# Research Papers — 2026-01 · bundle page 122 of 189 > Full-text markdown of papers #6051–6100 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/122 [← Previous bundle](https://aipod.dev/papers/archive/2026-01/page/121.md) [Next bundle →](https://aipod.dev/papers/archive/2026-01/page/123.md) ### DiffMM: Efficient Method for Accurate Noisy and Sparse Trajectory Map Matching via One Step Diffusion Authors: Chenxu Han, Sean Bin Yang, Jilin Hu Published: 2026-01-13 Categories: cs.LG, cs.CV arXiv: https://arxiv.org/abs/2601.08482v1 Map matching for sparse trajectories is a fundamental problem for many trajectory-based applications, e.g., traffic scheduling and traffic flow analysis. Existing methods for map matching are generally based on Hidden Markov Model (HMM) or encoder-decoder framework. However, these methods continue to face significant challenges when handling noisy or sparsely sampled GPS trajectories. To address these limitations, we propose DiffMM, an encoder-diffusion-based map matching framework that produces effective yet efficient matching results through a one-step diffusion process. We first introduce a road segment-aware trajectory encoder that jointly embeds the input trajectory and its surrounding candidate road segments into a shared latent space through an attention mechanism. Next, we propose a one step diffusion method to realize map matching through a shortcut model by leveraging the joint embedding of the trajectory and candidate road segments as conditioning context. We conduct extensive experiments on large-scale trajectory datasets, demonstrating that our approach consistently outperforms state-of-the-art map matching methods in terms of both accuracy and efficiency, particularly for sparse trajectories and complex road network topologies. --- ### Do You Understand How I Feel?: Towards Verified Empathy in Therapy Chatbots Authors: Francesco Dettori, Matteo Forasassi, Lorenzo Veronese, Livia Lestingi, Vincenzo Scotti, Matteo Giovanni Rossi Published: 2026-01-13 Categories: cs.CL, cs.HC, cs.SE arXiv: https://arxiv.org/abs/2601.08477v1 Conversational agents are increasingly used as support tools along mental therapeutic pathways with significant societal impacts. In particular, empathy is a key non-functional requirement in therapeutic contexts, yet current chatbot development practices provide no systematic means to specify or verify it. This paper envisions a framework integrating natural language processing and formal verification to deliver empathetic therapy chatbots. A Transformer-based model extracts dialogue features, which are then translated into a Stochastic Hybrid Automaton model of dyadic therapy sessions. Empathy-related properties can then be verified through Statistical Model Checking, while strategy synthesis provides guidance for shaping agent behavior. Preliminary results show that the formal model captures therapy dynamics with good fidelity and that ad-hoc strategies improve the probability of satisfying empathy requirements. --- ### Cross-modal Proxy Evolving for OOD Detection with Vision-Language Models Authors: Hao Tang, Yu Liu, Shuanglin Yan, Fei Shen, Shengfeng He, Jing Qin Published: 2026-01-13 Categories: cs.CV, cs.MM arXiv: https://arxiv.org/abs/2601.08476v2 Reliable zero-shot detection of out-of-distribution (OOD) inputs is critical for deploying vision-language models in open-world settings. However, the lack of labeled negatives in zero-shot OOD detection necessitates proxy signals that remain effective under distribution shift. Existing negative-label methods rely on a fixed set of textual proxies, which (i) sparsely sample the semantic space beyond in-distribution (ID) classes and (ii) remain static while only visual features drift, leading to cross-modal misalignment and unstable predictions. In this paper, we propose CoEvo, a training- and annotation-free test-time framework that performs bidirectional, sample-conditioned adaptation of both textual and visual proxies. Specifically, CoEvo introduces a proxy-aligned co-evolution mechanism to maintain two evolving proxy caches, which dynamically mines contextual textual negatives guided by test images and iteratively refines visual proxies, progressively realigning cross-modal similarities and enlarging local OOD margins. Finally, we dynamically re-weight the contributions of dual-modal proxies to obtain a calibrated OOD score that is robust to distribution shift. Extensive experiments on standard benchmarks demonstrate that CoEvo achieves state-of-the-art performance, improving AUROC by 1.33% and reducing FPR95 by 45.98% on ImageNet-1K compared to strong negative-label baselines. --- ### SUMMPILOT: Bridging Efficiency and Customization for Interactive Summarization System Authors: JungMin Yun, Juhwan Choi, Kyohoon Jin, Soojin Jang, Jinhee Jang, YoungBin Kim Published: 2026-01-13 Categories: cs.AI, cs.HC arXiv: https://arxiv.org/abs/2601.08475v1 This paper incorporates the efficiency of automatic summarization and addresses the challenge of generating personalized summaries tailored to individual users' interests and requirements. To tackle this challenge, we introduce SummPilot, an interaction-based customizable summarization system. SummPilot leverages a large language model to facilitate both automatic and interactive summarization. Users can engage with the system to understand document content and personalize summaries through interactive components such as semantic graphs, entity clustering, and explainable evaluation. Our demo and user studies demonstrate SummPilot's adaptability and usefulness for customizable summarization. --- ### sui-1: Grounded and Verifiable Long-Form Summarization Authors: Benedikt Droste, Jan Philipp Harries, Maximilian Idahl, Björn Plüster Published: 2026-01-13 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2601.08472v1 Large language models frequently generate plausible but unfaithful summaries that users cannot verify against source text, a critical limitation in compliance-sensitive domains such as government and legal analysis. We present sui-1, a 24B parameter model that produces abstractive summaries with inline citations, enabling users to trace each claim to its source sentence. Our synthetic data pipeline combines chain-of-thought prompting with multi-stage verification, generating over 22,000 high-quality training examples across five languages from diverse sources including parliamentary documents, web text, and Wikipedia. Evaluation shows sui-1 significantly outperforms all tested open-weight baselines, including models with 3x more parameters. These results demonstrate that task-specific training substantially outperforms scale alone for citation-grounded summarization. Model weights and an interactive demo are publicly available. --- ### Towards Safer Mobile Agents: Scalable Generation and Evaluation of Diverse Scenarios for VLMs Authors: Takara Taniguchi, Kuniaki Saito, Atsushi Hashimoto Published: 2026-01-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.08470v1 Vision Language Models (VLMs) are increasingly deployed in autonomous vehicles and mobile systems, making it crucial to evaluate their ability to support safer decision-making in complex environments. However, existing benchmarks inadequately cover diverse hazardous situations, especially anomalous scenarios with spatio-temporal dynamics. While image editing models are a promising means to synthesize such hazards, it remains challenging to generate well-formulated scenarios that include moving, intrusive, and distant objects frequently observed in the real world. To address this gap, we introduce \textbf{HazardForge}, a scalable pipeline that leverages image editing models to generate these scenarios with layout decision algorithms, and validation modules. Using HazardForge, we construct \textbf{MovSafeBench}, a multiple-choice question (MCQ) benchmark comprising 7,254 images and corresponding QA pairs across 13 object categories, covering both normal and anomalous objects. Experiments using MovSafeBench show that VLM performance degrades notably under conditions including anomalous objects, with the largest drop in scenarios requiring nuanced motion understanding. --- ### JudgeRLVR: Judge First, Generate Second for Efficient Reasoning Authors: Jiangshan Duo, Hanyu Li, Hailin Zhang, Yudong Wang, Sujian Li, Liang Zhao Published: 2026-01-13 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2601.08468v1 Reinforcement Learning with Verifiable Rewards (RLVR) has become a standard paradigm for reasoning in Large Language Models. However, optimizing solely for final-answer correctness often drives models into aimless, verbose exploration, where they rely on exhaustive trial-and-error tactics rather than structured planning to reach solutions. While heuristic constraints like length penalties can reduce verbosity, they often truncate essential reasoning steps, creating a difficult trade-off between efficiency and verification. In this paper, we argue that discriminative capability is a prerequisite for efficient generation: by learning to distinguish valid solutions, a model can internalize a guidance signal that prunes the search space. We propose JudgeRLVR, a two-stage judge-then-generate paradigm. In the first stage, we train the model to judge solution responses with verifiable answers. In the second stage, we fine-tune the same model with vanilla generating RLVR initialized from the judge. Compared to Vanilla RLVR using the same math-domain training data, JudgeRLVR achieves a better quality--efficiency trade-off for Qwen3-30B-A3B: on in-domain math, it delivers about +3.7 points average accuracy gain with -42\% average generation length; on out-of-domain benchmarks, it delivers about +4.5 points average accuracy improvement, demonstrating enhanced generalization. --- ### Zero-Shot Distracted Driver Detection