# Research Papers — 2026-01 · bundle page 31 of 189

> Full-text markdown of papers #1501–1550 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/31
[← Previous bundle](https://aipod.dev/papers/archive/2026-01/page/30.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-01/page/32.md)

### MAD: Modality-Adaptive Decoding for Mitigating Cross-Modal Hallucinations in Multimodal Large Language Models

Authors: Sangyun Chung, Se Yeon Kim, Youngchae Chee, Yong Man Ro
Published: 2026-01-29
Categories: cs.AI
arXiv: https://arxiv.org/abs/2601.21181v2

Multimodal Large Language Models (MLLMs) suffer from cross-modal hallucinations, where one modality inappropriately influences generation about another, leading to fabricated output. This exposes a more fundamental deficiency in modality-interaction control. To address this, we propose Modality-Adaptive Decoding (MAD), a training-free method that adaptively weights modality-specific decoding branches based on task requirements. MAD leverages the model's inherent ability to self-assess modality relevance by querying which modalities are needed for each task. The extracted modality probabilities are then used to adaptively weight contrastive decoding branches, enabling the model to focus on relevant information while suppressing cross-modal interference. Extensive experiments on CMM and AVHBench demonstrate that MAD significantly reduces cross-modal hallucinations across multiple audio-visual language models (7.8\% and 2.0\% improvements for VideoLLaMA2-AV, 8.7\% and 4.7\% improvements for Qwen2.5-Omni). Our approach demonstrates that explicit modality awareness through self-assessment is crucial for robust multimodal reasoning, offering a principled extension to existing contrastive decoding methods. Our code is available at \href{https://github.com/top-yun/MAD}{https://github.com/top-yun/MAD}

---

### Enhancing Underwater Light Field Images via Global Geometry-aware Diffusion Process

Authors: Yuji Lin, Qian Zhao, Zongsheng Yue, Junhui Hou, Deyu Meng
Published: 2026-01-29
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.21179v2

This work studies the challenging problem of acquiring high-quality underwater images via 4-D light field (LF) imaging. To this end, we propose GeoDiff-LF, a novel diffusion-based framework built upon SD-Turbo to enhance underwater 4-D LF imaging by leveraging its spatial-angular structure. GeoDiff-LF consists of three key adaptations: (1) a modified U-Net architecture with convolutional and attention adapters to model geometric cues, (2) a geometry-guided loss function using tensor decomposition and progressive weighting to regularize global structure, and (3) an optimized sampling strategy with noise prediction to improve efficiency. By integrating diffusion priors and LF geometry, GeoDiff-LF effectively mitigates color distortion in underwater scenes. Extensive experiments demonstrate that our framework outperforms existing methods across both visual fidelity and quantitative performance, advancing the state-of-the-art in enhancing underwater imaging. The code will be publicly available at https://github.com/linlos1234/GeoDiff-LF.

---

### Flow Perturbation++: Multi-Step Unbiased Jacobian Estimation for High-Dimensional Boltzmann Sampling

Authors: Xin Peng, Ang Gao
Published: 2026-01-29
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.21177v1

The scalability of continuous normalizing flows (CNFs) for unbiased Boltzmann sampling remains limited in high-dimensional systems due to the cost of Jacobian-determinant evaluation, which requires $D$ backpropagation passes through the flow layers. Existing stochastic Jacobian estimators such as the Hutchinson trace estimator reduce computation but introduce bias, while the recently proposed Flow Perturbation method is unbiased yet suffers from high variance. We present \textbf{Flow Perturbation++}, a variance-reduced extension of Flow Perturbation that discretizes the probability-flow ODE and performs unbiased stepwise Jacobian estimation at each integration step. This multi-step construction retains the unbiasedness of Flow Perturbation while achieves substantially lower estimator variance. Integrated into a Sequential Monte Carlo framework, Flow Perturbation++ achieves significantly improved equilibrium sampling on a 1000D Gaussian Mixture Model and the all-atom Chignolin protein compared with Hutchinson-based and single-step Flow Perturbation baselines.

---

### Breaking the Reasoning Horizon in Entity Alignment Foundation Models

Authors: Yuanning Cui, Zequn Sun, Wei Hu, Kexuan Xin, Zhangjie Fu
Published: 2026-01-29
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.21174v3

Entity alignment (EA) is critical for knowledge graph (KG) fusion. Existing EA models lack transferability and are incapable of aligning unseen KGs without retraining. While using graph foundation models (GFMs) offer a solution, we find that directly adapting GFMs to EA remains largely ineffective. This stems from a critical "reasoning horizon gap": unlike link prediction in GFMs, EA necessitates capturing long-range dependencies across sparse and heterogeneous KG structuresTo address this challenge, we propose a EA foundation model driven by a parallel encoding strategy. We utilize seed EA pairs as local anchors to guide the information flow, initializing and encoding two parallel streams simultaneously. This facilitates anchor-conditioned message passing and significantly shortens the inference trajectory by leveraging local structural proximity instead of global search. Additionally, we incorporate a merged relation graph to model global dependencies and a learnable interaction module for precise matching. Extensive experiments verify the effectiveness of our framework, highlighting its strong generalizability to unseen KGs.

---

### Multimodal Benchmark for Safety Assessment in Industrial Inspection Scenarios

Authors: Zeyi Liu, Shuang Liu, Jihai Min, Zhaoheng Zhang, Jun Cen, Pengyu Han, Songqiao Hu, Zihan Meng, Xiao He, Donghua Zhou
Published: 2026-01-29
Categories: cs.RO, cs.CV
arXiv: https://arxiv.org/abs/2601.21173v2

With the rapid development of industrial intelligence and unmanned inspection, reliable perception and safety assessment for AI systems in complex and dynamic industrial sites has become a key bottleneck for deploying predictive maintenance and autonomous inspection. Most public datasets remain limited by simulated data sources, single-modality sensing, or the absence of fine-grained object-level annotations, which prevents robust scene understanding and multimodal safety reasoning for industrial foundation models. To address these limitations, InspecSafe-V1 is released as the first multimodal benchmark dataset for industrial inspection safety assessment that is collected from routine operations of real inspection robots in real-world environments. InspecSafe-V1 covers five representative industrial scenarios, including tunnels, power facilities, sintering equipment, oil and gas petrochemical plants, and coal conveyor trestles. The dataset is constructed from 41 wheeled and rail-mounted inspection robots operating at 2,239 valid inspection sites, yielding 5,013 inspection instances. For each instance, pixel-level segmentation annotations are provided for key objects in visible-spectrum images. In addition, a semantic scene description and a corresponding safety level label are provided according to practical inspection tasks. Seven synchronized sensing modalities are further included, including infrared video, audio, depth point clouds, radar point clouds, gas measurements, temperature, and humidity, to support multimodal anomaly recognition, cross-modal fusion, and comprehensive safety assessment in industrial environments.

---

### AC2L-GAD: Active Counterfactual Contrastive Learning for Graph Anomaly Detection

Authors: Kamal Berahmand, Saman Forouzandeh, Mehrnoush Mohammadi, Parham Moradi, Mahdi Jalili
Published: 2026-01-29
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2601.21171v1

Graph anomaly detection aims to identify abnormal patterns in networks, but faces significant challenges from label scarcity and extreme class imbalance. While graph contrastive learning offers a promising unsupervised solution, existing methods suffer from two critical limitations: random augmentations break semantic consistency in positive pairs, while naive negative sampling produces trivial, uninformative contrasts. We propose AC2L-GAD, an Active Counterfactual Contrastive Learning framework that addresses both limitations through principled counterfactual reasoning. By combining information-theoretic active selection with counterfactual generation, our approach identifies structurally complex nodes and generates anomaly-preserving positive augmentations alongside normal negative counterparts that provide hard contrasts, while restricting expensive counterfactual generation to a strategically selected subset. This design reduces computational overhead by approximately 65% compared to full-graph counterfactual generation while maintaining detection quality. Experiments on nine benchmark datasets, including real-world financial transaction graphs from GADBench, show that AC2L-GAD achieves competitive or superior performance compared to state-of-the-art baselines, with notable gains in datasets where anomalies exhibit complex attribute-structure interactions.

