# Research Papers — 2026-01 · bundle page 4 of 189 > Full-text markdown of papers #151–200 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/4 [← Previous bundle](https://aipod.dev/papers/archive/2026-01/page/3.md) [Next bundle →](https://aipod.dev/papers/archive/2026-01/page/5.md) ### Physics-informed Diffusion Generation for Geomagnetic Map Interpolation Authors: Wenda Li, Tongya Zheng, Kaixuan Chen, Shunyu Liu, Haoze Jiang, Yunzhi Hao, Rui Miao, Zujie Ren, Mingli Song, Hang Shi, Gang Chen Published: 2026-01-31 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2602.00709v1 Geomagnetic map interpolation aims to infer unobserved geomagnetic data at spatial points, yielding critical applications in navigation and resource exploration. However, existing methods for scattered data interpolation are not specifically designed for geomagnetic maps, which inevitably leads to suboptimal performance due to detection noise and the laws of physics. Therefore, we propose a Physics-informed Diffusion Generation framework~(PDG) to interpolate incomplete geomagnetic maps. First, we design a physics-informed mask strategy to guide the diffusion generation process based on a local receptive field, effectively eliminating noise interference. Second, we impose a physics-informed constraint on the diffusion generation results following the kriging principle of geomagnetic maps, ensuring strict adherence to the laws of physics. Extensive experiments and in-depth analyses on four real-world datasets demonstrate the superiority and effectiveness of each component of PDG. --- ### Self-Guard: Defending Large Reasoning Models via enhanced self-reflection Authors: Jingnan Zheng, Jingjun Xu, Yanzhen Luo, Chenhang Cui, Gelei Deng, Zhenkai Liang, Xiang Wang, An Zhang, Tat-Seng Chua Published: 2026-01-31 Categories: cs.AI arXiv: https://arxiv.org/abs/2602.00707v1 The emergence of Large Reasoning Models (LRMs) introduces a new paradigm of explicit reasoning, enabling remarkable advances yet posing unique risks such as reasoning manipulation and information leakage. To mitigate these risks, current alignment strategies predominantly rely on heavy post-training paradigms or external interventions. However, these approaches are often computationally intensive and fail to address the inherent awareness-compliance gap, a critical misalignment where models recognize potential risks yet prioritize following user instructions due to their sycophantic tendencies. To address these limitations, we propose Self-Guard, a lightweight safety defense framework that reinforces safety compliance at the representational level. Self-Guard operates through two principal stages: (1) safety-oriented prompting, which activates the model's latent safety awareness to evoke spontaneous reflection, and (2) safety activation steering, which extracts the resulting directional shift in the hidden state space and amplifies it to ensure that safety compliance prevails over sycophancy during inference. Experiments demonstrate that Self-Guard effectively bridges the awareness-compliance gap, achieving robust safety performance without compromising model utility. Furthermore, Self-Guard exhibits strong generalization across diverse unseen risks and varying model scales, offering a cost-efficient solution for LRM safety alignment. --- ### QiMeng-ChipV-RTL: Exploiting Information Locality for IP-level Verilog Generation Authors: Hanqi Lyu, Di Huang, Yaoyu Zhu, Kangcheng Liu, Bohan Dou, Chongxiao Li, Pengwei Jin, Shuyao Cheng, Rui Zhang, Zidong Du, Qi Guo, Xing Hu et al. Published: 2026-01-31 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.00704v2 The generation of Register-Transfer Level (RTL) code is a crucial yet labor-intensive step in digital hardware design, traditionally requiring engineers to manually translate complex specifications into thousands of lines of synthesizable Hardware Description Language (HDL) code. While Large Language Models (LLMs) have shown promise in automating this process, existing approaches--including fine-tuned domain-specific models and advanced agent-based systems--struggle to scale to industrial IP-level design tasks. We identify three key challenges: (1) handling long, highly detailed documents, where critical interface constraints become buried in unrelated submodule descriptions; (2) generating long RTL code, where both syntactic and semantic correctness degrade sharply with increasing output length; and (3) navigating the complex debugging cycles required for functional verification through simulation and waveform analysis. To overcome these challenges, we propose ChipV-RTL, a multi-agent framework that leverages information locality in modular hardware design. ChipV-RTL decomposes the long-document to long-code generation problem into a set of short-document, short-code tasks, enabling scalable generation and debugging. Specifically, ChipV-RTL integrates hierarchical document partitioning, task planning, localized code generation, interface-consistent merging, and AST-guided locality-aware debugging. Experiments on RealBench, an IP-level Verilog generation benchmark, demonstrate that ChipV-RTL substantially outperforms state-of-the-art (SOTA) LLMs and agents, achieving a pass rate of 45.0% compared to 21.6%. Code, project page are available at https://iprc-dip.github.io/ChipV-RTL/. --- ### StomataSeg: Semi-Supervised Instance Segmentation for Sorghum Stomatal Components Authors: Zhongtian Huang, Zhi Chen, Zi Huang, Xin Yu, Daniel Smith, Chaitanya Purushothama, Erik Van Oosterom, Alex Wu, William Salter, Yan Li, Scott Chapman Published: 2026-01-31 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.00703v1 Sorghum is a globally important cereal grown widely in water-limited and stress-prone regions. Its strong drought tolerance makes it a priority crop for climate-resilient agriculture. Improving water-use efficiency in sorghum requires precise characterisation of stomatal traits, as stomata control of gas exchange, transpiration and photosynthesis have a major influence on crop performance. Automated analysis of sorghum stomata is difficult because the stomata are small (often less than 40 $μ$m in length in grasses such as sorghum) and vary in shape across genotypes and leaf surfaces. Automated segmentation contributes to high-throughput stomatal phenotyping, yet current methods still face challenges related to nested small structures and annotation bottlenecks. In this paper, we propose a semi-supervised instance segmentation framework tailored for analysis of sorghum stomatal components. We collect and annotate a sorghum leaf imagery dataset containing 11,060 human-annotated patches, covering the three stomatal components (pore, guard cell and complex area) across multiple genotypes and leaf surfaces. To improve the detection of tiny structures, we split high-resolution microscopy images into overlapping small patches. We then apply a pseudo-labelling strategy to unannotated images, producing an additional 56,428 pseudo-labelled patches. Benchmarking across semantic and instance segmentation models shows substantial performance gains: for semantic models the top mIoU increases from 65.93% to 70.35%, whereas for instance models the top AP rises from 28.30% to 46.10%. These results demonstrate that combining patch-based preprocessing with semi-supervised learning significantly improves the segmentation of fine stomatal structures. The proposed framework supports scalable extraction of stomatal traits and facilitates broader adoption of AI-driven phenotyping in crop science. --- ### JoyStreamer: Unlocking Highly Expressive Avatars via Harmonized Text-Audio Conditioning Authors: Ruikui Wang, Jinheng Feng, Lang Tian, Huaishao Luo, Chaochao Li, Liangbo Zhou, Huan Zhang, Youzheng Wu, Xiaodong He Published: 2026-01-31 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.00702v2 Existing video avatar models have demonstrated impressive capabilities in scenarios such as talking, public speaking, and singing. However, the majority of these methods exhibit limited alignment with respect to text instructions, particularly when the prompts involve complex elements including large full-body movement, dynamic camera trajectory, background transitions, or human-object interactions. To break out this limitation, we present JoyAvatar, a framework capable of generating long duration avatar videos, featuring two key technical innovations. Firstly, we introduce a twin-teacher enhanced training algorithm that enables the model to transfer inherent text-controllability from the foundation model while simultaneously learning audio-visual synchronization. Secondly, during training, we dynamically modulate the strength of multi-modal conditions (e.g., audio and text) based on the distinct denoising timestep, aiming to mitigate conflicts between the heterogeneous conditioning signals. These two key designs serve to substantially expand the avatar model's capacity to generate natural, temporally coherent full-body motions and dynamic camera movements as well as preserve the basic avatar capabilities, such as accurate lip-sync and identity consistency. GSB evaluation results demonstrate that our JoyStreamer model outperforms the state-of-the-art models such as Omnihuman-1.5 and KlingAvatar 2.0. Moreover, our approach enables complex applications including multi-person dialogues and non-human subjects role-playing. Some video samples are provided on https://joystreamer.github.io/. --- ### Cross-Modal Binary Attention: An Energy-Efficient Fusion Framework for Audio-Visual Learning Authors: Mohamed Saleh, Zahra Ahmadi Published: 2026-01-31 Categories: cs.MM, cs.CV, cs.LG, cs.SD arXiv: https://arxiv.org/abs/2602.00701v1 Effective multimodal fusion requires mechanisms that can capture complex cross-modal dependencies while remaining computationally scalable for real-world deployment. Existing audio-visual fusion approaches face a fundamental trade-off: attention-based methods effectively model cross-modal relationships but incur quadratic computational complexity that prevents hierarchical, multi-scale architectures, while efficient fusion strategies rely on simplistic concatenation that fails to extract complementary cross-modal information. We introduce CMQKA, a novel cross-modal