# Research Papers — 2026-01 · bundle page 135 of 189 > Full-text markdown of papers #6701–6750 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/135 [← Previous bundle](https://aipod.dev/papers/archive/2026-01/page/134.md) [Next bundle →](https://aipod.dev/papers/archive/2026-01/page/136.md) ### Constrained Density Estimation via Optimal Transport Authors: Yinan Hu, Esteban G. Tabak Published: 2026-01-11 Categories: stat.ML, cs.LG, math.NA, math.OC, math.PR arXiv: https://arxiv.org/abs/2601.06830v2 A novel framework for density estimation under expectation constraints is proposed. The framework minimizes the Wasserstein distance between the estimated density and a prior, subject to the constraints that the expected value of a set of functions adopts or exceeds given values. The framework is generalized to include regularization inequalities to mitigate the artifacts in the target measure. An annealing-like algorithm is developed to address non-smooth constraints, with its effectiveness demonstrated through both synthetic and proof-of-concept real world examples in finance. --- ### PDR: A Plug-and-Play Positional Decay Framework for LLM Pre-training Data Detection Authors: Jinhan Liu, Yibo Yang, Ruiying Lu, Piotr Piekos, Yimeng Chen, Peng Wang, Dandan Guo Published: 2026-01-11 Categories: cs.CL arXiv: https://arxiv.org/abs/2601.06827v1 Detecting pre-training data in Large Language Models (LLMs) is crucial for auditing data privacy and copyright compliance, yet it remains challenging in black-box, zero-shot settings where computational resources and training data are scarce. While existing likelihood-based methods have shown promise, they typically aggregate token-level scores using uniform weights, thereby neglecting the inherent information-theoretic dynamics of autoregressive generation. In this paper, we hypothesize and empirically validate that memorization signals are heavily skewed towards the high-entropy initial tokens, where model uncertainty is highest, and decay as context accumulates. To leverage this linguistic property, we introduce Positional Decay Reweighting (PDR), a training-free and plug-and-play framework. PDR explicitly reweights token-level scores to amplify distinct signals from early positions while suppressing noise from later ones. Extensive experiments show that PDR acts as a robust prior and can usually enhance a wide range of advanced methods across multiple benchmarks. --- ### AgentHallu: Benchmarking Automated Hallucination Attribution of LLM-based Agents Authors: Xuannan Liu, Xiao Yang, Zekun Li, Peipei Li, Ran He Published: 2026-01-11 Categories: cs.CL arXiv: https://arxiv.org/abs/2601.06818v1 As LLM-based agents operate over sequential multi-step reasoning, hallucinations arising at intermediate steps risk propagating along the trajectory, thus degrading overall reliability. Unlike hallucination detection in single-turn responses, diagnosing hallucinations in multi-step workflows requires identifying which step causes the initial divergence. To fill this gap, we propose a new research task, automated hallucination attribution of LLM-based agents, aiming to identify the step responsible for the hallucination and explain why. To support this task, we introduce AgentHallu, a comprehensive benchmark with: (1) 693 high-quality trajectories spanning 7 agent frameworks and 5 domains, (2) a hallucination taxonomy organized into 5 categories (Planning, Retrieval, Reasoning, Human-Interaction, and Tool-Use) and 14 sub-categories, and (3) multi-level annotations curated by humans, covering binary labels, hallucination-responsible steps, and causal explanations. We evaluate 13 leading models, and results show the task is challenging even for top-tier models (like GPT-5, Gemini-2.5-Pro). The best-performing model achieves only 41.1\% step localization accuracy, where tool-use hallucinations are the most challenging at just 11.6\%. We believe AgentHallu will catalyze future research into developing robust, transparent, and reliable agentic systems. --- ### Analyzing the effect of prediction accuracy on the distributionally-robust competitive ratio Authors: Toru Yoshinaga, Yasushi Kawase Published: 2026-01-11 Categories: cs.LG, cs.DS arXiv: https://arxiv.org/abs/2601.06813v1 The field of algorithms with predictions aims to improve algorithm performance by integrating machine learning predictions into algorithm design. A central question in this area is how predictions can improve performance, and a key aspect of this analysis is the role of prediction accuracy. In this context, prediction accuracy is defined as a guaranteed probability that an instance drawn from the distribution belongs to the predicted set. As a performance measure that incorporates prediction accuracy, we focus on the distributionally-robust competitive ratio (DRCR), introduced by Sun et al.~(ICML 2024). The DRCR is defined as the expected ratio between the algorithm's cost and the optimal cost, where the expectation is taken over the worst-case instance distribution that satisfies the given prediction and accuracy requirement. A known structural property is that, for any fixed algorithm, the DRCR decreases linearly as prediction accuracy increases. Building on this result, we establish that the optimal DRCR value (i.e., the infimum over all algorithms) is a monotone and concave function of prediction accuracy. We further generalize the DRCR framework to a multiple-prediction setting and show that monotonicity and concavity are preserved in this setting. Finally, we apply our results to the ski rental problem, a benchmark problem in online optimization, to identify the conditions on prediction accuracies required for the optimal DRCR to attain a target value. Moreover, we provide a method for computing the critical accuracy, defined as the minimum accuracy required for the optimal DRCR to strictly improve upon the performance attainable without any accuracy guarantee. --- ### WFR-FM: Simulation-Free Dynamic Unbalanced Optimal Transport Authors: Qiangwei Peng, Zihan Wang, Junda Ying, Yuhao Sun, Qing Nie, Lei Zhang, Tiejun Li, Peijie Zhou Published: 2026-01-11 Categories: cs.LG, cs.AI, math-ph arXiv: https://arxiv.org/abs/2601.06810v2 The Wasserstein-Fisher-Rao (WFR) metric extends dynamic optimal transport (OT) by coupling displacement with change of mass, providing a principled geometry for modeling unbalanced snapshot dynamics. Existing WFR solvers, however, are often unstable, computationally expensive, and difficult to scale. Here we introduce WFR Flow Matching (WFR-FM), a simulation-free training algorithm that unifies flow matching with dynamic unbalanced OT. Unlike classical flow matching which regresses only a transport vector field, WFR-FM simultaneously regresses a vector field for displacement and a scalar growth rate function for birth-death dynamics, yielding continuous flows under the WFR geometry. Theoretically, we show that minimizing the WFR-FM loss exactly recovers WFR geodesics. Empirically, WFR-FM yields more accurate and robust trajectory inference in single-cell biology, reconstructing consistent dynamics with proliferation and apoptosis, estimating time-varying growth fields, and applying to generative dynamics under imbalanced data. It outperforms state-of-the-art baselines in efficiency, stability, and reconstruction accuracy. Overall, WFR-FM establishes a unified and efficient paradigm for learning dynamical systems from unbalanced snapshots, where not only states but also mass evolve over time. The Python code is available at https://github.com/QiangweiPeng/WFR-FM. --- ### SpatialNav: Leveraging Spatial Scene Graphs for Zero-Shot Vision-and-Language Navigation Authors: Jiwen Zhang, Zejun Li, Siyuan Wang, Xiangyu Shi, Zhongyu Wei, Qi Wu Published: 2026-01-11 Categories: cs.CV, cs.AI, cs.RO arXiv: https://arxiv.org/abs/2601.06806v1 Although learning-based vision-and-language navigation (VLN) agents can learn spatial knowledge implicitly from large-scale training data, zero-shot VLN agents lack this process, relying primarily on local observations for navigation, which leads to inefficient exploration and a significant performance gap. To deal with the problem, we consider a zero-shot VLN setting that agents are allowed to fully explore the environment before task execution. Then, we construct the Spatial Scene Graph (SSG) to explicitly capture global spatial structure and semantics in the explored environment. Based on the SSG, we introduce SpatialNav, a zero-shot VLN agent that integrates an agent-centric spatial map, a compass-aligned visual representation, and a remote object localization strategy for efficient navigation. Comprehensive experiments in both discrete and continuous environments demonstrate that SpatialNav significantly outperforms existing zero-shot agents and clearly narrows the gap with state-of-the-art learning-based methods. Such results highlight the importance of global spatial representations for generalizable navigation. --- ### Forest Before Trees: Latent Superposition for Efficient Visual Reasoning Authors: Yubo Wang, Juntian Zhang, Yichen Wu, Yankai Lin, Nils Lukas, Yuhan Liu Published: 2026-01-11 Categories: cs.CL, cs.CV arXiv: https://arxiv.org/abs/2601.06803v2 While Chain-of-Thought empowers Large Vision-Language Models with multi-step reasoning, explicit textual rationales suffer from an information bandwidth bottleneck, where continuous visual details are discarded during discrete tokenization. Recent latent reasoning methods attempt to address this challenge, but often fall prey to premature semantic collapse due to rigid autoregressive objectives. In this paper, we propose Laser, a novel paradigm that reformulates visual deduction via Dynamic Windowed Alignment Learning (DWAL). Instead of forcing a point-wise prediction, Laser aligns the latent state with a dynamic validity window of future semantics. This mechanism enforces a "Forest-before-Trees" cognitive hierarchy, enabling the model to maintain a probabilistic superposition of global features before narrowing down to local details. Crucially, Laser maintains interpretability via decodable trajectories while stabilizing unconstrained learning via Self-Refined Superposition. Extensive experiments on 6 benchmarks demonstrate that Laser achieves state-of-the-art performance among latent reasoning methods, surpassing the strong baseline Monet by 5.03% on