# Research Papers — 2026-01 · bundle page 90 of 189 > Full-text markdown of papers #4451–4500 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/90 [← Previous bundle](https://aipod.dev/papers/archive/2026-01/page/89.md) [Next bundle →](https://aipod.dev/papers/archive/2026-01/page/91.md) ### The Post-Turing Condition: Conceptualising Artificial Subjectivity and Synthetic Sociality Authors: Thorsten Jelinek, Patrick Glauner, Alvin Wang Graylin, Yubao Qiu Published: 2026-01-19 Categories: cs.CY, cs.AI arXiv: https://arxiv.org/abs/2601.12938v1 In the Post-Turing era, artificial intelligence increasingly shapes social coordination and meaning formation rather than merely automating cognitive tasks. The central challenge is therefore not whether machines become conscious, but whether processes of interpretation and shared reference are progressively automated in ways that marginalize human participation. This paper introduces the PRMO framework, relating AI design trajectories to four constitutive dimensions of human subjectivity: Perception, Representation, Meaning, and the Real. Within this framework, Synthetic Sociality denotes a technological horizon in which artificial agents negotiate coherence and social order primarily among themselves, raising the structural risk of human exclusion from meaning formation. To address this risk, the paper proposes Quadrangulation as a design principle for socially embedded AI systems, requiring artificial agents to treat the human subject as a constitutive reference within shared contexts of meaning. This work is a conceptual perspective that contributes a structural vocabulary for analyzing AI systems at the intersection of computation and society, without proposing a specific technical implementation. --- ### On the Evidentiary Limits of Membership Inference for Copyright Auditing Authors: Murat Bilgehan Ertan, Emirhan Böge, Min Chen, Kaleel Mahmood, Marten van Dijk Published: 2026-01-19 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2601.12937v1 As large language models (LLMs) are trained on increasingly opaque corpora, membership inference attacks (MIAs) have been proposed to audit whether copyrighted texts were used during training, despite growing concerns about their reliability under realistic conditions. We ask whether MIAs can serve as admissible evidence in adversarial copyright disputes where an accused model developer may obfuscate training data while preserving semantic content, and formalize this setting through a judge-prosecutor-accused communication protocol. To test robustness under this protocol, we introduce SAGE (Structure-Aware SAE-Guided Extraction), a paraphrasing framework guided by Sparse Autoencoders (SAEs) that rewrites training data to alter lexical structure while preserving semantic content and downstream utility. Our experiments show that state-of-the-art MIAs degrade when models are fine-tuned on SAGE-generated paraphrases, indicating that their signals are not robust to semantics-preserving transformations. While some leakage remains in certain fine-tuning regimes, these results suggest that MIAs are brittle in adversarial settings and insufficient, on their own, as a standalone mechanism for copyright auditing of LLMs. --- ### QASA: Quality-Guided K-Adaptive Slot Attention for Unsupervised Object-Centric Learning Authors: Tianran Ouyang, Xingping Dong, Jing Zhang, Mang Ye, Jun Chen, Bo Du Published: 2026-01-19 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.12936v1 Slot Attention, an approach that binds different objects in a scene to a set of "slots", has become a leading method in unsupervised object-centric learning. Most methods assume a fixed slot count K, and to better accommodate the dynamic nature of object cardinality, a few works have explored K-adaptive variants. However, existing K-adaptive methods still suffer from two limitations. First, they do not explicitly constrain slot-binding quality, so low-quality slots lead to ambiguous feature attribution. Second, adding a slot-count penalty to the reconstruction objective creates conflicting optimization goals between reducing the number of active slots and maintaining reconstruction fidelity. As a result, they still lag significantly behind strong K-fixed baselines. To address these challenges, we propose Quality-Guided K-Adaptive Slot Attention (QASA). First, we decouple slot selection from reconstruction, eliminating the mutual constraints between the two objectives. Then, we propose an unsupervised Slot-Quality metric to assess per-slot quality, providing a principled signal for fine-grained slot--object binding. Based on this metric, we design a Quality-Guided Slot Selection scheme that dynamically selects a subset of high-quality slots and feeds them into our newly designed gated decoder for reconstruction during training. At inference, token-wise competition on slot attention yields a K-adaptive outcome. Experiments show that QASA substantially outperforms existing K-adaptive methods on both real and synthetic datasets. Moreover, on real-world datasets QASA surpasses K-fixed methods. --- ### Online Continual Learning for Time Series: a Natural Score-driven Approach Authors: Edoardo Urettini, Daniele Atzeni, Ioanna-Yvonni Tsaknaki, Antonio Carta Published: 2026-01-19 Categories: cs.LG, cs.AI, stat.ML arXiv: https://arxiv.org/abs/2601.12931v1 Online continual learning (OCL) methods adapt to changing environments without forgetting past knowledge. Similarly, online time series forecasting (OTSF) is a real-world problem where data evolve in time and success depends on both rapid adaptation and long-term memory. Indeed, time-varying and regime-switching forecasting models have been extensively studied, offering a strong justification for the use of OCL in these settings. Building on recent work that applies OCL to OTSF, this paper aims to strengthen the theoretical and practical connections between time series methods and OCL. First, we reframe neural network optimization as a parameter filtering problem, showing that natural gradient descent is a score-driven method and proving its information-theoretic optimality. Then, we show that using a Student's t likelihood in addition to natural gradient induces a bounded update, which improves robustness to outliers. Finally, we introduce Natural Score-driven Replay (NatSR), which combines our robust optimizer with a replay buffer and a dynamic scale heuristic that improves fast adaptation at regime drifts. Empirical results demonstrate that NatSR achieves stronger forecasting performance than more complex state-of-the-art methods. --- ### Membership Inference Test: Auditing Training Data in Object Classification Models Authors: Gonzalo Mancera, Daniel DeAlcala, Aythami Morales, Ruben Tolosana, Julian Fierrez Published: 2026-01-19 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2601.12929v1 In this research, we analyze the performance of Membership Inference Tests (MINT), focusing on determining whether given data were utilized during the training phase, specifically in the domain of object recognition. Within the area of object recognition, we propose and develop architectures tailored for MINT models. These architectures aim to optimize performance and efficiency in data utilization, offering a tailored solution to tackle the complexities inherent in the object recognition domain. We conducted experiments involving an object detection model, an embedding extractor, and a MINT module. These experiments were performed in three public databases, totaling over 174K images. The proposed architecture leverages convolutional layers to capture and model the activation patterns present in the data during the training process. Through our analysis, we are able to identify given data used for testing and training, achieving precision rates ranging between 70% and 80%, contingent upon the depth of the detection module layer chosen for input to the MINT module. Additionally, our studies entail an analysis of the factors influencing the MINT Module, delving into the contributing elements behind more transparent training processes. --- ### An efficient heuristic for geometric analysis of cell deformations Authors: Yaima Paz Soto, Silena Herold Garcia, Ximo Gual-Arnau, Antoni Jaume-i-Capó, Manuel González-Hidalgo Published: 2026-01-19 Categories: cs.LG, q-bio.QM arXiv: https://arxiv.org/abs/2601.12928v1 Sickle cell disease causes erythrocytes to become sickle-shaped, affecting their movement in the bloodstream and reducing oxygen delivery. It has a high global prevalence and places a significant burden on healthcare systems, especially in resource-limited regions. Automated classification of sickle cells in blood images is crucial, allowing the specialist to reduce the effort required and avoid errors when quantifying the deformed cells and assessing the severity of a crisis. Recent studies have proposed various erythrocyte representation and classification methods. Since classification depends solely on cell shape, a suitable approach models erythrocytes as closed planar curves in shape space. This approach employs elastic distances between shapes, which are invariant under rotations, translations, scaling, and reparameterizations, ensuring consistent distance measurements regardless of the curves' position, starting point, or traversal speed. While previous methods exploiting shape space distances had achieved high accuracy, we refined the model by considering the geometric characteristics of healthy and sickled erythrocytes. Our method proposes (1) to employ a fixed parameterization based on the major axis of each cell to compute distances and (2) to align each cell with two templates using this parameterization before computing distances. Aligning shapes to templates before distance computation, a concept successfully applied in areas such as molecular dynamics, and using a fixed parameterization, instead of minimizing distances across all possible parameterizations, simplifies calculations. This strategy achieves 96.03\% accuracy rate in both supervised classification and unsupervised clustering. Our