# Research Papers — 2026-02 · bundle page 199 of 210 > Full-text markdown of papers #9901–9950 of 10493 published in 2026-02, newest first. AI-readable mirrors of the full 10493-paper 2026-02 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2026-02/page/199 [← Previous bundle](https://aipod.dev/papers/archive/2026-02/page/198.md) [Next bundle →](https://aipod.dev/papers/archive/2026-02/page/200.md) ### FlyPrompt: Brain-Inspired Random-Expanded Routing with Temporal-Ensemble Experts for General Continual Learning Authors: Hongwei Yan, Guanglong Sun, Kanglei Zhou, Qian Li, Liyuan Wang, Yi Zhong Published: 2026-02-02 Categories: cs.LG, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2602.01976v3 General continual learning (GCL) challenges intelligent systems to learn from single-pass, non-stationary data streams without clear task boundaries. While recent advances in continual parameter-efficient tuning (PET) of pretrained models show promise, they typically rely on multiple training epochs and explicit task cues, limiting their effectiveness in GCL scenarios. Moreover, existing methods often lack targeted design and fail to address two fundamental challenges in continual PET: how to allocate expert parameters to evolving data distributions, and how to improve their representational capacity under limited supervision. Inspired by the fruit fly's hierarchical memory system characterized by sparse expansion and modular ensembles, we propose FlyPrompt, a brain-inspired framework that decomposes GCL into two subproblems: expert routing and expert competence improvement. FlyPrompt introduces a randomly expanded analytic router for instance-level expert activation and a temporal ensemble of output heads to dynamically adapt decision boundaries over time. Extensive theoretical and empirical evaluations demonstrate FlyPrompt's superior performance, achieving up to 11.23%, 12.43%, and 7.62% gains over state-of-the-art baselines on CIFAR-100, ImageNet-R, and CUB-200, respectively. Our source code is available at https://github.com/AnAppleCore/FlyGCL. --- ### IntraSlice: Towards High-Performance Structural Pruning with Block-Intra PCA for LLMs Authors: Meng Li, Peisong Wang, Yuantian Shao, Qinghao Hu, Hongjian Fang, Yifan Zhang, Zhihui Wei, Jian Cheng Published: 2026-02-02 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2602.01975v1 Large Language Models (LLMs) achieve strong performance across diverse tasks but face deployment challenges due to their massive size. Structured pruning offers acceleration benefits but leads to significant performance degradation. Recent PCA-based pruning methods have alleviated this issue by retaining key activation components, but are only applied between modules in order to fuse the transformation matrix, which introduces extra parameters and severely disrupts activation distributions due to residual connections. To address these issues, we propose IntraSlice, a framework that applies block-wise module-intra PCA compression pruning. By leveraging the structural characteristics of Transformer modules, we design an approximate PCA method whose transformation matrices can be fully fused into the model without additional parameters. We also introduce a PCA-based global pruning ratio estimator that further considers the distribution of compressed activations, building on conventional module importance. We validate our method on Llama2, Llama3, and Phi series across various language benchmarks. Experimental results demonstrate that our approach achieves superior compression performance compared to recent baselines at the same compression ratio or inference speed. --- ### Your AI-Generated Image Detector Can Secretly Achieve SOTA Accuracy, If Calibrated Authors: Muli Yang, Gabriel James Goenawan, Henan Wang, Huaiyuan Qin, Chenghao Xu, Yanhua Yang, Fen Fang, Ying Sun, Joo-Hwee Lim, Hongyuan Zhu Published: 2026-02-02 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2602.01973v1 Despite being trained on balanced datasets, existing AI-generated image detectors often exhibit systematic bias at test time, frequently misclassifying fake images as real. We hypothesize that this behavior stems from distributional shift in fake samples and implicit priors learned during training. Specifically, models tend to overfit to superficial artifacts that do not generalize well across different generation methods, leading to a misaligned decision threshold when faced with test-time distribution shift. To address this, we propose a theoretically grounded post-hoc calibration framework based on Bayesian decision theory. In particular, we introduce a learnable scalar correction to the model's logits, optimized on a small validation set from the target distribution while keeping the backbone frozen. This parametric adjustment compensates for distributional shift in model output, realigning the decision boundary even without requiring ground-truth labels. Experiments on challenging benchmarks show that our approach significantly improves robustness without retraining, offering a lightweight and principled solution for reliable and adaptive AI-generated image detection in the open world. Code is available at https://github.com/muliyangm/AIGI-Det-Calib. --- ### Small Generalizable Prompt Predictive Models Can Steer Efficient RL Post-Training of Large Reasoning Models Authors: Yun Qu, Qi Wang, Yixiu Mao, Heming Zou, Yuhang Jiang, Weijie Liu, Clive Bai, Kai Yang, Yangkun Chen, Saiyong Yang, Xiangyang Ji Published: 2026-02-02 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2602.01970v2 Reinforcement learning enhances the reasoning capabilities of large language models but often involves high computational costs due to rollout-intensive optimization. Online prompt selection presents a plausible solution by prioritizing informative prompts to improve training efficiency. However, current methods either depend on costly, exact evaluations or construct prompt-specific predictive models lacking generalization across prompts. This study introduces Generalizable Predictive Prompt Selection (GPS), which performs Bayesian inference towards prompt difficulty using a lightweight generative model trained on the shared optimization history. Intermediate-difficulty prioritization and history-anchored diversity are incorporated into the batch acquisition principle to select informative prompt batches. The small predictive model also generalizes at test-time for efficient computational allocation. Experiments across varied reasoning benchmarks indicate GPS's substantial improvements in training efficiency, final performance, and test-time efficiency over superior baseline methods. --- ### Orthogonal Hierarchical Decomposition for Structure-Aware Table Understanding with Large Language Models Authors: Bin Cao, Huixian Lu, Chenwen Ma, Ting Wang, Ruizhe Li, Jing Fan Published: 2026-02-02 Categories: cs.CL, cs.IR arXiv: https://arxiv.org/abs/2602.01969v2 Complex tables with multi-level headers, merged cells and heterogeneous layouts pose persistent challenges for LLMs in both understanding and reasoning. Existing approaches typically rely on table linearization or normalized grid modeling. However, these representations struggle to explicitly capture hierarchical structures and cross-dimensional dependencies, which can lead to misalignment between structural semantics and textual representations for non-standard tables. To address this issue, we propose an Orthogonal Hierarchical Decomposition (OHD) framework that constructs structure-preserving input representations of complex tables for LLMs. OHD introduces an Orthogonal Tree Induction (OTI) method based on spatial--semantic co-constraints, which decomposes irregular tables into a column tree and a row tree to capture vertical and horizontal hierarchical dependencies, respectively. Building on this representation, we design a dual-pathway association protocol to symmetrically reconstruct semantic lineage of each cell, and incorporate an LLM as a semantic arbitrator to align multi-level semantic information. We evaluate OHD framework on two complex table question answering benchmarks, AITQA and HiTab. Experimental results show that OHD consistently outperforms existing representation paradigms across multiple evaluation metrics. --- ### Mixture-of-Experts with Intermediate CTC Supervision for Accented Speech Recognition Authors: Wonjun Lee, Hyounghun Kim, Gary Geunbae Lee Published: 2026-02-02 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2602.01967v1 Accented speech remains a persistent challenge for automatic speech recognition (ASR), as most models are trained on data dominated by a few high-resource English varieties, leading to substantial performance degradation for other accents. Accent-agnostic approaches improve robustness yet struggle with heavily accented or unseen varieties, while accent-specific methods rely on limited and often noisy labels. We introduce Moe-Ctc, a Mixture-of-Experts architecture with intermediate CTC supervision that jointly promotes expert specialization and generalization. During training, accent-aware routing encourages experts to capture accent-specific patterns, which gradually transitions to label-free routing for inference. Each expert is equipped with its own CTC head to align routing with transcription quality, and a routing-augmented loss further stabilizes optimization. Experiments on the Mcv-Accent benchmark demonstrate consistent gains across both seen and unseen accents in low- and high-resource conditions, achieving up to 29.3% relative WER reduction over strong FastConformer baselines. --- ### Self-Consolidation for Self-Evolving Agents Authors: Hongzhuo Yu, Fei Zhu, Guo-Sen Xie, Ling Shao Published: 2026-02-02 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.01966v1 While large language model (LLM) agents have demonstrated impressive problem-solving capabilities, they typically operate as static systems, lacking the ability to evolve through lifelong interaction. Existing attempts to bridge this