# Research Papers — 2026-02 · bundle page 100 of 210

> Full-text markdown of papers #4951–5000 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/100
[← Previous bundle](https://aipod.dev/papers/archive/2026-02/page/99.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-02/page/101.md)

### Analytical Results for Two Exponential Family Distributions in Hierarchical Dirichlet Processes

Authors: Naiqi Li
Published: 2026-02-13
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.12527v1

The Hierarchical Dirichlet Process (HDP) provides a flexible Bayesian nonparametric framework for modeling grouped data with a shared yet unbounded collection of mixture components. While existing applications of the HDP predominantly focus on the Dirichlet-multinomial conjugate structure, the framework itself is considerably more general and, in principle, accommodates a broad class of conjugate prior-likelihood pairs. In particular, exponential family distributions offer a unified and analytically tractable modeling paradigm that encompasses many commonly used distributions. In this paper, we investigate analytic results for two important members of the exponential family within the HDP framework: the Poisson distribution and the normal distribution. We derive explicit closed-form expressions for the corresponding Gamma-Poisson and Normal-Gamma-Normal conjugate pairs under the hierarchical Dirichlet process construction. Detailed derivations and proofs are provided to clarify the underlying mathematical structure and to demonstrate how conjugacy can be systematically exploited in hierarchical nonparametric models. Our work extends the applicability of the HDP beyond the Dirichlet-multinomial setting and furnishes practical analytic results for researchers employing hierarchical Bayesian nonparametrics.

---

### Constraint-Rectified Training for Efficient Chain-of-Thought

Authors: Qinhang Wu, Sen Lin, Ming Zhang, Yingbin Liang, Ness B. Shroff
Published: 2026-02-13
Categories: cs.LG, cs.CL
arXiv: https://arxiv.org/abs/2602.12526v1

Chain-of-Thought (CoT) has significantly enhanced the reasoning capabilities of Large Language Models (LLMs), especially when combined with reinforcement learning (RL) based post-training methods. While longer reasoning traces can improve answer quality and unlock abilities such as self-correction, they also incur high inference costs and often introduce redundant steps, known as overthinking. Recent research seeks to develop efficient reasoning strategies that balance reasoning length and accuracy, either through length-aware reward design or prompt-based calibration. However, these heuristic-based approaches may suffer from severe accuracy drop and be very sensitive to hyperparameters. To address these problems, we introduce CRT (Constraint-Rectified Training), a principled post-training framework based on reference-guarded constrained optimization, yielding a more stable and interpretable formulation for efficient reasoning. CRT alternates between minimizing reasoning length and rectifying accuracy only when performance falls below the reference, enabling stable and effective pruning of redundant reasoning. We further extend CRT with a two-stage training scheme that first discovers the shortest reliable reasoning patterns and then refines accuracy under a learnt length budget, preventing the re-emergence of verbose CoT. Our comprehensive evaluation shows that this framework consistently reduces token usage while maintaining answer quality at a robust and reliable level. Further analysis reveals that CRT improves reasoning efficiency not only by shortening responses but also by reducing internal language redundancy, leading to a new evaluation metric. Moreover, CRT-based training naturally yields a sequence of intermediate checkpoints that span a spectrum of explanation lengths while preserving correctness, enabling fine-grained control over reasoning verbosity without retraining.

---

### Geometric Stratification for Singular Configurations of the P3P Problem via Local Dual Space

Authors: Xueying Sun, Zijia Li, Nan Li
Published: 2026-02-13
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.12525v1

This paper investigates singular configurations of the P3P problem. Using local dual space, a systematic algebraic-computational framework is proposed to give a complete geometric stratification for the P3P singular configurations with respect to the multiplicity $μ$ of the camera center $O$: for $μ\ge 2$, $O$ lies on the ``danger cylinder'', for $μ\ge 3$, $O$ lies on one of three generatrices of the danger cylinder associated with the first Morley triangle or the circumcircle, and for $μ\ge 4$, $O$ lies on the circumcircle which indeed corresponds to infinite P3P solutions. Furthermore, a geometric stratification for the complementary configuration $O^\prime$ associated with a singular configuration $O$ is studied as well: for $μ\ge 2$, $O^\prime$ lies on a deltoidal surface associated with the danger cylinder, and for $μ\ge 3$, $O^\prime$ lies on one of three cuspidal curves of the deltoidal surface.