---

### The Powers of Precision: Structure-Informed Detection in Complex Systems -- From Customer Churn to Seizure Onset

Authors: Augusto Santos, Teresa Santos, Catarina Rodrigues, José M. F. Moura
Published: 2026-01-29
Categories: cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2601.21170v3

Emergent phenomena -- onset of epileptic seizures, sudden customer churn, or pandemic outbreaks -- often arise from hidden causal interactions in complex systems. We propose a machine learning method for their early detection that addresses a core challenge: unveiling and harnessing a system's latent causal structure despite the data-generating process being unknown and partially observed. The method learns an optimal feature representation from a one-parameter family of estimators -- powers of the empirical covariance or precision matrix -- offering a principled way to tune in to the underlying structure driving the emergence of critical events. A supervised learning module then classifies the learned representation. We prove structural consistency of the family and demonstrate the empirical soundness of our approach on seizure detection and churn prediction, attaining competitive results in both. Beyond prediction, and toward explainability, we ascertain that the optimal covariance power exhibits evidence of good identifiability while capturing structural signatures, thus reconciling predictive performance with interpretable statistical structure.

---

### Output-Space Search: Targeting LLM Generations in a Frozen Encoder-Defined Output Space

Authors: Tobias Materzok
Published: 2026-01-29
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2601.21169v1

We introduce Output-Space Search (OS-Search), which turns LLM generation into endpoint search. An outer loop selects a target z* in a frozen encoder-defined 3D output space Z, and a retrieval-grounded policy trained with sequence-level RL generates outputs whose coordinates land near z* under standard autoregressive decoding. This enables parallel sweeps and black-box optimization in Z without path-dependent token/program search. On stories, sweeping Z (text) yields 3.1x higher LLM-scored diversity than prompt-chaining. On code, Bayesian optimization over Z (code) improves an objective withheld from the controller under matched inference budgets while preserving validity.

---

### Learning What to Recommend: Minimax Optimal Simple Regret in Logistic Bandits

Authors: Shuai Liu, Alireza Bakhtiari, Alex Ayoub, Botao Hao, Csaba Szepesvári
Published: 2026-01-29
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.21167v2

We study stochastic logistic bandits with $d$-dimensional action features under the simple-regret objective, where a learner uses $T$ rounds of exploration to output a single final action. The logistic structure is essential here: because the informativeness of an action depends on the local curvature of the sigmoid, actions that are best for immediate reward need not be the most useful for identifying the best final recommendation. We show that the first-order minimax difficulty is governed by $κ_*$, the inverse slope of the sigmoid at the optimal action. The lower bound is realized by a shifted saturated hard family in which saturation simultaneously limits the information available about the final decision and controls the value loss from a wrong recommendation. This reveals a hard mechanism distinct from cumulative-regret constructions, even though online-to-batch reductions recover the same leading order in expectation. We then develop two curvature-aware algorithms: \MULog, a pure-exploration method whose final recommendation satisfies a high-probability upper bound of order $\tilde O(d/\sqrt{κ_* T})$, matching the lower bound up to logarithmic factors, and \THATS, a Thompson-sampling-style method that provides a computationally lighter alternative. Experiments on both hard and easy geometries support the same picture: informative low-reward actions can make instances substantially easier, and the curvature-aware methods exploit this structure especially effectively.

---

### FrontierScience: Evaluating AI's Ability to Perform Expert-Level Scientific Tasks

Authors: Miles Wang, Robi Lin, Kat Hu, Joy Jiao, Neil Chowdhury, Ethan Chang, Tejal Patwardhan
Published: 2026-01-29
Categories: cs.AI, cs.CY, cs.LG
arXiv: https://arxiv.org/abs/2601.21165v1

We introduce FrontierScience, a benchmark evaluating expert-level scientific reasoning in frontier language models. Recent model progress has nearly saturated existing science benchmarks, which often rely on multiple-choice knowledge questions or already published information. FrontierScience addresses this gap through two complementary tracks: (1) Olympiad, consisting of international olympiad problems at the level of IPhO, IChO, and IBO, and (2) Research, consisting of PhD-level, open-ended problems representative of sub-tasks in scientific research. FrontierScience contains several hundred questions (including 160 in the open-sourced gold set) covering subfields across physics, chemistry, and biology, from quantum electrodynamics to synthetic organic chemistry. All Olympiad problems are originally produced by international Olympiad medalists and national team coaches to ensure standards of difficulty, originality, and factuality. All Research problems are research sub-tasks written and verified by PhD scientists (doctoral candidates, postdoctoral researchers, or professors). For Research, we introduce a granular rubric-based evaluation framework to assess model capabilities throughout the process of solving a research task, rather than judging only a standalone final answer.

---

### Concise Geometric Description as a Bridge: Unleashing the Potential of LLM for Plane Geometry Problem Solving

Authors: Jingyun Wang, Dian Li, Xiaohan Wang, Gang Liu, Jiahong Yan, Guoliang Kang
Published: 2026-01-29
Categories: cs.AI
arXiv: https://arxiv.org/abs/2601.21164v3

Plane Geometry Problem Solving (PGPS) is a multimodal reasoning task that aims to solve a plane geometric problem based on a geometric diagram and problem textual descriptions. Although Large Language Models (LLMs) possess strong reasoning skills, their direct application to PGPS is hindered by their inability to process visual diagrams. Existing works typically fine-tune Multimodal LLMs (MLLMs) end-to-end on large-scale PGPS data to enhance visual understanding and reasoning simultaneously. However, such joint optimization may compromise base LLMs' inherent reasoning capability. In this work, we observe that LLM itself is potentially a powerful PGPS solver when appropriately formulating visual information as textual descriptions. We propose to train a MLLM Interpreter to generate geometric descriptions for the visual diagram, and an off-the-shelf LLM is utilized to perform reasoning. Specifically, we choose Conditional Declaration Language (CDL) as the geometric description as its conciseness eases the MLLM Interpreter training. The MLLM Interpreter is fine-tuned via CoT (Chain-of-Thought)-augmented SFT followed by GRPO to generate CDL. Instead of using a conventional solution-based reward that compares the reasoning result with the ground-truth answer, we design CDL matching rewards to facilitate more effective GRPO training, which provides more direct and denser guidance for CDL generation. To support training, we construct a new dataset, Formalgeo7k-Rec-CoT, by manually reviewing Formalgeo7k v2 and incorporating CoT annotations. Extensive experiments on Formalgeo7k-Rec-CoT, Unigeo, and MathVista show our method (finetuned on only 5.5k data) performs favorably against leading open-source and closed-source MLLMs.

---

### A2RAG: Adaptive Agentic Graph Retrieval for Cost-Aware and Reliable Reasoning

Authors: Jiate Liu, Zebin Chen, Shaobo Qiao, Mingchen Ju, Danting Zhang, Bocheng Han, Shuyue Yu, Xin Shu, Jinglin Wu, Dong Wen, Xin Cao, Guanfeng Liu et al.
Published: 2026-01-29
Categories: cs.IR, cs.AI, cs.DB
arXiv: https://arxiv.org/abs/2601.21162v2

Graph Retrieval-Augmented Generation (Graph-RAG) enhances multihop question answering by organizing corpora into knowledge graphs and routing evidence through relational structure. However, practical deployments face two persistent bottlenecks: (i) mixed-difficulty workloads where one-size-fits-all retrieval either wastes cost on easy queries or fails on hard multihop cases, and (ii) extraction loss, where graph abstraction omits fine-grained qualifiers that remain only in source text. We present A2RAG, an adaptive-and-agentic GraphRAG framework for cost-aware and reliable reasoning. A2RAG couples an adaptive controller that verifies evidence sufficiency and triggers targeted refinement only when necessary, with an agentic retriever that progressively escalates retrieval effort and maps graph signals back to provenance text to remain robust under extraction loss and incomplete graphs. Experiments on HotpotQA and 2WikiMultiHopQA demonstrate that A2RAG achieves +9.9/+11.8 absolute gains in Recall@2, while cutting token consumption and end-to-end latency by about 50% relative to iterative multihop baselines.

---

### A Federated Generalized Expectation-Maximization Algorithm for Mixture Models with an Unknown Number of Components

Authors: Michael Ibrahim, Nagi Gebraeel, Weijun Xie
Published: 2026-01-29
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.21160v1

We study the problem of federated clustering when the total number of clusters $K$ across clients is unknown, and the clients have heterogeneous but potentially overlapping cluster sets in their local data. To that end, we develop FedGEM: a federated generalized expectation-maximization algorithm for the training of mixture models with an unknown number of components. Our proposed algorithm relies on each of the clients performing EM steps locally, and constructing an uncertainty set around the maximizer associated with each local component. The central server utilizes the uncertainty sets to learn potential cluster overlaps between clients, and infer the global number of clusters via closed-form computations. We perform a thorough theoretical study of our algorithm, presenting probabilistic convergence guarantees under common assumptions. Subsequently, we study the specific setting of isotropic GMMs, providing tractable, low-complexity computations to be performed by each client during each iteration of the algorithm, as well as rigorously verifying assumptions required for algorithm convergence. We perform various numerical experiments, where we empirically demonstrate that our proposed method achieves comparable performance to centralized EM, and that it outperforms various existing federated clustering methods.