gap primarily rely on retrieving successful past trajectories as demonstrations. However, this paradigm faces two critical limitations. First, by focusing solely on success, agents overlook the rich pedagogical value embedded in failed attempts, preventing them from identifying and avoiding recurrent pitfalls. Second, continually accumulating textual experiences not only increases the time consumption during retrieval but also inevitably introduces noise and exhausts the largest context window of current LLMs. To address these challenges, we propose a novel self-evolving framework for LLM agents that introduces a complementary evolution mechanism: First, a contrastive reflection strategy is introduced to explicitly summarize error-prone patterns and capture reusable insights. Second, we propose a self-consolidation mechanism that distills non-parametric textual experience into compact learnable parameters. This enables the agent to internalize extensive historical experience directly into its latent space. Extensive experiments demonstrate the advantages of our method in long-term agent evolution. --- ### Breaking the Static Graph: Context-Aware Traversal for Robust Retrieval-Augmented Generation Authors: Kwun Hang Lau, Fangyuan Zhang, Boyu Ruan, Yingli Zhou, Qintian Guo, Ruiyuan Zhang, Xiaofang Zhou Published: 2026-02-02 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2602.01965v1 Recent advances in Retrieval-Augmented Generation (RAG) have shifted from simple vector similarity to structure-aware approaches like HippoRAG, which leverage Knowledge Graphs (KGs) and Personalized PageRank (PPR) to capture multi-hop dependencies. However, these methods suffer from a "Static Graph Fallacy": they rely on fixed transition probabilities determined during indexing. This rigidity ignores the query-dependent nature of edge relevance, causing semantic drift where random walks are diverted into high-degree "hub" nodes before reaching critical downstream evidence. Consequently, models often achieve high partial recall but fail to retrieve the complete evidence chain required for multi-hop queries. To address this, we propose CatRAG, Context-Aware Traversal for robust RAG, a framework that builds on the HippoRAG 2 architecture and transforms the static KG into a query-adaptive navigation structure. We introduce a multi-faceted framework to steer the random walk: (1) Symbolic Anchoring, which injects weak entity constraints to regularize the random walk; (2) Query-Aware Dynamic Edge Weighting, which dynamically modulates graph structure, to prune irrelevant paths while amplifying those aligned with the query's intent; and (3) Key-Fact Passage Weight Enhancement, a cost-efficient bias that structurally anchors the random walk to likely evidence. Experiments across four multi-hop benchmarks demonstrate that CatRAG consistently outperforms state of the art baselines. Our analysis reveals that while standard Recall metrics show modest gains, CatRAG achieves substantial improvements in reasoning completeness, the capacity to recover the entire evidence path without gaps. These results reveal that our approach effectively bridges the gap between retrieving partial context and enabling fully grounded reasoning. Resources are available at https://github.com/kwunhang/CatRAG. --- ### Zero-Shot Off-Policy Learning Authors: Arip Asadulaev, Maksim Bobrin, Salem Lahlou, Dmitry Dylov, Fakhri Karray, Martin Takac Published: 2026-02-02 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2602.01962v2 Off-policy learning methods seek to derive an optimal policy directly from a fixed dataset of prior interactions. This objective presents significant challenges, primarily due to the inherent distributional shift and value function overestimation bias. These issues become even more noticeable in zero-shot reinforcement learning, where an agent trained on reward-free data must adapt to new tasks at test time without additional training. In this work, we address the off-policy problem in a zero-shot setting by discovering a theoretical connection of successor measures to stationary density ratios. Using this insight, our algorithm can infer optimal importance sampling ratios, effectively performing a stationary distribution correction with an optimal policy for any task on the fly. We benchmark our method in motion tracking tasks on SMPL Humanoid, continuous control on ExoRL, and for the long-horizon OGBench tasks. Our technique seamlessly integrates into forward-backward representation frameworks and enables fast-adaptation to new tasks in a training-free regime. More broadly, this work bridges off-policy learning and zero-shot adaptation, offering benefits to both research areas. --- ### Grounding Generated Videos in Feasible Plans via World Models Authors: Christos Ziakas, Amir Bar, Alessandra Russo Published: 2026-02-02 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.01960v3 Large-scale video generative models have shown emerging capabilities as zero-shot visual planners, yet video-generated plans often violate temporal consistency and physical constraints, leading to failures when mapped to executable actions. To address this, we propose Grounding Video Plans with World Models (GVP-WM), a planning method that grounds video-generated plans into feasible action sequences using a learned action-conditioned world model. At test-time, GVP-WM first generates a video plan from initial and goal observations, then projects the video guidance onto the manifold of dynamically feasible latent trajectories via video-guided latent collocation. In particular, we formulate grounding as a goal-conditioned latent-space trajectory optimization problem that jointly optimizes latent states and actions under world-model dynamics, while preserving semantic alignment with the video-generated plan. Empirically, GVP-WM recovers feasible long-horizon plans from zero-shot image-to-video-generated and motion-blurred videos that violate physical constraints, across navigation and manipulation simulation tasks. --- ### Efficient Epistemic Uncertainty Estimation for Large Language Models via Knowledge Distillation Authors: Seonghyeon Park, Jewon Yeom, Jaewon Sok, Jeongjae Park, Heejun Kim, Taesup Kim Published: 2026-02-02 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2602.01956v1 Quantifying uncertainty in Large Language Models (LLMs) is essential for mitigating hallucinations and enabling risk-aware deployment in safety-critical tasks. However, estimating Epistemic Uncertainty(EU) via Deep Ensembles is computationally prohibitive at the scale of modern models. We propose a framework that leverages the small draft models to efficiently estimate token-level EU, bypassing the need for full-scale ensembling. Theoretically grounded in a Bias-Variance Decomposition, our approach approximates EU via Jensen-Shannon divergence among drafts (variance proxy) and KL divergence between the draft mixture and the target (bias proxy). To further ensure accuracy without significant overhead, we introduce Online Stochastic Distillation (OSD) to efficiently approximate target aggregation and the Data-Diverse Drafts (DDD) strategy to enhance draft diversity for better target approximation. Extensive experiments on GSM8K demonstrate that our method reduces the estimation error (RMSE) by up to 37% compared to baselines. Crucially, our approach achieves Hallucination Detection performance competitive with heavy perturbation-based methods like TokUR while incurring negligible inference costs, offering a practical solution for uncertainty-aware LLM deployment. --- ### Beyond Open Vocabulary: Multimodal Prompting for Object Detection in Remote Sensing Images Authors: Shuai Yang, Ziyue Huang, Jiaxin Chen, Qingjie Liu, Yunhong Wang Published: 2026-02-02 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.01954v1 Open-vocabulary object detection in remote sensing commonly relies on text-only prompting to specify target categories, implicitly assuming that inference-time category queries can be reliably grounded through pretraining-induced text-visual alignment. In practice, this assumption often breaks down in remote sensing scenarios due to task- and application-specific category semantics, resulting in unstable category specification under open-vocabulary settings. To address this limitation, we propose RS-MPOD, a multimodal open-vocabulary detection framework that reformulates category specification beyond text-only prompting by incorporating instance-grounded visual prompts, textual prompts, and their multimodal integration. RS-MPOD introduces a visual prompt encoder to extract appearance-based category cues from exemplar instances, enabling text-free category specification, and a multimodal fusion module to integrate visual and textual information when both modalities are available. Extensive experiments on standard, cross-dataset, and fine-grained remote sensing benchmarks show that visual prompting yields more reliable category specification under semantic ambiguity and distribution shifts, while multimodal prompting provides a flexible alternative that remains competitive when textual semantics are well aligned. --- ### Deep Multivariate Models with Parametric Conditionals Authors: Dmitrij Schlesinger, Boris Flach, Alexander Shekhovtsov Published: 2026-02-02 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2602.01953v1 We consider deep multivariate models for heterogeneous collections of random variables. In the context of computer vision, such collections may e.g. consist of images, segmentations, image attributes, and latent variables. When developing such models, most existing works start from an application task and design the model components and their dependencies to meet the needs of the chosen task. This has the disadvantage of limiting the applicability of the resulting model for other downstream tasks. Here, instead, we propose to represent the joint probability distribution by means of conditional probability distributions for each group of