# Research Papers — 2026-01 · bundle page 140 of 189

> Full-text markdown of papers #6951–7000 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/140
[← Previous bundle](https://aipod.dev/papers/archive/2026-01/page/139.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-01/page/141.md)

### Perception Test 2025: Challenge Summary and a Unified VQA Extension

Authors: Joseph Heyward, Nikhil Parthasarathy, Tyler Zhu, Aravindh Mahendran, João Carreira, Dima Damen, Andrew Zisserman, Viorica Pătrăucean
Published: 2026-01-09
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.06287v2

The Third Perception Test challenge was organised as a full-day workshop alongside the IEEE/CVF International Conference on Computer Vision (ICCV) 2025. Its primary goal is to benchmark state-of-the-art video models and measure the progress in multimodal perception. This year, the workshop featured 2 guest tracks as well: KiVA (an image understanding challenge) and Physic-IQ (a video generation challenge). In this report, we summarise the results from the main Perception Test challenge, detailing both the existing tasks as well as novel additions to the benchmark. In this iteration, we placed an emphasis on task unification, as this poses a more challenging test for current SOTA multimodal models. The challenge included five consolidated tracks: unified video QA, unified object and point tracking, unified action and sound localisation, grounded video QA, and hour-long video QA, alongside an analysis and interpretability track that is still open for submissions. Notably, the unified video QA track introduced a novel subset that reformulates traditional perception tasks (such as point tracking and temporal action localisation) as multiple-choice video QA questions that video-language models can natively tackle. The unified object and point tracking merged the original object tracking and point tracking tasks, whereas the unified action and sound localisation merged the original temporal action localisation and temporal sound localisation tracks. Accordingly, we required competitors to use unified approaches rather than engineered pipelines with task-specific models. By proposing such a unified challenge, Perception Test 2025 highlights the significant difficulties existing models face when tackling diverse perception tasks through unified interfaces.

---

### NAS-GS: Noise-Aware Sonar Gaussian Splatting

Authors: Shida Xu, Jingqi Jiang, Jonatan Scharff Willners, Sen Wang
Published: 2026-01-09
Categories: cs.CV, cs.RO
arXiv: https://arxiv.org/abs/2601.06285v1

Underwater sonar imaging plays a crucial role in various applications, including autonomous navigation in murky water, marine archaeology, and environmental monitoring. However, the unique characteristics of sonar images, such as complex noise patterns and the lack of elevation information, pose significant challenges for 3D reconstruction and novel view synthesis. In this paper, we present NAS-GS, a novel Noise-Aware Sonar Gaussian Splatting framework specifically designed to address these challenges. Our approach introduces a Two-Ways Splatting technique that accurately models the dual directions for intensity accumulation and transmittance calculation inherent in sonar imaging, significantly improving rendering speed without sacrificing quality. Moreover, we propose a Gaussian Mixture Model (GMM) based noise model that captures complex sonar noise patterns, including side-lobes, speckle, and multi-path noise. This model enhances the realism of synthesized images while preventing 3D Gaussian overfitting to noise, thereby improving reconstruction accuracy. We demonstrate state-of-the-art performance on both simulated and real-world large-scale offshore sonar scenarios, achieving superior results in novel view synthesis and 3D reconstruction.

---

### Amory: Building Coherent Narrative-Driven Agent Memory through Agentic Reasoning

Authors: Yue Zhou, Xiaobo Guo, Belhassen Bayar, Srinivasan H. Sengamedu
Published: 2026-01-09
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2601.06282v1

Long-term conversational agents face a fundamental scalability challenge as interactions extend over time: repeatedly processing entire conversation histories becomes computationally prohibitive. Current approaches attempt to solve this through memory frameworks that predominantly fragment conversations into isolated embeddings or graph representations and retrieve relevant ones in a RAG style. While computationally efficient, these methods often treat memory formation minimally and fail to capture the subtlety and coherence of human memory. We introduce Amory, a working memory framework that actively constructs structured memory representations through enhancing agentic reasoning during offline time. Amory organizes conversational fragments into episodic narratives, consolidates memories with momentum, and semanticizes peripheral facts into semantic memory. At retrieval time, the system employs coherence-driven reasoning over narrative structures. Evaluated on the LOCOMO benchmark for long-term reasoning, Amory achieves considerable improvements over previous state-of-the-art, with performance comparable to full context reasoning while reducing response time by 50%. Analysis shows that momentum-aware consolidation significantly enhances response quality, while coherence-driven retrieval provides superior memory coverage compared to embedding-based approaches.

---

### EyeTheia: A Lightweight and Accessible Eye-Tracking Toolbox

Authors: Stevenson Pather, Niels Martignène, Arnaud Bugnet, Fouad Boutaleb, Fabien D'Hondt, Deise Santana Maia
Published: 2026-01-09
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.06279v2

We introduce EyeTheia, a lightweight and open deep learning pipeline for webcam-based gaze estimation, designed for browser-based experimental platforms and real-world cognitive and clinical research. EyeTheia enables real-time gaze tracking using only a standard laptop webcam, combining MediaPipe-based landmark extraction with a convolutional neural network inspired by iTracker and optional user-specific fine-tuning. We investigate two complementary strategies: adapting a model pretrained on mobile data and training the same architecture from scratch on a desktop-oriented dataset. Validation results on MPIIFaceGaze show comparable performance between both approaches prior to calibration, while lightweight user-specific fine-tuning consistently reduces gaze prediction error. We further evaluate EyeTheia in a realistic Dot-Probe task and compare it to the commercial webcam-based tracker SeeSo SDK. Results indicate strong agreement in left-right gaze allocation during stimulus presentation, despite higher temporal variability. Overall, EyeTheia provides a transparent and extensible solution for low-cost gaze tracking, suitable for scalable and reproducible experimental and clinical studies. The code, trained models, and experimental materials are publicly available.

---

### Performance Analysis of DCT, Hadamard, and PCA in Block-Based Image Compression

Authors: Yashika Ahlawat
Published: 2026-01-09
Categories: eess.IV, cs.CV
arXiv: https://arxiv.org/abs/2601.06273v1

Block based image compression relies on transform coding to concentrate signal energy into a small number of coefficients. While classical codecs use fixed transforms such as the Discrete Cosine Transform (DCT), data driven methods such as Principal Component Analysis (PCA) are theoretically optimal for decorrelation. This paper presents an experimental comparison of DCT, Hadamard, and PCA across multiple block sizes and compression rates. Using rate distortion and energy compaction analysis, we show that PCA outperforms fixed transforms only when block dimensionality is sufficiently large, while DCT remains near optimal for standard block sizes such as $8\times8$ and at low bit rates. These results explain the robustness of DCT in practical codecs and highlight the limitations of block wise learned transforms.

---

### Automated QoR improvement in OpenROAD with coding agents

Authors: Amur Ghose, Junyeong Jang, Andrew B. Kahng, Jakang Lee
Published: 2026-01-09
Categories: cs.SE, cs.AI
arXiv: https://arxiv.org/abs/2601.06268v2

EDA development and innovation has been constrained by scarcity of expert engineering resources. While leading LLMs have demonstrated excellent performance in coding and scientific reasoning tasks, their capacity to advance EDA technology itself has been largely untested. We present AuDoPEDA, an autonomous, repository-grounded coding system built atop OpenAI models and a Codex-class agent that reads OpenROAD, proposes research directions, expands them into implementation steps, and submits executable diffs. Our contributions include (i) a closed-loop LLM framework for EDA code changes; (ii) a task suite and evaluation protocol on OpenROAD for PPA-oriented improvements; and (iii) end-to-end demonstrations with minimal human oversight. Experiments in OpenROAD achieve routed wirelength reductions of up to 5.9%, effective clock period reductions of up to 10.0%, and power reductions of up to 19.4%.

---

### Matrix Factorization Framework for Community Detection under the Degree-Corrected Block Model

Authors: Alexandra Dache, Arnaud Vandaele, Nicolas Gillis
Published: 2026-01-09
Categories: cs.SI, math.OC, stat.ML
arXiv: https://arxiv.org/abs/2601.06262v2

Community detection is a fundamental task in data analysis, and block models provide an approach for identifying a wide variety of community structures while offering high interpretability. The degree-corrected block model (DCBM) is an established model that accounts for the heterogeneity of node degrees. However, inference methods are computationally costly and highly sensitive to initialization, while cheaper alternatives, such as spectral or modularity-based approaches, are restricted to detecting specific structures, typically assortative. In this work, we show that DCBM inference can be reformulated as a constrained nonnegative matrix factorization problem. Leveraging this insight, we propose a novel method for community detection and a theoretically well-grounded initialization strategy that provides an initial estimate of communities for inference algorithms. Our approach is agnostic to any specific network structure and applies to graphs with any structure representable by a DCBM. Experiments on synthetic and real benchmark networks show that our method detects communities comparable to those found by DCBM inference while being faster; for instance, it processes a graph with 100,000 nodes and 1,000,000 edges in approximately 4 minutes. Moreover, the proposed initialization strategy significantly improves solution quality and reduces the number of iterations required by all tested inference algorithms. Overall, this work provides a scalable and robust framework for community detection and highlights the benefits of a matrix-factorization perspective for the DCBM.

