integrates coding strategies to enforce structured aggregation. The proposed scheme not only ensures accurate global model construction under varying levels of privacy, but also avoids the partial participation issue, thereby significantly improving robustness, privacy preservation, and learning efficiency. Both theoretical analyses and experimental results demonstrate the superiority of our scheme under unreliable communication across arbitrarily strong privacy guarantees --- ### AI-based approach to burnout identification from textual data Authors: Marina Zavertiaeva, Petr Parshakov, Mikhail Usanin, Aleksei Smirnov, Sofia Paklina, Anastasiia Kibardina Published: 2026-01-25 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2601.17993v1 This study introduces an AI-based methodology that utilizes natural language processing (NLP) to detect burnout from textual data. The approach relies on a RuBERT model originally trained for sentiment analysis and subsequently fine-tuned for burnout detection using two data sources: synthetic sentences generated with ChatGPT and user comments collected from Russian YouTube videos about burnout. The resulting model assigns a burnout probability to input texts and can be applied to process large volumes of written communication for monitoring burnout-related language signals in high-stress work environments. --- ### A Cherry-Picking Approach to Large Load Shaping for More Effective Carbon Reduction Authors: Bokan Chen, Raiden Hasegawa, Adriaan Hilbers, Ross Koningstein, Ana Radovanović, Utkarsh Shah, Gabriela Volpato, Mohamed Ahmed, Tim Cary, Rod Frowd Published: 2026-01-25 Categories: stat.ML, cs.LG, eess.SY arXiv: https://arxiv.org/abs/2601.17990v1 Shaping multi-megawatt loads, such as data centers, impacts generator dispatch on the electric grid, which in turn affects system CO2 emissions and energy cost. Substantiating the effectiveness of prevalent load shaping strategies, such as those based on grid-level average carbon intensity, locational marginal price, or marginal emissions, is challenging due to the lack of detailed counterfactual data required for accurate attribution. This study uses a series of calibrated granular ERCOT day-ahead direct current optimal power flow (DC-OPF) simulations for counterfactual analysis of a broad set of load shaping strategies on grid CO2 emissions and cost of electricity. In terms of annual grid level CO2 emissions reductions, LMP-based shaping outperforms other common strategies, but can be significantly improved upon. Examining the performance of practicable strategies under different grid conditions motivates a more effective load shaping approach: one that "cherry-picks" a daily strategy based on observable grid signals and historical data. The cherry-picking approach to power load shaping is applicable to any large flexible consumer on the electricity grid, such as data centers, distributed energy resources and Virtual Power Plants (VPPs). --- ### Systematic Characterization of Minimal Deep Learning Architectures: A Unified Analysis of Convergence, Pruning, and Quantization Authors: Ziwei Zheng, Huizhi Liang, Vaclav Snasel, Vito Latora, Panos Pardalos, Giuseppe Nicosia, Varun Ojha Published: 2026-01-25 Categories: cs.LG, cs.CV arXiv: https://arxiv.org/abs/2601.17987v1 Deep learning networks excel at classification, yet identifying minimal architectures that reliably solve a task remains challenging. We present a computational methodology for systematically exploring and analyzing the relationships among convergence, pruning, and quantization. The workflow first performs a structured design sweep across a large set of architectures, then evaluates convergence behavior, pruning sensitivity, and quantization robustness on representative models. Focusing on well-known image classification of increasing complexity, and across Deep Neural Networks, Convolutional Neural Networks, and Vision Transformers, our initial results show that, despite architectural diversity, performance is largely invariant and learning dynamics consistently exhibit three regimes: unstable, learning, and overfitting. We further characterize the minimal learnable parameters required for stable learning, uncover distinct convergence and pruning phases, and quantify the effect of reduced numeric precision on trainable parameters. Aligning with intuition, the results confirm that deeper architectures are more resilient to pruning than shallower ones, with parameter redundancy as high as 60%, and quantization impacts models with fewer learnable parameters more severely and has a larger effect on harder image datasets. These findings provide actionable guidance for selecting compact, stable models under pruning and low-precision constraints in image classification. --- ### Federated learning for unpaired multimodal data through a homogeneous transformer model Authors: Anders Eklund Published: 2026-01-25 Categories: cs.LG arXiv: https://arxiv.org/abs/2601.17986v1 Training of multimodal foundation models is currently restricted to centralized data centers containing massive, aligned datasets (e.g., image-text pairs). However, in realistic federated environments, data is often unpaired and fragmented across disjoint nodes; one node may hold sensor data, while another holds textual logs. These datasets are strictly private and share no common samples. Current federated learning (FL) methods fail in this regime, as they assume local clients possess aligned pairs or require sharing raw feature embeddings, which violates data sovereignty. We propose a novel framework to train a global multimodal transformer across decentralized nodes with disjoint modalities. We introduce a small public anchor set to align disjoint private manifolds. Using Gram matrices calculated from these public anchors, we enforce semantic alignment across modalities through centered kernel alignment without ever transmitting private samples, offering a mathematically superior privacy guarantee compared to prototype sharing. Further, we introduce a subspace-stabilized fine-tuning method to handle FL with huge transformer models. We strictly decouple domain-specific magnitude shifts from semantic direction, ensuring that nodes with varying sensor characteristics align geometrically to the global consensus. Lastly, we propose precision weighted averaging, where efficiently obtained uncertainty estimates are used to downweight uncertain nodes. This paper establishes the mathematical backbone for federated unpaired foundation models, enabling a global model to learn a unified representation of the world from fragmented, disjoint, and private data silos without requiring centralized storage or paired samples. --- ### SD-E$^2$: Semantic Exploration for Reasoning Under Token Budgets Authors: Kshitij Mishra, Nils Lukas, Salem Lahlou Published: 2026-01-25 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2601.17982v1 Small language models (SLMs) struggle with complex reasoning because exploration is expensive under tight compute budgets. We introduce Semantic Diversity-Exploration-Exploitation (SD-E$^2$), a reinforcement learning framework that makes exploration explicit by optimizing semantic diversity in generated reasoning trajectories. Using a frozen sentence-embedding model, SD-E$^2$ assigns a diversity reward that captures (i) the coverage of semantically distinct solution strategies and (ii) their average pairwise dissimilarity in embedding space, rather than surface-form novelty. This diversity reward is combined with outcome correctness and solution efficiency in a z-score-normalized multi-objective objective that stabilizes training. On GSM8K, SD-E$^2$ surpasses the base Qwen2.5-3B-Instruct and strong GRPO baselines (GRPO-CFL and GRPO-CFEE) by +27.4, +5.2, and +1.5 percentage points, respectively, while discovering on average 9.8 semantically distinct strategies per question. We further improve MedMCQA to 49.64% versus 38.37% for the base model and show gains on the harder AIME benchmark (1983-2025), reaching 13.28% versus 6.74% for the base. These results indicate that rewarding semantic novelty yields a more compute-efficient exploration-exploitation signal for training reasoning-capable SLMs. By introducing cognitive adaptation-adjusting the reasoning process structure rather than per-token computation-SD-E$^2$ offers a complementary path to efficiency gains in resource-constrained models. --- ### Domain-Expert-Guided Hybrid Mixture-of-Experts for Medical AI: Integrating Data-Driven Learning with Clinical Priors Authors: Jinchen Gu, Nan Zhao, Lei Qiu, Lu Zhang Published: 2026-01-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.17977v1 Mixture-of-Experts (MoE) models increase representational capacity with modest computational cost, but their effectiveness in specialized domains such as medicine is limited by small datasets. In contrast, clinical practice offers rich expert knowledge, such as physician gaze patterns and diagnostic heuristics, that models cannot reliably