fusion mechanism that achieves linear O(N) complexity through efficient binary operations, enabling scalable hierarchical fusion previously infeasible with conventional attention. CMQKA employs bidirectional cross-modal Query-Key attention to extract complementary spatiotemporal features and uses learnable residual fusion to preserve modality-specific characteristics while enriching representations with cross-modal information. Building upon CMQKA, we present SNNergy, an energy-efficient multimodal fusion framework with a hierarchical architecture that processes inputs through progressively decreasing spatial resolutions and increasing semantic abstraction. This multi-scale fusion capability allows the framework to capture both local patterns and global context across modalities. Implemented with event-driven binary spike operations, SNNergy achieves remarkable energy efficiency while maintaining fusion effectiveness and establishing new state-of-the-art results on challenging audio-visual benchmarks, including CREMA-D, AVE, and UrbanSound8K-AV, significantly outperforming existing multimodal fusion baselines. Our framework advances multimodal fusion by introducing a scalable fusion mechanism that enables hierarchical cross-modal integration with practical energy efficiency for real-world audio-visual intelligence systems. --- ### From Prompt to Graph: Comparing LLM-Based Information Extraction Strategies in Domain-Specific Ontology Development Authors: Xuan Liu, Ziyu Li, Mu He, Ziyang Ma, Xiaoxu Wu, Gizem Yilmaz, Yiyuan Xia, Bingbing Li, He Tan, Jerry Ying Hsi Fuh, Wen Feng Lu, Anders E. W. Jarfors et al. Published: 2026-01-31 Categories: cs.AI, cs.CL, cs.IR arXiv: https://arxiv.org/abs/2602.00699v1 Ontologies are essential for structuring domain knowledge, improving accessibility, sharing, and reuse. However, traditional ontology construction relies on manual annotation and conventional natural language processing (NLP) techniques, making the process labour-intensive and costly, especially in specialised fields like casting manufacturing. The rise of Large Language Models (LLMs) offers new possibilities for automating knowledge extraction. This study investigates three LLM-based approaches, including pre-trained LLM-driven method, in-context learning (ICL) method and fine-tuning method to extract terms and relations from domain-specific texts using limited data. We compare their performances and use the best-performing method to build a casting ontology that validated by domian expert. --- ### Forecasting Energy Availability in Local Energy Communities via LSTM Federated Learning Authors: Fabio Turazza, Marcello Pietri, Natalia Selini Hadjidimitriou, Marco Mamei Published: 2026-01-31 Categories: cs.LG, cs.AI, cs.DC arXiv: https://arxiv.org/abs/2602.00694v1 Local Energy Communities are emerging as crucial players in the landscape of sustainable development. A significant challenge for these communities is achieving self-sufficiency through effective management of the balance between energy production and consumption. To meet this challenge, it is essential to develop and implement forecasting models that deliver accurate predictions, which can then be utilized by optimization and planning algorithms. However, the application of forecasting solutions is often hindered by privacy constrains and regulations as the users participating in the Local Energy Community can be (rightfully) reluctant sharing their consumption patterns with others. In this context, the use of Federated Learning (FL) can be a viable solution as it allows to create a forecasting model without the need to share privacy sensitive information among the users. In this study, we demonstrate how FL and long short-term memory (LSTM) networks can be employed to achieve this objective, highlighting the trade-off between data sharing and forecasting accuracy. --- ### Topology and Geometry of the Learning Space of ReLU Networks: Connectivity and Singularities Authors: Marco Nurisso, Pierrick Leroy, Giovanni Petri, Francesco Vaccarino Published: 2026-01-31 Categories: cs.LG, math.AG, math.AT arXiv: https://arxiv.org/abs/2602.00693v1 Understanding the properties of the parameter space in feed-forward ReLU networks is critical for effectively analyzing and guiding training dynamics. After initialization, training under gradient flow decisively restricts the parameter space to an algebraic variety that emerges from the homogeneous nature of the ReLU activation function. In this study, we examine two key challenges associated with feed-forward ReLU networks built on general directed acyclic graph (DAG) architectures: the (dis)connectedness of the parameter space and the existence of singularities within it. We extend previous results by providing a thorough characterization of connectedness, highlighting the roles of bottleneck nodes and balance conditions associated with specific subsets of the network. Our findings clearly demonstrate that singularities are intricately connected to the topology of the underlying DAG and its induced sub-networks. We discuss the reachability of these singularities and establish a principled connection with differentiable pruning. We validate our theory with simple numerical experiments. --- ### Provably Protecting Fine-Tuned LLMs from Training Data Extraction while Preserving Utility Authors: Tom Segal, Asaf Shabtai, Yuval Elovici Published: 2026-01-31 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.00688v2 Fine-tuning large language models (LLMs) on sensitive datasets raises privacy concerns, as training data extraction (TDE) attacks can expose highly confidential information. Existing defenses against such attacks either lack formal privacy guarantees or incur substantial utility degradation. We observe that fine-tuning induces widespread probability shifts, yet preserving only a small subset of influential token-level deviations is sufficient; the remaining shifts can be aggressively smoothed with minimal impact on utility. Motivated by this insight, we propose SCP-$Δ_r$, a Near Access Freeness (NAF)-based algorithm that operates on relative probabilities and explicitly smooths low-impact tokens using a base model. SCP-$Δ_r$ achieves orders-of-magnitude better theoretical bounds than existing NAF based methods and provides strong empirical protection against TDE attacks with minimal performance loss. --- ### V2X-DSC: Multi-Agent Collaborative Perception with Distributed Source Coding Guided Communication Authors: Yuankun Zeng, Shaohui Li, Zhi Li, Shulan Ruan, Yu Liu, You He Published: 2026-01-31 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.00687v1 Collaborative perception improves 3D understanding by fusing multi-agent observations, yet intermediate-feature sharing faces strict bandwidth constraints as dense BEV features saturate V2X links. We observe that collaborators view the same physical world, making their features strongly correlated; thus receivers only need innovation beyond their local context. Revisiting this from a distributed source coding perspective, we propose V2X-DSC, a framework with a Conditional Codec (DCC) for bandwidth-constrained fusion. The sender compresses BEV features into compact codes, while the receiver performs conditional reconstruction using its local features as side information, allocating bits to complementary cues rather than redundant content. This conditional structure regularizes learning, encouraging incremental representation and yielding lower-noise features. Experiments on DAIR-V2X, OPV2V, and V2X-Real demonstrate state-of-the-art accuracy-bandwidth trade-offs under KB-level communication, and generalizes as a plug-and-play communication layer across multiple fusion backbones. --- ### HumanStudy-Bench: Towards AI Agent Design for Participant Simulation Authors: Xuan Liu, Haoyang Shang, Zizhang Liu, Xinyan Liu, Yunze Xiao, Yiwen Tu, Haojian Jin Published: 2026-01-31 Categories: cs.AI arXiv: https://arxiv.org/abs/2602.00685v2 Large language models (LLMs) are increasingly used as simulated participants in social science experiments, but their behavior is often unstable and highly sensitive to design choices. Prior evaluations frequently conflate base model capabilities with experimental instantiation, obscuring whether outcomes reflect the model itself or the agent setup. We instead frame $\textbf{participant simulation as an agent-design problem}$ over full experimental protocols, where an agent is defined by a base model and a specification (e.g., participant attributes) that encodes behavioral assumptions. We introduce $\textit{HUMANSTUDY-BENCH}$, an open platform and execution engine designed for practitioners to develop and evaluate agents tailored to their target experimental settings. The platform reconstructs published human-subject experiments via a human-in-the-loop Filter--Extract--Execute--Evaluate pipeline that preserves the original stimuli, conditions, and statistical procedures end to end, while allowing practitioners to freely explore the agent design space. We introduce two complementary metrics that quantify agreement with humans on both the significance conclusion and the effect size, while accounting for finite-sample uncertainty in the human reference data. In collaboration with social scientists, we validate the platform on a suite of 12 foundational studies covering 6,000+ trials across individual cognition, strategic interaction, and social psychology --- ### Video Understanding: Through A Temporal Lens Authors: Thong Thanh Nguyen Published: 2026-01-31 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.00683v2 This thesis explores the central question of how to leverage temporal relations among video elements to advance video understanding. Addressing the limitations of existing methods, the work presents a five-fold contribution: (1) an automatic annotation framework that utilizes large vision-language models and a noise-robust contrastive learning objective with a subtractive angular margin; (2) a parameter-efficient fine-tuning strategy using "recurrent adapters" to capture temporal dynamics in low-data regimes; (3) the integration of State Space Layers (SSL) for efficient long-form video modeling, supported by the introduction of two new long-term benchmarks for