# Research Papers — 2026-01 · bundle page 80 of 189

> Full-text markdown of papers #3951–4000 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/80
[← Previous bundle](https://aipod.dev/papers/archive/2026-01/page/79.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-01/page/81.md)

### Large Data Limits of Laplace Learning for Gaussian Measure Data in Infinite Dimensions

Authors: Zhengang Zhong, Yury Korolev, Matthew Thorpe
Published: 2026-01-20
Categories: stat.ML, cs.LG, math.NA
arXiv: https://arxiv.org/abs/2601.14515v1

Laplace learning is a semi-supervised method, a solution for finding missing labels from a partially labeled dataset utilizing the geometry given by the unlabeled data points. The method minimizes a Dirichlet energy defined on a (discrete) graph constructed from the full dataset. In finite dimensions the asymptotics in the large (unlabeled) data limit are well understood with convergence from the graph setting to a continuum Sobolev semi-norm weighted by the Lebesgue density of the data-generating measure. The lack of the Lebesgue measure on infinite-dimensional spaces requires rethinking the analysis if the data aren't finite-dimensional. In this paper we make a first step in this direction by analyzing the setting when the data are generated by a Gaussian measure on a Hilbert space and proving pointwise convergence of the graph Dirichlet energy.

---

### "Just in Time" World Modeling Supports Human Planning and Reasoning

Authors: Tony Chen, Sam Cheyette, Kelsey Allen, Joshua Tenenbaum, Kevin Smith
Published: 2026-01-20
Categories: cs.AI, q-bio.NC
arXiv: https://arxiv.org/abs/2601.14514v1

Probabilistic mental simulation is thought to play a key role in human reasoning, planning, and prediction, yet the demands of simulation in complex environments exceed realistic human capacity limits. A theory with growing evidence is that people simulate using simplified representations of the environment that abstract away from irrelevant details, but it is unclear how people determine these simplifications efficiently. Here, we present a "Just-in-Time" framework for simulation-based reasoning that demonstrates how such representations can be constructed online with minimal added computation. The model uses a tight interleaving of simulation, visual search, and representation modification, with the current simulation guiding where to look and visual search flagging objects that should be encoded for subsequent simulation. Despite only ever encoding a small subset of objects, the model makes high-utility predictions. We find strong empirical support for this account over alternative models in a grid-world planning task and a physical reasoning task across a range of behavioral measures. Together, these results offer a concrete algorithmic account of how people construct reduced representations to support efficient mental simulation.

---

### Compounding Disadvantage: Auditing Intersectional Bias in LLM-Generated Explanations Across Indian and American STEM Education

Authors: Amogh Gupta, Niharika Patil, Sourojit Ghosh, SnehalKumar, S Gaikwad
Published: 2026-01-20
Categories: cs.CY, cs.CL
arXiv: https://arxiv.org/abs/2601.14506v3

Large language models are increasingly deployed in STEM education for personalized instruction and feedback across institutions in high- and low-income countries. These systems are designed to adapt content to student needs, but whether they adapt based on demonstrated ability or demographic signals remains untested at scale. Here we establish that LLM-generated STEM content systematically disadvantages marginalized student profiles across two cultural contexts, with the gap between the most privileged and most marginalized profiles reaching 2.55 grade levels. We audited four LLMs (Qwen 2.5-32B-Instruct, GPT-4o, GPT-4o-mini, GPT-OSS 20B) using synthetic profiles crossing dimensions specific to Indian education (caste, medium of instruction, college tier) and American education (race, HBCU attendance, school type), alongside income, gender, and disability, across ranking and generation tasks with FDR-corrected significance testing and SHAP feature attribution. Income produces significant effects across every model and context, medium of instruction drives the largest single effect in the Indian context, and disability status triggers simpler explanations. Effects compound non-additively: marginalization across multiple dimensions produces gaps larger than any single dimension predicts, and biases persist within elite institutions. Bias is consistent across all four architectures and persists through model selection, making intersectional, cross-cultural auditing a structural requirement before deployment.

---

### Uncovering and Understanding FPR Manipulation Attack in Industrial IoT Networks

Authors: Mohammad Shamim Ahsan, Peng Liu
Published: 2026-01-20
Categories: cs.CR, cs.LG
arXiv: https://arxiv.org/abs/2601.14505v2

In the network security domain, due to practical issues -- including imbalanced data and heterogeneous legitimate network traffic -- adversarial attacks in machine learning-based NIDSs have been viewed as attack packets misclassified as benign. Due to this prevailing belief, the possibility of (maliciously) perturbed benign packets being misclassified as attack has been largely ignored. In this paper, we demonstrate that this is not only theoretically possible, but also a particular threat to NIDS. In particular, we uncover a practical cyberattack, FPR manipulation attack (FPA), especially targeting industrial IoT networks, where domain-specific knowledge of the widely used MQTT protocol is exploited and a systematic simple packet-level perturbation is performed to alter the labels of benign traffic samples without employing traditional gradient-based or non-gradient-based methods. The experimental evaluations demonstrate that this novel attack results in a success rate of 80.19% to 100%. In addition, while estimating impacts in the Security Operations Center, we observe that even a small fraction of false positive alerts, irrespective of different budget constraints and alert traffic intensities, can increase the delay of genuine alerts investigations up to 2 hr in a single day under normal operating conditions. Furthermore, a series of relevant statistical and XAI analyses is conducted to understand the key factors behind this remarkable success. Finally, we explore the effectiveness of the FPA packets to enhance models' robustness through adversarial training and investigate the changes in decision boundaries accordingly.

---

### GutenOCR: A Grounded Vision-Language Front-End for Documents

Authors: Hunter Heidenreich, Ben Elliott, Olivia Dinica, Yosheb Getachew
Published: 2026-01-20
Categories: cs.CV, cs.AI, cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2601.14490v2

GutenOCR is a family of grounded OCR front-ends obtained by fine-tuning Qwen2.5-VL-3B and Qwen2.5-VL-7B. The resulting single-checkpoint vision-language models expose reading, detection, and grounding through a unified, prompt-based interface. Trained on business documents, scientific articles, and synthetic grounding data, the models support full-page and localized reading with line- and paragraph-level bounding boxes and conditional ``where is x?'' queries. We introduce a grounded OCR evaluation protocol and show that GutenOCR-7B more than doubles the composite grounded OCR score of its Qwen2.5-VL-7B backbone on 10.5K held-out business and scientific pages (0.40 to 0.82). On Fox and OmniDocBench v1.5, our approach substantially improves region- and line-level OCR as well as text-detection recall, but reveals trade-offs in page-level linearization, color-guided OCR, and formula-heavy layouts.

---

### Stabilizing autoregressive forecasts in chaotic systems via multi-rate latent recurrence

Authors: Mrigank Dhingra, Omer San
Published: 2026-01-20
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.14487v1

Long-horizon autoregressive forecasting of chaotic dynamical systems remains challenging due to rapid error amplification and distribution shift: small one-step inaccuracies compound into physically inconsistent rollouts and collapse of large-scale statistics. We introduce MSR-HINE, a hierarchical implicit forecaster that augments multiscale latent priors with multi-rate recurrent modules operating at distinct temporal scales. At each step, coarse-to-fine recurrent states generate latent priors, an implicit one-step predictor refines the state with multiscale latent injections, and a gated fusion with posterior latents enforces scale-consistent updates; a lightweight hidden-state correction further aligns recurrent memories with fused latents. The resulting architecture maintains long-term context on slow manifolds while preserving fast-scale variability, mitigating error accumulation in chaotic rollouts. Across two canonical benchmarks, MSR-HINE yields substantial gains over a U-Net autoregressive baseline: on Kuramoto-Sivashinsky it reduces end-horizon RMSE by 62.8% at H=400 and improves end-horizon ACC by +0.983 (from -0.155 to 0.828), extending the ACC >= 0.5 predictability horizon from 241 to 400 steps; on Lorenz-96 it reduces RMSE by 27.0% at H=100 and improves end horizon ACC by +0.402 (from 0.144 to 0.545), extending the ACC >= 0.5 horizon from 58 to 100 steps.