learn from limited data. Combining data-driven experts, which capture novel patterns, with domain-expert-guided experts, which encode accumulated clinical insights, provides complementary strengths for robust and clinically meaningful learning. To this end, we propose Domain-Knowledge-Guided Hybrid MoE (DKGH-MoE), a plug-and-play and interpretable module that unifies data-driven learning with domain expertise. DKGH-MoE integrates a data-driven MoE to extract novel features from raw imaging data, and a domain-expert-guided MoE incorporates clinical priors, specifically clinician eye-gaze cues, to emphasize regions of high diagnostic relevance. By integrating domain expert insights with data-driven features, DKGH-MoE improves both performance and interpretability. --- ### Boosting methods for interval-censored data with regression and classification Authors: Yuan Bian, Grace Y. Yi, Wenqing He Published: 2026-01-25 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2601.17973v2 Boosting has garnered significant interest across both machine learning and statistical communities. Traditional boosting algorithms, designed for fully observed random samples, often struggle with real-world problems, particularly with interval-censored data. This type of data is common in survival analysis and time-to-event studies where exact event times are unobserved but fall within known intervals. Effective handling of such data is crucial in fields like medical research, reliability engineering, and social sciences. In this work, we introduce novel nonparametric boosting methods for regression and classification tasks with interval-censored data. Our approaches leverage censoring unbiased transformations to adjust loss functions and impute transformed responses while maintaining model accuracy. Implemented via functional gradient descent, these methods ensure scalability and adaptability. We rigorously establish their theoretical properties, including optimality and mean squared error trade-offs. Our proposed methods not only offer a robust framework for enhancing predictive accuracy in domains where interval-censored data are common but also complement existing work, expanding the applicability of existing boosting techniques. Empirical studies demonstrate robust performance across various finite-sample scenarios, highlighting the practical utility of our approaches. --- ### LLMs as Cultural Archives: Cultural Commonsense Knowledge Graph Extraction Authors: Junior Cedric Tonga, Chen Cecilia Liu, Iryna Gurevych, Fajri Koto Published: 2026-01-25 Categories: cs.CL arXiv: https://arxiv.org/abs/2601.17971v1 Large language models (LLMs) encode rich cultural knowledge learned from diverse web-scale data, offering an unprecedented opportunity to model cultural commonsense at scale. Yet this knowledge remains mostly implicit and unstructured, limiting its interpretability and use. We present an iterative, prompt-based framework for constructing a Cultural Commonsense Knowledge Graph (CCKG) that treats LLMs as cultural archives, systematically eliciting culture-specific entities, relations, and practices and composing them into multi-step inferential chains across languages. We evaluate CCKG on five countries with human judgments of cultural relevance, correctness, and path coherence. We find that the cultural knowledge graphs are better realized in English, even when the target culture is non-English (e.g., Chinese, Indonesian, Arabic), indicating uneven cultural encoding in current LLMs. Augmenting smaller LLMs with CCKG improves performance on cultural reasoning and story generation, with the largest gains from English chains. Our results show both the promise and limits of LLMs as cultural technologies and that chain-structured cultural knowledge is a practical substrate for culturally grounded NLP. --- ### TensorLens: End-to-End Transformer Analysis via High-Order Attention Tensors Authors: Ido Andrew Atad, Itamar Zimerman, Shahar Katz, Lior Wolf Published: 2026-01-25 Categories: cs.LG arXiv: https://arxiv.org/abs/2601.17958v1 Attention matrices are fundamental to transformer research, supporting a broad range of applications including interpretability, visualization, manipulation, and distillation. Yet, most existing analyses focus on individual attention heads or layers, failing to account for the model's global behavior. While prior efforts have extended attention formulations across multiple heads via averaging and matrix multiplications or incorporated components such as normalization and FFNs, a unified and complete representation that encapsulates all transformer blocks is still lacking. We address this gap by introducing TensorLens, a novel formulation that captures the entire transformer as a single, input-dependent linear operator expressed through a high-order attention-interaction tensor. This tensor jointly encodes attention, FFNs, activations, normalizations, and residual connections, offering a theoretically coherent and expressive linear representation of the model's computation. TensorLens is theoretically grounded and our empirical validation shows that it yields richer representations than previous attention-aggregation methods. Our experiments demonstrate that the attention tensor can serve as a powerful foundation for developing tools aimed at interpretability and model understanding. Our code is attached as a supplementary. --- ### Scaling Effects and Uncertainty Quantification in Neural Actor Critic Algorithms Authors: Nikos Georgoudios, Konstantinos Spiliopoulos, Justin Sirignano Published: 2026-01-25 Categories: cs.LG, math.PR arXiv: https://arxiv.org/abs/2601.17954v1 We investigate the neural Actor Critic algorithm using shallow neural networks for both the Actor and Critic models. The focus of this work is twofold: first, to compare the convergence properties of the network outputs under various scaling schemes as the network width and the number of training steps tend to infinity; and second, to provide precise control of the approximation error associated with each scaling regime. Previous work has shown convergence to ordinary differential equations with random initial conditions under inverse square root scaling in the network width. In this work, we shift the focus from convergence speed alone to a more comprehensive statistical characterization of the algorithm's output, with the goal of quantifying uncertainty in neural Actor Critic methods. Specifically, we study a general inverse polynomial scaling in the network width, with an exponent treated as a tunable hyperparameter taking values strictly between one half and one. We derive an asymptotic expansion of the network outputs, interpreted as statistical estimators, in order to clarify their structure. To leading order, we show that the variance decays as a power of the network width, with an exponent equal to one half minus the scaling parameter, implying improved statistical robustness as the scaling parameter approaches one. Numerical experiments support this behavior and further suggest faster convergence for this choice of scaling. Finally, our analysis yields concrete guidelines for selecting algorithmic hyperparameters, including learning rates and exploration rates, as functions of the network width and the scaling parameter, ensuring provably favorable statistical behavior. --- ### A Monosemantic Attribution Framework for Stable Interpretability in Clinical Neuroscience Transformer-Based Language Models Authors: Michail Mamalakis, Tiago Azevedo, Cristian Cosentino, Chiara D'Ercoli, Subati Abulikemu, Zhongtian Sun, Richard Bethlehem, Pietro Lio Published: 2026-01-25 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2601.17952v2 Interpretability remains a key challenge for deploying language models (LM) in clinical settings such as progression diagnosis of Alzheimer disease, where early and trustworthy predictions are essential. Existing attribution methods exhibit high inter-method variability and unstable explanations due to the polysemantic nature of Transformer-Based LM and LLM representations, while mechanistic interpretability approaches lack direct alignment with model inputs and outputs and do not provide explicit importance scores. We introduce a unified interpretability framework that integrates attributional and mechanistic perspectives through monosemantic feature extraction. By constructing a monosemantic embedding space at the level of an transformer-based LM layer and optimizing the framework to explicitly reduce inter-method variability, our approach produces stable input-level importance scores and highlights salient features via a decompressed representation of the layer of interest, advancing the safe and trustworthy application of LMs in cognitive health and neurodegenerative disease. --- ### UPLiFT: Efficient Pixel-Dense Feature Upsampling with Local Attenders Authors: Matthew Walmer, Saksham Suri, Anirud Aggarwal, Abhinav Shrivastava Published: 2026-01-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.17950v2 