# Research Papers — 2026-01 · bundle page 91 of 189 > Full-text markdown of papers #4501–4550 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/91 [← Previous bundle](https://aipod.dev/papers/archive/2026-01/page/90.md) [Next bundle →](https://aipod.dev/papers/archive/2026-01/page/92.md) ### Joint Source-Channel-Generation Coding: From Distortion-oriented Reconstruction to Semantic-consistent Generation Authors: Tong Wu, Zhiyong Chen, Guo Lu, Li Song, Feng Yang, Meixia Tao, Wenjun Zhang Published: 2026-01-19 Categories: cs.IT, cs.CV, cs.LG arXiv: https://arxiv.org/abs/2601.12808v1 Conventional communication systems, including both separation-based coding and AI-driven joint source-channel coding (JSCC), are largely guided by Shannon's rate-distortion theory. However, relying on generic distortion metrics fails to capture complex human visual perception, often resulting in blurred or unrealistic reconstructions. In this paper, we propose Joint Source-Channel-Generation Coding (JSCGC), a novel paradigm that shifts the focus from deterministic reconstruction to probabilistic generation. JSCGC leverages a generative model at the receiver as a generator rather than a conventional decoder to parameterize the data distribution, enabling direct maximization of mutual information under channel constraints while controlling stochastic sampling to produce outputs residing on the authentic data manifold with high fidelity. We further derive a theoretical lower bound on the maximum semantic inconsistency with given transmitted mutual information, elucidating the fundamental limits of communication in controlling the generative process. Extensive experiments on image transmission demonstrate that JSCGC substantially improves perceptual quality and semantic fidelity, significantly outperforming conventional distortion-oriented JSCC methods. --- ### Semi-supervised Instruction Tuning for Large Language Models on Text-Attributed Graphs Authors: Zixing Song, Irwin King Published: 2026-01-19 Categories: cs.LG arXiv: https://arxiv.org/abs/2601.12807v1 The emergent reasoning capabilities of Large Language Models (LLMs) offer a transformative paradigm for analyzing text-attributed graphs. While instruction tuning is the prevailing method for adapting pre-trained LLMs to graph learning tasks like node classification, it requires a substantial volume of annotated (INSTRUCTION, OUTPUT) pairs deriving from labeled nodes. This requirement is particularly prohibitive in the social domain, where obtaining expert labels for sensitive or evolving content is costly and slow. Furthermore, standard graph instruction tuning fails to exploit the vast amount of unlabeled nodes, which contain latent correlations due to edge connections that are beneficial for downstream predictions. To bridge this gap, we propose a novel Semi-supervised Instruction Tuning pipeline for Graph Learning, named SIT-Graph. Notably, SIT-Graph is model-agnostic and can be seamlessly integrated into any graph instruction tuning method that utilizes LLMs as the predictor. SIT-Graph operates via an iterative self-training process. Initially, the model is fine-tuned using instruction pairs constructed solely from the labeled nodes. Then it generates confidence-filtered pseudo-responses for unlabeled nodes to strategically augment the dataset for the next round of fine-tuning. Finally, this iterative refinement progressively aligns the LLM with the underlying node correlations. Extensive experiments demonstrate that when incorporated into state-of-the-art graph instruction tuning methods, SIT-Graph significantly enhances their performance on text-attributed graph benchmarks, achieving over 20% improvement under the low label ratio settings. --- ### SciHorizon-GENE: Benchmarking LLM for Life Sciences Inference from Gene Knowledge to Functional Understanding Authors: Xiaohan Huang, Meng Xiao, Chuan Qin, Qingqing Long, Jinmiao Chen, Yuanchun Zhou, Hengshu Zhu Published: 2026-01-19 Categories: q-bio.GN, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2601.12805v4 Large language models (LLMs) have shown growing promise in biomedical research, particularly for knowledge-driven interpretation tasks. However, their ability to reliably reason from gene-level knowledge to functional understanding, a core requirement for knowledge-enhanced cell atlas interpretation, remains largely underexplored. To address this gap, we introduce SciHorizon-GENE, a large-scale gene-centric benchmark constructed from authoritative biological databases. The benchmark integrates curated knowledge for over 190K human genes and comprises more than 540K questions covering diverse gene-to-function reasoning scenarios relevant to cell type annotation, functional interpretation, and mechanism-oriented analysis. Motivated by behavioral patterns observed in preliminary examinations, SciHorizon-GENE evaluates LLMs along four biologically critical perspectives: research attention sensitivity, hallucination tendency, answer completeness, and literature influence, explicitly targeting failure modes that limit the safe adoption of LLMs in biological interpretation pipelines. We systematically evaluate a wide range of state-of-the-art general-purpose and biomedical LLMs, revealing substantial heterogeneity in gene-level reasoning capabilities and persistent challenges in generating faithful, complete, and literature-grounded functional interpretations. Our benchmark establishes a systematic foundation for analyzing LLM behavior at the gene scale and offers insights for model selection and development, with direct relevance to knowledge-enhanced biological interpretation. --- ### SL-CBM: Enhancing Concept Bottleneck Models with Semantic Locality for Better Interpretability Authors: Hanwei Zhang, Luo Cheng, Rui Wen, Yang Zhang, Lijun Zhang, Holger Hermanns Published: 2026-01-19 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2601.12804v1 Explainable AI (XAI) is crucial for building transparent and trustworthy machine learning systems, especially in high-stakes domains. Concept Bottleneck Models (CBMs) have emerged as a promising ante-hoc approach that provides interpretable, concept-level explanations by explicitly modeling human-understandable concepts. However, existing CBMs often suffer from poor locality faithfulness, failing to spatially align concepts with meaningful image regions, which limits their interpretability and reliability. In this work, we propose SL-CBM (CBM with Semantic Locality), a novel extension that enforces locality faithfulness by generating spatially coherent saliency maps at both concept and class levels. SL-CBM integrates a 1x1 convolutional layer with a cross-attention mechanism to enhance alignment between concepts, image regions, and final predictions. Unlike prior methods, SL-CBM produces faithful saliency maps inherently tied to the model's internal reasoning, facilitating more effective debugging and intervention. Extensive experiments on image datasets demonstrate that SL-CBM substantially improves locality faithfulness, explanation quality, and intervention efficacy while maintaining competitive classification accuracy. Our ablation studies highlight the importance of contrastive and entropy-based regularization for balancing accuracy, sparsity, and faithfulness. Overall, SL-CBM bridges the gap between concept-based reasoning and spatial explainability, setting a new standard for interpretable and trustworthy concept-based models. --- ### FRoM-W1: Towards General Humanoid Whole-Body Control with Language Instructions Authors: Peng Li, Zihan Zhuang, Yangfan Gao, Yi Dong, Sixian Li, Changhao Jiang, Shihan Dou, Zhiheng Xi, Enyu Zhou, Jixuan Huang, Hui Li, Jingjing Gong et al. Published: 2026-01-19 Categories: cs.RO, cs.CL, cs.CV arXiv: https://arxiv.org/abs/2601.12799v1 Humanoid robots are capable of performing various actions such as greeting, dancing and even backflipping. However, these motions are often hard-coded or specifically trained, which limits their versatility. In this work, we present FRoM-W1, an open-source framework designed to achieve general humanoid whole-body motion control using natural language. To universally understand natural language and generate corresponding motions, as well as enable various humanoid robots to stably execute these motions in the physical world under gravity, FRoM-W1 operates in two stages: (a) H-GPT: utilizing massive human data, a large-scale language-driven human whole-body motion generation model is trained to generate diverse natural behaviors. We further leverage the Chain-of-Thought technique to improve the model's generalization in instruction understanding. (b) H-ACT: After retargeting generated human whole-body motions into robot-specific actions, a motion controller that is pretrained and further fine-tuned through reinforcement learning in physical simulation enables humanoid robots to accurately and stably perform corresponding actions. It is then deployed on real robots via a modular simulation-to-reality module. We extensively evaluate FRoM-W1 on Unitree H1 and G1 robots. Results demonstrate superior performance on the HumanML3D-X benchmark for human whole-body motion generation, and our introduced reinforcement learning fine-tuning consistently improves both motion tracking accuracy and task success rates of these humanoid robots. We open-source the entire FRoM-W1 framework and hope it will advance the development of humanoid intelligence. --- ### PhyG-MoE: A Physics-Guided Mixture-of-Experts Framework for Energy-Efficient GNSS Interference Recognition Authors: Zhihan Zeng, Yang Zhao, Kaihe Wang, Dusit Niyato, Yue Xiu, Lu Chen, Zhongpei Zhang, Ning Wei Published: 2026-01-19 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.12798v1 Complex electromagnetic interference increasingly compromises Global Navigation Satellite Systems (GNSS), threatening the reliability of Space-Air-Ground Integrated Networks (SAGIN). Although deep learning has advanced interference recognition, current static models suffer from a \textbf{fundamental limitation}: they impose a fixed computational topology regardless of the input's physical entropy. This rigidity leads to severe resource mismatch, where simple primitives consume the same processing cost as chaotic, saturated mixtures. To resolve this, this paper introduces PhyG-MoE (Physics-Guided Mixture-of-Experts), a framework designed to \textbf{dynamically align model