# Research Papers — 2026-02 · bundle page 107 of 210 > Full-text markdown of papers #5301–5350 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/107 [← Previous bundle](https://aipod.dev/papers/archive/2026-02/page/106.md) [Next bundle →](https://aipod.dev/papers/archive/2026-02/page/108.md) ### Estimation of instrument and noise parameters for inverse problem based on prior diffusion model Authors: Jean-François Giovannelli Published: 2026-02-12 Categories: stat.ML, cs.LG, math.NA, stat.AP arXiv: https://arxiv.org/abs/2602.11711v2 This article addresses the issue of estimating observation parameters (response and error parameters) in inverse problems. The focus is on cases where regularization is introduced in a Bayesian framework and the prior is modeled by a diffusion process. In this context, the issue of posterior sampling is known to be thorny, and a recent paper proposes a notably simple and effective solution. Additionally, it opens an remarkable flexibility when it comes to estimating observation parameters. The proposed strategy enables to define an optimal estimator for both observation parameters and image of interest. Furthermore, the strategy provides a means for uncertainty quantification. In addition, MCMC algorithms allow for the computation of estimates and properties of posteriors, while offering some guarantees. The paper presents several numerical experiments that clearly confirm the computational efficiency and the quality of both estimates and uncertainty quantification. --- ### LLM-Driven 3D Scene Generation of Agricultural Simulation Environments Authors: Arafa Yoncalik, Wouter Jansen, Nico Huebel, Mohammad Hasan Rahmani, Jan Steckel Published: 2026-02-12 Categories: cs.CV, cs.AI, cs.RO arXiv: https://arxiv.org/abs/2602.11706v1 Procedural generation techniques in 3D rendering engines have revolutionized the creation of complex environments, reducing reliance on manual design. Recent approaches using Large Language Models (LLMs) for 3D scene generation show promise but often lack domain-specific reasoning, verification mechanisms, and modular design. These limitations lead to reduced control and poor scalability. This paper investigates the use of LLMs to generate agricultural synthetic simulation environments from natural language prompts, specifically to address the limitations of lacking domain-specific reasoning, verification mechanisms, and modular design. A modular multi-LLM pipeline was developed, integrating 3D asset retrieval, domain knowledge injection, and code generation for the Unreal rendering engine using its API. This results in a 3D environment with realistic planting layouts and environmental context, all based on the input prompt and the domain knowledge. To enhance accuracy and scalability, the system employs a hybrid strategy combining LLM optimization techniques such as few-shot prompting, Retrieval-Augmented Generation (RAG), finetuning, and validation. Unlike monolithic models, the modular architecture enables structured data handling, intermediate verification, and flexible expansion. The system was evaluated using structured prompts and semantic accuracy metrics. A user study assessed realism and familiarity against real-world images, while an expert comparison demonstrated significant time savings over manual scene design. The results confirm the effectiveness of multi-LLM pipelines in automating domain-specific 3D scene generation with improved reliability and precision. Future work will explore expanding the asset hierarchy, incorporating real-time generation, and adapting the pipeline to other simulation domains beyond agriculture. --- ### TG-Field: Geometry-Aware Radiative Gaussian Fields for Tomographic Reconstruction Authors: Yuxiang Zhong, Jun Wei, Chaoqi Chen, Senyou An, Hui Huang Published: 2026-02-12 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.11705v1 3D Gaussian Splatting (3DGS) has revolutionized 3D scene representation with superior efficiency and quality. While recent adaptations for computed tomography (CT) show promise, they struggle with severe artifacts under highly sparse-view projections and dynamic motions. To address these challenges, we propose Tomographic Geometry Field (TG-Field), a geometry-aware Gaussian deformation framework tailored for both static and dynamic CT reconstruction. A multi-resolution hash encoder is employed to capture local spatial priors, regularizing primitive parameters under ultra-sparse settings. We further extend the framework to dynamic reconstruction by introducing time-conditioned representations and a spatiotemporal attention block to adaptively aggregate features, thereby resolving spatiotemporal ambiguities and enforcing temporal coherence. In addition, a motion-flow network models fine-grained respiratory motion to track local anatomical deformations. Extensive experiments on synthetic and real-world datasets demonstrate that TG-Field consistently outperforms existing methods, achieving state-of-the-art reconstruction accuracy under highly sparse-view conditions. --- ### U-DAVI: Uncertainty-Aware Diffusion-Prior-Based Amortized Variational Inference for Image Reconstruction Authors: Ayush Varshney, Katherine L. Bouman, Berthy T. Feng Published: 2026-02-12 Categories: eess.IV, cs.CV arXiv: https://arxiv.org/abs/2602.11704v1 Ill-posed imaging inverse problems remain challenging due to the ambiguity in mapping degraded observations to clean images. Diffusion-based generative priors have recently shown promise, but typically rely on computationally intensive iterative sampling or per-instance optimization. Amortized variational inference frameworks address this inefficiency by learning a direct mapping from measurements to posteriors, enabling fast posterior sampling without requiring the optimization of a new posterior for every new set of measurements. However, they still struggle to reconstruct fine details and complex textures. To address this, we extend the amortized framework by injecting spatially adaptive perturbations to measurements during training, guided by uncertainty estimates, to emphasize learning in the most uncertain regions. Experiments on deblurring and super-resolution demonstrate that our method achieves superior or competitive performance to previous diffusion-based approaches, delivering more realistic reconstructions without the computational cost of iterative refinement. --- ### Semantically Conditioned Diffusion Models for Cerebral DSA Synthesis Authors: Qiwen Xu, David Rügamer, Holger Wenz, Johann Fontana, Nora Meggyeshazi, Andreas Bender, Máté E. Maros Published: 2026-02-12 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2602.11703v1 Digital subtraction angiography (DSA) plays a central role in the diagnosis and treatment of cerebrovascular disease, yet its invasive nature and high acquisition cost severely limit large-scale data collection and public data sharing. Therefore, we developed a semantically conditioned latent diffusion model (LDM) that synthesizes arterial-phase cerebral DSA frames under explicit control of anatomical circulation (anterior vs.\ posterior) and canonical C-arm positions. We curated a large single-centre DSA dataset of 99,349 frames and trained a conditional LDM using text embeddings that encoded anatomy and acquisition geometry. To assess clinical realism, four medical experts, including two neuroradiologists, one neurosurgeon, and one internal medicine expert, systematically rated 400 synthetic DSA images using a 5-grade Likert scale for evaluating proximal large, medium, and small peripheral vessels. The generated images achieved image-wise overall Likert scores ranging from 3.1 to 3.3, with high inter-rater reliability (ICC(2,k) = 0.80--0.87). Distributional similarity to real DSA frames was supported by a low median Fréchet inception distance (FID) of 15.27. Our results indicate that semantically controlled LDMs can produce realistic synthetic DSAs suitable for downstream algorithm development, research, and training. --- ### TabSieve: Explicit In-Table Evidence Selection for Tabular Prediction Authors: Yongyao Wang, Ziqi Miao, Lu Yang, Haonan Jia, Wenting Yan, Chen Qian, Lijun Li Published: 2026-02-12 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2602.11700v2 Tabular prediction can benefit from in-table rows as few-shot evidence, yet existing tabular models typically perform instance-wise inference and LLM-based prompting is often brittle. Models do not consistently leverage relevant rows, and noisy context can degrade performance. To address this challenge, we propose TabSieve, a select-then-predict framework that makes evidence usage explicit and auditable. Given a table and a query row, TabSieve first selects a small set of informative rows as evidence and then predicts the missing target conditioned on the selected evidence. To enable this capability, we construct TabSieve-SFT-40K by synthesizing high-quality reasoning trajectories from 331 real tables using a strong teacher model with strict filtering. Furthermore, we introduce TAB-GRPO, a reinforcement learning recipe that jointly optimizes evidence selection and prediction correctness with separate rewards, and stabilizes mixed regression and classification training via dynamic task-advantage balancing. Experiments on a held-out benchmark of 75 classification and 52 regression tables show that TabSieve consistently improves performance across shot budgets, with average gains of 2.92% on classification and 4.45% on regression over the second-best baseline. Further analysis indicates that TabSieve concentrates more attention on the selected evidence, which improves robustness to noisy context. --- ### TabSieve: Explicit In-Table Evidence Selection for Tabular Prediction Authors: Yongyao Wang, Ziqi Miao, Lu Yang, Haonan Jia, Wenting Yan, Chen Qian, Lijun Li Published: 2026-02-12 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2602.11700v1 Tabular prediction can benefit from in-table rows as few-shot evidence, yet existing tabular models typically perform instance-wise inference and LLM-based prompting is often brittle. Models do not consistently leverage relevant rows, and noisy context can degrade performance. To address this challenge, we propose TabSieve, a select-then-predict framework that makes evidence usage explicit and auditable. Given a table and a query