# Research Papers — 2026-01 · bundle page 95 of 189 > Full-text markdown of papers #4701–4750 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/95 [← Previous bundle](https://aipod.dev/papers/archive/2026-01/page/94.md) [Next bundle →](https://aipod.dev/papers/archive/2026-01/page/96.md) ### EmoKGEdit: Training-free Affective Injection via Visual Cue Transformation Authors: Jing Zhang, Bingjie Fan Published: 2026-01-18 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.12326v1 Existing image emotion editing methods struggle to disentangle emotional cues from latent content representations, often yielding weak emotional expression and distorted visual structures. To bridge this gap, we propose EmoKGEdit, a novel training-free framework for precise and structure-preserving image emotion editing. Specifically, we construct a Multimodal Sentiment Association Knowledge Graph (MSA-KG) to disentangle the intricate relationships among objects, scenes, attributes, visual clues and emotion. MSA-KG explicitly encode the causal chain among object-attribute-emotion, and as external knowledge to support chain of thought reasoning, guiding the multimodal large model to infer plausible emotion-related visual cues and generate coherent instructions. In addition, based on MSA-KG, we design a disentangled structure-emotion editing module that explicitly separates emotional attributes from layout features within the latent space, which ensures that the target emotion is effectively injected while strictly maintaining visual spatial coherence. Extensive experiments demonstrate that EmoKGEdit achieves excellent performance in both emotion fidelity and content preservation, and outperforms the state-of-the-art methods. --- ### Multi-Sensor Matching with HyperNetworks Authors: Eli Passov, Nathan S. Netanyahu, Yosi Keller Published: 2026-01-18 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.12325v1 Hypernetworks are models that generate or modulate the weights of another network. They provide a flexible mechanism for injecting context and task conditioning and have proven broadly useful across diverse applications without significant increases in model size. We leverage hypernetworks to improve multimodal patch matching by introducing a lightweight descriptor-learning architecture that augments a Siamese CNN with (i) hypernetwork modules that compute adaptive, per-channel scaling and shifting and (ii) conditional instance normalization that provides modality-specific adaptation (e.g., visible vs. infrared, VIS-IR) in shallow layers. This combination preserves the efficiency of descriptor-based methods during inference while increasing robustness to appearance shifts. Trained with a triplet loss and hard-negative mining, our approach achieves state-of-the-art results on VIS-NIR and other VIS-IR benchmarks and matches or surpasses prior methods on additional datasets, despite their higher inference cost. To spur progress on domain shift, we also release GAP-VIR, a cross-platform (ground/aerial) VIS-IR patch dataset with 500K pairs, enabling rigorous evaluation of cross-domain generalization and adaptation. --- ### MARO: Learning Stronger Reasoning from Social Interaction Authors: Yin Cai, Zhouhong Gu, Juntao Zhang, Ping Chen Published: 2026-01-18 Categories: cs.AI arXiv: https://arxiv.org/abs/2601.12323v2 Humans face countless scenarios that require reasoning and judgment in daily life. However, existing large language model training methods primarily allow models to learn from existing textual content or solve predetermined problems, lacking experience in real scenarios involving interaction, negotiation, and competition with others. To address this, this paper proposes Multi-Agent Reward Optimization (MARO), a method that enables large language models (LLMs) to acquire stronger reasoning abilities by learning and practicing in multi-agent social environments. Specifically, MARO first addresses the sparse learning signal problem by decomposing final success or failure outcomes into each specific behavior during the interaction process; second, it handles the uneven role distribution problem by balancing the training sample weights of different roles; finally, it addresses environmental instability issues by directly evaluating the utility of each behavior. Experimental results demonstrate that MARO not only achieves significant improvements in social reasoning capabilities, but also that the abilities acquired through social simulation learning can effectively transfer to other tasks such as mathematical reasoning and instruction following. This reveals the tremendous potential of multi-agent social learning in enhancing the general reasoning capabilities of LLMs. --- ### Ordered Local Momentum for Asynchronous Distributed Learning under Arbitrary Delays Authors: Chang-Wei Shi, Shi-Shang Wang, Wu-Jun Li Published: 2026-01-18 Categories: cs.LG arXiv: https://arxiv.org/abs/2601.12322v1 Momentum SGD (MSGD) serves as a foundational optimizer in training deep models due to momentum's key role in accelerating convergence and enhancing generalization. Meanwhile, asynchronous distributed learning is crucial for training large-scale deep models, especially when the computing capabilities of the workers in the cluster are heterogeneous. To reduce communication frequency, local updates are widely adopted in distributed learning. However, how to implement asynchronous distributed MSGD with local updates remains unexplored. To solve this problem, we propose a novel method, called \underline{or}dered \underline{lo}cal \underline{mo}mentum (OrLoMo), for asynchronous distributed learning. In OrLoMo, each worker runs MSGD locally. Then the local momentum from each worker will be aggregated by the server in order based on its global iteration index. To the best of our knowledge, OrLoMo is the first method to implement asynchronous distributed MSGD with local updates. We prove the convergence of OrLoMo for non-convex problems under arbitrary delays. Experiments validate that OrLoMo can outperform its synchronous counterpart and other asynchronous methods. --- ### Beyond Human Annotation: Recent Advances in Data Generation Methods for Document Intelligence Authors: Dehao Ying, Fengchang Yu, Haihua Chen, Changjiang Jiang, Yurong Li, Wei Lu Published: 2026-01-18 Categories: cs.AI arXiv: https://arxiv.org/abs/2601.12318v1 The advancement of Document Intelligence (DI) demands large-scale, high-quality training data, yet manual annotation remains a critical bottleneck. While data generation methods are evolving rapidly, existing surveys are constrained by fragmented focuses on single modalities or specific tasks, lacking a unified perspective aligned with real-world workflows. To fill this gap, this survey establishes the first comprehensive technical map for data generation in DI. Data generation is redefined as supervisory signal production, and a novel taxonomy is introduced based on the "availability of data and labels." This framework organizes methodologies into four resource-centric paradigms: Data Augmentation, Data Generation from Scratch, Automated Data Annotation, and Self-Supervised Signal Construction. Furthermore, a multi-level evaluation framework is established to integrate intrinsic quality and extrinsic utility, compiling performance gains across diverse DI benchmarks. Guided by this unified structure, the methodological landscape is dissected to reveal critical challenges such as fidelity gaps and frontiers including co-evolutionary ecosystems. Ultimately, by systematizing this fragmented field, data generation is positioned as the central engine for next-generation DI. --- ### Explanova: Automatically Discover Data Insights in N \times M Table via XAI Combined LLM Workflow Authors: Yiming Huang Published: 2026-01-18 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2601.12317v1 Automation in data analysis has been a long-time pursuit. Current agentic LLM shows a promising solution towards it. Like DeepAnalyze, DataSage, and Datawise. They are all powerful agentic frameworks for automatic fine-grained analysis and are powered by LLM-based agentic tool calling ability. However, what about powered by a preset AutoML-like workflow? If we traverse all possible exploration, like Xn itself`s statistics, Xn1-Xn2 relationships, Xn to all other, and finally explain? Our Explanova is such an attempt: Cheaper due to a Local Small LLM. --- ### GazeFormer-MoE: Context-Aware Gaze Estimation via CLIP and MoE Transformer Authors: Xinyuan Zhao, Xianrui Chen, Ahmad Chaddad Published: 2026-01-18 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2601.12316v1 We present a semantics modulated, multi scale Transformer for 3D gaze estimation. Our model conditions CLIP global features with learnable prototype banks (illumination, head pose, background, direction), fuses these prototype-enriched global vectors with CLIP patch tokens and high-resolution CNN tokens in a unified attention space, and replaces several FFN blocks with routed/shared Mixture of Experts to increase conditional capacity. Evaluated on MPIIFaceGaze, EYEDIAP, Gaze360 and ETH-XGaze, our model achieves new state of the art angular errors of 2.49°, 3.22°, 10.16°, and 1.44°, demonstrating up to a 64% relative improvement over previously reported results. ablations attribute gains to prototype conditioning, cross scale fusion, MoE and hyperparameter. Our code is publicly available at https://github. com/AIPMLab/Gazeformer. --- ### S^2F-Net:A Robust Spatial-Spectral Fusion Framework for Cross-Model AIGC Detection Authors: Xiangyu Hu, Yicheng Hong, Hongchuang Zheng, Wenjun Zeng, Bingyao Liu Published: 2026-01-18 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.12313v1 The rapid development of generative models has imposed an urgent demand for detection schemes with strong generalization capabilities. However, existing detection