average. Notably, it achieves these gains with extreme efficiency, reducing inference tokens by more than 97%, while demonstrating robust generalization to out-of-distribution domains. --- ### Doing More with Less: Data Augmentation for Sudanese Dialect Automatic Speech Recognition Authors: Ayman Mansour Published: 2026-01-11 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2601.06802v1 Although many Automatic Speech Recognition (ASR) systems have been developed for Modern Standard Arabic (MSA) and Dialectal Arabic (DA), few studies have focused on dialect-specific implementations, particularly for low-resource Arabic dialects such as Sudanese. This paper presents a comprehensive study of data augmentation techniques for fine-tuning OpenAI Whisper models and establishes the first benchmark for the Sudanese dialect. Two augmentation strategies are investigated: (1) self-training with pseudo-labels generated from unlabeled speech, and (2) TTS-based augmentation using synthetic speech from the Klaam TTS system. The best-performing model, Whisper-Medium fine-tuned with combined self-training and TTS augmentation (28.4 hours), achieves a Word Error Rate (WER) of 57.1% on the evaluation set and 51.6% on an out-of-domain holdout set substantially outperforming zero-shot multilingual Whisper (78.8% WER) and MSA-specialized Arabic models (73.8-123% WER). All experiments used low-cost resources (Kaggle free tier and Lightning.ai trial), demonstrating that strategic data augmentation can overcome resource limitations for low-resource dialects and provide a practical roadmap for developing ASR systems for low-resource Arabic dialects and other marginalized language varieties. The models, evaluation benchmarks, and reproducible training pipelines are publicly released to facilitate future research on low-resource Arabic ASR. --- ### Thinking with Deltas: Incentivizing Reinforcement Learning via Differential Visual Reasoning Policy Authors: Shujian Gao, Yuan Wang, Jiangtao Yan, Zuxuan Wu, Yu-Gang Jiang Published: 2026-01-11 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2601.06801v1 Reinforcement Learning with Verifiable Rewards (RLVR) has significantly advanced reasoning capabilities in Large Language Models. However, adapting RLVR to multimodal domains suffers from a critical \textit{perception-reasoning decoupling}. Existing paradigms, driven by text-centric outcome rewards, reasoning in language medium, inadvertently encourage models to bypass visual perception. We empirically validate this through blind experiments: state-of-the-art policies maintain or surprisingly improve performance even when visual inputs are entirely removed. This reveals that these models degenerate into \textit{blind reasoners}, exploiting linguistic priors to generate plausible answers instead of attending to visual evidence. In response, we propose \textbf{Thinking with Deltas}, a framework driven by a \textbf{Differential Visual Reasoning Policy (DVRP)}. DVRP introduces intrinsic supervision via visual triplets, comprising original, masked, and perturbed inputs. It optimizes the model to maximize reasoning divergence from masked inputs (enforcing \textit{visual sensitivity}) while minimizing divergence from perturbed inputs (ensuring \textit{visual robustness}). By aligning reasoning variations strictly with the \textit{Delta} of visual information, DVRP inherently bolsters visual understanding capabilities and significantly outperforms state-of-the-art methods on both general and medical benchmarks, without requiring external annotations or auxiliary tools. --- ### Graph Neural Network with One-side Edge Sampling for Fraud Detection Authors: Hoang Hiep Trieu Published: 2026-01-11 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2601.06800v1 Financial fraud is always a major problem in the field of finance, as it can cause significant consequences. As a result, many approaches have been designed to detect it, and lately Graph Neural Networks (GNNs) have been demonstrated as a competent candidate. However, when trained with a large amount of data, they are slow and computationally demanding. In addition, GNNs may need a deep architecture to detect complex fraud patterns, but doing so may make them suffer from problems such as over-fitting or over-smoothing. Over-fitting leads to reduced generalisation of the model on unseen data, while over-smoothing causes all nodes' features to converge to a fixed point due to excessive aggregation of information from neighbouring nodes. In this research, I propose an approach called One-Side Edge Sampling (OES) that can potentially reduce training duration as well as the effects of over-smoothing and over-fitting. The approach leverages predictive confidence in an edge classification task to sample edges from the input graph during a certain number of epochs. To explain why OES can alleviate over-smoothing, I perform a theoretical analysis of the proposed approach. In addition, to validate the effect of OES, I conduct experiments using different GNNs on two datasets. The results show that OES can empirically outperform backbone models in both shallow and deep architectures while also reducing training time. --- ### CIRAG: Construction-Integration Retrieval and Adaptive Generation for Multi-hop Question Answering Authors: Zili Wei, Xiaocui Yang, Yilin Wang, Zihan Wang, Weidong Bao, Shi Feng, Daling Wang, Yifei Zhang Published: 2026-01-11 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2601.06799v1 Triple-based Iterative Retrieval-Augmented Generation (iRAG) mitigates document-level noise for multi-hop question answering. However, existing methods still face limitations: (i) greedy single-path expansion, which propagates early errors and fails to capture parallel evidence from different reasoning branches, and (ii) granularity-demand mismatch, where a single evidence representation struggles to balance noise control with contextual sufficiency. In this paper, we propose the Construction-Integration Retrieval and Adaptive Generation model, CIRAG. It introduces an Iterative Construction-Integration module that constructs candidate triples and history-conditionally integrates them to distill core triples and generate the next-hop query. This module mitigates the greedy trap by preserving multiple plausible evidence chains. Besides, we propose an Adaptive Cascaded Multi-Granularity Generation module that progressively expands contextual evidence based on the problem requirements, from triples to supporting sentences and full passages. Moreover, we introduce Trajectory Distillation, which distills the teacher model's integration policy into a lightweight student, enabling efficient and reliable long-horizon reasoning. Extensive experiments demonstrate that CIRAG achieves superior performance compared to existing iRAG methods. --- ### GDEPO: Group Dual-dynamic and Equal-right Advantage Policy Optimization with Enhanced Training Data Utilization for Sample-Constrained Reinforcement Learning Authors: Zhengqing Yan, Xinyang Liu, Yi Zhang, Fan Guo, ChengXun Jia, Junchen Wan, Yao Liu, Qi Liu, Jihao Huang, Kang Song Published: 2026-01-11 Categories: cs.AI arXiv: https://arxiv.org/abs/2601.06795v3 Automated Theorem Proving (ATP) represents a fundamental challenge in Artificial Intelligence (AI), requiring the construction of machine-verifiable proofs in formal languages such as Lean to evaluate AI reasoning capabilities. Reinforcement learning (RL), particularly the high-performance Group Relative Policy Optimization (GRPO) algorithm, has emerged as a mainstream approach for this task. However, in ATP scenarios, GRPO faces two critical issues: when composite rewards are used, its relative advantage estimation may conflict with the binary feedback from the formal verifier; meanwhile, its static sampling strategy may discard entire batches of data if no valid proof is found, resulting in zero contribution to model updates and significant data waste. To address these limitations, we propose Group Dual-dynamic and Equal-right-advantage Policy Optimization (GDEPO), a method incorporating three core mechanisms: 1) dynamic additional sampling, which resamples invalid batches until a valid proof is discovered; 2) equal-right advantage, decoupling the sign of the advantage function (based on correctness) from its magnitude (modulated by auxiliary rewards) to ensure stable and correct policy updates; and 3) dynamic additional iterations, applying extra gradient steps to initially failed but eventually successful samples to accelerate learning on challenging cases. Experiments conducted on three datasets of varying difficulty (MinF2F-test, MathOlympiadBench, PutnamBench) confirm the effectiveness of GDEPO, while ablation studies validate the necessity of its synergistic components. The proposed method enhances data utilization and optimization efficiency, offering a novel training paradigm for ATP. --- ### No More Stale Feedback: Co-Evolving Critics for Open-World Agent Learning Authors: Zhicong Li, Lingjie Jiang, Yulan Hu, Xingchen Zeng, Yixia Li, Xiangwen Zhang, Guanhua Chen, Zheng Pan, Xin Li, Yong Liu Published: 2026-01-11 Categories: cs.AI arXiv: https://arxiv.org/abs/2601.06794v2 Critique-guided reinforcement learning (RL) has emerged as a powerful paradigm for training LLM agents by augmenting sparse outcome rewards with natural-language feedback. However, current methods often rely on static or offline critic models, which fail to adapt as the policy evolves. In on-policy RL, the agent's error patterns shift over time, causing stationary critics to become stale and providing feedback of diminishing utility. To address this, we introduce ECHO (Evolving Critic for Hindsight-Guided Optimization)}, a framework that jointly optimizes the policy and critic through a synchronized co-evolutionary loop. ECHO utilizes a cascaded rollout mechanism where the critic generates multiple diagnoses for an initial trajectory, followed by policy refinement to enable group-structured advantage estimation. We address the challenge of learning plateaus via a saturation-aware gain shaping objective, which rewards the critic for inducing incremental improvements in high-performing trajectories. By employing dual-track GRPO updates, ECHO ensures the critic's feedback stays synchronized with the evolving policy. Experimental results show that ECHO yields more stable training and