---

### Scalable Knee-Point Guided Activity Group Selection in Multi-Tree Genetic Programming for Dynamic Multi-Mode Project Scheduling

Authors: Yuan Tian, Yi Mei, Mengjie Zhang
Published: 2026-01-20
Categories: cs.AI
arXiv: https://arxiv.org/abs/2601.14485v1

The dynamic multi-mode resource-constrained project scheduling problem is a challenging scheduling problem that requires making decisions on both the execution order of activities and their corresponding execution modes. Genetic programming has been widely applied as a hyper-heuristic to evolve priority rules that guide the selection of activity-mode pairs from the current eligible set. Recently, an activity group selection strategy has been proposed to select a subset of activities rather than a single activity at each decision point, allowing for more effective scheduling by considering the interdependence between activities. Although effective in small-scale instances, this strategy suffers from scalability issues when applied to larger problems. In this work, we enhance the scalability of the group selection strategy by introducing a knee-point-based selection mechanism to identify a promising subset of activities before evaluating their combinations. An activity ordering rule is first used to rank all eligible activity-mode pairs, followed by a knee point selection to find the promising pairs. Then, a group selection rule selects the best activity combination. We develop a multi-tree GP framework to evolve both types of rules simultaneously. Experimental results demonstrate that our approach scales well to large instances and outperforms GP with sequential decision-making in most scenarios.

---

### Can LLM Reasoning Be Trusted? A Comparative Study: Using Human Benchmarking on Statistical Tasks

Authors: Crish Nagarkar, Leonid Bogachev, Serge Sharoff
Published: 2026-01-20
Categories: cs.CL
arXiv: https://arxiv.org/abs/2601.14479v1

This paper investigates the ability of large language models (LLMs) to solve statistical tasks, as well as their capacity to assess the quality of reasoning. While state-of-the-art LLMs have demonstrated remarkable performance in a range of NLP tasks, their competence in addressing even moderately complex statistical challenges is not well understood. We have fine-tuned selected open-source LLMs on a specially developed dataset to enhance their statistical reasoning capabilities, and compared their performance with the human scores used as a benchmark. Our results show that the fine-tuned models achieve better performance on advanced statistical tasks on the level comparable to a statistics student. Fine-tuning demonstrates architecture-dependent improvements, with some models showing significant performance gains, indicating clear potential for deployment in educational technology and statistical analysis assistance systems. We also show that LLMs themselves can be far better judges of the answers quality (including explanation and reasoning assessment) in comparison to traditional metrics, such as BLEU or BertScore. This self-evaluation capability enables scalable automated assessment for statistical education platforms and quality assurance in automated analysis tools. Potential applications also include validation tools for research methodology in academic and industry settings, and quality control mechanisms for data analysis workflows.

---

### Large Language Models for Large-Scale, Rigorous Qualitative Analysis in Applied Health Services Research

Authors: Sasha Ronaghi, Emma-Louise Aveling, Maria Levis, Rachel Lauren Ross, Emily Alsentzer, Sara Singer
Published: 2026-01-20
Categories: cs.CL
arXiv: https://arxiv.org/abs/2601.14478v1

Large language models (LLMs) show promise for improving the efficiency of qualitative analysis in large, multi-site health-services research. Yet methodological guidance for LLM integration into qualitative analysis and evidence of their impact on real-world research methods and outcomes remain limited. We developed a model- and task-agnostic framework for designing human-LLM qualitative analysis methods to support diverse analytic aims. Within a multi-site study of diabetes care at Federally Qualified Health Centers (FQHCs), we leveraged the framework to implement human-LLM methods for (1) qualitative synthesis of researcher-generated summaries to produce comparative feedback reports and (2) deductive coding of 167 interview transcripts to refine a practice-transformation intervention. LLM assistance enabled timely feedback to practitioners and the incorporation of large-scale qualitative data to inform theory and practice changes. This work demonstrates how LLMs can be integrated into applied health-services research to enhance efficiency while preserving rigor, offering guidance for continued innovation with LLMs in qualitative research.

---

### XD-MAP: Cross-Modal Domain Adaptation via Semantic Parametric Maps for Scalable Training Data Generation

Authors: Frank Bieder, Hendrik Königshof, Haohao Hu, Fabian Immel, Yinzhe Shen, Jan-Hendrik Pauls, Christoph Stiller
Published: 2026-01-20
Categories: cs.CV, cs.AI, eess.IV
arXiv: https://arxiv.org/abs/2601.14477v2

Until open-world foundation models match the performance of specialized approaches, deep learning systems remain dependent on task- and sensor-specific data availability. To bridge the gap between available datasets and deployment domains, domain adaptation strategies are widely used. In this work, we propose XD-MAP, a novel approach to transfer sensor-specific knowledge from an image dataset to LiDAR, an entirely different sensing domain. Our method leverages detections on camera images to create a semantic parametric map. The map elements are modeled to produce pseudo labels in the target domain without any manual annotation effort. Unlike previous domain transfer approaches, our method does not require direct overlap between sensors and enables extending the angular perception range from a front-view camera to a full 360° view. On our large-scale road feature dataset, XD-MAP outperforms single shot baseline approaches by +19.5 mIoU for 2D semantic segmentation, +19.5 PQth for 2D panoptic segmentation, and +32.3 mIoU in 3D semantic segmentation. The results demonstrate the effectiveness of our approach achieving strong performance on LiDAR data without any manual labeling.

---

### GPU-accelerated simulated annealing based on p-bits with real-world device-variability modeling

Authors: Naoya Onizawa, Takahiro Hanyu
Published: 2026-01-20
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2601.14476v1

Probabilistic computing using probabilistic bits (p-bits) presents an efficient alternative to traditional CMOS logic for complex problem-solving, including simulated annealing and machine learning. Realizing p-bits with emerging devices such as magnetic tunnel junctions (MTJs) introduces device variability, which was expected to negatively impact computational performance. However, this study reveals an unexpected finding: device variability can not only degrade but also enhance algorithm performance, particularly by leveraging timing variability. This paper introduces a GPU-accelerated, open-source simulated annealing framework based on p-bits that models key device variability factors -- timing, intensity, and offset -- to reflect real-world device behavior. Through CUDA-based simulations, our approach achieves a two-order magnitude speedup over CPU implementations on the MAX-CUT benchmark with problem sizes ranging from 800 to 20,000 nodes. By providing a scalable and accessible tool, this framework aims to advance research in probabilistic computing, enabling optimization applications in diverse fields.

---

### Real-Time Wildfire Localization on the NASA Autonomous Modular Sensor using Deep Learning

Authors: Yajvan Ravan, Aref Malek, Chester Dolph, Nikhil Behari
Published: 2026-01-20
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2601.14475v1

High-altitude, multi-spectral, aerial imagery is scarce and expensive to acquire, yet it is necessary for algorithmic advances and application of machine learning models to high-impact problems such as wildfire detection. We introduce a human-annotated dataset from the NASA Autonomous Modular Sensor (AMS) using 12-channel, medium to high altitude (3 - 50 km) aerial wildfire images similar to those used in current US wildfire missions. Our dataset combines spectral data from 12 different channels, including infrared (IR), short-wave IR (SWIR), and thermal. We take imagery from 20 wildfire missions and randomly sample small patches to generate over 4000 images with high variability, including occlusions by smoke/clouds, easily-confused false positives, and nighttime imagery. We demonstrate results from a deep-learning model to automate the human-intensive process of fire perimeter determination. We train two deep neural networks, one for image classification and the other for pixel-level segmentation. The networks are combined into a unique real-time segmentation model to efficiently localize active wildfire on an incoming image feed. Our model achieves 96% classification accuracy, 74% Intersection-over-Union(IoU), and 84% recall surpassing past methods, including models trained on satellite data and classical color-rule algorithms. By leveraging a multi-spectral dataset, our model is able to detect active wildfire at nighttime and behind clouds, while distinguishing between false positives. We find that data from the SWIR, IR, and thermal bands is the most important to distinguish fire perimeters. Our code and dataset can be found here: https://github.com/nasa/Autonomous-Modular-Sensor-Wildfire-Segmentation/tree/main and https://drive.google.com/drive/folders/1-u4vs9rqwkwgdeeeoUhftCxrfe_4QPTn?=usp=drive_link

---

### Adaptive KDE for Real-Time Thresholding: Prioritized Queues for Financial Crime Investigation

Authors: Danny Butvinik, Nana Boateng, Achi Hackmon
Published: 2026-01-20
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.14473v2

We study the problem of converting a continuous stream of risk scores into stable decision thresholds under non-stationary score distributions. This problem arises in a wide range of detection systems where scores must be partitioned into prioritized processing regions while preserving semantic consistency over time.