variables conditioned on the rest. Such models can then be used for practically any possible downstream task. Their learning can be approached as training a parametrised Markov chain kernel by maximising the data likelihood of its limiting distribution. This has the additional advantage of allowing a wide range of semi-supervised learning scenarios. --- ### Enabling Progressive Whole-slide Image Analysis with Multi-scale Pyramidal Network Authors: Shuyang Wu, Yifu Qiu, Ines P Nearchou, Sandrine Prost, Jonathan A Fallowfield, Hakan Bilen, Timothy J Kendall Published: 2026-02-02 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.01951v2 Multiple-instance Learning (MIL) is commonly used for computational pathology (CPath), where multi-scale features are essential for capturing both fine cellular details and broad tissue architecture. However, existing multi-scale MIL approaches typically rely on the inflexible multi-magnification inputs or the computationally expensive architectures. As pre-trained foundation models (FMs) become the trend for feature extraction and boost lightweight models, we rethink and explore a more efficient multi-scale MIL method. In this paper, we propose the Multi-scale Pyramidal Network (MSPN), a plug-and-play module for attention-based MIL. MSPN introduces progressive multi-scale whole-slide image analysis using only a single high-magnification input. It consists of (1) grid-based remapping that aggregates high-magnification features to derive spatially-aware coarse feature maps, and (2) the Coarse Guidance Network (CGN) that learns coarse contexts. We benchmark MSPN as an add-on module to 4 attention-based frameworks on 5 clinically relevant tasks with 2 foundation models, and a pre-trained MIL framework. Our results demonstrate that MSPN consistently improves MIL across the compared configurations and tasks, while being lightweight and easy-to-use. --- ### Boundary-Constrained Diffusion Models for Floorplan Generation: Balancing Realism and Diversity Authors: Leonardo Stoppani, Davide Bacciu, Shahab Mokarizadeh Published: 2026-02-02 Categories: cs.LG, cs.CV arXiv: https://arxiv.org/abs/2602.01949v1 Diffusion models have become widely popular for automated floorplan generation, producing highly realistic layouts conditioned on user-defined constraints. However, optimizing for perceptual metrics such as the Fréchet Inception Distance (FID) causes limited design diversity. To address this, we propose the Diversity Score (DS), a metric that quantifies layout diversity under fixed constraints. Moreover, to improve geometric consistency, we introduce a Boundary Cross-Attention (BCA) module that enables conditioning on building boundaries. Our experiments show that BCA significantly improves boundary adherence, while prolonged training drives diversity collapse undiagnosed by FID, revealing a critical trade-off between realism and diversity. Out-Of-Distribution evaluations further demonstrate the models' reliance on dataset priors, emphasizing the need for generative systems that explicitly balance fidelity, diversity, and generalization in architectural design tasks. --- ### Human Society-Inspired Approaches to Agentic AI Security: The 4C Framework Authors: Alsharif Abuadbba, Nazatul Sultan, Surya Nepal, Sanjay Jha Published: 2026-02-02 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2602.01942v1 AI is moving from domain-specific autonomy in closed, predictable settings to large-language-model-driven agents that plan and act in open, cross-organizational environments. As a result, the cybersecurity risk landscape is changing in fundamental ways. Agentic AI systems can plan, act, collaborate, and persist over time, functioning as participants in complex socio-technical ecosystems rather than as isolated software components. Although recent work has strengthened defenses against model and pipeline level vulnerabilities such as prompt injection, data poisoning, and tool misuse, these system centric approaches may fail to capture risks that arise from autonomy, interaction, and emergent behavior. This article introduces the 4C Framework for multi-agent AI security, inspired by societal governance. It organizes agentic risks across four interdependent dimensions: Core (system, infrastructure, and environmental integrity), Connection (communication, coordination, and trust), Cognition (belief, goal, and reasoning integrity), and Compliance (ethical, legal, and institutional governance). By shifting AI security from a narrow focus on system-centric protection to the broader preservation of behavioral integrity and intent, the framework complements existing AI security strategies and offers a principled foundation for building agentic AI systems that are trustworthy, governable, and aligned with human values. --- ### FluxNet: Learning Capacity-Constrained Local Transport Operators for Conservative and Bounded PDE Surrogates Authors: Zishuo Lan, Junjie Li, Lei Wang, Jincheng Wang Published: 2026-02-02 Categories: cond-mat.mtrl-sci, cs.CE, cs.LG, physics.comp-ph arXiv: https://arxiv.org/abs/2602.01941v2 Autoregressive learning of time-stepping operators provides an effective approach to data-driven partial differential equation (PDE) simulation, yet for conservation laws, they face a fundamental challenge: learned updates may violate global conservation over long rollouts. For the important subclass of mass-conservation-type equations, the problem is compounded by inherent physical bounds (e.g., nonnegativity or concentrations in (0,1)) whose violation further destabilizes predictions. We introduce FluxNet, which learns cumulative transport amounts representing the total conserved quantity redistributed between each cell and a configurable neighborhood over the full surrogate interval. A conservative update guarantees exact discrete conservation by construction; modular capacity-constrained transport heads (L, U, and D) enforce lower bounds, upper bounds, or near-zero dual-bound violations through architectural design. Unlike flux-rate surrogates that require temporal integration and thus inherit CFL constraints, FluxNet involves no such integration; configurable transport neighborhoods enable large-timestep prediction at full spatial resolution. Ghost cells extend the framework to non-periodic boundaries. Experiments on four benchmarks (1D convection--diffusion, 2D shallow water, 1D traffic flow, 2D Cahn--Hilliard) demonstrate exact conservation, structural bound preservation, architecture modularity, and superior stability over flux-rate surrogates at large temporal strides. The code is publicly available at: https://github.com/Lan-zs/FluxNet. --- ### Towards Exploratory and Focused Manipulation with Bimanual Active Perception: A New Problem, Benchmark and Strategy Authors: Yuxin He, Ruihao Zhang, Tianao Shen, Cheng Liu, Qiang Nie Published: 2026-02-02 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2602.01939v3 Recently, active vision has reemerged as an important concept for manipulation, since visual occlusion occurs more frequently when main cameras are mounted on the robot heads. We reflect on the visual occlusion issue and identify its essence as the absence of information useful for task completion. Inspired by this, we come up with the more fundamental problem of Exploratory and Focused Manipulation (EFM). The proposed problem is about actively collecting information to complete challenging manipulation tasks that require exploration or focus. As an initial attempt to address this problem, we establish the EFM-10 benchmark that consists of 4 categories of tasks that align with our definition (10 tasks in total). We further come up with a Bimanual Active Perception (BAP) strategy, which leverages one arm to provide active vision and another arm to provide force sensing while manipulating. Based on this idea, we collect a dataset named BAPData for the tasks in EFM-10. With the dataset, we successfully verify the effectiveness of the BAP strategy in an imitation learning manner. We hope that the EFM-10 benchmark along with the BAP strategy can become a cornerstone that facilitates future research towards this direction. Project website: EFManipulation.github.io. --- ### T-LLM: Teaching Large Language Models to Forecast Time Series via Temporal Distillation Authors: Suhan Guo, Bingxu Wang, Shaodan Zhang, Furao Shen Published: 2026-02-02 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2602.01937v1 Time series forecasting plays a critical role in decision-making across many real-world applications. Unlike data in vision and language domains, time series data is inherently tied to the evolution of underlying processes and can only accumulate as real-world time progresses, limiting the effectiveness of scale-driven pretraining alone. This time-bound constraint poses a challenge for enabling large language models (LLMs) to acquire forecasting capability, as existing approaches primarily rely on representation-level alignment or inference-time temporal modules rather than explicitly teaching forecasting behavior to the LLM. We propose T-LLM, a temporal distillation framework that equips general-purpose LLMs with time series forecasting capability by transferring predictive behavior from a lightweight temporal teacher during training. The teacher combines trend modeling and frequency-domain analysis to provide structured temporal supervision, and is removed entirely at inference, leaving the LLM as the sole forecasting model. Experiments on benchmark datasets and infectious disease forecasting tasks demonstrate that T-LLM consistently outperforms existing LLM-based forecasting methods under full-shot, few-shot, and zero-shot settings, while enabling a simple and efficient deployment pipeline. --- ### PIMCST: Physics-Informed Multi-Phase Consensus and Spatio-Temporal Few-Shot Learning for Traffic Flow Forecasting Authors: Abdul Joseph Fofanah, Lian Wen, David Chen Published: 2026-02-02 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2602.01936v1 Accurate traffic flow