higher long-horizon task success across open-world environments. --- ### CliffordNet: All You Need is Geometric Algebra Authors: Zhongping Ji Published: 2026-01-11 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2601.06793v2 Modern computer vision architectures, from CNNs to Transformers, predominantly rely on the stacking of heuristic modules: spatial mixers (Attention/Conv) followed by channel mixers (FFNs). In this work, we challenge this paradigm by returning to mathematical first principles. We propose the Clifford Algebra Network (CAN), also referred to as CliffordNet, a vision backbone grounded purely in Geometric Algebra. Instead of engineering separate modules for mixing and memory, we derive a unified interaction mechanism based on the Clifford Geometric Product ($uv = u \cdot v + u \wedge v$). This operation ensures algebraic completeness regarding the Geometric Product by simultaneously capturing feature coherence (via the generalized inner product) and structural variation (via the exterior wedge product). Implemented via an efficient sparse rolling mechanism with strict linear complexity $O(N)$, our model reveals a surprising emergent property: the geometric interaction is so representationally dense that standard Feed-Forward Networks (FFNs) become redundant. Empirically, CliffordNet establishes a new Pareto frontier: our Nano variant achieves 77.82\% accuracy on CIFAR-100 with only 1.4M parameters, effectively matching the heavy-weight ResNet-18 (11.2M) with $8\times$ fewer parameters, while our Lite variant (2.6M) sets a new SOTA for tiny models at 79.05\%. Our results suggest that global understanding can emerge solely from rigorous, algebraically complete local interactions, potentially signaling a shift where geometry is all you need. Code is available at https://github.com/ParaMind2025/CAN. --- ### Cross-Modal Computational Model of Brain-Heart Interactions via HRV and EEG Feature Authors: Malavika Pradeep, Akshay Sasi, Nusaibah Farrukh, Rahul Venugopal, Elizabeth Sherly Published: 2026-01-11 Categories: cs.LG arXiv: https://arxiv.org/abs/2601.06792v1 The electroencephalogram (EEG) has been the gold standard for quantifying mental workload; however, due to its complexity and non-portability, it can be constraining. ECG signals, which are feasible on wearable equipment pieces such as headbands, present a promising method for cognitive state monitoring. This research explores whether electrocardiogram (ECG) signals are able to indicate mental workload consistently and act as surrogates for EEG-based cognitive indicators. This study investigates whether ECG-derived features can serve as surrogate indicators of cognitive load, a concept traditionally quantified using EEG. Using a publicly available multimodal dataset (OpenNeuro) of EEG and ECG recorded during working-memory and listening tasks, features of HRV and Catch22 descriptors are extracted from ECG, and spectral band-power with Catch22 features from EEG. A cross-modal regression framework based on XGBoost was trained to map ECG-derived HRV representations to EEG-derived cognitive features. In order to address data sparsity and model brain-heart interactions, we integrated the PSV-SDG to produce EEG-conditioned synthetic HRV time series.This addresses the challenge of inferring cognitive load solely from ECG-derived features using a combination of multimodal learning, signal processing, and synthetic data generation. These outcomes form a basis for light, interpretable machine learning models that are implemented through wearable biosensors in non-lab environments. Synthetic HRV inclusion enhances robustness, particularly in sparse data situations. Overall, this work is an initiation for building low-cost, explainable, and real-time cognitive monitoring systems for mental health, education, and human-computer interaction, with a focus on ageing and clinical populations. --- ### SecMoE: Communication-Efficient Secure MoE Inference via Select-Then-Compute Authors: Bowen Shen, Yuyue Chen, Peng Yang, Bin Zhang, Xi Zhang, Zoe L. Jiang Published: 2026-01-11 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2601.06790v1 Privacy-preserving Transformer inference has gained attention due to the potential leakage of private information. Despite recent progress, existing frameworks still fall short of practical model scales, with gaps up to a hundredfold. A possible way to close this gap is the Mixture of Experts (MoE) architecture, which has emerged as a promising technique to scale up model capacity with minimal overhead. However, given that the current secure two-party (2-PC) protocols allow the server to homomorphically compute the FFN layer with its plaintext model weight, under the MoE setting, this could reveal which expert is activated to the server, exposing token-level privacy about the client's input. While naively evaluating all the experts before selection could protect privacy, it nullifies MoE sparsity and incurs the heavy computational overhead that sparse MoE seeks to avoid. To address the privacy and efficiency limitations above, we propose a 2-PC privacy-preserving inference framework, \SecMoE. Unifying per-entry circuits in both the MoE layer and piecewise polynomial functions, \SecMoE obliviously selects the extracted parameters from circuits and only computes one encrypted entry, which we refer to as Select-Then-Compute. This makes the model for private inference scale to 63$\times$ larger while only having a 15.2$\times$ increase in end-to-end runtime. Extensive experiments show that, under 5 expert settings, \SecMoE lowers the end-to-end private inference communication by 1.8$\sim$7.1$\times$ and achieves 1.3$\sim$3.8$\times$ speedup compared to the state-of-the-art (SOTA) protocols. --- ### MemGovern: Enhancing Code Agents through Learning from Governed Human Experiences Authors: Qihao Wang, Ziming Cheng, Shuo Zhang, Fan Liu, Rui Xu, Heng Lian, Kunyi Wang, Xiaoming Yu, Jianghao Yin, Sen Hu, Yue Hu, Shaolei Zhang et al. Published: 2026-01-11 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2601.06789v2 While autonomous software engineering (SWE) agents are reshaping programming paradigms, they currently suffer from a "closed-world" limitation: they attempt to fix bugs from scratch or solely using local context, ignoring the immense historical human experience available on platforms like GitHub. Accessing this open-world experience is hindered by the unstructured and fragmented nature of real-world issue-tracking data. In this paper, we introduce MemGovern, a framework designed to govern and transform raw GitHub data into actionable experiential memory for agents. MemGovern employs experience governance to convert human experience into agent-friendly experience cards and introduces an agentic experience search strategy that enables logic-driven retrieval of human expertise. By producing 135K governed experience cards, MemGovern achieves a significant performance boost, improving resolution rates on the SWE-bench Verified by 4.65%. As a plug-in approach, MemGovern provides a solution for agent-friendly memory infrastructure. --- ### Artificial Entanglement in the Fine-Tuning of Large Language Models Authors: Min Chen, Zihan Wang, Canyu Chen, Zeguan Wu, Manling Li, Junyu Liu Published: 2026-01-11 Categories: cs.LG, cs.AI, hep-th, quant-ph, stat.ML arXiv: https://arxiv.org/abs/2601.06788v1 Large language models (LLMs) can be adapted to new tasks using parameter-efficient fine-tuning (PEFT) methods that modify only a small number of trainable parameters, often through low-rank updates. In this work, we adopt a quantum-information-inspired perspective to understand their effectiveness. From this perspective, low-rank parameterizations naturally correspond to low-dimensional Matrix Product States (MPS) representations, which enable entanglement-based characterizations of parameter structure. Thereby, we term and measure "Artificial Entanglement", defined as the entanglement entropy of the parameters in artificial neural networks (in particular the LLMs). We first study the representative low-rank adaptation (LoRA) PEFT method, alongside full fine-tuning (FFT), using LLaMA models at the 1B and 8B scales trained on the Tulu3 and OpenThoughts3 datasets, and uncover: (i) Internal artificial entanglement in the updates of query and value projection matrices in LoRA follows a volume law with a central suppression (termed as the "Entanglement Valley"), which is sensitive to hyper-parameters and is distinct from that in FFT; (ii) External artificial entanglement in attention matrices, corresponding to token-token correlations in representation space, follows an area law with logarithmic corrections and remains robust to LoRA hyper-parameters and training steps. Drawing a parallel to the No-Hair Theorem in black hole physics, we propose that although LoRA and FFT induce distinct internal entanglement signatures, such differences do not manifest in the attention outputs, suggesting a "no-hair" property that results in the effectiveness of low rank updates. We further provide theoretical support based on random matrix theory, and extend our analysis to an MPS Adaptation PEFT method, which exhibits qualitatively similar behaviors. --- ### Garbage Attention in Large Language Models: BOS Sink Heads and Sink-aware Pruning Authors: Jaewon Sok, Jewon Yeom, Seonghyeon Park, Jeongjae Park, Taesup Kim Published: 2026-01-11 Categories: cs.CL arXiv: https://arxiv.org/abs/2601.06787v2 Large Language Models (LLMs) are known to contain significant redundancy, yet a systematic explanation for why certain components, particularly in higher layers, are more redundant has remained elusive. In this work, we identify the BOS sink phenomenon as a key mechanism driving this layer-wise sensitivity. We show that attention heads with high BOS sink scores are strongly associated with functional redundancy: such heads, especially in deeper layers, contribute little to predictive performance and effectively serve as dumping grounds for superfluous attention weights. Leveraging this insight, we introduce a simple pruning strategy that removes high-BOS sink heads. Experiments on Gemma-3, Llama-3.1, and Qwen3 demonstrate that this approach identifies redundant transformer components more reliably than weight- and activation-based criteria in terms of downstream task retention, remaining close to dense