capacity with signal complexity}. Unlike static architectures, the proposed system employs a spectrum-based gating mechanism that routes signals based on their spectral feature entanglement. A high-capacity TransNeXt expert is activated on-demand to disentangle complex features in saturated scenarios, while lightweight experts handle fundamental signals to minimize latency. Evaluations on 21 jamming categories demonstrate that PhyG-MoE achieves an overall accuracy of 97.58\%. By resolving the intrinsic conflict between static computing and dynamic electromagnetic environments, the proposed framework significantly reduces computational overhead without performance degradation, offering a viable solution for resource-constrained cognitive receivers. --- ### Combating Noisy Labels through Fostering Self- and Neighbor-Consistency Authors: Zeren Sun, Yazhou Yao, Tongliang Liu, Zechao Li, Fumin Shen, Jinhui Tang Published: 2026-01-19 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.12795v1 Label noise is pervasive in various real-world scenarios, posing challenges in supervised deep learning. Deep networks are vulnerable to such label-corrupted samples due to the memorization effect. One major stream of previous methods concentrates on identifying clean data for training. However, these methods often neglect imbalances in label noise across different mini-batches and devote insufficient attention to out-of-distribution noisy data. To this end, we propose a noise-robust method named Jo-SNC (\textbf{Jo}int sample selection and model regularization based on \textbf{S}elf- and \textbf{N}eighbor-\textbf{C}onsistency). Specifically, we propose to employ the Jensen-Shannon divergence to measure the ``likelihood'' of a sample being clean or out-of-distribution. This process factors in the nearest neighbors of each sample to reinforce the reliability of clean sample identification. We design a self-adaptive, data-driven thresholding scheme to adjust per-class selection thresholds. While clean samples undergo conventional training, detected in-distribution and out-of-distribution noisy samples are trained following partial label learning and negative learning, respectively. Finally, we advance the model performance further by proposing a triplet consistency regularization that promotes self-prediction consistency, neighbor-prediction consistency, and feature consistency. Extensive experiments on various benchmark datasets and comprehensive ablation studies demonstrate the effectiveness and superiority of our approach over existing state-of-the-art methods. --- ### SKANet: A Cognitive Dual-Stream Framework with Adaptive Modality Fusion for Robust Compound GNSS Interference Classification Authors: Zhihan Zeng, Yang Zhao, Kaihe Wang, Dusit Niyato, Hongyuan Shu, Junchu Zhao, Yanjun Huang, Yue Xiu, Zhongpei Zhang, Ning Wei Published: 2026-01-19 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.12791v1 As the electromagnetic environment becomes increasingly complex, Global Navigation Satellite Systems (GNSS) face growing threats from sophisticated jamming interference. Although Deep Learning (DL) effectively identifies basic interference, classifying compound interference remains difficult due to the superposition of diverse jamming sources. Existing single-domain approaches often suffer from performance degradation because transient burst signals and continuous global signals require conflicting feature extraction scales. We propose the Selective Kernel and Asymmetric convolution Network(SKANet), a cognitive deep learning framework built upon a dual-stream architecture that integrates Time-Frequency Images (TFIs) and Power Spectral Density (PSD). Distinct from conventional fusion methods that rely on static receptive fields, the proposed architecture incorporates a Multi-Branch Selective Kernel (SK) module combined with Asymmetric Convolution Blocks (ACBs). This mechanism enables the network to dynamically adjust its receptive fields, acting as an adaptive filter that simultaneously captures micro-scale transient features and macro-scale spectral trends within entangled compound signals. To complement this spatial-temporal adaptation, a Squeeze-and-Excitation (SE) mechanism is integrated at the fusion stage to adaptively recalibrate the contribution of heterogeneous features from each modality. Evaluations on a dataset of 405,000 samples demonstrate that SKANet achieves an overall accuracy of 96.99\%, exhibiting superior robustness for compound jamming classification, particularly under low Jamming-to-Noise Ratio (JNR) regimes. --- ### Distilling Time Series Foundation Models for Efficient Forecasting Authors: Yuqi Li, Kuiye Ding, Chuanguang Yang, Szu-Yu Chen, Yingli Tian Published: 2026-01-19 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2601.12785v1 Time Series foundation models (TSFMs) deliver strong forecasting performance through large-scale pretraining, but their large parameter sizes make deployment costly. While knowledge distillation offers a natural and effective approach for model compression, techniques developed for general machine learning tasks are not directly applicable to time series forecasting due to the unique characteristics. To address this, we present DistilTS, the first distillation framework specifically designed for TSFMs. DistilTS addresses two key challenges: (1) task difficulty discrepancy, specific to forecasting, where uniform weighting makes optimization dominated by easier short-term horizons, while long-term horizons receive weaker supervision; and (2) architecture discrepancy, a general challenge in distillation, for which we design an alignment mechanism in the time series forecasting. To overcome these issues, DistilTS introduces horizon-weighted objectives to balance learning across horizons, and a temporal alignment strategy that reduces architectural mismatch, enabling compact models. Experiments on multiple benchmarks demonstrate that DistilTS achieves forecasting performance comparable to full-sized TSFMs, while reducing parameters by up to 1/150 and accelerating inference by up to 6000x. Code is available at: https://github.com/itsnotacie/DistilTS-ICASSP2026. --- ### VIRO: Robust and Efficient Neuro-Symbolic Reasoning with Verification for Referring Expression Comprehension Authors: Hyejin Park, Junhyuk Kwon, Suha Kwak, Jungseul Ok Published: 2026-01-19 Categories: cs.AI, cs.CV arXiv: https://arxiv.org/abs/2601.12781v2 Referring Expression Comprehension (REC) aims to localize the image region corresponding to a natural language query. Recent neuro-symbolic REC approaches leverage large language models (LLMs) and vision-language models (VLMs) to perform compositional reasoning, decomposing queries into structured programs and executing them step-by-step. While such approaches achieve interpretable reasoning and strong zero-shot generalization, they assume that intermediate reasoning steps are accurate. However, this assumption causes cascading errors: false detections and invalid relations propagate through the reasoning chain, yielding high-confidence false positives even when no target is present in the image. To address this limitation, we introduce Verification-Integrated Reasoning Operators (VIRO), a neuro-symbolic framework that embeds lightweight operator-level verifiers within reasoning steps. Each operator executes and validates its output, such as object existence or spatial relationships, allowing the system to robustly handle no-target cases through verification-aware abstention. Our framework achieves state-of-the-art performance, reaching 61.1% balanced accuracy across target-present and no-target settings, and demonstrates generalization to real-world egocentric data. VIRO also shows high reliability with a program failure rate of at most 0.3%, efficient per-query runtime, and scalability through decoupled program generation and execution. --- ### Open Vocabulary Panoptic Segmentation With Retrieval Augmentation Authors: Nafis Sadeq, Qingfeng Liu, Mostafa El-Khamy Published: 2026-01-19 Categories: cs.CV, cs.CL arXiv: https://arxiv.org/abs/2601.12779v1 Given an input image and set of class names, panoptic segmentation aims to label each pixel in an image with class labels and instance labels. In comparison, Open Vocabulary Panoptic Segmentation aims to facilitate the segmentation of arbitrary classes according to user input. The challenge is that a panoptic segmentation system trained on a particular dataset typically does not generalize well to unseen classes beyond the training data. In this work, we propose RetCLIP, a retrieval-augmented panoptic segmentation method that improves the performance of unseen classes. In particular, we construct a masked segment feature database using paired image-text data. At inference time, we use masked segment features from the input image as query keys to retrieve similar features and associated class labels from the database. Classification scores for the masked segment are assigned based on the similarity between query features and retrieved features. The retrieval-based classification scores are combined with CLIP-based scores to produce the final output. We incorporate our solution with a previous SOTA method (FC-CLIP). When trained on COCO, the proposed method demonstrates 30.9 PQ, 19.3 mAP, 44.0 mIoU on the ADE20k dataset, achieving +4.5 PQ, +2.5 mAP, +10.0 mIoU absolute improvement over the baseline. --- ### Eddy-Resolving Global Ocean Forecasting with Multi-Scale Graph Neural Networks Authors: Yuta Hirabayashi, Daisuke Matusoka, Konobu Kimura Published: 2026-01-19 Categories: cs.LG arXiv: https://arxiv.org/abs/2601.12775v1 Research on data-driven ocean models has progressed rapidly in recent years; however, the application of these models to global eddy-resolving ocean forecasting remains limited. The accurate representation of ocean dynamics across a wide range of spatial scales remains a major challenge in such applications. This study proposes a multi-scale graph neural network-based ocean model for 10-day global forecasting that improves short-term prediction skill and enhances the representation of multi-scale ocean variability. The model employs an encoder-processor-decoder architecture and uses two spherical meshes with different resolutions to better capture the multi-scale nature of ocean dynamics. In addition, the model incorporates surface atmospheric variables along with ocean state variables