row, TabSieve first selects a small set of informative rows as evidence and then predicts the missing target conditioned on the selected evidence. To enable this capability, we construct TabSieve-SFT-40K by synthesizing high-quality reasoning trajectories from 331 real tables using a strong teacher model with strict filtering. Furthermore, we introduce TAB-GRPO, a reinforcement learning recipe that jointly optimizes evidence selection and prediction correctness with separate rewards, and stabilizes mixed regression and classification training via dynamic task-advantage balancing. Experiments on a held-out benchmark of 75 classification and 52 regression tables show that TabSieve consistently improves performance across shot budgets, with average gains of 2.92% on classification and 4.45% on regression over the second-best baseline. Further analysis indicates that TabSieve concentrates more attention on the selected evidence, which improves robustness to noisy context. --- ### Finding Sense in Nonsense with Generated Contexts: Perspectives from Humans and Language Models Authors: Katrina Olsen, Sebastian Padó Published: 2026-02-12 Categories: cs.CL arXiv: https://arxiv.org/abs/2602.11699v3 Nonsensical and anomalous sentences have been instrumental in the development of computational models of semantic interpretation. A core challenge is to distinguish between what is merely anomalous (but can be interpreted given a supporting context) and what is truly nonsensical. However, it is unclear (a) how nonsensical, rather than merely anomalous, existing datasets are; and (b) how well LLMs can make this distinction. In this paper, we answer both questions by collecting sensicality judgments from human raters and LLMs on sentences from five semantically deviant datasets: both context-free and when providing a context. We find that raters consider most sentences at most anomalous, and only a few as properly nonsensical. We also show that LLMs are substantially skilled in generating plausible contexts for anomalous cases. --- ### SpiralFormer: Looped Transformers Can Learn Hierarchical Dependencies via Multi-Resolution Recursion Authors: Chengting Yu, Xiaobo Shu, Yadao Wang, Yizhen Zhang, Haoyi Wu, You Wu, Rujiao Long, Ziheng Chen, Yuchi Xu, Wenbo Su, Bo Zheng Published: 2026-02-12 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.11698v2 Recursive (looped) Transformers decouple computational depth from parameter depth by repeatedly applying shared layers, providing an explicit architectural primitive for iterative refinement and latent reasoning. However, early looped Transformers often underperform non-recursive baselines of equal compute. While recent literature has introduced more effective recursion mechanisms to mitigate this gap, existing architectures still operate at a fixed, full-token resolution, neglecting the potential efficiency of computing over compressed latent representations. In this paper, we propose SpiralFormer, a looped Transformer that executes recurrence under a multi-resolution recursion schedule. We provide probing evidence that multi-resolution recursion enables the model to learn hierarchical dependencies by inducing iteration-wise functional specialization across different scales. Empirically, SpiralFormer achieves better parameter and compute efficiency than both looped and non-looped baselines across model scales from 160M to 1.4B, establishing sequence resolution as a potential axis for scaling recursive architectures. --- ### OMEGA-Avatar: One-shot Modeling of 360° Gaussian Avatars Authors: Zehao Xia, Yiqun Wang, Zhengda Lu, Kai Liu, Jun Xiao, Peter Wonka Published: 2026-02-12 Categories: cs.GR, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2602.11693v1 Creating high-fidelity, animatable 3D avatars from a single image remains a formidable challenge. We identified three desirable attributes of avatar generation: 1) the method should be feed-forward, 2) model a 360° full-head, and 3) should be animation-ready. However, current work addresses only two of the three points simultaneously. To address these limitations, we propose OMEGA-Avatar, the first feed-forward framework that simultaneously generates a generalizable, 360°-complete, and animatable 3D Gaussian head from a single image. Starting from a feed-forward and animatable framework, we address the 360° full-head avatar generation problem with two novel components. First, to overcome poor hair modeling in full-head avatar generation, we introduce a semantic-aware mesh deformation module that integrates multi-view normals to optimize a FLAME head with hair while preserving its topology structure. Second, to enable effective feed-forward decoding of full-head features, we propose a multi-view feature splatting module that constructs a shared canonical UV representation from features across multiple views through differentiable bilinear splatting, hierarchical UV mapping, and visibility-aware fusion. This approach preserves both global structural coherence and local high-frequency details across all viewpoints, ensuring 360° consistency without per-instance optimization. Extensive experiments demonstrate that OMEGA-Avatar achieves state-of-the-art performance, significantly outperforming existing baselines in 360° full-head completeness while robustly preserving identity across different viewpoints. --- ### ANML: Attribution-Native Machine Learning with Guaranteed Robustness Authors: Oliver Zahn, Matt Beton, Simran Chana Published: 2026-02-12 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2602.11690v1 Frontier AI systems increasingly train on specialized expert data, from clinical records to proprietary research to curated datasets, yet current training pipelines treat all samples identically. A Nobel laureate's contribution receives the same weight as an unverified submission. We introduce ANML (Attribution-Native Machine Learning), a framework that weights training samples by four quality factors: gradient-based consistency (q), verification status (v), contributor reputation (r), and temporal relevance (T). By combining what the model observes (gradient signals) with what the system knows about data provenance (external signals), ANML produces per-contributor quality weights that simultaneously improve model performance and enable downstream attribution. Across 5 datasets (178-32,561 samples), ANML achieves 33-72% error reduction over gradient-only baselines. Quality-weighted training is data-efficient: 20% high-quality data outperforms 100% uniformly weighted data by 47%. A Two-Stage Adaptive gating mechanism guarantees that ANML never underperforms the best available baseline, including under strategic joint attacks combining credential faking with gradient alignment. When per-sample detection fails against subtle corruption, contributor-level attribution provides 1.3-5.3x greater improvement than sample-level methods, with the advantage growing as corruption becomes harder to detect. --- ### LAER-MoE: Load-Adaptive Expert Re-layout for Efficient Mixture-of-Experts Training Authors: Xinyi Liu, Yujie Wang, Fangcheng Fu, Xuefeng Xiao, Huixia Li, Jiashi Li, Bin Cui Published: 2026-02-12 Categories: cs.DC, cs.LG arXiv: https://arxiv.org/abs/2602.11686v1 Expert parallelism is vital for effectively training Mixture-of-Experts (MoE) models, enabling different devices to host distinct experts, with each device processing different input data. However, during expert parallel training, dynamic routing results in significant load imbalance among experts: a handful of overloaded experts hinder overall iteration, emerging as a training bottleneck. In this paper, we introduce LAER-MoE, an efficient MoE training framework. The core of LAER-MoE is a novel parallel paradigm, Fully Sharded Expert Parallel (FSEP), which fully partitions each expert parameter by the number of devices and restores partial experts at expert granularity through All-to-All communication during training. This allows for flexible re-layout of expert parameters during training to enhance load balancing. In particular, we perform fine-grained scheduling of communication operations to minimize communication overhead. Additionally, we develop a load balancing planner to formulate re-layout strategies of experts and routing schemes for tokens during training. We perform experiments on an A100 cluster, and the results indicate that our system achieves up to 1.69x acceleration compared to the current state-of-the-art training systems. Source code available at https://github.com/PKU-DAIR/Hetu-Galvatron/tree/laer-moe. --- ### DRACO: a Cross-Domain Benchmark for Deep Research Accuracy, Completeness, and Objectivity Authors: Joey Zhong, Hao Zhang, Clare Southern, Jeremy Yang, Thomas Wang, Kate Jung, Shu Zhang, Denis Yarats, Johnny Ho, Jerry Ma Published: 2026-02-12 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2602.11685v1 We present DRACO (Deep Research Accuracy, Completeness, and Objectivity), a benchmark of complex deep research tasks. These tasks, which span 10 domains and draw on information sources from 40 countries, originate from anonymized real-world usage patterns within a large-scale deep research system. Tasks are sampled from a de-identified dataset of Perplexity Deep Research requests, then filtered and augmented to ensure that the tasks are anonymized, open-ended and complex, objectively evaluable, and representative of the broad scope of real-world deep research use cases. Outputs are graded against task-specific rubrics along four dimensions: factual accuracy (accuracy), breadth and depth of analysis (including completeness), presentation quality (including objectivity), and citation quality. DRACO is publicly available at https://hf.co/datasets/perplexity-ai/draco. --- ### PatientHub: A Unified Framework for Patient Simulation Authors: Sahand Sabour, TszYam NG, Minlie Huang Published: 2026-02-12 Categories: cs.CL, cs.AI, cs.HC arXiv: https://arxiv.org/abs/2602.11684v2 As Large Language Models increasingly power role-playing applications, simulating patients has become a valuable tool for training counselors and scaling therapeutic assessment. However, prior work remains fragmented: existing approaches rely on incompatible, non-standardized profiles, prompts, and evaluation metrics, hindering reproducibility, fair comparison, and reuse. We introduce