via Vision Language Models with Double Decoupling Authors: Takamichi Miyata, Sumiko Miyata, Andrew Morris Published: 2026-01-13 Categories: cs.CV, cs.LG, eess.IV arXiv: https://arxiv.org/abs/2601.08467v3 Distracted driving is a major cause of traffic collisions, calling for robust and scalable detection methods. Vision-language models (VLMs) enable strong zero-shot image classification, but existing VLM-based distracted driver detectors often underperform in real-world conditions. We identify subject-specific appearance variations (e.g., clothing, age, and gender) as a key bottleneck: VLMs entangle these factors with behavior cues, leading to decisions driven by who the driver is rather than what the driver is doing. To address this, we propose a subject decoupling framework that extracts a driver appearance embedding and removes its influence from the image embedding prior to zero-shot classification, thereby emphasizing distraction-relevant evidence. We further orthogonalize text embeddings via metric projection onto Stiefel manifold to improve separability while staying close to the original semantics. Experiments demonstrate consistent gains over prior baselines, indicating the promise of our approach for practical road-safety applications. Code is available at https://github.com/mtakamichi/ZVL-DDD --- ### CoMa: Contextual Massing Generation with Vision-Language Models Authors: Evgenii Maslov, Alexandra Vabnits, Vladimir Vorona, Anastasia Antsiferova, Valentin Khrulkov, Anastasia Volkova, Anton Gusarov, Andrey Kuznetsov, Ivan Oseledets Published: 2026-01-13 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2601.08464v2 Context-aware building massing is an important early-stage design task: given a site for buildings, a generated massing should not only fit the target parcel, but also relate to the scale, density, and morphology of its surrounding urban fabric. This task is naturally multimodal, since the target output should remain structured and editable, while the surrounding context, including other buildings or roads, can be represented as vector geometry, map imagery, or three-dimensional views. In this paper, we study contextual massing generation using vision-language models (VLMs) and analyze their performance on this task across different context modalities during training and inference. We assemble an experimental dataset of 12,845 Melbourne massings with parcel contours, structured 3D geometry, neighboring buildings, top-down views, and multi-view 3D context images. We also introduce a learned contextual relevance metric for evaluating whether generated massings are morphologically compatible with their surrounding context. Using Qwen3-VL models, we compare no-context, unimodal-context, and multimodal-context training regimes and evaluate inference performance under controlled combinations of modalities and amounts of context. The results show that model size strongly affects generation quality, multimodal training improves the use of individual modalities, and multimodal inference provides a stronger contextual signal than isolated context inputs. --- ### M3-BENCH: Process-Aware Evaluation of LLM Agents' Social Behaviors in Mixed-Motive Games Authors: Sixiong Xie, Zhuofan Shi, Haiyang Shen, Yun Ma, Xiang Jing Published: 2026-01-13 Categories: cs.AI arXiv: https://arxiv.org/abs/2601.08462v2 Existing benchmarks for LLM agents' social behavior typically focus on a single capability dimension and evaluate only behavioral outcomes, overlooking process signals from reasoning and communication. We present M3-BENCH, a benchmark of 24 mixed-motive games with a process-aware evaluation framework spanning three complementary views: Behavioral Trajectory Analysis (BTA), Reasoning Process Analysis (RPA), and Communication Content Analysis (CCA). Evaluating 11 frontier LLMs and a human baseline, M3-BENCH reveals substantial differences in social competence that outcome-only evaluation misses. In particular, we identify an "overthink-undercommunicate" pattern: reasoning models achieve strong internal deliberation scores but often fail to translate them into effective social communication. Although top models can surpass humans on task outcomes, humans exhibit markedly higher cross-view consistency, suggesting that current LLM agents still lack the behavioral coherence characteristic of human social competence. Our analysis further shows that the three-view decomposition surfaces safety-relevant risks, such as cooperative behavior paired with latent opportunistic reasoning, that remain hidden under outcome-only metrics. --- ### Modality-Decoupled RGB-Thermal Object Detector via Query Fusion Authors: Chao Tian, Zikun Zhou, Chao Yang, Guoqing Zhu, Fu'an Zhong, Zhenyu He Published: 2026-01-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.08458v1 The advantage of RGB-Thermal (RGB-T) detection lies in its ability to perform modality fusion and integrate cross-modality complementary information, enabling robust detection under diverse illumination and weather conditions. However, under extreme conditions where one modality exhibits poor quality and disturbs detection, modality separation is necessary to mitigate the impact of noise. To address this problem, we propose a Modality-Decoupled RGB-T detection framework with Query Fusion (MDQF) to balance modality complementation and separation. In this framework, DETR-like detectors are employed as separate branches for the RGB and TIR images, with query fusion interspersed between the two branches in each refinement stage. Herein, query fusion is performed by feeding the high-quality queries from one branch to the other one after query selection and adaptation. This design effectively excludes the degraded modality and corrects the predictions using high-quality queries. Moreover, the decoupled framework allows us to optimize each individual branch with unpaired RGB or TIR images, eliminating the need for paired RGB-T data. Extensive experiments demonstrate that our approach delivers superior performance to existing RGB-T detectors and achieves better modality independence. --- ### An Under-Explored Application for Explainable Multimodal Misogyny Detection in code-mixed Hindi-English Authors: Sargam Yadav, Abhishek Kaushik, Kevin Mc Daid Published: 2026-01-13 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2601.08457v1 Digital platforms have an ever-expanding user base, and act as a hub for communication, business, and connectivity. However, this has also allowed for the spread of hate speech and misogyny. Artificial intelligence models have emerged as an effective solution for countering online hate speech but are under explored for low resource and code-mixed languages and suffer from a lack of interpretability. Explainable Artificial Intelligence (XAI) can enhance transparency in the decisions of deep learning models, which is crucial for a sensitive domain such as hate speech detection. In this paper, we present a multi-modal and explainable web application for detecting misogyny in text and memes in code-mixed Hindi and English. The system leverages state-of-the-art transformer-based models that support multilingual and multimodal settings. For text-based misogyny identification, the system utilizes XLM-RoBERTa (XLM-R) and multilingual Bidirectional Encoder Representations from Transformers (mBERT) on a dataset of approximately 4,193 comments. For multimodal misogyny identification from memes, the system utilizes mBERT + EfficientNet, and mBERT + ResNET trained on a dataset of approximately 4,218 memes. It also provides feature importance scores using explainability techniques including Shapley Additive Values (SHAP) and Local Interpretable Model Agnostic Explanations (LIME). The application aims to serve as a tool for both researchers and content moderators, to promote further research in the field, combat gender based digital violence, and ensure a safe digital space. The system has been evaluated using human evaluators who provided their responses on Chatbot Usability Questionnaire (CUQ) and User Experience Questionnaire (UEQ) to determine overall usability. --- ### Developing Predictive and Robust Radiomics Models for Chemotherapy Response in High-Grade Serous Ovarian Carcinoma Authors: Sepideh Hatamikia, Geevarghese George, Florian Schwarzhans, Amirreza Mahbod, Marika AV Reinius, Ali Abbasian Ardakani, Mercedes Jimenez-Linan, Satish Viswanath, Mireia Crispin-Ortuzar, Lorena Escudero Sanchez, Evis Sala, James D Brenton et al. Published: 2026-01-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.08455v1 Objectives: High-grade serous ovarian carcinoma (HGSOC) is typically diagnosed at an advanced stage with extensive peritoneal metastases, making treatment challenging. Neoadjuvant chemotherapy (NACT) is often used to reduce tumor burden before surgery, but about 40% of patients show limited response. Radiomics, combined with machine learning (ML), offers a promising non-invasive method for predicting NACT response by analyzing computed tomography (CT) imaging data. This study aimed to improve response prediction in HGSOC patients undergoing NACT by integration different feature selection methods. Materials and methods: A framework for selecting robust radiomics features was introduced by employing an automated randomisation algorithm to mimic inter-observer variability, ensuring a balance between feature robustness and prediction accuracy. Four response metrics were used: chemotherapy response score (CRS), RECIST, volume reduction (VolR), and diameter reduction (DiaR). Lesions in different anatomical sites were studied. Pre- and post-NACT CT scans were used for feature extraction and model training on one cohort, and an independent cohort was used for external testing. Results: The best prediction performance was achieved using all lesions combined for VolR