---

### Gamma2Patterns: Deep Cognitive Attention Region Identification and Gamma-Alpha Pattern Analysis

Authors: Sobhana Jahan, Saydul Akbar Murad, Nick Rahimi, Noorbakhsh Amiri Golilarz
Published: 2026-01-09
Categories: q-bio.NC, cs.AI, cs.CV
arXiv: https://arxiv.org/abs/2601.06257v1

Deep cognitive attention is characterized by heightened gamma oscillations and coordinated visual behavior. Despite the physiological importance of these mechanisms, computational studies rarely synthesize these modalities or identify the neural regions most responsible for sustained focus. To address this gap, this work introduces Gamma2Patterns, a multimodal framework that characterizes deep cognitive attention by leveraging complementary Gamma and Alpha band EEG activity alongside Eye-tracking measurements. Using the SEED-IV dataset (1), we extract spectral power, burst-based temporal dynamics, and fixation-saccade-pupil signals across 62 channels or electrodes to analyze how neural activation differs between high-focus (Gamma-dominant) and low-focus (Alpha-dominant) states. Our findings reveal that frontopolar, temporal, anterior frontal, and parieto-occipital regions exhibit the strongest Gamma power and burst rates, indicating their dominant role in deep attentional engagement, while Eye-tracking signals confirm complementary contributions from frontal, frontopolar, and frontotemporal regions. Furthermore, we show that Gamma power and burst duration provide more discriminative markers of deep focus than Alpha power alone, demonstrating their value for attention decoding. Collectively, these results establish a multimodal, evidence-based map of cortical regions and oscillatory signatures underlying deep focus, providing a neurophysiological foundation for future brain-inspired attention mechanisms in AI systems.

---

### Hard Constraint Projection in a Physics Informed Neural Network

Authors: Miranda J. S. Horne, Peter K. Jimack, Amirul Khan, He Wang
Published: 2026-01-09
Categories: physics.flu-dyn, cs.LG
arXiv: https://arxiv.org/abs/2601.06244v1

In this work, we embed hard constraints in a physics informed neural network (PINN) which predicts solutions to the 2D incompressible Navier Stokes equations. We extend the hard constraint method introduced by Chen et al. (arXiv:2012.06148) from a linear PDE to a strongly non-linear PDE. The PINN is used to estimate the stream function and pressure of the fluid, and by differentiating the stream function we can recover an incompressible velocity field. An unlearnable hard constraint projection (HCP) layer projects the predicted velocity and pressure to a hyperplane that admits only exact solutions to a discretised form of the governing equations.

---

### Real-Time Image Processing Algorithms for Embedded Systems

Authors: Soundes Oumaima Boufaida, Abdemadjid Benmachiche, Majda Maatallah
Published: 2026-01-09
Categories: eess.IV, cs.AI, cs.CV
arXiv: https://arxiv.org/abs/2601.06243v1

Embedded vision systems need efficient and robust image processing algorithms to perform real-time, with resource-constrained hardware. This research investigates image processing algorithms, specifically edge detection, corner detection, and blob detection, that are implemented on embedded processors, including DSPs and FPGAs. To address latency, accuracy and power consumption noted in the image processing literature, optimized algorithm architectures and quantization techniques are employed. In addition, optimal techniques for inter-frame redundancy removal and adaptive frame averaging are used to improve throughput with reasonable image quality. Simulations and hardware trials of the proposed approaches show marked improvements in the speed and energy efficiency of processing as compared to conventional implementations. The advances of this research facilitate a path for scalable and inexpensive embedded imaging systems for the automotive, surveillance, and robotics sectors, and underscore the benefit of co-designing algorithms and hardware architectures for practical real-time embedded vision applications.

---

### Agentic AI Microservice Framework for Deepfake and Document Fraud Detection in KYC Pipelines

Authors: Chandra Sekhar Kubam
Published: 2026-01-09
Categories: cs.CR, cs.AI
arXiv: https://arxiv.org/abs/2601.06241v1

The rapid proliferation of synthetic media, presentation attacks, and document forgeries has created significant vulnerabilities in Know Your Customer (KYC) workflows across financial services, telecommunications, and digital-identity ecosystems. Traditional monolithic KYC systems lack the scalability and agility required to counter adaptive fraud. This paper proposes an Agentic AI Microservice Framework that integrates modular vision models, liveness assessment, deepfake detection, OCR-based document forensics, multimodal identity linking, and a policy driven risk engine. The system leverages autonomous micro-agents for task decomposition, pipeline orchestration, dynamic retries, and human-in-the-loop escalation. Experimental evaluations demonstrate improved detection accuracy, reduced latency, and enhanced resilience against adversarial inputs. The framework offers a scalable blueprint for regulated industries seeking robust, real-time, and privacy-preserving KYC verification.

---

### A survey of facial recognition techniques

Authors: Aya Kaysan Bahjat
Published: 2026-01-09
Categories: cs.CV, cs.GR
arXiv: https://arxiv.org/abs/2601.06239v1

As multimedia content is quickly growing, the field of facial recognition has become one of the major research fields, particularly in the recent years. The most problematic area to researchers in image processing and computer vision is the human face which is a complex object with myriads of distinctive features that can be used to identify the face. The survey of this survey is particularly focused on most challenging facial characteristics, including differences in the light, ageing, variation in poses, partial occlusion, and facial expression and presents methodological solutions. The factors, therefore, are inevitable in the creation of effective facial recognition mechanisms used on facial images. This paper reviews the most sophisticated methods of facial detection which are Hidden Markov Models, Principal Component Analysis (PCA), Elastic Cluster Plot Matching, Support Vector Machine (SVM), Gabor Waves, Artificial Neural Networks (ANN), Eigenfaces, Independent Component Analysis (ICA), and 3D Morphable Model. Alongside the works mentioned above, we have also analyzed the images of a number of facial databases, namely JAFEE, FEI, Yale, LFW, AT&T (then called ORL), and AR (created by Martinez and Benavente), to analyze the results. However, this survey is aimed at giving a thorough literature review of face recognition, and its applications, and some experimental results are provided at the end after a detailed discussion.

---

### An Intelligent AI glasses System with Multi-Agent Architecture for Real-Time Voice Processing and Task Execution

Authors: Sheng-Kai Chen, Jyh-Horng Wu, Ching-Yao Lin, Yen-Ting Lin
Published: 2026-01-09
Categories: cs.SD, cs.AI, cs.HC
arXiv: https://arxiv.org/abs/2601.06235v1

This paper presents an AI glasses system that integrates real-time voice processing, artificial intelligence(AI) agents, and cross-network streaming capabilities. The system employs dual-agent architecture where Agent 01 handles Automatic Speech Recognition (ASR) and Agent 02 manages AI processing through local Large Language Models (LLMs), Model Context Protocol (MCP) tools, and Retrieval-Augmented Generation (RAG). The system supports real-time RTSP streaming for voice and video data transmission, eye tracking data collection, and remote task execution through RabbitMQ messaging. Implementation demonstrates successful voice command processing with multilingual support and cross-platform task execution capabilities.

---

### PCoKG: Personality-aware Commonsense Reasoning with Debate

Authors: Weijie Li, Zhongqing Wang, Guodong Zhou
Published: 2026-01-09
Categories: cs.AI
arXiv: https://arxiv.org/abs/2601.06234v1

Most commonsense reasoning models overlook the influence of personality traits, limiting their effectiveness in personalized systems such as dialogue generation. To address this limitation, we introduce the Personality-aware Commonsense Knowledge Graph (PCoKG), a structured dataset comprising 521,316 quadruples. We begin by employing three evaluators to score and filter events from the ATOMIC dataset, selecting those that are likely to elicit diverse reasoning patterns across different personality types. For knowledge graph construction, we leverage the role-playing capabilities of large language models (LLMs) to perform reasoning tasks. To enhance the quality of the generated knowledge, we incorporate a debate mechanism consisting of a proponent, an opponent, and a judge, which iteratively refines the outputs through feedback loops. We evaluate the dataset from multiple perspectives and conduct fine-tuning and ablation experiments using multiple LLM backbones to assess PCoKG's robustness and the effectiveness of its construction pipeline. Our LoRA-based fine-tuning results indicate a positive correlation between model performance and the parameter scale of the base models. Finally, we apply PCoKG to persona-based dialogue generation, where it demonstrates improved consistency between generated responses and reference outputs. This work bridges the gap between commonsense reasoning and individual cognitive differences, enabling the development of more personalized and context-aware AI systems.