---

### LiDAR-Anchored Collaborative Distillation for Robust 2D Representations

Authors: Wonjun Jo, Hyunwoo Ha, Kim Ji-Yeon, Hawook Jeong, Tae-Hyun Oh
Published: 2026-02-13
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.12524v1

As deep learning continues to advance, self-supervised learning has made considerable strides. It allows 2D image encoders to extract useful features for various downstream tasks, including those related to vision-based systems. Nevertheless, pre-trained 2D image encoders fall short in conducting the task under noisy and adverse weather conditions beyond clear daytime scenes, which require for robust visual perception. To address these issues, we propose a novel self-supervised approach, \textbf{Collaborative Distillation}, which leverages 3D LiDAR as self-supervision to improve robustness to noisy and adverse weather conditions in 2D image encoders while retaining their original capabilities. Our method outperforms competing methods in various downstream tasks across diverse conditions and exhibits strong generalization ability. In addition, our method also improves 3D awareness stemming from LiDAR's characteristics. This advancement highlights our method's practicality and adaptability in real-world scenarios.

---

### Multi-Agent Model-Based Reinforcement Learning with Joint State-Action Learned Embeddings

Authors: Zhizun Wang, David Meger
Published: 2026-02-13
Categories: cs.LG, cs.MA
arXiv: https://arxiv.org/abs/2602.12520v1

Learning to coordinate many agents in partially observable and highly dynamic environments requires both informative representations and data-efficient training. To address this challenge, we present a novel model-based multi-agent reinforcement learning framework that unifies joint state-action representation learning with imaginative roll-outs. We design a world model trained with variational auto-encoders and augment the model using the state-action learned embedding (SALE). SALE is injected into both the imagination module that forecasts plausible future roll-outs and the joint agent network whose individual action values are combined through a mixing network to estimate the joint action-value function. By coupling imagined trajectories with SALE-based action values, the agents acquire a richer understanding of how their choices influence collective outcomes, leading to improved long-term planning and optimization under limited real-environment interactions. Empirical studies on well-established multi-agent benchmarks, including StarCraft II Micro-Management, Multi-Agent MuJoCo, and Level-Based Foraging challenges, demonstrate consistent gains of our method over baseline algorithms and highlight the effectiveness of joint state-action learned embeddings within a multi-agent model-based paradigm.

---

### Bench-MFG: A Benchmark Suite for Learning in Stationary Mean Field Games

Authors: Lorenzo Magnino, Jiacheng Shen, Matthieu Geist, Olivier Pietquin, Mathieu Laurière
Published: 2026-02-13
Categories: cs.LG, cs.AI, cs.MA, math.OC
arXiv: https://arxiv.org/abs/2602.12517v1

The intersection of Mean Field Games (MFGs) and Reinforcement Learning (RL) has fostered a growing family of algorithms designed to solve large-scale multi-agent systems. However, the field currently lacks a standardized evaluation protocol, forcing researchers to rely on bespoke, isolated, and often simplistic environments. This fragmentation makes it difficult to assess the robustness, generalization, and failure modes of emerging methods. To address this gap, we propose a comprehensive benchmark suite for MFGs (Bench-MFG), focusing on the discrete-time, discrete-space, stationary setting for the sake of clarity. We introduce a taxonomy of problem classes, ranging from no-interaction and monotone games to potential and dynamics-coupled games, and provide prototypical environments for each. Furthermore, we propose MF-Garnets, a method for generating random MFG instances to facilitate rigorous statistical testing. We benchmark a variety of learning algorithms across these environments, including a novel black-box approach (MF-PSO) for exploitability minimization. Based on our extensive empirical results, we propose guidelines to standardize future experimental comparisons. Code available at \href{https://github.com/lorenzomagnino/Bench-MFG}{https://github.com/lorenzomagnino/Bench-MFG}.