prediction, with an AUC of 0.83. Omental lesions provided the best results for CRS prediction (AUC 0.77), while pelvic lesions performed best for DiaR (AUC 0.76). Conclusion: The integration of robustness into the feature selection processes ensures the development of reliable models and thus facilitates the implementation of the radiomics models in clinical applications for HGSOC patients. Future work should explore further applications of radiomics in ovarian cancer, particularly in real-time clinical settings. --- ### Decoding Order Matters in Autoregressive Speech Synthesis Authors: Minghui Zhao, Anton Ragni Published: 2026-01-13 Categories: cs.SD, cs.AI, eess.AS arXiv: https://arxiv.org/abs/2601.08450v2 Autoregressive speech synthesis often adopts a left-to-right order, yet generation order is a modelling choice. We investigate decoding order through masked diffusion framework, which progressively unmasks positions and allows arbitrary decoding orders during training and inference. By interpolating between identity and random permutations, we show that randomness in decoding order affects speech quality. We further compare fixed strategies, such as \texttt{l2r} and \texttt{r2l} with adaptive ones, such as Top-$K$, finding that fixed-order decoding, including the dominating left-to-right approach, is suboptimal, while adaptive decoding yields better performance. Finally, since masked diffusion requires discrete inputs, we quantise acoustic representations and find that even 1-bit quantisation can support reasonably high-quality speech. --- ### Divide and Conquer: Static-Dynamic Collaboration for Few-Shot Class-Incremental Learning Authors: Kexin Bao, Daichi Zhang, Yong Li, Dan Zeng, Shiming Ge Published: 2026-01-13 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2601.08448v1 Few-shot class-incremental learning (FSCIL) aims to continuously recognize novel classes under limited data, which suffers from the key stability-plasticity dilemma: balancing the retention of old knowledge with the acquisition of new knowledge. To address this issue, we divide the task into two different stages and propose a framework termed Static-Dynamic Collaboration (SDC) to achieve a better trade-off between stability and plasticity. Specifically, our method divides the normal pipeline of FSCIL into Static Retaining Stage (SRS) and Dynamic Learning Stage (DLS), which harnesses old static and incremental dynamic class information, respectively. During SRS, we train an initial model with sufficient data in the base session and preserve the key part as static memory to retain fundamental old knowledge. During DLS, we introduce an extra dynamic projector jointly trained with the previous static memory. By employing both stages, our method achieves improved retention of old knowledge while continuously adapting to new classes. Extensive experiments on three public benchmarks and a real-world application dataset demonstrate that our method achieves state-of-the-art performance against other competitors. --- ### Sleep-Based Homeostatic Regularization for Stabilizing Spike-Timing-Dependent Plasticity in Recurrent Spiking Neural Networks Authors: Andreas Massey, Aliaksandr Hubin, Stefano Nichele, Solve Sæbø Published: 2026-01-13 Categories: cs.NE, stat.ML arXiv: https://arxiv.org/abs/2601.08447v1 Spike-timing-dependent plasticity (STDP) provides a biologically-plausible learning mechanism for spiking neural networks (SNNs); however, Hebbian weight updates in architectures with recurrent connections suffer from pathological weight dynamics: unbounded growth, catastrophic forgetting, and loss of representational diversity. We propose a neuromorphic regularization scheme inspired by the synaptic homeostasis hypothesis: periodic offline phases during which external inputs are suppressed, synaptic weights undergo stochastic decay toward a homeostatic baseline, and spontaneous activity enables memory consolidation. We demonstrate that this sleep-wake cycle prevents weight saturation while preserving learned structure. Empirically, we find that low to intermediate sleep durations (10-20\% of training) improve stability on MNIST-like benchmarks in our STDP-SNN model, without any data-specific hyperparameter tuning. In contrast, the same sleep intervention yields no measurable benefit for the surrogate-gradient spiking neural network (SG-SNN). Taken together, these results suggest that periodic, sleep-based renormalization may represent a fundamental mechanism for stabilizing local Hebbian learning in neuromorphic systems, while also indicating that special care is required when integrating such protocols with existing gradient-based optimization methods. --- ### Noise-Adaptive Regularization for Robust Multi-Label Remote Sensing Image Classification Authors: Tom Burgert, Julia Henkel, Begüm Demir Published: 2026-01-13 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2601.08446v2 The development of reliable methods for multi-label classification (MLC) has become a prominent research direction in remote sensing (RS). As the scale of RS data continues to expand, annotation procedures increasingly rely on thematic products or crowdsourced procedures to reduce the cost of manual annotation. While cost-effective, these strategies often introduce multi-label noise in the form of partially incorrect annotations. In MLC, label noise arises as additive noise, subtractive noise, or a combination of both in the form of mixed noise. Previous work has largely overlooked this distinction and commonly treats noisy annotations as supervised signals, lacking mechanisms that explicitly adapt learning behavior to different noise types. To address this limitation, we propose NAR, a noise-adaptive regularization method that explicitly distinguishes between additive and subtractive noise within a semi-supervised learning framework. NAR employs a confidence-based label handling mechanism that dynamically retains label entries with high confidence, temporarily deactivates entries with moderate confidence, and corrects low confidence entries via flipping. This selective attenuation of supervision is integrated with early-learning regularization (ELR) to stabilize training and mitigate overfitting to corrupted labels. Experiments across additive, subtractive, and mixed noise scenarios demonstrate that NAR consistently improves robustness compared with existing methods. Performance improvements are most pronounced under subtractive and mixed noise, indicating that adaptive suppression and selective correction of noisy supervision provide an effective strategy for noise robust learning in RS MLC. --- ### Beyond Linearization: Attributed Table Graphs for Table Reasoning Authors: Yuxiang Wang, Junhao Gan, Shengxiang Gao, Shenghao Ye, Zhengyi Yang, Jianzhong Qi Published: 2026-01-13 Categories: cs.AI arXiv: https://arxiv.org/abs/2601.08444v2 Table reasoning, a task to answer questions by reasoning over data presented in tables, is an important topic due to the prevalence of knowledge stored in tabular formats. Recent solutions use Large Language Models (LLMs) for their semantic understanding and reasoning capabilities. A common paradigm of such solutions linearizes tables to form plain texts that are served as input to LLMs. This paradigm has critical issues. It requires LLMs to infer row-column-cell relations from serialized inputs, makes evidence paths harder to trace, and is subject to the "lost-in-the-middle" issue. To address these issues, we propose Table Graph Reasoner (TabGR), a model that represents tables as an Attributed Table Graph (ATG) without task-specific training. The ATG explicitly preserves row-column-cell structure while enabling graph-based reasoning over traceable evidence paths. We further propose a Question-Guided Personalized PageRank (QG-PPR) mechanism to rerank tabular data and mitigate the lost-in-the-middle issue. Extensive experiments across multiple table reasoning benchmarks show that TabGR consistently outperforms state-of-the-art models by up to 9.7% in accuracy. Our code is available at: https://github.com/yxw-11/TabGR. --- ### YaPO: Learnable Sparse Activation Steering Vectors for Domain Adaptation Authors: Abdelaziz Bounhar, Rania Hossam Elmohamady Elbadry, Hadi Abdine, Preslav Nakov, Michalis Vazirgiannis, Guokan Shang Published: 2026-01-13 Categories: cs.AI arXiv: https://arxiv.org/abs/2601.08441v1 Steering Large Language Models (LLMs) through activation interventions has emerged as a lightweight alternative to fine-tuning for alignment and personalization. Recent work on Bi-directional Preference Optimization (BiPO) shows that dense steering vectors can be learned directly from preference data in a Direct Preference Optimization (DPO) fashion, enabling control over truthfulness, hallucinations, and safety behaviors. However, dense steering vectors often entangle multiple latent factors due to neuron multi-semanticity, limiting their effectiveness and stability in fine-grained settings such as cultural alignment, where closely related values and behaviors (e.g., among Middle Eastern cultures) must be distinguished. In this paper, we propose Yet another Policy Optimization (YaPO), a \textit{reference-free} method that learns \textit{sparse steering vectors} in the latent space of a Sparse Autoencoder (SAE). By optimizing sparse codes, YaPO produces disentangled, interpretable, and efficient steering directions. Empirically, we show that YaPO converges faster, achieves stronger performance, and exhibits improved training stability compared to dense steering baselines. Beyond cultural alignment, YaPO generalizes to a range of alignment-related behaviors, including hallucination, wealth-seeking, jailbreak, and power-seeking. Importantly, YaPO preserves general knowledge, with no measurable degradation on MMLU. Overall, our results show that YaPO provides a general