method ensures efficient erythrocyte classification, maintaining or improving accuracy over shape space models while significantly reducing computational costs. --- ### Dual-Stream Collaborative Transformer for Image Captioning Authors: Jun Wan, Jun Liu, Zhihui lai, Jie Zhou Published: 2026-01-19 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.12926v1 Current region feature-based image captioning methods have progressed rapidly and achieved remarkable performance. However, they are still prone to generating irrelevant descriptions due to the lack of contextual information and the over-reliance on generated partial descriptions for predicting the remaining words. In this paper, we propose a Dual-Stream Collaborative Transformer (DSCT) to address this issue by introducing the segmentation feature. The proposed DSCT consolidates and then fuses the region and segmentation features to guide the generation of caption sentences. It contains multiple Pattern-Specific Mutual Attention Encoders (PSMAEs) and Dynamic Nomination Decoders (DNDs). The PSMAE effectively highlights and consolidates the private information of two representations by querying each other. The DND dynamically searches for the most relevant learning blocks to the input textual representations and exploits the homogeneous features between the consolidated region and segmentation features to generate more accurate and descriptive caption sentences. To the best of our knowledge, this is the first study to explore how to fuse different pattern-specific features in a dynamic way to bypass their semantic inconsistencies and spatial misalignment issues for image captioning. The experimental results from popular benchmark datasets demonstrate that our DSCT outperforms the state-of-the-art image captioning models in the literature. --- ### ForeDiffusion: Foresight-Conditioned Diffusion Policy via Future View Construction for Robot Manipulation Authors: Weize Xie, Yi Ding, Ying He, Leilei Wang, Binwen Bai, Zheyi Zhao, Chenyang Wang, F. Richard Yu Published: 2026-01-19 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2601.12925v1 Diffusion strategies have advanced visual motor control by progressively denoising high-dimensional action sequences, providing a promising method for robot manipulation. However, as task complexity increases, the success rate of existing baseline models decreases considerably. Analysis indicates that current diffusion strategies are confronted with two limitations. First, these strategies only rely on short-term observations as conditions. Second, the training objective remains limited to a single denoising loss, which leads to error accumulation and causes grasping deviations. To address these limitations, this paper proposes Foresight-Conditioned Diffusion (ForeDiffusion), by injecting the predicted future view representation into the diffusion process. As a result, the policy is guided to be forward-looking, enabling it to correct trajectory deviations. Following this design, ForeDiffusion employs a dual loss mechanism, combining the traditional denoising loss and the consistency loss of future observations, to achieve the unified optimization. Extensive evaluation on the Adroit suite and the MetaWorld benchmark demonstrates that ForeDiffusion achieves an average success rate of 80% for the overall task, significantly outperforming the existing mainstream diffusion methods by 23% in complex tasks, while maintaining more stable performance across the entire tasks. --- ### Your Privacy Depends on Others: Collusion Vulnerabilities in Individual Differential Privacy Authors: Johannes Kaiser, Alexander Ziller, Eleni Triantafillou, Daniel Rückert, Georgios Kaissis Published: 2026-01-19 Categories: cs.CR, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2601.12922v1 Individual Differential Privacy (iDP) promises users control over their privacy, but this promise can be broken in practice. We reveal a previously overlooked vulnerability in sampling-based iDP mechanisms: while conforming to the iDP guarantees, an individual's privacy risk is not solely governed by their own privacy budget, but critically depends on the privacy choices of all other data contributors. This creates a mismatch between the promise of individual privacy control and the reality of a system where risk is collectively determined. We demonstrate empirically that certain distributions of privacy preferences can unintentionally inflate the privacy risk of individuals, even when their formal guarantees are met. Moreover, this excess risk provides an exploitable attack vector. A central adversary or a set of colluding adversaries can deliberately choose privacy budgets to amplify vulnerabilities of targeted individuals. Most importantly, this attack operates entirely within the guarantees of DP, hiding this excess vulnerability. Our empirical evaluation demonstrates successful attacks against 62% of targeted individuals, substantially increasing their membership inference susceptibility. To mitigate this, we propose $(\varepsilon_i,δ_i,\overlineΔ)$-iDP a privacy contract that uses $Δ$-divergences to provide users with a hard upper bound on their excess vulnerability, while offering flexibility to mechanism design. Our findings expose a fundamental challenge to the current paradigm, demanding a re-evaluation of how iDP systems are designed, audited, communicated, and deployed to make excess risks transparent and controllable. --- ### Injecting Knowledge from Social Science Journals to Improve Indonesian Cultural Understanding by LLMs Authors: Adimulya Kartiyasa, Bao Gia Cao, Boyang Li Published: 2026-01-19 Categories: cs.CL arXiv: https://arxiv.org/abs/2601.12921v1 Recently there have been intensifying efforts to improve the understanding of Indonesian cultures by large language models (LLMs). An attractive source of cultural knowledge that has been largely overlooked is local journals of social science, which likely contain substantial cultural studies from a native perspective. We present a novel text dataset of journal article passages, created from 151 open-source Indonesian social science journals, called IndoSoSci. We demonstrate an effective recipe for injecting Indonesian cultural knowledge therein into LLMs: extracting the facts related to Indonesian culture, and apply retrieval-augmented generation (RAG) with LLM-generated hypothetical documents as queries during retrieval. The proposed recipe yields strong performance gains over several strong baselines on the IndoCulture benchmark. Additionally, by combining IndoSoSci with Indonesian Wikipedia, we set a new state-of-the-art accuracy on the IndoCulture benchmark. --- ### Supervision-by-Hallucination-and-Transfer: A Weakly-Supervised Approach for Robust and Precise Facial Landmark Detection Authors: Jun Wan, Yuanzhi Yao, Zhihui Lai, Jie Zhou, Xianxu Hou, Wenwen Min Published: 2026-01-19 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.12919v1 High-precision facial landmark detection (FLD) relies on high-resolution deep feature representations. However, low-resolution face images or the compression (via pooling or strided convolution) of originally high-resolution images hinder the learning of such features, thereby reducing FLD accuracy. Moreover, insufficient training data and imprecise annotations further degrade performance. To address these challenges, we propose a weakly-supervised framework called Supervision-by-Hallucination-and-Transfer (SHT) for more robust and precise FLD. SHT contains two novel mutually enhanced modules: Dual Hallucination Learning Network (DHLN) and Facial Pose Transfer Network (FPTN). By incorporating FLD and face hallucination tasks, DHLN is able to learn high-resolution representations with low-resolution inputs for recovering both facial structures and local details and generating more effective landmark heatmaps. Then, by transforming faces from one pose to another, FPTN can further improve landmark heatmaps and faces hallucinated by DHLN for detecting more accurate landmarks. To the best of our knowledge, this is the first study to explore weakly-supervised FLD by integrating face hallucination and facial pose transfer tasks. Experimental results of both face hallucination and FLD demonstrate that our method surpasses state-of-the-art techniques. --- ### Dynamic Hand Gesture Recognition for Robot Manipulator Tasks Authors: Dharmendra Sharma, Peeyush Thakur, Sandeep Gupta, Narendra Kumar Dhar, Laxmidhar Behera Published: 2026-01-19 Categories: cs.RO, cs.LG arXiv: https://arxiv.org/abs/2601.12918v1 This paper proposes a novel approach to recognizing dynamic hand gestures facilitating seamless interaction between humans and robots. Here, each robot manipulator task is assigned a specific gesture. There may be several such tasks, hence, several gestures. These gestures may be prone to several dynamic variations. All such variations for different gestures shown to the robot are accurately recognized in real-time using the proposed unsupervised model based on the Gaussian Mixture model. The accuracy during training and real-time testing prove the efficacy of this methodology. --- ### CooperLLM: Cloud-Edge-End Cooperative Federated Fine-tuning for LLMs via ZOO-based Gradient Correction Authors: He Sun, Jinrui Zhou, Li Li, Mingjun Xiao Published: 2026-01-19 Categories: cs.LG, cs.DC arXiv: https://arxiv.org/abs/2601.12917v1 Large Language Models (LLMs) perform well on many NLP tasks, but fine-tuning them on resource-constrained mobile devices is challenging due to high memory and computation costs, despite growing demands for privacy-preserving personalization. Federated Learning (FL) enables local-data training, yet existing methods either rely on memory-intensive backpropagation or use zeroth-order optimization (ZOO), which avoids backward passes but suffers from slow convergence and degraded accuracy. We propose CooperLLM, a cloud-assisted edge-end cooperative federated fine-tuning framework that combines ZOO on mobile devices with cloud-guided gradient rectification. Mobile clients perform lightweight ZOO updates on private data, while the