PatientHub, a unified and modular framework that standardizes the creation, simulation, and evaluation of LLM-based patients. Our framework provides 16 patient simulators, a graph-based orchestrator for multi-turn, multi-session interactions, and a configurable LLM-as-a-judge evaluator that supports multiple rubric types. Via our command-line interface, users can generate patient profiles, run simulations, and apply rubric-driven evaluation at the turn and session level. To demonstrate PatientHub's utility, we compare several supported simulators under a shared interaction protocol and showcase its extensibility by prototyping a new simulator variant with minimal additional code. By consolidating existing work into a single reproducible pipeline, our framework eliminates much of the infrastructure overhead that currently fragments this research and accelerates the development of new methods. Our code and data are publicly available via https://github.com/Sahandfer/PatientHub. --- ### PatientHub: A Unified Framework for Patient Simulation Authors: Sahand Sabour, TszYam NG, Minlie Huang Published: 2026-02-12 Categories: cs.CL, cs.AI, cs.HC arXiv: https://arxiv.org/abs/2602.11684v1 As Large Language Models increasingly power role-playing applications, simulating patients has become a valuable tool for training counselors and scaling therapeutic assessment. However, prior work is fragmented: existing approaches rely on incompatible, non-standardized data formats, prompts, and evaluation metrics, hindering reproducibility and fair comparison. In this paper, we introduce PatientHub, a unified and modular framework that standardizes the definition, composition, and deployment of simulated patients. To demonstrate PatientHub's utility, we implement several representative patient simulation methods as case studies, showcasing how our framework supports standardized cross-method evaluation and the seamless integration of custom evaluation metrics. We further demonstrate PatientHub's extensibility by prototyping two new simulator variants, highlighting how PatientHub accelerates method development by eliminating infrastructure overhead. By consolidating existing work into a single reproducible pipeline, PatientHub lowers the barrier to developing new simulation methods and facilitates cross-method and cross-model benchmarking. Our framework provides a practical foundation for future datasets, methods, and benchmarks in patient-centered dialogue, and the code is publicly available via https://github.com/Sahandfer/PatientHub. --- ### ThinkRouter: Efficient Reasoning via Routing Thinking between Latent and Discrete Spaces Authors: Xin Xu, Tong Yu, Xiang Chen, Haoliang Wang, Julian McAuley, Saayan Mitra Published: 2026-02-12 Categories: cs.AI, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2602.11683v1 Recent work explores latent reasoning to improve reasoning efficiency by replacing explicit reasoning trajectories with continuous representations in a latent space, yet its effectiveness varies across settings. Analysis of model confidence dynamics under latent reasoning reveals that thinking trajectories ending in incorrect answers contain fewer low-confidence steps than those ending in correct answers. Meanwhile, we suggest that soft embeddings aggregated by multiple low-confidence thinking alternatives may introduce and propagate noise, leading to high confidence in unreliable reasoning trajectories. Motivated by these observations, ThinkRouter, an inference-time confidence-aware routing mechanism is proposed to avoid high confidence and noise for efficient reasoning. ThinkRouter routes thinking to the discrete token space when model confidence is low, and to the latent space otherwise. Extensive experiments on STEM reasoning and coding benchmarks across diverse large reasoning models demonstrate that ThinkRouter outperforms explicit CoT, random routing, and latent reasoning baselines in terms of accuracy, achieving an average improvement of 19.70 points in Pass@1, while reducing generation length by up to 15.55%. Further comprehensive analysis reveals that ThinkRouter can calibrate errors arising from explicit CoT and latent reasoning, and accelerates end-of-thinking token generation by globally lowering model confidence. --- ### Provable Offline Reinforcement Learning for Structured Cyclic MDPs Authors: Kyungbok Lee, Angelica Cristello Sarteau, Michael R. Kosorok Published: 2026-02-12 Categories: stat.ML, cs.AI, cs.LG, math.OC, stat.ME arXiv: https://arxiv.org/abs/2602.11679v1 We introduce a novel cyclic Markov decision process (MDP) framework for multi-step decision problems with heterogeneous stage-specific dynamics, transitions, and discount factors across the cycle. In this setting, offline learning is challenging: optimizing a policy at any stage shifts the state distributions of subsequent stages, propagating mismatch across the cycle. To address this, we propose a modular structural framework that decomposes the cyclic process into stage-wise sub-problems. While generally applicable, we instantiate this principle as CycleFQI, an extension of fitted Q-iteration enabling theoretical analysis and interpretation. It uses a vector of stage-specific Q-functions, tailored to each stage, to capture within-stage sequences and transitions between stages. This modular design enables partial control, allowing some stages to be optimized while others follow predefined policies. We establish finite-sample suboptimality error bounds and derive global convergence rates under Besov regularity, demonstrating that CycleFQI mitigates the curse of dimensionality compared to monolithic baselines. Additionally, we propose a sieve-based method for asymptotic inference of optimal policy values under a margin condition. Experiments on simulated and real-world Type 1 Diabetes data sets demonstrate CycleFQI's effectiveness. --- ### Beyond Pixels: Vector-to-Graph Transformation for Reliable Schematic Auditing Authors: Chengwei Ma, Zhen Tian, Zhou Zhou, Zhixian Xu, Xiaowei Zhu, Xia Hua, Si Shi, F. Richard Yu Published: 2026-02-12 Categories: cs.AI, cs.CV arXiv: https://arxiv.org/abs/2602.11678v1 Multimodal Large Language Models (MLLMs) have shown remarkable progress in visual understanding, yet they suffer from a critical limitation: structural blindness. Even state-of-the-art models fail to capture topology and symbolic logic in engineering schematics, as their pixel-driven paradigm discards the explicit vector-defined relations needed for reasoning. To overcome this, we propose a Vector-to-Graph (V2G) pipeline that converts CAD diagrams into property graphs where nodes represent components and edges encode connectivity, making structural dependencies explicit and machine-auditable. On a diagnostic benchmark of electrical compliance checks, V2G yields large accuracy gains across all error categories, while leading MLLMs remain near chance level. These results highlight the systemic inadequacy of pixel-based methods and demonstrate that structure-aware representations provide a reliable path toward practical deployment of multimodal AI in engineering domains. To facilitate further research, we release our benchmark and implementation at https://github.com/gm-embodied/V2G-Audit. --- ### Epistemic Regret Minimization: Label-Free Causal Critique Beyond Outcome Reward Authors: Edward Y. Chang, Longling Geng Published: 2026-02-12 Categories: cs.AI arXiv: https://arxiv.org/abs/2602.11675v4 Large language models can answer causal questions correctly for the wrong reasons. Current RL methods reward \emph{what} a model concludes but ignore \emph{why}, reinforcing correlational shortcuts -- a failure we call \emph{Reward Entrenchment}. We introduce \emph{Epistemic Regret Minimization} (\erm), a framework that critiques the causal \emph{structure} of a model's reasoning trace rather than its answer. Applying established causal principles, \erm flags unexamined confounders, correlation--intervention conflation, and unchecked back-door paths from exposed reasoning traces. The framework admits \emph{label-free} operation -- without the true causal graph or correct answer -- and we separately distinguish favorable benchmark-derived critique, error-direction cues, and fully label-free judge-generated critique in the experiments. Within a single episode, \erm detects and repairs causal reasoning errors; across episodes, it accumulates interventional evidence into a reward signal applicable where no answer key exists. Experiments on 1,360 scenarios across six frontier LLMs show that reasoning-heavy models (GPT-4 Turbo, GPT-5.2) resist outcome-only correction (25--31\% recovery) yet respond to causal critique (78--91\%), gaining $+53$--$59$ pp. Standard test-time methods (self-consistency, Best-of-$N$, Self-Refine) \emph{underperform} outcome-only reprompting on causal tasks, while ERM reduces residual Rung Collapse from 55--70\% to 4\%. A separation theorem proves outcome-only reward cannot close this gap; a controlled simulation confirms epistemic feedback does, outperforming outcome-only baselines 38-fold. --- ### Benchmark Health Index: A Systematic Framework for Benchmarking the Benchmarks of LLMs Authors: Longyuan Zhu, Hairan Hua, Linlin Miao, Bing Zhao Published: 2026-02-12 Categories: cs.AI arXiv: https://arxiv.org/abs/2602.11674v1 Large Language Models (LLMs) are advancing rapidly, yet the benchmarks used to measure this progress are becoming increasingly unreliable. Score inflation and selective reporting have eroded the authority of standard benchmarks, leaving the community uncertain about which evaluation results remain trustworthy. We introduce the Benchmark Health Index (BHI), a pure data-driven framework for auditing evaluation sets along three orthogonal and complementary axes: (1) Capability Discrimination, measuring how sharply a benchmark separates model performance beyond noise; (2) Anti-Saturation, estimating remaining headroom before ceiling effects erode resolution and thus the benchmark's expected longevity; and (3) Impact, quantifying influence across academic and industrial ecosystems via adoption breadth and practice-shaping power. By distilling 106 validated benchmarks from the technical reports of 91 representative models in 2025, we systematically characterize the evaluation landscape. BHI is the first framework to quantify benchmark