---

### Spatial-Regularization-Aware Dual-Branch Collaborative Inference for Training-Free OVSS in Remote Sensing Imagery

Authors: Jianzheng Wang, Huan Ni
Published: 2026-01-29
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.21159v2

High-resolution remote sensing images contain densely distributed objects with pronounced scale variations and complex boundaries, which impose higher demands on both the geometric localization and semantic prediction capabilities of semantic segmentation models. Existing training-free open-vocabulary semantic segmentation (OVSS) methods typically fuse Contrastive Language-Image Pretraining (CLIP) and vision foundation models (VFMs) using one-way injection and shallow post-processing strategies, making it difficult to satisfy these requirements. To address this issue, we propose a spatial-regularization-aware dual-branch collaborative inference framework for training-free OVSS, termed SDCI. First, during feature encoding, SDCI introduces a cross-model attention fusion (CAF) module, which guides collaborative inference by injecting self-attention maps into each other. Second, we propose a bidirectional cross-graph diffusion refinement (BCDR) module that enhances the reliability of dual-branch segmentation scores through iterative random-walk diffusion. Finally, we incorporate low-level superpixel structures and develop a convex-optimization-based superpixel collaborative prediction (CSCP) mechanism to further refine object boundaries. Experiments on multiple remote sensing semantic segmentation benchmarks demonstrate that our method achieves better performance than existing approaches. Our code is available at https://github.com/yu-ni1989/SDCI.

---

### Bridging the Arithmetic Gap: The Cognitive Complexity Benchmark and Financial-PoT for Robust Financial Reasoning

Authors: Boxiang Zhao, Qince Li, Zhonghao Wang, Yi Wang, Peng Cheng, Bo Lin
Published: 2026-01-29
Categories: cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2601.21157v1

While Large Language Models excel at semantic tasks, they face a critical bottleneck in financial quantitative reasoning, frequently suffering from "Arithmetic Hallucinations" and a systemic failure mode we term "Cognitive Collapse". To strictly quantify this phenomenon, we introduce the Cognitive Complexity Benchmark (CCB), a robust evaluation framework grounded in a dataset constructed from 95 real-world Chinese A-share annual reports. Unlike traditional datasets, the CCB stratifies financial queries into a three-dimensional taxonomy, Data Source, Mapping Difficulty, and Result Unit, enabling the precise diagnosis of reasoning degradation in high-cognitive-load scenarios. To address these failures, we propose the Iterative Dual-Phase Financial-PoT framework. This neuro-symbolic architecture enforces a strict architectural decoupling: it first isolates semantic variable extraction and logic formulation, then offloads computation to an iterative, self-correcting Python sandbox to ensure deterministic execution. Evaluation on the CCB demonstrates that while standard Chain-of-Thought falters on complex tasks, our approach offers superior robustness, elevating the Qwen3-235B model's average accuracy from 59.7\% to 67.3\% and achieving gains of up to 10-fold in high-complexity reasoning tasks. These findings suggest that architectural decoupling is a critical enabling factor for improving reliability in financial reasoning tasks, providing a transferable architectural insight for precision-critical domains that require tight alignment between semantic understanding and quantitative computation.

---

### A new strategy for finite-sample valid prediction of future insurance claims in the regression setting

Authors: Liang Hong
Published: 2026-01-29
Categories: stat.AP, cs.LG
arXiv: https://arxiv.org/abs/2601.21153v1

The extant insurance literature demonstrates a paucity of finite-sample valid prediction intervals of future insurance claims in the regression setting. To address this challenge, this article proposes a new strategy that converts a predictive method in the unsupervised iid (independent identically distributed) setting to a predictive method in the regression setting. In particular, it enables an actuary to obtain infinitely many finite-sample valid prediction intervals in the regression setting.

---

### Learning to Advect: A Neural Semi-Lagrangian Architecture for Weather Forecasting

Authors: Carlos A. Pereira, Stéphane Gaudreault, Valentin Dallerit, Christopher Subich, Shoyon Panday, Siqi Wei, Sasa Zhang, Siddharth Rout, Eldad Haber, Raymond J. Spiteri, David Millard
Published: 2026-01-29
Categories: cs.LG, physics.ao-ph
arXiv: https://arxiv.org/abs/2601.21151v3

Machine-learning approaches to weather forecasting often employ a monolithic architecture in which distinct physical mechanisms, such as advection, diffusive mixing, thermodynamic processes, and forcing, are represented implicitly within a single large neural network. This is particularly problematic for advection, where long-range transport typically requires expensive global interaction mechanisms or deep stacks of local convolutional layers. To address this limitation, we introduce a physics-inspired neural architecture that decomposes latent-state evolution into dedicated advection, diffusion, and reaction operators. Its central component is a Neural Semi-Lagrangian operator that performs trajectory-based transport via differentiable interpolation on the sphere, allowing the network to learn both a compressed set of latent modes to be transported and their characteristic trajectories. The atmospheric state is projected into latent space and spatially coarsened to a processor grid, where advection, diffusion, and reaction operators jointly evolve the representation. Diffusive mixing and unresolved dissipation are represented by depthwise-separable spatial mixing, while local source terms and vertical interactions are handled through pointwise channel interactions. We evaluate a reference implementation of the proposed architecture on global weather forecasting. Evaluated on ERA5 benchmarks, the reference model achieves competitive deterministic forecast skill, with particularly strong performance at short to medium lead times, while preserving improved spectral fidelity and forecast activity relative to several leading data-driven baselines.

---

### Can Neural Networks Learn Small Algebraic Worlds? An Investigation Into the Group-theoretic Structures Learned By Narrow Models Trained To Predict Group Operations

Authors: Henry Kvinge, Andrew Aguilar, Nayda Farnsworth, Grace O'Brien, Robert Jasper, Sarah Scullen, Helen Jenne
Published: 2026-01-29
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2601.21150v1

While a real-world research program in mathematics may be guided by a motivating question, the process of mathematical discovery is typically open-ended. Ideally, exploration needed to answer the original question will reveal new structures, patterns, and insights that are valuable in their own right. This contrasts with the exam-style paradigm in which the machine learning community typically applies AI to math. To maximize progress in mathematics using AI, we will need to go beyond simple question answering. With this in mind, we explore the extent to which narrow models trained to solve a fixed mathematical task learn broader mathematical structure that can be extracted by a researcher or other AI system. As a basic test case for this, we use the task of training a neural network to predict a group operation (for example, performing modular arithmetic or composition of permutations). We describe a suite of tests designed to assess whether the model captures significant group-theoretic notions such as the identity element, commutativity, or subgroups. Through extensive experimentation we find evidence that models learn representations capable of capturing abstract algebraic properties. For example, we find hints that models capture the commutativity of modular arithmetic. We are also able to train linear classifiers that reliably distinguish between elements of certain subgroups (even though no labels for these subgroups are included in the data). On the other hand, we are unable to extract notions such as the concept of the identity element. Together, our results suggest that in some cases the representations of even small neural networks can be used to distill interesting abstract structure from new mathematical objects.

---

### Mobility-Embedded POIs: Learning What A Place Is and How It Is Used from Human Movement

Authors: Maria Despoina Siampou, Shushman Choudhury, Shang-Ling Hsu, Neha Arora, Cyrus Shahabi
Published: 2026-01-29
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2601.21149v3

Recent progress in geospatial foundation models highlights the importance of learning general-purpose representations for real-world locations, particularly points-of-interest (POIs) where human activity concentrates. Existing approaches, however, focus primarily on place identity derived from static textual metadata, or learn representations tied to trajectory context, which capture movement regularities rather than how places are actually used (i.e., POI's function). We argue that POI function is a missing but essential signal for general POI representations. We introduce Mobility-Embedded POIs (ME-POIs), a framework that augments POI embeddings derived, from language models with large-scale human mobility data to learn POI-centric, context-independent representations grounded in real-world usage. ME-POIs encodes individual visits as temporally contextualized embeddings and aligns them with learnable POI representations via contrastive learning to capture usage patterns across users and time. To address long-tail sparsity, we propose a novel mechanism that propagates temporal visit patterns from nearby, frequently visited POIs across multiple spatial scales. We evaluate ME-POIs on five newly proposed map enrichment tasks, testing its ability to capture both the identity and function of POIs. Across all tasks, augmenting text-based embeddings with ME-POIs consistently outperforms both text-only and mobility-only baselines. Notably, ME-POIs trained on mobility data alone can surpass text-only models on certain tasks, highlighting that POI function is a critical component of accurate and generalizable POI representations.