cloud fine-tunes on auxiliary public data using backpropagation and injects guided perturbations to rectify local updates, improving convergence and accuracy without violating privacy. To address system bottlenecks, CooperLLM introduces pipeline scheduling and adaptive compression to overlap computation and communication and reduce memory usage. Experiments on multiple Transformer models and datasets show that CooperLLM reduces on-device memory by up to $86.4\%$, accelerates convergence by $8.8 \times$, and improves accuracy by up to 10 percentage points over state-of-the-art ZOO-based baselines. --- ### Actionable Interpretability Must Be Defined in Terms of Symmetries Authors: Pietro Barbiero, Mateo Espinosa Zarlenga, Francesco Giannini, Alberto Termine, Filippo Bonchi, Mateja Jamnik, Giuseppe Marra Published: 2026-01-19 Categories: cs.AI, cs.LG, cs.NE arXiv: https://arxiv.org/abs/2601.12913v4 This paper argues that interpretability research in Artificial Intelligence (AI) is fundamentally ill-posed as existing definitions of interpretability fail to describe how interpretability can be formally tested or designed for. We posit that actionable definitions of interpretability must be formulated in terms of *symmetries* that inform model design and lead to testable conditions. Under a probabilistic view, we hypothesise that four symmetries (inference equivariance, information invariance, concept-closure invariance, and structural invariance) suffice to (i) formalise interpretable models as a subclass of probabilistic models, (ii) yield a unified formulation of interpretable inference (e.g., alignment, interventions, and counterfactuals) as a form of Bayesian inversion, and (iii) provide a formal framework to verify compliance with safety standards and regulations. --- ### Human Emotion Verification by Action Languages via Answer Set Programming Authors: Andreas Brännström, Juan Carlos Nieves Published: 2026-01-19 Categories: cs.AI arXiv: https://arxiv.org/abs/2601.12912v1 In this paper, we introduce the action language C-MT (Mind Transition Language). It is built on top of answer set programming (ASP) and transition systems to represent how human mental states evolve in response to sequences of observable actions. Drawing on well-established psychological theories, such as the Appraisal Theory of Emotion, we formalize mental states, such as emotions, as multi-dimensional configurations. With the objective to address the need for controlled agent behaviors and to restrict unwanted mental side-effects of actions, we extend the language with a novel causal rule, forbids to cause, along with expressions specialized for mental state dynamics, which enables the modeling of principles for valid transitions between mental states. These principles of mental change are translated into transition constraints, and properties of invariance, which are rigorously evaluated using transition systems in terms of so-called trajectories. This enables controlled reasoning about the dynamic evolution of human mental states. Furthermore, the framework supports the comparison of different dynamics of change by analyzing trajectories that adhere to different psychological principles. We apply the action language to design models for emotion verification. Under consideration in Theory and Practice of Logic Programming (TPLP). --- ### SciCoQA: Quality Assurance for Scientific Paper--Code Alignment Authors: Tim Baumgärtner, Iryna Gurevych Published: 2026-01-19 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2601.12910v3 Discrepancies between scientific papers and their code undermine reproducibility, a concern that grows as automated research agents scale scientific output beyond human review capacity. Whether LLMs can reliably detect such discrepancies has not been systematically measured. To this end, we present SciCoQA, a dataset of 635 paper-code discrepancies (92 real, 543 synthetic) for this cross-modal verification task. Across 22 evaluated models, even the best-performing LLMs, Gemini 3.1 Pro and GPT-5 Mini, detect only 46.7% of real-world discrepancies, revealing a critical gap in automated scientific quality assurance. We construct SciCoQA from GitHub issues and reproducibility papers, and propose a synthetic generation pipeline to scale beyond AI to Physics, Quantitative Biology, and other computational sciences. We further introduce a taxonomy of discrepancy types and categories to characterize the occurring mismatches. Our analysis shows that models particularly struggle with omitted paper details, long-context inputs, and papers outside their pre-training corpus. --- ### Gated Differentiable Working Memory for Long-Context Language Modeling Authors: Lingrui Mei, Shenghua Liu, Yiwei Wang, Yuyao Ge, Baolong Bi, Jiayu Yao, Jun Wan, Ziling Yin, Jiafeng Guo, Xueqi Cheng Published: 2026-01-19 Categories: cs.CL arXiv: https://arxiv.org/abs/2601.12906v1 Long contexts challenge transformers: attention scores dilute across thousands of tokens, critical information is often lost in the middle, and models struggle to adapt to novel patterns at inference time. Recent work on test-time adaptation addresses this by maintaining a form of working memory -- transient parameters updated on the current context -- but existing approaches rely on uniform write policies that waste computation on low-utility regions and suffer from high gradient variance across semantically heterogeneous contexts. In this work, we reframe test-time adaptation as a budget-constrained memory consolidation problem, focusing on which parts of the context should be consolidated into working memory under limited computation. We propose Gdwm (Gated Differentiable Working Memory), a framework that introduces a write controller to gate the consolidation process. The controller estimates Contextual Utility, an information-theoretic measure of long-range contextual dependence, and allocates gradient steps accordingly while maintaining global coverage. Experiments on ZeroSCROLLS and LongBench v2 demonstrate that Gdwm achieves comparable or superior performance with 4$\times$ fewer gradient steps than uniform baselines, establishing a new efficiency-performance Pareto frontier for test-time adaptation. --- ### From Prefix Cache to Fusion RAG Cache: Accelerating LLM Inference in Retrieval-Augmented Generation Authors: Jiahao Wang, Weiyu Xie, Mingxing Zhang, Boxing Zhang, Jianwei Dong, Yuening Zhu, Chen Lin, Jinqi Tang, Yaochen Han, Zhiyuan Ai, Xianglin Chen, Yongwei Wu et al. Published: 2026-01-19 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2601.12904v1 Retrieval-Augmented Generation enhances Large Language Models by integrating external knowledge, which reduces hallucinations but increases prompt length. This increase leads to higher computational costs and longer Time to First Token (TTFT). To mitigate this issue, existing solutions aim to reuse the preprocessed KV cache of each retrieved chunk to accelerate RAG. However, the lack of cross-chunk contextual information leads to a significant drop in generation quality, leaving the potential benefits of KV cache reuse largely unfulfilled. The challenge lies in how to reuse the precomputed KV cache of chunks while preserving generation quality. We propose FusionRAG, a novel inference framework that optimizes both the preprocessing and reprocessing stages of RAG. In the offline preprocessing stage, we embed information from other related text chunks into each chunk, while in the online reprocessing stage, we recompute the KV cache for tokens that the model focuses on. As a result, we achieve a better trade-off between generation quality and efficiency. According to our experiments, FusionRAG significantly improves generation quality at the same recomputation ratio compared to previous state-of-the-art solutions. By recomputing fewer than 15% of the tokens, FusionRAG achieves up to 70% higher normalized F1 scores than baselines and reduces TTFT by 2.66x-9.39x compared to Full Attention. --- ### Deep Temporal Graph Clustering: A Comprehensive Benchmark and Datasets Authors: Meng Liu, Ke Liang, Siwei Wang, Xingchen Hu, Sihang Zhou, Xinwang Liu Published: 2026-01-19 Categories: cs.LG arXiv: https://arxiv.org/abs/2601.12903v1 Temporal Graph Clustering (TGC) is a new task with little attention, focusing on node clustering in temporal graphs. Compared with existing static graph clustering, it can find the balance between time requirement and space requirement (Time-Space Balance) through the interaction sequence-based batch-processing pattern. However, there are two major challenges that hinder the development of TGC, i.e., inapplicable clustering techniques and inapplicable datasets. To address these challenges, we propose a comprehensive benchmark, called BenchTGC. Specially, we design a BenchTGC Framework to illustrate the paradigm of temporal graph clustering and improve existing clustering techniques to fit temporal graphs. In addition, we also discuss problems with public temporal graph datasets and develop multiple datasets suitable for TGC task, called BenchTGC Datasets. According to extensive experiments, we not only verify the advantages of BenchTGC, but also demonstrate the necessity and importance of TGC task. We wish to point out that the dynamically changing and complex scenarios in real world are the foundation of temporal graph clustering. The code and data is available at: https://github.com/MGitHubL/BenchTGC. --- ### Supervised Learning for the (s,S) Inventory Model with General Interarrival Demands and General Lead Times Authors: Eliran Sherzer, Yonit Barron Published: 2026-01-19 Categories: cs.LG arXiv: https://arxiv.org/abs/2601.12900v1 The continuous-review (s,S) inventory model is a cornerstone of stochastic inventory theory, yet its analysis becomes analytically intractable when dealing with non-Markovian systems. In such systems, evaluating long-run performance measures typically relies on costly simulation. This paper proposes a supervised learning framework via a neural network model for approximating stationary performance measures of (s,S) inventory systems with general