baselines at low-to-moderate pruning ratios. We further find that high-scoring sink heads sustain their focus on BOS as context length grows. Overall, our results suggest that structural properties of attention offer a more direct basis for model compression than magnitude-based methods. --- ### EpiCaR: Knowing What You Don't Know Matters for Better Reasoning in LLMs Authors: Jewon Yeom, Jaewon Sok, Seonghyeon Park, Jeongjae Park, Taesup Kim Published: 2026-01-11 Categories: cs.CL arXiv: https://arxiv.org/abs/2601.06786v1 Improving the reasoning abilities of large language models (LLMs) has largely relied on iterative self-training with model-generated data. While effective at boosting accuracy, existing approaches primarily reinforce successful reasoning paths, incurring a substantial calibration cost: models become overconfident and lose the ability to represent uncertainty. This failure has been characterized as a form of model collapse in alignment, where predictive distributions degenerate toward low-variance point estimates. We address this issue by reframing reasoning training as an epistemic learning problem, in which models must learn not only how to reason, but also when their reasoning should be trusted. We propose epistemically-calibrated reasoning (EpiCaR) as a training objective that jointly optimizes reasoning performance and calibration, and instantiate it within an iterative supervised fine-tuning framework using explicit self-evaluation signals. Experiments on Llama-3 and Qwen-3 families demonstrate that our approach achieves Pareto-superiority over standard baselines in both accuracy and calibration, particularly in models with sufficient reasoning capacity (e.g., 3B+). This framework generalizes effectively to OOD mathematical reasoning (GSM8K) and code generation (MBPP). Ultimately, our approach enables a 3X reduction in inference compute, matching the K=30 performance of STaR with only K=10 samples in capable models. --- ### Dimension-reduced outcome-weighted learning for estimating individualized treatment regimes in observational studies Authors: Sungtaek Son, Eardi Lila, Kwun Chuen Gary Chan Published: 2026-01-11 Categories: stat.ML, cs.LG, stat.ME arXiv: https://arxiv.org/abs/2601.06782v1 Individualized treatment regimes (ITRs) aim to improve clinical outcomes by assigning treatment based on patient-specific characteristics. However, existing methods often struggle with high-dimensional covariates, limiting accuracy, interpretability, and real-world applicability. We propose a novel sufficient dimension reduction approach that directly targets the contrast between potential outcomes and identifies a low-dimensional subspace of the covariates capturing treatment effect heterogeneity. This reduced representation enables more accurate estimation of optimal ITRs through outcome-weighted learning. To accommodate observational data, our method incorporates kernel-based covariate balancing, allowing treatment assignment to depend on the full covariate set and avoiding the restrictive assumption that the subspace sufficient for modeling heterogeneous treatment effects is also sufficient for confounding adjustment. We show that the proposed method achieves universal consistency, i.e., its risk converges to the Bayes risk, under mild regularity conditions. We demonstrate its finite sample performance through simulations and an analysis of intensive care unit sepsis patient data to determine who should receive transthoracic echocardiography. --- ### AutoTour: Automatic Photo Tour Guide with Smartphones and LLMs Authors: Huatao Xu, Zihe Liu, Zilin Zeng, Baichuan Li, Mo Li Published: 2026-01-11 Categories: cs.HC, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2601.06781v1 We present AutoTour, a system that enhances user exploration by automatically generating fine-grained landmark annotations and descriptive narratives for photos captured by users. The key idea of AutoTour is to fuse visual features extracted from photos with nearby geospatial features queried from open matching databases. Unlike existing tour applications that rely on pre-defined content or proprietary datasets, AutoTour leverages open and extensible data sources to provide scalable and context-aware photo-based guidance. To achieve this, we design a training-free pipeline that first extracts and filters relevant geospatial features around the user's GPS location. It then detects major landmarks in user photos through VLM-based feature detection and projects them into the horizontal spatial plane. A geometric matching algorithm aligns photo features with corresponding geospatial entities based on their estimated distance and direction. The matched features are subsequently grounded and annotated directly on the original photo, accompanied by large language model-generated textual and audio descriptions to provide an informative, tour-like experience. We demonstrate that AutoTour can deliver rich, interpretable annotations for both iconic and lesser-known landmarks, enabling a new form of interactive, context-aware exploration that bridges visual perception and geospatial understanding. --- ### Multi-Stage Evolutionary Model Merging with Meta Data Driven Curriculum Learning for Sentiment-Specialized Large Language Modeling Authors: Keito Inoshita, Xiaokang Zhou, Akira Kawai Published: 2026-01-11 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2601.06780v1 The emergence of large language models (LLMs) has significantly transformed natural language processing (NLP), enabling more generalized models to perform various tasks with minimal training. However, traditional sentiment analysis methods, which focus on individual tasks such as sentiment classification or aspect-based analysis, are not practical for real-world applications that usually require handling multiple tasks. While offering flexibility, LLMs in sentiment-specific tasks often fall short of the required accuracy. Techniques like fine-tuning and evolutionary model merging help integrate models into a unified framework, which can improve the learning performance while reducing computational costs. The use of task meta-data and curriculum learning to optimize learning processes remains underexplored, while sentiment analysis is a critical task in NLP that requires high accuracy and scalability across multiple subtasks. In this study, we propose a hybrid learning model called Multi-stage Evolutionary Model Merging with Meta data driven Curriculum Learning (MEM-MCL), to enhance the sentiment analysis in large language modeling. In particular, expert models are created through instruction tuning for specific sentiment tasks and then merged using evolutionary algorithms to form a unified model. The merging process is optimized with weak data to enhance performance across tasks. The curriculum learning is incorporated to provide a learning sequence based on task difficulty, improving knowledge extraction from LLMs. Experiment results demonstrate that the proposed MEM-MCL model outperforms conventional LLMs in a majority of sentiment analysis tasks, achieving superior results across various subtasks. --- ### The Normalized Difference Layer: A Differentiable Spectral Index Formulation for Deep Learning Authors: Ali Lotfi, Adam Carter, Mohammad Meysami, Thuan Ha, Kwabena Nketia, Steve Shirtliffe Published: 2026-01-11 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.06777v1 Normalized difference indices have been a staple in remote sensing for decades. They stay reliable under lighting changes produce bounded values and connect well to biophysical signals. Even so, they are usually treated as a fixed pre processing step with coefficients set to one, which limits how well they can adapt to a specific learning task. In this study, we introduce the Normalized Difference Layer that is a differentiable neural network module. The proposed method keeps the classical idea but learns the band coefficients from data. We present a complete mathematical framework for integrating this layer into deep learning architectures that uses softplus reparameterization to ensure positive coefficients and bounded denominators. We describe forward and backward pass algorithms enabling end to end training through backpropagation. This approach preserves the key benefits of normalized differences, namely illumination invariance and outputs bounded to $(-1,1)$ while allowing gradient descent to discover task specific band weightings. We extend the method to work with signed inputs, so the layer can be stacked inside larger architectures. Experiments show that models using this layer reach similar classification accuracy to standard multilayer perceptrons while using about 75\% fewer parameters. They also handle multiplicative noise well, at 10\% noise accuracy drops only 0.17\% versus 3.03\% for baseline MLPs. The learned coefficient patterns stay consistent across different depths. --- ### From Text to Simulation: A Multi-Agent LLM Workflow for Automated Chemical Process Design Authors: Xufei Tian, Wenli Du, Shaoyi Yang, Han Hu, Hui Xin, Shifeng Qu, Ke Ye Published: 2026-01-11 Categories: cs.AI arXiv: https://arxiv.org/abs/2601.06776v1 Process simulation is a critical cornerstone of chemical engineering design. Current automated chemical design methodologies focus mainly on various representations of process flow diagrams. However, transforming these diagrams into executable simulation flowsheets remains a time-consuming and labor-intensive endeavor, requiring extensive manual parameter configuration within simulation software. In this work, we propose a novel multi-agent workflow that leverages the semantic understanding capabilities of large language models(LLMs) and enables iterative interactions with chemical process simulation software, achieving end-to-end automated simulation from textual process specifications to computationally validated software configurations for design enhancement. Our approach integrates four specialized agents responsible for task understanding, topology generation, parameter configuration, and evaluation analysis, respectively, coupled with Enhanced Monte Carlo Tree Search to accurately interpret semantics and robustly generate configurations. Evaluated on Simona, a large-scale process description dataset, our method achieves a 31.1% improvement in the simulation convergence rate compared to state-of-the-art baselines and reduces the design time by 89. 