---

### Multi-Agent Framework for Controllable and Protected Generative Content Creation: Addressing Copyright and Provenance in AI-Generated Media

Authors: Haris Khan, Sadia Asif, Shumaila Asif
Published: 2026-01-09
Categories: cs.CR, cs.AI
arXiv: https://arxiv.org/abs/2601.06232v1

The proliferation of generative AI systems creates unprecedented opportunities for content creation while raising critical concerns about controllability, copyright infringement, and content provenance. Current generative models operate as "black boxes" with limited user control and lack built-in mechanisms to protect intellectual property or trace content origin. We propose a novel multi-agent framework that addresses these challenges through specialized agent roles and integrated watermarking. Our system orchestrates Director, Generator, Reviewer, Integration, and Protection agents to ensure user intent alignment while embedding digital provenance markers. We demonstrate feasibility through two case studies: creative content generation with iterative refinement and copyright protection for AI-generated art in commercial contexts. Preliminary feasibility evidence from prior work indicates up to 23\% improvement in semantic alignment and 95\% watermark recovery rates. This work contributes to responsible generative AI deployment, positioning multi-agent systems as a solution for trustworthy creative workflows in legal and commercial applications.

---

### Triadic Concept Analysis for Logic Interpretation of Simple Artificial Networks

Authors: Ingo Schmitt
Published: 2026-01-09
Categories: cs.LG, cs.AI, cs.LO
arXiv: https://arxiv.org/abs/2601.06229v1

An artificial neural network (ANN) is a numerical method used to solve complex classification problems. Due to its high classification power, the ANN method often outperforms other classification methods in terms of accuracy. However, an ANN model lacks interpretability compared to methods that use the symbolic paradigm. Our idea is to derive a symbolic representation from a simple ANN model trained on minterm values of input objects. Based on ReLU nodes, the ANN model is partitioned into cells. We convert the ANN model into a cell-based, three-dimensional bit tensor. The theory of Formal Concept Analysis applied to the tensor yields concepts that are represented as logic trees, expressing interpretable attribute interactions. Their evaluations preserve the classification power of the initial ANN model.

---

### Synthetic FMCW Radar Range Azimuth Maps Augmentation with Generative Diffusion Model

Authors: Zhaoze Wang, Changxu Zhang, Tai Fei, Christopher Grimm, Yi Jin, Claas Tebruegge, Ernst Warsitz, Markus Gardill
Published: 2026-01-09
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2601.06228v1

The scarcity and low diversity of well-annotated automotive radar datasets often limit the performance of deep-learning-based environmental perception. To overcome these challenges, we propose a conditional generative framework for synthesizing realistic Frequency-Modulated Continuous-Wave radar Range-Azimuth Maps. Our approach leverages a generative diffusion model to generate radar data for multiple object categories, including pedestrians, cars, and cyclists. Specifically, conditioning is achieved via Confidence Maps, where each channel represents a semantic class and encodes Gaussian-distributed annotations at target locations. To address radar-specific characteristics, we incorporate Geometry Aware Conditioning and Temporal Consistency Regularization into the generative process. Experiments on the ROD2021 dataset demonstrate that signal reconstruction quality improves by \SI{3.6}{dB} in Peak Signal-to-Noise Ratio over baseline methods, while training with a combination of real and synthetic datasets improves overall mean Average Precision by 4.15% compared with conventional image-processing-based augmentation. These results indicate that our generative framework not only produces physically plausible and diverse radar spectrum but also substantially improves model generalization in downstream tasks.

---

### When Smaller Wins: Dual-Stage Distillation and Pareto-Guided Compression of Liquid Neural Networks for Edge Battery Prognostics

Authors: Dhivya Dharshini Kannan, Wei Li, Wei Zhang, Jianbiao Wang, Zhi Wei Seh, Man-Fai Ng
Published: 2026-01-09
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2601.06227v3

Battery management systems increasingly require accurate battery health prognostics under strict on-device constraints. This paper presents DLNet, a practical framework with dual-stage distillation of liquid neural networks that turns a high-capacity model into compact and edge-deployable models for battery health prediction. DLNet first applies Euler discretization to reformulate liquid dynamics for embedded compatibility. It then performs dual-stage knowledge distillation to transfer the teacher model's temporal behavior and recover it after further compression. Pareto-guided selection under joint error-cost objectives retains student models that balance accuracy and efficiency. We evaluate DLNet on a widely used dataset and validate real-device feasibility on an Arduino Nano 33 BLE Sense using int8 deployment. The final deployed student achieves a low error of 0.0066 when predicting battery health over the next 100 cycles, which is 15.4% lower than the teacher model. It reduces the model size from 616 kB to 94 kB with 84.7% reduction and takes 21 ms per inference on the device. These results support a practical smaller wins observation that a small model can match or exceed a large teacher for edge-based prognostics with proper supervision and selection. Beyond batteries, the DLNet framework can extend to other industrial analytics tasks with strict hardware constraints.

---

### Projecting Out the Malice: A Global Subspace Approach to LLM Detoxification

Authors: Zenghao Duan, Zhiyi Yin, Zhichao Shi, Liang Pang, Shaoling Jing, Zihe Huang, Jiayi Wu, Yu Yan, Jingcheng Deng, Huawei Shen, Xueqi Cheng
Published: 2026-01-09
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2601.06226v1

Large language models (LLMs) exhibit exceptional performance but pose inherent risks of generating toxic content, restricting their safe deployment. While traditional methods (e.g., alignment) adjust output preferences, they fail to eliminate underlying toxic regions in parameters, leaving models vulnerable to adversarial attacks. Prior mechanistic studies characterize toxic regions as "toxic vectors" or "layer-wise subspaces", yet our analysis identifies critical limitations: i) Removed toxic vectors can be reconstructed via linear combinations of non-toxic vectors, demanding targeting of entire toxic subspace; ii) Contrastive objective over limited samples inject noise into layer-wise subspaces, hindering stable extraction. These highlight the challenge of identifying robust toxic subspace and removing them. Therefore, we propose GLOSS (GLobal tOxic Subspace Suppression), a lightweight method that mitigates toxicity by identifying and eliminating this global subspace from FFN parameters. Experiments on LLMs (e.g., Qwen3) show GLOSS achieves SOTA detoxification while preserving general capabilities without requiring large-scale retraining. WARNING: This paper contains context which is toxic in nature.

---

### Classroom AI: Large Language Models as Grade-Specific Teachers

Authors: Jio Oh, Steven Euijong Whang, James Evans, Jindong Wang
Published: 2026-01-09
Categories: cs.CY, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2601.06225v2

Large Language Models (LLMs) offer a promising solution to complement traditional teaching and address global teacher shortages that affect hundreds of millions of children, but they fail to provide grade-appropriate responses for students at different educational levels. We introduce a framework for finetuning LLMs to generate age-appropriate educational content across six grade levels, from lower elementary to adult education. Our framework successfully adapts explanations to match students' comprehension capacities without sacrificing factual correctness. This approach integrates seven established readability metrics through a clustering method and builds a comprehensive dataset for grade-specific content generation. Evaluations across multiple datasets with 208 human participants demonstrate substantial improvements in grade-level alignment, achieving a 35.64 percentage point increase compared to prompt-based methods while maintaining response accuracy. AI-assisted learning tailored to different grade levels has the potential to advance educational engagement and equity.