The space of task-agnostic feature upsampling has emerged as a promising area of research to efficiently create denser features from pre-trained visual backbones. These methods act as a shortcut to achieve dense features for a fraction of the cost by learning to map low-resolution features to high-resolution versions. While early works in this space used iterative upsampling approaches, more recent works have switched to cross-attention-based methods, which risk falling into the same efficiency scaling problems of the backbones they are upsampling. In this work, we demonstrate that iterative upsampling methods can still compete with cross-attention-based methods; moreover, they can achieve state-of-the-art performance with lower inference costs. We propose UPLiFT, an architecture for Universal Pixel-dense Lightweight Feature Transforms. We also propose an efficient Local Attender operator to overcome the limitations of prior iterative feature upsampling methods. This operator uses an alternative attentional pooling formulation defined fully locally. We show that our Local Attender allows UPLiFT to maintain stable features throughout upsampling, enabling state-of-the-art performance with lower inference costs than existing pixel-dense feature upsamplers. In addition, we apply UPLiFT to generative downstream tasks and show that it achieves competitive performance with state-of-the-art Coupled Flow Matching models for VAE feature upsampling. Altogether, UPLiFT offers a versatile and efficient approach to creating denser features. --- ### FlowMorph: Physics-Consistent Self-Supervision for Label-Free Single-Cell Mechanics in Microfluidic Videos Authors: Bora Yimenicioglu, Vishal Manikanden Published: 2026-01-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.17947v1 Mechanical properties of red blood cells (RBCs) are promising biomarkers for hematologic and systemic disease, motivating microfluidic assays that probe deformability at throughputs of $10^3$--$10^6$ cells per experiment. However, existing pipelines rely on supervised segmentation or hand-crafted kymographs and rarely encode the laminar Stokes-flow physics that governs RBC shape evolution. We introduce FlowMorph, a physics-consistent self-supervised framework that learns a label-free scalar mechanics proxy $k$ for each tracked RBC from short brightfield microfluidic videos. FlowMorph models each cell by a low-dimensional parametric contour, advances boundary points through a differentiable ''capsule-in-flow'' combining laminar advection and curvature-regularized elastic relaxation, and optimizes a loss coupling silhouette overlap, intra-cellular flow agreement, area conservation, wall constraints, and temporal smoothness, using only automatically derived silhouettes and optical flow. Across four public RBC microfluidic datasets, FlowMorph achieves a mean silhouette IoU of $0.905$ on physics-rich videos with provided velocity fields and markedly improves area conservation and wall violations over purely data-driven baselines. On $\sim 1.5\times 10^5$ centered sequences, the scalar $k$ alone separates tank-treading from flipping dynamics with an AUC of $0.863$. Using only $200$ real-time deformability cytometry (RT-DC) events for calibration, a monotone map $E=g(k)$ predicts apparent Young's modulus with a mean absolute error of $0.118$\,MPa on $600$ held-out cells and degrades gracefully under shifts in channel geometry, optics, and frame rate. --- ### Credit Fairness: Online Fairness In Shared Resource Pools Authors: Seyed Majid Zahedi, Rupert Freeman Published: 2026-01-25 Categories: cs.GT, cs.AI, cs.OS arXiv: https://arxiv.org/abs/2601.17944v2 We study repeated allocation of shared resources among agents with time-varying demands and capped linear utilities. In this setting, independently maximizing the minimum endowment-normalized utility in each round satisfies sharing incentives (agents weakly prefer participating in the mechanism to not participating), strategyproofness (agents have no incentive to misreport their demands), and Pareto efficiency. However, this max-min mechanism can lead to large disparities in the total resources received by agents, even when they have the same average demand. We introduce credit fairness, a property that, together with Pareto efficiency, strengthens sharing incentives by giving agents who lend resources in early rounds priority toward recouping those resources in later rounds. Credit fairness can be achieved in conjunction with either Pareto efficiency or strategyproofness individually, but we show that, under anonymity, it cannot be achieved together with both. We propose a mechanism that is credit fair and Pareto efficient, and evaluate it in a computational resource-sharing setting. --- ### LLM-Based SQL Generation: Prompting, Self-Refinement, and Adaptive Weighted Majority Voting Authors: Yu-Jie Yang, Hung-Fu Chang, Po-An Chen Published: 2026-01-25 Categories: cs.AI, cs.DB arXiv: https://arxiv.org/abs/2601.17942v1 Text-to-SQL has emerged as a prominent research area, particularly with the rapid advancement of large language models (LLMs). By enabling users to query databases through natural language rather than SQL, this technology significantly lowers the barrier to data analysis. However, generating accurate SQL from natural language remains challenging due to ambiguity in user queries, the complexity of schema linking, limited generalization across SQL dialects, and the need for domain-specific understanding. In this study, we propose a Single-Agent Self-Refinement with Ensemble Voting (SSEV) pipeline built on PET-SQL that operates without ground-truth data, integrating self-refinement with Weighted Majority Voting (WMV) and its randomized variant (RWMA). Experimental results show that the SSEV achieves competitive performance across multiple benchmarks, attaining execution accuracies of 85.5% on Spider 1.0-Dev, 86.4% on Spider 1.0-Test, and 66.3% on BIRD-Dev. Building on insights from the SSEV pipeline, we further propose ReCAPAgent-SQL (Refinement-Critique-Act-Plan agent-based SQL framework) to address the growing complexity of enterprise databases and real-world Text-to-SQL tasks. The framework integrates multiple specialized agents for planning, external knowledge retrieval, critique, action generation, self-refinement, schema linking, and result validation, enabling iterative refinement of SQL predictions through agent collaboration. ReCAPAgent-SQL's WMA results achieve 31% execution accuracy on the first 100 queries of Spider 2.0-Lite, demonstrating significant improvements in handling real-world enterprise scenarios. Overall, our work facilitates the deployment of scalable Text-to-SQL systems in practical settings, supporting better data-driven decision-making at lower cost and with greater efficiency. --- ### DTC: A Deformable Transposed Convolution Module for Medical Image Segmentation Authors: Chengkun Sun, Jinqian Pan, Renjie Liang, Zhengkang Fan, Xin Miao, Jiang Bian, Jie Xu Published: 2026-01-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.17939v1 In medical image segmentation, particularly in UNet-like architectures, upsampling is primarily used to transform smaller feature maps into larger ones, enabling feature fusion between encoder and decoder features and supporting multi-scale prediction. Conventional upsampling methods, such as transposed convolution and linear interpolation, operate on fixed positions: transposed convolution applies kernel elements to predetermined pixel or voxel locations, while linear interpolation assigns values based on fixed coordinates in the original feature map. These fixed-position approaches may fail to capture structural information beyond predefined sampling positions and can lead to artifacts or loss of detail. Inspired by deformable convolutions, we propose a novel upsampling method, Deformable Transposed Convolution (DTC), which learns dynamic coordinates (i.e., sampling positions) to generate high-resolution feature maps for both 2D and 3D medical image segmentation tasks. Experiments on 3D (e.g., BTCV15) and 2D datasets (e.g., ISIC18, BUSI) demonstrate that DTC can be effectively integrated into existing medical image segmentation models, consistently improving the decoder's feature reconstruction and detail recovery capability. --- ### FedGraph-VASP: Privacy-Preserving Federated Graph Learning with Post-Quantum Security for Cross-Institutional Anti-Money Laundering Authors: Daniel Commey, Matilda Nkoom, Yousef Alsenani, Sena G. Hounsinou, Garth V. Crosby Published: 2026-01-25 Categories: cs.LG, cs.CR, cs.SI arXiv: https://arxiv.org/abs/2601.17935v1 Virtual Asset Service Providers (VASPs) face a fundamental tension between regulatory compliance and user privacy when detecting cross-institutional money laundering. Current approaches require either sharing sensitive transaction data or operating in isolation, leaving critical cross-chain laundering patterns undetected. We present FedGraph-VASP, a privacy-preserving