methods generally suffer from overfitting to specific source models, leading to significant performance degradation when confronted with unseen generative architectures. To address these challenges, this paper proposes a cross-model detection framework called S 2 F-Net, whose core lies in exploring and leveraging the inherent spectral discrepancies between real and synthetic textures. Considering that upsampling operations leave unique and distinguishable frequency fingerprints in both texture-poor and texture-rich regions, we focus our research on the detection of frequency-domain artifacts, aiming to fundamentally improve the generalization performance of the model. Specifically, we introduce a learnable frequency attention module that adaptively weights and enhances discriminative frequency bands by synergizing spatial texture analysis and spectral dependencies.On the AIGCDetectBenchmark, which includes 17 categories of generative models, S 2 F-Net achieves a detection accuracy of 90.49%, significantly outperforming various existing baseline methods in cross-domain detection scenarios. --- ### CurConMix+: A Unified Spatio-Temporal Framework for Hierarchical Surgical Workflow Understanding Authors: Yongjun Jeon, Jongmin Shin, Kanggil Park, Seonmin Park, Soyoung Lim, Jung Yong Kim, Jinsoo Rhu, Jongman Kim, Gyu-Seong Choi, Namkee Oh, Kyu-Hwan Jung Published: 2026-01-18 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.12312v1 Surgical action triplet recognition aims to understand fine-grained surgical behaviors by modeling the interactions among instruments, actions, and anatomical targets. Despite its clinical importance for workflow analysis and skill assessment, progress has been hindered by severe class imbalance, subtle visual variations, and the semantic interdependence among triplet components. Existing approaches often address only a subset of these challenges rather than tackling them jointly, which limits their ability to form a holistic understanding. This study builds upon CurConMix, a spatial representation framework. At its core, a curriculum-guided contrastive learning strategy learns discriminative and progressively correlated features, further enhanced by structured hard-pair sampling and feature-level mixup. Its temporal extension, CurConMix+, integrates a Multi-Resolution Temporal Transformer (MRTT) that achieves robust, context-aware understanding by adaptively fusing multi-scale temporal features and dynamically balancing spatio-temporal cues. Furthermore, we introduce LLS48, a new, hierarchically annotated benchmark for complex laparoscopic left lateral sectionectomy, providing step-, task-, and action-level annotations. Extensive experiments on CholecT45 and LLS48 demonstrate that CurConMix+ not only outperforms state-of-the-art approaches in triplet recognition, but also exhibits strong cross-level generalization, as its fine-grained features effectively transfer to higher-level phase and step recognition tasks. Together, the framework and dataset provide a unified foundation for hierarchy-aware, reproducible, and interpretable surgical workflow understanding. The code and dataset will be publicly released on GitHub to facilitate reproducibility and further research. --- ### Cross-reality location privacy protection in 6G-enabled vehicular metaverses: an LLM-enhanced hybrid generative diffusion model-based approach Authors: Xiaofeng Luo, Jiayi He, Jiawen Kang, Ruichen Zhang, Zhaoshui He, Ekram Hossain, Dong In Kim Published: 2026-01-18 Categories: cs.NI, cs.CR, cs.HC, cs.LG arXiv: https://arxiv.org/abs/2601.12311v2 The emergence of 6G-enabled vehicular metaverses enables Autonomous Vehicles (AVs) to operate across physical and virtual spaces through space-air-ground-sea integrated networks. The AVs can deploy AI agents powered by large AI models as personalized assistants, on edge servers to support intelligent driving decision making and enhanced on-board experiences. However, such cross-reality interactions may cause serious location privacy risks, as adversaries can infer AV trajectories by correlating the location reported when AVs request LBS in reality with the location of the edge servers on which their corresponding AI agents are deployed in virtuality. To address this challenge, we design a cross-reality location privacy protection framework based on hybrid actions, including continuous location perturbation in reality and discrete privacy-aware AI agent migration in virtuality. In this framework, a new privacy metric, termed cross-reality location entropy, is proposed to effectively quantify the privacy levels of AVs. Based on this metric, we formulate an optimization problem to optimize the hybrid action, focusing on achieving a balance between location protection, service latency reduction, and quality of service maintenance. To solve the complex mixed-integer problem, we develop a novel LLM-enhanced Hybrid Diffusion Proximal Policy Optimization (LHDPPO) algorithm, which integrates LLM-driven informative reward design to enhance environment understanding with double Generative Diffusion Models-based policy exploration to handle high-dimensional action spaces, thereby enabling reliable determination of optimal hybrid actions. Extensive experiments on real-world datasets demonstrate that the proposed framework effectively mitigates cross-reality location privacy leakage for AVs while maintaining strong user immersion within 6G-enabled vehicular metaverse scenarios. --- ### Survival is the Only Reward: Sustainable Self-Training Through Environment-Mediated Selection Authors: Jennifer Dodgson, Alfath Daryl Alhajir, Michael Joedhitya, Akira Rafhael Janson Pattirane, Surender Suresh Kumar, Joseph Lim, C. H. Peh, Adith Ramdas, Steven Zhang Zhexu Published: 2026-01-18 Categories: cs.AI arXiv: https://arxiv.org/abs/2601.12310v1 Self-training systems often degenerate due to the lack of an external criterion for judging data quality, leading to reward hacking and semantic drift. This paper provides a proof-of-concept system architecture for stable self-training under sparse external feedback and bounded memory, and empirically characterises its learning dynamics and failure modes. We introduce a self-training architecture in which learning is mediated exclusively by environmental viability, rather than by reward, objective functions, or externally defined fitness criteria. Candidate behaviours are executed under real resource constraints, and only those whose environmental effects both persist and preserve the possibility of future interaction are propagated. The environment does not provide semantic feedback, dense rewards, or task-specific supervision; selection operates solely through differential survival of behaviours as world-altering events, making proxy optimisation impossible and rendering reward-hacking evolutionarily unstable. Analysis of semantic dynamics shows that improvement arises primarily through the persistence of effective and repeatable strategies under a regime of consolidation and pruning, a paradigm we refer to as negative-space learning (NSL), and that models develop meta-learning strategies (such as deliberate experimental failure in order to elicit informative error messages) without explicit instruction. This work establishes that environment-grounded selection enables sustainable open-ended self-improvement, offering a viable path toward more robust and generalisable autonomous systems without reliance on human-curated data or complex reward shaping. --- ### Adaptive Multi-Scale Correlation Meta-Network for Few-Shot Remote Sensing Image Classification Authors: Anurag Kaushish, Ayan Sar, Sampurna Roy, Sudeshna Chakraborty, Prashant Trivedi, Tanupriya Choudhury, Kanav Gupta Published: 2026-01-18 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2601.12308v1 Few-shot learning in remote sensing remains challenging due to three factors: the scarcity of labeled data, substantial domain shifts, and the multi-scale nature of geospatial objects. To address these issues, we introduce Adaptive Multi-Scale Correlation Meta-Network (AMC-MetaNet), a lightweight yet powerful framework with three key innovations: (i) correlation-guided feature pyramids for capturing scale-invariant patterns, (ii) an adaptive channel correlation module (ACCM) for learning dynamic cross-scale relationships, and (iii) correlation-guided meta-learning that leverages correlation patterns instead of conventional prototype averaging. Unlike prior approaches that rely on heavy pre-trained models or transformers, AMC-MetaNet is trained from scratch with only $\sim600K$ parameters, offering $20\times$ fewer parameters than ResNet-18 while maintaining high efficiency ($<50$ms per image inference). AMC-MetaNet achieves up to 86.65\% accuracy in 5-way 5-shot classification on various remote sensing datasets, including EuroSAT, NWPU-RESISC45, UC Merced Land Use, and AID. Our results establish AMC-MetaNet as a computationally efficient, scale-aware framework for real-world few-shot remote sensing. --- ### Rethinking the Value of Multi-Agent Workflow: A Strong Single Agent Baseline Authors: Jiawei Xu, Arief Koesdwiady, Sisong Bei, Yan Han, Baixiang Huang, Dakuo Wang, Yutong Chen, Zheshen Wang, Peihao Wang, Pan Li, Ying Ding Published: 2026-01-18 Categories: cs.MA, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2601.12307v1 Recent advances in LLM-based multi-agent systems (MAS) show that workflows composed of multiple LLM agents with distinct roles, tools, and communication patterns can outperform single-LLM baselines on complex tasks. However, most frameworks are homogeneous, where all agents share the same base LLM and differ only in prompts, tools, and positions in the workflow. This raises the question of whether such workflows can be simulated by a single agent through multi-turn conversations. We investigate this across seven