prediction remains a fundamental challenge in intelligent transportation systems, particularly in cross-domain, data-scarce scenarios where limited historical data hinders model training and generalisation. The complex spatio-temporal dependencies and nonlinear dynamics of urban mobility networks further complicate few-shot learning across different cities. This paper proposes MCPST, a novel Multi-phase Consensus Spatio-Temporal framework for few-shot traffic forecasting that reconceptualises traffic prediction as a multi-phase consensus learning problem. Our framework introduces three core innovations: (1) a multi-phase engine that models traffic dynamics through diffusion, synchronisation, and spectral embeddings for comprehensive dynamic characterisation; (2) an adaptive consensus mechanism that dynamically fuses phase-specific predictions while enforcing consistency; and (3) a structured meta-learning strategy for rapid adaptation to new cities with minimal data. We establish extensive theoretical guarantees, including representation theorems with bounded approximation errors and generalisation bounds for few-shot adaptation. Through experiments on four real-world datasets, MCPST outperforms fourteen state-of-the-art methods in spatio-temporal graph learning methods, dynamic graph transfer learning methods, prompt-based spatio-temporal prediction methods and cross-domain few-shot settings, improving prediction accuracy while reducing required training data and providing interpretable insights. The implementation code is available at https://github.com/afofanah/MCPST. --- ### LiteCoOp: Lightweight Multi-LLM Shared-Tree Reasoning for Model-Serving Compiler Optimizations Authors: Annabelle Sujun Tang, Christopher Priebe, Lianhui Qin, Hadi Esmaeilzadeh Published: 2026-02-02 Categories: cs.LG, cs.AI, cs.PL arXiv: https://arxiv.org/abs/2602.01935v2 LLM-guided compiler optimization has recently shown promise, but existing approaches rely on a single large LLM throughout search, making them expensive and excluding smaller models. We pose the research question: whether heterogeneous LLMs can collaborate during compiler optimization while reducing compilation cost below optimization guided by a single large LLM. Crucially, this must be achieved without introducing overhead from agentic frameworks, which would run counter to the goal of lower compilation cost. To achieve these competing objectives, we introduce LiteCoOp, a lightweight framework that turns the optimization search tree itself into the mechanism for multi-LLM collaboration, enabling heterogeneous models to share progress without external agentic coordination. At each optimization step, LiteCoOp queries one LLM to propose both a compiler transformation and select the LLM to query at the next step. These LLM proposals are recorded in a shared MCTS tree, so all models are invoked serially and yet are informed by each other's decisions. The shared MCTS backpropagates the rewards, allowing progress made by one model to influence later decisions by others. This makes the MCTS tree the collaborative reasoning mechanism itself, avoiding inter-model communication, heavy reasoning traces, or agentic infrastructure. We instantiate this idea with an LLM-aware UCT that biases model selection toward smaller LLMs to reduce cost while still preserving the compiler performance objective. Across diverse GPU and (CPU) benchmarks, LiteCoOp consistently outperforms single-model baselines, with the best results obtained when scaling collaboration to eight heterogeneous LLMs. This eight-model config reduces total compilation time by 1.95x (1.74x), reduces API cost by 4.47x (4.32x), and invokes the largest model for only 23.1% (23.9%) of total calls while demonstrating collaboration scalability. --- ### Large Language Model and Formal Concept Analysis: a comparative study for Topic Modeling Authors: Fabrice Boissier, Monica Sen, Irina Rychkova Published: 2026-02-02 Categories: cs.AI arXiv: https://arxiv.org/abs/2602.01933v1 Topic modeling is a research field finding increasing applications: historically from document retrieving, to sentiment analysis and text summarization. Large Language Models (LLM) are currently a major trend in text processing, but few works study their usefulness for this task. Formal Concept Analysis (FCA) has recently been presented as a candidate for topic modeling, but no real applied case study has been conducted. In this work, we compare LLM and FCA to better understand their strengths and weakneses in the topic modeling field. FCA is evaluated through the CREA pipeline used in past experiments on topic modeling and visualization, whereas GPT-5 is used for the LLM. A strategy based on three prompts is applied with GPT-5 in a zero-shot setup: topic generation from document batches, merging of batch results into final topics, and topic labeling. A first experiment reuses the teaching materials previously used to evaluate CREA, while a second experiment analyzes 40 research articles in information systems to compare the extracted topics with the underling subfields. --- ### LIEREx: Language-Image Embeddings for Robotic Exploration Authors: Felix Igelbrink, Lennart Niecksch, Marian Renz, Martin Günther, Martin Atzmueller Published: 2026-02-02 Categories: cs.RO, cs.CV arXiv: https://arxiv.org/abs/2602.01930v1 Semantic maps allow a robot to reason about its surroundings to fulfill tasks such as navigating known environments, finding specific objects, and exploring unmapped areas. Traditional mapping approaches provide accurate geometric representations but are often constrained by pre-designed symbolic vocabularies. The reliance on fixed object classes makes it impractical to handle out-of-distribution knowledge not defined at design time. Recent advances in Vision-Language Foundation Models, such as CLIP, enable open-set mapping, where objects are encoded as high-dimensional embeddings rather than fixed labels. In LIEREx, we integrate these VLFMs with established 3D Semantic Scene Graphs to enable target-directed exploration by an autonomous agent in partially unknown environments. --- ### Probabilistic function-on-function nonlinear autoregressive model for emulation and reliability analysis of stochastic dynamical systems Authors: Zhouzhou Song, Marcos A. Valdebenito, Styfen Schär, Stefano Marelli, Bruno Sudret, Matthias G. R. Faes Published: 2026-02-02 Categories: math.DS, stat.CO, stat.ML arXiv: https://arxiv.org/abs/2602.01929v2 Constructing accurate and computationally efficient surrogate models (or emulators) for predicting dynamical system responses is critical in many engineering domains, yet remains challenging due to the strongly nonlinear and high-dimensional mapping from external excitations and system parameters to system responses. This work introduces a novel Function-on-Function Nonlinear AutoRegressive model with eXogenous inputs (F2NARX), which reformulates the recently proposed $\mathcal{F}$-NARX method from a function-on-function regression perspective. The proposed framework substantially improves predictive efficiency while maintaining high accuracy. By combining principal component analysis with Gaussian process regression, F2NARX further enables probabilistic predictions of dynamical responses via the unscented transform in an autoregressive manner. Such probabilistic prediction capabilities further facilitate active learning for first-passage probability evaluation. The effectiveness of the method is demonstrated through case studies of varying complexity. Results show that F2NARX outperforms state-of-the-art NARX model by orders of magnitude in efficiency while achieving higher accuracy in general. Meanwhile, the active learning approach enables accurate estimation of first-passage failure probabilities for dynamical systems using only a small number of training time histories. --- ### On the Inherent Privacy Amplification of Missing Data Authors: Simon Roburin, Rafa{ë}l Pinot, Erwan Scornet Published: 2026-02-02 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2602.01928v3 Privacy preservation is critical in many high-stakes domains such as medicine and finance, where sensitive data must be analyzed without compromising individual confidentiality. At the same time, these applications often involve datasets with inherent missing values due to non-response or data corruption for example. Missing data is traditionally analyzed through its impact on statistical efficiency and model performance. In fact, it reduces the information available to analysts and can degrade the final utility of the model. In this work, we take an alternative approach and study missing data through the lens of privacy preservation. Intuitively, when features are missing, less information is revealed about individuals, suggesting that data missingness could inherently enhance privacy. We formalize this intuition within a novel framework that integrates missing data into differential privacy. In essence, our approach accounts for the de facto missingness in the data to refine existing privacy guarantees without modifying the underlying mechanism. Using this framework, we show for the first time that missing data can induce inherent privacy amplification for differentially private algorithms, highlighting a previously overlooked interaction between missing data and formal privacy guarantees.. --- ### Privacy Amplification by Missing Data Authors: Simon Roburin, Rafaël Pinot, Erwan Scornet Published: 2026-02-02 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2602.01928v2 Privacy preservation is a fundamental requirement in many high-stakes domains such as medicine and finance, where sensitive personal data must be analyzed without compromising individual confidentiality. At the same time, these applications often involve datasets with missing values due to non-response, data corruption, or deliberate anonymization. Missing data is traditionally viewed as a limitation because it reduces the information available to analysts and can