---

### Prosody-Guided Harmonic Attention for Phase-Coherent Neural Vocoding in the Complex Spectrum

Authors: Mohammed Salah Al-Radhi, Riad Larbi, Mátyás Bartalis, Géza Németh
Published: 2026-01-20
Categories: cs.SD, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2601.14472v1

Neural vocoders are central to speech synthesis; despite their success, most still suffer from limited prosody modeling and inaccurate phase reconstruction. We propose a vocoder that introduces prosody-guided harmonic attention to enhance voiced segment encoding and directly predicts complex spectral components for waveform synthesis via inverse STFT. Unlike mel-spectrogram-based approaches, our design jointly models magnitude and phase, ensuring phase coherence and improved pitch fidelity. To further align with perceptual quality, we adopt a multi-objective training strategy that integrates adversarial, spectral, and phase-aware losses. Experiments on benchmark datasets demonstrate consistent gains over HiFi-GAN and AutoVocoder: F0 RMSE reduced by 22 percent, voiced/unvoiced error lowered by 18 percent, and MOS scores improved by 0.15. These results show that prosody-guided attention combined with direct complex spectrum modeling yields more natural, pitch-accurate, and robust synthetic speech, setting a strong foundation for expressive neural vocoding.

---

### Tokenomics: Quantifying Where Tokens Are Used in Agentic Software Engineering

Authors: Mohamad Salim, Jasmine Latendresse, SayedHassan Khatoonabadi, Emad Shihab
Published: 2026-01-20
Categories: cs.SE, cs.AI, cs.MA
arXiv: https://arxiv.org/abs/2601.14470v1

LLM-based Multi-Agent (LLM-MA) systems are increasingly applied to automate complex software engineering tasks such as requirements engineering, code generation, and testing. However, their operational efficiency and resource consumption remain poorly understood, hindering practical adoption due to unpredictable costs and environmental impact. To address this, we conduct an analysis of token consumption patterns in an LLM-MA system within the Software Development Life Cycle (SDLC), aiming to understand where tokens are consumed across distinct software engineering activities. We analyze execution traces from 30 software development tasks performed by the ChatDev framework using a GPT-5 reasoning model, mapping its internal phases to distinct development stages (Design, Coding, Code Completion, Code Review, Testing, and Documentation) to create a standardized evaluation framework. We then quantify and compare token distribution (input, output, reasoning) across these stages. Our preliminary findings show that the iterative Code Review stage accounts for the majority of token consumption for an average of 59.4% of tokens. Furthermore, we observe that input tokens consistently constitute the largest share of consumption for an average of 53.9%, providing empirical evidence for potentially significant inefficiencies in agentic collaboration. Our results suggest that the primary cost of agentic software engineering lies not in initial code generation but in automated refinement and verification. Our novel methodology can help practitioners predict expenses and optimize workflows, and it directs future research toward developing more token-efficient agent collaboration protocols.

---

### On the Generalization Gap in LLM Planning: Tests and Verifier-Reward RL

Authors: Valerio Belcamino, Nicholas Attolino, Alessio Capitanelli, Fulvio Mastrogiovanni
Published: 2026-01-20
Categories: cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2601.14456v1

Recent work shows that fine-tuned Large Language Models (LLMs) can achieve high valid plan rates on PDDL planning tasks. However, it remains unclear whether this reflects transferable planning competence or domain-specific memorization. In this work, we fine-tune a 1.7B-parameter LLM on 40,000 domain-problem-plan tuples from 10 IPC 2023 domains, and evaluate both in-domain and cross-domain generalization. While the model reaches 82.9% valid plan rate in in-domain conditions, it achieves 0% on two unseen domains. To analyze this failure, we introduce three diagnostic interventions, namely (i) instance-wise symbol anonymization, (ii) compact plan serialization, and (iii) verifier-reward fine-tuning using the VAL validator as a success-focused reinforcement signal. Symbol anonymization and compact serialization cause significant performance drops despite preserving plan semantics, thus revealing strong sensitivity to surface representations. Verifier-reward fine-tuning reaches performance saturation in half the supervised training epochs, but does not improve cross-domain generalization. For the explored configurations, in-domain performance plateaus around 80%, while cross-domain performance collapses, suggesting that our fine-tuned model relies heavily on domain-specific patterns rather than transferable planning competence in this setting. Our results highlight a persistent generalization gap in LLM-based planning and provide diagnostic tools for studying its causes.

---

### Gaussian Based Adaptive Multi-Modal 3D Semantic Occupancy Prediction

Authors: A. Enes Doruk
Published: 2026-01-20
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.14448v1

The sparse object detection paradigm shift towards dense 3D semantic occupancy prediction is necessary for dealing with long-tail safety challenges for autonomous vehicles. Nonetheless, the current voxelization methods commonly suffer from excessive computation complexity demands, where the fusion process is brittle, static, and breaks down under dynamic environmental settings. To this end, this research work enhances a novel Gaussian-based adaptive camera-LiDAR multimodal 3D occupancy prediction model that seamlessly bridges the semantic strengths of camera modality with the geometric strengths of LiDAR modality through a memory-efficient 3D Gaussian model. The proposed solution has four key components: (1) LiDAR Depth Feature Aggregation (LDFA), where depth-wise deformable sampling is employed for dealing with geometric sparsity, (2) Entropy-Based Feature Smoothing, where cross-entropy is employed for handling domain-specific noise, (3) Adaptive Camera-LiDAR Fusion, where dynamic recalibration of sensor outputs is performed based on model outputs, and (4) Gauss-Mamba Head that uses Selective State Space Models for global context decoding that enjoys linear computation complexity.

---

### Diffusion Large Language Models for Black-Box Optimization

Authors: Ye Yuan, Can, Chen, Zipeng Sun, Dinghuai Zhang, Christopher Pal, Xue Liu
Published: 2026-01-20
Categories: cs.CE, cs.AI
arXiv: https://arxiv.org/abs/2601.14446v1

Offline black-box optimization (BBO) aims to find optimal designs based solely on an offline dataset of designs and their labels. Such scenarios frequently arise in domains like DNA sequence design and robotics, where only a few labeled data points are available. Traditional methods typically rely on task-specific proxy or generative models, overlooking the in-context learning capabilities of pre-trained large language models (LLMs). Recent efforts have adapted autoregressive LLMs to BBO by framing task descriptions and offline datasets as natural language prompts, enabling direct design generation. However, these designs often contain bidirectional dependencies, which left-to-right models struggle to capture. In this paper, we explore diffusion LLMs for BBO, leveraging their bidirectional modeling and iterative refinement capabilities. This motivates our in-context denoising module: we condition the diffusion LLM on the task description and the offline dataset, both formatted in natural language, and prompt it to denoise masked designs into improved candidates. To guide the generation toward high-performing designs, we introduce masked diffusion tree search, which casts the denoising process as a step-wise Monte Carlo Tree Search that dynamically balances exploration and exploitation. Each node represents a partially masked design, each denoising step is an action, and candidates are evaluated via expected improvement under a Gaussian Process trained on the offline dataset. Our method, dLLM, achieves state-of-the-art results in few-shot settings on design-bench.

---

### VisTIRA: Closing the Image-Text Modality Gap in Visual Math Reasoning via Structured Tool Integration

Authors: Saeed Khaki, Ashudeep Singh, Nima Safaei, Kamal Ginotra
Published: 2026-01-20
Categories: cs.AI, cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2601.14440v2

Vision-language models (VLMs) lag behind text-only language models on mathematical reasoning when the same problems are presented as images rather than text. We empirically characterize this as a modality gap: the same question in text form yields markedly higher accuracy than its visually typeset counterpart, due to compounded failures in reading dense formulas, layout, and mixed symbolic-diagrammatic context. First, we introduce VisTIRA (Vision and Tool-Integrated Reasoning Agent), a tool-integrated reasoning framework that enables structured problem solving by iteratively decomposing a given math problem (as an image) into natural language rationales and executable Python steps to determine the final answer. Second, we build a framework to measure and improve visual math reasoning: a LaTeX-based pipeline that converts chain-of-thought math corpora (e.g., NuminaMath) into challenging image counterparts, and a large set of synthetic tool-use trajectories derived from a real-world, homework-style image dataset (called SnapAsk) for fine-tuning VLMs. Our experiments show that tool-integrated supervision improves image-based reasoning, and OCR grounding can further narrow the gap for smaller models, although its benefit diminishes at scale. These findings highlight that modality gap severity inversely correlates with model size, and that structured reasoning and OCR-based grounding are complementary strategies for advancing visual mathematical reasoning.