federated graph learning framework that enables collaborative anti-money laundering (AML) without exposing raw user data. Our key contribution is a Boundary Embedding Exchange protocol that shares only compressed, non-invertible graph neural network representations of boundary accounts. These exchanges are secured using post-quantum cryptography, specifically the NIST-standardized Kyber-512 key encapsulation mechanism combined with AES-256-GCM authenticated encryption. Experiments on the Elliptic Bitcoin dataset with realistic Louvain partitioning show that FedGraph-VASP achieves an F1-score of 0.508, outperforming the state-of-the-art generative baseline FedSage+ (F1 = 0.453) by 12.1 percent on binary fraud detection. We further show robustness under low-connectivity settings where generative imputation degrades performance, while approaching centralized performance (F1 = 0.620) in high-connectivity regimes. We additionally evaluate generalization on an Ethereum fraud detection dataset, where FedGraph-VASP (F1 = 0.635) is less effective under sparse cross-silo connectivity, while FedSage+ excels (F1 = 0.855), outperforming even local training (F1 = 0.785). These results highlight a topology-dependent trade-off: embedding exchange benefits connected transaction graphs, whereas generative imputation can dominate in highly modular sparse graphs. A privacy audit shows embeddings are only partially invertible (R^2 = 0.32), limiting exact feature recovery. --- ### From Specialist to Generalist: Unlocking SAM's Learning Potential on Unlabeled Medical Images Authors: Vi Vu, Thanh-Huy Nguyen, Tien-Thinh Nguyen, Ba-Thinh Lam, Hoang-Thien Nguyen, Tianyang Wang, Xingjian Li, Min Xu Published: 2026-01-25 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2601.17934v2 Foundation models like the Segment Anything Model (SAM) show strong generalization, yet adapting them to medical images remains difficult due to domain shift, scarce labels, and the inability of Parameter-Efficient Fine-Tuning (PEFT) to exploit unlabeled data. While conventional models like U-Net excel in semi-supervised medical learning, their potential to assist a PEFT SAM has been largely overlooked. We introduce SC-SAM, a specialist-generalist framework where U-Net provides point-based prompts and pseudo-labels to guide SAM's adaptation, while SAM serves as a powerful generalist supervisor to regularize U-Net. This reciprocal guidance forms a bidirectional co-training loop that allows both models to effectively exploit the unlabeled data. Across prostate MRI and polyp segmentation benchmarks, our method achieves state-of-the-art results, outperforming other existing semi-supervised SAM variants and even medical foundation models like MedSAM, highlighting the value of specialist-generalist cooperation for label-efficient medical image segmentation. Our code is available at https://github.com/vnlvi2k3/SC-SAM. --- ### Dissipative Learning: A Framework for Viable Adaptive Systems Authors: Laurent Caraffa Published: 2026-01-25 Categories: cs.LG, cs.CV arXiv: https://arxiv.org/abs/2601.17933v1 We propose a perspective in which learning is an intrinsically dissipative process. Forgetting and regularization are not heuristic add-ons but structural requirements for adaptive systems. Drawing on information theory, thermodynamics, and information geometry, we introduce the BEDS (Bayesian Emergent Dissipative Structures) framework, modeling learning as the evolution of compressed belief states under dissipation constraints. A central contribution is the Conditional Optimality Theorem, showing that Fisher-Rao regularization measuring change via information divergence rather than Euclidean distance is the unique thermodynamically optimal regularization strategy, achieving minimal dissipation. Euclidean regularization is shown to be structurally suboptimal. The framework unifies existing methods (Ridge, SIGReg, EMA, SAC) as special cases of a single governing equation. Within this view, overfitting corresponds to over-crystallization, while catastrophic forgetting reflects insufficient dissipation control. The framework distinguishes BEDS-crystallizable problems, where beliefs converge to stable equilibria, from BEDS-maintainable problems, which require continual adaptation. It extends naturally to continual and multi-agent systems, where viability, stability under adaptation and finite resources replaces asymptotic optimality as the primary criterion. Overall, this work reframes learning as maintaining viable belief states under dissipation constraints, providing a principled lens on forgetting, regularization, and stability. --- ### RemEdit: Efficient Diffusion Editing with Riemannian Geometry Authors: Eashan Adhikarla, Brian D. Davison Published: 2026-01-25 Categories: cs.CV, cs.MM arXiv: https://arxiv.org/abs/2601.17927v1 Controllable image generation is fundamental to the success of modern generative AI, yet it faces a critical trade-off between semantic fidelity and inference speed. The RemEdit diffusion-based framework addresses this trade-off with two synergistic innovations. First, for editing fidelity, we navigate the latent space as a Riemannian manifold. A mamba-based module efficiently learns the manifold's structure, enabling direct and accurate geodesic path computation for smooth semantic edits. This control is further refined by a dual-SLERP blending technique and a goal-aware prompt enrichment pass from a Vision-Language Model. Second, for additional acceleration, we introduce a novel task-specific attention pruning mechanism. A lightweight pruning head learns to retain tokens essential to the edit, enabling effective optimization without the semantic degradation common in content-agnostic approaches. RemEdit surpasses prior state-of-the-art editing frameworks while maintaining real-time performance under 50% pruning. Consequently, RemEdit establishes a new benchmark for practical and powerful image editing. Source code: https://www.github.com/eashanadhikarla/RemEdit. --- ### Learning Transferable Skills in Action RPGs via Directed Skill Graphs and Selective Adaptation Authors: Ali Najar Published: 2026-01-25 Categories: cs.AI arXiv: https://arxiv.org/abs/2601.17923v2 Lifelong agents should expand their competence over time without retraining from scratch or overwriting previously learned behaviors. We investigate this in a challenging real-time control setting (Dark Souls III) by representing combat as a directed skill graph and training its components in a hierarchical curriculum. The resulting agent decomposes control into five reusable skills: camera control, target lock-on, movement, dodging, and a heal-attack decision policy, each optimized for a narrow responsibility. This factorization improves sample efficiency by reducing the burden on any single policy and supports selective post-training: when the environment shifts from Phase 1 to Phase 2, only a subset of skills must be adapted, while upstream skills remain transferable. Empirically, we find that targeted fine-tuning of just two skills rapidly recovers performance under a limited interaction budget, suggesting that skill-graph curricula together with selective fine-tuning offer a practical pathway toward evolving, continually learning agents in complex real-time environments. --- ### ShapLoRA: Allocation of Low-rank Adaption on Large Language Models via Shapley Value Inspired Importance Estimation Authors: Yi Zhao, Qinghua Yao, Xinyuan song, Wei Zhu Published: 2026-01-25 Categories: cs.CL arXiv: https://arxiv.org/abs/2601.17921v1 Low-rank adaption (LoRA) is a representative method in the field of parameter-efficient fine-tuning (PEFT), and is key to Democratizating the modern large language models (LLMs). The vanilla LoRA is implemented with uniform ranks, and the recent literature have found that properly allocating ranks on the LLM backbones results in performance boosts. However, the previous rank allocation methods have limitations since they rely on inexplanable and unreliable importance measures for the LoRA ranks. To address the above issues, we propose the ShapLoRA framework. Inspired by the explanable attribution measure Shapley Value, we combine the sensitivity-based measures with the idea of coalitions in the collaborative games among LoRA ranks, and propose a more explainable importance measure called Shapley sensitivity. In addition, we optimize the workflow of the existing works by: (a) calculating Shapley sensitivity on a separate validation set; (b) Setting up the allocating-retraining procedures for fair comparisons. We have conducted experiments on various challenging tasks, and the experimental results demonstrate that our ShapLoRA method can outperform the recent baselines with comparable tunable parameters.