degrade model performance. In this work, we take an alternative perspective and study missing data from a privacy preservation standpoint. Intuitively, when features are missing, less information is revealed about individuals, suggesting that missingness could inherently enhance privacy. We formalize this intuition by analyzing missing data as a privacy amplification mechanism within the framework of differential privacy. We show, for the first time, that incomplete data can yield privacy amplification for differentially private algorithms. --- ### Bayesian Integration of Nonlinear Incomplete Clinical Data Authors: Lucía González-Zamorano, Nuria Balbás-Esteban, Vanessa Gómez-Verdejo, Albert Belenguer-Llorens, Carlos Sevilla-Salcedo Published: 2026-02-02 Categories: cs.LG, cs.CY arXiv: https://arxiv.org/abs/2602.01924v1 Multimodal clinical data are characterized by high dimensionality, heterogeneous representations, and structured missingness, posing significant challenges for predictive modeling, data integration, and interpretability. We propose BIONIC (Bayesian Integration of Nonlinear Incomplete Clinical data), a unified probabilistic framework that integrates heterogeneous multimodal data under missingness through a joint generative-discriminative latent architecture. BIONIC uses pretrained embeddings for complex modalities such as medical images and clinical text, while incorporating structured clinical variables directly within a Bayesian multimodal formulation. The proposed framework enables robust learning in partially observed and semi-supervised settings by explicitly modeling modality-level and variable-level missingness, as well as missing labels. We evaluate BIONIC on three multimodal clinical and biomedical datasets, demonstrating strong and consistent discriminative performance compared to representative multimodal baselines, particularly under incomplete data scenarios. Beyond predictive accuracy, BIONIC provides intrinsic interpretability through its latent structure, enabling population-level analysis of modality relevance and supporting clinically meaningful insight. --- ### Embedding Learning on Multiplex Networks for Link Prediction Authors: Orell Trautmann, Olaf Wolkenhauer, Clémence Réda Published: 2026-02-02 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.01922v1 Over the past years, embedding learning on networks has shown tremendous results in link prediction tasks for complex systems, with a wide range of real-life applications. Learning a representation for each node in a knowledge graph allows us to capture topological and semantic information, which can be processed in downstream analyses later. In the link prediction task, high-dimensional network information is encoded into low-dimensional vectors, which are then fed to a predictor to infer new connections between nodes in the network. As the network complexity (that is, the numbers of connections and types of interactions) grows, embedding learning turns out increasingly challenging. This review covers published models on embedding learning on multiplex networks for link prediction. First, we propose refined taxonomies to classify and compare models, depending on the type of embeddings and embedding techniques. Second, we review and address the problem of reproducible and fair evaluation of embedding learning on multiplex networks for the link prediction task. Finally, we tackle evaluation on directed multiplex networks by proposing a novel and fair testing procedure. This review constitutes a crucial step towards the development of more performant and tractable embedding learning approaches for multiplex networks and their fair evaluation for the link prediction task. We also suggest guidelines on the evaluation of models, and provide an informed perspective on the challenges and tools currently available to address downstream analyses applied to multiplex networks. --- ### PIMPC-GNN: Physics-Informed Multi-Phase Consensus Learning for Enhancing Imbalanced Node Classification in Graph Neural Networks Authors: Abdul Joseph Fofanah, Lian Wen, David Chen Published: 2026-02-02 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2602.01920v1 Graph neural networks (GNNs) often struggle in class-imbalanced settings, where minority classes are under-represented and predictions are biased toward majorities. We propose \textbf{PIMPC-GNN}, a physics-informed multi-phase consensus framework for imbalanced node classification. Our method integrates three complementary dynamics: (i) thermodynamic diffusion, which spreads minority labels to capture long-range dependencies, (ii) Kuramoto synchronisation, which aligns minority nodes through oscillatory consensus, and (iii) spectral embedding, which separates classes via structural regularisation. These perspectives are combined through class-adaptive ensemble weighting and trained with an imbalance-aware loss that couples balanced cross-entropy with physics-based constraints. Across five benchmark datasets and imbalance ratios from 5-100, PIMPC-GNN outperforms 16 state-of-the-art baselines, achieving notable gains in minority-class recall (up to +12.7\%) and balanced accuracy (up to +8.3\%). Beyond empirical improvements, the framework also provides interpretable insights into consensus dynamics in graph learning. The code is available at \texttt{https://github.com/afofanah/PIMPC-GNN}. --- ### From Code-Centric to Concept-Centric: Teaching NLP with LLM-Assisted "Vibe Coding" Authors: Hend Al-Khalifa Published: 2026-02-02 Categories: cs.CL arXiv: https://arxiv.org/abs/2602.01919v1 The rapid advancement of Large Language Models (LLMs) presents both challenges and opportunities for Natural Language Processing (NLP) education. This paper introduces ``Vibe Coding,'' a pedagogical approach that leverages LLMs as coding assistants while maintaining focus on conceptual understanding and critical thinking. We describe the implementation of this approach in a senior-level undergraduate NLP course, where students completed seven labs using LLMs for code generation while being assessed primarily on conceptual understanding through critical reflection questions. Analysis of end-of-course feedback from 19 students reveals high satisfaction (mean scores 4.4-4.6/5.0) across engagement, conceptual learning, and assessment fairness. Students particularly valued the reduced cognitive load from debugging, enabling deeper focus on NLP concepts. However, challenges emerged around time constraints, LLM output verification, and the need for clearer task specifications. Our findings suggest that when properly structured with mandatory prompt logging and reflection-based assessment, LLM-assisted learning can shift focus from syntactic fluency to conceptual mastery, preparing students for an AI-augmented professional landscape. --- ### GuideWeb: A Benchmark for Automatic In-App Guide Generation on Real-World Web UIs Authors: Chengguang Gan, Yoshihiro Tsujii, Yunhao Liang, Tatsunori Mori, Shiwen Ni, Hiroki Itoh Published: 2026-02-02 Categories: cs.CL arXiv: https://arxiv.org/abs/2602.01917v1 Digital Adoption Platform (DAP) provide web-based overlays that deliver operation guidance and contextual hints to help users navigate complex websites. Although modern DAP tools enable non-experts to author such guidance, maintaining these guides remains labor-intensive because website layouts and functionalities evolve continuously, which requires repeated manual updates and re-annotation. In this work, we introduce \textbf{GuideWeb}, a new benchmark for automatic in-app guide generation on real-world web UIs. GuideWeb formulates the task as producing page-level guidance by selecting \textbf{guide target elements} grounded in the webpage and generating concise guide text aligned with user intent. We also propose a comprehensive evaluation suite that jointly measures the accuracy of guide target element selection and the quality of generated intents and guide texts. Experiments show that our proposed \textbf{GuideWeb Agent} achieves \textbf{30.79\%} accuracy in guide target element prediction, while obtaining BLEU scores of \textbf{44.94} for intent generation and \textbf{21.34} for guide-text generation. Existing baselines perform substantially worse, which highlights that automatic guide generation remains challenging and that further advances are necessary before such systems can be reliably deployed in real-world settings. --- ### VLM-Guided Experience Replay Authors: Elad Sharony, Tom Jurgenson, Orr Krupnik, Dotan Di Castro, Shie Mannor Published: 2026-02-02 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2602.01915v2 Recent advances in Large Language Models (LLMs) and Vision-Language Models (VLMs) have enabled powerful semantic and multimodal reasoning capabilities, creating new opportunities to enhance sample efficiency, high-level planning, and interpretability in reinforcement learning (RL). While prior work has integrated LLMs and VLMs into various components of RL, the replay buffer, a core component for storing and reusing experiences, remains unexplored. We propose addressing this gap by leveraging VLMs to guide the prioritization of experiences in the replay buffer. Our key idea is to use a frozen, pre-trained VLM as an automated evaluator to identify and prioritize promising sub-trajectories from the agent's experiences. Across scenarios, including game-playing and robotics, spanning both discrete and continuous domains, agents trained with our proposed prioritization method achieve 15-57% higher average success rates and improve sample efficiency by 35-55% compared to previous approaches. Project page: https://esharony.me/projects/vlm-rb/ --- ### VLM-Guided Experience Replay Authors: Elad Sharony, Tom Jurgenson, Orr Krupnik, Dotan Di Castro, Shie Mannor Published: 2026-02-02 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2602.01915v1 Recent advances in Large Language Models (LLMs) and Vision-Language Models (VLMs) have enabled powerful semantic and multimodal reasoning capabilities, creating