as node inputs to improve short-term prediction accuracy by representing atmospheric forcing. Evaluation using surface kinetic energy spectra and case studies shows that the model accurately represents a broad range of spatial scales, while root mean square error comparisons demonstrate improved skill in short-term predictions. These results indicate that the proposed model delivers more accurate short-term forecasts and improved representation of multi-scale ocean dynamics, thereby highlighting its potential to advance data-driven, eddy-resolving global ocean forecasting. --- ### Who Does This Name Remind You of ? Nationality Prediction via Large Language Model Associative Memory Authors: Keito Inoshita Published: 2026-01-19 Categories: cs.CL arXiv: https://arxiv.org/abs/2601.12771v2 Large language models (LLMs) possess extensive world knowledge, yet methods for effectively eliciting this knowledge remain underexplored. Nationality and region prediction tasks require understanding of not only linguistic features but also cultural and historical background, making LLM world knowledge particularly valuable. However, conventional LLM prompting methods rely on direct reasoning approaches, which have limitations in applying abstract linguistic rules. We propose LLM Associative Memory Agents (LAMA), a novel framework that leverages LLM world knowledge as associative memory. Rather than directly inferring nationality from names, LAMA recalls famous individuals with the same name and aggregates their nationalities through indirect reasoning. A dual-agent architecture comprising a Person Agent and a Media Agent, specialized in different knowledge domains, recalls famous individuals in parallel, generating Top-1 predictions through voting and Top-K predictions through conditional completion. On a 99-country nationality prediction task, LAMA achieved 0.817 accuracy, substantially outperforming conventional LLM prompting methods and neural models. Our experiments reveal that LLMs exhibit higher reliability in recalling concrete examples than in abstract reasoning, that recall-based approaches are robust to low-frequency nationalities independent of data frequency distributions, and that the dual-agent architecture functions complementarily to produce synergistic effects. These results demonstrate the effectiveness of a new multi-agent system that retrieves and aggregates LLM knowledge rather than prompting reasoning. --- ### One-Shot Feed-Forward 360$^{\circ}$ Animatable Avatar via Inpainted UV-Space Gaussian Modeling Authors: Shuling Zhao, Dan Xu Published: 2026-01-19 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.12770v2 Building one-shot 3D animatable head avatars is an important yet challenging problem. Existing methods generally collapse under large camera pose variations, compromising the realism of 3D avatars. In this work, we propose a new framework to tackle the novel setting of one-shot 3D full-head animatable avatar reconstruction in a single forward pass via inpainted UV-space Gaussian modeling, enabling 360$^\circ$ rendering views and real-time animation. To facilitate efficient animation control, we model 3D head avatars with Gaussian primitives embedded on the surface of a parametric face model within the UV space, and project the input image features to the UV space, resulting in incomplete local UV feature maps. To inpaint the missing regions, we obtain knowledge of full-head geometry and textures from rich 3D full-head priors within a pretrained 3D generative adversarial network (GAN) for global full-head feature extraction and multi-view supervision. Specifically, to enhance the fidelity of 3D reconstruction during inpainting, we take advantage of the symmetric nature of the UV space and human faces to fuse incomplete yet detailed local UV feature maps with the extracted global full-head textures, resulting in inpainted UV Gaussian attribute maps for avatar modeling. Extensive experiments demonstrate that our method is the first to achieve high-quality 3D full-head animatable avatar modeling, significantly improving side and back views while outperforming state-of-the-art animation approaches, thereby improving the realism of 3D animatable avatars. --- ### Delving Deeper: Hierarchical Visual Perception for Robust Video-Text Retrieval Authors: Zequn Xie, Boyun Zhang, Yuxiao Lin, Tao Jin Published: 2026-01-19 Categories: cs.CV, cs.MM arXiv: https://arxiv.org/abs/2601.12768v1 Video-text retrieval (VTR) aims to locate relevant videos using natural language queries. Current methods, often based on pre-trained models like CLIP, are hindered by video's inherent redundancy and their reliance on coarse, final-layer features, limiting matching accuracy. To address this, we introduce the HVP-Net (Hierarchical Visual Perception Network), a framework that mines richer video semantics by extracting and refining features from multiple intermediate layers of a vision encoder. Our approach progressively distills salient visual concepts from raw patch-tokens at different semantic levels, mitigating redundancy while preserving crucial details for alignment. This results in a more robust video representation, leading to new state-of-the-art performance on challenging benchmarks including MSRVTT, DiDeMo, and ActivityNet. Our work validates the effectiveness of exploiting hierarchical features for advancing video-text retrieval. Our codes are available at https://github.com/boyun-zhang/HVP-Net. --- ### Spatial-VLN: Zero-Shot Vision-and-Language Navigation With Explicit Spatial Perception and Exploration Authors: Lu Yue, Yue Fan, Shiwei Lian, Yu Zhao, Jiaxin Yu, Liang Xie, Feitian Zhang Published: 2026-01-19 Categories: cs.CV, eess.SY arXiv: https://arxiv.org/abs/2601.12766v1 Zero-shot Vision-and-Language Navigation (VLN) agents leveraging Large Language Models (LLMs) excel in generalization but suffer from insufficient spatial perception. Focusing on complex continuous environments, we categorize key perceptual bottlenecks into three spatial challenges: door interaction,multi-room navigation, and ambiguous instruction execution, where existing methods consistently suffer high failure rates. We present Spatial-VLN, a perception-guided exploration framework designed to overcome these challenges. The framework consists of two main modules. The Spatial Perception Enhancement (SPE) module integrates panoramic filtering with specialized door and region experts to produce spatially coherent, cross-view consistent perceptual representations. Building on this foundation, our Explored Multi-expert Reasoning (EMR) module uses parallel LLM experts to address waypoint-level semantics and region-level spatial transitions. When discrepancies arise between expert predictions, a query-and-explore mechanism is activated, prompting the agent to actively probe critical areas and resolve perceptual ambiguities. Experiments on VLN-CE demonstrate that Spatial VLN achieves state-of-the-art performance using only low-cost LLMs. Furthermore, to validate real-world applicability, we introduce a value-based waypoint sampling strategy that effectively bridges the Sim2Real gap. Extensive real-world evaluations confirm that our framework delivers superior generalization and robustness in complex environments. Our codes and videos are available at https://yueluhhxx.github.io/Spatial-VLN-web/. --- ### Towards Unbiased Source-Free Object Detection via Vision Foundation Models Authors: Zhi Cai, Yingjie Gao, Yanan Zhang, Xinzhu Ma, Di Huang Published: 2026-01-19 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.12765v1 Source-Free Object Detection (SFOD) has garnered much attention in recent years by eliminating the need of source-domain data in cross-domain tasks, but existing SFOD methods suffer from the Source Bias problem, i.e. the adapted model remains skewed towards the source domain, leading to poor generalization and error accumulation during self-training. To overcome this challenge, we propose Debiased Source-free Object Detection (DSOD), a novel VFM-assisted SFOD framework that can effectively mitigate source bias with the help of powerful VFMs. Specifically, we propose Unified Feature Injection (UFI) module that integrates VFM features into the CNN backbone through Simple-Scale Extension (SSE) and Domain-aware Adaptive Weighting (DAAW). Then, we propose Semantic-aware Feature Regularization (SAFR) that constrains feature learning to prevent overfitting to source domain characteristics. Furthermore, we propose a VFM-free variant, termed DSOD-distill for computation-restricted scenarios through a novel Dual-Teacher distillation scheme. Extensive experiments on multiple benchmarks demonstrate that DSOD outperforms state-of-the-art SFOD methods, achieving 48.1% AP on Normal-to-Foggy weather adaptation, 39.3% AP on Cross-scene adaptation, and 61.4% AP on Synthetic-to-Real adaptation. --- ### Teaching LLMs to Learn Tool Trialing and Execution through Environment Interaction Authors: Xingjie Gao, Pengcheng Huang, Zhenghao Liu, Yukun Yan, Shuo Wang, Zulong Chen, Chen Qian, Ge Yu, Yu Gu Published: 2026-01-19 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2601.12762v1 Equipping Large Language Models (LLMs) with external tools enables them to solve complex real-world problems. However, the robustness of existing methods remains a critical challenge when confronting novel or evolving tools. Existing trajectory-centric paradigms primarily rely on memorizing static solution paths during training, which limits the ability of LLMs to generalize tool usage to newly introduced or previously unseen tools. In this paper, we propose ToolMaster, a framework that shifts tool use from imitating golden tool-calling trajectories to actively learning tool usage through interaction with the environment. To optimize LLMs for tool planning and invocation, ToolMaster adopts a trial-and-execution paradigm, which trains LLMs to first imitate teacher-generated trajectories containing explicit tool trials and self-correction, followed by reinforcement learning to coordinate the trial and execution phases jointly. This process enables agents to autonomously explore correct tool usage by actively interacting with environments and forming experiential knowledge that benefits tool execution. Experimental results demonstrate that ToolMaster significantly outperforms existing baselines in terms of generalization and robustness across unseen or unfamiliar