egocentric and feature-length content; (4) a novel contrastive learning framework designed to explicitly model fine-grained relations between motions and video moments; and (5) a comprehensive empirical study on Large Vision-Language Models (LVLMs) that identifies the visual-language interface as a bottleneck for temporal reasoning, leading to a new "temporal-oriented recipe" for upscaled video understanding. Collectively, these contributions demonstrate that explicit temporal modeling significantly enhances a model's ability to represent and reason about the fluid nature of video content. --- ### RecGOAT: Graph Optimal Adaptive Transport for LLM-Enhanced Multimodal Recommendation with Dual Semantic Alignment Authors: Yuecheng Li, Hengwei Ju, Zeyu Song, Wei Yang, Chi Lu, Peng Jiang, Kun Gai Published: 2026-01-31 Categories: cs.IR, cs.AI arXiv: https://arxiv.org/abs/2602.00682v2 Integrating large language model (LLM) representations into multimodal recommendation has shown promise, yet a fundamental challenge remains largely overlooked: the semantic heterogeneity between generative LM representations and the ID-based collaborative signals that recommendation systems rely on. Naively injecting LM features without alignment degrades recommendation performance rather than improving it. To resolve this, we propose RecGOAT, a dual-granularity semantic alignment framework built on graph neural networks and optimal transport theory. RecGOAT first enriches collaborative semantics through multimodal attentive graphs that capture item-item, user-item, and user-user relationships, initializing user representations via LLM-inferred behavioral preferences. It then aligns LM-derived modality representations with recommendation IDs at two complementary granularities: (1) instance-level alignment via cross-modal contrastive learning (CMCL), which produces discriminative per-sample representations; and (2) distribution-level alignment via optimal adaptive transport (OAT), which minimizes the 1-Wasserstein distance between ID distributions and LLM semantics to produce a unified, consistently aligned feature space. Theoretically, we prove that the unified representation achieves strictly lower target error than any single-modality representation, with the gap bounded by the Wasserstein distance and the InfoNCE loss, providing rigorous guarantees for both alignment consistency and fusion comprehensiveness. Extensive experiments on three public benchmarks demonstrate state-of-the-art performance. Deployment on a large-scale online advertising platform further validates RecGOAT's industrial scalability. Our code is available at https://github.com/6lyc/RecGOAT-LLM4Rec. --- ### Audio-to-Image Bird Species Retrieval without Audio-Image Pairs via Text Distillation Authors: Ilyass Moummad, Marius Miron, Lukas Rauch, David Robinson, Alexis Joly, Olivier Pietquin, Emmanuel Chemla, Matthieu Geist Published: 2026-01-31 Categories: cs.SD, cs.IR, cs.LG arXiv: https://arxiv.org/abs/2602.00681v2 Audio-to-image retrieval offers an interpretable alternative to audio-only classification for bioacoustic species recognition, but learning aligned audio-image representations is challenging due to the scarcity of paired audio-image data. We propose a simple and data-efficient approach that enables audio-to-image retrieval without any audio-image supervision. Our proposed method uses text as a semantic intermediary: we distill the text embedding space of a pretrained image-text model (BioCLIP-2), which encodes rich visual and taxonomic structure, into a pretrained audio-text model (BioLingual) by fine-tuning its audio encoder with a contrastive objective. This distillation transfers visually grounded semantics into the audio representation, inducing emergent alignment between audio and image embeddings without using images during training. We evaluate the resulting model on multiple bioacoustic benchmarks. The distilled audio encoder preserves audio discriminative power while substantially improving audio-text alignment on focal recordings and soundscape datasets. Most importantly, on the SSW60 benchmark, the proposed approach achieves strong audio-to-image retrieval performance exceeding baselines based on zero-shot model combinations or learned mappings between text embeddings, despite not training on paired audio-image data. These results demonstrate that indirect semantic transfer through text is sufficient to induce meaningful audio-image alignment, providing a practical solution for visually grounded species recognition in data-scarce bioacoustic settings. --- ### OpenGuanDan: A Large-Scale Imperfect Information Game Benchmark Authors: Chao Li, Shangdong Yang, Chiheng Zhan, Zhenxing Ge, Yujing Hu, Bingkun Bao, Xingguo Chen, Yang Gao Published: 2026-01-31 Categories: cs.AI, cs.MA arXiv: https://arxiv.org/abs/2602.00676v1 The advancement of data-driven artificial intelligence (AI), particularly machine learning, heavily depends on large-scale benchmarks. Despite remarkable progress across domains ranging from pattern recognition to intelligent decision-making in recent decades, exemplified by breakthroughs in board games, card games, and electronic sports games, there remains a pressing need for more challenging benchmarks to drive further research. To this end, this paper proposes OpenGuanDan, a novel benchmark that enables both efficient simulation of GuanDan (a popular four-player, multi-round Chinese card game) and comprehensive evaluation of both learning-based and rule-based GuanDan AI agents. OpenGuanDan poses a suite of nontrivial challenges, including imperfect information, large-scale information set and action spaces, a mixed learning objective involving cooperation and competition, long-horizon decision-making, variable action spaces, and dynamic team composition. These characteristics make it a demanding testbed for existing intelligent decision-making methods. Moreover, the independent API for each player allows human-AI interactions and supports integration with large language models. Empirically, we conduct two types of evaluations: (1) pairwise competitions among all GuanDan AI agents, and (2) human-AI matchups. Experimental results demonstrate that while current learning-based agents substantially outperform rule-based counterparts, they still fall short of achieving superhuman performance, underscoring the need for continued research in multi-agent intelligent decision-making domain. The project is publicly available at https://github.com/GameAI-NJUPT/OpenGuanDan. --- ### Strong Linear Baselines Strike Back: Closed-Form Linear Models as Gaussian Process Conditional Density Estimators for TSAD Authors: Aleksandr Yugay, Hang Cui, Changhua Pei, Alexey Zaytsev Published: 2026-01-31 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.00672v1 Research in time series anomaly detection (TSAD) has largely focused on developing increasingly sophisticated, hard-to-train, and expensive-to-infer neural architectures. We revisit this paradigm and show that a simple linear autoregressive anomaly score with the closed-form solution provided by ordinary least squares (OLS) regression consistently matches or outperforms state-of-the-art deep detectors. From a theoretical perspective, we show that linear models capture a broad class of anomaly types, estimating a finite-history Gaussian process conditional density. From a practical side, across extensive univariate and multivariate benchmarks, the proposed approach achieves superior accuracy while requiring orders of magnitude fewer computational resources. Thus, future research should consistently include strong linear baselines and, more importantly, develop new benchmarks with richer temporal structures pinpointing the advantages of deep learning models. --- ### HPC: Hierarchical Point-based Latent Representation for Streaming Dynamic Gaussian Splatting Compression Authors: Yangzhi Ma, Bojun Liu, Wenting Liao, Dong Liu, Zhu Li, Li Li Published: 2026-01-31 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.00671v1 While dynamic Gaussian Splatting has driven significant advances in free-viewpoint video, maintaining its rendering quality with a small memory footprint for efficient streaming transmission still presents an ongoing challenge. Existing streaming dynamic Gaussian Splatting compression methods typically leverage a latent representation to drive the neural network for predicting Gaussian residuals between frames. Their core latent representations can be categorized into structured grid-based and unstructured point-based paradigms. However, the former incurs significant parameter redundancy by inevitably modeling unoccupied space, while the latter suffers from limited compactness as it fails to exploit local correlations. To relieve these limitations, we propose HPC, a novel streaming dynamic Gaussian Splatting compression framework. It employs a hierarchical point-based latent representation that operates on a per-Gaussian basis to avoid parameter redundancy in unoccupied space. Guided by a tailored aggregation scheme, these latent points achieve high compactness with low spatial redundancy. To improve compression efficiency, we further undertake the first investigation to compress neural networks for streaming dynamic Gaussian Splatting through mining and exploiting the inter-frame correlation of parameters. Combined with latent compression, this forms a fully end-to-end compression framework. Comprehensive experimental evaluations demonstrate that HPC substantially outperforms state-of-the-art methods. It achieves a storage reduction of 67% against its baseline while maintaining high reconstruction fidelity. --- ### Three-Way Emotion Classification of EEG-based Signals using Machine Learning Authors: Ashna Purwar, Gaurav Simkar, Madhumita, Sachin Kadam Published: 2026-01-31 Categories: cs.LG, eess.SP arXiv: https://arxiv.org/abs/2602.00670v1 Electroencephalography (EEG) is a widely used technique for measuring brain activity. EEG-based signals can reveal a persons emotional state, as they directly reflect activity in different brain regions. Emotion-aware systems and EEG-based emotion recognition are a growing research area. This paper presents how machine learning (ML) models categorize a limited dataset of EEG