---

### BrainStack: Neuro-MoE with Functionally Guided Expert Routing for EEG-Based Language Decoding

Authors: Ziyi Zhao, Jinzhao Zhou, Xiaowei Jiang, Beining Cao, Wenhao Ma, Yang Shen, Ren Li, Yu-Kai Wang, Chin-teng Lin
Published: 2026-01-29
Categories: cs.AI
arXiv: https://arxiv.org/abs/2601.21148v1

Decoding linguistic information from electroencephalography (EEG) remains challenging due to the brain's distributed and nonlinear organization. We present BrainStack, a functionally guided neuro-mixture-of-experts (Neuro-MoE) framework that models the brain's modular functional architecture through anatomically partitioned expert networks. Each functional region is represented by a specialized expert that learns localized neural dynamics, while a transformer-based global expert captures cross-regional dependencies. A learnable routing gate adaptively aggregates these heterogeneous experts, enabling context-dependent expert coordination and selective fusion. To promote coherent representation across the hierarchy, we introduce cross-regional distillation, where the global expert provides top-down regularization to the regional experts. We further release SilentSpeech-EEG (SS-EEG), a large-scale benchmark comprising over 120 hours of EEG recordings from 12 subjects performing 24 silent words, the largest dataset of its kind. Experiments demonstrate that BrainStack consistently outperforms state-of-the-art models, achieving superior accuracy and generalization across subjects. Our results establish BrainStack as a functionally modular, neuro-inspired MoE paradigm that unifies neuroscientific priors with adaptive expert routing, paving the way for scalable and interpretable brain-language decoding.

---

### Smooth Dynamic Cutoffs for Machine Learning Interatomic Potentials

Authors: Kevin Han, Haolin Cong, Bowen Deng, Amir Barati Farimani
Published: 2026-01-29
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.21147v1

Machine learning interatomic potentials (MLIPs) have proven to be wildly useful for molecular dynamics simulations, powering countless drug and materials discovery applications. However, MLIPs face two primary bottlenecks preventing them from reaching realistic simulation scales: inference time and memory consumption. In this work, we address both issues by challenging the long-held belief that the cutoff radius for the MLIP must be held to a fixed, constant value. For the first time, we introduce a dynamic cutoff formulation that still leads to stable, long timescale molecular dynamics simulation. In introducing the dynamic cutoff, we are able to induce sparsity onto the underlying atom graph by targeting a specific number of neighbors per atom, significantly reducing both memory consumption and inference time. We show the effectiveness of a dynamic cutoff by implementing it onto 4 state of the art MLIPs: MACE, Nequip, Orbv3, and TensorNet, leading to 2.26x less memory consumption and 2.04x faster inference time, depending on the model and atomic system. We also perform an extensive error analysis and find that the dynamic cutoff models exhibit minimal accuracy dropoff compared to their fixed cutoff counterparts on both materials and molecular datasets. All model implementations and training code will be fully open sourced.

---

### Maxwait: A Generalized Mechanism for Distributed Time-Sensitive Systems

Authors: Francesco Paladino, Shulu Li, Edward A. Lee
Published: 2026-01-29
Categories: cs.DC, cs.CL
arXiv: https://arxiv.org/abs/2601.21146v1

Distributed time-sensitive systems must balance timing requirements (availability) and consistency in the presence of communication delays and synchronization uncertainty. This paper presents maxwait, a simple coordination mechanism with surprising generality that makes these tradeoffs explicit and configurable. We demonstrate that this mechanism subsumes classical distributed system methods such as PTIDES, Chandy-and-Misra with or without null messages, Jefferson's Time-Warp, and Lamport's time-based fault detection, while enabling real-time behavior in distributed cyber-physical applications. The mechanism can also realize many commonly used distributed system patterns, including logical execution time (LET), publish and subscribe, actors, conflict-free replicated data types (CRDTs), and remote procedure calls with futures. More importantly, it adds to these mechanisms better control over timing, bounded time fault detection, and the option of making them more deterministic, all within a single semantic framework. Implemented as an extension of the Lingua Franca coordination language, maxwait enforces logical-time consistency when communication latencies are bounded and provides structured fault handling when bounds are violated.

---

### Optimization and Mobile Deployment for Anthropocene Neural Style Transfer

Authors: Po-Hsun Chen, Ivan C. H. Liu
Published: 2026-01-29
Categories: cs.HC, cs.AI, cs.GR
arXiv: https://arxiv.org/abs/2601.21141v1

This paper presents AnthropoCam, a mobile-based neural style transfer (NST) system optimized for the visual synthesis of Anthropocene environments. Unlike conventional artistic NST, which prioritizes painterly abstraction, stylizing human-altered landscapes demands a careful balance between amplifying material textures and preserving semantic legibility. Industrial infrastructures, waste accumulations, and modified ecosystems contain dense, repetitive patterns that are visually expressive yet highly susceptible to semantic erosion under aggressive style transfer. To address this challenge, we systematically investigate the impact of NST parameter configurations on the visual translation of Anthropocene textures, including feature layer selection, style and content loss weighting, training stability, and output resolution. Through controlled experiments, we identify an optimal parameter manifold that maximizes stylistic expression while preventing semantic erasure. Our results demonstrate that appropriate combinations of convolutional depth, loss ratios, and resolution scaling enable the faithful transformation of anthropogenic material properties into a coherent visual language. Building on these findings, we implement a low-latency, feed-forward NST pipeline deployed on mobile devices. The system integrates a React Native frontend with a Flask-based GPU backend, achieving high-resolution inference within 3-5 seconds on general mobile hardware. This enables real-time, in-situ visual intervention at the site of image capture, supporting participatory engagement with Anthropocene landscapes. By coupling domain-specific NST optimization with mobile deployment, AnthropoCam reframes neural style transfer as a practical and expressive tool for real-time environmental visualization in the Anthropocene.

---

### EnsembleLink: Accurate Record Linkage Without Training Data

Authors: Noah Dasanaike
Published: 2026-01-29
Categories: cs.CL
arXiv: https://arxiv.org/abs/2601.21138v2

Record linkage, the process of matching records that refer to the same entity across datasets, is essential to empirical social science but remains methodologically underdeveloped. Researchers treat it as a preprocessing step, applying ad hoc rules without quantifying the uncertainty that linkage errors introduce into downstream analyses. Existing methods either achieve low accuracy or require substantial labeled training data. I present EnsembleLink, a method that achieves high accuracy without any training labels. EnsembleLink leverages pre-trained language models that have learned semantic relationships (e.g., that "South Ozone Park" is a neighborhood in "New York City" or that "Lutte ouvriere" refers to the Trotskyist "Workers' Struggle" party) from large text corpora. On benchmarks spanning city names, person names, organizations, multilingual political parties, and bibliographic records, EnsembleLink matches or exceeds methods requiring extensive labeling. The method runs locally on open-source models, requiring no external API calls, and completes typical linkage tasks in minutes.

---

### TRACE: Trajectory Recovery for Continuous Mechanism Evolution in Causal Representation Learning

Authors: Shicheng Fan, Kun Zhang, Lu Cheng
Published: 2026-01-29
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.21135v2

Temporal causal representation learning methods assume that causal mechanisms switch instantaneously between discrete domains, yet real-world systems often exhibit continuous mechanism transitions. For example, a vehicle's dynamics evolve gradually through a turning maneuver, and human gait shifts smoothly from walking to running. We formalize this setting by modeling transitional mechanisms as convex combinations of finitely many atomic mechanisms, governed by time-varying mixing coefficients. Our theoretical contributions establish that both the latent causal variables and the continuous mixing trajectory are jointly identifiable. We further propose TRACE, a Mixture-of-Experts framework where each expert learns one atomic mechanism during training, enabling recovery of mechanism trajectories at test time. This formulation generalizes to intermediate mechanism states never observed during training. Experiments on synthetic and real-world data demonstrate that TRACE recovers mixing trajectories with up to 0.99 correlation, substantially outperforming discrete-switching baselines.