0% compared to the expert manual design. This work demonstrates the potential of AI-assisted chemical process design, which bridges the gap between conceptual design and practical implementation. Our workflow is applicable to diverse process-oriented industries, including pharmaceuticals, petrochemicals, food processing, and manufacturing, offering a generalizable solution for automated process design. --- ### Structure-preserving learning and prediction in optimal control of collective motion Authors: Sofiia Huraka, Vakhtang Putkaradze Published: 2026-01-11 Categories: cs.LG arXiv: https://arxiv.org/abs/2601.06770v1 Wide-spread adoption of unmanned vehicle technologies requires the ability to predict the motion of the combined vehicle operation from observations. While the general prediction of such motion for an arbitrary control mechanism is difficult, for a particular choice of control, the dynamics reduces to the Lie-Poisson equations (33,34). Our goal is to learn the phase-space dynamics and predict the motion solely from observations, without any knowledge of the control Hamiltonian or the nature of interaction between vehicles. To achieve that goal, we propose the Control Optimal Lie-Poisson Neural Networks (CO-LPNets) for learning and predicting the dynamics of the system from data. Our methods learn the mapping of the phase space through the composition of Poisson maps, which are obtained as flows from Hamiltonians that could be integrated explicitly. CO-LPNets preserve the Poisson bracket and thus preserve Casimirs to machine precision. We discuss the completeness of the derived neural networks and their efficiency in approximating the dynamics. To illustrate the power of the method, we apply these techniques to systems of $N=3$ particles evolving on ${\rm SO}(3)$ group, which describe coupled rigid bodies rotating about their center of mass, and ${\rm SE}(3)$ group, applicable to the movement of unmanned air and water vehicles. Numerical results demonstrate that CO-LPNets learn the dynamics in phase space from data points and reproduce trajectories, with good accuracy, over hundreds of time steps. The method uses a limited number of points ($\sim200$/dimension) and parameters ($\sim 1000$ in our case), demonstrating potential for practical applications and edge deployment. --- ### ALFA: A Safe-by-Design Approach to Mitigate Quishing Attacks Launched via Fancy QR Codes Authors: Muhammad Wahid Akram, Keshav Sood, Muneeb Ul Hassan, Dhananjay Thiruvady Published: 2026-01-11 Categories: cs.CR, cs.LG arXiv: https://arxiv.org/abs/2601.06768v1 Phishing with Quick Response (QR) codes is termed as Quishing. The attackers exploit this method to manipulate individuals into revealing their confidential data. Recently, we see the colorful and fancy representations of QR codes, the 2D matrix of QR codes which does not reflect a typical mixture of black-white modules anymore. Instead, they become more tempting as an attack vector for adversaries which can evade the state-of-the-art deep learning visual-based and other prevailing countermeasures. We introduce "ALFA", a safe-by-design approach, to mitigate Quishing and prevent everyone from accessing the post-scan harmful payload of fancy QR codes. Our method first converts a fancy QR code into the replica of binary grid and then identify the erroneous representation of modules in that grid. Following that, we present "FAST" method which can conveniently recover erroneous modules from that binary grid. Afterwards, using this binary grid, our solution extracts the structural features of fancy QR code and predicts its legitimacy using a pre-trained model. The effectiveness of our proposal is demonstrated by the experimental evaluation on a synthetic dataset (containing diverse variations of fancy QR codes) and achieve a FNR of 0.06% only. We also develop the mobile app to test the practical feasibility of our solution and provide a performance comparison of the app with the real-world QR readers. This comparison further highlights the classification reliability and detection accuracy of this solution in real-world environments. --- ### GanitLLM: Difficulty-Aware Bengali Mathematical Reasoning through Curriculum-GRPO Authors: Shubhashis Roy Dipta, Khairul Mahbub, Nadia Najjar Published: 2026-01-11 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2601.06767v3 We present a Bengali mathematical reasoning model called GanitLLM (named after the Bangla word for mathematics, Ganit), together with a new difficulty-aware Bengali math corpus and a curriculum-based GRPO pipeline. Bengali is one of the world's most widely spoken languages, yet existing LLMs either reason in English and then translate, or simply fail on multi-step Bengali math, in part because reinforcement learning recipes are tuned for high-resource languages and collapse under reward sparsity in low-resource settings. To address this, we construct Ganit, a rigorously filtered and decontaminated Bengali math dataset with automatic difficulty tags derived from the pass@k of a strong evaluator model. Building on this dataset, we propose Curriculum-GRPO, which combines multi-stage training (SFT + GRPO) with difficulty-aware sampling and verifiable rewards for format, numerical correctness, and Bengali reasoning. On Bn-MGSM and Bn-MSVAMP, GanitLLM-4B improves over its Qwen3-4B base by +8 and +6 accuracy points, respectively, while increasing the percentage of Bengali reasoning tokens from 14% to over 88% and reducing average solution length from 943 to 193 words. Project page is available at https://dipta007.github.io/GanitLLM --- ### Comparative Separation: Evaluating Separation on Comparative Judgment Test Data Authors: Xiaoyin Xi, Neeku Capak, Kate Stockwell, Zhe Yu Published: 2026-01-11 Categories: cs.SE, cs.LG arXiv: https://arxiv.org/abs/2601.06761v1 This research seeks to benefit the software engineering society by proposing comparative separation, a novel group fairness notion to evaluate the fairness of machine learning software on comparative judgment test data. Fairness issues have attracted increasing attention since machine learning software is increasingly used for high-stakes and high-risk decisions. It is the responsibility of all software developers to make their software accountable by ensuring that the machine learning software do not perform differently on different sensitive groups -- satisfying the separation criterion. However, evaluation of separation requires ground truth labels for each test data point. This motivates our work on analyzing whether separation can be evaluated on comparative judgment test data. Instead of asking humans to provide the ratings or categorical labels on each test data point, comparative judgments are made between pairs of data points such as A is better than B. According to the law of comparative judgment, providing such comparative judgments yields a lower cognitive burden for humans than providing ratings or categorical labels. This work first defines the novel fairness notion comparative separation on comparative judgment test data, and the metrics to evaluate comparative separation. Then, both theoretically and empirically, we show that in binary classification problems, comparative separation is equivalent to separation. Lastly, we analyze the number of test data points and test data pairs required to achieve the same level of statistical power in the evaluation of separation and comparative separation, respectively. This work is the first to explore fairness evaluation on comparative judgment test data. It shows the feasibility and the practical benefits of using comparative judgment test data for model evaluations. --- ### A Backpropagation-Free Feedback-Hebbian Network for Continual Learning Dynamics Authors: Josh Li, Fow-sen Choa Published: 2026-01-11 Categories: cs.NE, cs.LG arXiv: https://arxiv.org/abs/2601.06758v3 Feedback-rich neural architectures can regenerate earlier representations and inject temporal context, making them a natural setting for strictly local synaptic plasticity. Existing literature raises doubt about whether a minimal, backpropagation-free feedback-Hebbian system can already express interpretable continual-learning-relevant behaviors under controlled training schedules. In this work, we introduce a compact prediction-reconstruction architecture with a dedicated feedback pathway providing lightweight, locally trainable temporal context for continual adaptation. All synapses are updated by a unified local rule combining centered Hebbian covariance, Oja-style stabilization, and a local supervised drive where targets are available. With a simple two-pair association task, learning is characterized through layer-wise activity snapshots, connectivity trajectories (row and column means of learned weights), and a normalized retention index across phases. Under sequential A to B training, forward output connectivity exhibits a long-term depression (LTD)-like suppression of the earlier association, while feedback connectivity preserves an A-related trace during acquisition of B. Under an alternating sequence, both associations are concurrently maintained rather than sequentially suppressed. Architectural controls and rule-term ablations isolate the role of dedicated feedback in regeneration and co-maintenance, alongside the role of the local supervised term in output selectivity and unlearning. Together, the results show that a compact feedback pathway trained with local plasticity can support regeneration and continual-learning-relevant dynamics in a minimal, mechanistically transparent setting. --- ### MTMCS-Bench: Evaluating Contextual Safety of Multimodal Large Language Models in Multi-Turn Dialogues Authors: Zheyuan Liu, Dongwhi Kim, Yixin Wan, Xiangchi Yuan, Zhaoxuan Tan, Fengran Mo, Meng Jiang Published: 2026-01-11 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2601.06757v1 Multimodal large language models (MLLMs) are increasingly deployed as assistants that interact through text and images, making it crucial to evaluate contextual safety when risk depends on both the visual scene and the evolving dialogue. Existing contextual safety benchmarks are mostly single-turn and often miss how malicious intent can emerge gradually or how the same scene can support both benign and exploitative goals. We introduce the Multi-Turn Multimodal