---

### Matching of SAR and optical images based on transformation to shared modality

Authors: Alexey Borisov, Evgeny Myasnikov, Vladislav Myasnikov
Published: 2026-02-13
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.12515v1

Significant differences in optical images and Synthetic Aperture Radar (SAR) images are caused by fundamental differences in the physical principles underlying their acquisition by Earth remote sensing platforms. These differences make precise image matching (co-registration) of these two types of images difficult. In this paper, we propose a new approach to image matching of optical and SAR images, which is based on transforming the images to a new modality. The new image modality is common to both optical and SAR images and satisfies the following conditions. First, the transformed images must have an equal pre-defined number of channels. Second, the transformed and co-registered images must be as similar as possible. Third, the transformed images must be non-degenerate, meaning they must preserve the significant features of the original images. To further match images transformed to this shared modality, we train the RoMa image matching model, which is one of the leading solutions for matching of regular digital photographs. We evaluated the proposed approach on the publicly available MultiSenGE dataset containing both optical and SAR images. We demonstrated its superiority over alternative approaches based on image translation between original modalities and various feature matching algorithms. The proposed solution not only provides better quality of matching, but is also more versatile. It enables the use of ready-made RoMa and DeDoDe models, pre-trained for regular images, without retraining for a new modality, while maintaining high-quality matching of optical and SAR images.

---

### Visual RAG Toolkit: Scaling Multi-Vector Visual Retrieval with Training-Free Pooling and Multi-Stage Search

Authors: Ara Yeroyan
Published: 2026-02-13
Categories: cs.IR, cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2602.12510v1

Multi-vector visual retrievers (e.g., ColPali-style late interaction models) deliver strong accuracy, but scale poorly because each page yields thousands of vectors, making indexing and search increasingly expensive. We present Visual RAG Toolkit, a practical system for scaling visual multi-vector retrieval with training-free, model-aware pooling and multi-stage retrieval. Motivated by Matryoshka Embeddings, our method performs static spatial pooling - including a lightweight sliding-window averaging variant - over patch embeddings to produce compact tile-level and global representations for fast candidate generation, followed by exact MaxSim reranking using full multi-vector embeddings. Our design yields a quadratic reduction in vector-to-vector comparisons by reducing stored vectors per page from thousands to dozens, notably without requiring post-training, adapters, or distillation. Across experiments with interaction-style models such as ColPali and ColSmol-500M, we observe that over the limited ViDoRe v2 benchmark corpus 2-stage retrieval typically preserves NDCG and Recall @ 5/10 with minimal degradation, while substantially improving throughput (approximately 4x QPS); with sensitivity mainly at very large k. The toolkit additionally provides robust preprocessing - high resolution PDF to image conversion, optional margin/empty-region cropping and token hygiene (indexing only visual tokens) - and a reproducible evaluation pipeline, enabling rapid exploration of two-, three-, and cascaded retrieval variants. By emphasizing efficiency at common cutoffs (e.g., k <= 10), the toolkit lowers hardware barriers and makes state-of-the-art visual retrieval more accessible in practice.

---

### Monocular Reconstruction of Neural Tactile Fields

Authors: Pavan Mantripragada, Siddhanth Deshmukh, Eadom Dessalene, Manas Desai, Yiannis Aloimonos
Published: 2026-02-13
Categories: cs.RO, cs.AI, cs.CV
arXiv: https://arxiv.org/abs/2602.12508v1

Robots operating in the real world must plan through environments that deform, yield, and reconfigure under contact, requiring interaction-aware 3D representations that extend beyond static geometric occupancy. To address this, we introduce neural tactile fields, a novel 3D representation that maps spatial locations to the expected tactile response upon contact. Our model predicts these neural tactile fields from a single monocular RGB image -- the first method to do so. When integrated with off-the-shelf path planners, neural tactile fields enable robots to generate paths that avoid high-resistance objects while deliberately routing through low-resistance regions (e.g. foliage), rather than treating all occupied space as equally impassable. Empirically, our learning framework improves volumetric 3D reconstruction by $85.8\%$ and surface reconstruction by $26.7\%$ compared to state-of-the-art monocular 3D reconstruction methods (LRM and Direct3D).