distributions for the interarrival time between demands and lead times under lost sales. Simulations are first used to generate training labels, after which the neural network is trained. After training, the neural network provides almost instantaneous predictions of various metrics of the system, such as the stationary distribution of inventory levels, the expected cycle time, and the probability of lost sales. We find that using a small number of low-order moments of the distributions as input is sufficient to train the neural networks and to accurately capture the steady-state distribution. Extensive numerical experiments demonstrate high accuracy over a wide range of system parameters. As such, it effectively replaces repeated and costly simulation runs. Our framework is easily extendable to other inventory models, offering an efficient and fast alternative for analyzing complex stochastic systems. --- ### TwoHead-SwinFPN: A Unified DL Architecture for Synthetic Manipulation, Detection and Localization in Identity Documents Authors: Chan Naseeb, Adeel Ashraf Cheema, Hassan Sami, Tayyab Afzal, Muhammad Omair, Usman Habib Published: 2026-01-19 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2601.12895v1 The proliferation of sophisticated generative AI models has significantly escalated the threat of synthetic manipulations in identity documents, particularly through face swapping and text inpainting attacks. This paper presents TwoHead-SwinFPN, a unified deep learning architecture that simultaneously performs binary classification and precise localization of manipulated regions in ID documents. Our approach integrates a Swin Transformer backbone with Feature Pyramid Network (FPN) and UNet-style decoder, enhanced with Convolutional Block Attention Module (CBAM) for improved feature representation. The model employs a dual-head architecture for joint optimization of detection and segmentation tasks, utilizing uncertainty-weighted multi-task learning. Extensive experiments on the FantasyIDiap dataset demonstrate superior performance with 84.31\% accuracy, 90.78\% AUC for classification, and 57.24\% mean Dice score for localization. The proposed method achieves an F1-score of 88.61\% for binary classification while maintaining computational efficiency suitable for real-world deployment through FastAPI implementation. Our comprehensive evaluation includes ablation studies, cross-device generalization analysis, and detailed performance assessment across 10 languages and 3 acquisition devices. --- ### Sparse ActionGen: Accelerating Diffusion Policy with Real-time Pruning Authors: Kangye Ji, Jianbo Zhou, Yuan Meng, Ye Li, Hanyun Cui, Zhi Wang Published: 2026-01-19 Categories: cs.RO, cs.CV arXiv: https://arxiv.org/abs/2601.12894v2 Diffusion Policy has dominated action generation due to its strong capabilities for modeling multi-modal action distributions, but its multi-step denoising processes make it impractical for real-time visuomotor control. Existing caching-based acceleration methods typically rely on $\textit{static}$ schedules that fail to adapt to the $\textit{dynamics}$ of robot-environment interactions, thereby leading to suboptimal performance. In this paper, we propose $\underline{\textbf{S}}$parse $\underline{\textbf{A}}$ction$\underline{\textbf{G}}$en ($\textbf{SAG}$) for extremely sparse action generation. To accommodate the iterative interactions, SAG customizes a rollout-adaptive prune-then-reuse mechanism that first identifies prunable computations globally and then reuses cached activations to substitute them during action diffusion. To capture the rollout dynamics, SAG parameterizes an observation-conditioned diffusion pruner for environment-aware adaptation and instantiates it with a highly parameter- and inference-efficient design for real-time prediction. Furthermore, SAG introduces a one-for-all reusing strategy that reuses activations across both timesteps and blocks in a zig-zag manner, minimizing the global redundancy. Extensive experiments on multiple robotic benchmarks demonstrate that SAG achieves up to 4$\times$ generation speedup without sacrificing performance. Project Page: https://sparse-actiongen.github.io. --- ### AdaNODEs: Test Time Adaptation for Time Series Forecasting Using Neural ODEs Authors: Ting Dang, Soumyajit Chatterjee, Hong Jia, Yu Wu, Flora Salim, Fahim Kawsar Published: 2026-01-19 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2601.12893v1 Test time adaptation (TTA) has emerged as a promising solution to adapt pre-trained models to new, unseen data distributions using unlabeled target domain data. However, most TTA methods are designed for independent data, often overlooking the time series data and rarely addressing forecasting tasks. This paper presents AdaNODEs, an innovative source-free TTA method tailored explicitly for time series forecasting. By leveraging Neural Ordinary Differential Equations (NODEs), we propose a novel adaptation framework that accommodates the unique characteristics of distribution shifts in time series data. Moreover, we innovatively propose a new loss function to tackle TTA for forecasting tasks. AdaNODEs only requires updating limited model parameters, showing effectiveness in capturing temporal dependencies while avoiding significant memory usage. Extensive experiments with one- and high-dimensional data demonstrate that AdaNODEs offer relative improvements of 5.88\% and 28.4\% over the SOTA baselines, especially demonstrating robustness across higher severity distribution shifts. --- ### Simultaneous Detection of LSD and FMD in Cattle Using Ensemble Deep Learning Authors: Nazibul Basar Ayon, Abdul Hasib, Md. Faishal Ahmed, Md. Sadiqur Rahman, Kamrul Islam, T. M. Mehrab Hasan, A. S. M. Ahsanul Sarkar Akib Published: 2026-01-19 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.12889v1 Lumpy Skin Disease (LSD) and Foot-and-Mouth Disease (FMD) are highly contagious viral diseases affecting cattle, causing significant economic losses and welfare challenges. Their visual diagnosis is complicated by significant symptom overlap with each other and with benign conditions like insect bites or chemical burns, hindering timely control measures. Leveraging a comprehensive dataset of 10,516 expert-annotated images from 18 farms across India, Brazil, and the USA, this study presents a novel Ensemble Deep Learning framework integrating VGG16, ResNet50, and InceptionV3 with optimized weighted averaging for simultaneous LSD and FMD detection. The model achieves a state-of-the-art accuracy of 98.2\%, with macro-averaged precision of 98.2\%, recall of 98.1\%, F1-score of 98.1\%, and an AUC-ROC of 99.5\%. This approach uniquely addresses the critical challenge of symptom overlap in multi-disease detection, enabling early, precise, and automated diagnosis. This tool has the potential to enhance disease management, support global agricultural sustainability, and is designed for future deployment in resource-limited settings. --- ### Communication Methods in Multi-Agent Reinforcement Learning Authors: Christoph Wittner Published: 2026-01-19 Categories: cs.MA, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2601.12886v1 Multi-agent reinforcement learning is a promising research area that extends established reinforcement learning approaches to problems formulated as multi-agent systems. Recently, a multitude of communication methods have been introduced to this field to address problems such as partially observable environments, non-stationarity, and exponentially growing action spaces. Communication further enables efficient cooperation among all agents interacting in an environment. This work aims at providing an overview of communication techniques in multi-agent reinforcement learning. By an in-depth analysis of 29 publications on this topic, the strengths and weaknesses of explicit, implicit, attention-based, graph-based, and hierarchical/role-based communication are evaluated. The results of this comparison show that there is no general, optimal communication framework for every problem. On the contrary, the choice of communication depends heavily on the problem at hand. The comparison also highlights the importance of communication methods with low computational overhead to enable scalability to environments where many agents interact. Finally, the paper discusses current research gaps, emphasizing the need for standardized benchmarking of system-level metrics and improved robustness under realistic communication conditions to enhance the real-world applicability of these approaches. --- ### YOLO26: An Analysis of NMS-Free End to End Framework for Real-Time Object Detection Authors: Sudip Chakrabarty Published: 2026-01-19 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2601.12882v2 The ``You Only Look Once'' (YOLO) framework has long served as a standard for real-time object detection, though traditional iterations have utilized Non-Maximum Suppression (NMS) post-processing, which introduces specific latency and hyperparameter variables. This paper presents a comprehensive architectural analysis of YOLO26, a model that shifts toward a native end-to-end learning strategy by eliminating NMS. This study examines the core mechanisms driving this framework: the MuSGD optimizer for backbone stabilization, Small-Target-Aware Label Assignment (STAL), and ProgLoss for dynamic supervision. To contextualize its performance, this article reviews exhaustive benchmark data from the COCO \texttt{val2017} leaderboard. This evaluation provides an objective comparison of YOLO26 across various model scales (Nano to Extra-Large) against both prior CNN lineages and contemporary Transformer-based architectures (e.g., RT-DETR, DEIM, RF-DETR), detailing the observed speed-accuracy trade-offs and parameter requirements without asserting a singular optimal model. Additionally, the analysis covers the framework's unified multi-task capabilities, including the YOLOE-26 open-vocabulary module for promptable detection. Ultimately, this paper serves to document how decoupling representation learning from heuristic post-processing