Contextual Safety Benchmark (MTMCS-Bench), a benchmark of realistic images and multi-turn conversations that evaluates contextual safety in MLLMs under two complementary settings, escalation-based risk and context-switch risk. MTMCS-Bench offers paired safe and unsafe dialogues with structured evaluation. It contains over 30 thousand multimodal (image+text) and unimodal (text-only) samples, with metrics that separately measure contextual intent recognition, safety-awareness on unsafe cases, and helpfulness on benign ones. Across eight open-source and seven proprietary MLLMs, we observe persistent trade-offs between contextual safety and utility, with models tending to either miss gradual risks or over-refuse benign dialogues. Finally, we evaluate five current guardrails and find that they mitigate some failures but do not fully resolve multi-turn contextual risks. --- ### Towards Computational Chinese Paleography Authors: Yiran Rex Ma Published: 2026-01-11 Categories: cs.CL arXiv: https://arxiv.org/abs/2601.06753v2 Chinese paleography, the study of ancient Chinese writing, is undergoing a computational turn powered by artificial intelligence. This position paper charts the trajectory of this emerging field, arguing that it is evolving from automating isolated visual tasks to creating integrated digital ecosystems for scholarly research. We first map the landscape of digital resources, analyzing critical datasets for oracle bone, bronze, and bamboo slip scripts. The core of our analysis follows the field's methodological pipeline: from foundational visual processing (image restoration, character recognition), through contextual analysis (artifact rejoining, dating), to the advanced reasoning required for automated decipherment and human-AI collaboration. We examine the technological shift from classical computer vision to modern deep learning paradigms, including transformers and large multimodal models. Finally, we synthesize the field's core challenges -- notably data scarcity and a disconnect between current AI capabilities and the holistic nature of humanistic inquiry -- and advocate for a future research agenda focused on creating multimodal, few-shot, and human-centric systems to augment scholarly expertise. --- ### Benchmarking Egocentric Clinical Intent Understanding Capability for Medical Multimodal Large Language Models Authors: Shaonan Liu, Guo Yu, Xiaoling Luo, Shiyi Zheng, Wenting Chen, Jie Liu, Linlin Shen Published: 2026-01-11 Categories: cs.CV, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2601.06750v1 Medical Multimodal Large Language Models (Med-MLLMs) require egocentric clinical intent understanding for real-world deployment, yet existing benchmarks fail to evaluate this critical capability. To address these challenges, we introduce MedGaze-Bench, the first benchmark leveraging clinician gaze as a Cognitive Cursor to assess intent understanding across surgery, emergency simulation, and diagnostic interpretation. Our benchmark addresses three fundamental challenges: visual homogeneity of anatomical structures, strict temporal-causal dependencies in clinical workflows, and implicit adherence to safety protocols. We propose a Three-Dimensional Clinical Intent Framework evaluating: (1) Spatial Intent: discriminating precise targets amid visual noise, (2) Temporal Intent: inferring causal rationale through retrospective and prospective reasoning, and (3) Standard Intent: verifying protocol compliance through safety checks. Beyond accuracy metrics, we introduce Trap QA mechanisms to stress-test clinical reliability by penalizing hallucinations and cognitive sycophancy. Experiments reveal current MLLMs struggle with egocentric intent due to over-reliance on global features, leading to fabricated observations and uncritical acceptance of invalid instructions. --- ### FinForge: Semi-Synthetic Financial Benchmark Generation Authors: Glenn Matlin, Akhil Theerthala, Anant Gupta, Anirudh JM, Rayan Castilla, Yi Mei Ng, Sudheer Chava Published: 2026-01-11 Categories: cs.AI arXiv: https://arxiv.org/abs/2601.06747v2 Evaluating Language Models (LMs) in specialized, high-stakes domains such as finance remains a significant challenge due to the scarcity of open, high-quality, and domain-specific datasets. Existing general-purpose benchmarks provide broad coverage but lack the depth and domain fidelity needed to assess LMs' capabilities for real-world financial reasoning, which requires both conceptual understanding and quantitative rigor. To address this gap, we introduce FinForge, a scalable, semi-synthetic pipeline for constructing finance-specific evaluation benchmarks through a hybrid of expert-guided data curation and controlled LM-based synthesis. FinForge combines manual and programmatic corpus construction from authoritative financial sources with structured question generation and validation using Gemini 2.5 Flash. To demonstrate the pipeline's efficacy, we produce FinForge-5k, a snapshot benchmark comprising over 5,000 human-validated question-answer pairs across 11 finance subdomains, derived from a curated corpus of 100,000 verified documents totaling 143M tokens. Evaluation of state-of-the-art open-source and closed-source models on FinForge-5k reveals significant differences in financial reasoning, with leading models achieving accuracy levels near 80%. These findings underscore the framework's utility for diagnosing current model limitations and guiding future improvements in financial domain competence. All code and data are available at https://github.com/gtfintechlab/FinForge. --- ### Federated Continual Learning for Privacy-Preserving Hospital Imaging Classification Authors: Anay Sinhal, Arpana Sinhal, Amit Sinhal Published: 2026-01-11 Categories: cs.LG arXiv: https://arxiv.org/abs/2601.06742v1 Deep learning models for radiology interpretation increasingly rely on multi-institutional data, yet privacy regulations and distribution shift across hospitals limit central data pooling. Federated learning (FL) allows hospitals to collaboratively train models without sharing raw images, but current FL algorithms typically assume a static data distribution. In practice, hospitals experience continual evolution in case mix, annotation protocols, and imaging devices, which leads to catastrophic forgetting when models are updated sequentially. Federated continual learning (FCL) aims to reconcile these challenges but existing methods either ignore the stringent privacy constraints of healthcare or rely on replay buffers and public surrogate datasets that are difficult to justify in clinical settings. We study FCL for chest radiography classification in a setting where hospitals are clients that receive temporally evolving streams of cases and labels. We introduce DP-FedEPC (Differentially Private Federated Elastic Prototype Consolidation), a method that combines elastic weight consolidation (EWC), prototype-based rehearsal, and client-side differential privacy within a standard FedAvg framework. EWC constrains updates along parameters deemed important for previous tasks, while a memory of latent prototypes preserves class structure without storing raw images. Differentially private stochastic gradient descent (DP-SGD) at each client adds calibrated Gaussian noise to clipped gradients, providing formal privacy guarantees for individual radiographs. --- ### Logic-Driven Semantic Communication for Resilient Multi-Agent Systems Authors: Tamara Alshammari, Mehdi Bennis Published: 2026-01-11 Categories: cs.MA, cs.AI, cs.LG, cs.LO arXiv: https://arxiv.org/abs/2601.06733v1 The advent of 6G networks is accelerating autonomy and intelligence in large-scale, decentralized multi-agent systems (MAS). While this evolution enables adaptive behavior, it also heightens vulnerability to stressors such as environmental changes and adversarial behavior. Existing literature on resilience in decentralized MAS largely focuses on isolated aspects, such as fault tolerance, without offering a principled unified definition of multi-agent resilience. This gap limits the ability to design systems that can continuously sense, adapt, and recover under dynamic conditions. This article proposes a formal definition of MAS resilience grounded in two complementary dimensions: epistemic resilience, wherein agents recover and sustain accurate knowledge of the environment, and action resilience, wherein agents leverage that knowledge to coordinate and sustain goals under disruptions. We formalize resilience via temporal epistemic logic and quantify it using recoverability time (how quickly desired properties are re-established after a disturbance) and durability time (how long accurate beliefs and goal-directed behavior are sustained after recovery). We design an agent architecture and develop decentralized algorithms to achieve both epistemic and action resilience. We provide formal verification guarantees, showing that our specifications are sound with respect to the metric bounds and admit finite-horizon verification, enabling design-time certification and lightweight runtime monitoring. Through a case study on distributed multi-agent decision-making under stressors, we show that our approach outperforms baseline methods. Our formal verification analysis and simulation results highlight that the proposed framework enables resilient, knowledge-driven decision-making and sustained operation, laying the groundwork for resilient decentralized MAS in next-generation communication systems. --- ### Why are there many equally good models? An Anatomy of the Rashomon Effect Authors: Harsh Parikh Published: 2026-01-11 Categories: cs.LG, cs.AI, stat.ME, stat.ML arXiv: https://arxiv.org/abs/2601.06730v2 The Rashomon effect -- the existence of multiple, distinct models that achieve nearly equivalent predictive performance -- has emerged as a fundamental phenomenon in modern machine learning and statistics. In this paper, we explore the causes underlying the Rashomon effect, organizing them into three categories: statistical sources arising from finite samples and noise in the data-generating process; structural sources arising from non-convexity of optimization objectives and unobserved variables that create fundamental non-identifiability; and procedural sources arising from limitations of optimization algorithms and deliberate restrictions to suboptimal model classes. We synthesize insights