signals into three different classes, namely Negative, Neutral, or Positive. It also presents the complete workflow, including data preprocessing and comparison of ML models. To understand which ML classification model works best for this kind of problem, we train and test the following three commonly used models: logistic regression (LR), support vector machine (SVM), and random forest (RF). The performance of each is evaluated with respect to accuracy and F1-score. The results indicate that ML models can be effectively utilized for three-way emotion classification of EEG signals. Among the three ML models trained on the available dataset, the RF model gave the best results. Its higher accuracy and F1-score suggest that it is able to capture the emotional patterns more accurately and effectively than the other two models. The RF model also outperformed the existing state-of-the-art classification models in terms of the accuracy parameter. --- ### Improving Neuropathological Reconstruction Fidelity via AI Slice Imputation Authors: Marina Crespo Aguirre, Jonathan Williams-Ramirez, Dina Zemlyanker, Xiaoling Hu, Lucas J. Deden-Binder, Rogeny Herisse, Mark Montine, Theresa R. Connors, Christopher Mount, Christine L. MacDonald, C. Dirk Keene, Caitlin S. Latimer et al. Published: 2026-01-31 Categories: cs.CV, cs.AI, physics.med-ph arXiv: https://arxiv.org/abs/2602.00669v1 Neuropathological analyses benefit from spatially precise volumetric reconstructions that enhance anatomical delineation and improve morphometric accuracy. Our prior work has shown the feasibility of reconstructing 3D brain volumes from 2D dissection photographs. However these outputs sometimes exhibit coarse, overly smooth reconstructions of structures, especially under high anisotropy (i.e., reconstructions from thick slabs). Here, we introduce a computationally efficient super-resolution step that imputes slices to generate anatomically consistent isotropic volumes from anisotropic 3D reconstructions of dissection photographs. By training on domain-randomized synthetic data, we ensure that our method generalizes across dissection protocols and remains robust to large slab thicknesses. The imputed volumes yield improved automated segmentations, achieving higher Dice scores, particularly in cortical and white matter regions. Validation on surface reconstruction and atlas registration tasks demonstrates more accurate cortical surfaces and MRI registration. By enhancing the resolution and anatomical fidelity of photograph-based reconstructions, our approach strengthens the bridge between neuropathology and neuroimaging. Our method is publicly available at https://surfer.nmr.mgh.harvard.edu/fswiki/mri_3d_photo_recon --- ### Can Small Language Models Handle Context-Summarized Multi-Turn Customer-Service QA? A Synthetic Data-Driven Comparative Evaluation Authors: Lakshan Cooray, Deshan Sumanathilaka, Pattigadapa Venkatesh Raju Published: 2026-01-31 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2602.00665v4 Customer-service question answering (QA) systems increasingly rely on conversational language understanding. While Large Language Models (LLMs) achieve strong performance, their high computational cost and deployment constraints limit practical use in resource-constrained environments. Small Language Models (SLMs) provide a more efficient alternative, yet their effectiveness for multi-turn customer-service QA remains underexplored, particularly in scenarios requiring dialogue continuity and contextual understanding. This study investigates instruction-tuned SLMs for context-summarized multi-turn customer-service QA, using a history summarization strategy to preserve essential conversational state. We also introduce a conversation stage-based qualitative analysis to evaluate model behavior across different phases of customer-service interactions. Nine instruction-tuned low-parameterized SLMs are evaluated against three commercial LLMs using lexical and semantic similarity metrics alongside qualitative assessments, including human evaluation and LLM-as-a-judge methods. Results show notable variation across SLMs, with some models demonstrating near-LLM performance, while others struggle to maintain dialogue continuity and contextual alignment. These findings highlight both the potential and current limitations of low-parameterized language models for real-world customer-service QA systems. --- ### SEISMO: Explanation-Aware, Trajectory-Conditioned LLM Agents for Sample-Efficient Molecular Optimisation Authors: Fabian P. Krüger, Andrea Hunklinger, Adrian Wolny, Tim J. Adler, Igor Tetko, Santiago David Villalba Published: 2026-01-31 Categories: cs.AI, cs.LG, q-bio.BM arXiv: https://arxiv.org/abs/2602.00663v3 Optimizing molecules to achieve desired properties is a central bottleneck across the chemical sciences, particularly in the pharmaceutical industry, where it underlies the discovery of new drugs. Since molecular property evaluation often relies on costly and rate-limited oracles, such as experimental assays, molecular optimization must be highly sample-efficient. To address this, we introduce SEISMO, an LLM agent for inference-time molecular optimisation that turns information routinely available alongside the oracle score, but discarded by existing methods, into an explicit guidance signal. Rather than treating the oracle as a scalar black box, SEISMO conditions each proposal on a natural-language task description, the full optimization trajectory, and machine-readable feedback derived from post-hoc explainability methods and sub-score decompositions. Across a wide range of drug-discovery-relevant tasks, this consistently improves sample efficiency over existing optimisers as well as zero-shot LLM generation, with gains growing as explanatory feedback is enriched. In practice, medicinal chemists can inspect the agent's reasoning and intervene to steer generation in natural language, keeping them central to molecular optimisation projects. --- ### Schrödinger-Inspired Time-Evolution for 4D Deformation Forecasting Authors: Ahsan Raza Siyal, Markus Haltmeier, Ruth Steiger, Elke Ruth Gizewski, Astrid Ellen Grams Published: 2026-01-31 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.00661v1 Spatiotemporal forecasting of complex three-dimensional phenomena (4D: 3D + time) is fundamental to applications in medical imaging, fluid and material dynamics, and geophysics. In contrast to unconstrained neural forecasting models, we propose a Schrödinger-inspired, physics-guided neural architecture that embeds an explicit time-evolution operator within a deep convolutional framework for 4D prediction. From observed volumetric sequences, the model learns voxelwise amplitude, phase, and potential fields that define a complex-valued wavefunction $ψ= A e^{iφ}$, which is evolved forward in time using a differentiable, unrolled Schrödinger time stepper. This physics-guided formulation yields several key advantages: (i) temporal stability arising from the structured evolution operator, which mitigates drift and error accumulation in long-horizon forecasting; (ii) an interpretable latent representation, where phase encodes transport dynamics, amplitude captures structural intensity, and the learned potential governs spatiotemporal interactions; and (iii) natural compatibility with deformation-based synthesis, which is critical for preserving anatomical fidelity in medical imaging applications. By integrating physical priors directly into the learning process, the proposed approach combines the expressivity of deep networks with the robustness and interpretability of physics-based modeling. We demonstrate accurate and stable prediction of future 4D states, including volumetric intensities and deformation fields, on synthetic benchmarks that emulate realistic shape deformations and topological changes. To our knowledge, this is the first end-to-end 4D neural forecasting framework to incorporate a Schrödinger-type evolution operator, offering a principled pathway toward interpretable, stable, and anatomically consistent spatiotemporal prediction. --- ### Predictive Maintenance for Ultrafiltration Membranes Using Explainable Similarity-Based Prognostics Authors: Qusai Khaled, Laura Genga, Uzay Kaymak Published: 2026-01-31 Categories: cs.AI arXiv: https://arxiv.org/abs/2602.00659v1 In reverse osmosis desalination, ultrafiltration (UF) membranes degrade due to fouling, leading to performance loss and costly downtime. Most plants rely on scheduled preventive maintenance, since existing predictive maintenance models, often based on opaque machine learning methods, lack interpretability and operator trust. This study proposes an explainable prognostic framework for UF membrane remaining useful life (RUL) estimation using fuzzy similarity reasoning. A physics-informed Health Index, derived from transmembrane pressure, flux, and resistance, captures degradation dynamics, which are then fuzzified via Gaussian membership functions. Using a similarity measure, the model identifies historical degradation trajectories resembling the current state and formulates RUL predictions as Takagi-Sugeno fuzzy rules. Each rule corresponds to a historical exemplar and contributes to a transparent, similarity-weighted RUL estimate. Tested on 12,528 operational cycles from an industrial-scale UF system, the framework achieved a mean absolute error of 4.50 cycles, while generating interpretable rule bases consistent with expert understanding. --- ### Non-Clashing Teaching in Graphs: Algorithms, Complexity, and Bounds Authors: Sujoy Bhore, Liana Khazaliya, Fionn Mc Inerney Published: 2026-01-31 Categories: cs.CC, cs.DM, cs.DS, cs.LG, math.CO arXiv: https://arxiv.org/abs/2602.00657v2 Kirkpatrick et al. (ALT 2019) and Fallat et al. (JMLR 2023) introduced non-clashing teaching and proved that it is the most efficient batch machine teaching model satisfying the collusion-avoidance benchmark established in the seminal work of Goldman and Mathias (COLT 1993). Recently, (positive) non-clashing teaching was thoroughly studied for balls in graphs, yielding numerous algorithmic and combinatorial results. In particular, Chalopin et al. (COLT 2024) and Ganian et al. (ICLR 2025) gave an almost complete picture of the complexity landscape