health at a macro level, providing a principled basis for benchmark selection and enabling dynamic lifecycle management for next-generation evaluation protocols. --- ### RI-Mamba: Rotation-Invariant Mamba for Robust Text-to-Shape Retrieval Authors: Khanh Nguyen, Dasith de Silva Edirimuni, Ghulam Mubashar Hassan, Ajmal Mian Published: 2026-02-12 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.11673v1 3D assets have rapidly expanded in quantity and diversity due to the growing popularity of virtual reality and gaming. As a result, text-to-shape retrieval has become essential in facilitating intuitive search within large repositories. However, existing methods require canonical poses and support few object categories, limiting their real-world applicability where objects can belong to diverse classes and appear in random orientations. To address this challenge, we propose RI-Mamba, the first rotation-invariant state-space model for point clouds. RI-Mamba defines global and local reference frames to disentangle pose from geometry and uses Hilbert sorting to construct token sequences with meaningful geometric structure while maintaining rotation invariance. We further introduce a novel strategy to compute orientational embeddings and reintegrate them via feature-wise linear modulation, effectively recovering spatial context and enhancing model expressiveness. Our strategy is inherently compatible with state-space models and operates in linear time. To scale up retrieval, we adopt cross-modal contrastive learning with automated triplet generation, allowing training on diverse datasets without manual annotation. Extensive experiments demonstrate RI-Mamba's superior representational capacity and robustness, achieving state-of-the-art performance on the OmniObject3D benchmark across more than 200 object categories under arbitrary orientations. Our code will be made available at https://github.com/ndkhanh360/RI-Mamba.git. --- ### U-Net with Hadamard Transform and DCT Latent Spaces for Next-day Wildfire Spread Prediction Authors: Yingyi Luo, Shuaiang Rong, Adam Watts, Ahmet Enis Cetin Published: 2026-02-12 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.11672v1 We developed a lightweight and computationally efficient tool for next-day wildfire spread prediction using multimodal satellite data as input. The deep learning model, which we call Transform Domain Fusion UNet (TD-FusionUNet), incorporates trainable Hadamard Transform and Discrete Cosine Transform layers that apply two-dimensional transforms, enabling the network to capture essential "frequency" components in orthogonalized latent spaces. Additionally, we introduce custom preprocessing techniques, including random margin cropping and a Gaussian mixture model, to enrich the representation of the sparse pre-fire masks and enhance the model's generalization capability. The TD-FusionUNet is evaluated on two datasets which are the Next-Day Wildfire Spread dataset released by Google Research in 2023, and WildfireSpreadTS dataset. Our proposed TD-FusionUNet achieves an F1 score of 0.591 with 370k parameters, outperforming the UNet baseline using ResNet18 as the encoder reported in the WildfireSpreadTS dataset while using substantially fewer parameters. These results show that the proposed latent space fusion model balances accuracy and efficiency under a lightweight setting, making it suitable for real time wildfire prediction applications in resource limited environments. --- ### Egocentric Gaze Estimation via Neck-Mounted Camera Authors: Haoyu Huang, Yoichi Sato Published: 2026-02-12 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.11669v1 This paper introduces neck-mounted view gaze estimation, a new task that estimates user gaze from the neck-mounted camera perspective. Prior work on egocentric gaze estimation, which predicts device wearer's gaze location within the camera's field of view, mainly focuses on head-mounted cameras while alternative viewpoints remain underexplored. To bridge this gap, we collect the first dataset for this task, consisting of approximately 4 hours of video collected from 8 participants during everyday activities. We evaluate a transformer-based gaze estimation model, GLC, on the new dataset and propose two extensions: an auxiliary gaze out-of-bound classification task and a multi-view co-learning approach that jointly trains head-view and neck-view models using a geometry-aware auxiliary loss. Experimental results show that incorporating gaze out-of-bound classification improves performance over standard fine-tuning, while the co-learning approach does not yield gains. We further analyze these results and discuss implications for neck-mounted gaze estimation. --- ### Explainable Machine-Learning based Detection of Knee Injuries in Runners Authors: David Fuentes-Jiménez, Sara García-de-Villa, David Casillas-Pérez, Pablo Floría, Francisco-Manuel Melgarejo-Meseguer Published: 2026-02-12 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.11668v1 Running is a widely practiced activity but shows a high incidence of knee injuries, especially Patellofemoral Pain Syndrome (PFPS) and Iliotibial Band Syndrome (ITBS). Identifying gait patterns linked to these injuries can improve clinical decision-making, which requires precise systems capable of capturing and analyzing temporal kinematic data. This study uses optical motion capture systems to enhance detection of injury-related running patterns. We analyze a public dataset of 839 treadmill recordings from healthy and injured runners to evaluate how effectively these systems capture dynamic parameters relevant to injury classification. The focus is on the stance phase, using joint and segment angle time series and discrete point values. Three classification tasks are addressed: healthy vs. injured, healthy vs. PFPS, and healthy vs. ITBS. We examine different feature spaces, from traditional point-based metrics to full stance-phase time series and hybrid representations. Multiple models are tested, including classical algorithms (K-Nearest Neighbors, Gaussian Processes, Decision Trees) and deep learning architectures (CNNs, LSTMs). Performance is evaluated with accuracy, precision, recall, and F1-score. Explainability tools such as Shapley values, saliency maps, and Grad-CAM are used to interpret model behavior. Results show that combining time series with point values substantially improves detection. Deep learning models outperform classical ones, with CNNs achieving the highest accuracy: 77.9% for PFPS, 73.8% for ITBS, and 71.43% for the combined injury class. These findings highlight the potential of motion capture systems coupled with advanced machine learning to identify knee injury-related running patterns. --- ### PhyNiKCE: A Neurosymbolic Agentic Framework for Autonomous Computational Fluid Dynamics Authors: E Fan, Lisong Shi, Zhengtong Li, Chih-yung Wen Published: 2026-02-12 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2602.11666v1 The deployment of autonomous agents for Computational Fluid Dynamics (CFD), is critically limited by the probabilistic nature of Large Language Models (LLMs), which struggle to enforce the strict conservation laws and numerical stability required for physics-based simulations. Reliance on purely semantic Retrieval Augmented Generation (RAG) often leads to "context poisoning," where agents generate linguistically plausible but physically invalid configurations due to a fundamental Semantic-Physical Disconnect. To bridge this gap, this work introduces PhyNiKCE (Physical and Numerical Knowledgeable Context Engineering), a neurosymbolic agentic framework for trustworthy engineering. Unlike standard black-box agents, PhyNiKCE decouples neural planning from symbolic validation. It employs a Symbolic Knowledge Engine that treats simulation setup as a Constraint Satisfaction Problem, rigidly enforcing physical constraints via a Deterministic RAG Engine with specialized retrieval strategies for solvers, turbulence models, and boundary conditions. Validated through rigorous OpenFOAM experiments on practical, non-tutorial CFD tasks using Gemini-2.5-Pro/Flash, PhyNiKCE demonstrates a 96% relative improvement over state-of-the-art baselines. Furthermore, by replacing trial-and-error with knowledge-driven initialization, the framework reduced autonomous self-correction loops by 59% while simultaneously lowering LLM token consumption by 17%. These results demonstrate that decoupling neural generation from symbolic constraint enforcement significantly enhances robustness and efficiency. While validated on CFD, this architecture offers a scalable, auditable paradigm for Trustworthy Artificial Intelligence in broader industrial automation. --- ### Fully First-Order Algorithms for Online Bilevel Optimization Authors: Tingkai Jia, Cheng Chen Published: 2026-02-12 Categories: cs.LG, math.OC arXiv: https://arxiv.org/abs/2602.11665v2 In this work, we study nonconvex-strongly convex online bilevel optimization (OBO) using only first-order oracle. Existing OBO algorithms are mainly based on hypergradient descent, which requires access to a Hessian-vector product (HVP) oracle and potentially incurs high computational costs. By reformulating the original OBO problem as a single-level online problem with inequality constraints and constructing a sequence of Lagrangian function, we eliminate the need for HVPs arising from implicit differentiation. Specifically, we propose a fully first-order algorithm for OBO, and provide theoretical guarantees showing that it achieves regret of $O(1 + V_T + H_{2,T})$ with a total of $O(T\log T)$ iterations, where $V_T$ measures the variation in function values and $H_{2,T}$ characterizes the drift variation of the inner-level optimal solution. We also establish a sublinear regret bound under the single-loop structure by introducing additional gradient-variation terms. Furthermore, we develop an improved variant with an adaptive inner-iteration scheme, which removes the dependence on $H_{2,T}$ and achieves regret of $O(\log T + V_T)$. Finally, under the stochastic OBO setting, we establish the regret bound for the fully first-order algorithm, i.e., $O(T^{2/3}(1 + σ^2) + V_T + H_{2,T})$. Numerical experiments demonstrate the feasibility of our algorithm and support our theoretical findings. --- ### UMAP Is Spectral Clustering on the Fuzzy