\footnote{Codes and fine-tuned models will be open-sourced to facilitate future research. --- ### Agentic AI for Self-Driving Laboratories in Soft Matter: Taxonomy, Benchmarks,and Open Challenges Authors: Xuanzhou Chen, Audrey Wang, Stanley Yin, Hanyang Jiang, Dong Zhang Published: 2026-01-25 Categories: cs.AI arXiv: https://arxiv.org/abs/2601.17920v1 Self-driving laboratories (SDLs) close the loop between experiment design, automated execution, and data-driven decision making, and they provide a demanding testbed for agentic AI under expensive actions, noisy and delayed feedback, strict feasibility and safety constraints, and non-stationarity. This survey uses soft matter as a representative setting but focuses on the AI questions that arise in real laboratories. We frame SDL autonomy as an agent environment interaction problem with explicit observations, actions, costs, and constraints, and we use this formulation to connect common SDL pipelines to established AI principles. We review the main method families that enable closed loop experimentation, including Bayesian optimization and active learning for sample efficient experiment selection, planning and reinforcement learning for long horizon protocol optimization, and tool using agents that orchestrate heterogeneous instruments and software. We emphasize verifiable and provenance aware policies that support debugging, reproducibility, and safe operation. We then propose a capability driven taxonomy that organizes systems by decision horizon, uncertainty modeling, action parameterization, constraint handling, failure recovery, and human involvement. To enable meaningful comparison, we synthesize benchmark task templates and evaluation metrics that prioritize cost aware performance, robustness to drift, constraint violation behavior, and reproducibility. Finally, we distill lessons from deployed SDLs and outline open challenges in multi-modal representation, calibrated uncertainty, safe exploration, and shared benchmark infrastructure. --- ### Benchmarking Direct Preference Optimization for Medical Large Vision-Language Models Authors: Dain Kim, Jiwoo Lee, Jaehoon Yun, Yong Hoe Koo, Qingyu Chen, Hyunjae Kim, Jaewoo Kang Published: 2026-01-25 Categories: cs.CV, cs.CL arXiv: https://arxiv.org/abs/2601.17918v1 Large Vision-Language Models (LVLMs) hold significant promise for medical applications, yet their deployment is often constrained by insufficient alignment and reliability. While Direct Preference Optimization (DPO) has emerged as a potent framework for refining model responses, its efficacy in high-stakes medical contexts remains underexplored, lacking the rigorous empirical groundwork necessary to guide future methodological advances. To bridge this gap, we present the first comprehensive examination of diverse DPO variants within the medical domain, evaluating nine distinct formulations across two medical LVLMs: LLaVA-Med and HuatuoGPT-Vision. Our results reveal several critical limitations: current DPO approaches often yield inconsistent gains over supervised fine-tuning, with their efficacy varying significantly across different tasks and backbones. Furthermore, they frequently fail to resolve fundamental visual misinterpretation errors. Building on these insights, we present a targeted preference construction strategy as a proof-of-concept that explicitly addresses visual misinterpretation errors frequently observed in existing DPO models. This design yields a 3.6% improvement over the strongest existing DPO baseline on visual question-answering tasks. To support future research, we release our complete framework, including all training data, model checkpoints, and our codebase at https://github.com/dmis-lab/med-vlm-dpo. --- ### Streaming-dLLM: Accelerating Diffusion LLMs via Suffix Pruning and Dynamic Decoding Authors: Zhongyu Xiao, Zhiwei Hao, Jianyuan Guo, Yong Luo, Jia Liu, Jie Xu, Han Hu Published: 2026-01-25 Categories: cs.LG, cs.AI, cs.CL, cs.CV arXiv: https://arxiv.org/abs/2601.17917v3 Diffusion Large Language Models (dLLMs) offer a compelling paradigm for natural language generation, leveraging parallel decoding and bidirectional attention to achieve superior global coherence compared to autoregressive models. While recent works have accelerated inference via KV cache reuse or heuristic decoding, they overlook the intrinsic inefficiencies within the block-wise diffusion process. Specifically, they suffer from spatial redundancy by modeling informative-sparse suffix regions uniformly and temporal inefficiency by applying fixed denoising schedules across all the decoding process. To address this, we propose Streaming-dLLM, a training-free framework that streamlines inference across both spatial and temporal dimensions. Spatially, we introduce attenuation guided suffix modeling to approximate the full context by pruning redundant mask tokens. Temporally, we employ a dynamic confidence aware strategy with an early exit mechanism, allowing the model to skip unnecessary iterations for converged tokens. Extensive experiments show that Streaming-dLLM achieves up to 68.2X speedup while maintaining generation quality, highlighting its effectiveness in diffusion decoding. The code is available at https://github.com/xiaoshideta/Streaming-dLLM. --- ### UniPACT: A Multimodal Framework for Prognostic Question Answering on Raw ECG and Structured EHR Authors: Jialu Tang, Tong Xia, Yuan Lu, Aaqib Saeed Published: 2026-01-25 Categories: cs.LG arXiv: https://arxiv.org/abs/2601.17916v1 Accurate clinical prognosis requires synthesizing structured Electronic Health Records (EHRs) with real-time physiological signals like the Electrocardiogram (ECG). Large Language Models (LLMs) offer a powerful reasoning engine for this task but struggle to natively process these heterogeneous, non-textual data types. To address this, we propose UniPACT (Unified Prognostic Question Answering for Clinical Time-series), a unified framework for prognostic question answering that bridges this modality gap. UniPACT's core contribution is a structured prompting mechanism that converts numerical EHR data into semantically rich text. This textualized patient context is then fused with representations learned directly from raw ECG waveforms, enabling an LLM to reason over both modalities holistically. We evaluate UniPACT on the comprehensive MDS-ED benchmark, it achieves a state-of-the-art mean AUROC of 89.37% across a diverse set of prognostic tasks including diagnosis, deterioration, ICU admission, and mortality, outperforming specialized baselines. Further analysis demonstrates that our multimodal, multi-task approach is critical for performance and provides robustness in missing data scenarios. --- ### Think Locally, Explain Globally: Graph-Guided LLM Investigations via Local Reasoning and Belief Propagation Authors: Saurabh Jha, Rohan Arora, Bhavya, Noah Zheutlin, Paulina Toro Isaza, Laura Shwartz, Yu Deng, Daby Sow, Ruchi Mahindru, Ruchir Puri Published: 2026-01-25 Categories: cs.AI, cs.LG, cs.LO arXiv: https://arxiv.org/abs/2601.17915v2 LLM agents excel when environments are mostly static and the needed information fits in a model's context window, but they often fail in open-ended investigations where explanations must be constructed by iteratively mining evidence from massive, heterogeneous operational data. These investigations exhibit hidden dependency structure: entities interact, signals co-vary, and the importance of a fact may only become clear after other evidence is discovered. Because the context window is bounded, agents must summarize intermediate findings before their significance is known, increasing the risk of discarding key evidence. ReAct-style agents are especially brittle in this regime. Their retrieve-summarize-reason loop makes conclusions sensitive to exploration order and introduces run-to-run non-determinism, producing a reliability gap where Pass-at-k may be high but Majority-at-k remains low. Simply sampling more rollouts or generating longer reasoning traces does not reliably stabilize results, since hypotheses cannot be autonomously checked as new evidence arrives and there is no explicit mechanism for belief bookkeeping and revision. In addition, ReAct entangles semantic reasoning with controller duties such as tool orchestration and state tracking, so execution errors and plan drift degrade reasoning while consuming scarce context. We address these issues by formulating investigation as abductive reasoning over a dependency graph and proposing EoG (Explanations over Graphs), a disaggregated framework in which an LLM performs bounded local evidence mining and labeling (cause vs symptom) while a deterministic controller manages traversal, state, and belief propagation to compute a minimal explanatory frontier. On a representative ITBench diagnostics task, EoG improves both accuracy and run-to-run consistency over ReAct baselines, including a 7x average gain in Majority-at-k entity F1. --- ### Causal Pre-training Under the Fairness Lens: An Empirical Study of TabPFN Authors: Qinyi Liu, Mohammad Khalil, Naman Goel Published: 2026-01-25 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2601.17912v2 Foundation models for tabular data, such as the Tabular Prior-data