of the positive variant, showing that it is tractable only for restricted graph classes due to the non-trivial nature of the problem and concept class. In this work, we consider (positive) non-clashing teaching for closed neighborhoods in graphs. This concept class is not only extensively studied in various related contexts, but it also exhibits broad generality, as any finite binary concept class can be equivalently represented by a set of closed neighborhoods in a graph. In comparison to the works on balls in graphs, we provide improved algorithmic results, notably including FPT algorithms for more general classes of parameters, and we complement these results by deriving stronger lower bounds. Lastly, we obtain combinatorial upper bounds for wider classes of graphs. --- ### DisRFM: Polar Riemannian Flow Matching for Structure-Preserving Graph Domain Adaptation Authors: Yingxu Wang, Xinwang Liu, Mengzhu Wang, Siyang Gao, Nan Yin Published: 2026-01-31 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.00656v2 Graph Domain Adaptation (GDA) aims to transfer graph classifiers across domains with both semantic and topological shifts. Existing Euclidean adversarial methods face two challenges: Structural Degeneration, where domain confusion entangles and suppresses label-relevant topology, and Optimization Instability, where minimax training induces oscillatory gradients under large structural shifts. We propose DisRFM, a geometry-aware GDA framework that addresses these challenges with Riemannian representation learning and flow-based transport. DisRFM embeds graph representations on a constant-curvature manifold and expresses them in geodesic polar coordinates. Polar endpoint regularization calibrates topologysensitive radial scales via univariate Wasserstein alignment and preserves scalenormalized class semantics through confidence-filtered angular alignment, with radial magnitude modulating pseudo-label reliability. DisRFM introduces topologyconditioned polar flow matching, which couples class-compatible source and target samples by a normalized polar transport cost and learns a metric-corrected vector field along geodesic interpolants. Theoretical analysis characterizes the structural risk of unconditional domain confusion and relates polar discrepancies and flow error to target risk. Extensive experiments under diverse domain shifts demonstrate that DisRFM consistently outperforms state-of-the-art methods. --- ### PHAT: Modeling Period Heterogeneity for Multivariate Time Series Forecasting Authors: Jiaming Ma, Qihe Huang, Haofeng Ma, Guanjun Wang, Sheng Huang, Zhengyang Zhou, Pengkun Wang, Binwu Wang, Yang Wang Published: 2026-01-31 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.00654v3 While existing multivariate time series forecasting models have advanced significantly in modeling periodicity, they largely neglect the periodic heterogeneity common in real-world data, where variables exhibit distinct and dynamically changing periods. To effectively capture this periodic heterogeneity, we propose PHAT (Period Heterogeneity-Aware Transformer). Specifically, PHAT arranges multivariate inputs into a three-dimensional "periodic bucket" tensor, where the dimensions correspond to variable group characteristics with similar periodicity, time steps aligned by phase, and offsets within the period. By restricting interactions within buckets and masking cross-bucket connections, PHAT effectively avoids interference from inconsistent periods. We also propose a positive-negative attention mechanism, which captures periodic dependencies from two perspectives: periodic alignment and periodic deviation. Additionally, the periodic alignment attention scores are decomposed into positive and negative components, with a modulation term encoding periodic priors. This modulation constrains the attention mechanism to more faithfully reflect the underlying periodic trends. A mathematical explanation is provided to support this property. We evaluate PHAT comprehensively on 14 real-world datasets against 18 baselines, and the results show that it significantly outperforms existing methods, achieving highly competitive forecasting performance. Our sources is available at GitHub. --- ### Non-Contrastive Vision-Language Learning with Predictive Embedding Alignment Authors: Lukas Kuhn, Giuseppe Serra, Florian Buettner Published: 2026-01-31 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2602.00653v2 Vision-language models have transformed multimodal representation learning, yet dominant contrastive approaches like CLIP require large batch sizes, careful negative sampling, and extensive hyperparameter tuning. We introduce NOVA, a NOn-contrastive Vision-language Alignment framework based on joint embedding prediction with distributional regularization. NOVA aligns visual representations to a frozen, domain-specific text encoder by predicting text embeddings from augmented image views, while enforcing an isotropic Gaussian structure via Sketched Isotropic Gaussian Regularization (SIGReg). This eliminates the need for negative sampling, momentum encoders, or stop-gradients, reducing the training objective to a single hyperparameter. We evaluate NOVA on zeroshot chest X-ray classification using ClinicalBERT as the text encoder and Vision Transformers trained from scratch on MIMIC-CXR. On zero-shot classification across three benchmark datasets, NOVA outperforms multiple standard baselines while exhibiting substantially more consistent training runs. Our results demonstrate that non-contrastive vision-language pretraining offers a simpler, more stable, and more effective alternative to contrastive methods. --- ### A Hybrid Mamba-SAM Architecture for Efficient 3D Medical Image Segmentation Authors: Mohammadreza Gholipour Shahraki, Mehdi Rezaeian, Mohammad Ghasemzadeh Published: 2026-01-31 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.00650v1 Accurate segmentation of 3D medical images such as MRI and CT is essential for clinical diagnosis and treatment planning. Foundation models like the Segment Anything Model (SAM) provide powerful general-purpose representations but struggle in medical imaging due to domain shift, their inherently 2D design, and the high computational cost of fine-tuning. To address these challenges, we propose Mamba-SAM, a novel and efficient hybrid architecture that combines a frozen SAM encoder with the linear-time efficiency and long-range modeling capabilities of Mamba-based State Space Models (SSMs). We investigate two parameter-efficient adaptation strategies. The first is a dual-branch architecture that explicitly fuses general features from a frozen SAM encoder with domain-specific representations learned by a trainable VMamba encoder using cross-attention. The second is an adapter-based approach that injects lightweight, 3D-aware Tri-Plane Mamba (TPMamba) modules into the frozen SAM ViT encoder to implicitly model volumetric context. Within this framework, we introduce Multi-Frequency Gated Convolution (MFGC), which enhances feature representation by jointly analyzing spatial and frequency-domain information via 3D discrete cosine transforms and adaptive gating. Extensive experiments on the ACDC cardiac MRI dataset demonstrate the effectiveness of the proposed methods. The dual-branch Mamba-SAM-Base model achieves a mean Dice score of 0.906, comparable to UNet++ (0.907), while outperforming all baselines on Myocardium (0.910) and Left Ventricle (0.971) segmentation. The adapter-based TP MFGC variant offers superior inference speed (4.77 FPS) with strong accuracy (0.880 Dice). These results show that hybridizing foundation models with efficient SSM-based architectures provides a practical and effective solution for 3D medical image segmentation. --- ### CoRe-Fed: Bridging Collaborative and Representation Fairness via Federated Embedding Distillation Authors: Noorain Mukhtiar, Adnan Mahmood, Quan Z. Sheng Published: 2026-01-31 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.00647v1 With the proliferation of distributed data sources, Federated Learning (FL) has emerged as a key approach to enable collaborative intelligence through decentralized model training while preserving data privacy. However, conventional FL algorithms often suffer from performance disparities across clients caused by heterogeneous data distributions and unequal participation, which leads to unfair outcomes. Specifically, we focus on two core fairness challenges, i.e., representation bias, arising from misaligned client representations, and collaborative bias, stemming from inequitable contribution during aggregation, both of which degrade model performance and generalizability. To mitigate these disparities, we propose CoRe-Fed, a unified optimization framework that bridges collaborative and representation fairness via embedding-level regularization and fairness-aware aggregation. Initially, an alignment-driven mechanism promotes semantic consistency between local and global embeddings to reduce representational divergence. Subsequently, a dynamic reward-penalty-based aggregation strategy adjusts each client's weight based on participation history and embedding alignment to ensure contribution-aware aggregation. Extensive experiments across diverse models and datasets demonstrate that CoRe-Fed improves both fairness and model performance over the state-of-the-art baseline algorithms. --- ### LegalOne: A Family of Foundation Models for Reliable Legal Reasoning Authors: Haitao Li, Yifan Chen, Shuo Miao, Qian Dong, Jia Chen, Yiran Hu, Junjie Chen, Minghao Qin, Yueyue Wu, Yujia Zhou, Qingyao Ai, Yiqun Liu et al. Published: 2026-01-31 Categories: cs.CL arXiv: https://arxiv.org/abs/2602.00642v2 While Large Language Models (LLMs) have demonstrated impressive general capabilities, their direct application in the legal domain is often hindered by a lack of precise domain knowledge and complexity of performing rigorous multi-step judicial reasoning. To address this gap, we present LegalOne, a family of foundational models specifically tailored for the Chinese legal domain. LegalOne is developed through a comprehensive three-phase pipeline designed to master legal reasoning. First, during mid-training phase, we propose Plasticity-Adjusted Sampling (PAS) to address the challenge of domain adaptation. This perplexity-based scheduler strikes a balance between the acquisition of new knowledge and the retention of original capabilities, effectively establishing a robust legal foundation. Second, during supervised fine-tuning, we employ Legal Agentic CoT Distillation (LEAD) to distill explicit reasoning from raw legal texts. Unlike naive distillation, LEAD utilizes an agentic workflow to convert complex judicial processes into structured reasoning trajectories, thereby enforcing factual grounding and logical rigor. Finally, we implement a Curriculum Reinforcement Learning (RL) strategy. Through a progressive reinforcement process spanning memorization, understanding, and reasoning, LegalOne evolves from simple pattern matching to autonomous and reliable legal reasoning. Experimental results demonstrate that LegalOne achieves state-of-the-art performance across a wide range of legal tasks, surpassing general-purpose LLMs with vastly larger parameter counts through enhanced knowledge density and efficiency. We publicly release the LegalOne weights and the LegalKit evaluation framework to advance the field of Legal AI, paving the way for deploying trustworthy and interpretable foundation models in high-stakes judicial applications. --- ### Sampling from multi-modal distributions on Riemannian manifolds with training-free stochastic interpolants Authors: Alain Durmus, Maxence Noble, Thibaut Pellerin Published: 2026-01-31 Categories: stat.ML, cs.LG, stat.CO arXiv: https://arxiv.org/abs/2602.00641v1 In this paper, we propose a general methodology for sampling from un-normalized densities defined on Riemannian manifolds, with a particular focus on multi-modal targets that remain challenging for existing sampling methods. Inspired by the framework of diffusion models developed for generative modeling, we introduce a sampling algorithm based on the simulation of a non-equilibrium deterministic dynamics that transports an easy-to-sample noise distribution toward the target. At the marginal level, the induced density path follows a prescribed stochastic interpolant between the noise and target distributions, specifically constructed to respect the underlying Riemannian geometry. In contrast to related generative modeling approaches that rely on machine learning, our method is entirely training-free. It instead builds on iterative posterior sampling procedures using only standard Monte Carlo techniques, thereby extending recent diffusion-based sampling methodologies beyond the Euclidean setting. We complement our approach with a rigorous theoretical analysis and demonstrate its effectiveness on a range of multi-modal sampling problems, including high-dimensional and heavy-tailed examples. --- ### Combinatorial Bandit Bayesian Optimization for Tensor Outputs Authors: Jingru Huang, Haijie Xu, Jie Guo, Manrui Jiang, Chen Zhang Published: 2026-01-31 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.00640v2 Bayesian optimization (BO) has been widely used to optimize expensive and black-box functions across various domains. However, existing BO methods have not addressed tensor-output functions. To fill this gap, we propose a novel tensor-output BO framework. Specifically, we first introduce a tensor-output Gaussian process (TOGP) with two classes of tensor-output kernels as a surrogate model of the tensor-output function, which can effectively capture the structural dependencies within the tensor. Based on it, we develop an upper confidence bound (UCB) acquisition function to select query points. Furthermore, we introduce a more practical and challenging problem setting, termed combinatorial bandit Bayesian optimization (CBBO), where only a subset of the tensor outputs can be selected to contribute to the objective. To tackle this, we propose a tensor-output CBBO method, which extends TOGP to handle partially observed tensor outputs, and accordingly design a novel combinatorial multi-arm bandit-UCB2 (CMAB-UCB2) criterion to sequentially select both the query points and the output subset. We establish theoretical regret bounds for both methods, guaranteeing sublinear regret. Extensive experiments on synthetic and real-world datasets demonstrate the superiority of our methods. --- ### Diff-PC: Identity-preserving and 3D-aware Controllable Diffusion for Zero-shot Portrait Customization Authors: Yifang Xu, Benxiang Zhai, Chenyu Zhang, Ming Li, Yang Li, Sidan Du Published: 2026-01-31 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.00639v1 Portrait customization (PC) has recently garnered significant attention due to its potential applications. However, existing PC methods lack precise identity (ID) preservation and face control. To address these tissues, we propose Diff-PC, a diffusion-based framework for zero-shot PC, which generates realistic portraits with high ID fidelity, specified facial attributes, and diverse backgrounds. Specifically, our approach employs the 3D face predictor to reconstruct the 3D-aware facial priors encompassing the reference ID, target expressions, and poses. To capture fine-grained face details, we design ID-Encoder that fuses local and global facial features. Subsequently, we devise ID-Ctrl using the 3D face to guide the alignment of ID features. We further introduce ID-Injector to enhance ID fidelity and facial controllability. Finally, training on our collected ID-centric dataset improves face similarity and text-to-image (T2I) alignment. Extensive experiments demonstrate that Diff-PC surpasses state-of-the-art methods in ID preservation, facial control, and T2I consistency. Furthermore, our method is compatible with multi-style foundation models. --- ### Formal Semantic Control over Language Models Authors: Yingji Zhang Published: 2026-01-31 Categories: cs.CL arXiv: https://arxiv.org/abs/2602.00638v1 This thesis advances semantic representation learning to render language representations or models more semantically and geometrically interpretable, and to enable localised, quasi-symbolic, compositional control through deliberate shaping of their latent space geometry. We pursue this goal within a VAE framework, exploring two complementary research directions: (i) Sentence-level learning and control: disentangling and manipulating specific semantic features in the latent space to guide sentence generation, with explanatory text serving as the testbed; and (ii) Reasoning-level learning and control: isolating and steering inference behaviours in the latent space to control NLI. In this direction, we focus on Explanatory NLI tasks, in which two premises (explanations) are provided to infer a conclusion. The overarching objective is to move toward language models whose internal semantic representations can be systematically interpreted, precisely structured, and reliably directed. We introduce a set of novel theoretical frameworks and practical methodologies, together with corresponding experiments, to demonstrate that our approaches enhance both the interpretability and controllability of latent spaces for natural language across the thesis. --- ### VIZOR: Viewpoint-Invariant Zero-Shot Scene Graph Generation for 3D Scene Reasoning Authors: Vivek Madhavaram, Vartika Sengar, Arkadipta De, Charu Sharma Published: 2026-01-31 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.00637v1 Scene understanding and reasoning has been a fundamental problem in 3D computer vision, requiring models to identify objects, their properties, and spatial or comparative relationships among the objects. Existing approaches enable this by creating scene graphs using multiple inputs such as 2D images, depth maps, object labels, and annotated relationships from specific reference view. However, these methods often struggle with generalization and produce inaccurate spatial relationships like "left/right", which become inconsistent across different viewpoints. To address these limitations, we propose Viewpoint-Invariant Zero-shot scene graph generation for 3D scene Reasoning (VIZOR). VIZOR is a training-free, end-to-end framework that constructs dense, viewpoint-invariant 3D scene graphs directly from raw 3D scenes. The generated scene graph is unambiguous, as spatial relationships are defined relative to each object's front-facing direction, making them consistent regardless of the reference view. Furthermore, it infers open-vocabulary relationships that describe spatial and proximity relationships among scene objects without requiring annotated training data. We conduct extensive quantitative and qualitative evaluations to assess the effectiveness of VIZOR in scene graph generation and downstream tasks, such as query-based object grounding. VIZOR outperforms state-of-the-art methods, showing clear improvements in scene graph generation and achieving 22% and 4.81% gains in zero-shot grounding accuracy on the Replica and Nr3D datasets, respectively. --- ### On the Equilibrium between Feasible Zone and Uncertain Model in Safe Exploration Authors: Yujie Yang, Zhilong Zheng, Shengbo Eben Li Published: 2026-01-31 Categories: cs.LG, eess.SY arXiv: https://arxiv.org/abs/2602.00636v2 Ensuring the safety of environmental exploration is a critical problem in reinforcement learning (RL). While limiting exploration to a feasible zone has become widely accepted as a way to ensure safety, key questions remain unresolved: what is the maximum feasible zone achievable through exploration, and how can it be identified? This paper, for the first time, answers these questions by revealing that the goal of safe exploration is to find the equilibrium between the feasible zone and the environment model. This conclusion is based on the understanding that these two components are interdependent: a larger feasible zone leads to a more accurate environment model, and a more accurate model, in turn, enables exploring a larger zone. We propose the first equilibrium-oriented safe exploration framework called safe equilibrium exploration (SEE), which alternates between finding the maximum feasible zone and the least uncertain model. Using a graph formulation of the uncertain model, we prove that the uncertain model obtained by SEE is monotonically refined, the feasible zones monotonically expand, and both converge to the equilibrium