---

### Vision-Based Natural Language Scene Understanding for Autonomous Driving: An Extended Dataset and a New Model for Traffic Scene Description Generation

Authors: Danial Sadrian Zadeh, Otman A. Basir, Behzad Moshiri
Published: 2026-01-20
Categories: cs.CV, cs.AI, cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2601.14438v1

Traffic scene understanding is essential for enabling autonomous vehicles to accurately perceive and interpret their environment, thereby ensuring safe navigation. This paper presents a novel framework that transforms a single frontal-view camera image into a concise natural language description, effectively capturing spatial layouts, semantic relationships, and driving-relevant cues. The proposed model leverages a hybrid attention mechanism to enhance spatial and semantic feature extraction and integrates these features to generate contextually rich and detailed scene descriptions. To address the limited availability of specialized datasets in this domain, a new dataset derived from the BDD100K dataset has been developed, with comprehensive guidelines provided for its construction. Furthermore, the study offers an in-depth discussion of relevant evaluation metrics, identifying the most appropriate measures for this task. Extensive quantitative evaluations using metrics such as CIDEr and SPICE, complemented by human judgment assessments, demonstrate that the proposed model achieves strong performance and effectively fulfills its intended objectives on the newly developed dataset.

---

### Agentic AI Meets Edge Computing in Autonomous UAV Swarms

Authors: Thuan Minh Nguyen, Vu Tuan Truong, Long Bao Le
Published: 2026-01-20
Categories: cs.RO, cs.AI
arXiv: https://arxiv.org/abs/2601.14437v1

The integration of agentic AI, powered by large language models (LLMs) with autonomous reasoning, planning, and execution, into unmanned aerial vehicle (UAV) swarms opens new operational possibilities and brings the vision of the Internet of Drones closer to reality. However, infrastructure constraints, dynamic environments, and the computational demands of multi-agent coordination limit real-world deployment in high-risk scenarios such as wildfires and disaster response. This paper investigates the integration of LLM-based agentic AI and edge computing to realize scalable and resilient autonomy in UAV swarms. We first discuss three architectures for supporting UAV swarms - standalone, edge-enabled, and edge-cloud hybrid deployment - each optimized for varying autonomy and connectivity levels. Then, a use case for wildfire search and rescue (SAR) is designed to demonstrate the efficiency of the edge-enabled architecture, enabling high SAR coverage, reduced mission completion times, and a higher level of autonomy compared to traditional approaches. Finally, we highlight open challenges in integrating LLMs and edge computing for mission-critical UAV-swarm applications.

---

### A full process algebraic representation of Ant Colony Optimization

Authors: Maria Garcia, Natalia Lopez, Ismael Rodriguez
Published: 2026-01-20
Categories: cs.NE
arXiv: https://arxiv.org/abs/2601.14436v1

We present a process algebra capable of specifying parallelized Ant Colony Optimization algorithms in full detail: PA$^2$CO. After explaining the basis of three different ACO algorithms (Ant System, MAX-MIN Ant System, and Ant Colony System), we formally define PA$^2$CO and use it for representing several types of implementations with different parallel schemes. In particular fine-grained and coarse-grained specifications, each one taking advantage of parallel executions at different levels of system granularity, are formalized.

---

### Quantum Super-resolution by Adaptive Non-local Observables

Authors: Hsin-Yi Lin, Huan-Hsin Tseng, Samuel Yen-Chi Chen, Shinjae Yoo
Published: 2026-01-20
Categories: quant-ph, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2601.14433v2

Super-resolution (SR) seeks to reconstruct high-resolution (HR) data from low-resolution (LR) observations. Classical deep learning methods have advanced SR substantially, but require increasingly deeper networks, large datasets, and heavy computation to capture fine-grained correlations. In this work, we present the \emph{first study} to investigate quantum circuits for SR. We propose a framework based on Variational Quantum Circuits (VQCs) with \emph{Adaptive Non-Local Observable} (ANO) measurements. Unlike conventional VQCs with fixed Pauli readouts, ANO introduces trainable multi-qubit Hermitian observables, allowing the measurement process to adapt during training. This design leverages the high-dimensional Hilbert space of quantum systems and the representational structure provided by entanglement and superposition. Experiments demonstrate that ANO-VQCs achieve up to five-fold higher resolution with a relatively small model size, suggesting a promising new direction at the intersection of quantum machine learning and super-resolution.

---

### Meta Flow Maps enable scalable reward alignment

Authors: Peter Potaptchik, Adhi Saravanan, Abbas Mammadov, Alvaro Prat, Michael S. Albergo, Yee Whye Teh
Published: 2026-01-20
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2601.14430v2

Controlling generative models is computationally expensive. This is because optimal alignment with a reward function--whether via inference-time steering or fine-tuning--requires estimating the value function. This task demands access to the conditional posterior $p_{1|t}(x_1|x_t)$, the distribution of clean data $x_1$ consistent with an intermediate state $x_t$, a requirement that typically compels methods to resort to costly trajectory simulations. To address this bottleneck, we introduce Meta Flow Maps (MFMs), a framework extending consistency models and flow maps into the stochastic regime. MFMs are trained to perform stochastic one-step posterior sampling, generating arbitrarily many i.i.d. draws of clean data $x_1$ from any intermediate state. Crucially, these samples provide a differentiable reparametrization that unlocks efficient value function estimation. We leverage this capability to solve bottlenecks in both paradigms: enabling inference-time steering without inner rollouts, and facilitating unbiased, off-policy fine-tuning to general rewards. Empirically, our single-particle steered-MFM sampler outperforms a Best-of-1000 baseline on ImageNet across multiple rewards at a fraction of the compute.

---

### Measuring the State of Open Science in Transportation Using Large Language Models

Authors: Junyi Ji, Ruth Lu, Linda Belkessa, Liming Wang, Silvia Varotto, Yongqi Dong, Nicolas Saunier, Mostafa Ameli, Gregory S. Macfarlane, Bahman Madadi, Cathy Wu
Published: 2026-01-20
Categories: cs.DL, cs.AI, cs.CY, cs.ET
arXiv: https://arxiv.org/abs/2601.14429v2

Open science initiatives have strengthened scientific integrity and accelerated research progress across many fields, but the state of their practice within transportation research remains under-investigated. Key features of open science, defined here as data and code availability, are difficult to extract due to the inherent complexity of the field. Previous work has either been limited to small-scale studies due to the labor-intensive nature of manual analysis or has relied on large-scale bibliometric approaches that sacrifice contextual richness. This paper introduces an automatic and scalable feature-extraction pipeline to measure code and data availability in transportation research. We employ Large Language Models (LLMs) for this task and validate their performance against a manually curated dataset and through an inter-rater agreement analysis. We applied this pipeline to examine 10,724 research articles published in the Transportation Research Part series of journals between 2019 and 2024. Our analysis found that only 5% of quantitative papers shared a code repository, 4% of quantitative papers shared a data repository, and about 3% of papers shared both, with trends differing across journals, topics, and geographic regions. We found no significant difference in citation counts or review duration between papers that provided data and code and those that did not, suggesting a misalignment between open science efforts and traditional academic metrics. Consequently, encouraging these practices will likely require structural interventions from journals and funding agencies to supplement the lack of direct author incentives. The pipeline developed in this study can be readily scaled to other journals, representing a critical step toward the automated measurement and monitoring of open science practices in transportation research.

---

### Quantifying Speaker Embedding Phonological Rule Interactions in Accented Speech Synthesis

Authors: Thanathai Lertpetchpun, Yoonjeong Lee, Thanapat Trachu, Jihwan Lee, Tiantian Feng, Dani Byrd, Shrikanth Narayanan
Published: 2026-01-20
Categories: cs.CL
arXiv: https://arxiv.org/abs/2601.14417v2

Many spoken languages, including English, exhibit wide variation in dialects and accents, making accent control an important capability for flexible text-to-speech (TTS) models. Current TTS systems typically generate accented speech by conditioning on speaker embeddings associated with specific accents. While effective, this approach offers limited interpretability and controllability, as embeddings also encode traits such as timbre and emotion. In this study, we analyze the interaction between speaker embeddings and linguistically motivated phonological rules in accented speech synthesis. Using American and British English as a case study, we implement rules for flapping, rhoticity, and vowel correspondences. We propose the phoneme shift rate (PSR), a novel metric quantifying how strongly embeddings preserve or override rule-based transformations. Experiments show that combining rules with embeddings yields more authentic accents, while embeddings can attenuate or overwrite rules, revealing entanglement between accent and speaker identity. Our findings highlight rules as a lever for accent control and a framework for evaluating disentanglement in speech generation.