impacts the "Export Gap" and deterministic latency in modern edge-based computer vision deployments. --- ### Hierarchical Sparse Circuit Extraction from Billion-Parameter Language Models through Scalable Attribution Graph Decomposition Authors: Mohammed Mudassir Uddin, Shahnawaz Alam, Mohammed Kaif Pasha Published: 2026-01-19 Categories: cs.LG, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2601.12879v2 Extracting sparse circuits from billion-parameter transformers is constrained by $O(2^n)$ search cost and pervasive feature reuse across co-active pathways. Hierarchical Attribution Graph Decomposition (HAGD) addresses this through four stages: cross-layer transcoder training, spectral coarsening of attribution graphs, graph-neural-network (GNN)-guided hierarchical traversal, and causal intervention verification, reducing worst-case complexity to $O(n^2 \log n)$. Per-layer transcoders trained on the RedPajama corpus yield monosemantic dictionaries; gradient-activation products form weighted attribution graphs; normalized-Laplacian spectral clustering builds multi-resolution hierarchies; an attention-based GNN assigns circuit-membership scores at successive coarsening stages. Evaluation spans GPT-2 (117M-774M), Pythia (1.4B-6.9B), and Llama (7B-70B) across modular arithmetic, parity computation, integer sorting, coreference resolution (WinoGrande), commonsense reasoning (HellaSwag), and factual recall. Behavioral preservation reaches 91\% ($\pm$2.3\%) on modular arithmetic with 49-347-node circuits, while ACDC exhausts memory beyond 1.4B parameters. Cross-architecture transfer coefficients span 0.38-0.82, with within-family pairs (Llama-7B $\to$ Llama-70B) attaining 0.82. Limitations include omitted attention-head circuits, 15-20\% unexplained reconstruction variance, ablation-based validation circularity, and uncertain interpretability of circuits exceeding several hundred nodes. --- ### Exploring Talking Head Models With Adjacent Frame Prior for Speech-Preserving Facial Expression Manipulation Authors: Zhenxuan Lu, Zhihua Xu, Zhijing Yang, Feng Gao, Yongyi Lu, Keze Wang, Tianshui Chen Published: 2026-01-19 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.12876v1 Speech-Preserving Facial Expression Manipulation (SPFEM) is an innovative technique aimed at altering facial expressions in images and videos while retaining the original mouth movements. Despite advancements, SPFEM still struggles with accurate lip synchronization due to the complex interplay between facial expressions and mouth shapes. Capitalizing on the advanced capabilities of audio-driven talking head generation (AD-THG) models in synthesizing precise lip movements, our research introduces a novel integration of these models with SPFEM. We present a new framework, Talking Head Facial Expression Manipulation (THFEM), which utilizes AD-THG models to generate frames with accurately synchronized lip movements from audio inputs and SPFEM-altered images. However, increasing the number of frames generated by AD-THG models tends to compromise the realism and expression fidelity of the images. To counter this, we develop an adjacent frame learning strategy that finetunes AD-THG models to predict sequences of consecutive frames. This strategy enables the models to incorporate information from neighboring frames, significantly improving image quality during testing. Our extensive experimental evaluations demonstrate that this framework effectively preserves mouth shapes during expression manipulations, highlighting the substantial benefits of integrating AD-THG with SPFEM. --- ### Tracing the Latent Threads: A Mechanistic Study of How LLMs Represent and Operationalize Race and Ethnicity Cues Authors: Shiyue Hu, Ruizhe Li, Yanjun Gao Published: 2026-01-19 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2601.12868v2 Large language models (LLMs) increasingly operate in high-stakes settings where demographic attributes such as race and ethnicity may be explicitly stated or implicitly suggested through textual cues. However, existing studies primarily document outcome-level disparities, offering limited insight into internal mechanisms underlying these effects. We present a mechanistic study of how race and ethnicity cues are represented and operationalized within LLMs. Using two publicly available datasets spanning toxicity-related generation and clinical narrative understanding tasks, we analyze three open-source models with a reproducible interpretability pipeline combining probing, neuron-level attribution, and targeted intervention. We find that sensitivity to demographic cues is distributed across internal units and varies substantially across models. These units often align with entangled semantic facets, including explicit group labels, geography, language, culture, and associations related to stereotypes. Interventions on selected units can change some biased prediction patterns, but substantial residual effects remain, suggesting that effective mitigation requires understanding distributed, task-specific mechanisms rather than manipulating a small set of identified neurons alone. Code: https://github.com/LARK-NLP-Lab/LLM-Bias-Interpretability. --- ### PDFInspect: A Unified Feature Extraction Framework for Malicious Document Detection Authors: Sharmila S P Published: 2026-01-19 Categories: cs.CR, cs.LG arXiv: https://arxiv.org/abs/2601.12866v1 The increasing prevalence of malicious Portable Document Format (PDF) files necessitates robust and comprehensive feature extraction techniques for effective detection and analysis. This work presents a unified framework that integrates graph-based, structural, and metadata-driven analysis to generate a rich feature representation for each PDF document. The system extracts text from PDF pages and constructs undirected graphs based on pairwise word relationships, enabling the computation of graph-theoretic features such as node count, edge density, and clustering coefficient. Simultaneously, the framework parses embedded metadata to quantify character distributions, entropy patterns, and inconsistencies across fields such as author, title, and producer. Temporal features are derived from creation and modification timestamps to capture behavioral signatures, while structural elements including, object streams, fonts, and embedded images, are quantified to reflect document complexity. Boolean flags for potentially malicious PDF constructs (e.g., JavaScript, launch actions) are also extracted. Together, these features form a high-dimensional vector representation (170 dimensions) that is well-suited for downstream tasks such as malware classification, anomaly detection, and forensic analysis. The proposed approach is scalable, extensible, and designed to support real-world PDF threat intelligence workflows.6 --- ### Proxy Robustness in Vision Language Models is Effortlessly Transferable Authors: Xiaowei Fu, Fuxiang Huang, Lei Zhang Published: 2026-01-19 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.12865v1 As a pivotal technique for improving the defense of deep models, adversarial robustness transfer via distillation has demonstrated remarkable success in conventional image classification tasks. However, this paradigm encounters critical challenges when applied to vision-language models (VLM) (e.g., CLIP): constructing adversarially robust teacher for large-scale multi-modal models demands prohibitively high computational resources. We bridge this gap by revealing an interesting phenomenon: vanilla CLIP (without adversarial training) exhibits intrinsic defensive capabilities against adversarial examples generated by another CLIP with different architectures. We formally define this as proxy adversarial robustness, and naturally propose a Heterogeneous Proxy Transfer (HPT) framework that establishes cross-architectural robustness distillation channels between CLIP variants, effortlessly enabling the VLM robustness transfer from proxy to target models. Yet, such proxy transfer paradigm easily induces severe overfitting, leading to a sharp degradation in zero-shot natural generalization. To resolve that, we design Generalization-Pivot Decoupling (GPD) by leveraging the difference in learning rate scheduling. This decouples the proxy transfer process into a generalization-anchored warm-up that maintains generalization and a generalization-pulled HPT that promotes adversarial robustness, to achieve an equilibrium between natural generalization and adversarial robustness. Extensive experiments on 15 zero-shot datasets demonstrate the effectiveness of our HPT-GPD method. The code is available at the website of github.com/fxw13/HPT-GPD. --- ### FGTBT: Frequency-Guided Task-Balancing Transformer for Unified Facial Landmark Detection Authors: Jun Wan, Xinyu Xiong, Ning Chen, Zhihui Lai, Jie Zhou, Wenwen Min Published: 2026-01-19 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.12863v1 Recently, deep learning based facial landmark detection (FLD) methods have achieved considerable success. However, in challenging scenarios such as large pose variations, illumination changes, and facial expression variations, they still struggle to accurately capture the geometric structure of the face, resulting in performance degradation. Moreover, the limited size and diversity of existing FLD datasets hinder robust model training, leading to reduced detection accuracy. To address these challenges, we propose a Frequency-Guided Task-Balancing Transformer (FGTBT), which enhances facial structure perception through frequency-domain modeling and multi-dataset unified training. Specifically, we propose a novel Fine-Grained Multi-Task Balancing loss (FMB-loss), which moves beyond coarse task-level balancing by assigning weights to individual landmarks based on their occurrence across datasets. This enables more effective unified training and mitigates the issue of inconsistent gradient magnitudes. Additionally, a Frequency-Guided Structure-Aware (FGSA) model is designed to utilize frequency-guided structure injection and regularization to help learn facial structure constraints. Extensive experimental