of safe exploration. Experiments on classic control tasks show that our algorithm successfully expands the feasible zones with zero constraint violation, and achieves the equilibrium of safe exploration within a few iterations. --- ### S$^3$POT: Contrast-Driven Face Occlusion Segmentation via Self-Supervised Prompt Learning Authors: Lingsong Wang, Mancheng Meng, Ziyan Wu, Terrence Chen, Fan Yang, Dinggang Shen Published: 2026-01-31 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2602.00635v1 Existing face parsing methods usually misclassify occlusions as facial components. This is because occlusion is a high-level concept, it does not refer to a concrete category of object. Thus, constructing a real-world face dataset covering all categories of occlusion object is almost impossible and accurate mask annotation is labor-intensive. To deal with the problems, we present S$^3$POT, a contrast-driven framework synergizing face generation with self-supervised spatial prompting, to achieve occlusion segmentation. The framework is inspired by the insights: 1) Modern face generators' ability to realistically reconstruct occluded regions, creating an image that preserve facial geometry while eliminating occlusion, and 2) Foundation segmentation models' (e.g., SAM) capacity to extract precise mask when provided with appropriate prompts. In particular, S$^3$POT consists of three modules: Reference Generation (RF), Feature enhancement (FE), and Prompt Selection (PS). First, a reference image is produced by RF using structural guidance from parsed mask. Second, FE performs contrast of tokens between raw and reference images to obtain an initial prompt, then modifies image features with the prompt by cross-attention. Third, based on the enhanced features, PS constructs a set of positive and negative prompts and screens them with a self-attention network for a mask decoder. The network is learned under the guidance of three novel and complementary objective functions without occlusion ground truth mask involved. Extensive experiments on a dedicatedly collected dataset demonstrate S$^3$POT's superior performance and the effectiveness of each module. --- ### Action-Free Offline-to-Online RL via Discretised State Policies Authors: Natinael Solomon Neggatu, Jeremie Houssineau, Giovanni Montana Published: 2026-01-31 Categories: stat.ML, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2602.00629v1 Most existing offline RL methods presume the availability of action labels within the dataset, but in many practical scenarios, actions may be missing due to privacy, storage, or sensor limitations. We formalise the setting of action-free offline-to-online RL, where agents must learn from datasets consisting solely of $(s,r,s')$ tuples and later leverage this knowledge during online interaction. To address this challenge, we propose learning state policies that recommend desirable next-state transitions rather than actions. Our contributions are twofold. First, we introduce a simple yet novel state discretisation transformation and propose Offline State-Only DecQN (\algo), a value-based algorithm designed to pre-train state policies from action-free data. \algo{} integrates the transformation to scale efficiently to high-dimensional problems while avoiding instability and overfitting associated with continuous state prediction. Second, we propose a novel mechanism for guided online learning that leverages these pre-trained state policies to accelerate the learning of online agents. Together, these components establish a scalable and practical framework for leveraging action-free datasets to accelerate online RL. Empirical results across diverse benchmarks demonstrate that our approach improves convergence speed and asymptotic performance, while analyses reveal that discretisation and regularisation are critical to its effectiveness. --- ### From Associations to Activations: Comparing Behavioral and Hidden-State Semantic Geometry in LLMs Authors: Louis Schiekiera, Max Zimmer, Christophe Roux, Sebastian Pokutta, Fritz Günther Published: 2026-01-31 Categories: cs.LG, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2602.00628v2 We investigate the extent to which an LLM's hidden-state geometry can be recovered from its behavior in psycholinguistic experiments. Across eight instruction-tuned transformer models, we run two experimental paradigms -- similarity-based forced choice and free association -- over a shared 5,000-word vocabulary, collecting 17.5M+ trials to build behavior-based similarity matrices. Using representational similarity analysis, we compare behavioral geometries to layerwise hidden-state similarity and benchmark against FastText, BERT, and cross-model consensus. We find that forced-choice behavior aligns substantially more with hidden-state geometry than free association. In a held-out-words regression, behavioral similarity (especially forced choice) predicts unseen hidden-state similarities beyond lexical baselines and cross-model consensus, indicating that behavior-only measurements retain recoverable information about internal semantic geometry. Finally, we discuss implications for the ability of behavioral tasks to uncover hidden cognitive states. --- ### FaceSnap: Enhanced ID-fidelity Network for Tuning-free Portrait Customization Authors: Benxiang Zhai, Yifang Xu, Guofeng Zhang, Yang Li, Sidan Du Published: 2026-01-31 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.00627v1 Benefiting from the significant advancements in text-to-image diffusion models, research in personalized image generation, particularly customized portrait generation, has also made great strides recently. However, existing methods either require time-consuming fine-tuning and lack generalizability or fail to achieve high fidelity in facial details. To address these issues, we propose FaceSnap, a novel method based on Stable Diffusion (SD) that requires only a single reference image and produces extremely consistent results in a single inference stage. This method is plug-and-play and can be easily extended to different SD models. Specifically, we design a new Facial Attribute Mixer that can extract comprehensive fused information from both low-level specific features and high-level abstract features, providing better guidance for image generation. We also introduce a Landmark Predictor that maintains reference identity across landmarks with different poses, providing diverse yet detailed spatial control conditions for image generation. Then we use an ID-preserving module to inject these into the UNet. Experimental results demonstrate that our approach performs remarkably in personalized and customized portrait generation, surpassing other state-of-the-art methods in this domain. --- ### MoDEx: Mixture of Depth-specific Experts for Multivariate Long-term Time Series Forecasting Authors: Hyekyung Yoon, Minhyuk Lee, Imseung Park, Myungjoo Kang Published: 2026-01-31 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2602.00624v1 Multivariate long-term time series forecasting (LTSF) supports critical applications such as traffic-flow management, solar-power scheduling, and electricity-transformer monitoring. The existing LTSF paradigms follow a three-stage pipeline of embedding, backbone refinement, and long-horizon prediction. However, the behaviors of individual backbone layers remain underexplored. We introduce layer sensitivity, a gradient-based metric inspired by GradCAM and effective receptive field theory, which quantifies both positive and negative contributions of each time point to a layer's latent features. Applying this metric to a three-layer MLP backbone reveals depth-specific specialization in modeling temporal dynamics in the input sequence. Motivated by these insights, we propose MoDEx, a lightweight Mixture of Depth-specific Experts, which replaces complex backbones with depth-specific MLP experts. MoDEx achieves state-of-the-art accuracy on seven real-world benchmarks, ranking first in 78 percent of cases, while using significantly fewer parameters and computational resources. It also integrates seamlessly into transformer variants, consistently boosting their performance and demonstrating robust generalizability as an efficient and high-performance LTSF framework. --- ### Towards Interpretable Hallucination Analysis and Mitigation in LVLMs via Contrastive Neuron Steering Authors: Guangtao Lyu, Xinyi Cheng, Qi Liu, Chenghao Xu, Jiexi Yan, Muli Yang, Fen Fang, Cheng Deng Published: 2026-01-31 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.00621v1 LVLMs achieve remarkable multimodal understanding and generation but remain susceptible to hallucinations. Existing mitigation methods predominantly focus on output-level adjustments, leaving the internal mechanisms that give rise to these hallucinations largely unexplored. To gain a deeper understanding, we adopt a representation-level perspective by introducing sparse autoencoders (SAEs) to decompose dense visual embeddings into sparse, interpretable neurons. Through neuron-level analysis, we identify distinct neuron types, including always-on neurons and image-specific neurons. Our findings reveal that hallucinations often result from disruptions or spurious activations of image-specific neurons, while always-on neurons remain largely stable. Moreover, selectively enhancing or suppressing image-specific neurons enables controllable intervention in LVLM outputs, improving visual grounding and reducing hallucinations. Building on these insights, we propose Contrastive Neuron Steering (CNS), which identifies image-specific neurons via contrastive analysis between clean and noisy inputs. CNS selectively amplifies informative neurons while suppressing perturbation-induced activations, producing more robust and semantically grounded visual representations. This not only enhances visual understanding but also effectively mitigates hallucinations. By operating at the prefilling stage, CNS is fully compatible with existing decoding-stage methods. Extensive experiments on both hallucination-focused and general multimodal benchmarks demonstrate that CNS consistently reduces hallucinations while preserving overall multimodal understanding. --- ### Rethinking Zero-Shot Time Series Classification: From