tools. All code and data are available at https://github.com/NEUIR/ToolMaster. --- ### Moaw: Unleashing Motion Awareness for Video Diffusion Models Authors: Tianqi Zhang, Ziyi Wang, Wenzhao Zheng, Weiliang Chen, Yuanhui Huang, Zhengyang Huang, Jie Zhou, Jiwen Lu Published: 2026-01-19 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.12761v1 Video diffusion models, trained on large-scale datasets, naturally capture correspondences of shared features across frames. Recent works have exploited this property for tasks such as optical flow prediction and tracking in a zero-shot setting. Motivated by these findings, we investigate whether supervised training can more fully harness the tracking capability of video diffusion models. To this end, we propose Moaw, a framework that unleashes motion awareness for video diffusion models and leverages it to facilitate motion transfer. Specifically, we train a diffusion model for motion perception, shifting its modality from image-to-video generation to video-to-dense-tracking. We then construct a motion-labeled dataset to identify features that encode the strongest motion information, and inject them into a structurally identical video generation model. Owing to the homogeneity between the two networks, these features can be naturally adapted in a zero-shot manner, enabling motion transfer without additional adapters. Our work provides a new paradigm for bridging generative modeling and motion understanding, paving the way for more unified and controllable video learning frameworks. --- ### VISPA: Pluralistic Alignment via Automatic Value Selection and Activation Authors: Shenyan Zheng, Jiayou Zhong, Anudeex Shetty, Heng Ji, Preslav Nakov, Usman Naseem Published: 2026-01-19 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2601.12758v1 As large language models are increasingly used in high-stakes domains, it is essential that their outputs reflect not average} human preference, rather range of varying perspectives. Achieving such pluralism, however, remains challenging. Existing approaches consider limited values or rely on prompt-level interventions, lacking value control and representation. To address this, we introduce VISPA, a training-free pluralistic alignment framework, that enables direct control over value expression by dynamic selection and internal model activation steering. Across extensive empirical studies spanning multiple models and evaluation settings, we show VISPA is performant across all pluralistic alignment modes in healthcare and beyond. Further analysis reveals VISPA is adaptable with different steering initiations, model, and/or values. These results suggest that pluralistic alignment can be achieved through internal activation mechanisms, offering a scalable path toward language models that serves all. --- ### PAIR-SAFE: A Paired-Agent Approach for Runtime Auditing and Refining AI-Mediated Mental Health Support Authors: Jiwon Kim, Violeta J. Rodriguez, Dong Whi Yoo, Eshwar Chandrasekharan, Koustuv Saha Published: 2026-01-19 Categories: cs.HC, cs.AI, cs.CL, cs.CY arXiv: https://arxiv.org/abs/2601.12754v1 Large language models (LLMs) are increasingly used for mental health support, yet they can produce responses that are overly directive, inconsistent, or clinically misaligned, particularly in sensitive or high-risk contexts. Existing approaches to mitigating these risks largely rely on implicit alignment through training or prompting, offering limited transparency and runtime accountability. We introduce PAIR-SAFE, a paired-agent framework for auditing and refining AI-generated mental health support that integrates a Responder agent with a supervisory Judge agent grounded in the clinically validated Motivational Interviewing Treatment Integrity (MITI-4) framework. The Judgeaudits each response and provides structuredALLOW or REVISE decisions that guide runtime response refinement. We simulate counseling interactions using a support-seeker simulator derived from human-annotated motivational interviewing data. We find that Judge-supervised interactions show significant improvements in key MITI dimensions, including Partnership, Seek Collaboration, and overall Relational quality. Our quantitative findings are supported by qualitative expert evaluation, which further highlights the nuances of runtime supervision. Together, our results reveal that such pairedagent approach can provide clinically grounded auditing and refinement for AI-assisted conversational mental health support. --- ### SoundPlot: An Open-Source Framework for Birdsong Acoustic Analysis and Neural Synthesis with Interactive 3D Visualization Authors: Naqcho Ali Mehdi, Mohammad Adeel, Aizaz Ali Larik Published: 2026-01-19 Categories: cs.SD, cs.LG arXiv: https://arxiv.org/abs/2601.12752v1 We present SoundPlot, an open-source framework for analyzing avian vocalizations through acoustic feature extraction, dimensionality reduction, and neural audio synthesis. The system transforms audio signals into a multi-dimensional acoustic feature space, enabling real-time visualization of temporal dynamics in 3D using web-based interactive graphics. Our framework implements a complete analysis-synthesis pipeline that extracts spectral features (centroid, bandwidth, contrast), pitch contours via probabilistic YIN (pYIN), and mel-frequency cepstral coefficients (MFCCs), mapping them to a unified timbre space for visualization. Audio reconstruction employs the Griffin-Lim phase estimation algorithm applied to mel spectrograms. The accompanying Three.js-based interface provides dual-viewport visualization comparing original and synthesized audio trajectories with independent playback controls. We demonstrate the framework's capabilities through comprehensive waveform analysis, spectrogram comparisons, and feature space evaluation using Principal Component Analysis (PCA). Quantitative evaluation shows mel spectrogram correlation scores exceeding 0.92, indicating high-fidelity preservation of perceptual acoustic structure. SoundPlot is released under the MIT License to facilitate research in bioacoustics, audio signal processing, and computational ethology. --- ### A Boolean Function-Theoretic Framework for Expressivity in GNNs with Applications to Fair Graph Mining Authors: Manjish Pal Published: 2026-01-19 Categories: cs.LG arXiv: https://arxiv.org/abs/2601.12751v1 We propose a novel expressivity framework for Graph Neural Networks (GNNs) grounded in Boolean function theory, enabling a fine-grained analysis of their ability to capture complex subpopulation structures. We introduce the notion of \textit{Subpopulation Boolean Isomorphism} (SBI) as an invariant that strictly subsumes existing expressivity measures such as Weisfeiler-Lehman (WL), biconnectivity-based, and homomorphism-based frameworks. Our theoretical results identify Fourier degree, circuit class (AC$^0$, NC$^1$), and influence as key barriers to expressivity in fairness-aware GNNs. We design a circuit-traversal-based fairness algorithm capable of handling subpopulations defined by high-complexity Boolean functions, such as parity, which break existing baselines. Experiments on real-world graphs show that our method achieves low fairness gaps across intersectional groups where state-of-the-art methods fail, providing the first principled treatment of GNN expressivity tailored to fairness. --- ### Towards Robust Process Reward Modeling via Noise-aware Learning Authors: Bin Xie, Bingbing Xu, Xueyun Tian, Yilin Chen, Huawei Shen Published: 2026-01-19 Categories: cs.CL arXiv: https://arxiv.org/abs/2601.12748v1 Process Reward Models (PRMs) have achieved strong results in complex reasoning, but are bottlenecked by costly process-level supervision. A widely used alternative, Monte Carlo Estimation (MCE), defines process rewards as the probability that a policy model reaches the correct final answer from a given reasoning step. However, step correctness is an intrinsic property of the reasoning trajectory, and should be invariant to policy choice. Our empirical findings show that MCE producing policy-dependent rewards that induce label noise, including false positives that reward incorrect steps and false negatives that penalize correct ones. To address above challenges, we propose a two-stage framework to mitigate noisy supervision. In the labeling stage, we introduce a reflection-aware label correction mechanism that uses a large language model (LLM) as a judge to detect reflection and self-correction behaviors related to the current reasoning step, thereby suppressing overestimated rewards. In the training stage, we further propose a \underline{\textbf{N}}oise-\underline{\textbf{A}}ware \underline{\textbf{I}}terative \underline{\textbf{T}}raining framework that enables the PRM to progressively refine noisy labels based on its own confidence. Extensive Experiments show that our method substantially improves step-level correctness discrimination, achieving up to a 27\% absolute gain in average F1 over PRMs trained with noisy supervision. --- ### SSPFormer: Self-Supervised Pretrained Transformer for MRI Images Authors: Jingkai Li, Xiaoze Tian, Yuhang Shen, Jia Wang, Dianjie Lu, Guijuan Zhang, Zhuoran Zheng Published: 2026-01-19 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.12747v1 The pre-trained transformer demonstrates remarkable generalization ability in natural image processing. However, directly transferring it to magnetic resonance images faces two key challenges: the inability to adapt to the specificity of medical anatomical structures and the limitations brought about by the privacy and scarcity of medical data. To address these issues, this paper proposes a Self-Supervised Pretrained Transformer (SSPFormer) for MRI images, which effectively learns domain-specific feature representations of medical images by leveraging unlabeled raw imaging data. To tackle the domain gap and data scarcity, we introduce inverse frequency projection masking, which prioritizes the reconstruction of high-frequency anatomical regions to enforce structure-aware representation learning. Simultaneously, to enhance robustness against real-world MRI artifacts, we employ frequency-weighted FFT noise enhancement that injects physiologically realistic noise into the Fourier domain. Together, these strategies enable the model to learn domain-invariant and artifact-robust features directly from raw scans. Through extensive experiments on