results on popular benchmark datasets demonstrate that the integration of the proposed FMB-loss and FGSA model into our FGTBT framework achieves performance comparable to state-of-the-art methods. The code is available at https://github.com/Xi0ngxinyu/FGTBT. --- ### Generating Cyclic Conformers with Flow Matching in Cremer-Pople Coordinates Authors: Luca Schaufelberger, Aline Hartgers, Kjell Jorner Published: 2026-01-19 Categories: cs.LG, physics.chem-ph arXiv: https://arxiv.org/abs/2601.12859v1 Cyclic molecules are ubiquitous across applications in chemistry and biology. Their restricted conformational flexibility provides structural pre-organization that is key to their function in drug discovery and catalysis. However, reliably sampling the conformer ensembles of ring systems remains challenging. Here, we introduce PuckerFlow, a generative machine learning model that performs flow matching on the Cremer-Pople space, a low-dimensional internal coordinate system capturing the relevant degrees of freedom of rings. Our approach enables generation of valid closed rings by design and demonstrates strong performance in generating conformers that are both diverse and precise. We show that PuckerFlow outperforms other conformer generation methods on nearly all quantitative metrics and illustrate the potential of PuckerFlow for ring systems relevant to chemical applications, particularly in catalysis and drug discovery. This work enables efficient and reliable conformer generation of cyclic structures, paving the way towards modeling structure-property relationships and the property-guided generation of rings across a wide range of applications in chemistry and biology. --- ### Mining Citywide Dengue Spread Patterns in Singapore Through Hotspot Dynamics from Open Web Data Authors: Liping Huang, Gaoxi Xiao, Stefan Ma, Hechang Chen, Shisong Tang, Flora Salim Published: 2026-01-19 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2601.12856v2 Dengue, a mosquito-borne disease, continues to pose a persistent public health challenge in urban areas, particularly in tropical regions such as Singapore. Effective and affordable control requires anticipating where transmission risks are likely to emerge so that interventions can be deployed proactively rather than reactively. This study introduces a novel framework that uncovers and exploits latent transmission links between urban regions, mined directly from publicly available dengue case data. Instead of treating cases as isolated reports, we model how hotspot formation in one area is influenced by epidemic dynamics in neighboring regions. While mosquito movement is highly localized, long-distance transmission is often driven by human mobility, and in our case study, the learned network aligns closely with commuting flows, providing an interpretable explanation for citywide spread. These hidden links are optimized through gradient descent and used not only to forecast hotspot status but also to verify the consistency of spreading patterns, by examining the stability of the inferred network across consecutive weeks. Case studies on Singapore during 2013-2018 and 2020 show that four weeks of hotspot history are sufficient to achieve an average F-score of 0.79. Importantly, the learned transmission links align with commuting flows, highlighting the interpretable interplay between hidden epidemic spread and human mobility. By shifting from simply reporting dengue cases to mining and validating hidden spreading dynamics, this work transforms open web-based case data into a predictive and explanatory resource. The proposed framework advances epidemic modeling while providing a scalable, low-cost tool for public health planning, early intervention, and urban resilience. --- ### Accurate Simulation Pipeline for Passive Single-Photon Imaging Authors: Aleksi Suonsivu, Lauri Salmela, Leevi Uosukainen, Edoardo Peretti, Radu Ciprian Bilcu, Giacomo Boracchi Published: 2026-01-19 Categories: physics.ins-det, cs.CV arXiv: https://arxiv.org/abs/2601.12850v1 Single-Photon Avalanche Diodes (SPADs) are new and promising imaging sensors. These sensors are sensitive enough to detect individual photons hitting each pixel, with extreme temporal resolution and without readout noise. Thus, SPADs stand out as an optimal choice for low-light imaging. Due to the high price and limited availability of SPAD sensors, the demand for an accurate data simulation pipeline is substantial. Indeed, the scarcity of SPAD datasets hinders the development of SPAD-specific processing algorithms and impedes the training of learning-based solutions. In this paper, we present a comprehensive SPAD simulation pipeline and validate it with multiple experiments using two recent commercial SPAD sensors. Our simulator is used to generate the SPAD-MNIST, a single-photon version of the seminal MNIST dataset, to investigate the effectiveness of convolutional neural network (CNN) classifiers on reconstructed fluxes, even at extremely low light conditions, e.g., 5 mlux. We also assess the performance of classifiers exclusively trained on simulated data on real images acquired from SPAD sensors at different light conditions. The synthetic dataset encompasses different SPAD imaging modalities and is made available for download. Project page: https://boracchi.faculty.polimi.it/Projects/SPAD-MNIST.html. --- ### The Cost of EFX: Generalized-Mean Welfare and Complexity Dichotomies with Few Surplus Items Authors: Eugene Lim, Tzeh Yuan Neoh, Nicholas Teh Published: 2026-01-19 Categories: cs.GT, cs.AI, cs.MA, econ.TH arXiv: https://arxiv.org/abs/2601.12849v1 Envy-freeness up to any good (EFX) is a central fairness notion for allocating indivisible goods, yet its existence is unresolved in general. In the setting with few surplus items, where the number of goods exceeds the number of agents by a small constant (at most three), EFX allocations are guaranteed to exist, shifting the focus from existence to efficiency and computation. We study how EFX interacts with generalized-mean ($p$-mean) welfare, which subsumes commonly-studied utilitarian ($p=1$), Nash ($p=0$), and egalitarian ($p \rightarrow -\infty$) objectives. We establish sharp complexity dichotomies at $p=0$: for any fixed $p \in (0,1)$, both deciding whether EFX can attain the global $p$-mean optimum and computing an EFX allocation maximizing $p$-mean welfare are NP-hard, even with at most three surplus goods; in contrast, for any fixed $p \leq 0$, we give polynomial-time algorithms that optimize $p$-mean welfare within the space of EFX allocations and efficiently certify when EFX attains the global optimum. We further quantify the welfare loss of enforcing EFX via the price of fairness framework, showing that for $p > 0$, the loss can grow linearly with the number of agents, whereas for $p \leq 0$, it is bounded by a constant depending on the surplus (and for Nash welfare it vanishes asymptotically). Finally we show that requiring Pareto-optimality alongside EFX is NP-hard (and becomes $Σ_2^P$-complete for a stronger variant of EFX). Overall, our results delineate when EFX is computationally costly versus structurally aligned with welfare maximization in the setting with few surplus items. --- ### Rapport du Projet de Recherche TRAIMA Authors: Julie Rançon, Jean-François Cerisier, Emilie Remond, Aurélien Nguyen, Andrew Peterson, Ladjel Bellatreche Published: 2026-01-19 Categories: cs.CL arXiv: https://arxiv.org/abs/2601.12844v1 The TRAIMA project (TRaitement Automatique des Interactions Multimodales en Apprentissage), conducted between March 2019 and June 2020, investigates the potential of automatic processing of multimodal interactions in educational settings. The project addresses a central methodological challenge in educational and interactional research: the analysis of verbal, paraverbal, and non-verbal data is currently carried out manually, making it extremely time-consuming and difficult to scale. TRAIMA explores how machine learning approaches could contribute to the categorisation and classification of such interactions. The project focuses specifically on explanatory and collaborative sequences occurring in classroom interactions, particularly in French as a Foreign Language (FLE) and French as a First Language (FLM) contexts. These sequences are analysed as inherently multimodal phenomena, combining spoken language with prosody, gestures, posture, gaze, and spatial positioning. A key theoretical contribution of the project is the precise linguistic and interactional definition of explanatory discourse as a tripartite sequence (opening, explanatory core, closure), drawing on discourse analysis and interactional linguistics. A substantial part of the research is devoted to the methodological foundations of transcription, which constitute a critical bottleneck for any form of automation. The report provides a detailed state of the art of existing transcription conventions (ICOR, Mondada, GARS, VALIBEL, Ferr{é}), highlighting their respective strengths and limitations when applied to multimodal classroom data. Through comparative analyses of manually transcribed sequences, the project demonstrates the inevitable variability and interpretative dimension of transcription practices, depending on theoretical positioning and analytical goals. Empirical work is based on several corpora, notably the INTER-EXPLIC corpus (approximately 30 hours of classroom interaction) and the EXPLIC-LE… --- ### SCULPT: Constraint-Guided Pruned MCTS that Carves Efficient Paths for Mathematical Reasoning Authors: Qitong Fang, Haotian Li, Xu Wang Published: 2026-01-19 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2601.12842v1 Automated agent workflows can enhance the problem-solving ability of large language models (LLMs), but common search strategies rely on stochastic exploration and often traverse implausible branches. This occurs because current pipelines sample candidate steps from generic prompts or learned policies with weak domain priors, yielding near-random walks over operators, units, and formats. To promote ordered exploration, this paper introduces