Task-specific Classifiers to In-Context Inference Authors: Juntao Fang, Shifeng Xie, Shengbin Nie, Yuhui Ling, Yuming Liu, Zijian Li, Keli Zhang, Lujia Pan, Themis Palpanas, Ruichu Cai Published: 2026-01-31 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2602.00620v2 The zero-shot evaluation of time series foundation models (TSFMs) for classification typically uses a frozen encoder followed by a task-specific classifier. However, this practice violates the training-free premise of zero-shot deployment and introduces evaluation bias due to classifier-dependent training choices. To address this issue, we propose TIC-FM, an in-context learning framework that treats the labeled training set as context and predicts labels for all test instances in a single forward pass, without parameter updates. TIC-FM pairs a time series encoder and a lightweight projection adapter with a split-masked latent memory Transformer. We further provide theoretical justification that in-context inference can subsume trained classifiers and can emulate gradient-based classifier training within a single forward pass. Experiments on 128 UCR datasets show strong accuracy, with consistent gains in the extreme low-label situation, highlighting training-free transfer for time series classification.The source code is publicly available at https://github.com/fangjuntao/TIC-FM. --- ### Jailbreaking LLMs via Calibration Authors: Yuxuan Lu, Yongkang Guo, Yuqing Kong Published: 2026-01-31 Categories: cs.CL, cs.AI, cs.CR, cs.LG arXiv: https://arxiv.org/abs/2602.00619v1 Safety alignment in Large Language Models (LLMs) often creates a systematic discrepancy between a model's aligned output and the underlying pre-aligned data distribution. We propose a framework in which the effect of safety alignment on next-token prediction is modeled as a systematic distortion of a pre-alignment distribution. We cast Weak-to-Strong Jailbreaking as a forecast aggregation problem and derive an optimal aggregation strategy characterized by a Gradient Shift in the loss-induced dual space. We show that logit-arithmetic jailbreaking methods are a special case of this framework under cross-entropy loss, and derive a broader family of aggregation rules corresponding to other proper losses. We also propose a new hybrid aggregation rule. Evaluations across red-teaming benchmarks and math utility tasks using frontier models demonstrate that our approach achieves superior Attack Success Rates and lower "Jailbreak Tax" compared with existing methods, especially on the safety-hardened gpt-oss-120b. --- ### Tune-Your-Style: Intensity-tunable 3D Style Transfer with Gaussian Splatting Authors: Yian Zhao, Rushi Ye, Ruochong Zheng, Zesen Cheng, Chaoran Feng, Jiashu Yang, Pengchong Qiao, Chang Liu, Jie Chen Published: 2026-01-31 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.00618v1 3D style transfer refers to the artistic stylization of 3D assets based on reference style images. Recently, 3DGS-based stylization methods have drawn considerable attention, primarily due to their markedly enhanced training and rendering speeds. However, a vital challenge for 3D style transfer is to strike a balance between the content and the patterns and colors of the style. Although the existing methods strive to achieve relatively balanced outcomes, the fixed-output paradigm struggles to adapt to the diverse content-style balance requirements from different users. In this work, we introduce a creative intensity-tunable 3D style transfer paradigm, dubbed \textbf{Tune-Your-Style}, which allows users to flexibly adjust the style intensity injected into the scene to match their desired content-style balance, thus enhancing the customizability of 3D style transfer. To achieve this goal, we first introduce Gaussian neurons to explicitly model the style intensity and parameterize a learnable style tuner to achieve intensity-tunable style injection. To facilitate the learning of tunable stylization, we further propose the tunable stylization guidance, which obtains multi-view consistent stylized views from diffusion models through cross-view style alignment, and then employs a two-stage optimization strategy to provide stable and efficient guidance by modulating the balance between full-style guidance from the stylized views and zero-style guidance from the initial rendering. Extensive experiments demonstrate that our method not only delivers visually appealing results, but also exhibits flexible customizability for 3D style transfer. Project page is available at https://zhao-yian.github.io/TuneStyle. --- ### SPOT: Selective Prompt Projection via Total Variation for Inference-Only Safe Text-to-Image Generation Authors: Minhyuk Lee, Hyekyung Yoon, Myungjoo Kang Published: 2026-01-31 Categories: cs.AI arXiv: https://arxiv.org/abs/2602.00616v3 Text-to-Image (T2I) diffusion models enable high quality open ended synthesis, but practical use requires suppressing unsafe generations while preserving behavior on benign prompts. We study this tension relative to the frozen generator, using its prompt conditioned distribution as the preservation reference. Since T2I safety is commonly evaluated by bounded risk scores on generated images, total variation (TV) bounds how much expected risk can change from this reference. We call this fixed reference constraint the Safety-Prompt Alignment Tradeoff (SPAT): reducing expected unsafety requires prompt conditioned distributional deviation. To make this deviation selective and adjustable, we define the tau safe set as prompts whose reference risk is at most tau, and cast intervention as projection toward nearby prompts in this set. We propose Selective Prompt prOjecTion (SPOT), an inference time framework that approximates this projection without retraining the generator or learning a category specific rewriter. SPOT uses an LLM to rank candidate rewrites and a safeguard VLM to accept generated images under the same tau. Across four datasets and three diffusion backbones, SPOT achieves relative inappropriate (IP) score reductions from 14.2% to 44.4% over strong safety alignment baselines while keeping benign prompt behavior close to the fixed reference. --- ### Transformer-Based Model for Multilingual Hope Speech Detection Authors: Nsrin Ashraf, Mariam Labib, Hamada Nayel Published: 2026-01-31 Categories: cs.CL arXiv: https://arxiv.org/abs/2602.00613v1 This paper describes a system that has been submitted to the "PolyHope-M" at RANLP2025. In this work various transformers have been implemented and evaluated for hope speech detection for English and Germany. RoBERTa has been implemented for English, while the multilingual model XLM-RoBERTa has been implemented for both English and German languages. The proposed system using RoBERTa reported a weighted f1-score of 0.818 and an accuracy of 81.8% for English. On the other hand, XLM-RoBERTa achieved a weighted f1-score of 0.786 and an accuracy of 78.5%. These results reflects the importance of improvement of pre-trained large language models and how these models enhancing the performance of different natural language processing tasks. --- ### Lookahead-then-Verify: Reliable Constrained Decoding for Diffusion LLMs under Context-Free Grammars Authors: Yitong Zhang, Yongmin Li, Yuetong Liu, Jia Li, Xiaoran Jia, Zherui Li, Ge Li Published: 2026-01-31 Categories: cs.CL arXiv: https://arxiv.org/abs/2602.00612v3 Diffusion Large Language Models (dLLMs) have demonstrated promising generative capabilities and are increasingly used to produce formal languages defined by context-free grammars, such as source code and chemical expressions. However, as probabilistic models, they still struggle to generate syntactically valid outputs reliably. A natural and promising direction to address this issue is to adapt constrained decoding techniques to enforce grammatical correctness during generation. However, applying these techniques faces two primary obstacles. On the one hand, the non-autoregressive nature of dLLMs renders most existing constrained decoding approaches inapplicable. On the other hand, current approaches specifically designed for dLLMs may allow intermediate outputs that are impossible to complete into valid sentences, which significantly limits their reliability in practice. To address these challenges, we present LAVE, a constrained decoding approach specifically designed for dLLMs. Our approach leverages a key property of dLLMs, namely their ability to predict token distributions for all positions in parallel during each forward pass. Whenever a new token is proposed by model, LAVE performs lookahead using these distributions to efficiently and reliably verify the validity of the proposed token. This design ensures reliable constraints by reliably preserving the potential for intermediate outputs to be extended into valid sentences. Extensive experiments across four widely used dLLMs and three representative benchmarks demonstrate that LAVE consistently outperforms existing baselines and achieves substantial improvements in syntactic correctness, while incurring negligible runtime overhead. --- ### Structured Self-Consistency:A Multi-Task Evaluation of LLMs on VirtualHome Authors: Jiaqi Xu, Tao Huang, Kai Zhang Published: 2026-01-31 Categories: cs.AI arXiv: https://arxiv.org/abs/2602.00611v2 Embodied AI requires agents to understand goals, plan actions, and execute tasks in simulated environments. We present a comprehensive evaluation of Large Language Models (LLMs) on the VirtualHome benchmark using the Embodied Agent Interface (EAI) framework. We compare two representative 7B-parameter models OPENPANGU-7B and QWEN2.5-7B across four fundamental tasks: Goal Interpretation, Action Sequencing, Subgoal Decomposition, and Transition Modeling. We propose Structured Self-Consistency (SSC), an enhanced decoding strategy that leverages multiple sampling with domain-specific voting mechanisms to improve output quality for structured generation tasks. Experimental results demonstrate that SSC significantly enhances performance, with OPENPANGU-7B excelling at hierarchical planning while QWEN2.5-7B show advantages in action-level tasks. Our analysis reveals complementary strengths across model types, providing insights for future embodied AI system development. ---