---

### On Robustness and Chain-of-Thought Consistency of RL-Finetuned VLMs

Authors: Rosie Zhao, Anshul Shah, Xiaoyu Zhu, Xinke Deng, Zhongyu Jiang, Yang Yang, Joerg Liebelt, Arnab Mondal
Published: 2026-02-13
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.12506v3

Reinforcement learning (RL) finetuning has become a key technique for enhancing large language models (LLMs) on reasoning-intensive tasks, motivating its extension to vision-language models (VLMs). While RL-tuned VLMs improve on visual reasoning benchmarks, they remain vulnerable to weak visual grounding, hallucinations, and over-reliance on textual cues. We show that simple, controlled textual perturbations, including misleading captions or incorrect chain-of-thought (CoT) traces, cause substantial drops in robustness and confidence, and that these effects are more pronounced when CoT consistency is taken into account across open-source multimodal reasoning models. In contrast, closed models exhibit similar failure modes but maintain markedly greater robustness and reasoning consistency, suggesting that the gap reflects a shortcoming in current open-source RL finetuning rather than an inherent limitation of the task. To better understand these vulnerabilities, we further analyze RL finetuning dynamics and uncover an accuracy-faithfulness trade-off: finetuning raises benchmark accuracy, but can simultaneously erode the reliability of the accompanying CoT and its robustness to contextual shifts. Although adversarial augmentation improves robustness, it does not by itself prevent faithfulness drift. Incorporating a faithfulness-aware reward can restore alignment between answers and reasoning, but when paired with augmentation, training risks collapsing onto shortcut strategies and robustness remains elusive. Together, these findings highlight the limitations of accuracy-only evaluations and motivate training and assessment protocols that jointly emphasize correctness, robustness, and the faithfulness of visually grounded reasoning.

---

### Favia: Forensic Agent for Vulnerability-fix Identification and Analysis

Authors: André Storhaug, Jiamou Sun, Jingyue Li
Published: 2026-02-13
Categories: cs.SE, cs.AI, cs.CR
arXiv: https://arxiv.org/abs/2602.12500v1

Identifying vulnerability-fixing commits corresponding to disclosed CVEs is essential for secure software maintenance but remains challenging at scale, as large repositories contain millions of commits of which only a small fraction address security issues. Existing automated approaches, including traditional machine learning techniques and recent large language model (LLM)-based methods, often suffer from poor precision-recall trade-offs. Frequently evaluated on randomly sampled commits, we uncover that they are substantially underestimating real-world difficulty, where candidate commits are already security-relevant and highly similar. We propose Favia, a forensic, agent-based framework for vulnerability-fix identification that combines scalable candidate ranking with deep and iterative semantic reasoning. Favia first employs an efficient ranking stage to narrow the search space of commits. Each commit is then rigorously evaluated using a ReAct-based LLM agent. By providing the agent with a pre-commit repository as environment, along with specialized tools, the agent tries to localize vulnerable components, navigates the codebase, and establishes causal alignment between code changes and vulnerability root causes. This evidence-driven process enables robust identification of indirect, multi-file, and non-trivial fixes that elude single-pass or similarity-based methods. We evaluate Favia on CVEVC, a large-scale dataset we made that comprises over 8 million commits from 3,708 real-world repositories, and show that it consistently outperforms state-of-the-art traditional and LLM-based baselines under realistic candidate selection, achieving the strongest precision-recall trade-offs and highest F1-scores.

---

### A Theoretical Analysis of Mamba's Training Dynamics: Filtering Relevant Features for Generalization in State Space Models

Authors: Mugunthan Shandirasegaran, Hongkang Li, Songyang Zhang, Meng Wang, Shuai Zhang
Published: 2026-02-13
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.12499v1

The recent empirical success of Mamba and other selective state space models (SSMs) has renewed interest in non-attention architectures for sequence modeling, yet their theoretical foundations remain underexplored. We present a first-step analysis of generalization and learning dynamics for a simplified but representative Mamba block: a single-layer, single-head selective SSM with input-dependent gating, followed by a two-layer MLP trained via gradient descent (GD). Our study adopts a structured data model with tokens that include both class-relevant and class-irrelevant patterns under token-level noise and examines two canonical regimes: majority-voting and locality-structured data sequences. We prove that the model achieves guaranteed generalization by establishing non-asymptotic sample complexity and convergence rate bounds, which improve as the effective signal increases and the noise decreases. Furthermore, we show that the gating vector aligns with class-relevant features while ignoring irrelevant ones, thereby formalizing a feature-selection role similar to attention but realized through selective recurrence. Numerical experiments on synthetic data justify our theoretical results. Overall, our results provide principled insight into when and why Mamba-style selective SSMs learn efficiently, offering a theoretical counterpoint to Transformer-centric explanations.