Nearest-Neighbor Graph Authors: Yang Yang Published: 2026-02-12 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.11662v1 UMAP (Uniform Manifold Approximation and Projection) is among the most widely used algorithms for non linear dimensionality reduction and data visualisation. Despite its popularity, and despite being presented through the lens of algebraic topology, the exact relationship between UMAP and classical spectral methods has remained informal. In this work, we prove that UMAP performs spectral clustering on the fuzzy k nearest neighbour graph. Our proof proceeds in three steps: (1) we show that UMAP's stochastic optimisation with negative sampling is a contrastive learning objective on the similarity graph; (2) we invoke the result of HaoChen et al. (8), establishing that contrastive learning on a similarity graph is equivalent to spectral clustering; and (3) we verify that UMAP's spectral initialisation computes the exact linear solution to this spectral problem. The equivalence is exact for Gaussian kernels, and holds as a first order approximation for UMAP's default Cauchy type kernel. Our result unifies UMAP, contrastive learning, and spectral clustering under a single framework, and provides theoretical grounding for several empirical observations about UMAP's behaviour. --- ### Quark Medical Alignment: A Holistic Multi-Dimensional Alignment and Collaborative Optimization Paradigm Authors: Tianxiang Xu, Jiayi Liu, Yixuan Tong, Jialu Xu, Yunqing Wei, Kaiwen Feng, PanPan Hou, Kangping Yin, Jiyuan Hu, Hao Zhou, Zhenxin Ma, Jian Xu et al. Published: 2026-02-12 Categories: cs.AI arXiv: https://arxiv.org/abs/2602.11661v2 While reinforcement learning for large language model alignment has progressed rapidly in recent years, transferring these paradigms to high-stakes medical question answering reveals a fundamental paradigm mismatch. Reinforcement Learning from Human Feedback relies on preference annotations that are prohibitively expensive and often fail to reflect the absolute correctness of medical facts. Reinforcement Learning from Verifiable Rewards lacks effective automatic verifiers and struggles to handle complex clinical contexts. Meanwhile, medical alignment requires the simultaneous optimization of correctness, safety, and compliance, yet multi-objective heterogeneous reward signals are prone to scale mismatch and optimization conflicts. To address these challenges, we propose a robust medical alignment paradigm. We first construct a holistic multi-dimensional medical alignment matrix that decomposes alignment objectives into four categories: fundamental capabilities, expert knowledge, online feedback, and format specifications. Within each category, we establish a closed loop of where observable metrics inform attributable diagnosis, which in turn drives optimizable rewards, thereby providing fine-grained, high-resolution supervision signals for subsequent iterative optimization. To resolve gradient domination and optimization instability problem caused by heterogeneous signals, we further propose a unified optimization mechanism. This mechanism employs Reference-Frozen Normalization to align reward scales and implements a Tri-Factor Adaptive Dynamic Weighting strategy to achieve collaborative optimization that is weakness-oriented, risk-prioritized, and redundancy-reducing. Experimental results demonstrate the effectiveness of our proposed paradigm in real-world medical scenario evaluations, establishing a new paradigm for complex alignment in vertical domains. --- ### Clutt3R-Seg: Sparse-view 3D Instance Segmentation for Language-grounded Grasping in Cluttered Scenes Authors: Jeongho Noh, Tai Hyoung Rhee, Eunho Lee, Jeongyun Kim, Sunwoo Lee, Ayoung Kim Published: 2026-02-12 Categories: cs.CV, cs.RO arXiv: https://arxiv.org/abs/2602.11660v1 Reliable 3D instance segmentation is fundamental to language-grounded robotic manipulation. Its critical application lies in cluttered environments, where occlusions, limited viewpoints, and noisy masks degrade perception. To address these challenges, we present Clutt3R-Seg, a zero-shot pipeline for robust 3D instance segmentation for language-grounded grasping in cluttered scenes. Our key idea is to introduce a hierarchical instance tree of semantic cues. Unlike prior approaches that attempt to refine noisy masks, our method leverages them as informative cues: through cross-view grouping and conditional substitution, the tree suppresses over- and under-segmentation, yielding view-consistent masks and robust 3D instances. Each instance is enriched with open-vocabulary semantic embeddings, enabling accurate target selection from natural language instructions. To handle scene changes during multi-stage tasks, we further introduce a consistency-aware update that preserves instance correspondences from only a single post-interaction image, allowing efficient adaptation without rescanning. Clutt3R-Seg is evaluated on both synthetic and real-world datasets, and validated on a real robot. Across all settings, it consistently outperforms state-of-the-art baselines in cluttered and sparse-view scenarios. Even on the most challenging heavy-clutter sequences, Clutt3R-Seg achieves an AP@25 of 61.66, over 2.2x higher than baselines, and with only four input views it surpasses MaskClustering with eight views by more than 2x. The code is available at: https://github.com/jeonghonoh/clutt3r-seg. --- ### EmoSpace: Immersive Affective Image Generation Guided by Fine-Grained Emotion Prototypes Authors: Bingyuan Wang, Xingbei Chen, Zongyang Qiu, Lin-Ping Yuan, Zeyu Wang Published: 2026-02-12 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.11658v2 Immersive affective content generation aims to create visually compelling VR imagery with controllable emotional nuance, yet existing methods typically rely on coarse labels or prompt-only control. Although modern diffusion transformers (DiTs) such as FLUX improve visual fidelity, they are not designed to incorporate structured affective representations. We present EmoSpace, an immersive affective content generation framework guided by fine-grained emotion prototypes, transforming free-form text and emotion descriptions into fine-grained affective imagery through three coordinated components. First, to represent sub-emotion variation beyond conventional categorical models, EmoSpace learns a hierarchical bank of 256 prototypes with input-conditioned adaptation through vision-language alignment. Second, Prototype-Conditioned Steering converts these prototypes into DiT-compatible generation signals through multi-pathway injection and temporal blending, while Iterative Prompt Refinement enriches prompts with prototype-aligned sub-emotion descriptors. Third, Affect-Grounded Modulation coordinates emotion conditioning with controllable LoRAs for panoramic, stylized, and multi-conditional generation. Through quantitative and qualitative evaluations, EmoSpace improves fine-grained emotional alignment while maintaining high aesthetic quality. Our user study shows that EmoSpace outputs are perceived as more emotionally aligned than baseline results and more suitable for immersive scene design. Additionally, we find that immersive presentation alters emotional perception and increases emotional engagement. Together, these findings inform the design of emotion-aware generative systems for immersive media, with potential applications including education, immersive storytelling, and artistic creation. We will release our code and models to facilitate future research along this line. --- ### SToRM: Supervised Token Reduction for Multi-modal LLMs toward efficient end-to-end autonomous driving Authors: Seo Hyun Kim, Jin Bok Park, Do Yeon Koo, Hogun Park, Il Yong Chun Published: 2026-02-12 Categories: cs.CV, cs.AI, cs.RO arXiv: https://arxiv.org/abs/2602.11656v3 In autonomous driving, end-to-end (E2E) driving systems that predict control commands directly from sensor data have achieved significant advancements. For safe driving in unexpected scenarios, these systems may additionally rely on human interventions such as natural language instructions. Using a multi-modal large language model (MLLM) facilitates human-vehicle interaction and can improve performance in such scenarios. However, this approach requires substantial computational resources due to its reliance on an LLM and numerous visual tokens from sensor inputs, which are limited in autonomous vehicles. Many MLLM studies have explored reducing visual tokens, but often suffer end-task performance degradation compared to using all tokens. To enable efficient E2E driving while maintaining performance comparable to using all tokens, this paper proposes the first Supervised Token Reduction framework for multi-modal LLMs (SToRM). The proposed framework consists of three key elements. First, a lightweight importance predictor with short-term sliding windows estimates token importance scores. Second, a supervised training approach uses an auxiliary path to obtain pseudo-supervision signals from an all-token LLM pass. Third, an anchor-context merging module partitions tokens into anchors and context tokens, and merges context tokens into relevant anchors to reduce redundancy while minimizing information loss. Experiments on the LangAuto benchmark show that SToRM outperforms state-of-the-art E2E driving MLLMs under the same reduced-token budget, maintaining all-token performance while reducing computational cost by up to 30x, and enabling real-time E2E driving on a standard GPU. --- ### LoRA-based Parameter-Efficient LLMs for Continuous Learning in Edge-based Malware Detection Authors: Christian Rondanini, Barbara Carminati, Elena Ferrari, Niccolò Lardo, Ashish Kundu Published: 2026-02-12 Categories: cs.CR, cs.AI, cs.DC arXiv: https://arxiv.org/abs/2602.11655v1 The proliferation of edge devices has created an urgent need for security solutions capable of detecting malware in real time while operating under strict computational and memory constraints. Recently, Large Language Models (LLMs) have demonstrated remarkable capabilities in recognizing complex patterns, yet their deployment on edge devices remains impractical due to their resource demands. However, in edge malware detection, static or centrally retrained models degrade under evolving threats and heterogeneous traffic; locally trained