---

### Large Language Models Naively Recover Ethnicity from Individual Records

Authors: Noah Dasanaike
Published: 2026-01-29
Categories: cs.CL
arXiv: https://arxiv.org/abs/2601.21132v1

I demonstrate that large language models can infer ethnicity from names with accuracy exceeding that of Bayesian Improved Surname Geocoding (BISG) without additional training data, enabling inference outside the United States and to contextually appropriate classification categories. Using stratified samples from Florida and North Carolina voter files with self-reported race, LLM-based classification achieves up to 84.7% accuracy, outperforming BISG (68.2%) on balanced samples. I test six models including Gemini 3 Flash, GPT-4o, and open-source alternatives such as DeepSeek v3.2 and GLM-4.7. Enabling extended reasoning can improve accuracy by 1-3 percentage points, though effects vary across contexts; including metadata such as party registration reaches 86.7%. LLM classification also reduces the income bias inherent in BISG, where minorities in wealthier neighborhoods are systematically misclassified as White. I further validate using Lebanese voter registration with religious sect (64.3% accuracy), Indian MPs from reserved constituencies (99.2%), and Indian land records with caste classification (74.0%). Aggregate validation across India, Uganda, Nepal, Armenia, Chile, and Costa Rica using original full-count voter rolls demonstrates that the method recovers known population distributions where naming conventions are distinctive. For large-scale applications, small transformer models fine-tuned on LLM labels exceed BISG accuracy while enabling local deployment at no cost.

---

### Thompson sampling: Precise arm-pull dynamics and adaptive inference

Authors: Qiyang Han
Published: 2026-01-29
Categories: math.ST, cs.IT, cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2601.21131v1

Adaptive sampling schemes are well known to create complex dependence that may invalidate conventional inference methods. A recent line of work shows that this need not be the case for UCB-type algorithms in multi-armed bandits. A central emerging theme is a `stability' property with asymptotically deterministic arm-pull counts in these algorithms, making inference as easy as in the i.i.d. setting. In this paper, we study the precise arm-pull dynamics in another canonical class of Thompson-sampling type algorithms. We show that the phenomenology is qualitatively different: the arm-pull count is asymptotically deterministic if and only if the arm is suboptimal or is the unique optimal arm; otherwise it converges in distribution to the unique invariant law of an SDE. This dichotomy uncovers a unifying principle behind many existing (in)stability results: an arm is stable if and only if its interaction with statistical noise is asymptotically negligible. As an application, we show that normalized arm means obey the same dichotomy, with Gaussian limits for stable arms and a semi-universal, non-Gaussian limit for unstable arms. This not only enables the construction of confidence intervals for the unknown mean rewards despite non-normality, but also reveals the potential of developing tractable inference procedures beyond the stable regime. The proofs rely on two new approaches. For suboptimal arms, we develop an `inverse process' approach that characterizes the inverse of the arm-pull count process via a Stieltjes integral. For optimal arms, we adopt a reparametrization of the arm-pull and noise processes that reduces the singularity in the natural SDE to proving the uniqueness of the invariant law of another SDE. We prove the latter by a set of analytic tools, including the parabolic Hörmander condition and the Stroock-Varadhan support theorem.

---

### What You Feel Is Not What They See: On Predicting Self-Reported Emotion from Third-Party Observer Labels

Authors: Yara El-Tawil, Aneesha Sampath, Emily Mower Provost
Published: 2026-01-29
Categories: cs.AI
arXiv: https://arxiv.org/abs/2601.21130v1

Self-reported emotion labels capture internal experience, while third-party labels reflect external perception. These perspectives often diverge, limiting the applicability of third-party-trained models to self-report contexts. This gap is critical in mental health, where accurate self-report modeling is essential for guiding intervention. We present the first cross-corpus evaluation of third-party-trained models on self-reports. We find activation unpredictable (CCC approximately 0) and valence moderately predictable (CCC approximately 0.3). Crucially, when content is personally significant to the speaker, models achieve high performance for valence (CCC approximately 0.6-0.8). Our findings point to personal significance as a key pathway for aligning external perception with internal experience and underscore the challenge of self-report activation modeling.

---

### Beyond a Single Reference: Training and Evaluation with Paraphrases in Sign Language Translation

Authors: Václav Javorek, Tomáš Železný, Alessa Carbo, Marek Hrúz, Ivan Gruber
Published: 2026-01-29
Categories: cs.AI
arXiv: https://arxiv.org/abs/2601.21128v1

Most Sign Language Translation (SLT) corpora pair each signed utterance with a single written-language reference, despite the highly non-isomorphic relationship between sign and spoken languages, where multiple translations can be equally valid. This limitation constrains both model training and evaluation, particularly for n-gram-based metrics such as BLEU. In this work, we investigate the use of Large Language Models to automatically generate paraphrased variants of written-language translations as synthetic alternative references for SLT. First, we compare multiple paraphrasing strategies and models using an adapted ParaScore metric. Second, we study the impact of paraphrases on both training and evaluation of the pose-based T5 model on the YouTubeASL and How2Sign datasets. Our results show that naively incorporating paraphrases during training does not improve translation performance and can even be detrimental. In contrast, using paraphrases during evaluation leads to higher automatic scores and better alignment with human judgments. To formalize this observation, we introduce BLEUpara, an extension of BLEU that evaluates translations against multiple paraphrased references. Human evaluation confirms that BLEUpara correlates more strongly with perceived translation quality. We release all generated paraphrases, generation and evaluation code to support reproducible and more reliable evaluation of SLT systems.

---

### Equity Bias: An Ethical Framework for AI Design

Authors: Mary Lockwood
Published: 2026-01-28
Categories: cs.CY, cs.AI
arXiv: https://arxiv.org/abs/2604.21907v1

Equity Bias is a philosophical and practical framework for building smarter, more equitable AI systems. Grounded in hermeneutic philosophy and epistemic injustice theory, it treats bias not as an error to eliminate but as a reflection of whose knowledge is encoded into systems. While traditional approaches aim to reduce or remove bias, Equity Bias instead makes bias transparent and contestable. In doing so, it broadens whose perspectives shape AI and provides a lens for understanding AI systems as interpretive agents. The framework introduces a three-phase AI Life Cycle methodology: 'Equity Archaeology' (mapping knowledge and assumptions), 'Co-Creating Meaning' (participatory design), and 'Ongoing Accountability' (continuous evaluation). Equity Bias guides developers, researchers, and policymakers towards AI that is ethically accountable and capable of addressing complex real-world challenges.

---

### Spatiotemporal Robustness of Temporal Logic Tasks using Multi-Objective Reasoning

Authors: Oliver Schön, Lars Lindemann
Published: 2026-01-28
Categories: cs.AI, cs.LO
arXiv: https://arxiv.org/abs/2603.29868v2

The reliability of autonomous systems depends on their robustness, i.e., their ability to meet their objectives under uncertainty. In this paper, we study spatiotemporal robustness of temporal logic specifications evaluated over discrete-time signals. Existing work has proposed robust semantics that capture not only Boolean satisfiability, but also the geometric distance from unsatisfiability, corresponding to admissible spatial perturbations of a given signal. In contrast, we propose spatiotemporal robustness (STR), which captures admissible spatial and temporal perturbations jointly. This notion is particularly informative for interacting systems, such as multi-agent robotics, smart cities, and air traffic control. We define STR as a multi-objective reasoning problem, formalized via a partial order over spatial and temporal perturbations. This perspective has two key advantages: (1) STR can be interpreted as a Pareto-optimal set that characterizes all admissible spatiotemporal perturbations, and (2) STR can be computed using tools from multi-objective optimization. To navigate computational challenges, we propose robust semantics for STR that are sound in the sense of suitably under-approximating STR while being computationally tractable. Finally, we present monitoring algorithms for STR using these robust semantics. To the best of our knowledge, this is the first work to deal with robustness across multiple dimensions via multi-objective reasoning.

---

### UltRAG: a Universal Simple Scalable Recipe for Knowledge Graph RAG

Authors: Dobrik Georgiev, Kheeran Naidu, Alberto Cattaneo, Federico Monti, Carlo Luschi, Daniel Justus
Published: 2026-01-28
Categories: cs.IR, cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2603.28773v1

Large language models (LLMs) frequently generate confident yet factually incorrect content when used for language generation (a phenomenon often known as hallucination). Retrieval augmented generation (RAG) tries to reduce factual errors by identifying information in a knowledge corpus and putting it in the context window of the model. While this approach is well-established for document-structured data, it is non-trivial to adapt it for Knowledge Graphs (KGs), especially for queries that require multi-node/multi-hop reasoning on graphs. We introduce ULTRAG, a general framework for retrieving information from Knowledge Graphs that shifts away from classical RAG. By endowing LLMs with off-the-shelf neural query executing modules, we highlight how readily available language models can achieve state-of-the-art results on Knowledge Graph Question Answering (KGQA) tasks without any retraining of the LLM or executor involved. In our experiments, ULTRAG achieves better performance when compared to state-of-the-art KG-RAG solutions, and it enables language models to interface with Wikidata-scale graphs (116M entities, 1.6B relations) at comparable or lower costs.