recipe for efficient, stable, and fine-grained alignment of LLMs, with broad applications to controllability and domain adaptation. The associated code and data are publicly available\footnote{https://github.com/MBZUAI-Paris/YaPO}. --- ### Incentivizing Cardiologist-Like Reasoning in MLLMs for Interpretable Echocardiographic Diagnosis Authors: Yi Qin, Lehan Wang, Chenxu Zhao, Alex P. W. Lee, Xiaomeng Li Published: 2026-01-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.08440v1 Echocardiographic diagnosis is vital for cardiac screening yet remains challenging. Existing echocardiography foundation models do not effectively capture the relationships between quantitative measurements and clinical manifestations, whereas medical reasoning multimodal large language models (MLLMs) require costly construction of detailed reasoning paths and remain ineffective at directly incorporating such echocardiographic priors into their reasoning. To address these limitations, we propose a novel approach comprising Cardiac Reasoning Template (CRT) and CardiacMind to enhance MLLM's echocardiographic reasoning by introducing cardiologist-like mindset. Specifically, CRT provides stepwise canonical diagnostic procedures for complex cardiac diseases to streamline reasoning path construction without the need for costly case-by-case verification. To incentivize reasoning MLLM under CRT, we develop CardiacMind, a new reinforcement learning scheme with three novel rewards: Procedural Quantity Reward (PQtR), Procedural Quality Reward (PQlR), and Echocardiographic Semantic Reward (ESR). PQtR promotes detailed reasoning; PQlR promotes integration of evidence across views and modalities, while ESR grounds stepwise descriptions in visual content. Our methods show a 48% improvement in multiview echocardiographic diagnosis for 15 complex cardiac diseases and a 5% improvement on CardiacNet-PAH over prior methods. The user study on our method's reasoning outputs shows 93.33% clinician agreement with cardiologist-like reasoning logic. Our code will be available. --- ### Fine-Mem: Fine-Grained Feedback Alignment for Long-Horizon Memory Management Authors: Weitao Ma, Xiaocheng Feng, Lei Huang, Xiachong Feng, Zhanyu Ma, Jun Xu, Jiuchong Gao, Jinghua Hao, Renqing He, Bing Qin Published: 2026-01-13 Categories: cs.CL arXiv: https://arxiv.org/abs/2601.08435v1 Effective memory management is essential for large language model agents to navigate long-horizon tasks. Recent research has explored using Reinforcement Learning to develop specialized memory manager agents. However, existing approaches rely on final task performance as the primary reward, which results in severe reward sparsity and ineffective credit assignment, providing insufficient guidance for individual memory operations. To this end, we propose Fine-Mem, a unified framework designed for fine-grained feedback alignment. First, we introduce a Chunk-level Step Reward to provide immediate step-level supervision via auxiliary chunk-specific question answering tasks. Second, we devise Evidence-Anchored Reward Attribution to redistribute global rewards by anchoring credit to key memory operations, based on the specific memory items utilized as evidence in reasoning. Together, these components enable stable policy optimization and align local memory operations with the long-term utility of memory. Experiments on Memalpha and MemoryAgentBench demonstrate that Fine-Mem consistently outperforms strong baselines, achieving superior success rates across various sub-tasks. Further analysis reveals its adaptability and strong generalization capabilities across diverse model configurations and backbones. --- ### Large Multimodal Models for Embodied Intelligent Driving: The Next Frontier in Self-Driving? Authors: Long Zhang, Yuchen Xia, Bingqing Wei, Zhen Liu, Shiwen Mao, Zhu Han, Mohsen Guizani Published: 2026-01-13 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2601.08434v3 The advent of Large Multimodal Models (LMMs) offers a promising technology to tackle the limitations of modular design in autonomous driving, which often falters in open-world scenarios requiring sustained environmental understanding and logical reasoning. Besides, embodied artificial intelligence facilitates policy optimization through closed-loop interactions to achieve the continuous learning capability, thereby advancing autonomous driving toward embodied intelligent (El) driving. However, such capability will be constrained by relying solely on LMMs to enhance EI driving without joint decision-making. This article introduces a novel semantics and policy dual-driven hybrid decision framework to tackle this challenge, ensuring continuous learning and joint decision. The framework merges LMMs for semantic understanding and cognitive representation, and deep reinforcement learning (DRL) for real-time policy optimization. We start by introducing the foundational principles of EI driving and LMMs. Moreover, we examine the emerging opportunities this framework enables, encompassing potential benefits and representative use cases. A case study is conducted experimentally to validate the performance superiority of our framework in completing lane-change planning task. Finally, several future research directions to empower EI driving are identified to guide subsequent work. --- ### RubricHub: A Comprehensive and Highly Discriminative Rubric Dataset via Automated Coarse-to-Fine Generation Authors: Sunzhu Li, Jiale Zhao, Miteto Wei, Huimin Ren, Yang Zhou, Jingwen Yang, Shunyu Liu, Kaike Zhang, Wei Chen Published: 2026-01-13 Categories: cs.AI arXiv: https://arxiv.org/abs/2601.08430v2 Reinforcement Learning with Verifiable Rewards (RLVR) has driven substantial progress in reasoning-intensive domains like mathematics. However, optimizing open-ended generation remains challenging due to the lack of ground truth. While rubric-based evaluation offers a structured proxy for verification, existing methods suffer from scalability bottlenecks and coarse criteria, resulting in a supervision ceiling effect. To address this, we propose an automated Coarse-to-Fine Rubric Generation framework. By synergizing principle-guided synthesis, multi-model aggregation, and difficulty evolution, our approach produces comprehensive and highly discriminative criteria capable of capturing the subtle nuances. Based on this framework, we introduce RubricHub, a large-scale ($\sim$110k) and multi-domain dataset. We validate its utility through a two-stage post-training pipeline comprising Rubric-based Rejection Sampling Fine-Tuning (RuFT) and Reinforcement Learning (RuRL). Experimental results demonstrate that RubricHub unlocks significant performance gains: our post-trained Qwen3-14B achieves state-of-the-art (SOTA) results on HealthBench (69.3), surpassing proprietary frontier models such as GPT-5. Our code is available at \href{https://github.com/teqkilla/RubricHub}{ this URL}. --- ### Deep Learning Based Facial Retargeting Using Local Patches Authors: Yeonsoo Choi, Inyup Lee, Sihun Cha, Seonghyeon Kim, Sunjin Jung, Junyong Noh Published: 2026-01-13 Categories: cs.CV, cs.GR arXiv: https://arxiv.org/abs/2601.08429v1 In the era of digital animation, the quest to produce lifelike facial animations for virtual characters has led to the development of various retargeting methods. While the retargeting facial motion between models of similar shapes has been very successful, challenges arise when the retargeting is performed on stylized or exaggerated 3D characters that deviate significantly from human facial structures. In this scenario, it is important to consider the target character's facial structure and possible range of motion to preserve the semantics assumed by the original facial motions after the retargeting. To achieve this, we propose a local patch-based retargeting method that transfers facial animations captured in a source performance video to a target stylized 3D character. Our method consists of three modules. The Automatic Patch Extraction Module extracts local patches from the source video frame. These patches are processed through the Reenactment Module to generate correspondingly re-enacted target local patches. The Weight Estimation Module calculates the animation parameters for the target character at every frame for the creation of a complete facial animation sequence. Extensive experiments demonstrate that our method can successfully transfer the semantic meaning of source facial expressions to stylized characters with considerable variations in facial feature proportion. --- ### Silence the Judge: Reinforcement Learning with Self-Verifier via Latent Geometric Clustering Authors: Nonghai Zhang, Weitao Ma, Zhanyu Ma, Jun Xu, Jiuchong Gao, Jinghua Hao, Renqing He, Jingwen Xu Published: 2026-01-13 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2601.08427v2 Group Relative Policy Optimization (GRPO) significantly enhances the reasoning performance of Large Language Models (LLMs). However, this success heavily relies on expensive external verifiers or human rules. Such dependency not only leads to significant computational costs and training latency, but also yields sparse rewards that hinder optimization efficiency. To address these challenges, we propose Latent-GRPO, a framework that derives intrinsic rewards directly from latent space geometry. Crucially, our empirical analysis reveals a compelling geometric property: terminal token representations of correct reasoning trajectories form dense clusters with high intra-class similarity, whereas incorrect trajectories remain scattered as outliers. In light of this discovery, we introduce the Iterative Robust Centroid Estimation (IRCE) algorithm, which generates dense, continuous rewards by mitigating magnitude fluctuations via spherical projection and estimating a robust ``truth centroid'' through iterative