benchmarks spanning coding, mathematics, general question answering, domain-specific reasoning, and real-world planning and tool use. Our results show that a single agent can reach the performance of homogeneous workflows with an efficiency advantage from KV cache reuse, and can even match the performance of an automatically optimized heterogeneous workflow. Building on this finding, we propose \textbf{OneFlow}, an algorithm that automatically tailors workflows for single-agent execution, reducing inference costs compared to existing automatic multi-agent design frameworks without trading off accuracy. These results position the single-LLM implementation of multi-agent workflows as a strong baseline for MAS research. We also note that single-LLM methods cannot capture heterogeneous workflows due to the lack of KV cache sharing across different LLMs, highlighting future opportunities in developing \textit{truly} heterogeneous multi-agent systems. --- ### Machine Learning as a Service (MLaaS) Dataset Generator Framework for IoT Environments Authors: Deepak Kanneganti, Sajib Mistry, Sheik Fattah, Joshua Boland, Aneesh Krishna Published: 2026-01-18 Categories: cs.LG arXiv: https://arxiv.org/abs/2601.12305v1 We propose a novel MLaaS Dataset Generator (MDG) framework that creates configurable and reproducible datasets for evaluating Machine Learning as a Service (MLaaS) selection and composition. MDG simulates realistic MLaaS behaviour by training and evaluating diverse model families across multiple real-world datasets and data distribution settings. It records detailed functional attributes, quality of service metrics, and composition-specific indicators, enabling systematic analysis of service performance and cross-service behaviour. Using MDG, we generate more than ten thousand MLaaS service instances and construct a large-scale benchmark dataset suitable for downstream evaluation. We also implement a built-in composition mechanism that models how services interact under varied Internet of Things conditions. Experiments demonstrate that datasets generated by MDG enhance selection accuracy and composition quality compared to existing baselines. MDG provides a practical and extensible foundation for advancing data-driven research on MLaaS selection and composition --- ### A Two-Stage Globally-Diverse Adversarial Attack for Vision-Language Pre-training Models Authors: Wutao Chen, Huaqin Zou, Chen Wan, Lifeng Huang Published: 2026-01-18 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2601.12304v1 Vision-language pre-training (VLP) models are vulnerable to adversarial examples, particularly in black-box scenarios. Existing multimodal attacks often suffer from limited perturbation diversity and unstable multi-stage pipelines. To address these challenges, we propose 2S-GDA, a two-stage globally-diverse attack framework. The proposed method first introduces textual perturbations through a globally-diverse strategy by combining candidate text expansion with globally-aware replacement. To enhance visual diversity, image-level perturbations are generated using multi-scale resizing and block-shuffle rotation. Extensive experiments on VLP models demonstrate that 2S-GDA consistently improves attack success rates over state-of-the-art methods, with gains of up to 11.17\% in black-box settings. Our framework is modular and can be easily combined with existing methods to further enhance adversarial transferability. --- ### Concepts from Representations: Post-hoc Concept Bottleneck Models via Sparse Decomposition of Visual Representations Authors: Shizhan Gong, Xiaofan Zhang, Qi Dou Published: 2026-01-18 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.12303v1 Deep learning has achieved remarkable success in image recognition, yet their inherent opacity poses challenges for deployment in critical domains. Concept-based interpretations aim to address this by explaining model reasoning through human-understandable concepts. However, existing post-hoc methods and ante-hoc concept bottleneck models (CBMs), suffer from limitations such as unreliable concept relevance, non-visual or labor-intensive concept definitions, and model or data-agnostic assumptions. This paper introduces Post-hoc Concept Bottleneck Model via Representation Decomposition (PCBM-ReD), a novel pipeline that retrofits interpretability onto pretrained opaque models. PCBM-ReD automatically extracts visual concepts from a pre-trained encoder, employs multimodal large language models (MLLMs) to label and filter concepts based on visual identifiability and task relevance, and selects an independent subset via reconstruction-guided optimization. Leveraging CLIP's visual-text alignment, it decomposes image representations into linear combination of concept embeddings to fit into the CBMs abstraction. Extensive experiments across 11 image classification tasks show PCBM-ReD achieves state-of-the-art accuracy, narrows the performance gap with end-to-end models, and exhibits better interpretability. --- ### Distribution Shift Is Key to Learning Invariant Prediction Authors: Hong Zheng, Fei Teng Published: 2026-01-18 Categories: cs.LG arXiv: https://arxiv.org/abs/2601.12296v1 An interesting phenomenon arises: Empirical Risk Minimization (ERM) sometimes outperforms methods specifically designed for out-of-distribution tasks. This motivates an investigation into the reasons behind such behavior beyond algorithmic design. In this study, we find that one such reason lies in the distribution shift across training domains. A large degree of distribution shift can lead to better performance even under ERM. Specifically, we derive several theoretical and empirical findings demonstrating that distribution shift plays a crucial role in model learning and benefits learning invariant prediction. Firstly, the proposed upper bounds indicate that the degree of distribution shift directly affects the prediction ability of the learned models. If it is large, the models' ability can increase, approximating invariant prediction models that make stable predictions under arbitrary known or unseen domains; and vice versa. We also prove that, under certain data conditions, ERM solutions can achieve performance comparable to that of invariant prediction models. Secondly, the empirical validation results demonstrated that the predictions of learned models approximate those of Oracle or Optimal models, provided that the degree of distribution shift in the training data increases. --- ### ToolPRMBench: Evaluating and Advancing Process Reward Models for Tool-using Agents Authors: Dawei Li, Yuguang Yao, Zhen Tan, Huan Liu, Ruocheng Guo Published: 2026-01-18 Categories: cs.AI, cs.SE arXiv: https://arxiv.org/abs/2601.12294v1 Reward-guided search methods have demonstrated strong potential in enhancing tool-using agents by effectively guiding sampling and exploration over complex action spaces. As a core design, those search methods utilize process reward models (PRMs) to provide step-level rewards, enabling more fine-grained monitoring. However, there is a lack of systematic and reliable evaluation benchmarks for PRMs in tool-using settings. In this paper, we introduce ToolPRMBench, a large-scale benchmark specifically designed to evaluate PRMs for tool-using agents. ToolPRMBench is built on top of several representative tool-using benchmarks and converts agent trajectories into step-level test cases. Each case contains the interaction history, a correct action, a plausible but incorrect alternative, and relevant tool metadata. We respectively utilize offline sampling to isolate local single-step errors and online sampling to capture realistic multi-step failures from full agent rollouts. A multi-LLM verification pipeline is proposed to reduce label noise and ensure data quality. We conduct extensive experiments across large language models, general PRMs, and tool-specialized PRMs on ToolPRMBench. The results reveal clear differences in PRM effectiveness and highlight the potential of specialized PRMs for tool-using. Code and data will be released at https://github.com/David-Li0406/ToolPRMBench. --- ### OpenNavMap: Multi-Session Appearance-Based Topometric Mapping for Scalable Visual Navigation Authors: Jianhao Jiao, Changkun Liu, Jingwen Yu, Boyi Liu, Qianyi Zhang, Yue Wang, Dimitrios Kanoulas Published: 2026-01-18 Categories: cs.RO, cs.CV arXiv: https://arxiv.org/abs/2601.12291v2 Scalable and maintainable maps are fundamental to large-scale navigation and the long-term deployment of robots in real-world environments. However, conventional maps that explicitly maintain dense geometry or 3D landmarks incur high storage and maintenance costs, while the core challenge of scaling to multi-session mapping is visual localization under sparse viewpoint overlap, temporal appearance shifts, and cross-device variance. To address this, we propose OpenNavMap, a lightweight, landmark-free topometric mapping system that organizes image nodes into covisibility, odometry, and traversability graphs and delegates local geometry recovery to 3D geometric foundation models (GFMs) on demand. For localization, dynamic-programming-based sequence matching narrows candidate correspondences for a GFM, reducing global estimation to a lightweight, pose-only optimization; for mapping, a lifelong pipeline fuses multi-session, multi-device data via cross-device merging and node culling. On a 19km dataset across four real-world environments, \methodname attains a state-of-the-art $0.62$m translation error on the Map-Free benchmark, bounds the absolute trajectory error below $3$m across 15.7km without depth sensors, and completes $12$ autonomous image-goal visual navigation tasks on both simulated and physical robots. Code and datasets will be made publicly available at https://rpl-cs-ucl.github.io/OpenNavMap_page. --- ### ParaMETA: Towards Learning Disentangled Paralinguistic