Fitted Network (TabPFN), are pre-trained on a massive number of synthetic datasets generated by structural causal models (SCM). They leverage in-context learning to offer high predictive accuracy in real-world tasks. However, the fairness properties of these foundational models, which incorporate ideas from causal reasoning during pre-training, remain underexplored. In this work, we conduct a comprehensive empirical evaluation of TabPFN and its fine-tuned variants, assessing predictive performance, fairness, and robustness across varying dataset sizes and distributional shifts. Our results reveal that while TabPFN achieves stronger predictive accuracy compared to baselines and exhibits robustness to spurious correlations, improvements in fairness are moderate and inconsistent, particularly under missing-not-at-random (MNAR) covariate shifts. These findings suggest that the causal pre-training in TabPFN is helpful but insufficient for algorithmic fairness, highlighting implications for deploying TabPFN (and similar) models in practice and the need for further fairness interventions. --- ### Adaptive Weighting in Knowledge Distillation: An Axiomatic Framework for Multi-Scale Teacher Ensemble Optimization Authors: Aaron R. Flouro, Shawn P. Chadwick Published: 2026-01-25 Categories: cs.LG arXiv: https://arxiv.org/abs/2601.17910v1 Knowledge distillation with multiple teachers is increasingly used to improve robustness, efficiency, and safety, yet existing approaches rely largely on heuristic or implementation-specific weighting schemes. This paper develops an operator-agnostic axiomatic framework for adaptive weighting in multi-teacher knowledge distillation across three complementary scales: token, task, and context. We formalize structural conditions under which adaptive weighting operators are well-defined, admit multiple non-equivalent implementations, and can be hierarchically composed via product-structure normalization. Within this framework, we establish existence and non-uniqueness of conforming operators, characterize convergence of gradient-based optimization under standard assumptions, analyze stability and perturbation robustness, and provide an abstract formulation of safety-constrained distillation. The results decouple theoretical guarantees from specific weighting formulas, enabling principled analysis of adaptive distillation methods under heterogeneity, distribution shift, and safety constraints. --- ### FARM: Few-shot Adaptive Malware Family Classification under Concept Drift Authors: Numan Halit Guldemir, Oluwafemi Olukoya, Jesús Martínez-del-Rincón Published: 2026-01-25 Categories: cs.CR, cs.LG arXiv: https://arxiv.org/abs/2601.17907v2 Malware classification models often suffer performance degradation under concept drift due to evolving threat landscapes and the emergence of novel malware families. This paper presents FARM (Few-shot Adaptive Recognition of Malware), a unified framework for detecting and adapting to both covariate drift and label drift in Windows Portable Executable (PE) malware family classification. FARM uses a triplet autoencoder to project samples into a discriminative latent space, enabling unsupervised drift detection through DBSCAN clustering and dynamic thresholding. To enable rapid adaptation, the framework employs a few-shot strategy that can incorporate new classes from only a small number of labeled samples. FARM also supports full retraining when sufficient drifted samples accumulate, allowing longer-term model updating. Experiments on the BenchMFC dataset show that FARM improves classification performance under covariate drift by 5.6%, and achieves an average F1 score of 0.85 on unseen malware families using few-shot adaptation, increasing to 0.94 after retraining. These results indicate that FARM provides an effective approach for drift-aware malware family classification in dynamic environments with limited supervision. --- ### Feature-Space Generative Models for One-Shot Class-Incremental Learning Authors: Jack Foster, Kirill Paramonov, Mete Ozay, Umberto Michieli Published: 2026-01-25 Categories: cs.CV, cs.AI, stat.ML arXiv: https://arxiv.org/abs/2601.17905v1 Few-shot class-incremental learning (FSCIL) is a paradigm where a model, initially trained on a dataset of base classes, must adapt to an expanding problem space by recognizing novel classes with limited data. We focus on the challenging FSCIL setup where a model receives only a single sample (1-shot) for each novel class and no further training or model alterations are allowed after the base training phase. This makes generalization to novel classes particularly difficult. We propose a novel approach predicated on the hypothesis that base and novel class embeddings have structural similarity. We map the original embedding space into a residual space by subtracting the class prototype (i.e., the average class embedding) of input samples. Then, we leverage generative modeling with VAE or diffusion models to learn the multi-modal distribution of residuals over the base classes, and we use this as a valuable structural prior to improve recognition of novel classes. Our approach, Gen1S, consistently improves novel class recognition over the state of the art across multiple benchmarks and backbone architectures. --- ### Revisiting 3D Reconstruction Kernels as Low-Pass Filters Authors: Shengjun Zhang, Min Chen, Yibo Wei, Mingyu Dong, Yueqi Duan Published: 2026-01-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.17900v1 3D reconstruction is to recover 3D signals from the sampled discrete 2D pixels, with the goal to converge continuous 3D spaces. In this paper, we revisit 3D reconstruction from the perspective of signal processing, identifying the periodic spectral extension induced by discrete sampling as the fundamental challenge. Previous 3D reconstruction kernels, such as Gaussians, Exponential functions, and Student's t distributions, serve as the low pass filters to isolate the baseband spectrum. However, their unideal low-pass property results in the overlap of high-frequency components with low-frequency components in the discrete-time signal's spectrum. To this end, we introduce Jinc kernel with an instantaneous drop to zero magnitude exactly at the cutoff frequency, which is corresponding to the ideal low pass filters. As Jinc kernel suffers from low decay speed in the spatial domain, we further propose modulated kernels to strick an effective balance, and achieves superior rendering performance by reconciling spatial efficiency and frequency-domain fidelity. Experimental results have demonstrated the effectiveness of our Jinc and modulated kernels. --- ### Evolving Interdependent Operators with Large Language Models for Multi-Objective Combinatorial Optimization Authors: Junhao Qiu, Xin Chen, Liang Ge, Liyong Lin, Zhichao Lu, Qingfu Zhang Published: 2026-01-25 Categories: cs.NE arXiv: https://arxiv.org/abs/2601.17899v2 Neighborhood search operators are critical to the performance of Multi-Objective Evolutionary Algorithms (MOEAs) and rely heavily on expert design. Although recent LLM-based Automated Heuristic Design (AHD) methods have made notable progress, they primarily optimize individual heuristics or components independently, lacking explicit exploration and exploitation of dynamic coupling relationships between operators. In this paper, multi-operator optimization in MOEAs is formulated as a Markov decision process, enabling the improvement of interdependent operators through sequential decision-making. To address this, we propose the Evolution of Operator Combination (E2OC) framework for MOEAs, which achieves the co-evolution of design strategies and executable codes. E2OC employs Monte Carlo Tree Search to progressively search combinations of operator design strategies and adopts an operator rotation mechanism to identify effective operator configurations while supporting the integration of mainstream AHD methods as the underlying designer. Experimental results across AHD tasks with varying objectives and problem scales show that E2OC consistently outperforms state-of-the-art AHD and other multi-heuristic co-design frameworks, demonstrating strong generalization and sustained optimization capability. --- ### Assessment of Generative Named Entity Recognition in the Era of Large Language Models Authors: Qi Zhan, Yile Wang, Hui Huang Published: 2026-01-25 Categories: cs.CL arXiv: https://arxiv.org/abs/2601.17898v2 Named entity recognition (NER) is evolving from a sequence labeling task into a generative paradigm with the rise of large language models (LLMs). We conduct a systematic evaluation of open-source LLMs on both flat and nested NER tasks. We investigate several research questions including the performance gap between generative NER and traditional NER models, the impact of output formats, whether LLMs rely on memorization, and the preservation of general capabilities after fine-tuning. Through experiments across eight LLMs of varying scales and four standard