new opportunities to enhance sample efficiency, high-level planning, and interpretability in reinforcement learning (RL). While prior work has integrated LLMs and VLMs into various components of RL, the replay buffer, a core component for storing and reusing experiences, remains unexplored. We propose addressing this gap by leveraging VLMs to guide the prioritization of experiences in the replay buffer. Our key idea is to use a frozen, pre-trained VLM (requiring no fine-tuning) as an automated evaluator to identify and prioritize promising sub-trajectories from the agent's experiences. Across scenarios, including game-playing and robotics, spanning both discrete and continuous domains, agents trained with our proposed prioritization method achieve 11-52% higher average success rates and improve sample efficiency by 19-45% compared to previous approaches. https://esharony.me/projects/vlm-rb/ --- ### Towards Long-Horizon Interpretability: Efficient and Faithful Multi-Token Attribution for Reasoning LLMs Authors: Wenbo Pan, Zhichao Liu, Xianlong Wang, Haining Yu, Xiaohua Jia Published: 2026-02-02 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.01914v4 Token attribution methods provide intuitive explanations for language model outputs by identifying causally important input tokens. However, as modern LLMs increasingly rely on extended reasoning chains, existing schemes face two critical challenges: (1) efficiency bottleneck, where attributing a target span of M tokens within a context of length N requires O(M*N) operations, making long-context attribution prohibitively slow; and (2) faithfulness drop, where intermediate reasoning tokens absorb attribution mass, preventing importance from propagating back to the original input. To address these, we introduce FlashTrace, an efficient multi-token attribution method that employs span-wise aggregation to compute attribution over multi-token targets in a single pass, while maintaining faithfulness. Moreover, we design a recursive attribution mechanism that traces importance through intermediate reasoning chains back to source inputs. Extensive experiments on long-context retrieval (RULER) and multi-step reasoning (MATH, MorehopQA) tasks demonstrate that FlashTrace achieves over 130x speedup over existing baselines while maintaining superior faithfulness. We further analyze the dynamics of recursive attribution, showing that even a single recursive hop improves faithfulness by tracing importance through the reasoning chain. --- ### Reliable Real-Time Value at Risk Estimation via Quantile Regression Forest with Conformal Calibration Authors: Du-Yi Wang, Guo Liang, Kun Zhang, Qianwen Zhu Published: 2026-02-02 Categories: stat.ML, cs.AI, cs.LG, q-fin.RM arXiv: https://arxiv.org/abs/2602.01912v1 Rapidly evolving market conditions call for real-time risk monitoring, but its online estimation remains challenging. In this paper, we study the online estimation of one of the most widely used risk measures, Value at Risk (VaR). Its accurate and reliable estimation is essential for timely risk control and informed decision-making. We propose to use the quantile regression forest in the offline-simulation-online-estimation (OSOA) framework. Specifically, the quantile regression forest is trained offline to learn the relationship between the online VaR and risk factors, and real-time VaR estimates are then produced online by incorporating observed risk factors. To further ensure reliability, we develop a conformalized estimator that calibrates the online VaR estimates. To the best of our knowledge, we are the first to leverage conformal calibration to estimate real-time VaR reliably based on the OSOA formulation. Theoretical analysis establishes the consistency and coverage validity of the proposed estimators. Numerical experiments confirm the proposed method and demonstrate its effectiveness in practice. --- ### DomusFM: A Foundation Model for Event-Based Behavioral Monitoring in Smart-Homes Authors: Michele Fiori, Gabriele Civitarese, Flora D. Salim, Claudio Bettini Published: 2026-02-02 Categories: cs.AI arXiv: https://arxiv.org/abs/2602.01910v2 Smart-home sensor-based behavioral monitoring holds significant potential for healthcare, independent living, and early detection of functional or cognitive changes. In this setting, tasks like activity recognition, prediction, and pattern discovery provide complementary views of daily life, supporting the modeling of personal routines and habits, and their long-term changes. Existing approaches, however, face critical limitations. Supervised approaches require impractical amounts of labeled activity data to capture the variability of daily behavior across residents and environments. Foundation models represent a promising direction for learning transferable representations of latent behavioral patterns from sensor data. Still, current efforts are mostly designed for continuous inertial or physiological sensor data and do not address the sparse, discrete, and semantically rich event streams produced by smart homes. In this paper, we introduce DomusFM, a domain-specific foundation model for sensor-based behavioral monitoring in smart homes based on semantic event streams. DomusFM employs a self-supervised dual contrastive learning paradigm to capture both event-level semantic attributes and sequence-level temporal dependencies. By integrating semantic embeddings from a lightweight language model and specialized encoders for temporal patterns and binary states, DomusFM learns transferable representations that can be adapted across heterogeneous smart-home environments and tasks related to activity and event analysis. Through a leave-one-dataset-out evaluation across seven public smart-home datasets, we demonstrate that DomusFM consistently outperforms baselines on three downstream tasks: ADL recognition, next-k event prediction, and unsupervised clustering. DomusFM has a small footprint and can be deployed on edge devices. --- ### DomusFM: A Foundation Model for Smart-Home Sensor Data Authors: Michele Fiori, Gabriele Civitarese, Flora D. Salim, Claudio Bettini Published: 2026-02-02 Categories: cs.AI arXiv: https://arxiv.org/abs/2602.01910v1 Smart-home sensor data holds significant potential for several applications, including healthcare monitoring and assistive technologies. Existing approaches, however, face critical limitations. Supervised models require impractical amounts of labeled data. Foundation models for activity recognition focus only on inertial sensors, failing to address the unique characteristics of smart-home binary sensor events: their sparse, discrete nature combined with rich semantic associations. LLM-based approaches, while tested in this domain, still raise several issues regarding the need for natural language descriptions or prompting, and reliance on either external services or expensive hardware, making them infeasible in real-life scenarios due to privacy and cost concerns. We introduce DomusFM, the first foundation model specifically designed and pretrained for smart-home sensor data. DomusFM employs a self-supervised dual contrastive learning paradigm to capture both token-level semantic attributes and sequence-level temporal dependencies. By integrating semantic embeddings from a lightweight language model and specialized encoders for temporal patterns and binary states, DomusFM learns generalizable representations that transfer across environments and tasks related to activity and event analysis. Through leave-one-dataset-out evaluation across seven public smart-home datasets, we demonstrate that DomusFM outperforms state-of-the-art baselines on different downstream tasks, achieving superior performance even with only 5% of labeled training data available for fine-tuning. Our approach addresses data scarcity while maintaining practical deployability for real-world smart-home systems. --- ### Propagating the prior from far to near offset: A self-supervised diffusion framework for progressively recovering near-offsets of towed-streamer data Authors: Shijun Cheng, Tariq Alkhalifah Published: 2026-02-02 Categories: physics.geo-ph, cs.LG arXiv: https://arxiv.org/abs/2602.01909v1 In marine towed-streamer seismic acquisition, the nearest hydrophone is often two hundred meter away from the source resulting in missing near-offset traces, which degrades critical processing workflows such as surface-related multiple elimination, velocity analysis, and full-waveform inversion. Existing reconstruction methods, like transform-domain interpolation, often produce kinematic inconsistencies and amplitude distortions, while supervised deep learning approaches require complete ground-truth near-offset data that are unavailable in realistic acquisition scenarios. To address these limitations, we propose a self-supervised diffusion-based framework that reconstructs missing near-offset traces without requiring near-offset reference data. Our method leverages overlapping patch extraction with single-trace shifts from the available far-offset section to train a conditional diffusion model, which learns offset-dependent statistical patterns governing event curvature, amplitude variation, and wavelet characteristics. At inference, we perform trace-by-trace recursive extrapolation from the nearest recorded offset toward zero offset, progressively propagating learned prior information from far to near offsets. The generative formulation further provides uncertainty estimates via ensemble sampling, quantifying prediction confidence where validation data are absent. Controlled validation experiments on synthetic and field datasets show substantial performance gains over conventional parabolic Radon transform baselines. Operational deployment on actual near-offset gaps demonstrates practical viability where ground-truth validation is impossible. Notably, the reconstructed waveforms preserve realistic amplitude-versus-offset trends despite training exclusively on far-offset observations, and uncertainty maps