Speaking Styles Representations from Speech Authors: Haowei Lou, Hye-young Paik, Wen Hu, Lina Yao Published: 2026-01-18 Categories: cs.SD, cs.LG, eess.AS arXiv: https://arxiv.org/abs/2601.12289v1 Learning representative embeddings for different types of speaking styles, such as emotion, age, and gender, is critical for both recognition tasks (e.g., cognitive computing and human-computer interaction) and generative tasks (e.g., style-controllable speech generation). In this work, we introduce ParaMETA, a unified and flexible framework for learning and controlling speaking styles directly from speech. Unlike existing methods that rely on single-task models or cross-modal alignment, ParaMETA learns disentangled, task-specific embeddings by projecting speech into dedicated subspaces for each type of style. This design reduces inter-task interference, mitigates negative transfer, and allows a single model to handle multiple paralinguistic tasks such as emotion, gender, age, and language classification. Beyond recognition, ParaMETA enables fine-grained style control in Text-To-Speech (TTS) generative models. It supports both speech- and text-based prompting and allows users to modify one speaking styles while preserving others. Extensive experiments demonstrate that ParaMETA outperforms strong baselines in classification accuracy and generates more natural and expressive speech, while maintaining a lightweight and efficient model suitable for real-world applications. --- ### TimeGMM: Single-Pass Probabilistic Forecasting via Adaptive Gaussian Mixture Models with Reversible Normalization Authors: Lei Liu, Tengyuan Liu, Hongwei Zhao, Jiahui Huang, Ruibo Guo, Bin Li Published: 2026-01-18 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2601.12288v1 Probabilistic time series forecasting is crucial for quantifying future uncertainty, with significant applications in fields such as energy and finance. However, existing methods often rely on computationally expensive sampling or restrictive parametric assumptions to characterize future distributions, which limits predictive performance and introduces distributional mismatch. To address these challenges, this paper presents TimeGMM, a novel probabilistic forecasting framework based on Gaussian Mixture Models (GMM) that captures complex future distributions in a single forward pass. A key component is GMM-adapted Reversible Instance Normalization (GRIN), a novel module designed to dynamically adapt to temporal-probabilistic distribution shifts. The framework integrates a dedicated Temporal Encoder (TE-Module) with a Conditional Temporal-Probabilistic Decoder (CTPD-Module) to jointly capture temporal dependencies and mixture distribution parameters. Extensive experiments demonstrate that TimeGMM consistently outperforms state-of-the-art methods, achieving maximum improvements of 22.48\% in CRPS and 21.23\% in NMAE. --- ### Conversational Context Classification: A Representation Engineering Approach Authors: Jonathan Pan Published: 2026-01-18 Categories: cs.CL, cs.AI, cs.CR arXiv: https://arxiv.org/abs/2601.12286v1 The increasing prevalence of Large Language Models (LLMs) demands effective safeguards for their operation, particularly concerning their tendency to generate out-of-context responses. A key challenge is accurately detecting when LLMs stray from expected conversational norms, manifesting as topic shifts, factual inaccuracies, or outright hallucinations. Traditional anomaly detection struggles to directly apply within contextual semantics. This paper outlines our experiment in exploring the use of Representation Engineering (RepE) and One-Class Support Vector Machine (OCSVM) to identify subspaces within the internal states of LLMs that represent a specific context. By training OCSVM on in-context examples, we establish a robust boundary within the LLM's hidden state latent space. We evaluate out study with two open source LLMs - Llama and Qwen models in specific contextual domain. Our approach entailed identifying the optimal layers within the LLM's internal state subspaces that strongly associates with the context of interest. Our evaluation results showed promising results in identifying the subspace for a specific context. Aside from being useful in detecting in or out of context conversation threads, this research work contributes to the study of better interpreting LLMs. --- ### LegacyAvatars: Volumetric Face Avatars For Traditional Graphics Pipelines Authors: Safa C. Medin, Gengyan Li, Ziqian Bai, Ruofei Du, Leonhard Helminger, Yinda Zhang, Stephan J. Garbin, Philip L. Davidson, Gregory W. Wornell, Thabo Beeler, Abhimitra Meka Published: 2026-01-18 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.12285v1 We introduce a novel representation for efficient classical rendering of photorealistic 3D face avatars. Leveraging recent advances in radiance fields anchored to parametric face models, our approach achieves controllable volumetric rendering of complex facial features, including hair, skin, and eyes. At enrollment time, we learn a set of radiance manifolds in 3D space to extract an explicit layered mesh, along with appearance and warp textures. During deployment, this allows us to control and animate the face through simple linear blending and alpha compositing of textures over a static mesh. This explicit representation also enables the generated avatar to be efficiently streamed online and then rendered using classical mesh and shader-based rendering on legacy graphics platforms, eliminating the need for any custom engineering or integration. --- ### SDiT: Semantic Region-Adaptive for Diffusion Transformers Authors: Bowen Lin, Fanjiang Ye, Yihua Liu, Zhenghui Guo, Boyuan Zhang, Weijian Zheng, Yufan Xu, Tiancheng Xing, Yuke Wang, Chengming Zhang Published: 2026-01-18 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.12283v1 Diffusion Transformers (DiTs) achieve state-of-the-art performance in text-to-image synthesis but remain computationally expensive due to the iterative nature of denoising and the quadratic cost of global attention. In this work, we observe that denoising dynamics are spatially non-uniform-background regions converge rapidly while edges and textured areas evolve much more actively. Building on this insight, we propose SDiT, a Semantic Region-Adaptive Diffusion Transformer that allocates computation according to regional complexity. SDiT introduces a training-free framework combining (1) semantic-aware clustering via fast Quickshift-based segmentation, (2) complexity-driven regional scheduling to selectively update informative areas, and (3) boundary-aware refinement to maintain spatial coherence. Without any model retraining or architectural modification, SDiT achieves up to 3.0x acceleration while preserving nearly identical perceptual and semantic quality to full-attention inference. --- ### CytoCLIP: Learning Cytoarchitectural Characteristics in Developing Human Brain Using Contrastive Language Image Pre-Training Authors: Pralaypati Ta, Sriram Venkatesaperumal, Keerthi Ram, Mohanasankar Sivaprakasam Published: 2026-01-18 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2601.12282v2 The functions of different regions of the human brain are closely linked to their distinct cytoarchitecture, which is defined by the spatial arrangement and morphology of the cells. Identifying brain regions by their cytoarchitecture enables various scientific analyses of the brain. However, delineating these areas manually in brain histological sections is time-consuming and requires specialized knowledge. An automated approach is necessary to minimize the effort needed from human experts. To address this, we propose CytoCLIP, a suite of vision-language models derived from pre-trained Contrastive Language-Image Pre-Training (CLIP) frameworks to learn joint visual-text representations of brain cytoarchitecture. CytoCLIP comprises two model variants: one is trained using low-resolution whole-region images to understand the overall cytoarchitectural pattern of an area, and the other is trained on high-resolution image tiles for detailed cellular-level representation. The training dataset is created from NISSL-stained histological sections of developing fetal brains of different gestational weeks. It includes 86 distinct regions for low-resolution images and 379 brain regions for high-resolution tiles. We evaluate the model's understanding of the cytoarchitecture and generalization ability using region classification and cross-modal retrieval tasks. Multiple experiments are performed under various data setups, including data from samples of different ages and sectioning planes. Experimental results demonstrate that CytoCLIP outperforms existing methods. It achieves a weighted F1 score of 0.87 for whole-region classification and 0.91 for high-resolution image tile classification. --- ### HCFT: Hierarchical Convolutional Fusion Transformer for EEG Decoding Authors: Haodong Zhang, Jiapeng Zhu, Yitong Chen, Hongqi Li Published: 2026-01-18 Categories: cs.HC, cs.LG arXiv: https://arxiv.org/abs/2601.12279v1 Electroencephalography (EEG) decoding requires models that can effectively extract and integrate complex temporal, spectral, and spatial features from multichannel signals. To address this challenge, we propose a lightweight and generalizable decoding framework named Hierarchical Convolutional Fusion Transformer (HCFT), which combines dual-branch convolutional encoders and hierarchical Transformer blocks for multi-scale EEG representation learning. Specifically, the model first captures local temporal and spatiotemporal dynamics through time-domain and time-space convolutional branches, and then aligns these features via a cross-attention mechanism that enables interaction between branches at each stage. Subsequently, a hierarchical Transformer fusion structure is employed to encode global