---

### Ground What You See: Hallucination-Resistant MLLMs via Caption Feedback, Diversity-Aware Sampling, and Conflict Regularization

Authors: Miao Pan, Wangjie Gan, Jintao Chen, Wenqi Zhang, Bing Sun, Jianwei Yin, Xuhong Zhang
Published: 2026-01-09
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.06224v2

While Multimodal Large Language Models (MLLMs) have achieved remarkable success across diverse tasks, their practical deployment is severely hindered by hallucination issues, which become particularly acute during Reinforcement Learning (RL) optimization. This paper systematically analyzes the root causes of hallucinations in MLLMs under RL training, identifying three critical factors: (1) an over-reliance on chained visual reasoning, where inaccurate initial descriptions or redundant information anchor subsequent inferences to incorrect premises; (2) insufficient exploration diversity during policy optimization, leading the model to generate overly confident but erroneous outputs; and (3) destructive conflicts between training samples, where Neural Tangent Kernel (NTK) similarity causes false associations and unstable parameter updates. To address these challenges, we propose a comprehensive framework comprising three core modules. First, we enhance visual localization by introducing dedicated planning and captioning stages before the reasoning phase, employing a quality-based caption reward to ensure accurate initial anchoring. Second, to improve exploration, we categorize samples based on the mean and variance of their reward distributions, prioritizing samples with high variance to focus the model on diverse and informative data. Finally, to mitigate sample interference, we regulate NTK similarity by grouping sample pairs and applying an InfoNCE loss to push overly similar pairs apart and pull dissimilar ones closer, thereby guiding gradient interactions toward a balanced range. Experimental results demonstrate that our proposed method significantly reduces hallucination rates and effectively enhances the inference accuracy of MLLMs.

---

### Toward Safe and Responsible AI Agents: A Three-Pillar Model for Transparency, Accountability, and Trustworthiness

Authors: Edward C. Cheng, Jeshua Cheng, Alice Siu
Published: 2026-01-09
Categories: cs.CY, cs.AI
arXiv: https://arxiv.org/abs/2601.06223v1

This paper presents a conceptual and operational framework for developing and operating safe and trustworthy AI agents based on a Three-Pillar Model grounded in transparency, accountability, and trustworthiness. Building on prior work in Human-in-the-Loop systems, reinforcement learning, and collaborative AI, the framework defines an evolutionary path toward autonomous agents that balances increasing automation with appropriate human oversight. The paper argues that safe agent autonomy must be achieved through progressive validation, analogous to the staged development of autonomous driving, rather than through immediate full automation. Transparency and accountability are identified as foundational requirements for establishing user trust and for mitigating known risks in generative AI systems, including hallucinations, data bias, and goal misalignment, such as the inversion problem. The paper further describes three ongoing work streams supporting this framework: public deliberation on AI agents conducted by the Stanford Deliberative Democracy Lab, cross-industry collaboration through the Safe AI Agent Consortium, and the development of open tooling for an agent operating environment aligned with the Three-Pillar Model. Together, these contributions provide both conceptual clarity and practical guidance for enabling the responsible evolution of AI agents that operate transparently, remain aligned with human values, and sustain societal trust.

---

### SAPL: Semantic-Agnostic Prompt Learning in CLIP for Weakly Supervised Image Manipulation Localization

Authors: Xinghao Wang, Changtao Miao, Dianmo Sheng, Tao Gong, Qi Chu, Nenghai Yu, Quanchen Zou, Deyue Zhang, Xiangzheng Zhang
Published: 2026-01-09
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2601.06222v1

Malicious image manipulation threatens public safety and requires efficient localization methods. Existing approaches depend on costly pixel-level annotations which make training expensive. Existing weakly supervised methods rely only on image-level binary labels and focus on global classification, often overlooking local edge cues that are critical for precise localization. We observe that feature variations at manipulated boundaries are substantially larger than in interior regions. To address this gap, we propose Semantic-Agnostic Prompt Learning (SAPL) in CLIP, which learns text prompts that intentionally encode non-semantic, boundary-centric cues so that CLIPs multimodal similarity highlights manipulation edges rather than high-level object semantics. SAPL combines two complementary modules Edge-aware Contextual Prompt Learning (ECPL) and Hierarchical Edge Contrastive Learning (HECL) to exploit edge information in both textual and visual spaces. The proposed ECPL leverages edge-enhanced image features to generate learnable textual prompts via an attention mechanism, embedding semantic-irrelevant information into text features, to guide CLIP focusing on manipulation edges. The proposed HECL extract genuine and manipulated edge patches, and utilize contrastive learning to boost the discrimination between genuine edge patches and manipulated edge patches. Finally, we predict the manipulated regions from the similarity map after processing. Extensive experiments on multiple public benchmarks demonstrate that SAPL significantly outperforms existing approaches, achieving state-of-the-art localization performance.

---

### LDTC: Lifelong deep temporal clustering for multivariate time series

Authors: Zhi Wang, Yanni Li, Pingping Zheng, Yiyuan Jiao
Published: 2026-01-09
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2601.06221v1

Clustering temporal and dynamically changing multivariate time series from real-world fields, called temporal clustering for short, has been a major challenge due to inherent complexities. Although several deep temporal clustering algorithms have demonstrated a strong advantage over traditional methods in terms of model learning and clustering results, the accuracy of the few algorithms are not satisfactory. None of the existing algorithms can continuously learn new tasks and deal with the dynamic data effectively and efficiently in the sequential tasks learning. To bridge the gap and tackle these issues, this paper proposes a novel algorithm \textbf{L}ifelong \textbf{D}eep \textbf{T}emporal \textbf{C}lustering (\textbf{LDTC}), which effectively integrates dimensionality reduction and temporal clustering into an end-to-end deep unsupervised learning framework. Using a specifically designed autoencoder and jointly optimizing for both the latent representation and clustering objective, the LDTC can achieve high-quality clustering results. Moreover, unlike any previous work, the LDTC is uniquely equipped with the fully dynamic model expansion and rehearsal-based techniques to effectively learn new tasks and to tackle the dynamic data in the sequential tasks learning without the catastrophic forgetting or degradation of the model accuracy. Experiments on seven real-world multivariate time series datasets show that the LDTC is a promising method for dealing with temporal clustering issues effectively and efficiently.

---

### Breaking Model Lock-in: Cost-Efficient Zero-Shot LLM Routing via a Universal Latent Space

Authors: Cheng Yan, Wuyang Zhang, Zhiyuan Ning, Fan Xu, Ziyang Tao, Lu Zhang, Bing Yin, Yanyong Zhang
Published: 2026-01-09
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2601.06220v1

The rapid proliferation of Large Language Models (LLMs) has led to a fragmented and inefficient ecosystem, a state of ``model lock-in'' where seamlessly integrating novel models remains a significant bottleneck. Current routing frameworks require exhaustive, costly retraining, hindering scalability and adaptability. We introduce ZeroRouter, a new paradigm for LLM routing that breaks this lock-in. Our approach is founded on a universal latent space, a model-agnostic representation of query difficulty that fundamentally decouples the characterization of a query from the profiling of a model. This allows for zero-shot onboarding of new models without full-scale retraining. ZeroRouter features a context-aware predictor that maps queries to this universal space and a dual-mode optimizer that balances accuracy, cost, and latency. Our framework consistently outperforms all baselines, delivering higher accuracy at lower cost and latency.

---

### AI-Powered Algorithms for the Prevention and Detection of Computer Malware Infections

Authors: Rakesh Keshava, Sathish Kuppan Pandurangan, M. Sakthivanitha, Sankaranainar Parmsivan, Goutham Sunkara, R. Maruthi
Published: 2026-01-09
Categories: cs.CR, cs.AI
arXiv: https://arxiv.org/abs/2601.06219v1

The rise in frequency and complexity of malware attacks are viewed as a major threat to modern digital infrastructure, which means that traditional signature-based detection methods are becoming less effective. As cyber threats continue to evolve, there is a growing need for intelligent systems to accurately and proactively identify and prevent malware infections. This study presents a new hybrid context-aware malware detection framework(HCAMDF) based on artificial intelligence (AI), which combines static file analysis, dynamic behavioural analysis, and contextual metadata to provide more accurate and timely detection. HCADMF has a multi-layer architecture, which consists of lightweight static classifiers such as Long Short Term Memory (LSTM) for real-time behavioral analysis, and an ensemble risk scoring through the integration of multiple layers of prediction. Experimental evaluations of the new/methodology with benchmark datasets, EMBER and CIC-MalMem2022, showed that the new approach provides superior performances with an accuracy of 97.3%, only a 1.5% false positive rate and minimal detection delay compared to several existing machine learning(ML) and deep learning(DL) established methods in the same fields. The results show strong evidence that hybrid AI can detect both existing and novel malware variants, and lay the foundation on intelligent security systems that can enable real-time detection and adapt to a rapidly evolving threat landscape.