---

### Large-Scale Label Quality Assessment for Medical Segmentation via a Vision-Language Judge and Synthetic Data

Authors: Yixiong Chen, Zongwei Zhou, Wenxuan Li, Alan Yuille
Published: 2026-01-20
Categories: cs.CV, eess.IV
arXiv: https://arxiv.org/abs/2601.14406v1

Large-scale medical segmentation datasets often combine manual and pseudo-labels of uneven quality, which can compromise training and evaluation. Low-quality labels may hamper performance and make the model training less robust. To address this issue, we propose SegAE (Segmentation Assessment Engine), a lightweight vision-language model (VLM) that automatically predicts label quality across 142 anatomical structures. Trained on over four million image-label pairs with quality scores, SegAE achieves a high correlation coefficient of 0.902 with ground-truth Dice similarity and evaluates a 3D mask in 0.06s. SegAE shows several practical benefits: (I) Our analysis reveals widespread low-quality labeling across public datasets; (II) SegAE improves data efficiency and training performance in active and semi-supervised learning, reducing dataset annotation cost by one-third and quality-checking time by 70% per label. This tool provides a simple and effective solution for quality control in large-scale medical segmentation datasets. The dataset, model weights, and codes are released at https://github.com/Schuture/SegAE.

---

### Recursivism: An Artistic Paradigm for Self-Transforming Art in the Age of AI

Authors: Florentin Koch
Published: 2026-01-20
Categories: cs.CY, cs.AI, cs.HC
arXiv: https://arxiv.org/abs/2601.14401v1

This article introduces Recursivism as a conceptual framework for analyzing contemporary artistic practices in the age of artificial intelligence. While recursion is precisely defined in mathematics and computer science, it has not previously been formalized as an aesthetic paradigm. Recursivism designates practices in which not only outputs vary over time, but in which the generative process itself becomes capable of reflexive modification through its own effects. The paper develops a five-level analytical scale distinguishing simple iteration, cumulative iteration, parametric recursion, reflexive recursion, and meta-recursion. This scale clarifies the threshold at which a system shifts from variation within a fixed rule to genuine self-modification of the rule itself. From this perspective, art history is reinterpreted as a recursive dynamic alternating between internal recursion within movements and meta-recursive transformations of their generative principles. Artificial intelligence renders this logic technically explicit through learning loops, parameter updates, and code-level self-modification. To distinguish Recursivism from related notions such as generative art, cybernetics, process art, and evolutionary art, the article proposes three operational criteria: state memory, rule evolvability, and reflexive visibility. These concepts are examined through case studies including Refik Anadol, Sougwen Chung, Karl Sims, and the Darwin-Godel Machine. The article concludes by examining the aesthetic, curatorial, and ethical implications of self-modifying artistic systems.

---

### Cosmo-FOLD: Fast generation and upscaling of field-level cosmological maps with overlap latent diffusion

Authors: Satvik Mishra, Roberto Trotta, Matteo Viel
Published: 2026-01-20
Categories: astro-ph.CO, astro-ph.IM, cs.LG
arXiv: https://arxiv.org/abs/2601.14377v1

We demonstrate the capabilities of probabilistic diffusion models to reduce dramatically the computational cost of expensive hydrodynamical simulations to study the relationship between observable baryonic cosmological probes and dark matter at field level and well into the non-linear regime. We introduce a novel technique, Cosmo-FOLD (Cosmological Fields via Overlap Latent Diffusion) to rapidly generate accurate and arbitrarily large cosmological and astrophysical 3-dimensional fields, conditioned on a given input field. We are able to generate TNG300-2 dark matter density and gas temperature fields from a model trained only on ~1% of the volume (a process we refer to as `upscaling'), reproducing both large scale coherent dark matter filaments and power spectra to within 10% for wavenumbers k <= 5 h Mpc^-1. These results are obtained within a small fraction of the original simulation cost and produced on a single GPU. Beyond one and two points statistics, the bispectrum is also faithfully reproduced through the inclusion of positional encodings. Finally, we demonstrate Cosmo-FOLD's generalisation capabilities by upscaling a CAMELS volume of 25 (Mpc h^-1)^3 to a full TNG300-2 volume of 205 (Mpc h^-1)^3$ with no fine-tuning. Cosmo-FOLD opens the door to full field-level simulation-based inference on cosmological scale.

---

### VJEPA: Variational Joint Embedding Predictive Architectures as Probabilistic World Models

Authors: Yongchao Huang
Published: 2026-01-20
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.14354v1

Joint Embedding Predictive Architectures (JEPA) offer a scalable paradigm for self-supervised learning by predicting latent representations rather than reconstructing high-entropy observations. However, existing formulations rely on \textit{deterministic} regression objectives, which mask probabilistic semantics and limit its applicability in stochastic control. In this work, we introduce \emph{Variational JEPA (VJEPA)}, a \textit{probabilistic} generalization that learns a predictive distribution over future latent states via a variational objective. We show that VJEPA unifies representation learning with Predictive State Representations (PSRs) and Bayesian filtering, establishing that sequential modeling does not require autoregressive observation likelihoods. Theoretically, we prove that VJEPA representations can serve as sufficient information states for optimal control without pixel reconstruction, while providing formal guarantees for collapse avoidance. We further propose \emph{Bayesian JEPA (BJEPA)}, an extension that factorizes the predictive belief into a learned dynamics expert and a modular prior expert, enabling zero-shot task transfer and constraint (e.g. goal, physics) satisfaction via a Product of Experts. Empirically, through a noisy environment experiment, we demonstrate that VJEPA and BJEPA successfully filter out high-variance nuisance distractors that cause representation collapse in generative baselines. By enabling principled uncertainty estimation (e.g. constructing credible intervals via sampling) while remaining likelihood-free regarding observations, VJEPA provides a foundational framework for scalable, robust, uncertainty-aware planning in high-dimensional, noisy environments.

---

### If You Want Coherence, Orchestrate a Team of Rivals: Multi-Agent Models of Organizational Intelligence

Authors: Gopal Vijayaraghavan, Prasanth Jayachandran, Arun Murthy, Sunil Govindan, Vivek Subramanian
Published: 2026-01-20
Categories: cs.MA, cs.AI
arXiv: https://arxiv.org/abs/2601.14351v1

AI Agents can perform complex operations at great speed, but just like all the humans we have ever hired, their intelligence remains fallible. Miscommunications aren't noticed, systemic biases have no counter-action, and inner monologues are rarely written down. We did not come to fire them for their mistakes, but to hire them and provide a safe productive working environment. We posit that we can reuse a common corporate organizational structure: teams of independent AI agents with strict role boundaries can work with common goals, but opposing incentives. Multiple models serving as a team of rivals can catch and minimize errors within the final product at a small cost to the velocity of actions. In this paper we demonstrate that we can achieve reliability without acquiring perfect components, but through careful orchestration of imperfect ones. This paper describes the architecture of such a system in practice: specialized agent teams (planners, executors, critics, experts), organized into an organization with clear goals, coordinated through a remote code executor that keeps data transformations and tool invocations separate from reasoning models. Rather than agents directly calling tools and ingesting full responses, they write code that executes remotely; only relevant summaries return to agent context. By preventing raw data and tool outputs from contaminating context windows, the system maintains clean separation between perception (brains that plan and reason) and execution (hands that perform heavy data transformations and API calls). We demonstrate the approach achieves over 90% internal error interception prior to user exposure while maintaining acceptable latency tradeoffs. A survey from our traces shows that we only trade off cost and latency to achieve correctness and incrementally expand capabilities without impacting existing ones.