models become siloed and fail to transfer across domains. To overcome these limitations, in this paper, we present a continuous learning architecture for edge-based malware detection that combines local adaptation on each device with global knowledge sharing through parameter-efficient LoRA adapters. Lightweight transformer models (DistilBERT, DistilGPT-2, TinyT5) run on edge nodes and are incrementally fine-tuned on device-specific traffic; only the resulting LoRA modules are aggregated by a lightweight coordinator and redistributed, enabling cross-device generalization without exchanging raw data. We evaluate on two public IoT security datasets, Edge-IIoTset and TON-IoT, under multi-round learning to simulate evolving threats. Compared to isolated fine-tuning, the LoRA-based exchange yields up to 20-25% accuracy gains when models encounter previously unseen attacks from another domain, while maintaining stable loss and F1 across rounds. LoRA adds less than 1% to model size (~0.6-1.8 MB), making updates practical for constrained edge hardware. --- ### GR-Diffusion: 3D Gaussian Representation Meets Diffusion in Whole-Body PET Reconstruction Authors: Mengxiao Geng, Zijie Chen, Ran Hong, Bingxuan Li, Qiegen Liu Published: 2026-02-12 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.11653v1 Positron emission tomography (PET) reconstruction is a critical challenge in molecular imaging, often hampered by noise amplification, structural blurring, and detail loss due to sparse sampling and the ill-posed nature of inverse problems. The three-dimensional discrete Gaussian representation (GR), which efficiently encodes 3D scenes using parameterized discrete Gaussian distributions, has shown promise in computer vision. In this work, we pro-pose a novel GR-Diffusion framework that synergistically integrates the geometric priors of GR with the generative power of diffusion models for 3D low-dose whole-body PET reconstruction. GR-Diffusion employs GR to generate a reference 3D PET image from projection data, establishing a physically grounded and structurally explicit benchmark that overcomes the low-pass limitations of conventional point-based or voxel-based methods. This reference image serves as a dual guide during the diffusion process, ensuring both global consistency and local accuracy. Specifically, we employ a hierarchical guidance mechanism based on the GR reference. Fine-grained guidance leverages differences to refine local details, while coarse-grained guidance uses multi-scale difference maps to correct deviations. This strategy allows the diffusion model to sequentially integrate the strong geometric prior from GR and recover sub-voxel information. Experimental results on the UDPET and Clinical datasets with varying dose levels show that GR-Diffusion outperforms state-of-the-art methods in enhancing 3D whole-body PET image quality and preserving physiological details. --- ### DMind-3: A Sovereign Edge--Local--Cloud AI System with Controlled Deliberation and Correction-Based Tuning for Safe, Low-Latency Transaction Execution Authors: Enhao Huang, Frank Li, Tony Lin, Lowes Yang Published: 2026-02-12 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2602.11651v1 This paper introduces DMind-3, a sovereign Edge-Local-Cloud intelligence stack designed to secure irreversible financial execution in Web3 environments against adversarial risks and strict latency constraints. While existing cloud-centric assistants compromise privacy and fail under network congestion, and purely local solutions lack global ecosystem context, DMind-3 resolves these tensions by decomposing capability into three cooperating layers: a deterministic signing-time intent firewall at the edge, a private high-fidelity reasoning engine on user hardware, and a policy-governed global context synthesizer in the cloud. We propose policy-driven selective offloading to route computation based on privacy sensitivity and uncertainty, supported by two novel training objectives: Hierarchical Predictive Synthesis (HPS) for fusing time-varying macro signals, and Contrastive Chain-of-Correction Supervised Fine-Tuning (C$^3$-SFT) to enhance local verification reliability. Extensive evaluations demonstrate that DMind-3 achieves a 93.7% multi-turn success rate in protocol-constrained tasks and superior domain reasoning compared to general-purpose baselines, providing a scalable framework where safety is bound to the edge execution primitive while maintaining sovereignty over sensitive user intent. --- ### Investigating Learner-Aware Design of LLM-Generated Educational Feedback Authors: Momoka Furuhashi, Kouta Nakayama, Noboru Kawai, Takashi Kodama, Saku Sugawara, Kyosuke Takami Published: 2026-02-12 Categories: cs.CL arXiv: https://arxiv.org/abs/2602.11650v3 Although large language models (LLMs) show promise for generating educational feedback, it remains unclear how feedback should be designed (e.g., tone and coverage) to support answer revision and learner evaluations across learner profiles. We define six feedback designs for multiple-choice biology questions, including a baseline design and five variants with additional feedback elements, and conduct an empirical study with 321 high school students. We evaluate feedback using immediate revision performance and six subjective evaluation criteria, and analyze differences in subjective evaluations across learner profiles based on personality traits. Our results show that presenting task-relevant information clearly is associated with better immediate revision performance and is favorably evaluated across learner profiles, while we observe descriptive differences in evaluation patterns, particularly for informational novelty and affective framing. These findings support further investigation of personalized LLM feedback design. --- ### Which Feedback Works for Whom? Differential Effects of LLM-Generated Feedback Elements Across Learner Profiles Authors: Momoka Furuhashi, Kouta Nakayama, Noboru Kawai, Takashi Kodama, Saku Sugawara, Kyosuke Takami Published: 2026-02-12 Categories: cs.CL arXiv: https://arxiv.org/abs/2602.11650v1 Large language models (LLMs) show promise for automatically generating feedback in education settings. However, it remains unclear how specific feedback elements, such as tone and information coverage, contribute to learning outcomes and learner acceptance, particularly across learners with different personality traits. In this study, we define six feedback elements and generate feedback for multiple-choice biology questions using GPT-5. We conduct a learning experiment with 321 first-year high school students and evaluate feedback effectiveness using two learning outcomes measures and subjective evaluations across six criteria. We further analyze differences in how feedback acceptance varies across learners based on Big Five personality traits. Our results show that effective feedback elements share common patterns supporting learning outcomes, while learners' subjective preferences differ across personality-based clusters. These findings highlight the importance of selecting and adapting feedback elements according to learners' personality traits when we design LLM-generated feedback, and provide practical implications for personalized feedback design in education. --- ### Brain Tumor Classifiers Under Attack: Robustness of ResNet Variants Against Transferable FGSM and PGD Attacks Authors: Ryan Deem, Garrett Goodman, Waqas Majeed, Md Abdullah Al Hafiz Khan, Michail S. Alexiou Published: 2026-02-12 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2602.11646v1 Adversarial robustness in deep learning models for brain tumor classification remains an underexplored yet critical challenge, particularly for clinical deployment scenarios involving MRI data. In this work, we investigate the susceptibility and resilience of several ResNet-based architectures, referred to as BrainNet, BrainNeXt and DilationNet, against gradient-based adversarial attacks, namely FGSM and PGD. These models, based on ResNet, ResNeXt, and dilated ResNet variants respectively, are evaluated across three preprocessing configurations (i) full-sized augmented, (ii) shrunk augmented and (iii) shrunk non-augmented MRI datasets. Our experiments reveal that BrainNeXt models exhibit the highest robustness to black-box attacks, likely due to their increased cardinality, though they produce weaker transferable adversarial samples. In contrast, BrainNet and Dilation models are more vulnerable to attacks from each other, especially under PGD with higher iteration steps and $α$ values. Notably, shrunk and non-augmented data significantly reduce model resilience, even when the untampered test accuracy remains high, highlighting a key trade-off between input resolution and adversarial vulnerability. These results underscore the importance of jointly evaluating classification performance and adversarial robustness for reliable real-world deployment in brain MRI analysis. --- ### ViTaS: Visual Tactile Soft Fusion Contrastive Learning for Visuomotor Learning Authors: Yufeng Tian, Shuiqi Cheng, Tianming Wei, Tianxing Zhou, Yuanhang Zhang, Zixian Liu, Qianwei Han, Zhecheng Yuan, Huazhe Xu Published: 2026-02-12 Categories: cs.RO, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2602.11643v1 Tactile information plays a crucial role in human manipulation tasks and has recently garnered increasing attention in robotic manipulation. However, existing approaches mostly focus on the alignment of visual and tactile features and the integration mechanism tends to be direct concatenation. Consequently, they struggle to effectively cope with occluded scenarios due to neglecting the inherent complementary nature of both modalities and the alignment may not be exploited enough, limiting the potential of their real-world deployment. In this paper, we present ViTaS, a simple yet effective framework that incorporates both visual and tactile information to guide the behavior of an agent. We introduce Soft Fusion Contrastive Learning, an advanced version of conventional contrastive learning method and a CVAE module to utilize the alignment and complementarity within visuo-tactile representations. We demonstrate the effectiveness of our method in 12 simulated and 3 real-world environments, and our experiments show that ViTaS significantly outperforms