---

### Two-step Authentication: Multi-biometric System Using Voice and Facial Recognition

Authors: Kuan Wei Chen, Ting Yi Lin, Wen Ren Yang, Aryan Kesarwani, Riya Singh
Published: 2026-01-09
Categories: cs.CV, cs.AI, cs.MM
arXiv: https://arxiv.org/abs/2601.06218v1

We present a cost-effective two-step authentication system that integrates face identification and speaker verification using only a camera and microphone available on common devices. The pipeline first performs face recognition to identify a candidate user from a small enrolled group, then performs voice recognition only against the matched identity to reduce computation and improve robustness. For face recognition, a pruned VGG-16 based classifier is trained on an augmented dataset of 924 images from five subjects, with faces localized by MTCNN; it achieves 95.1% accuracy. For voice recognition, a CNN speaker-verification model trained on LibriSpeech (train-other-360) attains 98.9% accuracy and 3.456% EER on test-clean. Source code and trained models are available at https://github.com/NCUE-EE-AIAL/Two-step-Authentication-Multi-biometric-System.

---

### Manifold limit for the training of shallow graph convolutional neural networks

Authors: Johanna Tengler, Christoph Brune, José A. Iglesias
Published: 2026-01-09
Categories: stat.ML, cs.LG, math.FA, math.OC
arXiv: https://arxiv.org/abs/2601.06025v2

We study the discrete-to-continuum consistency of the training of shallow graph convolutional neural networks (GCNNs) on proximity graphs of sampled point clouds under a manifold assumption. Graph convolution is defined spectrally via the graph Laplacian, whose low-frequency spectrum approximates that of the Laplace-Beltrami operator of the underlying smooth manifold, and shallow GCNNs of possibly infinite width are linear functionals on the space of measures on the parameter space. From this functional-analytic perspective, graph signals are seen as spatial discretizations of functions on the manifold, which leads to a natural notion of training data consistent across graph resolutions. To enable convergence results, the continuum parameter space is chosen as a weakly compact product of unit balls, with Sobolev regularity imposed on the output weight and bias, but not on the convolutional parameter. The corresponding discrete parameter spaces inherit the corresponding spectral decay, and are additionally restricted by a frequency cutoff adapted to the informative spectral window of the graph Laplacians. Under these assumptions, we prove $Γ$-convergence of regularized empirical risk minimization functionals and corresponding convergence of their global minimizers, in the sense of weak convergence of the parameter measures and uniform convergence of the functions over compact sets. This provides a formalization of mesh and sample independence, and hence of transferability across discretizations, for the training of such networks.

---

### Manifold limit for the training of shallow graph convolutional neural networks

Authors: Johanna Tengler, Christoph Brune, José A. Iglesias
Published: 2026-01-09
Categories: stat.ML, cs.LG, math.FA, math.OC
arXiv: https://arxiv.org/abs/2601.06025v1

We study the discrete-to-continuum consistency of the training of shallow graph convolutional neural networks (GCNNs) on proximity graphs of sampled point clouds under a manifold assumption. Graph convolution is defined spectrally via the graph Laplacian, whose low-frequency spectrum approximates that of the Laplace-Beltrami operator of the underlying smooth manifold, and shallow GCNNs of possibly infinite width are linear functionals on the space of measures on the parameter space. From this functional-analytic perspective, graph signals are seen as spatial discretizations of functions on the manifold, which leads to a natural notion of training data consistent across graph resolutions. To enable convergence results, the continuum parameter space is chosen as a weakly compact product of unit balls, with Sobolev regularity imposed on the output weight and bias, but not on the convolutional parameter. The corresponding discrete parameter spaces inherit the corresponding spectral decay, and are additionally restricted by a frequency cutoff adapted to the informative spectral window of the graph Laplacians. Under these assumptions, we prove $Γ$-convergence of regularized empirical risk minimization functionals and corresponding convergence of their global minimizers, in the sense of weak convergence of the parameter measures and uniform convergence of the functions over compact sets. This provides a formalization of mesh and sample independence for the training of such networks.

---

### AdaFuse: Adaptive Ensemble Decoding with Test-Time Scaling for LLMs

Authors: Chengming Cui, Tianxin Wei, Ziyi Chen, Ruizhong Qiu, Zhichen Zeng, Zhining Liu, Xuying Ning, Duo Zhou, Jingrui He
Published: 2026-01-09
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2601.06022v2

Large language models (LLMs) exhibit complementary strengths arising from differences in pretraining data, model architectures, and decoding behaviors. Inference-time ensembling provides a practical way to combine these capabilities without retraining. However, existing ensemble approaches suffer from fundamental limitations. Most rely on fixed fusion granularity, which lacks the flexibility required for mid-generation adaptation and fails to adapt to different generation characteristics across tasks. To address these challenges, we propose AdaFuse, an adaptive ensemble decoding framework that dynamically selects semantically appropriate fusion units during generation. Rather than committing to a fixed granularity, AdaFuse adjusts fusion behavior on the fly based on the decoding context, with words serving as basic building blocks for alignment. To be specific, we introduce an uncertainty-based criterion to decide whether to apply ensembling at each decoding step. Under confident decoding states, the model continues generation directly. In less certain states, AdaFuse invokes a diversity-aware scaling strategy to explore alternative candidate continuations and inform ensemble decisions. This design establishes a synergistic interaction between adaptive ensembling and test-time scaling, where ensemble decisions guide targeted exploration, and the resulting diversity in turn strengthens ensemble quality. Experiments on open-domain question answering, arithmetic reasoning, and machine translation demonstrate that AdaFuse consistently outperforms strong ensemble baselines, achieving an average relative improvement of 6.88%. The code is available at https://github.com/CCM0111/AdaFuse.

---

### AdaFuse: Adaptive Ensemble Decoding with Test-Time Scaling for LLMs

Authors: Chengming Cui, Tianxin Wei, Ziyi Chen, Ruizhong Qiu, Zhichen Zeng, Zhining Liu, Xuying Ning, Duo Zhou, Jingrui He
Published: 2026-01-09
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2601.06022v1

Large language models (LLMs) exhibit complementary strengths arising from differences in pretraining data, model architectures, and decoding behaviors. Inference-time ensembling provides a practical way to combine these capabilities without retraining. However, existing ensemble approaches suffer from fundamental limitations. Most rely on fixed fusion granularity, which lacks the flexibility required for mid-generation adaptation and fails to adapt to different generation characteristics across tasks. To address these challenges, we propose AdaFuse, an adaptive ensemble decoding framework that dynamically selects semantically appropriate fusion units during generation. Rather than committing to a fixed granularity, AdaFuse adjusts fusion behavior on the fly based on the decoding context, with words serving as basic building blocks for alignment. To be specific, we introduce an uncertainty-based criterion to decide whether to apply ensembling at each decoding step. Under confident decoding states, the model continues generation directly. In less certain states, AdaFuse invokes a diversity-aware scaling strategy to explore alternative candidate continuations and inform ensemble decisions. This design establishes a synergistic interaction between adaptive ensembling and test-time scaling, where ensemble decisions guide targeted exploration, and the resulting diversity in turn strengthens ensemble quality. Experiments on open-domain question answering, arithmetic reasoning, and machine translation demonstrate that AdaFuse consistently outperforms strong ensemble baselines, achieving an average relative improvement of 6.88%. The code is available at https://github.com/CCM0111/AdaFuse.

---

### Chaining the Evidence: Robust Reinforcement Learning for Deep Search Agents with Citation-Aware Rubric Rewards

Authors: Jiajie Zhang, Xin Lv, Ling Feng, Lei Hou, Juanzi Li
Published: 2026-01-09
Categories: cs.CL
arXiv: https://arxiv.org/abs/2601.06021v1

Reinforcement learning (RL) has emerged as a critical technique for enhancing LLM-based deep search agents. However, existing approaches primarily rely on binary outcome rewards, which fail to capture the comprehensiveness and factuality of agents' reasoning process, and often lead to undesirable behaviors such as shortcut exploitation and hallucinations. To address these limitations, we propose \textbf{Citation-aware Rubric Rewards (CaRR)}, a fine-grained reward framework for deep search agents that emphasizes reasoning comprehensiveness, factual grounding, and evidence connectivity. CaRR decomposes complex questions into verifiable single-hop rubrics and requires agents to satisfy these rubrics by explicitly identifying hidden entities, supporting them with correct citations, and constructing complete evidence chains that link to the predicted answer. We further introduce \textbf{Citation-aware Group Relative Policy Optimization (C-GRPO)}, which combines CaRR and outcome rewards for training robust deep search agents. Experiments show that C-GRPO consistently outperforms standard outcome-based RL baselines across multiple deep search benchmarks. Our analysis also validates that C-GRPO effectively discourages shortcut exploitation, promotes comprehensive, evidence-grounded reasoning, and exhibits strong generalization to open-ended deep research tasks. Our code and data are available at https://github.com/THUDM/CaRR.