dependencies across all feature stages, while a customized Dynamic Tanh normalization module is introduced to replace traditional Layer Normalization in order to enhance training stability and reduce redundancy. Extensive experiments are conducted on two representative benchmark datasets, BCI Competition IV-2b and CHB-MIT, covering both event-related cross-subject classification and continuous seizure prediction tasks. Results show that HCFT achieves 80.83% average accuracy and a Cohen's kappa of 0.6165 on BCI IV-2b, as well as 99.10% sensitivity, 0.0236 false positives per hour, and 98.82% specificity on CHB-MIT, consistently outperforming over ten state-of-the-art baseline methods. Ablation studies confirm that each core component of the proposed framework contributes significantly to the overall decoding performance, demonstrating HCFT's effectiveness in capturing EEG dynamics and its potential for real-world BCI applications. --- ### Predictive Prototyping: Evaluating Design Concepts with ChatGPT Authors: Hilsann Yong, Bradley A. Camburn Published: 2026-01-18 Categories: cs.HC, cs.AI arXiv: https://arxiv.org/abs/2601.12276v2 The design-build-test cycle is essential for innovation, but physical prototyping is often slow and expensive. Although physics-based simulation and strategic prototyping can reduce cost, meaningful evaluation is frequently constrained until an integrated prototype is built. This paper investigates whether a generative pretrained transformer (GPT) can predict information typically obtained through prototyping, including cost, performance, and perceived usability. We introduce a retrieval-augmented generation (RAG) method to emulate design feedback using OpenAI GPT-4o, grounded in prototyping data scraped from Instructables.com to increase access to relevant precedent. Two studies are reported. First, a controlled experiment compares GPT-RAG and human designers, who receive design sketches and predict cost, performance, and usability; predictions are evaluated against ground-truth results from physical prototypes. Second, we report an applied demonstration in which a physical prototype is produced from GPT-RAG recommendations and compared with a commercial baseline and a topology-optimized design. Results show that GPT-RAG provides more accurate cost and performance estimates than individual or crowd human estimates, while yielding comparable usability insights; the GPT-RAG-informed prototype also outperforms both comparison prototypes. Repeated querying with response averaging significantly improves accuracy, suggesting that LLMs can emulate crowd aggregation effects consistent with the law of large numbers. --- ### AgenticPruner: MAC-Constrained Neural Network Compression via LLM-Driven Strategy Search Authors: Shahrzad Esmat, Mahdi Banisharif, Ali Jannesari Published: 2026-01-18 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.12272v1 Neural network pruning remains essential for deploying deep learning models on resource-constrained devices, yet existing approaches primarily target parameter reduction without directly controlling computational cost. This yields unpredictable inference latency in deployment scenarios where strict Multiply-Accumulate (MAC) operation budgets must be met. We propose AgenticPruner, a framework utilizing large language models to achieve MAC-constrained optimization through iterative strategy learning. Our approach coordinates three specialized agents: a Profiling Agent that analyzes model architecture and MAC distributions, a Master Agent that orchestrates the workflow with divergence monitoring, and an Analysis Agent powered by Claude 3.5 Sonnet that learns optimal strategies from historical attempts. Through in-context learning, the Analysis Agent improves convergence success rate from 48% to 71% compared to grid search. Building upon isomorphic pruning's graph-based structural grouping, our method adds context-aware adaptation by analyzing patterns across pruning iterations, enabling automatic convergence to target MAC budgets within user-defined tolerance bands. We validate our framework on ImageNet-1K across ResNet, ConvNeXt, and DeiT architectures. On CNNs, our approach achieves MAC targeting while maintaining or improving accuracy: ResNet-50 reaches 1.77G MACs with 77.04% accuracy (+0.91% vs baseline); ResNet-101 achieves 4.22G MACs with 78.94% accuracy (+1.56% vs baseline). For ConvNeXt-Small, pruning to 8.17G MACs yields 1.41x GPU and 1.07x CPU speedup with 45% parameter reduction. On Vision Transformers, we demonstrate MAC-budget compliance within user-defined tolerance bands (typically +1% to +5% overshoot, -5% to -15% undershoot), establishing feasibility for deployment scenarios requiring strict computational guarantees. --- ### Simulated Annealing Enhances Theory-of-Mind Reasoning in Autoregressive Language Models Authors: Xucong Hu, Jian-Qiao Zhu Published: 2026-01-18 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2601.12269v1 Autoregressive language models are next-token predictors and have been criticized for only optimizing surface plausibility (i.e., local coherence) rather than maintaining correct latent-state representations (i.e., global coherence). Because Theory of Mind (ToM) tasks crucially depend on reasoning about latent mental states of oneself and others, such models are therefore often thought to fail at ToM. While post-training methods can improve ToM performance, we show that strong ToM capability can be recovered directly from the base model without any additional weight updates or verifications. Our approach builds on recent power-sampling methods (Karan & Du, 2025) that use Markov chain Monte Carlo (MCMC) to sample from sharpened sequence-level (rather than token-level) probability distributions of autoregressive language models. We further find that incorporating annealing, where the tempered distribution is gradually shifted from high to low temperature, substantially improves ToM performance over fixed-temperature power sampling. Together, these results suggest that sampling-based optimization provides a powerful way to extract latent capabilities from language models without retraining. --- ### Statistical Firefly Algorithm for Truss Topology Optimization Authors: Nghi Huu Duong, Duy Vo, Pruettha Nanakorn Published: 2026-01-18 Categories: cs.NE arXiv: https://arxiv.org/abs/2601.12265v1 This study proposes an algorithm titled a statistical firefly algorithm (SFA) for truss topology optimization. In the proposed algorithm, historical results of fireflies' motions are used in hypothesis testing to limit the motions of fireflies that are suggested by current information exchanges between fireflies only to those that are potentially useful. Hypothesis testing is applied to the mechanism of an ordinary firefly algorithm (FA) without changing its structure. As a result, the implementation of the proposed algorithm is simple and straightforward. Limiting the motions of fireflies to those that are potential useful results in reduction of firefly evaluations, and, subsequently, reduction of computational efforts. To test the validity and efficiency of the proposed algorithm, it is used to solve several truss topology optimization problems, including some benchmark problems. It is found that the added statistical strategy in the SFA significantly enhances the performance of the original FA in terms of computational efforts while still maintains the quality of the obtained results. --- ### Multimodal Generative Engine Optimization: Rank Manipulation for Vision-Language Model Rankers Authors: Yixuan Du, Chenxiao Yu, Haoyan Xu, Ziyi Wang, Yue Zhao, Xiyang Hu Published: 2026-01-18 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2601.12263v2 Vision-Language Models (VLMs) integrate visual and textual knowledge into unified representations that increasingly underpin modern retrieval and recommendation systems. However, it remains unclear how reliably these models utilize their cross-modal knowledge when ranking multimodal items, and whether their knowledge grounding can be subverted. In this paper, we expose a fundamental vulnerability in how VLMs apply multimodal knowledge for product ranking: through Multimodal Generative Engine Optimization (MGEO), we show that an adversary can manipulate a VLM's ranking decisions by jointly crafting imperceptible image perturbations and fluent textual suffixes that exploit the model's internal cross-modal knowledge coupling. Using an alternating optimization strategy, MGEO targets the deep interactions between visual and linguistic representations within the VLM, achieving rank manipulations that substantially exceed those of unimodal attacks and heuristic baselines powered by strong commercial models. Our findings reveal that surface-level content quality is insufficient for rank promotion; instead, direct alignment with the model's internal knowledge utilization mechanism is required. These results raise important questions on the faithfulness and robustness of knowledge grounding in multimodal foundation models, and motivate future work on defense mechanisms for multimodal retrieval systems. Code is available at: https://github.com/glad-lab/MGEO --- ### Environment-Aware Code Generation: How far are We? Authors: Tongtong Wu, Rongyi Chen, Wenjie Du, Suyu Ma, Guilin Qi, Zhenchang Xing, Shahram Khadivi, Ramesh Periyathambi, Gholamreza Haffari Published: 2026-01-18 Categories: cs.SE, cs.CL arXiv: https://arxiv.org/abs/2601.12262v1 Recent progress in large language models (LLMs) has improved code generation, but most evaluations still test isolated, small-scale code (e.g., a single function) under default or unspecified software environments. As a result, it is unclear whether LLMs can reliably generate executable code tailored to a user's specific environment. We present the first systematic study of Environment-Aware Code Generation (EACG), where generated code must be functionally correct and directly executable under arbitrary software configurations. To enable realistic evaluation, we introduce VersiBCB, a benchmark that is multi-package, execution-verified, and deprecation-aware, capturing complex and evolving environments that prior datasets often overlook. Using VersiBCB, we investigate three complementary adaptation axes: data, parameters, and cache, and develop representative strategies for each. Our results show that current LLMs struggle with environment-specific code generation, while our adaptations improve environment compatibility and executability. These findings highlight key challenges and opportunities for deploying LLMs in practical software engineering workflows. --- ### DALD-PCAC: Density-Adaptive Learning Descriptor for Point Cloud Lossless Attribute Compression Authors: Chunyang Fu, Ge Li, Wei Gao, Shiqi Wang, Zhu Li, Shan Liu Published: 2026-01-18 Categories: eess.IV, cs.CV arXiv: https://arxiv.org/abs/2601.12261v1 Recently, deep learning has significantly advanced the performance of point cloud geometry compression. However, the learning-based lossless attribute compression of point clouds with varying densities is under-explored. In this paper, we develop a learning-based framework, namely DALD-PCAC that leverages Levels of Detail (LoD) to tailor for point cloud lossless attribute compression. We develop a point-wise attention model using a permutation-invariant Transformer to tackle the challenges of sparsity and irregularity of point clouds during context modeling. We also propose a Density-Adaptive Learning Descriptor (DALD) capable of capturing structure and correlations among points across a large range of neighbors. In addition, we develop a prior-guided block partitioning to reduce the attribute variance within blocks and enhance the performance. Experiments on LiDAR and object point clouds show that DALD-PCAC achieves the state-of-the-art performance on most data. Our method boosts the compression performance and is robust to the varying densities of point clouds. Moreover, it guarantees a good trade-off between performance and complexity, exhibiting great potential in real-world applications. The source code is available at https://github.com/zb12138/DALD_PCAC. --- ### Docs2Synth: A Synthetic Data Trained Retriever Framework for Scanned Visually Rich Documents Understanding Authors: Yihao Ding, Qiang Sun, Puzhen Wu, Sirui Li, Siwen Luo, Wei Liu Published: 2026-01-18 Categories: cs.AI arXiv: https://arxiv.org/abs/2601.12260v1 Document understanding (VRDU) in regulated domains is particularly challenging, since scanned documents often contain sensitive, evolving, and domain specific knowledge. This leads to two major challenges: the lack of manual annotations for model adaptation and the difficulty for pretrained models to stay up-to-date with domain-specific facts. While Multimodal Large Language Models (MLLMs) show strong zero-shot abilities, they still suffer from hallucination and limited domain grounding. In contrast, discriminative Vision-Language Pre-trained Models (VLPMs) provide reliable grounding but require costly annotations to cover new domains. We introduce Docs2Synth, a synthetic-supervision framework that enables retrieval-guided inference for private and low-resource domains. Docs2Synth automatically processes raw document collections, generates and verifies diverse QA pairs via an agent-based system, and trains a lightweight visual retriever to extract domain-relevant evidence. During inference, the retriever collaborates with an MLLM through an iterative retrieval--generation loop, reducing hallucination and improving response consistency. We further deliver Docs2Synth as an easy-to-use Python package, enabling plug-and-play deployment across diverse real-world scenarios. Experiments on multiple VRDU benchmarks show that Docs2Synth substantially enhances grounding and domain generalization without requiring human annotations. --- ### FutureX-Pro: Extending Future Prediction to High-Value Vertical Domains Authors: Jiashuo Liu, Siyuan Chen, Zaiyuan Wang, Zhiyuan Zeng, Jiacheng Guo, Liang Hu, Lingyue Yin, Suozhi Huang, Wenxin Hao, Yang Yang, Zerui Cheng, Zixin Yao et al. Published: 2026-01-18 Categories: cs.AI, cs.CE, cs.LG arXiv: https://arxiv.org/abs/2601.12259v1 Building upon FutureX, which established a live benchmark for general-purpose future prediction, this report introduces FutureX-Pro, including FutureX-Finance, FutureX-Retail, FutureX-PublicHealth, FutureX-NaturalDisaster, and FutureX-Search. These together form a specialized framework extending agentic future prediction to high-value vertical domains. While generalist agents demonstrate proficiency in open-domain search, their reliability in capital-intensive and safety-critical sectors remains under-explored. FutureX-Pro targets four economically and socially pivotal verticals: Finance, Retail, Public Health, and Natural Disaster. We benchmark agentic Large Language Models (LLMs) on entry-level yet foundational prediction tasks -- ranging from forecasting market indicators and supply chain demands to tracking epidemic trends and natural disasters. By adapting the contamination-free, live-evaluation pipeline of FutureX, we assess whether current State-of-the-Art (SOTA) agentic LLMs possess the domain grounding necessary for industrial deployment. Our findings reveal the performance gap between generalist reasoning and the precision required for high-value vertical applications. --- ### Soft Shadow Diffusion (SSD): Physics-inspired Learning for 3D Computational Periscopy Authors: Fadlullah Raji, John Murray-Bruce Published: 2026-01-18 Categories: cs.CV, cs.AI, cs.CG, cs.GR arXiv: https://arxiv.org/abs/2601.12257v1 Conventional imaging requires a line of sight to create accurate visual representations of a scene. In certain circumstances, however, obtaining a suitable line of sight may be impractical, dangerous, or even impossible. Non-line-of-sight (NLOS) imaging addresses this challenge by reconstructing the scene from indirect measurements. Recently, passive NLOS methods that use an ordinary photograph of the subtle shadow cast onto a visible wall by the hidden scene have gained interest. These methods are currently limited to 1D or low-resolution 2D color imaging or to localizing a hidden object whose shape is approximately known. Here, we generalize this class of methods and demonstrate a 3D reconstruction of a hidden scene from an ordinary NLOS photograph. To achieve this, we propose a novel reformulation of the light transport model that conveniently decomposes the hidden scene into \textit{light-occluding} and \textit{non-light-occluding} components to yield a separable non-linear least squares (SNLLS) inverse problem. We develop two solutions: A gradient-based optimization method and a physics-inspired neural network approach, which we call Soft Shadow diffusion (SSD). Despite the challenging ill-conditioned inverse problem encountered here, our approaches are effective on numerous 3D scenes in real experimental scenarios. Moreover, SSD is trained in simulation but generalizes well to unseen classes in simulation and real-world NLOS scenes. SSD also shows surprising robustness to noise and ambient illumination. --- ### Improving Large Molecular Language Model via Relation-aware Multimodal Collaboration Authors: Jinyoung Park, Minseong Bae, Jeehye Na, Hyunwoo J. Kim Published: 2026-01-18 Categories: cs.AI arXiv: https://arxiv.org/abs/2601.12256v1 Large language models (LLMs) have demonstrated their instruction-following capabilities and achieved powerful performance on various tasks. Inspired by their success, recent works in the molecular domain have led to the development of large molecular language models (LMLMs) that integrate 1D molecular strings or 2D molecular graphs into the language models. However, existing LMLMs often suffer from hallucination and limited robustness, largely due to inadequate integration of diverse molecular modalities such as 1D sequences, 2D molecular graphs, and 3D conformations. To address these limitations, we propose CoLLaMo, a large language model-based molecular assistant equipped with a multi-level molecular modality-collaborative projector. The relation-aware modality-collaborative attention mechanism in the projector facilitates fine-grained and relation-guided information exchange between atoms by incorporating 2D structural and 3D spatial relations. Furthermore, we present a molecule-centric new automatic measurement, including a hallucination assessment metric and GPT-based caption quality evaluation to address the limitations of token-based generic evaluation metrics (i.e., BLEU) widely used in assessing molecular comprehension of LMLMs. Our extensive experiments demonstrate that our CoLLaMo enhances the molecular modality generalization capabilities of LMLMs, achieving the best performance on multiple tasks, including molecule captioning, computed property QA, descriptive property QA, motif counting, and IUPAC name prediction. --- ### DeepRAHT: Learning Predictive RAHT for Point Cloud Attribute Compression Authors: Chunyang Fu, Tai Qin, Shiqi Wang, Zhu Li Published: 2026-01-18 Categories: eess.IV, cs.CV, cs.IT, cs.MM arXiv: https://arxiv.org/abs/2601.12255v1 Regional Adaptive Hierarchical Transform (RAHT) is an effective point cloud attribute compression (PCAC) method. However, its application in deep learning lacks research. In this paper, we propose an end-to-end RAHT framework for lossy PCAC based on the sparse tensor, called DeepRAHT. The RAHT transform is performed within the learning reconstruction process, without requiring manual RAHT for preprocessing. We also introduce the predictive RAHT to reduce bitrates and design a learning-based prediction model to enhance performance. Moreover, we devise a bitrate proxy