---

### Continual Fine-Tuning with Provably Accurate and Parameter-Free Task Retrieval

Authors: Hang Thi-Thuy Le, Long Minh Bui, Minh Hoang, Trong Nghia Hoang
Published: 2026-01-28
Categories: cs.LG
arXiv: https://arxiv.org/abs/2603.13235v1

Continual fine-tuning aims to adapt a pre-trained backbone to new tasks sequentially while preserving performance on earlier tasks whose data are no longer available. Existing approaches fall into two categories which include input- and parameter-adaptation. Input-adaptation methods rely on retrieving the most relevant prompts at test time, but require continuously learning a retrieval function that is prone to forgetting. Parameter-adaptation methods instead use a fixed input embedding function to enable retrieval-free prediction and avoid forgetting, but sacrifice representation adaptability. To combine their best strengths, we propose a new parameter-adaptation method that enables adaptive use of input embeddings during test time with parameter-free retrieval. We derive task-retrieval error bounds for a clustering-based, parameter-free paradigm, providing theoretical guarantees that link low retrieval error to structural properties of task-specific representation clusters, revealing a fresh insight into how well-organized clustering structure will enable reliable retrieval. Motivated by this insight, our method is designed with two key components: (i) an adaptive module composition strategy that learns informative task-specific updates to preserve and complement prior knowledge, and (ii) a clustering-based retrieval mechanism that captures distinct representation signatures for each task, enabling adaptive representation use at test time. Extensive experiments show that these components work synergistically to improve retrieval and predictive performance under large shifts in task semantics.

---

### Toward Effective Multi-Domain Rumor Detection in Social Networks Using Domain-Gated Mixture-of-Experts

Authors: Mohadeseh Sheikhqoraei, Zainabolhoda Heshmati, Zeinab Rajabi, Leila Rabiei
Published: 2026-01-28
Categories: cs.SI, cs.CL, cs.IR
arXiv: https://arxiv.org/abs/2602.21214v1

Social media platforms have become key channels for spreading and tracking rumors due to their widespread accessibility and ease of information sharing. Rumors can continuously emerge across diverse domains and topics, often with the intent to mislead society for personal or commercial gain. Therefore, developing methods that can accurately detect rumors at early stages is crucial to mitigating their negative impact. While existing approaches often specialize in single-domain detection, their performance degrades when applied to new domains due to shifts in data distribution, such as lexical patterns and propagation dynamics. To bridge this gap, this study introduces PerFact, a large-scale multi-domain rumor dataset comprising 8,034 annotated posts from the X platform, annotated into two primary categories: rumor (including true, false, and unverified rumors) and non-rumor. Annotator agreement, measured via Fleiss' Kappa ($κ= 0.74$), ensures high-quality labels. This research further proposes an effective multi-domain rumor detection model that employs a domain gate to dynamically aggregate multiple feature representations extracted through a Mixture-of-Experts method. Each expert combines CNN and BiLSTM networks to capture local syntactic features and long-range contextual dependencies. By leveraging both textual content and publisher information, the proposed model classifies posts into rumor and non-rumor categories with high accuracy. Evaluations demonstrate state-of-the-art performance, achieving an F1-score of 79.86\% and an accuracy of 79.98\% in multi-domain settings. Keywords: Rumor Detection, Multi-Domain, Natural Language Processing, Social Networks, Mixture-of-Experts Model

---

### Disaster Question Answering with LoRA Efficiency and Accurate End Position

Authors: Takato Yasuno
Published: 2026-01-28
Categories: cs.CL, cs.IR, cs.LG
arXiv: https://arxiv.org/abs/2602.21212v1

Natural disasters such as earthquakes, torrential rainfall, floods, and volcanic eruptions occur with extremely low frequency and affect limited geographic areas. When individuals face disaster situations, they often experience confusion and lack the domain-specific knowledge and experience necessary to determine appropriate responses and actions. While disaster information is continuously updated, even when utilizing RAG search and large language models for inquiries, obtaining relevant domain knowledge about natural disasters and experiences similar to one's specific situation is not guaranteed. When hallucinations are included in disaster question answering, artificial misinformation may spread and exacerbate confusion. This work introduces a disaster-focused question answering system based on Japanese disaster situations and response experiences. Utilizing the cl-tohoku/bert-base-japanese-v3 + Bi-LSTM + Enhanced Position Heads architecture with LoRA efficiency optimization, we achieved 70.4\% End Position accuracy with only 5.7\% of the total parameters (6.7M/117M). Experimental results demonstrate that the combination of Japanese BERT-base optimization and Bi-LSTM contextual understanding achieves accuracy levels suitable for real disaster response scenarios, attaining a 0.885 Span F1 score. Future challenges include: establishing natural disaster Q\&A benchmark datasets, fine-tuning foundation models with disaster knowledge, developing lightweight and power-efficient edge AI Disaster Q\&A applications for situations with insufficient power and communication during disasters, and addressing disaster knowledge base updates and continual learning capabilities.

---

### Benchmarking Distilled Language Models: Performance and Efficiency in Resource-Constrained Settings

Authors: Sachin Gopal Wani, Eric Page, Ajay Dholakia, David Ellison
Published: 2026-01-28
Categories: cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2602.20164v1

Knowledge distillation offers a transformative pathway to developing powerful, yet efficient, small language models (SLMs) suitable for resource-constrained environments. In this paper, we benchmark the performance and computational cost of distilled models against their vanilla and proprietary counterparts, providing a quantitative analysis of their efficiency. Our results demonstrate that distillation creates a superior performance-tocompute curve. We find that creating a distilled 8B model is over 2,000 times more compute-efficient than training its vanilla counterpart, while achieving reasoning capabilities on par with, or even exceeding, standard models ten times its size. These findings validate distillation not just as a compression technique, but as a primary strategy for building state-of-the-art, accessible AI

---

### INSURE-Dial: A Phase-Aware Conversational Dataset & Benchmark for Compliance Verification and Phase Detection

Authors: Shubham Kulkarni, Alexander Lyzhov, Preetam Joshi, Shiva Chaitanya
Published: 2026-01-28
Categories: cs.CL
arXiv: https://arxiv.org/abs/2602.18448v2

Administrative phone tasks drain roughly 1 trillion USD annually from U.S. healthcare, with over 500 million insurance-benefit verification calls manually handled in 2024. We introduce INSURE-Dial, to our knowledge the first public benchmark for developing and assessing compliance-aware voice agents for phase-aware call auditing with span-based compliance verification. The corpus includes 50 de-identified, AI-initiated calls with live insurance representatives (mean 71 turns/call) and 1,000 synthetically generated calls that mirror the same workflow. All calls are annotated with a phase-structured JSON schema covering IVR navigation, patient identification, coverage status, medication checks (up to two drugs), and agent identification (CRN), and each phase is labeled for Information and Procedural compliance under explicit ask/answer logic. We define two novel evaluation tasks: (1) Phase Boundary Detection (span segmentation under phase-specific acceptance rules) and (2) Compliance Verification (IC/PC decisions given fixed spans). Per-phase scores are strong across small, low-latency baselines, but end-to-end reliability is constrained by span-boundary errors. On real calls, full-call exact segmentation is low, showing a gap between conversational fluency and audit-grade evidence.

---

### ConfSpec: Efficient Step-Level Speculative Reasoning via Confidence-Gated Verification

Authors: Siran Liu, Cyril Y. He
Published: 2026-01-28
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2602.18447v1

Chain-of-Thought reasoning significantly improves the performance of large language models on complex tasks, but incurs high inference latency due to long generation traces. Step-level speculative reasoning aims to mitigate this cost, yet existing approaches face a long-standing trade-off among accuracy, inference speed, and resource efficiency. We propose ConfSpec, a confidence-gated cascaded verification framework that resolves this trade-off. Our key insight is an asymmetry between generation and verification: while generating a correct reasoning step requires substantial model capacity, step-level verification is a constrained discriminative task for which small draft models are well-calibrated within their competence range, enabling high-confidence draft decisions to be accepted directly while selectively escalating uncertain cases to the large target model. Evaluation across diverse workloads shows that ConfSpec achieves up to 2.24$\times$ end-to-end speedups while matching target-model accuracy. Our method requires no external judge models and is orthogonal to token-level speculative decoding, enabling further multiplicative acceleration.