---

### LookAroundNet: Extending Temporal Context with Transformers for Clinically Viable EEG Seizure Detection

Authors: Þór Sverrisson, Steinn Guðmundsson
Published: 2026-01-09
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.06016v1

Automated seizure detection from electroencephalography (EEG) remains difficult due to the large variability of seizure dynamics across patients, recording conditions, and clinical settings. We introduce LookAroundNet, a transformer-based seizure detector that uses a wider temporal window of EEG data to model seizure activity. The seizure detector incorporates EEG signals before and after the segment of interest, reflecting how clinicians use surrounding context when interpreting EEG recordings. We evaluate the proposed method on multiple EEG datasets spanning diverse clinical environments, patient populations, and recording modalities, including routine clinical EEG and long-term ambulatory recordings, in order to study performance across varying data distributions. The evaluation includes publicly available datasets as well as a large proprietary collection of home EEG recordings, providing complementary views of controlled clinical data and unconstrained home-monitoring conditions. Our results show that LookAroundNet achieves strong performance across datasets, generalizes well to previously unseen recording conditions, and operates with computational costs compatible with real-world clinical deployment. The results indicate that extended temporal context, increased training data diversity, and model ensembling are key factors for improving performance. This work contributes to moving automatic seizure detection models toward clinically viable solutions.

---

### Detecting Stochasticity in Discrete Signals via Nonparametric Excursion Theorem

Authors: Sunia Tanweer, Firas A. Khasawneh
Published: 2026-01-09
Categories: stat.ML, cs.LG, eess.SP, math.PR, stat.AP
arXiv: https://arxiv.org/abs/2601.06009v1

We develop a practical framework for distinguishing diffusive stochastic processes from deterministic signals using only a single discrete time series. Our approach is based on classical excursion and crossing theorems for continuous semimartingales, which correlates number $N_\varepsilon$ of excursions of magnitude at least $\varepsilon$ with the quadratic variation $(X)_T$ of the process. The scaling law holds universally for all continuous semimartingales with finite quadratic variation, including general Ito diffusions with nonlinear or state-dependent volatility, but fails sharply for deterministic systems -- thereby providing a theoretically-certfied method of distinguishing between these dynamics, as opposed to the subjective entropy or recurrence based state of the art methods. We construct a robust data-driven diffusion test. The method compares the empirical excursion counts against the theoretical expectation. The resulting ratio $K(\varepsilon)=N_{\varepsilon}^{\mathrm{emp}}/N_{\varepsilon}^{\mathrm{theory}}$ is then summarized by a log-log slope deviation measuring the $\varepsilon^{-2}$ law that provides a classification into diffusion-like or not. We demonstrate the method on canonical stochastic systems, some periodic and chaotic maps and systems with additive white noise, as well as the stochastic Duffing system. The approach is nonparametric, model-free, and relies only on the universal small-scale structure of continuous semimartingales.

---

### Don't Break the Cache: An Evaluation of Prompt Caching for Long-Horizon Agentic Tasks

Authors: Elias Lumer, Faheem Nizar, Akshaya Jangiti, Kevin Frank, Anmol Gulati, Mandar Phadate, Vamse Kumar Subbiah
Published: 2026-01-09
Categories: cs.CL
arXiv: https://arxiv.org/abs/2601.06007v2

Recent advancements in Large Language Model (LLM) agents have enabled complex multi-turn agentic tasks requiring extensive tool calling, where conversations can span dozens of API calls with increasingly large context windows. However, although major LLM providers offer prompt caching to reduce cost and latency, its benefits for agentic workloads remain underexplored in the research literature. To our knowledge, no prior work quantifies these cost savings or compares caching strategies for multi-turn agentic tasks. We present a comprehensive evaluation of prompt caching across three major LLM providers (OpenAI, Anthropic, and Google) and compare three caching strategies, including full context caching, system prompt only caching, and caching that excludes dynamic tool results. We evaluate on DeepResearch Bench, a multi-turn agentic benchmark where agents autonomously execute real-world web search tool calls to answer complex research questions, measuring both API cost and time to first token (TTFT) across over 500 agent sessions with 10,000-token system prompts. Our results demonstrate that prompt caching reduces API costs by 41-80% and improves time to first token by 13-31% across providers. We find that strategic prompt cache block control, such as placing dynamic content at the end of the system prompt, avoiding dynamic traditional function calling, and excluding dynamic tool results, provides more consistent benefits than naive full-context caching, which can paradoxically increase latency. An ablation study across prompt sizes (500-50,000 tokens) and tool call counts (3-50) demonstrates universal linear cost and TTFT benefits, after the provider caching token minimum, and reveal provider-specific strategy discrepancies across variants. We provide nuanced discussion and guidance for implementing prompt caching in production agentic systems.

---

### Don't Break the Cache: An Evaluation of Prompt Caching for Long-Horizon Agentic Tasks

Authors: Elias Lumer, Faheem Nizar, Akshaya Jangiti, Kevin Frank, Anmol Gulati, Mandar Phadate, Vamse Kumar Subbiah
Published: 2026-01-09
Categories: cs.CL
arXiv: https://arxiv.org/abs/2601.06007v1

Recent advancements in Large Language Model (LLM) agents have enabled complex multi-turn agentic tasks requiring extensive tool calling, where conversations can span dozens of API calls with increasingly large context windows. However, although major LLM providers offer prompt caching to reduce cost and latency, its benefits for agentic workloads remain underexplored in the research literature. To our knowledge, no prior work quantifies these cost savings or compares caching strategies for multi-turn agentic tasks. We present a comprehensive evaluation of prompt caching across three major LLM providers (OpenAI, Anthropic, and Google) and compare three caching strategies, including full context caching, system prompt only caching, and caching that excludes dynamic tool results. We evaluate on DeepResearchBench, a multi-turn agentic benchmark where agents autonomously execute real-world web search tool calls to answer complex research questions, measuring both API cost and time to first token (TTFT) across over 500 agent sessions with 10,000-token system prompts. Our results demonstrate that prompt caching reduces API costs by 45-80% and improves time to first token by 13-31% across providers. We find that strategic prompt cache block control, such as placing dynamic content at the end of the system prompt, avoiding dynamic traditional function calling, and excluding dynamic tool results, provides more consistent benefits than naive full-context caching, which can paradoxically increase latency. Our analysis reveals nuanced variations in caching behavior across providers, and we provide practical guidance for implementing prompt caching in production agentic systems.

---

### The Molecular Structure of Thought: Mapping the Topology of Long Chain-of-Thought Reasoning

Authors: Qiguang Chen, Yantao Du, Ziniu Li, Jinhao Liu, Songyao Duan, Jiarui Guo, Minghao Liu, Jiaheng Liu, Tong Yang, Ge Zhang, Libo Qin, Wanxiang Che et al.
Published: 2026-01-09
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2601.06002v2

Large language models (LLMs) often fail to learn effective long chain-of-thought (Long CoT) reasoning from human or non-Long-CoT LLMs imitation. To understand this, we propose that effective and learnable Long CoT trajectories feature stable molecular-like structures in unified view, which are formed by three interaction types: Deep-Reasoning (covalent-like), Self-Reflection (hydrogen-bond-like), and Self-Exploration (van der Waals-like). Analysis of distilled trajectories reveals these structures emerge from Long CoT fine-tuning, not keyword imitation. We introduce Effective Semantic Isomers and show that only bonds promoting fast entropy convergence support stable Long CoT learning, while structural competition impairs training. Drawing on these findings, we present Mole-Syn, a distribution-transfer-graph method that guides synthesis of effective Long CoT structures, boosting performance and RL stability across benchmarks.