---

### MARBLE: Multi-Agent Reasoning for Bioinformatics Learning and Evolution

Authors: Sunghyun Kim, Seokwoo Yun, Youngseo Yun, Youngrak Lee, Sangsoo Lim
Published: 2026-01-20
Categories: cs.MA, cs.LG
arXiv: https://arxiv.org/abs/2601.14349v1

Motivation: Developing high-performing bioinformatics models typically requires repeated cycles of hypothesis formulation, architectural redesign, and empirical validation, making progress slow, labor-intensive, and difficult to reproduce. Although recent LLM-based assistants can automate isolated steps, they lack performance-grounded reasoning and stability-aware mechanisms required for reliable, iterative model improvement in bioinformatics workflows. Results: We introduce MARBLE, an execution-stable autonomous model refinement framework for bioinformatics models. MARBLE couples literature-aware reference selection with structured, debate-driven architectural reasoning among role-specialized agents, followed by autonomous execution, evaluation, and memory updates explicitly grounded in empirical performance. Across spatial transcriptomics domain segmentation, drug-target interaction prediction, and drug response prediction, MARBLE consistently achieves sustained performance improvements over strong baselines across multiple refinement cycles, while maintaining high execution robustness and low regression rates. Framework-level analyses demonstrate that structured debate, balanced evidence selection, and performance-grounded memory are critical for stable, repeatable model evolution, rather than single-run or brittle gains. Availability: Source code, data and Supplementary Information are available at https://github.com/PRISM-DGU/MARBLE.

---

### DiSPA: Differential Substructure-Pathway Attention for Drug Response Prediction

Authors: Yewon Han, Sunghyun Kim, Eunyi Jeong, Sungkyung Lee, Seokwoo Yun, Sangsoo Lim
Published: 2026-01-20
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2601.14346v2

Accurate prediction of drug response in precision medicine requires models that capture how specific chemical substructures interact with cellular pathway states. However, most existing deep learning approaches treat chemical and transcriptomic modalities independently or combine them only at late stages, limiting their ability to model fine-grained, context-dependent mechanisms of drug action. In addition, vanilla attention mechanisms are often sensitive to noise and sparsity in high-dimensional biological networks, hindering both generalization and interpretability. We present DiSPA (Differential Substructure-Pathway Attention), a framework that models bidirectional interactions between chemical substructures and pathway-level gene expression. DiSPA introduces differential cross-attention to suppress spurious associations while enhancing context-relevant interactions. On the GDSC benchmark, DiSPA achieves state-of-the-art performance, with strong improvements in the disjoint setting. These gains are consistent across random and drug-blind splits, suggesting improved robustness. Analyses of attention patterns indicate more selective and concentrated interactions compared to standard cross-attention. Exploratory evaluation shows that differential attention better prioritizes predefined target-related pathways, although this does not constitute mechanistic validation. DiSPA also shows promising generalization on external datasets (CTRP) and cross-dataset settings, although further validation is needed. It further enables zero-shot application to spatial transcriptomics, providing exploratory insights into region-specific drug sensitivity patterns without ground-truth validation.

---

### Turn-Based Structural Triggers: Structure-Conditioned Backdoors in Multi-Turn LLMs

Authors: Yiyang Lu, Jinwen He, Yue Zhao, Kai Chen, Ruigang Liang, Cheng Hong, Yingjun Zhang
Published: 2026-01-20
Categories: cs.CR, cs.LG
arXiv: https://arxiv.org/abs/2601.14340v3

Large Language Models (LLMs) are increasingly deployed as multi-turn assistants and customized through instruction tuning with project-specific training components. This practice creates a supply-chain risk when organizations reuse third-party fine-tuning frameworks, trainer extensions, or outsourced training code: an adversary who subtly compromises the loss-computation component can inject malicious supervision during fine-tuning while leaving the stored training corpus, model architecture, and deployment interface unchanged. Existing LLM backdoors and defenses are largely prompt-centric, relying on lexical, syntactic, or semantic patterns in user inputs while overlooking structural signals in multi-turn conversations. We propose Turn-based Structural Trigger (TST), a prompt-free backdoor that uses dialogue turn position as its activation condition. TST exploits structural cues implicitly encoded by chat templates and is implanted without modifying the stored dialogue corpus. Its trigger is automatically present once the conversation reaches the attacker-specified turn, making activation independent of downstream user inputs and resistant to prompt filtering, sanitization, and paraphrasing. In our primary setting, the model behaves normally during early interactions and activates the attacker-defined behavior only after the conversation reaches the designated structural condition. Across four open-source LLM families, TST achieves an average Attack Success Rate of 98.10% on target turns and a Clean Rate of 99.96% on non-target turns, while retaining 97.78% of clean-model utility. These results identify dialogue structure as an overlooked attack surface and motivate structure-aware auditing beyond prompt inspection.

---

### CityCube: Benchmarking Cross-view Spatial Reasoning on Vision-Language Models in Urban Environments

Authors: Haotian Xu, Yue Hu, Zhengqiu Zhu, Chen Gao, Ziyou Wang, Junreng Rao, Wenhao Lu, Weishi Li, Quanjun Yin, Yong Li
Published: 2026-01-20
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2601.14339v1

Cross-view spatial reasoning is essential for embodied AI, underpinning spatial understanding, mental simulation and planning in complex environments. Existing benchmarks primarily emphasize indoor or street settings, overlooking the unique challenges of open-ended urban spaces characterized by rich semantics, complex geometries, and view variations. To address this, we introduce CityCube, a systematic benchmark designed to probe cross-view reasoning capabilities of current VLMs in urban settings. CityCube integrates four viewpoint dynamics to mimic camera movements and spans a wide spectrum of perspectives from multiple platforms, e.g., vehicles, drones and satellites. For a comprehensive assessment, it features 5,022 meticulously annotated multi-view QA pairs categorized into five cognitive dimensions and three spatial relation expressions. A comprehensive evaluation of 33 VLMs reveals a significant performance disparity with humans: even large-scale models struggle to exceed 54.1% accuracy, remaining 34.2% below human performance. By contrast, small-scale fine-tuned VLMs achieve over 60.0% accuracy, highlighting the necessity of our benchmark. Further analyses indicate the task correlations and fundamental cognitive disparity between VLMs and human-like reasoning.

---

### Partial Decoder Attention Network with Contour-weighted Loss Function for Data-Imbalance Medical Image Segmentation

Authors: Zhengyong Huang, Ning Jiang, Xingwen Sun, Lihua Zhang, Peng Chen, Jens Domke, Yao Sui
Published: 2026-01-20
Categories: eess.IV, cs.CV
arXiv: https://arxiv.org/abs/2601.14338v1

Image segmentation is pivotal in medical image analysis, facilitating clinical diagnosis, treatment planning, and disease evaluation. Deep learning has significantly advanced automatic segmentation methodologies by providing superior modeling capability for complex structures and fine-grained anatomical regions. However, medical images often suffer from data imbalance issues, such as large volume disparities among organs or tissues, and uneven sample distributions across different anatomical structures. This imbalance tends to bias the model toward larger organs or more frequently represented structures, while overlooking smaller or less represented structures, thereby affecting the segmentation accuracy and robustness. To address these challenges, we proposed a novel contour-weighted segmentation approach, which improves the model's capability to represent small and underrepresented structures. We developed PDANet, a lightweight and efficient segmentation network based on a partial decoder mechanism. We evaluated our method using three prominent public datasets. The experimental results show that our methodology excelled in three distinct tasks: segmenting multiple abdominal organs, brain tumors, and pelvic bone fragments with injuries. It consistently outperformed nine state-of-the-art methods. Moreover, the proposed contour-weighted strategy improved segmentation for other comparison methods across the three datasets, yielding average enhancements in Dice scores of 2.32%, 1.67%, and 3.60%, respectively. These results demonstrate that our contour-weighted segmentation method surpassed current leading approaches in both accuracy and robustness. As a model-independent strategy, it can seamlessly fit various segmentation frameworks, enhancing their performance. This flexibility highlighted its practical importance and potential for broad use in medical image analysis.

---

### Unsupervised Deformable Image Registration with Local-Global Attention and Image Decomposition

Authors: Zhengyong Huang, Xingwen Sun, Xuting Chang, Ning Jiang, Yao Wang, Jianfei Sun, Hongbin Han, Yao Sui
Published: 2026-01-20
Categories: eess.IV, cs.CV
arXiv: https://arxiv.org/abs/2601.14337v1

Deformable image registration is a critical technology in medical image analysis, with broad applications in clinical practice such as disease diagnosis, multi-modal fusion, and surgical navigation. Traditional methods often rely on iterative optimization, which is computationally intensive and lacks generalizability. Recent advances in deep learning have introduced attention-based mechanisms that improve feature alignment, yet accurately registering regions with high anatomical variability remains challenging. In this study, we proposed a novel unsupervised deformable image registration framework, LGANet++, which employs a novel local-global attention mechanism integrated with a unique technique for feature interaction and fusion to enhance registration accuracy, robustness, and generalizability. We evaluated our approach using five publicly available datasets, representing three distinct registration scenarios: cross-patient, cross-time, and cross-modal CT-MR registration. The results demonstrated that our approach consistently outperforms several state-of-the-art registration methods, improving registration accuracy by 1.39% in cross-patient registration, 0.71% in cross-time registration, and 6.12% in cross-modal CT-MR registration tasks. These results underscore the potential of LGANet++ to support clinical workflows requiring reliable and efficient image registration. The source code is available at https://github.com/huangzyong/LGANet-Registration.