that applies run-length coding to entropy model, achieving seamless variable-rate coding and improving robustness. DeepRAHT is a reversible and distortion-controllable framework, ensuring its lower bound performance and offering significant application potential. The experiments demonstrate that DeepRAHT is a high-performance, faster, and more robust solution than the baseline methods. Project Page: https://github.com/zb12138/DeepRAHT. --- ### Federated Joint Learning for Domain and Class Generalization Authors: Haoran Xu, Jiaze Li, Jianzhong Ju, Zhenbo Luo Published: 2026-01-18 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2601.12253v2 Efficient fine-tuning of visual-language models like CLIP has become crucial due to their large-scale parameter size and extensive pretraining requirements. Existing methods typically address either the issue of unseen classes or unseen domains in isolation, without considering a joint framework for both. In this paper, we propose \textbf{Fed}erated Joint Learning for \textbf{D}omain and \textbf{C}lass \textbf{G}eneralization, termed \textbf{FedDCG}, a novel approach that addresses both class and domain generalization in federated learning settings. Our method introduces a domain grouping strategy where class-generalized networks are trained within each group to prevent decision boundary confusion. During inference, we aggregate class-generalized results based on domain similarity, effectively integrating knowledge from both class and domain generalization. Specifically, a learnable network is employed to enhance class generalization capabilities, and a decoupling mechanism separates general and domain-specific knowledge, improving generalization to unseen domains. Extensive experiments across various datasets show that \textbf{FedDCG} outperforms state-of-the-art baselines in terms of accuracy and robustness. --- ### Breaking Coordinate Overfitting: Geometry-Aware WiFi Sensing for Cross-Layout 3D Pose Estimation Authors: Songming Jia, Yan Lu, Bin Liu, Xiang Zhang, Peng Zhao, Xinmeng Tang, Yelin Wei, Jinyang Huang, Huan Yan, Zhi Liu Published: 2026-01-18 Categories: cs.HC, cs.CV arXiv: https://arxiv.org/abs/2601.12252v1 WiFi-based 3D human pose estimation offers a low-cost and privacy-preserving alternative to vision-based systems for smart interaction. However, existing approaches rely on visual 3D poses as supervision and directly regress CSI to a camera-based coordinate system. We find that this practice leads to coordinate overfitting: models memorize deployment-specific WiFi transceiver layouts rather than only learning activity-relevant representations, resulting in severe generalization failures. To address this challenge, we present PerceptAlign, the first geometry-conditioned framework for WiFi-based cross-layout pose estimation. PerceptAlign introduces a lightweight coordinate unification procedure that aligns WiFi and vision measurements in a shared 3D space using only two checkerboards and a few photos. Within this unified space, it encodes calibrated transceiver positions into high-dimensional embeddings and fuses them with CSI features, making the model explicitly aware of device geometry as a conditional variable. This design forces the network to disentangle human motion from deployment layouts, enabling robust and, for the first time, layout-invariant WiFi pose estimation. To support systematic evaluation, we construct the largest cross-domain 3D WiFi pose estimation dataset to date, comprising 21 subjects, 5 scenes, 18 actions, and 7 device layouts. Experiments show that PerceptAlign reduces in-domain error by 12.3% and cross-domain error by more than 60% compared to state-of-the-art baselines. These results establish geometry-conditioned learning as a viable path toward scalable and practical WiFi sensing. --- ### An Innovative Framework for Breast Cancer Detection Using Pyramid Adaptive Atrous Convolution, Transformer Integration, and Multi-Scale Feature Fusion Authors: Ehsan Sadeghi Pour, Mahdi Esmaeili, Morteza Romoozi Published: 2026-01-18 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2601.12249v1 Breast cancer is one of the most common cancers among women worldwide, and its accurate and timely diagnosis plays a critical role in improving treatment outcomes. This thesis presents an innovative framework for detecting malignant masses in mammographic images by integrating the Pyramid Adaptive Atrous Convolution (PAAC) and Transformer architectures. The proposed approach utilizes Multi-Scale Feature Fusion to enhance the extraction of features from benign and malignant tissues and combines Dice Loss and Focal Loss functions to improve the model's learning process, effectively reducing errors in binary breast cancer classification and achieving high accuracy and efficiency. In this study, a comprehensive dataset of breast cancer images from INbreast, MIAS, and DDSM was preprocessed through data augmentation and contrast enhancement and resized to 227x227 pixels for model training. Leveraging the Transformer's ability to manage long-range dependencies with Self-Attention mechanisms, the proposed model achieved high accuracy in detecting cancerous masses, outperforming foundational models such as BreastNet, DeepMammo, Multi-Scale CNN, Swin-Unet, and SegFormer. The final evaluation results for the proposed model include an accuracy of 98.5\%, sensitivity of 97.8\%, specificity of 96.3\%, F1-score of 98.2\%, and overall precision of 97.9\%. These metrics demonstrate a significant improvement over traditional methods and confirm the model's effectiveness in identifying cancerous masses in complex scenarios and large datasets. This model shows potential as a reliable and efficient tool for breast cancer diagnosis and can be effectively integrated into medical diagnostic systems. --- ### AQUA-Bench: Beyond Finding Answers to Knowing When There Are None in Audio Question Answering Authors: Chun-Yi Kuan, Hung-yi Lee Published: 2026-01-18 Categories: eess.AS, cs.AI, cs.CL, cs.LG, cs.SD arXiv: https://arxiv.org/abs/2601.12248v3 Recent advances in audio-aware large language models have shown strong performance on audio question answering. However, existing benchmarks mainly cover answerable questions and overlook the challenge of unanswerable ones, where no reliable answer can be inferred from the audio. Such cases are common in real-world settings, where questions may be misleading, ill-posed, or incompatible with the information. To address this gap, we present AQUA-Bench, a benchmark for Audio Question Unanswerability Assessment. It systematically evaluates three scenarios: Absent Answer Detection (the correct option is missing), Incompatible Answer Set Detection (choices are categorically mismatched with the question), and Incompatible Audio Question Detection (the question is irrelevant or lacks sufficient grounding in the audio). By assessing these cases, AQUA-Bench offers a rigorous measure of model reliability and promotes the development of audio-language systems that are more robust and trustworthy. Our experiments suggest that while models excel on standard answerable tasks, they often face notable challenges with unanswerable ones, pointing to a blind spot in current audio-language understanding. --- ### Plan, Verify and Fill: A Structured Parallel Decoding Approach for Diffusion Language Models Authors: Miao Li, Hanyang Jiang, Sikai Cheng, Hengyu Fu, Yuhang Cai, Baihe Huang, Tinghan Ye, Xuanzhou Chen, Pascal Van Hentenryck Published: 2026-01-18 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2601.12247v3 Diffusion Language Models (DLMs) present a promising non-sequential paradigm for text generation, distinct from standard autoregressive (AR) approaches. However, current decoding strategies often adopt a reactive stance, underutilizing the global bidirectional context to dictate global trajectories. To address this, we propose Plan-Verify-Fill (PVF), a training-free paradigm that grounds planning via quantitative validation. PVF actively constructs a hierarchical skeleton by prioritizing high-leverage semantic anchors and employs a verification protocol to operationalize pragmatic structural stopping where further deliberation yields diminishing returns. Extensive evaluations on LLaDA-8B-Instruct and Dream-7B-Instruct demonstrate that PVF reduces the Number of Function Evaluations (NFE) by up to 65% compared to confidence-based parallel decoding across benchmark datasets, unlocking superior efficiency without compromising accuracy. --- ### A Comprehensive Review of Bio-Inspired Approaches to Coordination, Communication, and System Architecture in Underwater Swarm Robotics Authors: Shyalan Ramesh, Scott Mann, Alex Stumpf Published: 2026-01-18 Categories: cs.RO, cs.NE arXiv: https://arxiv.org/abs/2601.12244v1 The increasing complexity of marine operations has intensified the need for intelligent robotic systems to support ocean observation, exploration, and resource management. Underwater swarm robotics offers a promising framework that extends the capabilities of individual autonomous platforms through collective coordination. Inspired by natural systems, such as fish schools and insect colonies, bio-inspired swarm approaches enable distributed decision-making, adaptability, and resilience under challenging marine conditions. Yet research in this field remains fragmented, with limited integration across algorithmic, communication, and hardware design perspectives. This review synthesises bio-inspired coordination mechanisms, communication strategies, and system design considerations for underwater swarm robotics. It examines key marine-specific algorithms, including the Artificial Fish Swarm Algorithm, Whale Optimisation Algorithm, Coral Reef Optimisation, and Marine Predators Algorithm, highlighting their applications in formation control, task allocation, and environmental interaction. The