NER datasets, we find that: (1) With parameter-efficient fine-tuning and structured formats like inline bracketed or XML, open-source LLMs achieve performance competitive with traditional encoder-based models and surpass decoder-based LLMs with in-context learning techniques; (2) The NER capability of LLMs stems from instruction-following and generative power, not mere memorization of entity-label pairs; and (3) Applying NER instruction tuning has minimal impact on general capabilities of LLMs, even improving performance on datasets like DROP by 25.50 to 45.32 F1 points due to enhanced entity understanding. These findings demonstrate that generative NER with LLMs is a promising, user-friendly alternative to traditional methods. We release the data and code at https://github.com/szu-tera/LLMs4NER. --- ### UniCog: Uncovering Cognitive Abilities of LLMs through Latent Mind Space Analysis Authors: Jiayu Liu, Yinhe Long, Zhenya Huang, Enhong Chen Published: 2026-01-25 Categories: cs.AI arXiv: https://arxiv.org/abs/2601.17897v1 A growing body of research suggests that the cognitive processes of large language models (LLMs) differ fundamentally from those of humans. However, existing interpretability methods remain limited in explaining how cognitive abilities are engaged during LLM reasoning. In this paper, we propose UniCog, a unified framework that analyzes LLM cognition via a latent mind space. Formulated as a latent variable model, UniCog encodes diverse abilities from dense model activations into sparse, disentangled latent dimensions. Through extensive analysis on six advanced LLMs, including DeepSeek-V3.2 and GPT-4o, we reveal a Pareto principle of LLM cognition, where a shared reasoning core is complemented by ability-specific signatures. Furthermore, we discover that reasoning failures often manifest as anomalous intensity in latent activations. These findings opens a new paradigm in LLM analysis, providing a cognition grounded view of reasoning dynamics. Finally, leveraging these insights, we introduce a latent-informed candidate prioritization strategy, which improves reasoning performance by up to 7.5% across challenging benchmarks. Our code is available at https://github.com/milksalute/unicog. --- ### Masked Depth Modeling for Spatial Perception Authors: Bin Tan, Changjiang Sun, Xiage Qin, Hanat Adai, Zelin Fu, Tianxiang Zhou, Han Zhang, Yinghao Xu, Xing Zhu, Yujun Shen, Nan Xue Published: 2026-01-25 Categories: cs.CV, cs.RO arXiv: https://arxiv.org/abs/2601.17895v1 Spatial visual perception is a fundamental requirement in physical-world applications like autonomous driving and robotic manipulation, driven by the need to interact with 3D environments. Capturing pixel-aligned metric depth using RGB-D cameras would be the most viable way, yet it usually faces obstacles posed by hardware limitations and challenging imaging conditions, especially in the presence of specular or texture-less surfaces. In this work, we argue that the inaccuracies from depth sensors can be viewed as "masked" signals that inherently reflect underlying geometric ambiguities. Building on this motivation, we present LingBot-Depth, a depth completion model which leverages visual context to refine depth maps through masked depth modeling and incorporates an automated data curation pipeline for scalable training. It is encouraging to see that our model outperforms top-tier RGB-D cameras in terms of both depth precision and pixel coverage. Experimental results on a range of downstream tasks further suggest that LingBot-Depth offers an aligned latent representation across RGB and depth modalities. We release the code, checkpoint, and 3M RGB-depth pairs (including 2M real data and 1M simulated data) to the community of spatial perception. --- ### Artificial Intelligence and Intellectual Property Rights: Comparative Transnational Policy Analysis Authors: Sahibpreet Singh, Manjit Singh Published: 2026-01-25 Categories: cs.CY, cs.AI, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2601.17892v1 Artificial intelligence's rapid integration with intellectual property rights necessitates assessment of its impact on trade secrets, copyrights and patents. This study addresses lacunae in existing laws where India lacks AI-specific provisions, creating doctrinal inconsistencies and enforcement inefficacies. Global discourse on AI-IPR protections remains nascent. The research identifies gaps in Indian IP laws' adaptability to AI-generated outputs: trade secret protection is inadequate against AI threats; standardized inventorship criteria are absent. Employing doctrinal and comparative methodology, it scrutinizes legislative texts, judicial precedents and policy instruments across India, US, UK and EU. Preliminary findings reveal shortcomings: India's contract law creates fragmented trade secret regime; Section 3(k) of Indian Patents Act blocks AI invention patenting; copyright varies in authorship attribution. The study proposes harmonized legal taxonomy accommodating AI's role while preserving innovation incentives. India's National AI Strategy (2024) shows progress but legislative clarity is imperative. This contributes to global discourse with AI-specific IP protections ensuring resilience and equitable innovation. Promising results underscore recalibrating India's IP jurisprudence for global alignment. --- ### When Personalization Legitimizes Risks: Uncovering Safety Vulnerabilities in Personalized Dialogue Agents Authors: Jiahe Guo, Xiangran Guo, Yulin Hu, Zimo Long, Xingyu Sui, Xuda Zhi, Yongbo Huang, Hao He, Weixiang Zhao, Yanyan Zhao, Bing Qin Published: 2026-01-25 Categories: cs.AI arXiv: https://arxiv.org/abs/2601.17887v2 Long-term memory enables large language model (LLM) agents to support personalized and sustained interactions. However, most work on personalized agents prioritizes utility and user experience, treating memory as a neutral component and largely overlooking its safety implications. In this paper, we reveal intent legitimation, a previously underexplored safety failure in personalized agents, where benign personal memories bias intent inference and cause models to legitimize inherently harmful queries. To study this phenomenon, we introduce PS-Bench, a benchmark designed to identify and quantify intent legitimation in personalized interactions. Across multiple memory-augmented agent frameworks and base LLMs, personalization increases attack success rates by 15.8\%--243.7\% relative to stateless baselines. We further provide mechanistic evidence for intent legitimation from internal representations space, and propose a lightweight detection-reflection method that effectively reduces safety degradation. Overall, our work provides the first systematic exploration and evaluation of intent legitimation as a safety failure mode that naturally arises from benign, real-world personalization, highlighting the importance of assessing safety under long-term personal context. Our code is available at: https://github.com/MuyuenLP/PS-Bench. WARNING: This paper may contain harmful content. --- ### PEAfowl: Perception-Enhanced Multi-View Vision-Language-Action for Bimanual Manipulation Authors: Qingyu Fan, Zhaoxiang Li, Jinrui Hu, Yi Lu, Wang Chen, Qiu Shen, Xiao-xiao Long, Yinghao Cai, Tao Lu, Shuo Wang, Xun Cao Published: 2026-01-25 Categories: cs.CV, cs.AI, cs.RO arXiv: https://arxiv.org/abs/2601.17885v2 Bimanual manipulation in cluttered scenes requires policies that remain stable under occlusions, viewpoint changes and scene variations. Existing vision-language-action models often lack such robustness because (i) multi-view features are fused via view-agnostic token concatenation, yielding limited cross-view spatial representations, and (ii) language is injected as global conditioning, resulting in coarse instruction grounding. In this paper, we introduce PEAfowl, a perception-enhanced multi-view VLA policy for bimanual manipulation. For spatial perception, PEAfowl predicts per-token depth distributions, performs differentiable 3D lifting, and aggregates local cross-view neighbors to form geometrically grounded, cross-view aligned representations. For language utilization, we propose to replace global conditioning with a Perceiver-style text-aware readout over frozen CLIP visual features, enabling iterative evidence accumulation. To better exploit commodity RGB-D sensing despite noisy and incomplete depth, PEAfowl's depth-distribution lifting naturally supports training-only depth distillation, where a pretrained depth teacher supervises the depth-distribution head to inject refined geometric priors without adding inference overhead. On RoboTwin 2.0 under domain-randomized setting, PEAfowl improves the strongest baseline by 23.0 pp in success rate, and physical experiments further demonstrate improved performance on the evaluated real-robot tasks. Project website: https://peafowlvla.github.io/. --- ### EEG-FM-Compass: Progress, Benchmarking, and Future Directions for EEG Foundation Models Authors: Dingkun