---

### Reducing Text Bias in Synthetically Generated MCQAs for VLMs in Autonomous Driving

Authors: Sutej Kulgod, Sean Ye, Sanchit Tanwar, Christoffer Heckman
Published: 2026-01-28
Categories: cs.LG, cs.CL, cs.RO
arXiv: https://arxiv.org/abs/2602.17677v1

Multiple Choice Question Answering (MCQA) benchmarks are an established standard for measuring Vision Language Model (VLM) performance in driving tasks. However, we observe the known phenomenon that synthetically generated MCQAs are highly susceptible to hidden textual cues that allow models to exploit linguistic patterns rather than visual context. Our results show that a VLM fine-tuned on such data can achieve accuracy comparable to human-validated benchmarks even without visual input. Our proposed method reduces blind accuracy from +66.9% above random to +2.9%, eliminating the vast majority of exploitable textual shortcuts. By decoupling the correct answer from linguistic artifacts and employing a curriculum learning strategy, we force the model to rely on visual grounding, ensuring that performance accurately reflects perceptual understanding.

---

### AIdentifyAGE Ontology for Decision Support in Forensic Dental Age Assessment

Authors: Renato Marcelo, Ana Rodrigues, Cristiana Palmela Pereira, António Figueiras, Rui Santos, José Rui Figueira, Alexandre P Francisco, Cátia Vaz
Published: 2026-01-28
Categories: cs.AI
arXiv: https://arxiv.org/abs/2602.16714v1

Age assessment is crucial in forensic and judicial decision-making, particularly in cases involving undocumented individuals and unaccompanied minors, where legal thresholds determine access to protection, healthcare, and judicial procedures. Dental age assessment is widely recognized as one of the most reliable biological approaches for adolescents and young adults, but current practices are challenged by methodological heterogeneity, fragmented data representation, and limited interoperability between clinical, forensic, and legal information systems. These limitations hinder transparency and reproducibility, amplified by the increasing adoption of AI- based methods. The AIdentifyAGE ontology is domain-specific and provides a standardized, semantically coherent framework, encompassing both manual and AI-assisted forensic dental age assessment workflows, and enabling traceable linkage between observations, methods, reference data, and reported outcomes. It models the complete medico-legal workflow, integrating judicial context, individual-level information, forensic examination data, dental developmental assessment methods, radiographic imaging, statistical reference studies, and AI-based estimation methods. It is being developed together with domain experts, and it builds on upper and established biomedical, dental, and machine learning ontologies, ensuring interoperability, extensibility, and compliance with FAIR principles. The AIdentifyAGE ontology is a fundamental step to enhance consistency, transparency, and explainability, establishing a robust foundation for ontology-driven decision support systems in medico-legal and judicial contexts.

---

### MARVL: Multi-Stage Guidance for Robotic Manipulation via Vision-Language Models

Authors: Xunlan Zhou, Xuanlin Chen, Shaowei Zhang, ShengHua Wan, Xiaohai Hu, Lei Yuan, De-chuan Zhan
Published: 2026-01-28
Categories: cs.RO, cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2602.15872v3

Designing dense reward functions is pivotal for efficient robotic Reinforcement Learning (RL). However, most dense rewards rely on manual engineering, which fundamentally limits the scalability and automation of reinforcement learning. While Vision-Language Models (VLMs) offer a promising path to reward design, naive VLM rewards often misalign with task progress, struggle with spatial grounding, and show limited understanding of task semantics. To address these issues, we propose MARVL-Multi-stAge guidance for Robotic manipulation via Vision-Language models. MARVL fine-tunes a VLM for spatial and semantic consistency and decomposes tasks into multi-stage subtasks with task direction projection for trajectory sensitivity. Empirically, MARVL significantly outperforms existing VLM-reward methods on the Meta-World benchmark, demonstrating superior sample efficiency and robustness on sparse-reward manipulation tasks.

---

### An Explainable Failure Prediction Framework for Neural Networks in Radio Access Networks

Authors: Khaleda Papry, Francesco Spinnato, Marco Fiore, Mirco Nanni, Israat Haque
Published: 2026-01-28
Categories: cs.NI, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2602.13231v1

As 5G networks continue to evolve to deliver high speed, low latency, and reliable communications, ensuring uninterrupted service has become increasingly critical. While millimeter wave (mmWave) frequencies enable gigabit data rates, they are highly susceptible to environmental factors, often leading to radio link failures (RLF). Predictive models leveraging radio and weather data have been proposed to address this issue; however, many operate as black boxes, offering limited transparency for operational deployment. This work bridges that gap by introducing a framework that combines explainability based feature pruning with model refinement. Our framework can be integrated into state of the art predictors such as GNN Transformer and LSTM based architectures for RLF prediction, enabling the development of accurate and explainability guided models in 5G networks. It provides insights into the contribution of input features and the decision making logic of neural networks, leading to lighter and more scalable models. When applied to RLF prediction, our framework unveils that weather data contributes minimally to the forecast in extensive real world datasets, which informs the design of a leaner model with 50 percent fewer parameters and improved F1 scores with respect to the state of the art solution. Ultimately, this work empowers network providers to evaluate and refine their neural network based prediction models for better interpretability, scalability, and performance.

---

### Intelligence as Trajectory-Dominant Pareto Optimization

Authors: Truong Xuan Khanh, Truong Quynh Hoa
Published: 2026-01-28
Categories: cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2602.13230v1

Despite recent advances in artificial intelligence, many systems exhibit stagnation in long-horizon adaptability despite continued performance optimization. This work argues that such limitations do not primarily arise from insufficient learning, data, or model capacity, but from a deeper structural property of how intelligence is optimized over time. We formulate intelligence as a trajectory-level phenomenon governed by multi-objective trade-offs, and introduce Trajectory-Dominant Pareto Optimization, a path-wise generalization of classical Pareto optimality in which dominance is defined over full trajectories. Within this framework, Pareto traps emerge as locally non-dominated regions of trajectory space that nevertheless restrict access to globally superior developmental paths under conservative local optimization. To characterize the rigidity of such constraints, we define the Trap Escape Difficulty Index (TEDI), a composite geometric measure capturing escape distance, structural constraints, and behavioral inertia. We show that dynamic intelligence ceilings arise as inevitable geometric consequences of trajectory-level dominance, independent of learning progress or architectural scale. We further introduce a formal taxonomy of Pareto traps and illustrate the resulting trajectory-level divergence using a minimal agent-environment model. Together, these results shift the locus of intelligence from terminal performance to optimization geometry, providing a principled framework for diagnosing and overcoming long-horizon developmental constraints in adaptive systems.

---

### String-Level Ground Fault Localization for TN-Earthed Three-Phase Photovoltaic Systems

Authors: Yuanliang Li, Xun Gong, Reza Iravani, Bo Cao, Heng Liu, Ziming Chen
Published: 2026-01-28
Categories: eess.SY, cs.LG, eess.SP
arXiv: https://arxiv.org/abs/2602.12289v2

The DC-side ground fault (GF) poses significant risks to three-phase TN-earthed photovoltaic (PV) systems, as the resulting high fault current can directly damage both PV inverters and PV modules. Once a fault occurs, locating the faulty string through manual string-by-string inspection is highly time-consuming and inefficient. This work presents a comprehensive analysis of GF characteristics through fault-current analysis and a simulation-based case study covering multiple fault locations. Building on these insights, we propose an edge-AI-based GF localization approach tailored for three-phase TN-earthed PV systems. A PLECS-based simulation model that incorporates PV hysteresis effects is developed to generate diverse GF scenarios, from which correlation-based features are extracted throughout the inverter's four-stage shutdown sequence. Using the simulated dataset, a lightweight Variational Information Bottleneck (VIB)-based localization model is designed and trained, achieving over 93% localization accuracy at typical sampling rates with low computational cost, demonstrating strong potential for deployment on resource-constrained PV inverters.