---

### Log anomaly detection via Meta Learning and Prototypical Networks for Cross domain generalization

Authors: Krishna Sharma, Vivek Yelleti
Published: 2026-01-20
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.14336v1

Log anomaly detection is essential for system reliability, but it is extremely challenging to do considering it involves class imbalance. Additionally, the models trained in one domain are not applicable to other domains, necessitating the need for cross-domain adaptation (such as HDFS and Linux). Traditional detection models often fail to generalize due to significant data drift and the inherent absence of labeled anomalies in new target domains. To handle the above challenges, we proposed a new end-to-end framework based on a meta-learning approach. Our methodology first gets the data ready by combining a Drain3 log parsing mechanism with a dynamic drift-based labeling technique that uses semantic and fuzzy matching to move existing anomaly knowledge from one source to another. BERT-based semantic embeddings are obtained, and the feature selection is invoked to reduce the dimensionality. Later, Model Agnostic Meta-Learning (MAML) and Prototypical Networks models are trained to adapt quickly and effectively. The SMOTE oversampling method is employed to handle imbalances in the data. All the results are obtained by employing the leave-one-out source method, and the corresponding mean F1 scores are reported. Our empirical findings validate that the proposed meta-learning-driven approach yielded the highest mean F1 score and proved to be effective for cross-domain settings.

---

### Self-Supervised Score-Based Despeckling for SAR Imagery via Log-Domain Transformation

Authors: Junhyuk Heo
Published: 2026-01-20
Categories: eess.IV, cs.AI, cs.CV
arXiv: https://arxiv.org/abs/2601.14334v1

The speckle noise inherent in Synthetic Aperture Radar (SAR) imagery significantly degrades image quality and complicates subsequent analysis. Given that SAR speckle is multiplicative and Gamma-distributed, effectively despeckling SAR imagery remains challenging. This paper introduces a novel self-supervised framework for SAR image despeckling based on score-based generative models operating in the transformed log domain. We first transform the data into the log-domain and then convert the speckle noise residuals into an approximately additive Gaussian distribution. This step enables the application of score-based models, which are trained in the transformed domain using a self-supervised objective. This objective allows our model to learn the clean underlying signal by training on further corrupted versions of the input data itself. Consequently, our method exhibits significantly shorter inference times compared to many existing self-supervised techniques, offering a robust and practical solution for SAR image restoration.

---

### Hierarchical Contextual Uplift Bandits for Catalog Personalization

Authors: Anupam Agrawal, Rajesh Mohanty, Shamik Bhattacharjee, Abhimanyu Mittal
Published: 2026-01-20
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.14333v1

Contextual Bandit (CB) algorithms are widely adopted for personalized recommendations but often struggle in dynamic environments typical of fantasy sports, where rapid changes in user behavior and dramatic shifts in reward distributions due to external influences necessitate frequent retraining. To address these challenges, we propose a Hierarchical Contextual Uplift Bandit framework. Our framework dynamically adjusts contextual granularity from broad, system-wide insights to detailed, user-specific contexts, using contextual similarity to facilitate effective policy transfer and mitigate cold-start issues. Additionally, we integrate uplift modeling principles into our approach. Results from large-scale A/B testing on the Dream11 fantasy sports platform show that our method significantly enhances recommendation quality, achieving a 0.4% revenue improvement while also improving user satisfaction metrics compared to the current production system. We subsequently deployed this system to production as the default catalog personalization system in May 2025 and observed a further 0.5% revenue improvement.

---

### LURE: Latent Space Unblocking for Multi-Concept Reawakening in Diffusion Models

Authors: Mengyu Sun, Ziyuan Yang, Andrew Beng Jin Teoh, Junxu Liu, Haibo Hu, Yi Zhang
Published: 2026-01-20
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2601.14330v2

Concept erasure aims to suppress sensitive content in diffusion models, but recent studies show that erased concepts can still be reawakened, revealing vulnerabilities in erasure methods. Existing reawakening methods mainly rely on prompt-level optimization to manipulate sampling trajectories, neglecting other generative factors, which limits a comprehensive understanding of the underlying dynamics. In this paper, we model the generation process as an implicit function to enable a comprehensive theoretical analysis of multiple factors, including text conditions, model parameters, and latent states. We theoretically show that perturbing each factor can reawaken erased concepts. Building on this insight, we propose a novel concept reawakening method: Latent space Unblocking for concept REawakening (LURE), which reawakens erased concepts by reconstructing the latent space and guiding the sampling trajectory. Specifically, our semantic re-binding mechanism reconstructs the latent space by aligning denoising predictions with target distributions to reestablish severed text-visual associations. However, in multi-concept scenarios, naive reconstruction can cause gradient conflicts and feature entanglement. To address this, we introduce Gradient Field Orthogonalization, which enforces feature orthogonality to prevent mutual interference. Additionally, our Latent Semantic Identification-Guided Sampling (LSIS) ensures stability of the reawakening process via posterior density verification. Extensive experiments demonstrate that LURE enables simultaneous, high-fidelity reawakening of multiple erased concepts across diverse erasure tasks and methods.

---

### Yuan3.0 Ultra: A Trillion-Parameter Enterprise-Oriented MoE LLM

Authors: YuanLab. ai, :, Shawn Wu, Jiangang Luo, Darcy Chen, Sean Wang, Louie Li, Allen Wang, Xudong Zhao, Tong Yu, Bach Li, Joseph Shen et al.
Published: 2026-01-20
Categories: cs.LG, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2601.14327v3

We introduce Yuan3.0 Ultra, an open-source Mixture-of-Experts (MoE) large language model featuring 68.8B activated parameters and 1010B total parameters, specially designed to enhance performance on enterprise scenarios tasks while maintaining competitive capabilities on general purpose tasks. We propose Layer-Adaptive Expert Pruning (LAEP) algorithm designed for the pre-training stage of MoE LLMs. In contrast to previous expert pruning approaches that operate primarily in the post-training phase, the proposed algorithm enhances training efficiency by selectively pruning underutilized experts and reorganizing experts across computing devices according to token distribution statistics. Comprehensive experiments demonstrate that LAEP effectively reduces model size and substantially improves pre-training efficiency. When pre-training Yuan3.0 Ultra from scratch original with 1515B parameters, this algorithm delivers a 49\% boost in pre-training efficiency and a 33.3\% reduction in total parameters, while preserving the model's outstanding multi-domain performance. On enterprise scenario benchmarks including Docmatix, ChatRAG, SummEval and MMTab, Yuan3.0 Ultra achieves leading accuracy. The model and codes are publicly available at https://github.com/Yuan-lab-LLM/Yuan3.0-Ultra.

---

### SilentDrift: Exploiting Action Chunking for Stealthy Backdoor Attacks on Vision-Language-Action Models

Authors: Bingxin Xu, Yuzhang Shang, Binghui Wang, Emilio Ferrara
Published: 2026-01-20
Categories: cs.CR, cs.AI, cs.RO
arXiv: https://arxiv.org/abs/2601.14323v2

Vision-Language-Action (VLA) models are increasingly deployed in safety-critical robotic applications, yet their security vulnerabilities remain underexplored. We identify a fundamental security flaw in modern VLA systems: the combination of action chunking and delta pose representations creates an intra-chunk visual open-loop. This mechanism forces the robot to execute K-step action sequences, allowing per-step perturbations to accumulate through integration. We propose SILENTDRIFT, a stealthy black-box backdoor attack exploiting this vulnerability. Our method employs the Smootherstep function to construct perturbations with guaranteed C2 continuity, ensuring zero velocity and acceleration at trajectory boundaries to satisfy strict kinematic consistency constraints. Furthermore, our keyframe attack strategy selectively poisons only the critical approach phase, maximizing impact while minimizing trigger exposure. The resulting poisoned trajectories are visually indistinguishable from successful demonstrations. Evaluated on the LIBERO, SILENTDRIFT achieves a 93.2% Attack Success Rate with a poisoning rate under 2%, while maintaining a 95.3% Clean Task Success Rate.