---

### The Molecular Structure of Thought: Mapping the Topology of Long Chain-of-Thought Reasoning

Authors: Qiguang Chen, Yantao Du, Ziniu Li, Jinhao Liu, Songyao Duan, Jiarui Guo, Minghao Liu, Jiaheng Liu, Tong Yang, Ge Zhang, Libo Qin, Wanxiang Che et al.
Published: 2026-01-09
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2601.06002v1

Large language models (LLMs) often fail to learn effective long chain-of-thought (Long CoT) reasoning from human or non-Long-CoT LLMs imitation. To understand this, we propose that effective and learnable Long CoT trajectories feature stable molecular-like structures in unified view, which are formed by three interaction types: Deep-Reasoning (covalent-like), Self-Reflection (hydrogen-bond-like), and Self-Exploration (van der Waals-like). Analysis of distilled trajectories reveals these structures emerge from Long CoT fine-tuning, not keyword imitation. We introduce Effective Semantic Isomers and show that only bonds promoting fast entropy convergence support stable Long CoT learning, while structural competition impairs training. Drawing on these findings, we present Mole-Syn, a distribution-transfer-graph method that guides synthesis of effective Long CoT structures, boosting performance and RL stability across benchmarks.

---

### 3D Instruction Ambiguity Detection

Authors: Jiayu Ding, Haoran Tang, Hongbo Jin, Wei Gao, Ge Li
Published: 2026-01-09
Categories: cs.AI
arXiv: https://arxiv.org/abs/2601.05991v2

In safety-critical domains, linguistic ambiguity can have severe consequences; a vague command like "Pass me the vial" in a surgical setting could lead to catastrophic errors. Yet, most embodied AI research overlooks this, assuming instructions are clear and focusing on execution rather than confirmation. To address this critical safety gap, we are the first to define 3D Instruction Ambiguity Detection, a fundamental new task where a model must determine if a command has a single, unambiguous meaning within a given 3D scene. To support this research, we build Ambi3D, the large-scale benchmark for this task, featuring over 700 diverse 3D scenes and around 22k instructions. Our analysis reveals a surprising limitation: state-of-the-art 3D Large Language Models (LLMs) struggle to reliably determine if an instruction is ambiguous. To address this challenge, we propose AmbiVer, a two-stage framework that collects explicit visual evidence from multiple views and uses it to guide an vision-language model (VLM) in judging instruction ambiguity. Extensive experiments demonstrate the challenge of our task and the effectiveness of AmbiVer, paving the way for safer and more trustworthy embodied AI. Code and dataset available at https://jiayuding031020.github.io/ambi3d/.

---

### Open-Vocabulary 3D Instruction Ambiguity Detection

Authors: Jiayu Ding, Haoran Tang, Ge Li
Published: 2026-01-09
Categories: cs.AI
arXiv: https://arxiv.org/abs/2601.05991v1

In safety-critical domains, linguistic ambiguity can have severe consequences; a vague command like "Pass me the vial" in a surgical setting could lead to catastrophic errors. Yet, most embodied AI research overlooks this, assuming instructions are clear and focusing on execution rather than confirmation. To address this critical safety gap, we are the first to define Open-Vocabulary 3D Instruction Ambiguity Detection, a fundamental new task where a model must determine if a command has a single, unambiguous meaning within a given 3D scene. To support this research, we build Ambi3D, the large-scale benchmark for this task, featuring over 700 diverse 3D scenes and around 22k instructions. Our analysis reveals a surprising limitation: state-of-the-art 3D Large Language Models (LLMs) struggle to reliably determine if an instruction is ambiguous. To address this challenge, we propose AmbiVer, a two-stage framework that collects explicit visual evidence from multiple views and uses it to guide an vision-language model (VLM) in judging instruction ambiguity. Extensive experiments demonstrate the challenge of our task and the effectiveness of AmbiVer, paving the way for safer and more trustworthy embodied AI. Code and dataset available at https://jiayuding031020.github.io/ambi3d/.

---

### CyberGFM: Graph Foundation Models for Lateral Movement Detection in Enterprise Networks

Authors: Isaiah J. King, Bernardo Trindade, Benjamin Bowman, H. Howie Huang
Published: 2026-01-09
Categories: cs.CR, cs.LG
arXiv: https://arxiv.org/abs/2601.05988v1

Representing networks as a graph and training a link prediction model using benign connections is an effective method of anomaly-based intrusion detection. Existing works using this technique have shown great success using temporal graph neural networks and skip-gram-based approaches on random walks. However, random walk-based approaches are unable to incorporate rich edge data, while the GNN-based approaches require large amounts of memory to train. In this work, we propose extending the original insight from random walk-based skip-grams--that random walks through a graph are analogous to sentences in a corpus--to the more modern transformer-based foundation models. Using language models that take advantage of GPU optimizations, we can quickly train a graph foundation model to predict missing tokens in random walks through a network of computers. The graph foundation model is then finetuned for link prediction and used as a network anomaly detector. This new approach allows us to combine the efficiency of random walk-based methods and the rich semantic representation of deep learning methods. This system, which we call CyberGFM, achieved state-of-the-art results on three widely used network anomaly detection datasets, delivering a up to 2$\times$ improvement in average precision. We found that CyberGFM outperforms all prior works in unsupervised link prediction for network anomaly detection, using the same number of parameters, and with equal or better efficiency than the previous best approaches.

---

### Deepfake detectors are DUMB: A benchmark to assess adversarial training robustness under transferability constraints

Authors: Adrian Serrano, Erwan Umlil, Ronan Thomas
Published: 2026-01-09
Categories: cs.CV, cs.CR
arXiv: https://arxiv.org/abs/2601.05986v1

Deepfake detection systems deployed in real-world environments are subject to adversaries capable of crafting imperceptible perturbations that degrade model performance. While adversarial training is a widely adopted defense, its effectiveness under realistic conditions -- where attackers operate with limited knowledge and mismatched data distributions - remains underexplored. In this work, we extend the DUMB -- Dataset soUrces, Model architecture and Balance - and DUMBer methodology to deepfake detection. We evaluate detectors robustness against adversarial attacks under transferability constraints and cross-dataset configuration to extract real-world insights. Our study spans five state-of-the-art detectors (RECCE, SRM, XCeption, UCF, SPSL), three attacks (PGD, FGSM, FPBA), and two datasets (FaceForensics++ and Celeb-DF-V2). We analyze both attacker and defender perspectives mapping results to mismatch scenarios. Experiments show that adversarial training strategies reinforce robustness in the in-distribution cases but can also degrade it under cross-dataset configuration depending on the strategy adopted. These findings highlight the need for case-aware defense strategies in real-world applications exposed to adversarial attacks.

---

### Community-Based Model Sharing and Generalisation: Anomaly Detection in IoT Temperature Sensor Networks

Authors: Sahibzada Saadoon Hammad, Joaquín Huerta Guijarro, Francisco Ramos, Michael Gould Carlson, Sergio Trilles Oliver
Published: 2026-01-09
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.05984v1

The rapid deployment of Internet of Things (IoT) devices has led to large-scale sensor networks that monitor environmental and urban phenomena in real time. Communities of Interest (CoIs) provide a promising paradigm for organising heterogeneous IoT sensor networks by grouping devices with similar operational and environmental characteristics. This work presents an anomaly detection framework based on the CoI paradigm by grouping sensors into communities using a fused similarity matrix that incorporates temporal correlations via Spearman coefficients, spatial proximity using Gaussian distance decay, and elevation similarities. For each community, representative stations based on the best silhouette are selected and three autoencoder architectures (BiLSTM, LSTM, and MLP) are trained using Bayesian hyperparameter optimization with expanding window cross-validation and tested on stations from the same cluster and the best representative stations of other clusters. The models are trained on normal temperature patterns of the data and anomalies are detected through reconstruction error analysis. Experimental results show a robust within-community performance across the evaluated configurations, while variations across communities are observed. Overall, the results support the applicability of community-based model sharing in reducing computational overhead and to analyse model generalisability across IoT sensor networks.

---

### Adaptive Conditional Contrast-Agnostic Deformable Image Registration with Uncertainty Estimation

Authors: Yinsong Wang, Xinzhe Luo, Siyi Du, Chen Qin
Published: 2026-01-09
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.05981v1

Deformable multi-contrast image registration is a challenging yet crucial task due to the complex, non-linear intensity relationships across different imaging contrasts. Conventional registration methods typically rely on iterative optimization of the deformation field, which is time-consuming. Although recent learning-based approaches enable fast and accurate registration during inference, their generalizability remains limited to the specific contrasts observed during training. In this work, we propose an adaptive conditional contrast-agnostic deformable image registration framework (AC-CAR) based on a random convolution-based contrast augmentation scheme. AC-CAR can generalize to arbitrary imaging contrasts without observing them during training. To encourage contrast-invariant feature learning, we propose an adaptive conditional feature modulator (ACFM) that adaptively modulates the features and the contrast-invariant latent regularization to enforce the consistency of the learned feature across different imaging contrasts. Additionally, we enable our framework to provide contrast-agnostic registration uncertainty by integrating a variance network that leverages the contrast-agnostic registration encoder to improve the trustworthiness and reliability of AC-CAR. Experimental results demonstrate that AC-CAR outperforms baseline methods in registration accuracy and exhibits superior generalization to unseen imaging contrasts. Code is available at https://github.com/Yinsong0510/AC-CAR.