segmentation, super-resolution, and denoising tasks, the proposed SSPFormer achieves state-of-the-art performance, fully verifying its ability to capture fine-grained MRI image fidelity and adapt to clinical application requirements. --- ### A Graph Prompt Fine-Tuning Method for WSN Spatio-Temporal Correlation Anomaly Detection Authors: Miao Ye, Jing Cui, Yuan huang, Qian He, Yong Wang, Jiwen Zhang Published: 2026-01-19 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2601.12745v1 Anomaly detection of multi-temporal modal data in Wireless Sensor Network (WSN) can provide an important guarantee for reliable network operation. Existing anomaly detection methods in multi-temporal modal data scenarios have the problems of insufficient extraction of spatio-temporal correlation features, high cost of anomaly sample category annotation, and imbalance of anomaly samples. In this paper, a graph neural network anomaly detection backbone network incorporating spatio-temporal correlation features and a multi-task self-supervised training strategy of "pre-training - graph prompting - fine-tuning" are designed for the characteristics of WSN graph structure data. First, the anomaly detection backbone network is designed by improving the Mamba model based on a multi-scale strategy and inter-modal fusion method, and combining it with a variational graph convolution module, which is capable of fully extracting spatio-temporal correlation features in the multi-node, multi-temporal modal scenarios of WSNs. Secondly, we design a three-subtask learning "pre-training" method with no-negative comparative learning, prediction, and reconstruction to learn generic features of WSN data samples from unlabeled data, and design a "graph prompting-fine-tuning" mechanism to guide the pre-trained self-supervised learning. The model is fine-tuned through the "graph prompting-fine-tuning" mechanism to guide the pre-trained self-supervised learning model to complete the parameter fine-tuning, thereby reducing the training cost and enhancing the detection generalization performance. The F1 metrics obtained from experiments on the public dataset and the actual collected dataset are up to 91.30% and 92.31%, respectively, which provides better detection performance and generalization ability than existing methods designed by the method. --- ### Vision Language Models for Optimization-Driven Intent Processing in Autonomous Networks Authors: Tasnim Ahmed, Yifan Zhu, Salimur Choudhury Published: 2026-01-19 Categories: cs.AI, cs.NI, cs.SE arXiv: https://arxiv.org/abs/2601.12744v1 Intent-Based Networking (IBN) allows operators to specify high-level network goals rather than low-level configurations. While recent work demonstrates that large language models can automate configuration tasks, a distinct class of intents requires generating optimization code to compute provably optimal solutions for traffic engineering, routing, and resource allocation. Current systems assume text-based intent expression, requiring operators to enumerate topologies and parameters in prose. Network practitioners naturally reason about structure through diagrams, yet whether Vision-Language Models (VLMs) can process annotated network sketches into correct optimization code remains unexplored. We present IntentOpt, a benchmark of 85 optimization problems across 17 categories, evaluating four VLMs (GPT-5-Mini, Claude-Haiku-4.5, Gemini-2.5-Flash, Llama-3.2-11B-Vision) under three prompting strategies on multimodal versus text-only inputs. Our evaluation shows that visual parameter extraction reduces execution success by 12-21 percentage points (pp), with GPT-5-Mini dropping from 93% to 72%. Program-of-thought prompting decreases performance by up to 13 pp, and open-source models lag behind closed-source ones, with Llama-3.2-11B-Vision reaching 18% compared to 75% for GPT-5-Mini. These results establish baseline capabilities and limitations of current VLMs for optimization code generation within an IBN system. We also demonstrate practical feasibility through a case study that deploys VLM-generated code to network testbed infrastructure using Model Context Protocol. --- ### AirHunt: Bridging VLM Semantics and Continuous Planning for Efficient Aerial Object Navigation Authors: Xuecheng Chen, Zongzhuo Liu, Jianfa Ma, Bang Du, Tiantian Zhang, Xueqian Wang, Boyu Zhou Published: 2026-01-19 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2601.12742v1 Recent advances in large Vision-Language Models (VLMs) have provided rich semantic understanding that empowers drones to search for open-set objects via natural language instructions. However, prior systems struggle to integrate VLMs into practical aerial systems due to orders-of-magnitude frequency mismatch between VLM inference and real-time planning, as well as VLMs' limited 3D scene understanding. They also lack a unified mechanism to balance semantic guidance with motion efficiency in large-scale environments. To address these challenges, we present AirHunt, an aerial object navigation system that efficiently locates open-set objects with zero-shot generalization in outdoor environments by seamlessly fusing VLM semantic reasoning with continuous path planning. AirHunt features a dual-pathway asynchronous architecture that establishes a synergistic interface between VLM reasoning and path planning, enabling continuous flight with adaptive semantic guidance that evolves through motion. Moreover, we propose an active dual-task reasoning module that exploits geometric and semantic redundancy to enable selective VLM querying, and a semantic-geometric coherent planning module that dynamically reconciles semantic priorities and motion efficiency in a unified framework, enabling seamless adaptation to environmental heterogeneity. We evaluate AirHunt across diverse object navigation tasks and environments, demonstrating a higher success rate with lower navigation error and reduced flight time compared to state-of-the-art methods. Real-world experiments further validate AirHunt's practical capability in complex and challenging environments. Code and dataset will be made publicly available before publication. --- ### TreeWriter: AI-Assisted Hierarchical Planning and Writing for Long-Form Documents Authors: Zijian Zhang, Fangshi Du, Xingjian Liu, Pan Chen, Oliver Huang, Runlong Ye, Michael Liut, Alán Aspuru-Guzik Published: 2026-01-19 Categories: cs.HC, cs.AI arXiv: https://arxiv.org/abs/2601.12740v1 Long documents pose many challenges to current intelligent writing systems. These include maintaining consistency across sections, sustaining efficient planning and writing as documents become more complex, and effectively providing and integrating AI assistance to the user. Existing AI co-writing tools offer either inline suggestions or limited structured planning, but rarely support the entire writing process that begins with high-level ideas and ends with polished prose, in which many layers of planning and outlining are needed. Here, we introduce TreeWriter, a hierarchical writing system that represents documents as trees and integrates contextual AI support. TreeWriter allows authors to create, save, and refine document outlines at multiple levels, facilitating drafting, understanding, and iterative editing of long documents. A built-in AI agent can dynamically load relevant content, navigate the document hierarchy, and provide context-aware editing suggestions. A within-subject study (N=12) comparing TreeWriter with Google Docs + Gemini on long-document editing and creative writing tasks shows that TreeWriter improves idea exploration/development, AI helpfulness, and perceived authorial control. A two-month field deployment (N=8) further demonstrated that hierarchical organization supports collaborative writing. Our findings highlight the potential of hierarchical, tree-structured editors with integrated AI support and provide design guidelines for future AI-assisted writing tools that balance automation with user agency. --- ### KaoLRM: Repurposing Pre-trained Large Reconstruction Models for Parametric 3D Face Reconstruction Authors: Qingtian Zhu, Xu Cao, Zhixiang Wang, Yinqiang Zheng, Takafumi Taketomi Published: 2026-01-19 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.12736v1 We propose KaoLRM to re-target the learned prior of the Large Reconstruction Model (LRM) for parametric 3D face reconstruction from single-view images. Parametric 3D Morphable Models (3DMMs) have been widely used for facial reconstruction due to their compact and interpretable parameterization, yet existing 3DMM regressors often exhibit poor consistency across varying viewpoints. To address this, we harness the pre-trained 3D prior of LRM and incorporate FLAME-based 2D Gaussian Splatting into LRM's rendering pipeline. Specifically, KaoLRM projects LRM's pre-trained triplane features into the FLAME parameter space to recover geometry, and models appearance via 2D Gaussian primitives that are tightly coupled to the FLAME mesh. The rich prior enables the FLAME regressor to be aware of the 3D structure, leading to accurate and robust reconstructions under self-occlusions and diverse viewpoints. Experiments on both controlled and in-the-wild benchmarks demonstrate that KaoLRM achieves superior reconstruction accuracy and cross-view consistency, while existing methods remain sensitive to viewpoint variations. The code is released at https://github.com/CyberAgentAILab/KaoLRM. --- ### A Shared Geometry of Difficulty in Multilingual Language Models Authors: Stefano Civelli, Pietro Bernardelle, Nicolò Brunello, Gianluca Demartini Published: 2026-01-19 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2601.12731v1 Predicting problem-difficulty in large language models (LLMs) refers to estimating how difficult a task is according to the model itself, typically by training linear probes on its internal representations. In this work, we study the multilingual geometry of problem-difficulty in LLMs by training linear probes using the AMC subset of the Easy2Hard benchmark, translated into 21 languages. We found that difficulty-related signals emerge at two distinct stages of the model internals, corresponding to shallow (early-layers) and deep (later-layers) internal representations, that exhibit functionally different behaviors. Probes trained on deep representations achieve high accuracy when evaluated on the same language but exhibit poor cross-lingual generalization. In