---

### Implicit Neural Representation Facilitates Unified Universal Vision Encoding

Authors: Matthew Gwilliam, Xiao Wang, Xuefeng Hu, Zhenheng Yang
Published: 2026-01-20
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.14256v1

Models for image representation learning are typically designed for either recognition or generation. Various forms of contrastive learning help models learn to convert images to embeddings that are useful for classification, detection, and segmentation. On the other hand, models can be trained to reconstruct images with pixel-wise, perceptual, and adversarial losses in order to learn a latent space that is useful for image generation. We seek to unify these two directions with a first-of-its-kind model that learns representations which are simultaneously useful for recognition and generation. We train our model as a hyper-network for implicit neural representation, which learns to map images to model weights for fast, accurate reconstruction. We further integrate our INR hyper-network with knowledge distillation to improve its generalization and performance. Beyond the novel training design, the model also learns an unprecedented compressed embedding space with outstanding performance for various visual tasks. The complete model competes with state-of-the-art results for image representation learning, while also enabling generative capabilities with its high-quality tiny embeddings. The code is available at https://github.com/tiktok/huvr.

---

### VideoMaMa: Mask-Guided Video Matting via Generative Prior

Authors: Sangbeom Lim, Seoung Wug Oh, Jiahui Huang, Heeji Yoon, Seungryong Kim, Joon-Young Lee
Published: 2026-01-20
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2601.14255v1

Generalizing video matting models to real-world videos remains a significant challenge due to the scarcity of labeled data. To address this, we present Video Mask-to-Matte Model (VideoMaMa) that converts coarse segmentation masks into pixel accurate alpha mattes, by leveraging pretrained video diffusion models. VideoMaMa demonstrates strong zero-shot generalization to real-world footage, even though it is trained solely on synthetic data. Building on this capability, we develop a scalable pseudo-labeling pipeline for large-scale video matting and construct the Matting Anything in Video (MA-V) dataset, which offers high-quality matting annotations for more than 50K real-world videos spanning diverse scenes and motions. To validate the effectiveness of this dataset, we fine-tune the SAM2 model on MA-V to obtain SAM2-Matte, which outperforms the same model trained on existing matting datasets in terms of robustness on in-the-wild videos. These findings emphasize the importance of large-scale pseudo-labeled video matting and showcase how generative priors and accessible segmentation cues can drive scalable progress in video matting research.

---

### Motion 3-to-4: 3D Motion Reconstruction for 4D Synthesis

Authors: Hongyuan Chen, Xingyu Chen, Youjia Zhang, Zexiang Xu, Anpei Chen
Published: 2026-01-20
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.14253v1

We present Motion 3-to-4, a feed-forward framework for synthesising high-quality 4D dynamic objects from a single monocular video and an optional 3D reference mesh. While recent advances have significantly improved 2D, video, and 3D content generation, 4D synthesis remains difficult due to limited training data and the inherent ambiguity of recovering geometry and motion from a monocular viewpoint. Motion 3-to-4 addresses these challenges by decomposing 4D synthesis into static 3D shape generation and motion reconstruction. Using a canonical reference mesh, our model learns a compact motion latent representation and predicts per-frame vertex trajectories to recover complete, temporally coherent geometry. A scalable frame-wise transformer further enables robustness to varying sequence lengths. Evaluations on both standard benchmarks and a new dataset with accurate ground-truth geometry show that Motion 3-to-4 delivers superior fidelity and spatial consistency compared to prior work. Project page is available at https://motion3-to-4.github.io/.

---

### LightOnOCR: A 1B End-to-End Multilingual Vision-Language Model for State-of-the-Art OCR

Authors: Said Taghadouini, Adrien Cavaillès, Baptiste Aubertin
Published: 2026-01-20
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.14251v2

We present LightOnOCR-2-1B, a 1B-parameter end-to-end multilingual vision--language model that converts document images (e.g., PDFs) into clean, naturally ordered text without brittle OCR pipelines. Trained on a large-scale, high-quality distillation mix with strong coverage of scans, French documents, and scientific PDFs, LightOnOCR-2 achieves state-of-the-art results on OlmOCR-Bench while being 9$\times$ smaller and substantially faster than prior best-performing models. We further extend the output format to predict normalized bounding boxes for embedded images, introducing localization during pretraining via a resume strategy and refining it with RLVR using IoU-based rewards. Finally, we improve robustness with checkpoint averaging and task-arithmetic merging. We release model checkpoints under Apache 2.0, and publicly release the dataset and LightOnOCR-bbox-bench evaluation under their respective licenses.

---

### OmniTransfer: All-in-one Framework for Spatio-temporal Video Transfer

Authors: Pengze Zhang, Yanze Wu, Mengtian Li, Xu Bai, Songtao Zhao, Fulong Ye, Chong Mou, Xinghui Li, Zhuowei Chen, Qian He, Mingyuan Gao
Published: 2026-01-20
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.14250v1

Videos convey richer information than images or text, capturing both spatial and temporal dynamics. However, most existing video customization methods rely on reference images or task-specific temporal priors, failing to fully exploit the rich spatio-temporal information inherent in videos, thereby limiting flexibility and generalization in video generation. To address these limitations, we propose OmniTransfer, a unified framework for spatio-temporal video transfer. It leverages multi-view information across frames to enhance appearance consistency and exploits temporal cues to enable fine-grained temporal control. To unify various video transfer tasks, OmniTransfer incorporates three key designs: Task-aware Positional Bias that adaptively leverages reference video information to improve temporal alignment or appearance consistency; Reference-decoupled Causal Learning separating reference and target branches to enable precise reference transfer while improving efficiency; and Task-adaptive Multimodal Alignment using multimodal semantic guidance to dynamically distinguish and tackle different tasks. Extensive experiments show that OmniTransfer outperforms existing methods in appearance (ID and style) and temporal transfer (camera movement and video effects), while matching pose-guided methods in motion transfer without using pose, establishing a new paradigm for flexible, high-fidelity video generation.

---

### Which Reasoning Trajectories Teach Students to Reason Better? A Simple Metric of Informative Alignment

Authors: Yuming Yang, Mingyoung Lai, Wanxu Zhao, Xiaoran Fan, Zhiheng Xi, Mingqi Wu, Chiyue Huang, Jun Zhao, Haijun Lv, Jian Tong, Yunhua Zhou, Yicheng Zou et al.
Published: 2026-01-20
Categories: cs.CL
arXiv: https://arxiv.org/abs/2601.14249v5

Long chain-of-thought (CoT) trajectories provide rich supervision signals for distilling reasoning from teacher to student LLMs. However, both prior work and our experiments show that trajectories from stronger teachers do not necessarily yield better students, highlighting the importance of data-student suitability in distillation. Existing methods assess suitability primarily through student likelihood, favoring trajectories that align closely with the student model's current behavior but overlooking more informative ones. Addressing this, we propose Rank-Surprisal Ratio (RSR), a simple metric that captures both alignment and informativeness to assess the suitability of a reasoning trajectory. RSR is motivated by the observation that effective trajectories typically balance learning signal strength and behavioral alignment by combining low absolute probability with relatively high-ranked tokens under the student model. Concretely, RSR is defined as the ratio of a trajectory's average token-wise rank to its average negative log-likelihood, and is straightforward to compute and interpret. Across five student models and reasoning trajectories from 11 diverse teachers, RSR strongly correlates with post-training reasoning performance (average Spearman 0.86), consistently outperforming existing metrics. We further demonstrate its practical utility in both trajectory selection and teacher selection.

---

### Soft Tail-dropping for Adaptive Visual Tokenization

Authors: Zeyuan Chen, Kai Zhang, Zhuowen Tu, Yuanjun Xiong
Published: 2026-01-20
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.14246v1

We present Soft Tail-dropping Adaptive Tokenizer (STAT), a 1D discrete visual tokenizer that adaptively chooses the number of output tokens per image according to its structural complexity and level of detail. STAT encodes an image into a sequence of discrete codes together with per-token keep probabilities. Beyond standard autoencoder objectives, we regularize these keep probabilities to be monotonically decreasing along the sequence and explicitly align their distribution with an image-level complexity measure. As a result, STAT produces length-adaptive 1D visual tokens that are naturally compatible with causal 1D autoregressive (AR) visual generative models. On ImageNet-1k, equipping vanilla causal AR models with STAT yields competitive or superior visual generation quality compared to other probabilistic model families, while also exhibiting favorable scaling behavior that has been elusive in prior vanilla AR visual generation attempts.

---