aggregation. Experimental results on multiple datasets show that our method maintains model performance while achieving a training speedup of over 2x compared to baselines. Furthermore, extensive results demonstrate strong generalization ability and robustness. The code will be released soon. --- ### Coverage Improvement and Fast Convergence of On-policy Preference Learning Authors: Juno Kim, Jihun Yun, Jason D. Lee, Kwang-Sung Jun Published: 2026-01-13 Categories: cs.LG arXiv: https://arxiv.org/abs/2601.08421v1 Online on-policy preference learning algorithms for language model alignment such as online direct policy optimization (DPO) can significantly outperform their offline counterparts. We provide a theoretical explanation for this phenomenon by analyzing how the sampling policy's coverage evolves throughout on-policy training. We propose and rigorously justify the \emph{coverage improvement principle}: with sufficient batch size, each update moves into a region around the target where coverage is uniformly better, making subsequent data increasingly informative and enabling rapid convergence. In the contextual bandit setting with Bradley-Terry preferences and linear softmax policy class, we show that on-policy DPO converges exponentially in the number of iterations for batch size exceeding a generalized coverage threshold. In contrast, any learner restricted to offline samples from the initial policy suffers a slower minimax rate, leading to a sharp separation in total sample complexity. Motivated by this analysis, we further propose a simple hybrid sampler based on a novel \emph{preferential} G-optimal design, which removes dependence on coverage and guarantees convergence in just two rounds. Finally, we develop principled on-policy schemes for reward distillation in the general function class setting, and show faster noiseless rates under an alternative deviation-based notion of coverage. Experimentally, we confirm that on-policy DPO and our proposed reward distillation algorithms outperform their off-policy counterparts and enjoy stable, monotonic performance gains across iterations. --- ### MMLGNet: Cross-Modal Alignment of Remote Sensing Data using CLIP Authors: Aditya Chaudhary, Sneha Barman, Mainak Singha, Ankit Jha, Girish Mishra, Biplab Banerjee Published: 2026-01-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.08420v1 In this paper, we propose a novel multimodal framework, Multimodal Language-Guided Network (MMLGNet), to align heterogeneous remote sensing modalities like Hyperspectral Imaging (HSI) and LiDAR with natural language semantics using vision-language models such as CLIP. With the increasing availability of multimodal Earth observation data, there is a growing need for methods that effectively fuse spectral, spatial, and geometric information while enabling semantic-level understanding. MMLGNet employs modality-specific encoders and aligns visual features with handcrafted textual embeddings in a shared latent space via bi-directional contrastive learning. Inspired by CLIP's training paradigm, our approach bridges the gap between high-dimensional remote sensing data and language-guided interpretation. Notably, MMLGNet achieves strong performance with simple CNN-based encoders, outperforming several established multimodal visual-only methods on two benchmark datasets, demonstrating the significant benefit of language supervision. Codes are available at https://github.com/AdityaChaudhary2913/CLIP_HSI. --- ### Taxon: Hierarchical Tax Code Prediction with Semantically Aligned LLM Expert Guidance Authors: Jihang Li, Qing Liu, Zulong Chen, Jing Wang, Wei Wang, Chuanfei Xu, Zeyi Wen Published: 2026-01-13 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2601.08418v2 Tax code prediction is a crucial yet underexplored task in automating invoicing and compliance management for large-scale e-commerce platforms. Each product must be accurately mapped to a node within a multi-level taxonomic hierarchy defined by national standards, where errors lead to financial inconsistencies and regulatory risks. This paper presents Taxon, a semantically aligned and expert-guided framework for hierarchical tax code prediction. Taxon integrates (i) a feature-gating mixture-of-experts architecture that adaptively routes multi-modal features across taxonomy levels, and (ii) a semantic consistency model distilled from large language models acting as domain experts to verify alignment between product titles and official tax definitions. To address noisy supervision in real business records, we design a multi-source training pipeline that combines curated tax databases, invoice validation logs, and merchant registration data to provide both structural and semantic supervision. Extensive experiments on the proprietary TaxCode dataset and public benchmarks demonstrate that Taxon achieves state-of-the-art performance, outperforming strong baselines. Further, an additional full hierarchical paths reconstruction procedure significantly improves structural consistency, yielding the highest overall F1 scores. Taxon has been deployed in production within Alibaba's tax service system, handling an average of over 500,000 tax code queries per day and reaching peak volumes above five million requests during business event with improved accuracy, interpretability, and robustness. --- ### Regulatory gray areas of LLM Terms Authors: Brittany I. Davidson, Kate Muir, Florian A. D. Burnat, Adam N. Joinson Published: 2026-01-13 Categories: cs.CY, cs.AI arXiv: https://arxiv.org/abs/2601.08415v2 Large Language Models (LLMs) are increasingly integrated into academic research pipelines; however, the Terms of Service governing their use remain under-examined. We present a comparative analysis of the Terms of Service of five major LLM providers (Anthropic, DeepSeek, Google, OpenAI, and xAI) collected in November 2025. Our analysis reveals substantial variation in the stringency and specificity of usage restrictions for general users and researchers. We identify specific complexities for researchers in security research, computational social sciences, and psychological studies. We identify `regulatory gray areas' where Terms of Service create uncertainty for legitimate use. We contribute a publicly available resource comparing terms across platforms (OSF) and discuss implications for general users and researchers navigating this evolving landscape. --- ### SPARK: Scalable Real-Time Point Cloud Aggregation with Multi-View Self-Calibration Authors: Chentian Sun Published: 2026-01-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.08414v3 Real-time multi-camera 3D reconstruction is crucial for 3D perception, immersive interaction, and robotics. Existing methods struggle with multi-view fusion, camera extrinsic uncertainty, and scalability for large camera setups. We propose SPARK, a self-calibrating real-time multi-camera point cloud reconstruction framework that jointly handles point cloud fusion and extrinsic uncertainty. SPARK consists of: (1) a geometry-aware online extrinsic estimation module leveraging multi-view priors and enforcing cross-view and temporal consistency for stable self-calibration, and (2) a confidence-driven point cloud fusion strategy modeling depth reliability and visibility at pixel and point levels to suppress noise and view-dependent inconsistencies. By performing frame-wise fusion without accumulation, SPARK produces stable point clouds in dynamic scenes while scaling linearly with the number of cameras. Extensive experiments on real-world multi-camera systems show that SPARK outperforms existing approaches in extrinsic accuracy, geometric consistency, temporal stability, and real-time performance, demonstrating its effectiveness and scalability for large-scale multi-camera 3D reconstruction. --- ### Hybrid Distillation with CoT Guidance for Edge-Drone Control Code Generation Authors: Yizhan Feng, Hichem Snoussi, Yuhang Wang, Jing Teng, Abel Cherouat, Tian Wang Published: 2026-01-13 Categories: cs.AI arXiv: https://arxiv.org/abs/2601.08412v1 With large language models demonstrating significant potential in code generation tasks, their application to onboard control of resource-constrained Unmanned Aerial Vehicles has emerged as an important research direction. However, a notable contradiction exists between the high resource consumption of large models and the real-time, lightweight requirements of UAV platforms. This paper proposes an integrated approach that combines knowledge distillation, chain-of-thought guidance, and supervised fine-tuning for UAV multi-SDK control tasks, aiming to efficiently transfer complex reasoning and code generation capabilities to smaller models. Firstly, a high-quality dataset covering various mainstream UAV SDKs is constructed, featuring instruction-code-reasoning chains, and incorporates counterfactual negative samples for data augmentation, guiding the model to learn the end-to-end logic from instruction parsing to code generation. Secondly, leveraging DeepSeek-Coder-V2-Lite quantized via QLoRA as the teacher model, and based on a hybrid black-box and white-box distillation strategy, high-quality chain-of-thought soft labels are generated. These are combined with a weighted cross-entropy loss using hard labels to transfer complex reasoning capabilities to the smaller student model. Finally, through prompt tuning engineering optimized for the UAV control scenario, the model performance on core tasks such as SDK type recognition and function call matching is enhanced. Experimental results indicate that the distilled lightweight model maintains high code generation accuracy while achieving significant improvements in deployment and inference efficiency, effectively demonstrating the feasibility and superiority of our approach in achieving precise and lightweight intelligent control for UAVs --- ### Edge-Optimized Multimodal Learning for UAV Video Understanding via BLIP-2 Authors: Yizhan Feng, Hichem Snoussi, Jing Teng, Jian Liu, Yuyang Wang, Abel Cherouat, Tian Wang Published: 2026-01-13 Categories: cs.CV, cs.RO arXiv: https://arxiv.org/abs/2601.08408v1 The demand for real-time visual understanding and interaction in complex scenarios is increasingly critical for unmanned aerial vehicles. However, a significant challenge arises from the contradiction between the high computational cost of large Vision language models and the limited computing resources available on UAV edge devices. To address this challenge, this paper proposes a lightweight multimodal task platform based on BLIP-2, integrated with YOLO-World and YOLOv8-Seg models. This integration extends the multi-task capabilities of BLIP-2 for UAV applications with minimal adaptation and without requiring task-specific fine-tuning on drone data. Firstly, the deep integration of BLIP-2 with YOLO models enables it to leverage the precise perceptual results of YOLO for fundamental tasks like object detection and instance segmentation, thereby facilitating deeper visual-attention understanding and reasoning. Secondly, a content-aware key frame sampling mechanism based on K-Means clustering is designed, which incorporates intelligent frame selection and temporal feature concatenation. This equips the lightweight BLIP-2 architecture with the capability to handle video-level interactive tasks effectively. Thirdly, a unified prompt optimization scheme for multi-task adaptation is implemented. This scheme strategically injects structured event logs from the YOLO models as contextual information into BLIP-2's input. Combined with output constraints designed to filter out technical details, this approach effectively guides the model to generate accurate and contextually relevant outputs for various tasks. --- ### WebTrap Park: An Automated Platform for Systematic Security Evaluation of Web Agents Authors: Xinyi Wu, Jiagui Chen, Geng Hong, Jiayi Dong, Xudong Pan, Jiarun Dai, Min Yang Published: 2026-01-13 Categories: cs.AI, cs.CR arXiv: https://arxiv.org/abs/2601.08406v1 Web Agents are increasingly deployed to perform complex tasks in real web environments, yet their security evaluation remains fragmented and difficult to standardize. We present WebTrap Park, an automated platform for systematic security evaluation of Web Agents through direct observation of their concrete interactions with live web pages. WebTrap Park instantiates three major sources of security risk into 1,226 executable evaluation tasks and enables action based assessment without requiring agent modification. Our results reveal clear security differences across agent frameworks, highlighting the importance of agent architecture beyond the underlying model. WebTrap Park is publicly accessible at https://security.fudan.edu.cn/webagent and provides a scalable foundation for reproducible Web Agent security evaluation. --- ### Out-of-distribution generalization of deep-learning surrogates for 2D PDE-generated dynamics in the small-data regime Authors: Binh Duong Nguyen, Stefan Sandfeld Published: 2026-01-13 Categories: cs.LG arXiv: https://arxiv.org/abs/2601.08404v1 Partial differential equations (PDEs) are a central tool for modeling the dynamics of physical, engineering, and materials systems, but high-fidelity simulations are often computationally expensive. At the same time, many scientific applications can be viewed as the evolution of spatially distributed fields, making data-driven forecasting of such fields a core task in scientific machine learning. In this work we study autoregressive deep-learning surrogates for two-dimensional PDE dynamics on periodic domains, focusing on generalization to out-of-distribution initial conditions within a fixed PDE and parameter regime and on strict small-data settings with at most $\mathcal{O}(10^2)$ simulated trajectories per system. We introduce a multi-channel U-Net (...), evaluate it on five qualitatively different PDE families and compare it to ViT, AFNO, PDE-Transformer, and KAN-UNet under a common training setup. Across all datasets, me-UNet matches or outperforms these more complex architectures in terms of field-space error, spectral similarity, and physics-based metrics for in-distribution rollouts, while requiring substantially less training time. It also generalizes qualitatively to unseen initial conditions with as few as $\approx 20$ training simulations. A data-efficiency study and Grad-CAM analysis further suggest that, in small-data periodic 2D PDE settings, convolutional architectures with inductive biases aligned to locality and periodic boundary conditions remain strong contenders for accurate and moderately out-of-distribution-robust surrogate modeling. --- ### Owen-Shapley Policy Optimization: A Principled RL Algorithm for Generative Search LLMs Authors: Abhijnan Nath, Alireza Bagheri Garakani, Tianchen Zhou, Fan Yang, Yan Gao, Nikhil Krishnaswamy Published: 2026-01-13 Categories: cs.AI arXiv: https://arxiv.org/abs/2601.08403v2 Large language models are increasingly trained via reinforcement learning for personalized recommendation tasks, but standard methods like GRPO rely on sparse, sequence-level rewards. These obscure which tokens actually contribute to high-quality outputs, creating a credit assignment gap. This gap is especially problematic when models must infer latent user intent from under-specified language without ground truth labels, which is a reasoning pattern rarely seen during pretraining but commonly required in deployment. We introduce Owen-Shapley Policy Optimization (OSPO), a framework that redistributes sequence-level advantages based on tokens' marginal contributions to outcomes. OSPO transforms task feedback into potential-based reward shaping via Shapley-Owen attributions to assign segment-level credit while preserving the optimal policy, all without parametric value models. By forming coalitions of semantically coherent units (e.g., phrases describing product attributes or sentences capturing preferences), OSPO identifies which response parts drive performance. Experiments on Amazon ESCI and H&M Fashion datasets including controlled generation tasks show consistent gains over baselines and notable test-time robustness to out-of-distribution retrievers unseen during training. --- ### PATS: Personality-Aware Teaching Strategies with Large Language Model Tutors Authors: Donya Rooein, Sankalan Pal Chowdhury, Mariia Eremeeva, Yuan Qin, Debora Nozza, Mrinmaya Sachan, Dirk Hovy Published: 2026-01-13 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2601.08402v1 Recent advances in large language models (LLMs) demonstrate their potential as educational tutors. However, different tutoring strategies benefit different student personalities, and mismatches can be counterproductive to student outcomes. Despite this, current LLM tutoring systems do not take into account student personality traits. To address this problem, we first construct a taxonomy that links pedagogical methods to personality profiles, based on pedagogical literature. We simulate student-teacher conversations and use our framework to let the LLM tutor adjust its strategy to the simulated student personality. We evaluate the scenario with human teachers and find that they consistently prefer our approach over two baselines. Our method also increases the use of less common, high-impact strategies such as role-playing, which human and LLM annotators prefer significantly. Our findings pave the way for developing more personalized and effective LLM use in educational applications. --- ### An Explainable Two Stage Deep Learning Framework for Pericoronitis Assessment in Panoramic Radiographs Using YOLOv8 and ResNet-50 Authors: Ajo Babu George, Pranav S, Kunal Agarwal Published: 2026-01-13 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2601.08401v1 Objectives: To overcome challenges in diagnosing pericoronitis on panoramic radiographs, an AI-assisted assessment system integrating anatomical localization, pathological classification, and interpretability. Methods: A two-stage deep learning pipeline was implemented. The first stage used YOLOv8 to detect third molars and classify their anatomical positions and angulations based on Winter's classification. Detected regions were then fed into a second-stage classifier, a modified ResNet-50 architecture, for detecting radiographic features suggestive of pericoronitis. To enhance clinical trust, Grad-CAM was used to highlight key diagnostic regions on the radiographs. Results: The YOLOv8 component achieved 92% precision and 92.5% mean average precision. The ResNet-50 classifier yielded F1-scores of 88% for normal cases and 86% for pericoronitis. Radiologists reported 84% alignment between Grad-CAM and their diagnostic impressions, supporting the radiographic relevance of the interpretability output. Conclusion: The system shows strong potential for AI-assisted panoramic assessment, with explainable AI features that support clinical confidence. --- ### Design and Development of a Low-Cost Scalable GSM-IoT Smart Pet Feeder with a Remote Mobile Application Authors: Md. Rakibul Hasan Nishat, S. M. Khalid Bin Zahid, Abdul Hasib, T. M. Mehrab Hasan, Mohammad Arman, A. S. M. Ahsanul Sarkar Akib Published: 2026-01-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.08394v1 Pet ownership is increasingly common in modern households, yet maintaining a consistent feeding schedule remains challenging for the owners particularly those who live in cities and have busy lifestyles. This paper presents the design, development, and validation of a low-cost, scalable GSM-IoT smart pet feeder that enables remote monitoring and control through cellular communication. The device combines with an Arduino microcontroller, a SIM800L GSM module for