SCULPT, a constraint-guided approach for Monte Carlo Tree Search (MCTS) that integrates domain-aware scoring into selection, expansion, simulation, and backpropagation. SCULPT scores and prunes actions using a combination of symbolic checks (dimensional consistency, type compatibility, magnitude sanity, depth control, and diversity) and structural pattern guidance, thereby steering the search toward plausible reasoning paths. Under matched LLM configurations, SCULPT yields stable improvements on multiple datasets; additional results with GPT-5.2 assess executor transferability and performance on frontier reasoning models. Overall, domain-aware constraints can improve accuracy while maintaining efficiency and reasoning stability. --- ### Knowledge-Integrated Representation Learning for Crypto Anomaly Detection under Extreme Label Scarcity; Relational Domain-Logic Integration with Retrieval-Grounded Context and Path-Level Explanations Authors: Gyuyeon Na, Minjung Park, Soyoun Kim, Jungbin Shin, Sangmi Chai Published: 2026-01-19 Categories: cs.LG, q-fin.RM arXiv: https://arxiv.org/abs/2601.12839v1 Detecting anomalous trajectories in decentralized crypto networks is fundamentally challenged by extreme label scarcity and the adaptive evasion strategies of illicit actors. While Graph Neural Networks (GNNs) effectively capture local structural patterns, they struggle to internalize multi hop, logic driven motifs such as fund dispersal and layering that characterize sophisticated money laundering, limiting their forensic accountability under regulations like the FATF Travel Rule. To address this limitation, we propose Relational Domain Logic Integration (RDLI), a framework that embeds expert derived heuristics as differentiable, logic aware latent signals within representation learning. Unlike static rule based approaches, RDLI enables the detection of complex transactional flows that evade standard message passing. To further account for market volatility, we incorporate a Retrieval Grounded Context (RGC) module that conditions anomaly scoring on regulatory and macroeconomic context, mitigating false positives caused by benign regime shifts. Under extreme label scarcity (0.01%), RDLI outperforms state of the art GNN baselines by 28.9% in F1 score. A micro expert user study further confirms that RDLI path level explanations significantly improve trustworthiness, perceived usefulness, and clarity compared to existing methods, highlighting the importance of integrating domain logic with contextual grounding for both accuracy and explainability. --- ### Cognition spaces: natural, artificial, and hybrid Authors: Ricard Solé, Luis F Seoane, Jordi Pla-Mauri, Michael Timothy Bennett, Michael E. Hochberg, Michael Levin Published: 2026-01-19 Categories: q-bio.NC, cs.AI, cs.HC, cs.NE arXiv: https://arxiv.org/abs/2601.12837v1 Cognitive processes are realized across an extraordinary range of natural, artificial, and hybrid systems, yet there is no unified framework for comparing their forms, limits, and unrealized possibilities. Here, we propose a cognition space approach that replaces narrow, substrate-dependent definitions with a comparative representation based on organizational and informational dimensions. Within this framework, cognition is treated as a graded capacity to sense, process, and act upon information, allowing systems as diverse as cells, brains, artificial agents, and human-AI collectives to be analyzed within a common conceptual landscape. We introduce and examine three cognition spaces -- basal aneural, neural, and human-AI hybrid -- and show that their occupation is highly uneven, with clusters of realized systems separated by large unoccupied regions. We argue that these voids are not accidental but reflect evolutionary contingencies, physical constraints, and design limitations. By focusing on the structure of cognition spaces rather than on categorical definitions, this approach clarifies the diversity of existing cognitive systems and highlights hybrid cognition as a promising frontier for exploring novel forms of complexity beyond those produced by biological evolution. --- ### Data-Consistent Learning of Inverse Problems Authors: Markus Haltmeier, Gyeongha Hwang Published: 2026-01-19 Categories: math.NA, cs.CV arXiv: https://arxiv.org/abs/2601.12831v1 Inverse problems are inherently ill-posed, suffering from non-uniqueness and instability. Classical regularization methods provide mathematically well-founded solutions, ensuring stability and convergence, but often at the cost of reduced flexibility or visual quality. Learned reconstruction methods, such as convolutional neural networks, can produce visually compelling results, yet they typically lack rigorous theoretical guarantees. DC (DC) networks address this gap by enforcing the measurement model within the network architecture. In particular, null-space networks combined with a classical regularization method as an initial reconstruction define a convergent regularization method. This approach preserves the theoretical reliability of classical schemes while leveraging the expressive power of data-driven learning, yielding reconstructions that are both accurate and visually appealing. --- ### Seeing Isn't Always Believing: Analysis of Grad-CAM Faithfulness and Localization Reliability in Lung Cancer CT Classification Authors: Teerapong Panboonyuen Published: 2026-01-19 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.12826v1 Explainable Artificial Intelligence (XAI) techniques, such as Gradient-weighted Class Activation Mapping (Grad-CAM), have become indispensable for visualizing the reasoning process of deep neural networks in medical image analysis. Despite their popularity, the faithfulness and reliability of these heatmap-based explanations remain under scrutiny. This study critically investigates whether Grad-CAM truly represents the internal decision-making of deep models trained for lung cancer image classification. Using the publicly available IQ-OTH/NCCD dataset, we evaluate five representative architectures: ResNet-50, ResNet-101, DenseNet-161, EfficientNet-B0, and ViT-Base-Patch16-224, to explore model-dependent variations in Grad-CAM interpretability. We introduce a quantitative evaluation framework that combines localization accuracy, perturbation-based faithfulness, and explanation consistency to assess Grad-CAM reliability across architectures. Experimental findings reveal that while Grad-CAM effectively highlights salient tumor regions in most convolutional networks, its interpretive fidelity significantly degrades for Vision Transformer models due to non-local attention behavior. Furthermore, cross-model comparisons indicate substantial variability in saliency localization, implying that Grad-CAM explanations may not always correspond to the true diagnostic evidence used by the networks. This work exposes critical limitations of current saliency-based XAI approaches in medical imaging and emphasizes the need for model-aware interpretability methods that are both computationally sound and clinically meaningful. Our findings aim to inspire a more cautious and rigorous adoption of visual explanation tools in medical AI, urging the community to rethink what it truly means to "trust" a model's explanation. --- ### TreeDGS: Aerial Gaussian Splatting for Distant DBH Measurement Authors: Belal Shaheen, Minh-Hieu Nguyen, Bach-Thuan Bui, Shubham, Tim Wu, Michael Fairley, Matthew David Zane, Michael Wu, James Tompkin Published: 2026-01-19 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.12823v3 Aerial remote sensing efficiently surveys large areas, but accurate direct object-level measurement remains difficult in complex natural scenes. Advancements in 3D computer vision, particularly radiance field representations such as NeRF and 3D Gaussian splatting, can improve reconstruction fidelity from posed imagery. Nevertheless, direct aerial measurement of important attributes like tree diameter at breast height (DBH) remains challenging. Trunks in aerial forest scans are distant and sparsely observed in image views; at typical operating altitudes, stems may span only a few pixels. With these constraints, conventional reconstruction methods have inaccurate breast-height trunk geometry. TreeDGS is an aerial image reconstruction method that uses 3D Gaussian splatting as a continuous scene representation for trunk measurement. After SfM--MVS initialization and Gaussian optimization, we extract a dense point set from the Gaussian field using RaDe-GS's depth-aware cumulative-opacity integration and associate each sample with a multi-view opacity reliability score. Then, we isolate trunk points and estimate DBH using opacity-weighted solid-circle fitting. Evaluated on 10 plots with field-measured DBH, TreeDGS reaches 4.79 cm RMSE (about 2.6 pixels at this GSD) and outperforms a LiDAR baseline (7.66 cm RMSE). This shows that TreeDGS can enable accurate, low-cost aerial DBH measurement . --- ### MirrorGuard: Toward Secure Computer-Use Agents via Simulation-to-Real Reasoning Correction Authors: Wenqi Zhang, Yulin Shen, Changyue Jiang, Jiarun Dai, Geng Hong, Xudong Pan Published: 2026-01-19 Categories: cs.AI arXiv: https://arxiv.org/abs/2601.12822v1 Large foundation models are integrated into Computer Use Agents (CUAs), enabling autonomous interaction with operating systems through graphical user interfaces (GUIs) to perform complex tasks. This autonomy introduces serious security risks: malicious instructions or visual prompt injections can trigger unsafe reasoning and cause harmful system-level actions. Existing defenses, such as detection-based blocking, prevent damage but often abort tasks prematurely, reducing agent utility. In this paper, we present MirrorGuard, a plug-and-play defense framework that uses simulation-based training to improve CUA security in the real world. To reduce the cost of large-scale training in operating systems, we propose a novel neural-symbolic simulation pipeline, which generates realistic, high-risk GUI interaction trajectories entirely in a text-based simulated environment, which captures