---

### Hierarchical JEPA Meets Predictive Remote Control in Beyond 5G Networks

Authors: Abanoub M. Girgis, Ibtissam Labriji, Mehdi Bennis
Published: 2026-01-28
Categories: eess.SY, cs.AI, cs.RO
arXiv: https://arxiv.org/abs/2602.07000v1

In wireless networked control systems, ensuring timely and reliable state updates from distributed devices to remote controllers is essential for robust control performance. However, when multiple devices transmit high-dimensional states (e.g., images or video frames) over bandwidth-limited wireless networks, a critical trade-off emerges between communication efficiency and control performance. To address this challenge, we propose a Hierarchical Joint-Embedding Predictive Architecture (H-JEPA) for scalable predictive control. Instead of transmitting states, device observations are encoded into low-dimensional embeddings that preserve essential dynamics. The proposed architecture employs a three-level hierarchical prediction, with high-level, medium-level, and low-level predictors operating across different temporal resolutions, to achieve long-term prediction stability, intermediate interpolation, and fine-grained refinement, respectively. Control actions are derived within the embedding space, removing the need for state reconstruction. Simulation results on inverted cart-pole systems demonstrate that H-JEPA enables up to 42.83 % more devices to be supported under limited wireless capacity without compromising control performance.

---

### Adaptive Temporal Dynamics for Personalized Emotion Recognition: A Liquid Neural Network Approach

Authors: Anindya Bhattacharjee, Nittya Ananda Biswas, K. A. Shahriar, Adib Rahman
Published: 2026-01-28
Categories: eess.SP, cs.AI, cs.LG, cs.NE
arXiv: https://arxiv.org/abs/2602.06997v1

Emotion recognition from physiological signals remains challenging due to their non-stationary, noisy, and subject-dependent characteristics. This work presents, to the best of our knowledge, the first comprehensive application of liquid neural networks for EEG-based emotion recognition. The proposed multimodal framework combines convolutional feature extraction, liquid neural networks with learnable time constants, and attention-guided fusion to model temporal EEG dynamics with complementary peripheral physiological and personality features. Dedicated subnetworks are used to process EEG features and auxiliary modalities, and a shared autoencoder-based fusion module is used to learn discriminative latent representations before classification. Subject-dependent experiments conducted on the PhyMER dataset across seven emotional classes achieve an accuracy of 95.45%, surpassing previously reported results. Furthermore, temporal attention analysis provides interpretable insights into emotion-specific temporal relevance, and t-SNE visualizations demonstrate enhanced class separability, highlighting the effectiveness of the proposed approach. Finally, statistical analysis of temporal dynamics confirms that the network self-organizes into distinct functional groups with specialized fast and slow neurons, proving it independently tunes learnable time constants and memory dominance to effectively capture complex emotion artifacts.

---

### Curriculum-Learned Vanishing Stacked Residual PINNs for Hyperbolic PDE State Reconstruction

Authors: Katayoun Eshkofti, Matthieu Barreau
Published: 2026-01-28
Categories: cs.NE, cs.LG, eess.SY
arXiv: https://arxiv.org/abs/2602.06996v1

Modeling distributed dynamical systems governed by hyperbolic partial differential equations (PDEs) remains challenging due to discontinuities and shocks that hinder the convergence of traditional physics-informed neural networks (PINNs). The recently proposed vanishing stacked residual PINN (VSR-PINN) embeds a vanishing-viscosity mechanism within stacked residual refinements to enable a smooth transition from the parabolic to hyperbolic regime. This paper integrates three curriculum-learning methods as primal-dual (PD) optimization, causality progression, and adaptive sampling into the VSR-PINN. The PD strategy balances physics and data losses, the causality scheme unlocks deeper stacks by respecting temporal and gradient evolution, and adaptive sampling targets high residuals. Numerical experiments on traffic reconstruction confirm that enforcing causality systematically reduces the median point-wise MSE and its variability across runs, yielding improvements of nearly one order of magnitude over non-causal training in both the baseline and PD variants.

---

### When Simultaneous Localization and Mapping Meets Wireless Communications: A Survey

Authors: Konstantinos Gounis, Sotiris A. Tegos, Dimitrios Tyrovolas, Panagiotis D. Diamantoulakis, George K. Karagiannidis
Published: 2026-01-28
Categories: cs.RO, cs.CV, cs.IT, cs.MA
arXiv: https://arxiv.org/abs/2602.06995v2

This paper surveys the state-of-the-art in the nexus of SLAM and Wireless Communications, attributing the bidirectional impact of each with a focus on visual SLAM (V-SLAM) integration. We provide an overview of key concepts related to wireless signal propagation, geometric channel modeling, and radio frequency (RF)-based localization and sensing. In addition to this, we show image processing techniques that can detect landmarks, proactively predicting optimal paths for wireless channels. Several dimensions are considered, including the prerequisites, techniques, background, and future directions and challenges of the intersection between SLAM and wireless communications. We analyze estimation and control approaches such as Bayesian filters, feature-based pose estimation, perception-aware motion control, spatial methods for signal processing such as vector fields, and key technological aspects. We expose techniques and items towards enabling a highly effective retrieval of the autonomous robot state. Among other interesting findings, we observe that monocular V-SLAM would benefit from RF relevant information, as the latter can serve as a proxy for the scale ambiguity resolution. Conversely, we find that wireless communications in the context of 5G and beyond can potentially benefit from visual odometry that is central in SLAM. Moreover, we examine other sources besides the camera for SLAM and describe the twofold relation with wireless communications. Finally, integrated solutions performing joint communications and SLAM appear to be in their infancy: theoretical and practical advancements are required to add higher-level localization and semantic perception capabilities to RF and multi-antenna technologies.

---

### SurfAge-Net: A Hierarchical Surface-Based Network for Interpretable Fine-Grained Brain Age Prediction

Authors: Rongzhao He, Dalin Zhu, Ying Wang, Songhong Yue, Leilei Zhao, Yu Fu, Dan Wu, Bin Hu, Weihao Zheng
Published: 2026-01-28
Categories: q-bio.NC, cs.AI, cs.CV
arXiv: https://arxiv.org/abs/2602.06994v1

Brain age prediction serves as a powerful framework for assessing brain status and detecting deviations associated with neurodevelopmental and neurodegenerative disorders. However, most existing approaches emphasize whole-brain age prediction and therefore overlook the pronounced regional heterogeneity of brain maturation that is crucial for detecting localized atypical trajectories. To address this limitation, we propose a novel spherical surface-based brain age prediction network (SurfAge-Net) that leverages multiple morphological metrics to capture region-specific developmental patterns with enhanced robustness and clinical interpretability. SurfAge-Net establishes a new modeling paradigm by incorporating the connectomic principles of cortical organization: it explicitly models both intra- and inter-hemispheric dependencies through a spatial-channel mixing and a lateralization-aware attention mechanism, enabling the network to characterize the coordinate maturation pattern uniquely associated with each target region. Validated on three fetal and neonatal datasets, SurfAge-Net outperforms existing approaches (global MAE = 0.54, regional MAE = 0.45 in gestational/postmenstrual weeks) and demonstrates strong generalizability across external cohorts. Importantly, it provides spatially precise and biologically interpretable maps of cortical maturation, effectively identifying heterogeneous delays and regional-specific abnormalities in atypical developmental populations. These results established fine-grained brain age prediction as a promising paradigm for advancing neurodevelopmental research and supporting early clinical assessment.

---

### Attractor Patch Networks: Reducing Catastrophic Forgetting with Routed Low-Rank Patch Experts

Authors: Shashank
Published: 2026-01-28
Categories: cs.LG, cs.CL
arXiv: https://arxiv.org/abs/2602.06993v1

Transformers achieve strong language modeling accuracy, yet their position-wise feed-forward networks (FFNs) are dense, globally shared, and typically updated end to end. These properties create two practical tensions. First, dense FFNs spend the same compute on every token regardless of context, and they allocate capacity uniformly even when language exhibits highly clustered context structure. Second, continual learning, in the sense of updating the model while serving a data stream, often produces interference because a small update touches broadly shared weights. We propose Attractor Patch Networks (APN), a plug-compatible replacement for the Transformer FFN. APN is a bank of patch experts. A similarity router selects a small top-k set of patches for each token by matching the token representation to learned prototypes. Each selected patch emits a low-rank residual update conditioned on a compact code. The architecture yields conditional, context-specialized nonlinear transformations while preserving the standard Transformer interface. This paper focuses on APN as an architectural primitive. We formalize APN, analyze its expressivity as a piecewise low-rank residual function class, and derive simple interference and stability arguments that make APN naturally compatible with continual learning. In experiments on character-level language modeling, APN achieves competitive perplexity (4.57 vs 4.32 PPL) while enabling dramatically better continual adaptation: when adapting to a shifted domain, APN achieves 2.6 times better retention (11.1 vs 29.4 PPL on the original domain) and 2.8 times better adaptation (6.4 vs 17.8 PPL on the new domain) compared to global fine-tuning of a dense FFN baseline.

---