from machine learning, statistics, and optimization literature to provide a unified framework for understanding why the multiplicity of good models arises. A key distinction emerges: statistical multiplicity diminishes with more data, structural multiplicity persists asymptotically and cannot be resolved without different data or additional assumptions, and procedural multiplicity reflects choices made by practitioners. Beyond characterizing causes, we discuss both the challenges and opportunities presented by the Rashomon effect, including implications for inference, interpretability, fairness, and decision-making under uncertainty. --- ### Predicting Student Success with Heterogeneous Graph Deep Learning and Machine Learning Models Authors: Anca Muresan, Mihaela Cardei, Ionut Cardei Published: 2026-01-11 Categories: cs.LG arXiv: https://arxiv.org/abs/2601.06729v1 Early identification of student success is crucial for enabling timely interventions, reducing dropout rates, and promoting on time graduation. In educational settings, AI powered systems have become essential for predicting student performance due to their advanced analytical capabilities. However, effectively leveraging diverse student data to uncover latent and complex patterns remains a key challenge. While prior studies have explored this area, the potential of dynamic data features and multi category entities has been largely overlooked. To address this gap, we propose a framework that integrates heterogeneous graph deep learning models to enhance early and continuous student performance prediction, using traditional machine learning algorithms for comparison. Our approach employs a graph metapath structure and incorporates dynamic assessment features, which progressively influence the student success prediction task. Experiments on the Open University Learning Analytics (OULA) dataset demonstrate promising results, achieving a 68.6% validation F1 score with only 7% of the semester completed, and reaching up to 89.5% near the semester's end. Our approach outperforms top machine learning models by 4.7% in validation F1 score during the critical early 7% of the semester, underscoring the value of dynamic features and heterogeneous graph representations in student success prediction. --- ### USFetal: Tools for Fetal Brain Ultrasound Compounding Authors: Mohammad Khateri, Morteza Ghahremani, Sergio Valencia, Camilo Jaimes, Alejandra Sierra, Jussi Tohka, P. Ellen Grant, Davood Karimi Published: 2026-01-11 Categories: eess.IV, cs.CV arXiv: https://arxiv.org/abs/2601.06726v1 Ultrasound offers a safe, cost-effective, and widely accessible technology for fetal brain imaging, making it especially suitable for routine clinical use. However, it suffers from view-dependent artifacts, operator variability, and a limited field of view, which make interpretation and quantitative evaluation challenging. Ultrasound compounding aims to overcome these limitations by integrating complementary information from multiple 3D acquisitions into a single, coherent volumetric representation. This work provides four main contributions: (1) We present the first systematic categorization of computational strategies for fetal brain ultrasound compounding, including both classical techniques and modern learning-based frameworks. (2) We implement and compare representative methods across four key categories - multi-scale, transformation-based, variational, and deep learning approaches - emphasizing their core principles and practical advantages. (3) Motivated by the lack of full-view, artifact-free ground truth required for supervised learning, we focus on unsupervised and self-supervised strategies and introduce two new deep learning based approaches: a self-supervised compounding framework and an adaptation of unsupervised deep plug-and-play priors for compounding. (4) We conduct a comprehensive evaluation on ten multi-view fetal brain ultrasound datasets, using both expert radiologist scoring and standard quantitative image-quality metrics. We also release the USFetal Compounding Toolbox, publicly available to support benchmarking and future research. Keywords: Ultrasound compounding, fetal brain, deep learning, self-supervised, unsupervised. --- ### When Humans Judge Irises: Pupil Size Normalization as an Aid and Synthetic Irises as a Challenge Authors: Mahsa Mitcheff, Adam Czajka Published: 2026-01-11 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2601.06725v1 Iris recognition is a mature biometric technology offering remarkable precision and speed, and allowing for large-scale deployments to populations exceeding a billion enrolled users (e.g., AADHAAR in India). However, in forensic applications, a human expert may be needed to review and confirm a positive identification before an iris matching result can be presented as evidence in court, especially in cases where processed samples are degraded (e.g., in post-mortem cases) or where there is a need to judge whether the sample is authentic, rather than a result of a presentation attack. This paper presents a study that examines human performance in iris verification in two controlled scenarios: (a) under varying pupil sizes, with and without a linear/nonlinear alignment of the pupil size between compared images, and (b) when both genuine and impostor iris image pairs are synthetically generated. The results demonstrate that pupil size normalization carried out by a modern autoencoder-based identity-preserving image-to-image translation model significantly improves verification accuracy. Participants were also able to determine whether iris pairs corresponded to the same or different eyes when both images were either authentic or synthetic. However, accuracy declined when subjects were comparing authentic irises against high-quality, same-eye synthetic counterparts. These findings (a) demonstrate the importance of pupil-size alignment for iris matching tasks in which humans are involved, and (b) indicate that despite the high fidelity of modern generative models, same-eye synthetic iris images are more often judged by humans as different-eye images, compared to same-eye authentic image pairs. We offer data and human judgments along with this paper to allow full replicability of this study and future works. --- ### A Methodology for Identifying Evaluation Items for Practical Dialogue Systems Based on Business-Dialogue System Alignment Models Authors: Mikio Nakano, Hironori Takeuchi, Kazunori Komatani Published: 2026-01-10 Categories: cs.HC, cs.CL, cs.SE arXiv: https://arxiv.org/abs/2602.15835v1 This paper proposes a methodology for identifying evaluation items for practical dialogue systems. Traditionally, user satisfaction and user experiences have been the primary metrics for evaluating dialogue systems. However, there are various other evaluation items to consider when developing and operating practical dialogue systems, and such evaluation items are expected to lead to new research topics. So far, there has been no methodology for identifying these evaluation items. We propose identifying evaluation items based on business-dialogue system alignment models, which are applications of business-IT alignment models used in the development and operation of practical IT systems. We also present a generic model that facilitates the construction of a business-dialogue system alignment model for each dialogue system. --- ### Attribution Techniques for Mitigating Hallucinated Information in RAG Systems: A Survey Authors: Yuqing Zhao, Ziyao Liu, Yongsen Zheng, Kwok-Yan Lam Published: 2026-01-10 Categories: cs.CL arXiv: https://arxiv.org/abs/2601.19927v1 Large Language Models (LLMs)-based question answering (QA) systems play a critical role in modern AI, demonstrating strong performance across various tasks. However, LLM-generated responses often suffer from hallucinations, unfaithful statements lacking reliable references. Retrieval-Augmented Generation (RAG) frameworks enhance LLM responses by incorporating external references but also introduce new forms of hallucination due to complex interactions between the retriever and generator. To address these challenges, researchers have explored attribution-based techniques that ensure responses are verifiably supported by retrieved content. Despite progress, a unified pipeline for these techniques, along with a clear taxonomy and systematic comparison of their strengths and weaknesses, remains lacking. A well-defined taxonomy is essential for identifying specific failure modes within RAG systems, while comparative analysis helps practitioners choose appropriate solutions based on hallucination types and application context. This survey investigates how attribution-based techniques are used within RAG systems to mitigate hallucinations and addresses the gap by: (i) outlining a taxonomy of hallucination types in RAG systems, (ii) presenting a unified pipeline for attribution techniques, (iii) reviewing techniques based on the hallucinations they target, and (iv) discussing strengths and weaknesses with practical guidelines. This work offers insights for future research and practical use of attribution techniques in RAG systems. --- ### Scalable Board Expansion within a General Game System Authors: Clémentine Sacré Published: 2026-01-10 Categories: cs.AI, cs.GT, cs.SE arXiv: https://arxiv.org/abs/2601.16216v1 This thesis explores the use of a General Game System (GGS) to support the automatic expansion of game boards in boardless games. Traditional implementations of such games often rely on oversized static boards defined from the start, even though large portions of these boards may never be used during gameplay. This approach leads to unnecessary complexity. To address this issue, this thesis propose a dynamic board expansion mechanism in which the game board grows automatically during play. --- ### An Explainable Market Integrity Monitoring System with Multi-Source Attention Signals and Transparent Scoring Authors: Sandeep Neela Published: 2026-01-10 Categories: q-fin.RM, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2601.15304v1 Market integrity monitoring is difficult because suspicious price/volume behavior can arise from many benign mechanisms, while modern detection systems often rely on opaque models that are hard to audit and communicate. We present AIMM-X, an explainable monitoring pipeline that combines market