accurately identify challenging extrapolation regions. --- ### DSXFormer: Dual-Pooling Spectral Squeeze-Expansion and Dynamic Context Attention Transformer for Hyperspectral Image Classification Authors: Farhan Ullah, Irfan Ullah, Khalil Khan, Giovanni Pau, JaKeoung Koo Published: 2026-02-02 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2602.01906v1 Hyperspectral image classification (HSIC) is a challenging task due to high spectral dimensionality, complex spectral-spatial correlations, and limited labeled training samples. Although transformer-based models have shown strong potential for HSIC, existing approaches often struggle to achieve sufficient spectral discriminability while maintaining computational efficiency. To address these limitations, we propose a novel DSXFormer, a novel dual-pooling spectral squeeze-expansion transformer with Dynamic Context Attention for HSIC. The proposed DSXFormer introduces a Dual-Pooling Spectral Squeeze-Expansion (DSX) block, which exploits complementary global average and max pooling to adaptively recalibrate spectral feature channels, thereby enhancing spectral discriminability and inter-band dependency modeling. In addition, DSXFormer incorporates a Dynamic Context Attention (DCA) mechanism within a window-based transformer architecture to dynamically capture local spectral-spatial relationships while significantly reducing computational overhead. The joint integration of spectral dual-pooling squeeze-expansion and DCA enables DSXFormer to achieve an effective balance between spectral emphasis and spatial contextual representation. Furthermore, patch extraction, embedding, and patch merging strategies are employed to facilitate efficient multi-scale feature learning. Extensive experiments conducted on four widely used hyperspectral benchmark datasets, including Salinas (SA), Indian Pines (IP), Pavia University (PU), and Kennedy Space Center (KSC), demonstrate that DSXFormer consistently outperforms state-of-the-art methods, achieving classification accuracies of 99.95%, 98.91%, 99.85%, and 98.52%, respectively. --- ### Learning Sparse Visual Representations via Spatial-Semantic Factorization Authors: Theodore Zhengde Zhao, Sid Kiblawi, Jianwei Yang, Naoto Usuyama, Reuben Tan, Noel C Codella, Tristan Naumann, Hoifung Poon, Mu Wei Published: 2026-02-02 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2602.01905v1 Self-supervised learning (SSL) faces a fundamental conflict between semantic understanding and image reconstruction. High-level semantic SSL (e.g., DINO) relies on global tokens that are forced to be location-invariant for augmentation alignment, a process that inherently discards the spatial coordinates required for reconstruction. Conversely, generative SSL (e.g., MAE) preserves dense feature grids for reconstruction but fails to produce high-level abstractions. We introduce STELLAR, a framework that resolves this tension by factorizing visual features into a low-rank product of semantic concepts and their spatial distributions. This disentanglement allows us to perform DINO-style augmentation alignment on the semantic tokens while maintaining the precise spatial mapping in the localization matrix necessary for pixel-level reconstruction. We demonstrate that as few as 16 sparse tokens under this factorized form are sufficient to simultaneously support high-quality reconstruction (2.60 FID) and match the semantic performance of dense backbones (79.10% ImageNet accuracy). Our results highlight STELLAR as a versatile sparse representation that bridges the gap between discriminative and generative vision by strategically separating semantic identity from spatial geometry. Code available at https://aka.ms/stellar. --- ### Data- and Variance-dependent Regret Bounds for Online Tabular MDPs Authors: Mingyi Li, Taira Tsuchiya, Kenji Yamanishi Published: 2026-02-02 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2602.01903v3 This work studies online episodic tabular Markov decision processes (MDPs) with known transitions and develops best-of-both-worlds algorithms that achieve refined data-dependent regret bounds in the adversarial regime and variance-dependent regret bounds in the stochastic regime. We quantify MDP complexity using a first-order quantity and several new data-dependent measures for the adversarial regime, including a second-order quantity and a path-length measure, as well as variance-based measures for the stochastic regime. To adapt to these measures, we develop algorithms based on global optimization and policy optimization, both built on optimistic follow-the-regularized-leader with log-barrier regularization. For global optimization, our algorithms achieve first-order, second-order, and path-length regret bounds in the adversarial regime, and in the stochastic regime, they achieve a variance-aware gap-independent bound and a variance-aware gap-dependent bound that is polylogarithmic in the number of episodes. For policy optimization, our algorithms achieve the same data- and variance-dependent adaptivity, up to a factor of the episode horizon, by exploiting a new optimistic $Q$-function estimator. Finally, we establish regret lower bounds in terms of data-dependent complexity measures for the adversarial regime and a variance measure for the stochastic regime, implying that the regret upper bounds achieved by the global-optimization approach are nearly optimal. --- ### Q Cache: Visual Attention is Valuable in Less than Half of Decode Layers for Multimodal Large Language Model Authors: Jiedong Zhuang, Lu Lu, Ming Dai, Rui Hu, Jian Chen, Qiang Liu, Haoji Hu Published: 2026-02-02 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.01901v1 Multimodal large language models (MLLMs) are plagued by exorbitant inference costs attributable to the profusion of visual tokens within the vision encoder. The redundant visual tokens engenders a substantial computational load and key-value (KV) cache footprint bottleneck. Existing approaches focus on token-wise optimization, leveraging diverse intricate token pruning techniques to eliminate non-crucial visual tokens. Nevertheless, these methods often unavoidably undermine the integrity of the KV cache, resulting in failures in long-text generation tasks. To this end, we conduct an in-depth investigation towards the attention mechanism of the model from a new perspective, and discern that attention within more than half of all decode layers are semantic similar. Upon this finding, we contend that the attention in certain layers can be streamlined by inheriting the attention from their preceding layers. Consequently, we propose Lazy Attention, an efficient attention mechanism that enables cross-layer sharing of similar attention patterns. It ingeniously reduces layer-wise redundant computation in attention. In Lazy Attention, we develop a novel layer-shared cache, Q Cache, tailored for MLLMs, which facilitates the reuse of queries across adjacent layers. In particular, Q Cache is lightweight and fully compatible with existing inference frameworks, including Flash Attention and KV cache. Additionally, our method is highly flexible as it is orthogonal to existing token-wise techniques and can be deployed independently or combined with token pruning approaches. Empirical evaluations on multiple benchmarks demonstrate that our method can reduce KV cache usage by over 35% and achieve 1.5x throughput improvement, while sacrificing only approximately 1% of performance on various MLLMs. Compared with SOTA token-wise methods, our technique achieves superior accuracy preservation. --- ### Multi-Task Learning for Robot Perception with Imbalanced Data Authors: Ozgur Erkent Published: 2026-02-02 Categories: cs.RO, cs.CV arXiv: https://arxiv.org/abs/2602.01899v1 Multi-task problem solving has been shown to improve the accuracy of the individual tasks, which is an important feature for robots, as they have a limited resource. However, when the number of labels for each task is not equal, namely imbalanced data exist, a problem may arise due to insufficient number of samples, and labeling is not very easy for mobile robots in every environment. We propose a method that can learn tasks even in the absence of the ground truth labels for some of the tasks. We also provide a detailed analysis of the proposed method. An interesting finding is related to the interaction of the tasks. We show a methodology to find out which tasks can improve the performance of other tasks. We investigate this by training the teacher network with the task outputs such as depth as inputs. We further provide empirical evidence when trained with a small amount of data. We use semantic segmentation and depth estimation tasks on different datasets, NYUDv2 and Cityscapes. --- ### Correcting Boundary Bias and Observation Independence in Bayesian Experimental Design Authors: Sanna Jarl, Jens Sjölund, Jonathan J. S. Scragg, Maria Bånkestad Published: 2026-02-02 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2602.01898v2 In many experimental settings, active learning can improve sample efficiency by sequentially selecting where to measure, which is particularly valuable when experiments are expensive. Gaussian processes with variance-based acquisition criteria are widely used for this purpose, but have two limitations. First, they are observation-independent: their posterior variance depends only on where samples are acquired, not on what is measured, impairing their sensitivity to the structure of the acquired data. Second, they inflate the variance near boundaries, leading to excessive sampling at the edges of the space compared to the interior. These limitations undermine the gains in sampling efficiency expected from sequential acquisition. We address both limitations. We derive a reconstruction-driven design density and use the posterior mean to build a training-free warp that places more measurements where the target function varies rapidly. A geometric equalizer separately corrects boundary bias. Across sixteen synthetic