unsafe reasoning patterns and potential system hazards without executing real operations. In the simulation environment, MirrorGuard learns to intercept and rectify insecure reasoning chains of CUAs before they produce and execute unsafe actions. In real-world testing, extensive evaluations across diverse benchmarks and CUA architectures show that MirrorGuard significantly mitigates security risks. For instance, on the ByteDance UI-TARS system, it reduces the unsafe rate from 66.5% to 13.0% while maintaining a marginal false refusal rate (FRR). In contrast, the state-of-the-art GuardAgent only achieves a reduction to 53.9% and suffers from a 15.4% higher FRR. Our work proves that simulation-derived defenses can provide robust, real-world protection while maintaining the fundamental utility of the agent. Our code and model are publicly available at https://bmz-q-q.github.io/MirrorGuard/. --- ### A Generalist Foundation Model for Total-body PET/CT Enables Diagnostic Reporting and System-wide Metabolic Profiling Authors: Wei Chen, Liang Wu, Shuyi Lu, Yuanyuan Sun, Wenkai Bi, Zilong Yuan, Yaoyao He, Feng Wang, Junchi Ma, Shuyong Liu, Zhaoping Cheng, Xiaoyan Hu et al. Published: 2026-01-19 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.12820v1 Total-body PET/CT enables system-wide molecular imaging, but heterogeneous anatomical and metabolic signals, approximately 2 m axial coverage, and structured radiology semantics challenge existing medical AI models that assume single-modality inputs, localized fields of view, and coarse image-text alignment. We introduce SDF-HOLO (Systemic Dual-stream Fusion Holo Model), a multimodal foundation model for holistic total-body PET/CT, pre-trained on more than 10,000 patients. SDF-HOLO decouples CT and PET representation learning with dual-stream encoders and couples them through a cross-modal interaction module, allowing anatomical context to refine PET aggregation while metabolic saliency guides subtle morphological reasoning. To model long-range dependencies across the body, hierarchical context modeling combines efficient local windows with global attention. To bridge voxels and clinical language, we use anatomical segmentation masks as explicit semantic anchors and perform voxel-mask-text alignment during pre-training. Across tumor segmentation, low-dose lesion detection, and multilingual diagnostic report generation, SDF-HOLO outperforms strong task-specific and clinical-reference baselines while reducing localization errors and hallucinated findings. Beyond focal interpretation, the model enables system-wide metabolic profiling and reveals tumor-associated fingerprints of inter-organ metabolic network interactions, providing a scalable computational foundation for total-body PET/CT diagnostics and system-level precision oncology. --- ### Fisher-Orthogonal Projected Natural Gradient Descent for Continual Learning Authors: Ishir Garg, Neel Kolhe, Andy Peng, Rohan Gopalam Published: 2026-01-19 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2601.12816v2 Continual learning aims to enable neural networks to acquire new knowledge on sequential tasks. However, the key challenge in such settings is to learn new tasks without catastrophically forgetting previously learned tasks. We propose the Fisher-Orthogonal Projected Natural Gradient Descent (FOPNG) optimizer, which enforces Fisher-orthogonal constraints on parameter updates to preserve old task performance while learning new tasks. Unlike existing methods that operate in Euclidean parameter space, FOPNG projects gradients onto the Fisher-orthogonal complement of previous task gradients. This approach unifies natural gradient descent with orthogonal gradient methods within an information-geometric framework. We provide theoretical analysis deriving the projected update, describe efficient and practical implementations using the diagonal Fisher, and demonstrate strong results on standard continual learning benchmarks such as Permuted-MNIST, Split-MNIST, Rotated-MNIST, Split-CIFAR10, and Split-CIFAR100. Our code is available at https://github.com/ishirgarg/FOPNG. --- ### Multimodal Multi-Agent Empowered Legal Judgment Prediction Authors: Zhaolu Kang, Junhao Gong, Qingxi Chen, Hao Zhang, Jiaxin Liu, Rong Fu, Zhiyuan Feng, Yuan Wang, Simon Fong, Kaiyue Zhou Published: 2026-01-19 Categories: cs.CL, cs.AI, cs.CY, cs.MA arXiv: https://arxiv.org/abs/2601.12815v5 Legal Judgment Prediction (LJP) aims to predict the outcomes of legal cases based on factual descriptions, serving as a fundamental task to advance the development of legal systems. Traditional methods often rely on statistical analyses or role-based simulations but face challenges with multiple allegations, diverse evidence, and lack adaptability. In this paper, we introduce JurisMMA, a novel framework for LJP that effectively decomposes trial tasks, standardizes processes, and organizes them into distinct stages. Furthermore, we build JurisMM, a large dataset with over 100,000 recent Chinese judicial records, including both text and multimodal video-text data, enabling comprehensive evaluation. Experiments on JurisMM and the benchmark LawBench validate our framework's effectiveness. These results indicate that our framework is effective not only for LJP but also for a broader range of legal applications, offering new perspectives for the development of future legal methods and datasets. --- ### CSGaussian: Progressive Rate-Distortion Compression and Segmentation for 3D Gaussian Splatting Authors: Yu-Jen Tseng, Chia-Hao Kao, Jing-Zhong Chen, Alessandro Gnutti, Shao-Yuan Lo, Yen-Yu Lin, Wen-Hsiao Peng Published: 2026-01-19 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.12814v1 We present the first unified framework for rate-distortion-optimized compression and segmentation of 3D Gaussian Splatting (3DGS). While 3DGS has proven effective for both real-time rendering and semantic scene understanding, prior works have largely treated these tasks independently, leaving their joint consideration unexplored. Inspired by recent advances in rate-distortion-optimized 3DGS compression, this work integrates semantic learning into the compression pipeline to support decoder-side applications--such as scene editing and manipulation--that extend beyond traditional scene reconstruction and view synthesis. Our scheme features a lightweight implicit neural representation-based hyperprior, enabling efficient entropy coding of both color and semantic attributes while avoiding costly grid-based hyperprior as seen in many prior works. To facilitate compression and segmentation, we further develop compression-guided segmentation learning, consisting of quantization-aware training to enhance feature separability and a quality-aware weighting mechanism to suppress unreliable Gaussian primitives. Extensive experiments on the LERF and 3D-OVS datasets demonstrate that our approach significantly reduces transmission cost while preserving high rendering quality and strong segmentation performance. --- ### Do Clinical Question Answering Systems Really Need Specialised Medical Fine Tuning? Authors: Sushant Kumar Ray, Gautam Siddharth Kashyap, Sahil Tripathi, Nipun Joshi, Vijay Govindarajan, Rafiq Ali, Jiechao Gao, Usman Naseem Published: 2026-01-19 Categories: cs.CL arXiv: https://arxiv.org/abs/2601.12812v1 Clinical Question-Answering (CQA) industry systems are increasingly rely on Large Language Models (LLMs), yet their deployment is often guided by the assumption that domain-specific fine-tuning is essential. Although specialised medical LLMs such as BioBERT, BioGPT, and PubMedBERT remain popular, they face practical limitations including narrow coverage, high retraining costs, and limited adaptability. Efforts based on Supervised Fine-Tuning (SFT) have attempted to address these assumptions but continue to reinforce what we term the SPECIALISATION FALLACY-the belief that specialised medical LLMs are inherently superior for CQA. To address this assumption, we introduce MEDASSESS-X, a deployment-industry-oriented CQA framework that applies alignment at inference time rather than through SFT. MEDASSESS-X uses lightweight steering vectors to guide model activations toward medically consistent reasoning without updating model weights or requiring domain-specific retraining. This inference-time alignment layer stabilises CQA performance across both general-purpose and specialised medical LLMs, thereby resolving the SPECIALISATION FALLACY. Empirically, MEDASSESS-X delivers consistent gains across all LLM families, improving Accuracy by up to +6%, Factual Consistency by +7%, and reducing Safety Error Rate by as much as 50%. --- ### Left-Right Symmetry Breaking in CLIP-style Vision-Language Models Trained on Synthetic Spatial-Relation Data Authors: Takaki Yamamoto, Chihiro Noguchi, Toshihiro Tanizawa Published: 2026-01-19 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2601.12809v2 Spatial understanding remains a key challenge in vision-language models. Yet it is still unclear whether such understanding is truly acquired, and if so, through what mechanisms. We present a controllable 1D image-text testbed to probe how left-right relational understanding emerges in Transformer-based vision and text encoders trained with a CLIP-style contrastive objective. We train lightweight Transformer-based vision and text encoders end-to-end on paired descriptions of one- and two-object scenes and evaluate generalization to unseen object pairs while systematically varying label and layout diversity. We find that contrastive training learns left-right relations and that label diversity, more than layout diversity, is the primary driver of generalization in this setting. To gain the mechanistic understanding, we perform an attention decomposition and show that interactions between positional and token embeddings induce a horizontal attention gradient that breaks left-right symmetry in the encoders; ablating this contribution substantially reduces left-right discrimination. Our results provide a mechanistic insight of when and how CLIP-style models acquire relational competence. ---