contrast, probes trained on shallow representations generalize substantially better across languages, despite achieving lower within-language performance. Together, these results suggest that LLMs first form a language-agnostic representation of problem difficulty, which subsequently becomes language-specific. This closely aligns with existing findings in LLM interpretability showing that models tend to operate in an abstract conceptual space before producing language-specific outputs. We demonstrate that this two-stage representational process extends beyond semantic content to high-level meta-cognitive properties such as problem-difficulty estimation. --- ### Distribution-Centric Policy Optimization Dominates Exploration-Exploitation Trade-off Authors: Zhaochun Li, Chen Wang, Jionghao Bai, Shisheng Cui, Ge Lan, Zhou Zhao, Yue Wang Published: 2026-01-19 Categories: cs.LG arXiv: https://arxiv.org/abs/2601.12730v1 The exploration-exploitation (EE) trade-off is a central challenge in reinforcement learning (RL) for large language models (LLMs). With Group Relative Policy Optimization (GRPO), training tends to be exploitation driven: entropy decreases monotonically, samples convergence, and exploration fades. Most existing fixes are \textbf{sample-centric}: they seek or bonus rare samples, assuming exploration comes from novel trajectories and tokens. These heuristics depend on the "luck" of informative samples, lack principled control of the policy, and often yield limited or inconsistent gains. In this work, we are the first to introduce a \textbf{distribution-centric} perspective for RL, in which exploration is always guided by a "better" target distribution, and reveal that a policy's ability to resist entropy collapse is governed by the distribution itself rather than individual samples. Building on this insight, we propose Distribution-Centric Policy Optimization (DCPO), which reformulates entropy regulation as distribution-level regularization. DCPO achieves controllable entropy fully on-policy without sampling from external distributions, enabling efficient exploration while maintaining training stability. Across multiple models and seven benchmarks, DCPO improves over GRPO by about 20\% on average. Overall, DCPO replaces sample-level heuristics with distribution-level principles, offering a theoretically grounded and flexible framework for controllable exploration and a stronger EE trade-off. The code is available in https://github.com/597358816/DCPO. --- ### DC-VLAQ: Query-Residual Aggregation for Robust Visual Place Recognition Authors: Hanyu Zhu, Zhihao Zhan, Yuhang Ming, Liang Li, Dibo Hou, Javier Civera, Wanzeng Kong Published: 2026-01-19 Categories: cs.CV, cs.RO arXiv: https://arxiv.org/abs/2601.12729v1 One of the central challenges in visual place recognition (VPR) is learning a robust global representation that remains discriminative under large viewpoint changes, illumination variations, and severe domain shifts. While visual foundation models (VFMs) provide strong local features, most existing methods rely on a single model, overlooking the complementary cues offered by different VFMs. However, exploiting such complementary information inevitably alters token distributions, which challenges the stability of existing query-based global aggregation schemes. To address these challenges, we propose DC-VLAQ, a representation-centric framework that integrates the fusion of complementary VFMs and robust global aggregation. Specifically, we first introduce a lightweight residual-guided complementary fusion that anchors representations in the DINOv2 feature space while injecting complementary semantics from CLIP through a learned residual correction. In addition, we propose the Vector of Local Aggregated Queries (VLAQ), a query--residual global aggregation scheme that encodes local tokens by their residual responses to learnable queries, resulting in improved stability and the preservation of fine-grained discriminative cues. Extensive experiments on standard VPR benchmarks, including Pitts30k, Tokyo24/7, MSLS, Nordland, SPED, and AmsterTime, demonstrate that DC-VLAQ consistently outperforms strong baselines and achieves state-of-the-art performance, particularly under challenging domain shifts and long-term appearance changes. --- ### AI-exhibited Personality Traits Can Shape Human Self-concept through Conversations Authors: Jingshu Li, Tianqi Song, Nattapat Boonprakong, Zicheng Zhu, Yitian Yang, Yi-Chieh Lee Published: 2026-01-19 Categories: cs.HC, cs.AI arXiv: https://arxiv.org/abs/2601.12727v1 Recent Large Language Model (LLM) based AI can exhibit recognizable and measurable personality traits during conversations to improve user experience. However, as human understandings of their personality traits can be affected by their interaction partners' traits, a potential risk is that AI traits may shape and bias users' self-concept of their own traits. To explore the possibility, we conducted a randomized behavioral experiment. Our results indicate that after conversations about personal topics with an LLM-based AI chatbot using GPT-4o default personality traits, users' self-concepts aligned with the AI's measured personality traits. The longer the conversation, the greater the alignment. This alignment led to increased homogeneity in self-concepts among users. We also observed that the degree of self-concept alignment was positively associated with users' conversation enjoyment. Our findings uncover how AI personality traits can shape users' self-concepts through human-AI conversation, highlighting both risks and opportunities. We provide important design implications for developing more responsible and ethical AI systems. --- ### An Evolutionary Framework for Automatic Optimization Benchmark Generation via Large Language Models Authors: Yuhiro Ono, Tomohiro Harada, Yukiya Miura Published: 2026-01-19 Categories: cs.NE, cs.AI arXiv: https://arxiv.org/abs/2601.12723v3 Optimization benchmarks play a fundamental role in assessing algorithm performance; however, existing artificial benchmarks often fail to capture the diversity and irregularity of real-world problem structures, while benchmarks derived from real-world problems are costly and difficult to construct. To address these challenges, we propose an evolutionary automatic benchmark generation framework that leverages a large language model (LLM) as a generative operator, termed the LLM-driven evolutionary benchmark generator (LLM-EBG). In this framework, the LLM serves as an evolutionary operator that generates and evolves benchmark problems within a flexible, expressive representation space. As a case study, we generate unconstrained single-objective continuous minimization problems represented as mathematical expressions designed to induce significant performance differences between a genetic algorithm (GA) and differential evolution (DE). Experimental results show that LLM-EBG successfully produces benchmark problems in which the designated target algorithm consistently outperforms the comparative algorithm in more than 80\% of trials. Furthermore, exploratory landscape analysis reveals that benchmarks favoring GA are highly sensitive to variable scaling, demonstrating that the proposed framework can generate problems with distinct geometric characteristics that reflect the intrinsic search behaviors of different optimization algorithms. --- ### Teaching Large Reasoning Models Effective Reflection Authors: Hanbin Wang, Jingwei Song, Jinpeng Li, Qi Zhu, Fei Mi, Ganqu Cui, Yasheng Wang, Lifeng Shang Published: 2026-01-19 Categories: cs.AI arXiv: https://arxiv.org/abs/2601.12720v1 Large Reasoning Models (LRMs) have recently shown impressive performance on complex reasoning tasks, often by engaging in self-reflective behaviors such as self-critique and backtracking. However, not all reflections are beneficial-many are superficial, offering little to no improvement over the original answer and incurring computation overhead. In this paper, we identify and address the problem of superficial reflection in LRMs. We first propose Self-Critique Fine-Tuning (SCFT), a training framework that enhances the model's reflective reasoning ability using only self-generated critiques. SCFT prompts models to critique their own outputs, filters high-quality critiques through rejection sampling, and fine-tunes the model using a critique-based objective. Building on this strong foundation, we further introduce Reinforcement Learning with Effective Reflection Rewards (RLERR). RLERR leverages the high-quality reflections initialized by SCFT to construct reward signals, guiding the model to internalize the self-correction process via reinforcement learning. Experiments on two challenging benchmarks, AIME2024 and AIME2025, show that SCFT and RLERR significantly improve both reasoning accuracy and reflection quality, outperforming state-of-the-art baselines. All data and codes are available at https://github.com/wanghanbinpanda/SCFT. --- ### S2DiT: Sandwich Diffusion Transformer for Mobile Streaming Video Generation Authors: Lin Zhao, Yushu Wu, Aleksei Lebedev, Dishani Lahiri, Meng Dong, Arpit Sahni, Michael Vasilkovsky, Hao Chen, Ju Hu, Aliaksandr Siarohin, Sergey Tulyakov, Yanzhi Wang et al. Published: 2026-01-19 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.12719v2 Diffusion Transformers (DiTs) have recently improved video generation quality. However, their heavy computational cost makes real-time or on-device generation infeasible. In this work, we introduce S2DiT, a Streaming Sandwich Diffusion Transformer designed for efficient, high-fidelity, and streaming video generation on mobile hardware. S2DiT generates more tokens but maintains efficiency with novel efficient attentions: a mixture of LinConv Hybrid Attention (LCHA) and Stride Self-Attention (SSA). Based on this, we uncover the sandwich design via a budget-aware dynamic programming search, achieving superior quality and efficiency. We further propose a 2-in-1 distillation framework that transfers the capacity of large teacher models (e.g., Wan 2.2-14B) to the compact few-step sandwich model. Together, S2DiT achieves quality on par with state-of-the-art server video models, while streaming at over 10 FPS on an iPhone. --- ### RSOD: Reliability-Guided Sonar Image Object Detection with Extremely Limited Labels Authors: Chengzhou Li, Ping Guo, Guanchen Meng, Qi Jia, Jinyuan Liu, Zhu Liu, Xiaokang