existing baselines. Project page: https://skyrainwind.github.io/ViTaS/index.html. --- ### Electrostatics-Inspired Surface Reconstruction (EISR): Recovering 3D Shapes as a Superposition of Poisson's PDE Solutions Authors: Diego Patiño, Knut Peterson, Kostas Daniilidis, David K. Han Published: 2026-02-12 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.11642v1 Implicit shape representation, such as SDFs, is a popular approach to recover the surface of a 3D shape as the level sets of a scalar field. Several methods approximate SDFs using machine learning strategies that exploit the knowledge that SDFs are solutions of the Eikonal partial differential equation (PDEs). In this work, we present a novel approach to surface reconstruction by encoding it as a solution to a proxy PDE, namely Poisson's equation. Then, we explore the connection between Poisson's equation and physics, e.g., the electrostatic potential due to a positive charge density. We employ Green's functions to obtain a closed-form parametric expression for the PDE's solution, and leverage the linearity of our proxy PDE to find the target shape's implicit field as a superposition of solutions. Our method shows improved results in approximating high-frequency details, even with a small number of shape priors. --- ### Both Topology and Text Matter: Revisiting LLM-guided Out-of-Distribution Detection on Text-attributed Graphs Authors: Yinlin Zhu, Di Wu, Xu Wang, Guocong Quan, Miao Hu Published: 2026-02-12 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.11641v2 Text-attributed graphs (TAGs) associate nodes with textual attributes and graph structure, enabling GNNs to jointly model semantic and structural information. Although effective on in-distribution (ID) data, GNNs often fail on out-of-distribution (OOD) nodes with unseen textual or structural patterns, producing overconfident predictions without reliable OOD detection. Existing topology-driven methods mitigate node-level bias through neighboring structures, but typically encode texts as shallow features, underutilizing semantic information. Recent LLM-based approaches instead synthesize pseudo OOD priors from textual knowledge, yet suffer from two key limitations: (1) a trade-off between reliability and informativeness, where generated OOD exposures either deviate from true OOD semantics or introduce substantial ID noise; and (2) dependence on specialized architectures, limiting compatibility with topology-level advances validated in prior work. To address these issues, we propose LG-Plug, an LLM-Guided Plug-and-play framework for TAG OOD detection. LG-Plug aligns topology and text representations to obtain fine-grained node embeddings, then constructs consensus-driven OOD exposure through clustered iterative LLM prompting. To reduce LLM query cost, it further adopts lightweight in-cluster codebooks and heuristic sampling. The generated OOD exposure acts as a regularizer that separates ID and OOD nodes, enabling seamless integration with existing detectors. Experiments on six TAG benchmarks demonstrate that LG-Plug consistently improves topology-driven OOD detectors (>7% FPR95 reduction) and surpasses prior LLM-based methods (>5% FPR95 reduction). --- ### PACE: Prefix-Protected and Difficulty-Aware Compression for Efficient Reasoning Authors: Ruixiang Feng, Yuntao Wen, Silin Zhou, Ke Shi, Yifan Wang, Ran Le, Zhenwei An, Zongchao Chen, Chen Yang, Guangyue Peng, Yiming Jia, Dongsheng Wang et al. Published: 2026-02-12 Categories: cs.CL arXiv: https://arxiv.org/abs/2602.11639v1 Language Reasoning Models (LRMs) achieve strong performance by scaling test-time computation but often suffer from ``overthinking'', producing excessively long reasoning traces that increase latency and memory usage. Existing LRMs typically enforce conciseness with uniform length penalties, which over-compress crucial early deduction steps at the sequence level and indiscriminately penalize all queries at the group level. To solve these limitations, we propose \textbf{\model}, a dual-level framework for prefix-protected and difficulty-aware compression under hierarchical supervision. At the sequence level, prefix-protected optimization employs decaying mixed rollouts to maintain valid reasoning paths while promoting conciseness. At the group level, difficulty-aware penalty dynamically scales length constraints based on query complexity, maintaining exploration for harder questions while curbing redundancy on easier ones. Extensive experiments on DeepSeek-R1-Distill-Qwen (1.5B/7B) demonstrate that \model achieves a substantial reduction in token usage (up to \textbf{55.7\%}) while simultaneously improving accuracy (up to \textbf{4.1\%}) on math benchmarks, with generalization ability to code, science, and general domains. --- ### Variation-aware Flexible 3D Gaussian Editing Authors: Hao Qin, Yukai Sun, Meng Wang, Ming Kong, Mengxu Lu, Qiang Zhu Published: 2026-02-12 Categories: cs.GR, cs.AI arXiv: https://arxiv.org/abs/2602.11638v3 Indirect editing methods for 3D Gaussian Splatting (3DGS) have recently witnessed significant advancements. These approaches operate by first applying edits in the rendered 2D space and subsequently projecting the modifications back into 3D. However, this paradigm inevitably introduces cross-view inconsistencies and constrains both the flexibility and efficiency of the editing process. To address these challenges, we present VF-Editor, which enables native editing of Gaussian primitives by predicting attribute variations in a feedforward manner. To accurately and efficiently estimate these variations, we design a novel variation predictor distilled from 2D editing knowledge. The predictor encodes the input to generate a variation field and employs two learnable, parallel decoding functions to iteratively infer attribute changes for each 3D Gaussian. Thanks to its unified design, VF-Editor can seamlessly distill editing knowledge from diverse 2D editors and strategies into a single predictor, allowing for flexible and effective knowledge transfer into the 3D domain. Extensive experiments on both public and private datasets reveal the inherent limitations of indirect editing pipelines and validate the effectiveness and flexibility of our approach. --- ### ScalSelect: Scalable Training-Free Multimodal Data Selection for Efficient Visual Instruction Tuning Authors: Changti Wu, Jiahuai Mao, Yuzhuo Miao, Shijie Lian, Bin Yu, Xiaopeng Lin, Cong Huang, Lei Zhang, Kai Chen Published: 2026-02-12 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2602.11636v1 Large-scale Visual Instruction Tuning (VIT) has become a key paradigm for advancing the performance of vision-language models (VLMs) across various multimodal tasks. However, training on the large-scale datasets is computationally expensive and inefficient due to redundancy in the data, which motivates the need for multimodal data selection to improve training efficiency. Existing data selection methods for VIT either require costly training or gradient computation. Training-free alternatives often depend on proxy models or datasets, instruction-agnostic representations, and pairwise similarity with quadratic complexity, limiting scalability and representation fidelity. In this work, we propose ScalSelect, a scalable training-free multimodal data selection method with linear-time complexity with respect to the number of samples, eliminating the need for external models or auxiliary datasets. ScalSelect first constructs sample representations by extracting visual features most attended by instruction tokens in the target VLM, capturing instruction-relevant information. It then identifies samples whose representations best approximate the dominant subspace of the full dataset representations, enabling scalable importance scoring without pairwise comparisons. Extensive experiments across multiple VLMs, datasets, and selection budgets demonstrate that ScalSelect achieves over 97.5% of the performance of training on the full dataset using only 16% of the data, and even outperforms full-data training in some settings. The code is available at \href{https://github.com/ChangtiWu/ScalSelect}{ScalSelect}. --- ### Do MLLMs Really Understand Space? A Mathematical Reasoning Evaluation Authors: Shuo Lu, Jianjie Cheng, Yinuo Xu, Yongcan Yu, Lijun Sheng, Peijie Wang, Siru Jiang, Yongguan Hu, Run Ling, Yihua Shao, Ao Ma, Wei Feng et al. Published: 2026-02-12 Categories: cs.AI arXiv: https://arxiv.org/abs/2602.11635v2 Multimodal large language models (MLLMs) have achieved strong performance on perception-oriented tasks, yet their ability to perform mathematical spatial reasoning, defined as the capacity to parse and manipulate two- and three-dimensional relations, remains unclear. Humans easily solve textbook-style spatial reasoning problems with over 95\% accuracy, but we find that most leading MLLMs fail to reach even 60\% on the same tasks. This striking gap highlights spatial reasoning as a fundamental weakness of current models. To investigate this gap, we present \emph{MathSpatial}, the first large-scale and systematic dataset resource dedicated to mathematical spatial reasoning in MLLMs. \emph{MathSpatial} provides two complementary subsets: (i)~\emph{MathSpatial-Bench}, a rigorously curated evaluation set of 2{,}000 problems spanning 3 categories and 11 subtypes, designed to isolate spatial reasoning from perceptual noise; and (ii)~\emph{MathSpatial-Corpus}, a training set of 8{,}000 problems equipped with verified solutions and structured reasoning traces. All problems are sourced from authentic educational materials and undergo multi-stage quality control including deduplication, geometric consistency checking, and cross-validated solution verification. Benchmarking 16 leading MLLMs on \emph{MathSpatial-Bench} reveals that spatial reasoning remains a fundamental bottleneck: even GPT-5 lags behind human performance by over 35 percentage points, with particularly poor results on abstract deduction tasks. We further show that training on \emph{MathSpatial-Corpus} yields consistent improvements across model families, demonstrating the dataset's practical value for advancing spatial reasoning capabilities. \emph{MathSpatial} is publicly available at https://shuolucs.github.io/MathSpatial. --- ### TIP: Resisting Gradient Inversion via Targeted Interpretable