communication, an ultrasonic sensor for real-time food-level assessment, and a servo mechanism for accurate portion dispensing. A dedicated mobile application was developed using MIT App Inventor which allows owners to send feeding commands and receive real-time status updates. Experimental results demonstrate a 98\% SMS command success rate, consistent portion dispensing with $\pm 2.67$\% variance, and reliable autonomous operation. Its modular, energy-efficient design makes it easy to use in a wide range of households, including those with limited resources. This work pushes forward the field of accessible pet care technology by providing a practical, scalable, and completely internet-independent solution for personalized pet feeding. In doing so, it sets a new benchmark for low-cost, GSM-powered automation in smart pet products. --- ### Controlled LLM Training on Spectral Sphere Authors: Tian Xie, Haoming Luo, Haoyu Tang, Yiwen Hu, Jason Klein Liu, Qingnan Ren, Yang Wang, Wayne Xin Zhao, Rui Yan, Bing Su, Chong Luo, Baining Guo Published: 2026-01-13 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2601.08393v3 Scaling large models requires optimization strategies that ensure rapid convergence grounded in stability. Maximal Update Parametrization ($\boldsymbolμ$P) provides a theoretical safeguard for width-invariant $Θ(1)$ activation control, whereas emerging optimizers like Muon are only ``half-aligned'' with these constraints: they control updates but allow weights to drift. To address this limitation, we introduce the \textbf{Spectral Sphere Optimizer (SSO)}, which enforces strict module-wise spectral constraints on both weights and their updates. By deriving the steepest descent direction on the spectral sphere, SSO realizes a fully $\boldsymbolμ$P-aligned optimization process. To enable large-scale training, we implement SSO as an efficient parallel algorithm within Megatron. Through extensive pretraining on diverse architectures, including Dense 1.7B, MoE 8B-A1B, and 200-layer DeepNet models, SSO consistently outperforms AdamW and Muon. Furthermore, we observe significant practical stability benefits, including improved MoE router load balancing, suppressed outliers, and strictly bounded activations. --- ### Creativity in AI as Emergence from Domain-Limited Generative Models Authors: Corina Chutaux Published: 2026-01-13 Categories: cs.AI arXiv: https://arxiv.org/abs/2601.08388v1 Creativity in artificial intelligence is most often addressed through evaluative frameworks that aim to measure novelty, diversity, or usefulness in generated outputs. While such approaches have provided valuable insights into the behavior of modern generative models, they largely treat creativity as a property to be assessed rather than as a phenomenon to be explicitly modeled. In parallel, recent advances in large-scale generative systems, particularly multimodal architectures, have demonstrated increasingly sophisticated forms of pattern recombination, raising questions about the nature and limits of machine creativity. This paper proposes a generative perspective on creativity in AI, framing it as an emergent property of domain-limited generative models embedded within bounded informational environments. Rather than introducing new evaluative criteria, we focus on the structural and contextual conditions under which creative behaviors arise. We introduce a conceptual decomposition of creativity into four interacting components-pattern-based generation, induced world models, contextual grounding, and arbitrarity, and examine how these components manifest in multimodal generative systems. By grounding creativity in the interaction between generative dynamics and domain-specific representations, this work aims to provide a technical framework for studying creativity as an emergent phenomenon in AI systems, rather than as a post hoc evaluative label. --- ### Deconstructing Pre-training: Knowledge Attribution Analysis in MoE and Dense Models Authors: Bo Wang, Junzhuo Li, Hong Chen, Yuanlin Chu, Yuxuan Fan, Xuming Hu Published: 2026-01-13 Categories: cs.AI, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2601.08383v1 Mixture-of-Experts (MoE) architectures decouple model capacity from per-token computation, enabling scaling beyond the computational limits imposed by dense scaling laws. Yet how MoE architectures shape knowledge acquisition during pre-training, and how this process differs from dense architectures, remains unknown. To address this issue, we introduce Gated-LPI (Log-Probability Increase), a neuron-level attribution metric that decomposes log-probability increase across neurons. We present a time-resolved comparison of knowledge acquisition dynamics in MoE and dense architectures, tracking checkpoints over 1.2M training steps (~ 5.0T tokens) and 600K training steps (~ 2.5T tokens), respectively. Our experiments uncover three patterns: (1) Low-entropy backbone. The top approximately 1% of MoE neurons capture over 45% of positive updates, forming a high-utility core, which is absent in the dense baseline. (2) Early consolidation. The MoE model locks into a stable importance profile within < 100K steps, whereas the dense model remains volatile throughout training. (3) Functional robustness. Masking the ten most important MoE attention heads reduces relational HIT@10 by < 10%, compared with > 50% for the dense model, showing that sparsity fosters distributed -- rather than brittle -- knowledge storage. These patterns collectively demonstrate that sparsity fosters an intrinsically stable and distributed computational backbone from early in training, helping bridge the gap between sparse architectures and training-time interpretability. --- ### A Qualitative Model to Reason about Object Rotations (QOR) applied to solve the Cube Comparison Test (CCT) Authors: Zoe Falomir Published: 2026-01-13 Categories: cs.AI, cs.SC arXiv: https://arxiv.org/abs/2601.08382v2 This paper presents a Qualitative model for Reasoning about Object Rotations (QOR) which is applied to solve the Cube Comparison Test (CCT) by Ekstrom et al. (1976). A conceptual neighborhood graph relating the Rotation movement to the Location change and the Orientation change (CNGRLO) of the features on the cube sides has been built and it produces composition tables to calculate inferences for reasoning about rotations. --- ### Thematic Working Group 5 -- Artificial Intelligence (AI) literacy for teaching and learning: design and implementation Authors: Mary Webb, Matt Bower, Ana Amélia Carvalho, Fredrik Mørk Røkenes, Jodie Torrington, Jonathan D. Cohen, Yousra Chtouki, Kathryn Maccallum, Tanya Linden, Deirdre Butler, Juliana Elisa Raffaghelli, Henriikka Vartiainen et al. Published: 2026-01-13 Categories: cs.AI arXiv: https://arxiv.org/abs/2601.08380v1 TWG 5 focused on developing and implementing effective strategies for enhancing AI literacy and agency of teachers, equipping them with the knowledge and skills necessary to integrate AI into their teaching practices. Explorations covered curriculum design, professional development programs, practical classroom applications, and policy guidelines aiming to empower educators to confidently utilize AI tools and foster a deeper understanding of AI concepts among students. --- ### MMD Guidance: Training-Free Distribution Adaptation for Diffusion Models via Maximum Mean Discrepancy Guidance Authors: Matina Mahdizadeh Sani, Nima Jamali, Mohammad Jalali, Farzan Farnia Published: 2026-01-13 Categories: cs.LG, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2601.08379v2 Pre-trained diffusion models have emerged as powerful generative priors for both unconditional and conditional sample generation, yet their outputs often deviate from the characteristics of user-specific target data. Such mismatches are especially problematic in domain adaptation tasks, where only a few reference examples are available and retraining the diffusion model is infeasible. Existing inference-time guidance methods can adjust sampling trajectories, but they typically optimize surrogate objectives such as classifier likelihoods rather than directly aligning with the target distribution. We propose \emph{MMD Guidance}, a training-free mechanism that augments the reverse diffusion process with gradients of the \textit{Maximum Mean Discrepancy (MMD)} between generated samples and a reference dataset. MMD provides reliable distributional estimates from limited data, exhibits low variance in practice, and is efficiently differentiable, which makes it particularly well-suited for the guidance task. Our framework naturally extends to prompt-aware adaptation in conditional generation models via product kernels. Also, it can be applied with computational efficiency in latent diffusion models (LDMs), since guidance is applied in the latent space of the LDM. Experiments on synthetic and real-world benchmarks demonstrate that MMD Guidance can achieve distributional alignment while preserving sample fidelity. The project code is available at github.com/matinamehdizadeh/MMD-Guidance. --- ### Source-Free Domain Adaptation for Geospatial Point Cloud Semantic Segmentation Authors: Yuan Gao, Di Cao, Xiaohuan Xi, Sheng Nie, Shaobo Xia, Cheng Wang Published: 2026-01-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.08375v2 Semantic segmentation of 3D geospatial point clouds is fundamental to remote sensing applications, yet domain shifts caused by regional and acquisition-related variations often degrade model performance. Although domain adaptation can mitigate such shifts, existing methods typically require access to source-domain data, which is often infeasible due to privacy concerns and regulatory policies. To address this, we propose LoGo (Local-Global Dual-Consensus), a novel source-free unsupervised domain adaptation (SFUDA) framework requiring only a pretrained model and