Liu, Yu Liu, Zhongxuan Luo, Xin Fan Published: 2026-01-19 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2601.12715v1 Object detection in sonar images is a key technology in underwater detection systems. Compared to natural images, sonar images contain fewer texture details and are more susceptible to noise, making it difficult for non-experts to distinguish subtle differences between classes. This leads to their inability to provide precise annotation data for sonar images. Therefore, designing effective object detection methods for sonar images with extremely limited labels is particularly important. To address this, we propose a teacher-student framework called RSOD, which aims to fully learn the characteristics of sonar images and develop a pseudo-label strategy suitable for these images to mitigate the impact of limited labels. First, RSOD calculates a reliability score by assessing the consistency of the teacher's predictions across different views. To leverage this score, we introduce an object mixed pseudo-label method to tackle the shortage of labeled data in sonar images. Finally, we optimize the performance of the student by implementing a reliability-guided adaptive constraint. By taking full advantage of unlabeled data, the student can perform well even in situations with extremely limited labels. Notably, on the UATD dataset, our method, using only 5% of labeled data, achieves results that can compete against those of our baseline algorithm trained on 100% labeled data. We also collected a new dataset to provide more valuable data for research in the field of sonar. --- ### P2L-CA: An Effective Parameter Tuning Framework for Rehearsal-Free Multi-Label Class-Incremental Learning Authors: Songlin Dong, Jiangyang Li, Chenhao Ding, Zhiheng Ma, Haoyu Luo, Yuhang He, Yihong Gong Published: 2026-01-19 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2601.12714v1 Multi-label Class-Incremental Learning aims to continuously recognize novel categories in complex scenes where multiple objects co-occur. However, existing approaches often incur high computational costs due to full-parameter fine-tuning and substantial storage overhead from memory buffers, or they struggle to address feature confusion and domain discrepancies adequately. To overcome these limitations, we introduce P2L-CA, a parameter-efficient framework that integrates a Prompt-to-Label module with a Continuous Adapter module. The P2L module leverages class-specific prompts to disentangle multi-label representations while incorporating linguistic priors to enforce stable semantic-visual alignment. Meanwhile, the CA module employs lightweight adapters to mitigate domain gaps between pre-trained models and downstream tasks, thereby enhancing model plasticity. Extensive experiments across standard and challenging MLCIL settings on MS-COCO and PASCAL VOC show that P2L-CA not only achieves substantial improvements over state-of-the-art methods but also demonstrates strong generalization in CIL scenarios, all while requiring minimal trainable parameters and eliminating the need for memory buffers. --- ### Neurosymbolic LoRA: Why and When to Tune Weights vs. Rewrite Prompts Authors: Kevin Wang, Neel P. Bhatt, Cong Liu, Junbo Li, Runjin Chen, Yihan Xi, Timothy Barclay, Alvaro Velasquez, Ufuk Topcu, Zhangyang Wang Published: 2026-01-19 Categories: cs.AI, cs.LG, cs.SC arXiv: https://arxiv.org/abs/2601.12711v1 Large language models (LLMs) can be adapted either through numerical updates that alter model parameters or symbolic manipulations that work on discrete prompts or logical constraints. While numerical fine-tuning excels at injecting new factual knowledge, symbolic updates offer flexible control of style and alignment without retraining. We introduce a neurosymbolic LoRA framework that dynamically combines these two complementary strategies. Specifically, we present a unified monitoring signal and a reward-based classifier to decide when to employ LoRA for deeper factual reconstruction and when to apply TextGrad for token-level edits. Our approach remains memory-efficient by offloading the symbolic transformations to an external LLM only when needed. Additionally, the refined prompts produced during symbolic editing serve as high-quality, reusable training data, an important benefit in data-scarce domains like mathematical reasoning. Extensive experiments across multiple LLM backbones show that neurosymbolic LoRA consistently outperforms purely numerical or purely symbolic baselines, demonstrating superior adaptability and improved performance. Our findings highlight the value of interleaving numerical and symbolic updates to unlock a new level of versatility in language model fine-tuning. --- ### Decoding Rewards in Competitive Games: Inverse Game Theory with Entropy Regularization Authors: Junyi Liao, Zihan Zhu, Ethan Fang, Zhuoran Yang, Vahid Tarokh Published: 2026-01-19 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2601.12707v2 Estimating the unknown reward functions driving agents' behaviors is of central interest in inverse reinforcement learning and game theory. To tackle this problem, we develop a unified framework for reward function recovery in two-player zero-sum matrix games and Markov games with entropy regularization, where we aim to reconstruct the underlying reward functions given observed players' strategies and actions. This task is challenging due to the inherent ambiguity of inverse problems, the non-uniqueness of feasible rewards, and limited observational data coverage. To address these challenges, we establish the reward function's identifiability using the quantal response equilibrium (QRE) under linear assumptions. Building upon this theoretical foundation, we propose a novel algorithm to learn reward functions from observed actions. Our algorithm works in both static and dynamic settings and is adaptable to incorporate different methods, such as Maximum Likelihood Estimation (MLE). We provide strong theoretical guarantees for the reliability and sample efficiency of our algorithm. Further, we conduct extensive numerical studies to demonstrate the practical effectiveness of the proposed framework, offering new insights into decision-making in competitive environments. --- ### Trend-Adjusted Time Series Models with an Application to Gold Price Forecasting Authors: Sina Kazemdehbashi Published: 2026-01-19 Categories: cs.LG arXiv: https://arxiv.org/abs/2601.12706v2 Time series data play a critical role in various fields, including finance, healthcare, marketing, and engineering. A wide range of techniques (from classical statistical models to neural network-based approaches such as Long Short-Term Memory (LSTM)) have been employed to address time series forecasting challenges. In this paper, we reframe time series forecasting as a two-part task: (1) predicting the trend (directional movement) of the time series at the next time step, and (2) forecasting the quantitative value at the next time step. The trend can be predicted using a binary classifier, while quantitative values can be forecasted using models such as LSTM and Bidirectional Long Short-Term Memory (Bi-LSTM). Building on this reframing, we propose the Trend-Adjusted Time Series (TATS) model, which adjusts the forecasted values based on the predicted trend provided by the binary classifier. We validate the proposed approach through both theoretical analysis and empirical evaluation. The TATS model is applied to a volatile financial time series (the daily gold price) with the objective of forecasting the next days price. Experimental results demonstrate that TATS consistently outperforms standard LSTM and Bi-LSTM models by achieving significantly lower forecasting error. In addition, our results indicate that commonly used metrics such as MSE and MAE are insufficient for fully assessing time series model performance. Therefore, we also incorporate trend detection accuracy, which measures how effectively a model captures trends in a time series. --- ### Adaptively trained Physics-informed Radial Basis Function Neural Networks for Solving Multi-asset Option Pricing Problems Authors: Yan Ma, Yumeng Ren, Elisabeth Larsson Published: 2026-01-19 Categories: cs.LG arXiv: https://arxiv.org/abs/2601.12704v2 The present study investigates the numerical solution of Black-Scholes partial differential equation (PDE) for option valuation with multiple underlying assets. We develop a physics-informed (PI) machine learning algorithm based on a radial basis function neural network (RBFNN) that concurrently optimizes the network architecture and predicts the target option price. The physics-informed radial basis function neural network (PIRBFNN) combines the strengths of the traditional radial basis function collocation method and the physics-informed neural network machine learning approach to effectively solve PDE problems in the financial context. By employing a PDE residual-based technique to adaptively refine the distribution of hidden neurons during the training process, the PIRBFNN facilitates accurate and efficient handling of multidimensional option pricing models featuring non-smooth payoff conditions. The validity of the proposed method is demonstrated through a set of experiments encompassing a single-asset European put option, a double-asset exchange option, and a four-asset basket call option. --- ### Towards Spectroscopy: Susceptibility Clusters in Language Models Authors: Andrew Gordon, Garrett Baker, George Wang, William Snell, Stan van Wingerden, Daniel Murfet Published: 2026-01-19 Categories: cs.LG arXiv: https://arxiv.org/abs/2601.12703v1 Spectroscopy infers the internal structure of physical systems by measuring their response to perturbations. We apply this principle to neural networks: perturbing the data distribution by upweighting a token $y$ in context $x$, we measure the model's response via susceptibilities $χ_{xy}$, which are covariances between component-level observables and the perturbation computed over a localized Gibbs posterior via stochastic gradient Langevin dynamics (SGLD). Theoretically, we show that susceptibilities decompose as a sum over modes of the data distribution, explaining why tokens that follow their contexts "for similar reasons" cluster together in susceptibility space. Empirically, we apply this methodology to Pythia-14M, developing a conductance-based clustering algorithm that identifies 510 interpretable