---

### AWaRe-SAC: Proactive Slice Admission Control under Weather-Induced Capacity Uncertainty

Authors: Dror Jacoby, Yanzhi Li, Shuyue Yu, Nicola Di Cicco, Hagit Messer, Gil Zussman, Igor Kadota
Published: 2026-01-09
Categories: cs.NI, cs.LG
arXiv: https://arxiv.org/abs/2601.05978v2

Millimeter-wave (mmWave) links are increasingly utilized in wireless x-haul transport to meet growing service demands. However, the inherent susceptibility of mmWave links to weather-related attenuation creates uncertainty about future network capacity which can significantly affect Quality of Service (QoS). This creates a critical challenge: how to make admission control decisions for slices with QoS requirements, balancing acceptance rewards against the risk of future QoS-violation penalties due to capacity uncertainty? To address this, we develop a proactive slice admission control framework that tightly integrates: (i) a predictor that leverages historical link measurements to forecast short-term attenuation and quantify uncertainty; and (ii) an admission control algorithm that incorporates both the predictions and uncertainties to maximize rewards and minimize QoS-violation penalties. We compare our framework against baseline, state-of-the-art, and idealized oracle algorithms using real-world mmWave x-haul data and residential traffic traces. Simulations suggest that our framework can achieve revenues that are 250% larger than baseline algorithms and 75% larger than state-of-the-art algorithms.

---

### AWaRe-SAC: Proactive Slice Admission Control under Weather-Induced Capacity Uncertainty

Authors: Dror Jacoby, Yanzhi Li, Shuyue Yu, Nicola Di Cicco, Hagit Messer, Gil Zussman, Igor Kadota
Published: 2026-01-09
Categories: cs.NI, cs.LG
arXiv: https://arxiv.org/abs/2601.05978v1

As emerging applications demand higher throughput and lower latencies, operators are increasingly deploying millimeter-wave (mmWave) links within x-haul transport networks, spanning fronthaul, midhaul, and backhaul segments. However, the inherent susceptibility of mmWave frequencies to weather-related attenuation, particularly rain fading, complicates the maintenance of stringent Quality of Service (QoS) requirements. This creates a critical challenge: making admission decisions under uncertainty regarding future network capacity. To address this, we develop a proactive slice admission control framework for mmWave x-haul networks subject to rain-induced fluctuations. Our objective is to improve network performance, ensure QoS, and optimize revenue, thereby surpassing the limitations of standard reactive approaches. The proposed framework integrates a deep learning predictor of future network conditions with a proactive Q-learning-based slice admission control mechanism. We validate our solution using real-world data from a mmWave x-haul deployment in a dense urban area, incorporating realistic models of link capacity attenuation and dynamic slice demands. Extensive evaluations demonstrate that our proactive solution achieves 2-3x higher long-term average revenue under dynamic link conditions, providing a scalable and resilient framework for adaptive admission control.

---

### DeePM: Regime-Robust Deep Learning for Systematic Macro Portfolio Management

Authors: Kieran Wood, Stephen J. Roberts, Stefan Zohren
Published: 2026-01-09
Categories: q-fin.TR, cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2601.05975v1

We propose DeePM (Deep Portfolio Manager), a structured deep-learning macro portfolio manager trained end-to-end to maximize a robust, risk-adjusted utility. DeePM addresses three fundamental challenges in financial learning: (1) it resolves the asynchronous "ragged filtration" problem via a Directed Delay (Causal Sieve) mechanism that prioritizes causal impulse-response learning over information freshness; (2) it combats low signal-to-noise ratios via a Macroeconomic Graph Prior, regularizing cross-asset dependence according to economic first principles; and (3) it optimizes a distributionally robust objective where a smooth worst-window penalty serves as a differentiable proxy for Entropic Value-at-Risk (EVaR) - a window-robust utility encouraging strong performance in the most adverse historical subperiods. In large-scale backtests from 2010-2025 on 50 diversified futures with highly realistic transaction costs, DeePM attains net risk-adjusted returns that are roughly twice those of classical trend-following strategies and passive benchmarks, solely using daily closing prices. Furthermore, DeePM improves upon the state-of-the-art Momentum Transformer architecture by roughly fifty percent. The model demonstrates structural resilience across the 2010s "CTA (Commodity Trading Advisor) Winter" and the post-2020 volatility regime shift, maintaining consistent performance through the pandemic, inflation shocks, and the subsequent higher-for-longer environment. Ablation studies confirm that strictly lagged cross-sectional attention, graph prior, principled treatment of transaction costs, and robust minimax optimization are the primary drivers of this generalization capability.

---

### VideoAR: Autoregressive Video Generation via Next-Frame & Scale Prediction

Authors: Longbin Ji, Xiaoxiong Liu, Junyuan Shang, Shuohuan Wang, Yu Sun, Hua Wu, Haifeng Wang
Published: 2026-01-09
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2601.05966v2

Recent advances in video generation have been dominated by diffusion and flow-matching models, which produce high-quality results but remain computationally intensive and difficult to scale. In this work, we introduce VideoAR, the first large-scale Visual Autoregressive (VAR) framework for video generation that combines multi-scale next-frame prediction with autoregressive modeling. VideoAR disentangles spatial and temporal dependencies by integrating intra-frame VAR modeling with causal next-frame prediction, supported by a 3D multi-scale tokenizer that efficiently encodes spatio-temporal dynamics. To improve long-term consistency, we propose Multi-scale Temporal RoPE, Cross-Frame Error Correction, and Random Frame Mask, which collectively mitigate error propagation and stabilize temporal coherence. Our multi-stage pretraining pipeline progressively aligns spatial and temporal learning across increasing resolutions and durations. Empirically, VideoAR achieves new state-of-the-art results among autoregressive models, improving FVD on UCF-101 from 99.5 to 88.6 while reducing inference steps by over 10x, and reaching a VBench score of 81.74-competitive with diffusion-based models an order of magnitude larger. These results demonstrate that VideoAR narrows the performance gap between autoregressive and diffusion paradigms, offering a scalable, efficient, and temporally consistent foundation for future video generation research.

---

### VideoAR: Autoregressive Video Generation via Next-Frame & Scale Prediction

Authors: Longbin Ji, Xiaoxiong Liu, Junyuan Shang, Shuohuan Wang, Yu Sun, Hua Wu, Haifeng Wang
Published: 2026-01-09
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2601.05966v1

Recent advances in video generation have been dominated by diffusion and flow-matching models, which produce high-quality results but remain computationally intensive and difficult to scale. In this work, we introduce VideoAR, the first large-scale Visual Autoregressive (VAR) framework for video generation that combines multi-scale next-frame prediction with autoregressive modeling. VideoAR disentangles spatial and temporal dependencies by integrating intra-frame VAR modeling with causal next-frame prediction, supported by a 3D multi-scale tokenizer that efficiently encodes spatio-temporal dynamics. To improve long-term consistency, we propose Multi-scale Temporal RoPE, Cross-Frame Error Correction, and Random Frame Mask, which collectively mitigate error propagation and stabilize temporal coherence. Our multi-stage pretraining pipeline progressively aligns spatial and temporal learning across increasing resolutions and durations. Empirically, VideoAR achieves new state-of-the-art results among autoregressive models, improving FVD on UCF-101 from 99.5 to 88.6 while reducing inference steps by over 10x, and reaching a VBench score of 81.74-competitive with diffusion-based models an order of magnitude larger. These results demonstrate that VideoAR narrows the performance gap between autoregressive and diffusion paradigms, offering a scalable, efficient, and temporally consistent foundation for future video generation research.

---

### Distilling Feedback into Memory-as-a-Tool

Authors: Víctor Gallego
Published: 2026-01-09
Categories: cs.CL
arXiv: https://arxiv.org/abs/2601.05960v2

We propose a framework that amortizes the cost of inference-time reasoning by converting transient critiques into retrievable guidelines, through a file-based memory system and agent-controlled tool calls. We evaluate this method on the Rubric Feedback Bench, a novel dataset for rubric-based learning. Experiments demonstrate that our augmented LLMs rapidly match the performance of test-time refinement pipelines while drastically reducing inference cost.

---