microstructure-style signals derived from OHLCV time series with multi-source public attention signals (e.g., news and online discussion proxies) to surface time windows that merit analyst review. The system detects candidate anomalous windows using transparent thresholding and aggregation, then assigns an interpretable integrity score decomposed into a small set of additive components, allowing practitioners to trace why a window was flagged and which factors drove the score. We provide an end-to-end, reproducible implementation that downloads data, constructs attention features, builds unified panels, detects windows, computes component signals, and generates summary figures/tables. Our goal is not to label manipulation, but to provide a practical, auditable screening tool that supports downstream investigation by compliance teams, exchanges, or researchers. --- ### Quality or Quantity? Error-Informed Selective Online Learning with Gaussian Processes in Multi-Agent Systems: Extended Version Authors: Zewen Yang, Xiaobing Dai, Jiajun Cheng, Yulong Huang, Peng Shi Published: 2026-01-10 Categories: cs.LG, cs.MA arXiv: https://arxiv.org/abs/2601.14275v1 Effective cooperation is pivotal in distributed learning for multi-agent systems, where the interplay between the quantity and quality of the machine learning models is crucial. This paper reveals the irrationality of indiscriminate inclusion of all models on agents for joint prediction, highlighting the imperative to prioritize quality over quantity in cooperative learning. Specifically, we present the first selective online learning framework for distributed Gaussian process (GP) regression, namely distributed error-informed GP (EIGP), that enables each agent to assess its neighboring collaborators, using the proposed selection function to choose the higher quality GP models with less prediction errors. Moreover, algorithmic enhancements are embedded within the EIGP, including a greedy algorithm (gEIGP) for accelerating prediction and an adaptive algorithm (aEIGP) for improving prediction accuracy. In addition, approaches for fast prediction and model update are introduced in conjunction with the error-informed quantification term iteration and a data deletion strategy to achieve real-time learning operations. Numerical simulations are performed to demonstrate the effectiveness of the developed methodology, showcasing its superiority over the state-of-the-art distributed GP methods with different benchmarks. --- ### Divide and Refine: Enhancing Multimodal Representation and Explainability for Emotion Recognition in Conversation Authors: Anh-Tuan Mai, Cam-Van Thi Nguyen, Duc-Trong Le Published: 2026-01-10 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2601.14274v1 Multimodal emotion recognition in conversation (MERC) requires representations that effectively integrate signals from multiple modalities. These signals include modality-specific cues, information shared across modalities, and interactions that emerge only when modalities are combined. In information-theoretic terms, these correspond to \emph{unique}, \emph{redundant}, and \emph{synergistic} contributions. An ideal representation should leverage all three, yet achieving such balance remains challenging. Recent advances in contrastive learning and augmentation-based methods have made progress, but they often overlook the role of data preparation in preserving these components. In particular, applying augmentations directly to raw inputs or fused embeddings can blur the boundaries between modality-unique and cross-modal signals. To address this challenge, we propose a two-phase framework \emph{\textbf{D}ivide and \textbf{R}efine} (\textbf{DnR}). In the \textbf{Divide} phase, each modality is explicitly decomposed into uniqueness, pairwise redundancy, and synergy. In the \textbf{Refine} phase, tailored objectives enhance the informativeness of these components while maintaining their distinct roles. The refined representations are plug-and-play compatible with diverse multimodal pipelines. Extensive experiments on IEMOCAP and MELD demonstrate consistent improvements across multiple MERC backbones. These results highlight the effectiveness of explicitly dividing, refining, and recombining multimodal representations as a principled strategy for advancing emotion recognition. Our implementation is available at https://github.com/mattam301/DnR-WACV2026 --- ### NoiseFormer -- Noise Diffused Symmetric Attention Transformer Authors: Phani Kumar, Nyshadham, Jyothendra Varma, Polisetty V R K, Aditya Rathore Published: 2026-01-10 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2601.11619v1 Transformer architecture has been very successful long runner in the field of Deep Learning (DL) and Large Language Models (LLM) because of its powerful attention-based learning and parallel-natured architecture. As the models grow gigantic in terms of memory footprint, difficulties in fitting the model on a device like a GPU or an AI accelerator give rise to the need for multiple computing devices thereby escalating the computing cost. This increased training/inference cost paved the way for efficient model size reduction/parametric reduction deploying Sparse Attention techniques. In this paper, we start analyzing one of the techniques of Sparse Attention called Symmetric Dot-Product Attention (referred to as Symmetric Attention) and propose a novel unified model architecture called Noise Diffused Symmetric Attention Transformer to enhance the model's performance. While maintaining the memory gains of Symmetric Attention, with minute overhead in terms of model parameters and computational overhead, the proposed model brings in enhanced performance in terms of accuracy and inference-time sampling. The proposed model is validated upon GPT2 base model and the results reflect the performance gains falling between plain Symmetric attention and GPT2 base model on a variety of GLUE benchmark tasks in terms of accuracy, with significant model size reduction with respect to the base model. --- ### Architecture Before the Formula: Individuating Neural Architecture Beyond the Composite Map Authors: Luis F. Rosario Freytes Published: 2026-01-10 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2601.11618v3 Neural architecture is often identified by module syntax, computation graphs, or the composite functions they realize. These descriptions answer different identity questions. We study the represented process available at a receiver: an actual factorization $B_j=G_jQ_j$ in which $Q_j(x)$ is the intermediate state supplied for further computation. Forgetting the presentation and retaining only $\ker Q_j$ yields the predecessor distinctions preserved at that cut. For a fixed branch, this extensional shadow exactly classifies unmarked surjective factorizations up to unique carrier re-presentation, but it does not determine marked receiver organization or the accessibility of retained information to restricted continuations. Under composition the relevant interface is $Q_{j,θ}A$, so downstream architectural distinctions depend on the states produced upstream. An exact two-token construction shows that local and attention schemas are distinction-equivalent after one injective prefix and inequivalent after another, even though neither prefix loses predecessor information. The result exposes a context dependence hidden by modular architecture labels and motivates architecture comparison at the represented-process level. --- ### PointSLAM++: Robust Dense Neural Gaussian Point Cloud-based SLAM Authors: Xu Wang, Boyao Han, Xiaojun Chen, Ying Liu, Ruihui Li Published: 2026-01-10 Categories: cs.CV, cs.GR, cs.RO arXiv: https://arxiv.org/abs/2601.11617v1 Real-time 3D reconstruction is crucial for robotics and augmented reality, yet current simultaneous localization and mapping(SLAM) approaches often struggle to maintain structural consistency and robust pose estimation in the presence of depth noise. This work introduces PointSLAM++, a novel RGB-D SLAM system that leverages a hierarchically constrained neural Gaussian representation to preserve structural relationships while generating Gaussian primitives for scene mapping. It also employs progressive pose optimization to mitigate depth sensor noise, significantly enhancing localization accuracy. Furthermore, it utilizes a dynamic neural representation graph that adjusts the distribution of Gaussian nodes based on local geometric complexity, enabling the map to adapt to intricate scene details in real time. This combination yields high-precision 3D mapping and photorealistic scene rendering. Experimental results show PointSLAM++ outperforms existing 3DGS-based SLAM methods in reconstruction accuracy and rendering quality, demonstrating its advantages for large-scale AR and robotics. --- ### Line-based Event Preprocessing: Towards Low-Energy Neuromorphic Computer Vision Authors: Amélie Gruel, Pierre Lewden, Adrien F. Vincent, Sylvain Saïghi Published: 2026-01-10 Categories: cs.NE, cs.AI, cs.CV, eess.IV arXiv: https://arxiv.org/abs/2601.10742v1 Neuromorphic vision made significant progress in recent years, thanks to the natural match between spiking neural networks and event data in terms of biological inspiration, energy savings, latency and memory use for dynamic visual data processing. However, optimising its energy requirements still remains a challenge within the community, especially for embedded applications. One solution may reside in preprocessing events to optimise data quantity thus lowering the energy cost on neuromorphic hardware, proportional to the number of synaptic operations. To this end, we extend an end-to-end neuromorphic line detection mechanism to introduce line-based event data preprocessing. Our results demonstrate on three benchmark event-based datasets that preprocessing leads to an advantageous trade-off between energy consumption and classification performance. Depending on the line-based preprocessing strategy and the complexity of the classification task, we show that one can maintain or increase the classification accuracy while significantly reducing the theoretical energy consumption. Our approach systematically leads to a significant improvement of the neuromorphic classification efficiency, thus laying the groundwork towards a more frugal neuromorphic computer vision thanks to event preprocessing. ---