and two real-data benchmarks, the geometric equalizer consistently improves function reconstruction by correcting boundary bias, while the reconstruction warp provides further gains by concentrating measurements where the posterior mean varies rapidly. --- ### Observation-dependent Bayesian active learning via input-warped Gaussian processes Authors: Sanna Jarl, Maria Bånkestad, Jonathan J. S. Scragg, Jens Sjölund Published: 2026-02-02 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2602.01898v1 Bayesian active learning relies on the precise quantification of predictive uncertainty to explore unknown function landscapes. While Gaussian process surrogates are the standard for such tasks, an underappreciated fact is that their posterior variance depends on the observed outputs only through the hyperparameters, rendering exploration largely insensitive to the actual measurements. We propose to inject observation-dependent feedback by warping the input space with a learned, monotone reparameterization. This mechanism allows the design policy to expand or compress regions of the input space in response to observed variability, thereby shaping the behavior of variance-based acquisition functions. We demonstrate that while such warps can be trained via marginal likelihood, a novel self-supervised objective yields substantially better performance. Our approach improves sample efficiency across a range of active learning benchmarks, particularly in regimes where non-stationarity challenges traditional methods. --- ### Internal Flow Signatures for Self-Checking and Refinement in LLMs Authors: Sungheon Jeong, Sanggeon Yun, Ryozo Masukawa, Wenjun Haung, Hanning Chen, Mohsen Imani Published: 2026-02-02 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.01897v1 Large language models can generate fluent answers that are unfaithful to the provided context, while many safeguards rely on external verification or a separate judge after generation. We introduce \emph{internal flow signatures} that audit decision formation from depthwise dynamics at a fixed inter-block monitoring boundary. The method stabilizes token-wise motion via bias-centered monitoring, then summarizes trajectories in compact \emph{moving} readout-aligned subspaces constructed from the top token and its close competitors within each depth window. Neighboring window frames are aligned by an orthogonal transport, yielding depth-comparable transported step lengths, turning angles, and subspace drift summaries that are invariant to within-window basis choices. A lightweight GRU validator trained on these signatures performs self-checking without modifying the base model. Beyond detection, the validator localizes a culprit depth event and enables a targeted refinement: the model rolls back to the culprit token and clamps an abnormal transported step at the identified block while preserving the orthogonal residual. The resulting pipeline provides actionable localization and low-overhead self-checking from internal decision dynamics. \emph{Code is available at} \texttt{github.com/EavnJeong/Internal-Flow-Signatures-for-Self-Checking-and-Refinement-in-LLMs}. --- ### Geometric Analysis of Token Selection in Multi-Head Attention Authors: Timur Mudarisov, Mikhal Burtsev, Tatiana Petrova, Radu State Published: 2026-02-02 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2602.01893v2 We present a geometric framework for analysing multi-head attention in large language models (LLMs). Without altering the mechanism, we view standard attention through a top-N selection lens and study its behaviour directly in value-state space. We define geometric metrics - Precision, Recall, and F-score - to quantify separability between selected and non-selected tokens, and derive non-asymptotic bounds with explicit dependence on dimension and margin under empirically motivated assumptions (stable value norms with a compressed sink token, exponential similarity decay, and piecewise attention weight profiles). The theory predicts a small-N operating regime of strongest non-trivial separability and clarifies how sequence length and sink similarity shape the metrics. Empirically, across LLaMA-2-7B, Gemma-7B, and Mistral-7B, measurements closely track the theoretical envelopes: top-N selection sharpens separability, sink similarity correlates with Recall. We also found that in LLaMA-2-7B heads specialize into three regimes - Retriever, Mixer, Reset - with distinct geometric signatures. Overall, attention behaves as a structured geometric classifier with measurable criteria for token selection, offering head level interpretability and informing geometry-aware sparsification and design of attention in LLMs. --- ### ES-MemEval: Benchmarking Conversational Agents on Personalized Long-Term Emotional Support Authors: Tiantian Chen, Jiaqi Lu, Ying Shen, Lin Zhang Published: 2026-02-02 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2602.01885v1 Large Language Models (LLMs) have shown strong potential as conversational agents. Yet, their effectiveness remains limited by deficiencies in robust long-term memory, particularly in complex, long-term web-based services such as online emotional support. However, existing long-term dialogue benchmarks primarily focus on static and explicit fact retrieval, failing to evaluate agents in critical scenarios where user information is dispersed, implicit, and continuously evolving. To address this gap, we introduce ES-MemEval, a comprehensive benchmark that systematically evaluates five core memory capabilities: information extraction, temporal reasoning, conflict detection, abstention, and user modeling, in long-term emotional support settings, covering question answering, summarization, and dialogue generation tasks. To support the benchmark, we also propose EvoEmo, a multi-session dataset for personalized long-term emotional support that captures fragmented, implicit user disclosures and evolving user states. Extensive experiments on open-source long-context, commercial, and retrieval-augmented (RAG) LLMs show that explicit long-term memory is essential for reducing hallucinations and enabling effective personalization. At the same time, RAG improves factual consistency but struggles with temporal dynamics and evolving user states. These findings highlight both the potential and limitations of current paradigms and motivate more robust integration of memory and retrieval for long-term personalized dialogue systems. --- ### Entropy-Guided Data-Efficient Training for Multimodal Reasoning Reward Models Authors: Shidong Yang, Tongwen Huang, Hao Wen, Yong Wang, Li Chen, Xiangxiang Chu Published: 2026-02-02 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2602.01884v1 Multimodal reward models are crucial for aligning multimodal large language models with human preferences. Recent works have incorporated reasoning capabilities into these models, achieving promising results. However, training these models suffers from two critical challenges: (1) the inherent noise in preference datasets, which degrades model performance, and (2) the inefficiency of conventional training methods, which ignore the differences in sample difficulty. In this paper, we identify a strong correlation between response entropy and accuracy, indicating that entropy can serve as a reliable and unsupervised proxy for annotation noise and sample difficulty. Based on this insight, we propose a novel Entropy-Guided Training (EGT) approach for multimodal reasoning reward models, which combines two strategies: (1) entropy-guided data curation to mitigate the impact of unreliable samples, and (2) an entropy-guided training strategy that progressively introduces more complex examples. Extensive experiments across three benchmarks show that the EGT-trained model consistently outperforms state-of-the-art multimodal reward models. --- ### ProxyImg: Towards Highly-Controllable Image Representation via Hierarchical Disentangled Proxy Embedding Authors: Ye Chen, Yupeng Zhu, Xiongzhen Zhang, Zhewen Wan, Yingzhe Li, Wenjun Zhang, Bingbing Ni Published: 2026-02-02 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.01881v1 Prevailing image representation methods, including explicit representations such as raster images and Gaussian primitives, as well as implicit representations such as latent images, either suffer from representation redundancy that leads to heavy manual editing effort, or lack a direct mapping from latent variables to semantic instances or parts, making fine-grained manipulation difficult. These limitations hinder efficient and controllable image and video editing. To address these issues, we propose a hierarchical proxy-based parametric image representation that disentangles semantic, geometric, and textural attributes into independent and manipulable parameter spaces. Based on a semantic-aware decomposition of the input image, our representation constructs hierarchical proxy geometries through adaptive Bezier fitting and iterative internal region subdivision and meshing. Multi-scale implicit texture parameters are embedded into the resulting geometry-aware distributed proxy nodes, enabling continuous high-fidelity reconstruction in the pixel domain and instance- or part-independent semantic editing. In addition, we introduce a locality-adaptive feature indexing mechanism to ensure spatial texture coherence, which further supports high-quality background completion without relying on generative models. Extensive experiments on image reconstruction and editing benchmarks, including ImageNet, OIR-Bench, and HumanEdit, demonstrate that our method achieves state-of-the-art rendering fidelity with significantly fewer parameters, while enabling intuitive, interactive, and physically plausible manipulation. Moreover, by integrating proxy nodes with Position-Based Dynamics, our framework supports real-time physics-driven animation using lightweight implicit rendering, achieving superior temporal consistency and visual realism compared with generative approaches. ---