Perturbation in Federated Learning Authors: Jianhua Wang, Yinlin Su Published: 2026-02-12 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.11633v1 Federated Learning (FL) facilitates collaborative model training while preserving data locality; however, the exchange of gradients renders the system vulnerable to Gradient Inversion Attacks (GIAs), allowing adversaries to reconstruct private training data with high fidelity. Existing defenses, such as Differential Privacy (DP), typically employ indiscriminate noise injection across all parameters, which severely degrades model utility and convergence stability. To address those limitation, we proposes Targeted Interpretable Perturbation (TIP), a novel defense framework that integrates model interpretability with frequency domain analysis. Unlike conventional methods that treat parameters uniformly, TIP introduces a dual-targeting strategy. First, leveraging Gradient-weighted Class Activation Mapping (Grad-CAM) to quantify channel sensitivity, we dynamically identify critical convolution channels that encode primary semantic features. Second, we transform these selected kernels into the frequency domain via the Discrete Fourier Transform and selectively inject calibrated perturbations into the high-frequency spectrum. By selectively perturbing high-frequency components, TIP effectively destroys the fine-grained details necessary for image reconstruction while preserving the low-frequency information crucial for model accuracy. Extensive experiments on benchmark datasets demonstrate that TIP renders reconstructed images visually unrecognizable against state-of-the-art GIAs, while maintaining global model accuracy comparable to non-private baselines, significantly outperforming existing DP-based defenses in the privacy-utility trade-off and interpretability. Code is available in https://github.com/2766733506/asldkfjssdf_arxiv --- ### CL API: Real-Time Closed-Loop Interactions with Biological Neural Networks Authors: David Hogan, Andrew Doherty, Boon Kien Khoo, Johnson Zhou, Richard Salib, James Stewart, Kiaran Lawson, Alon Loeffler, Brett Kagan Published: 2026-02-12 Categories: q-bio.NC, cs.ET, cs.NE, eess.SY arXiv: https://arxiv.org/abs/2602.11632v1 Biological neural networks (BNNs) are increasingly explored for their rich dynamics, parallelism, and adaptive behavior. Beyond understanding their function as a scientific endeavour, a key focus has been using these biological systems as a novel computing substrate. However, BNNs can only function as reliable information-processing systems if inputs are delivered in a temporally and structurally consistent manner. In practice, this requires stimulation with precisely controlled structure, microsecond-scale timing, multi-channel synchronization, and the ability to observe and respond to neural activity in real-time. Existing approaches to interacting with BNNs face a fundamental trade-off: they either depend on low-level hardware mechanisms, imposing prohibitive complexity for rapid iteration, or they sacrifice temporal and structural control, undermining consistency and reproducibility - particularly in closed-loop experiments. The Cortical Labs Application Programming Interface (CL API) enables real-time, sub-millisecond closed-loop interactions with BNNs. Taking a contract-based API design approach, the CL API provides users with precise stimulation semantics, transactional admission, deterministic ordering, and explicit synchronization guarantees. This contract is presented through a declarative Python interface, enabling non-expert programmers to express complex stimulation and closed-loop behavior without managing low-level scheduling or hardware details. Ultimately, the CL API provides an accessible and reproducible foundation for real-time experimentation with BNNs, supporting both fundamental biological research and emerging neurocomputing applications. --- ### Enforcing Reciprocity in Operator Learning for Seismic Wave Propagation Authors: Caifeng Zou, Yaozhong Shi, Zachary E. Ross, Robert W. Clayton, Kamyar Azizzadenesheli Published: 2026-02-12 Categories: physics.geo-ph, cs.LG arXiv: https://arxiv.org/abs/2602.11631v2 Accurate and efficient wavefield modeling underpins seismic structure and source studies. Traditional methods comply with physical laws but are computationally intensive. Data-driven methods, while opening new avenues for advancement, have yet to incorporate strict physical consistency. The principle of reciprocity is one of the most fundamental physical laws in wave propagation. We introduce the Reciprocity-Enforced Neural Operator (RENO), a transformer-based architecture for modeling seismic wave propagation that hard-codes the reciprocity principle. The model leverages the cross-attention mechanism and commutative operations to guarantee invariance under swapping source and receiver positions. Beyond improved physical consistency, the proposed architecture supports simultaneous realizations for multiple sources. This yields an order-of-magnitude inference speedup at a similar memory footprint over a conventional neural operator on a realistic multi-source configuration. We demonstrate the functionality using the reciprocity relation for particle velocity fields under single forces. This architecture is also applicable to pressure fields under dilatational sources and travel-time fields governed by the eikonal equation, paving the way for encoding more complex reciprocity relations. --- ### Neuro-Symbolic Multitasking: A Unified Framework for Discovering Generalizable Solutions to PDE Families Authors: Yipeng Huang, Dejun Xu, Zexin Lin, Zhenzhong Wang, Min Jiang Published: 2026-02-12 Categories: cs.AI arXiv: https://arxiv.org/abs/2602.11630v1 Solving Partial Differential Equations (PDEs) is fundamental to numerous scientific and engineering disciplines. A common challenge arises from solving the PDE families, which are characterized by sharing an identical mathematical structure but varying in specific parameters. Traditional numerical methods, such as the finite element method, need to independently solve each instance within a PDE family, which incurs massive computational cost. On the other hand, while recent advancements in machine learning PDE solvers offer impressive computational speed and accuracy, their inherent ``black-box" nature presents a considerable limitation. These methods primarily yield numerical approximations, thereby lacking the crucial interpretability provided by analytical expressions, which are essential for deeper scientific insight. To address these limitations, we propose a neuro-assisted multitasking symbolic PDE solver framework for PDE family solving, dubbed NMIPS. In particular, we employ multifactorial optimization to simultaneously discover the analytical solutions of PDEs. To enhance computational efficiency, we devise an affine transfer method by transferring learned mathematical structures among PDEs in a family, avoiding solving each PDE from scratch. Experimental results across multiple cases demonstrate promising improvements over existing baselines, achieving up to a $\sim$35.7% increase in accuracy while providing interpretable analytical solutions. --- ### GP2F: Cross-Domain Graph Prompting with Adaptive Fusion of Pre-trained Graph Neural Networks Authors: Dongxiao He, Wenxuan Sun, Yongqi Huang, Jitao Zhao, Di Jin Published: 2026-02-12 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.11629v2 Graph Prompt Learning (GPL) has recently emerged as a promising paradigm for downstream adaptation of pre-trained graph models, mitigating the misalignment between pre-training objectives and downstream tasks. Recently, the focus of GPL has shifted from in-domain to cross-domain scenarios, which is closer to the real world applications, where the pre-training source and downstream target often differ substantially in data distribution. However, why GPLs remain effective under such domain shifts is still unexplored. Empirically, we observe that representative GPL methods are competitive with two simple baselines in cross-domain settings: full fine-tuning (FT) and linear probing (LP), motivating us to explore a deeper understanding of the prompting mechanism. We provide a theoretical analysis demonstrating that jointly leveraging these two complementary branches yields a smaller estimation error than using either branch alone, formally proving that cross-domain GPL benefits from the integration between pre-trained knowledge and task-specific adaptation. Based on this insight, we propose GP2F, a dual-branch GPL method that explicitly instantiates the two extremes: (1) a frozen branch that retains pre-trained knowledge, and (2) an adapted branch with lightweight adapters for task-specific adaptation. We then perform adaptive fusion under topology constraints via a contrastive loss and a topology-consistent loss. Extensive experiments on cross-domain few-shot node and graph classification demonstrate that our method outperforms existing methods. --- ### PLESS: Pseudo-Label Enhancement with Spreading Scribbles for Weakly Supervised Segmentation Authors: Yeva Gabrielyan, Varduhi Yeghiazaryan, Irina Voiculescu Published: 2026-02-12 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2602.11628v1 Weakly supervised learning with scribble annotations uses sparse user-drawn strokes to indicate segmentation labels on a small subset of pixels. This annotation reduces the cost of dense pixel-wise labeling, but suffers inherently from noisy and incomplete supervision. Recent scribble-based approaches in medical image segmentation address this limitation using pseudo-label-based training; however, the quality of the pseudo-labels remains a key performance limit. We propose PLESS, a generic pseudo-label enhancement strategy which improves reliability and spatial consistency. It builds on a hierarchical partitioning of the image into a hierarchy of spatially coherent regions. PLESS propagates scribble information to refine pseudo-labels within semantically coherent regions. The framework is model-agnostic and easily integrates into existing pseudo-label methods. Experiments on two public cardiac MRI datasets (ACDC and MSCMRseg) across four scribble-supervised algorithms show consistent improvements in segmentation accuracy. Code will be made available on GitHub upon acceptance. ---