clusters ranging from grammatical patterns to code structure to mathematical notation. Comparing to sparse autoencoders, 50% of our clusters match SAE features, validating that both methods recover similar structure. --- ### Bandit Algorithms for Deep Brain Stimulation Authors: Arkaprava Gupta, Nicholas Carter, William Zellers, Prateek Ganguli, Benedikt Dietrich, Vibhor Krishna, Parasara Sridhar Duggirala, Samarjit Chakraborty Published: 2026-01-19 Categories: cs.LG, eess.SY arXiv: https://arxiv.org/abs/2601.12699v2 Deep Brain Stimulation (DBS) is an effective treatment for Parkinson's disease, but conventional fixed-parameter stimulation can reduce battery life and cause side effects while failing to adapt to changing neural dynamics. Recent reinforcement learning approaches improve adaptability, yet most rely on deep neural networks that require offline training and are computationally too expensive for implantable hardware. This paper presents a resource-conscious adaptive DBS framework based on a Time- and Threshold-Triggered Pruned Multi-Armed Bandit (T3P MAB) algorithm. The proposed method jointly tunes stimulation frequency and amplitude, avoids prior training, and remains transparent enough to support clinician-guided adjustment. Using a computational basal ganglia-thalamic model, we show that T3P converges faster than competing MAB methods and outperforms deep-RL baselines in suppressing pathological beta-band activity while reducing stimulation power. We implemented it on different microcontrollers and report detailed energy measurements, showing convergence in under two minutes and suitability for resource-constrained implantable systems. These results support lightweight bandit-based control as a practical path toward personalized, energy-efficient DBS. --- ### A Two-Stage GPU Kernel Tuner Combining Semantic Refactoring and Search-Based Optimization Authors: Qiuyi Qu, Yicheng Sui, Yufei Sun, Rui Chen, Xiaofei Zhang, Yuzhi Zhang, Haofeng Wang, Ge Lan Published: 2026-01-19 Categories: cs.CL arXiv: https://arxiv.org/abs/2601.12698v3 GPU code optimization is a key performance bottleneck for HPC workloads as well as large-model training and inference. Although compiler optimizations and hand-written kernels can partially alleviate this issue, achieving near-hardware-limit performance still relies heavily on manual code refactoring and parameter tuning. Recent progress in LLM-agent-based kernel generation and optimization has been reported, yet many approaches primarily focus on direct code rewriting, where parameter choices are often implicit and hard to control, or require human intervention, leading to unstable performance gains. This paper introduces a template-based rewriting layer on top of an agent-driven iterative loop: kernels are semantically refactored into explicitly parameterizable templates, and template parameters are then optimized via search-based autotuning, yielding more stable and higher-quality speedups. Experiments on a set of real-world kernels demonstrate speedups exceeding 3x in the best case. We extract representative CUDA kernels from SGLang as evaluation targets; the proposed agentic tuner iteratively performs templating, testing, analysis, and planning, and leverages profiling feedback to execute constrained parameter search under hardware resource limits. Compared to agent-only direct rewriting, the template-plus-search design significantly reduces the randomness of iterative optimization, making the process more interpretable and enabling a more systematic approach toward high-performance configurations. The proposed method can be further extended to OpenCL, HIP, and other backends to deliver automated performance optimization for real production workloads. --- ### Fusing in 3D: Free-Viewpoint Fusion Rendering with a 3D Infrared-Visible Scene Representation Authors: Chao Yang, Deshui Miao, Chao Tian, Guoqing Zhu, Yameng Gu, Zhenyu He Published: 2026-01-19 Categories: cs.CV, cs.CG arXiv: https://arxiv.org/abs/2601.12697v1 Infrared-visible image fusion aims to integrate infrared and visible information into a single fused image. Existing 2D fusion methods focus on fusing images from fixed camera viewpoints, neglecting a comprehensive understanding of complex scenarios, which results in the loss of critical information about the scene. To address this limitation, we propose a novel Infrared-Visible Gaussian Fusion (IVGF) framework, which reconstructs scene geometry from multimodal 2D inputs and enables direct rendering of fused images. Specifically, we propose a cross-modal adjustment (CMA) module that modulates the opacity of Gaussians to solve the problem of cross-modal conflicts. Moreover, to preserve the distinctive features from both modalities, we introduce a fusion loss that guides the optimization of CMA, thus ensuring that the fused image retains the critical characteristics of each modality. Comprehensive qualitative and quantitative experiments demonstrate the effectiveness of the proposed method. --- ### UbuntuGuard: A Culturally-Grounded Policy Benchmark for Equitable AI Safety in African Languages Authors: Tassallah Abdullahi, Macton Mgonzo, Mardiyyah Oduwole, Paul Okewunmi, Abraham Owodunni, Ritambhara Singh, Carsten Eickhoff Published: 2026-01-19 Categories: cs.CL arXiv: https://arxiv.org/abs/2601.12696v3 Current guardian models are predominantly Western-centric and optimized for high-resource languages, leaving low-resource African languages vulnerable to evolving harms, cross-lingual failures, and cultural misalignment. Moreover, most guardian models rely on rigid, predefined safety categories that fail to generalize across diverse linguistic and sociocultural contexts. Achieving robust safety requires flexible, runtime-enforceable policies and benchmarks that reflect local norms, harm scenarios, and cultural expectations. We introduce UbuntuGuard, the first policy-based safety benchmark for African languages built from adversarial queries authored by 155 domain experts across sensitive fields, including healthcare. From these expert-crafted queries, we derive context-specific safety policies and reference responses that capture culturally grounded risk signals, enabling policy-aligned evaluation of guardian models. We evaluate 15 models, comprising seven general-purpose LLMs and eight guardian models across three distinct variants: static, dynamic, and multilingual. Our findings reveal that existing English-centric benchmarks overestimate real-world multilingual safety, cross-lingual transfer provides partial but insufficient coverage, and dynamic models, while better equipped to leverage policies at inference time, still struggle to fully localize African-language contexts. These findings highlight the urgent need for multilingual, culturally grounded safety benchmarks to enable the development of reliable and equitable guardian models for low-resource languages. --- ### BlocksecRT-DETR: Decentralized Privacy-Preserving and Token-Efficient Federated Transformer Learning for Secure Real-Time Object Detection in ITS Authors: Mohoshin Ara Tahera, Sabbir Rahman, Shuvalaxmi Dass, Sharif Ullah, Mahmoud Abouyessef Published: 2026-01-19 Categories: cs.CR, cs.LG arXiv: https://arxiv.org/abs/2601.12693v1 Federated real-time object detection using transformers in Intelligent Transportation Systems (ITS) faces three major challenges: (1) missing-class non-IID data heterogeneity from geographically diverse traffic environments, (2) latency constraints on edge hardware for high-capacity transformer models, and (3) privacy and security risks from untrusted client updates and centralized aggregation. We propose BlockSecRT-DETR, a BLOCKchain-SECured Real-Time Object DEtection TRansformer framework for ITS that provides a decentralized, token-efficient, and privacy-preserving federated training solution using RT-DETR transformer, incorporating a blockchain-secured update validation mechanism for trustworthy aggregation. In this framework, challenges (1) and (2) are jointly addressed through a unified client-side design that integrates RT-DETR training with a Token Engineering Module (TEM). TEM prunes low-utility tokens, reducing encoder complexity and latency on edge hardware, while aggregated updates mitigate non-IID data heterogeneity across clients. To address challenge (3), BlockSecRT-DETR incorporates a decentralized blockchain-secured update validation mechanism that enables tamper-proof, privacy-preserving, and trust-free authenticated model aggregation without relying on a central server. We evaluated the proposed framework under a missing-class Non-IID partition of the KITTI dataset and conducted a blockchain case study to quantify security overhead. TEM improves inference latency by 17.2% and reduces encoder FLOPs by 47.8%, while maintaining global detection accuracy (89.20% mAP@0.5). The blockchain integration adds 400 ms per round, and the ledger size remains under 12 KB due to metadata-only on-chain storage. --- ### Logic-Guided Multistage Inference for Explainable Multidefendant Judgment Prediction Authors: Xu Zhang, Qinghua Wang, Mengyang Zhao, Fang Wang, Cunquan Qu Published: 2026-01-19 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2601.12688v1 Crime disrupts societal stability, making law essential for balance. In multidefendant cases, assigning responsibility is complex and challenges fairness, requiring precise role differentiation. However, judicial phrasing often obscures the roles of the defendants, hindering effective AI-driven analyses. To address this issue, we incorporate sentencing logic into a pretrained Transformer encoder framework to enhance the intelligent assistance in multidefendant cases while ensuring legal interpretability. Within this framework an oriented masking mechanism clarifies roles and a comparative data construction strategy improves the model's sensitivity to culpability distinctions between principals and accomplices. Predicted guilt labels are further incorporated into a regression model through broadcasting, consolidating crime descriptions and court views. Our proposed masked multistage inference (MMSI) framework, evaluated on the custom IMLJP dataset for intentional injury cases, achieves significant accuracy improvements, outperforming baselines in role-based culpability differentiation. This work offers a robust solution for enhancing intelligent judicial systems, with publicly code available. ---