Liu, Yuheng Chen, Zhu Chen, Zhenyao Cui, Yaozhi Wen, Jiayu An, Jingwei Luo, Dongrui Wu Published: 2026-01-25 Categories: cs.LG, cs.CV arXiv: https://arxiv.org/abs/2601.17883v3 Electroencephalography (EEG) foundation models (FMs) have recently emerged as a promising paradigm for brain-computer interfaces, aiming to learn transferable neural representations from large-scale heterogeneous recordings. Despite rapid progress, a fair and comprehensive comparison of existing EEG FMs is still lacking, owing to inconsistent pre-training objectives, preprocessing choices, and downstream evaluation protocols. To fill this gap, we present EEG-FM-Compass. We first review 55 representative models and organize their design choices into a unified taxonomic framework including data standardization, model architectures, and self-supervised pre-training strategies. We then evaluate 12 open source FMs and competitive specialist baselines across 13 EEG datasets spanning nine brain-computer interface paradigms. Emphasizing real-world deployments, we consider both cross-subject generalization under a leave-one-subject-out protocol and rapid calibration under a within-subject few-shot setting. We further compare full-parameter fine-tuning with linear probing to assess the transferability of pre-trained representations, and examine the relationship between model scale and downstream performance. Our results indicate that: 1) linear probing is frequently insufficient; 2) specialist models trained from scratch remain competitive across many tasks; and 3) larger FMs do not necessarily yield better generalization performance under current data regimes and training practices. --- ### Quran-MD: A Fine-Grained Multilingual Multimodal Dataset of the Quran Authors: Muhammad Umar Salman, Mohammad Areeb Qazi, Mohammed Talha Alam Published: 2026-01-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.17880v1 We present Quran MD, a comprehensive multimodal dataset of the Quran that integrates textual, linguistic, and audio dimensions at the verse and word levels. For each verse (ayah), the dataset provides its original Arabic text, English translation, and phonetic transliteration. To capture the rich oral tradition of Quranic recitation, we include verse-level audio from 32 distinct reciters, reflecting diverse recitation styles and dialectical nuances. At the word level, each token is paired with its corresponding Arabic script, English translation, transliteration, and an aligned audio recording, allowing fine-grained analysis of pronunciation, phonology, and semantic context. This dataset supports various applications, including natural language processing, speech recognition, text-to-speech synthesis, linguistic analysis, and digital Islamic studies. Bridging text and audio modalities across multiple reciters, this dataset provides a unique resource to advance computational approaches to Quranic recitation and study. Beyond enabling tasks such as ASR, tajweed detection, and Quranic TTS, it lays the foundation for multimodal embeddings, semantic retrieval, style transfer, and personalized tutoring systems that can support both research and community applications. The dataset is available at https://huggingface.co/datasets/Buraaq/quran-audio-text-dataset --- ### Self-Manager: Parallel Agent Loop for Long-form Deep Research Authors: Yilong Xu, Zhi Zheng, Xiang Long, Yujun Cai, Yiwei Wang Published: 2026-01-25 Categories: cs.CL, cs.AI, cs.IR arXiv: https://arxiv.org/abs/2601.17879v1 Long-form deep research requires multi-faceted investigations over extended horizons to get a comprehensive report. When handling such complex tasks, existing agents manage context at the subtask level to overcome linear context accumulation and information loss. However, they still adhere to a single context window and sequential execution paradigm, which results in mutual interference and blocking behavior, restricting scalability and adaptability. To address this issue, this paper introduces Self-Manager, a parallel agent loop that enables asynchronous and concurrent execution. The main thread can create multiple subthreads, each with its own isolated context, and manage them iteratively through Thread Control Blocks, allowing for more focused and flexible parallel agent execution. To assess its effectiveness, we benchmark Self-Manager on DeepResearch Bench, where it consistently outperforms existing single-agent loop baselines across all metrics. Furthermore, we conduct extensive analytical experiments to demonstrate the necessity of Self-Manager's design choices, as well as its advantages in contextual capacity, efficiency, and generalization. --- ### Comparative Algorithmic Governance of Public Health Instruments across India, EU, US and LMICs Authors: Sahibpreet Singh Published: 2026-01-25 Categories: cs.CY, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2601.17877v1 The study investigates the juridico-technological architecture of international public health instruments, focusing on their implementation across India, the European Union, the United States and low- and middle-income countries (LMICs), particularly in Sub-Saharan Africa. It addresses a research lacuna: the insufficient harmonisation between normative health law and algorithmic public health infrastructures in resource-constrained jurisdictions. The principal objective is to assess how artificial intelligence augments implementation of instruments grounded in IHR 2005 and the WHO FCTC while identifying doctrinal and infrastructural bottlenecks. Using comparative doctrinal analysis and legal-normative mapping, the study triangulates legislative instruments, WHO monitoring frameworks, AI systems including BlueDot, Aarogya Setu and EIOS, and compliance metrics. Preliminary results show that AI has improved early detection, surveillance precision and responsiveness in high-capacity jurisdictions, whereas LMICs face infrastructural deficits, data privacy gaps and fragmented legal scaffolding. The findings highlight the relevance of the EU Artificial Intelligence Act and GDPR as regulatory prototypes for health-oriented algorithmic governance and contrast them with embryonic AI integration and limited internet penetration in many LMICs. The study argues for embedding AI within a rights-compliant, supranationally coordinated regulatory framework to secure equitable health outcomes and stronger compliance. It proposes a model for algorithmic treaty-making inspired by FCTC architecture and calls for WHO-led compliance mechanisms modelled on the WTO Dispute Settlement Body to enhance pandemic preparedness, surveillance equity and transnational governance resilience. --- ### On the Emergence and Test-Time Use of Structural Information in Large Language Models Authors: Michelle Chao Chen, Moritz Miller, Bernhard Schölkopf, Siyuan Guo Published: 2026-01-25 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2601.17869v1 Learning structural information from observational data is central to producing new knowledge outside the training corpus. This holds for mechanistic understanding in scientific discovery as well as flexible test-time compositional generation. We thus study how language models learn abstract structures and utilize the learnt structural information at test-time. To ensure a controlled setup, we design a natural language dataset based on linguistic structural transformations. We empirically show that the emergence of learning structural information correlates with complex reasoning tasks, and that the ability to perform test-time compositional generation remains limited. --- ### VidLaDA: Bidirectional Diffusion Large Language Models for Efficient Video Understanding Authors: Zhihao He, Tieyuan Chen, Kangyu Wang, Ziran Qin, Yang Shao, Chaofan Gan, Shijie Li, Zuxuan Wu, Weiyao Lin Published: 2026-01-25 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2601.17868v2 Current Video Large Language Models (Video LLMs) typically encode frames via a vision encoder and employ an autoregressive (AR) LLM for understanding and generation. However, this AR paradigm inevitably faces a dual efficiency bottleneck: strictly unidirectional attention compromises understanding efficiency by hindering global spatiotemporal aggregation, while serial decoding restricts generation efficiency. To address this, we propose VidLaDA, a Video LLM based on Diffusion Language Models (DLMs) that leverages bidirectional attention to unlock comprehensive spatiotemporal modeling and decode tokens in parallel. To further mitigate the computational overhead of diffusion decoding, we introduce MARS-Cache, an acceleration strategy that prunes redundancy by combining asynchronous visual cache refreshing with frame-wise chunk attention. Experiments show VidLaDA rivals state-of-the-art AR baselines (e.g., Qwen2.5-VL and LLaVA-Video) and outperforms DLM baselines, with MARS-Cache delivering over 12x speedup without compromising accuracy. Code and checkpoints are open-sourced at https://github.com/ziHoHe/VidLaDA. ---