review also analyses communication constraints unique to the underwater domain and emerging acoustic, optical, and hybrid solutions that support cooperative operation. Additionally, it examines hardware and system design advances that enhance system efficiency and scalability. A multi-dimensional classification framework evaluates existing approaches across communication dependency, environmental adaptability, energy efficiency, and swarm scalability. Through this integrated analysis, the review unifies bio-inspired coordination algorithms, communication modalities, and system design approaches. It also identifies converging trends, key challenges, and future research directions for real-world deployment of underwater swarm systems. --- ### Less is More: Label-Guided Summarization of Procedural and Instructional Videos Authors: Shreya Rajpal, Michal Golovanevsky, Carsten Eickhoff Published: 2026-01-18 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2601.12243v2 Video summarization helps turn long videos into clear, concise representations that are easier to review, document, and analyze, especially in high-stakes domains like surgical training. Prior work has progressed from using basic visual features like color, motion, and structural changes to using pre-trained vision-language models that can better understand what's happening in the video (semantics) and capture temporal flow, resulting in more context-aware video summarization. We propose a three-stage framework, PRISM: Procedural Representation via Integrated Semantic and Multimodal analysis, that produces semantically grounded video summaries. PRISM combines adaptive visual sampling, label-driven keyframe anchoring, and contextual validation using a large language model (LLM). Our method ensures that selected frames reflect meaningful and procedural transitions while filtering out generic or hallucinated content, resulting in contextually coherent summaries across both domain-specific and instructional videos. We evaluate our method on instructional and activity datasets, using reference summaries for instructional videos. Despite sampling fewer than 5% of the original frames, our summaries retain 84% semantic content while improving over baselines by as much as 33%. Our approach generalizes across procedural and domain-specific video tasks, achieving strong performance with both semantic alignment and precision. --- ### Optimal Power Allocation and Sub-Optimal Channel Assignment for Downlink NOMA Systems Using Deep Reinforcement Learning Authors: WooSeok Kim, Jeonghoon Lee, Sangho Kim, Taesun An, WonMin Lee, Dowon Kim, Kyungseop Shin Published: 2026-01-18 Categories: cs.AI, cs.LG, cs.NI arXiv: https://arxiv.org/abs/2601.12242v1 In recent years, Non-Orthogonal Multiple Access (NOMA) system has emerged as a promising candidate for multiple access frameworks due to the evolution of deep machine learning, trying to incorporate deep machine learning into the NOMA system. The main motivation for such active studies is the growing need to optimize the utilization of network resources as the expansion of the internet of things (IoT) caused a scarcity of network resources. The NOMA addresses this need by power multiplexing, allowing multiple users to access the network simultaneously. Nevertheless, the NOMA system has few limitations. Several works have proposed to mitigate this, including the optimization of power allocation known as joint resource allocation(JRA) method, and integration of the JRA method and deep reinforcement learning (JRA-DRL). Despite this, the channel assignment problem remains unclear and requires further investigation. In this paper, we propose a deep reinforcement learning framework incorporating replay memory with an on-policy algorithm, allocating network resources in a NOMA system to generalize the learning. Also, we provide extensive simulations to evaluate the effects of varying the learning rate, batch size, type of model, and the number of features in the state. --- ### On the Provable Suboptimality of Momentum SGD in Nonstationary Stochastic Optimization Authors: Sharan Sahu, Cameron J. Hogan, Martin T. Wells Published: 2026-01-18 Categories: stat.ML, cs.LG, math.OC arXiv: https://arxiv.org/abs/2601.12238v5 In this paper, we provide a comprehensive theoretical analysis of Stochastic Gradient Descent (SGD) and its momentum variants (Polyak Heavy-Ball and Nesterov) for tracking time-varying optima under strong convexity and smoothness. Our finite-time bounds reveal a sharp decomposition of tracking error into transient, noise-induced, and drift-induced components. This decomposition exposes a fundamental trade-off: while momentum is often used as a gradient-smoothing heuristic, under distribution shift it incurs an explicit drift-amplification penalty that diverges as the momentum parameter $β$ approaches 1, yielding systematic tracking lag. We complement these upper bounds with minimax lower bounds under gradient-variation constraints, proving this momentum-induced tracking penalty is not an analytical artifact but an information-theoretic barrier: in drift-dominated regimes, momentum is unavoidably worse because stale-gradient averaging forces systematic lag. Our results provide theoretical grounding for the empirical instability of momentum in dynamic settings and precisely delineate regime boundaries where vanilla SGD provably outperforms its accelerated counterparts. --- ### Proc3D: Procedural 3D Generation and Parametric Editing of 3D Shapes with Large Language Models Authors: Fadlullah Raji, Stefano Petrangeli, Matheus Gadelha, Yu Shen, Uttaran Bhattacharya, Gang Wu Published: 2026-01-18 Categories: cs.GR, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2601.12234v1 Generating 3D models has traditionally been a complex task requiring specialized expertise. While recent advances in generative AI have sought to automate this process, existing methods produce non-editable representation, such as meshes or point clouds, limiting their adaptability for iterative design. In this paper, we introduce Proc3D, a system designed to generate editable 3D models while enabling real-time modifications. At its core, Proc3D introduces procedural compact graph (PCG), a graph representation of 3D models, that encodes the algorithmic rules and structures necessary for generating the model. This representation exposes key parameters, allowing intuitive manual adjustments via sliders and checkboxes, as well as real-time, automated modifications through natural language prompts using Large Language Models (LLMs). We demonstrate Proc3D's capabilities using two generative approaches: GPT-4o with in-context learning (ICL) and a fine-tuned LLAMA-3 model. Experimental results show that Proc3D outperforms existing methods in editing efficiency, achieving more than 400x speedup over conventional approaches that require full regeneration for each modification. Additionally, Proc3D improves ULIP scores by 28%, a metric that evaluates the alignment between generated 3D models and text prompts. By enabling text-aligned 3D model generation along with precise, real-time parametric edits, Proc3D facilitates highly accurate text-based image editing applications. --- ### DiffusionQC: Artifact Detection in Histopathology via Diffusion Model Authors: Zhenzhen Wang, Zhongliang Zhou, Zhuoyu Wen, Jeong Hwan Kook, John B Wojcik, John Kang Published: 2026-01-18 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.12233v1 Digital pathology plays a vital role across modern medicine, offering critical insights for disease diagnosis, prognosis, and treatment. However, histopathology images often contain artifacts introduced during slide preparation and digitization. Detecting and excluding them is essential to ensure reliable downstream analysis. Traditional supervised models typically require large annotated datasets, which is resource-intensive and not generalizable to novel artifact types. To address this, we propose DiffusionQC, which detects artifacts as outliers among clean images using a diffusion model. It requires only a set of clean images for training rather than pixel-level artifact annotations and predefined artifact types. Furthermore, we introduce a contrastive learning module to explicitly enlarge the distribution separation between artifact and clean images, yielding an enhanced version of our method. Empirical results demonstrate superior performance to state-of-the-art and offer cross-stain generalization capacity, with significantly less data and annotations. --- ### Wavelet-Aware Anomaly Detection in Multi-Channel User Logs via Deviation Modulation and Resolution-Adaptive Attention Authors: Kaichuan Kong, Dongjie Liu, Xiaobo Jin, Shijie Xu, Guanggang Geng Published: 2026-01-18 Categories: cs.LG, cs.CR, stat.CO arXiv: https://arxiv.org/abs/2601.12231v1 Insider threat detection is a key challenge in enterprise security, relying on user activity logs that capture rich and complex behavioral patterns. These logs are often multi-channel, non-stationary, and anomalies are rare, making anomaly detection challenging. To address these issues, we propose a novel framework that integrates wavelet-aware modulation, multi-resolution wavelet decomposition, and resolution-adaptive attention for robust anomaly detection. Our approach first applies a deviation-aware modulation scheme to suppress routine behaviors while amplifying anomalous deviations. Next, discrete wavelet transform (DWT) decomposes the log signals into multi-resolution representations, capturing both long-term trends and short-term anomalies. Finally, a learnable attention mechanism dynamically reweights the most discriminative frequency bands for detection. On the CERT r4.2 benchmark, our approach consistently outperforms existing baselines in precision, recall, and F1 score across various time granularities and scenarios. ---