unlabeled target data. At the local level, we introduce a class-balanced prototype estimation module that ensures that robust feature prototypes can be generated even for sample-scarce tail classes, effectively mitigating the feature collapse caused by long-tailed distributions. At the global level, we introduce an optimal transport-based global distribution alignment module that formulates pseudo-label assignment as a global optimization problem, effectively correcting the over-dominance of head classes inherent in local greedy assignments, and thereby preventing model predictions from being severely biased towards majority classes. Finally, we propose a dual-consistency pseudo-label filtering mechanism that retains only high-confidence pseudo-labels where local multi-augmented ensemble predictions align with global optimal transport assignments for self-training. Extensive experiments on two challenging benchmarks, encompassing cross-scene and cross-sensor settings, demonstrate that LoGo consistently outperforms existing state-of-the-art methods. The source code is available at https://github.com/GYproject/LoGo-SFUDA. --- ### Geo-NVS-w: Geometry-Aware Novel View Synthesis In-the-Wild with an SDF Renderer Authors: Anastasios Tsalakopoulos, Angelos Kanlis, Evangelos Chatzis, Antonis Karakottas, Dimitrios Zarpalas Published: 2026-01-13 Categories: cs.CV, cs.AI, cs.GR, cs.LG arXiv: https://arxiv.org/abs/2601.08371v1 We introduce Geo-NVS-w, a geometry-aware framework for high-fidelity novel view synthesis from unstructured, in-the-wild image collections. While existing in-the-wild methods already excel at novel view synthesis, they often lack geometric grounding on complex surfaces, sometimes producing results that contain inconsistencies. Geo-NVS-w addresses this limitation by leveraging an underlying geometric representation based on a Signed Distance Function (SDF) to guide the rendering process. This is complemented by a novel Geometry-Preservation Loss which ensures that fine structural details are preserved. Our framework achieves competitive rendering performance, while demonstrating a 4-5x reduction reduction in energy consumption compared to similar methods. We demonstrate that Geo-NVS-w is a robust method for in-the-wild NVS, yielding photorealistic results with sharp, geometrically coherent details. --- ### PosIR: Position-Aware Heterogeneous Information Retrieval Benchmark Authors: Ziyang Zeng, Dun Zhang, Yu Yan, Xu Sun, Cuiqiaoshu Pan, Yudong Zhou, Yuqing Yang Published: 2026-01-13 Categories: cs.IR, cs.CL arXiv: https://arxiv.org/abs/2601.08363v2 In real-world documents, the information relevant to a user query may reside anywhere from the beginning to the end. This makes position bias -- a systematic tendency of retrieval models to favor or neglect content based on its location -- a critical concern. Although recent studies have identified such bias, existing analyses focus predominantly on English, fail to disentangle document length from information position, and lack a standardized framework for systematic diagnosis. To address these limitations, we introduce PosIR (Position-Aware Information Retrieval), the first standardized benchmark designed to systematically diagnose position bias in diverse retrieval scenarios. PosIR comprises 310 datasets spanning 10 languages and 31 domains, with relevance tied to precise reference spans. At its methodological core, PosIR employs a length-controlled bucketing strategy that groups queries by positive document length and analyzes positional effects within each bucket. This design strictly isolates position bias from length-induced performance degradation. Extensive experiments on 10 state-of-the-art embedding-based retrieval models reveal that: (1) retrieval performance on PosIR with documents exceeding 1536 tokens correlates poorly with the MMTEB benchmark, exposing limitations of current short-text evaluations; (2) position bias is pervasive in embedding models and even increases with document length, with most models exhibiting primacy bias while certain models show unexpected recency bias; (3) as an exploratory investigation, gradient-based saliency analysis further uncovers two distinct internal mechanisms that correlate with these positional preferences. We hope that PosIR can serve as a valuable diagnostic framework to advance the development of position-robust retrieval systems. --- ### Scalable Sequential Recommendation under Latency and Memory Constraints Authors: Adithya Parthasarathy, Aswathnarayan Muthukrishnan Kirubakaran, Vinoth Punniyamoorthy, Nachiappan Chockalingam, Lokesh Butra, Kabilan Kannan, Abhirup Mazumder, Sumit Saha Published: 2026-01-13 Categories: cs.IR, cs.AI arXiv: https://arxiv.org/abs/2601.08360v2 Sequential recommender systems must model long-range user behavior while operating under strict memory and latency constraints. Transformer-based approaches achieve strong accuracy but suffer from quadratic attention complexity, forcing aggressive truncation of user histories and limiting their practicality for long-horizon modeling. This paper presents HoloMambaRec, a lightweight sequential recommendation architecture that combines holographic reduced representations for attribute-aware embedding with a selective state space encoder for linear-time sequence processing. Item and attribute information are bound using circular convolution, preserving embedding dimensionality while encoding structured metadata. A shallow selective state space backbone, inspired by recent Mamba-style models, enables efficient training and constant-time recurrent inference. Experiments on Amazon Beauty and MovieLens-1M under a 10-epoch budget show that HoloMambaRec surpasses SASRec on both datasets, attains state-of-the-art ranking on MovieLens-1M, and trails only GRU4Rec on Amazon Beauty, all while maintaining substantially lower memory complexity. The design further incorporates forward-compatible mechanisms for temporal bundling and inference-time compression, positioning HoloMambaRec as a practical and extensible alternative for scalable, metadata-aware sequential recommendation. --- ### Linear probing enables Ship-Radiated Noise recognition with pretrained audio embeddings Authors: Hilde I. Hummel, Sandjai Bhulai, Rob D. van der Mei, Burooj Ghani Published: 2026-01-13 Categories: cs.LG, cs.SD, eess.AS arXiv: https://arxiv.org/abs/2601.08358v2 Even though the ocean covers the majority of the planet's surface, it remains the least explored ecosystem. As light and radio waves do not propagate through water, underwater acoustics is the main choice for various ocean applications ranging from marine biology to pollution monitoring. Increasing levels of anthropogenic noise from ships contribute significantly to underwater sound pollution, posing risks to marine ecosystems. This makes monitoring crucial to understand and quantify the impact of the ship radiated noise. Passive Acoustic Monitoring (PAM) systems are widely deployed for this purpose, generating years of underwater recordings across diverse soundscapes. Manual analysis of such large-scale data is impractical, motivating the need for automated approaches based on machine learning. Recent advances in automatic Underwater Acoustic Target Recognition (UATR) have largely relied on supervised learning, which is constrained by the scarcity of labeled data. Transfer Learning (TL) offers a promising alternative to mitigate this limitation. In this work, we conduct the first empirical comparative study of transfer learning for UATR, evaluating multiple pretrained audio models originating from diverse audio domains. The pretrained model weights are frozen, and the resulting embeddings are analyzed through classification, clustering, and similarity-based evaluations. The analysis shows that the geometrical structure of the embedding space is largely dominated by recording-specific characteristics. However, a simple linear probe can effectively suppress this recording-specific information and isolate ship-type features from these embeddings. As a result, linear probing enables effective automatic UATR using pretrained audio models at low computational cost, significantly reducing the need for a large amounts of high-quality labeled ship recordings. --- ### Semantic Misalignment in Vision-Language Models under Perceptual Degradation Authors: Guo Cheng Published: 2026-01-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.08355v2 Vision-Language Models (VLMs) are increasingly deployed in autonomous driving and embodied AI systems, where reliable perception is critical for safe semantic reasoning and decision-making. While recent VLMs demonstrate strong performance on multimodal benchmarks, their robustness to realistic perception degradation remains poorly understood. In this work, we systematically study semantic misalignment in VLMs under controlled degradation of upstream visual perception, using semantic segmentation on the Cityscapes dataset as a representative perception module. We introduce perception-realistic corruptions that induce only moderate drops in conventional segmentation metrics, yet observe severe failures in downstream VLM behavior, including hallucinated object mentions, omission of safety-critical entities, and inconsistent safety judgments. To quantify these effects, we propose a set of language-level misalignment metrics that capture hallucination, critical omission, and safety misinterpretation, and analyze their relationship with segmentation quality across multiple contrastive and generative VLMs. Our results reveal a clear disconnect between pixel-level robustness and multimodal semantic reliability, highlighting a critical limitation of current VLM-based systems and motivating the need for evaluation frameworks that explicitly account for perception uncertainty in safety-critical applications. ---