---

### NAST: Improving Negation Handling in Medical Vision-Language Models through Negation-Aware Selective Training

Authors: Ali Abbasi, Mehdi Taghipour, Rahmatollah Beheshti
Published: 2026-02-13
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.12498v2

Negation is a fundamental linguistic operation in clinical reporting, yet vision-language models (VLMs) frequently fail to distinguish affirmative from negated medical statements. To systematically characterize this limitation, we introduce a radiology-specific diagnostic benchmark that evaluates polarity sensitivity under controlled clinical conditions, revealing that common medical VLMs consistently confuse negated and non-negated findings. To enable learning beyond simple condition absence, we further construct a contextual clinical negation dataset that encodes structured claims and supports attribute-level negations involving location and severity. Building on these resources, we propose Negation-Aware Selective Training (NAST), an interpretability-guided adaptation method that uses causal tracing effects (CTEs) to modulate layer-wise gradient updates during fine-tuning. Rather than applying uniform learning rates, NAST scales each layer's update according to its causal contribution to negation processing, transforming mechanistic interpretability signals into a principled optimization rule. Experiments demonstrate improved discrimination of affirmative and negated clinical statements without degrading general vision-language alignment, highlighting the value of causal interpretability for targeted model adaptation in safety-critical medical settings. Code and resources are available at https://github.com/healthylaife/NAST.

---

### Layer-Specific Fine-Tuning for Improved Negation Handling in Medical Vision-Language Models

Authors: Ali Abbasi, Mehdi Taghipour, Rahmatollah Beheshti
Published: 2026-02-13
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.12498v1

Negation is a fundamental linguistic operation in clinical reporting, yet vision-language models (VLMs) frequently fail to distinguish affirmative from negated medical statements. To systematically characterize this limitation, we introduce a radiology-specific diagnostic benchmark that evaluates polarity sensitivity under controlled clinical conditions, revealing that common medical VLMs consistently confuse negated and non-negated findings. To enable learning beyond simple condition absence, we further construct a contextual clinical negation dataset that encodes structured claims and supports attribute-level negations involving location and severity. Building on these resources, we propose Negation-Aware Selective Training (NAST), an interpretability-guided adaptation method that uses causal tracing effects (CTEs) to modulate layer-wise gradient updates during fine-tuning. Rather than applying uniform learning rates, NAST scales each layer's update according to its causal contribution to negation processing, transforming mechanistic interpretability signals into a principled optimization rule. Experiments demonstrate improved discrimination of affirmative and negated clinical statements without degrading general vision-language alignment, highlighting the value of causal interpretability for targeted model adaptation in safety-critical medical settings. Code and resources are available at https://github.com/healthylaife/NAST.

---

### Composable Model-Free RL for Navigation with Input-Affine Systems

Authors: Xinhuan Sang, Abdelrahman Abdelgawad, Roberto Tron
Published: 2026-02-13
Categories: cs.RO, cs.LG
arXiv: https://arxiv.org/abs/2602.12492v1

As autonomous robots move into complex, dynamic real-world environments, they must learn to navigate safely in real time, yet anticipating all possible behaviors is infeasible. We propose a composable, model-free reinforcement learning method that learns a value function and an optimal policy for each individual environment element (e.g., goal or obstacle) and composes them online to achieve goal reaching and collision avoidance. Assuming unknown nonlinear dynamics that evolve in continuous time and are input-affine, we derive a continuous-time Hamilton-Jacobi-Bellman (HJB) equation for the value function and show that the corresponding advantage function is quadratic in the action and optimal policy. Based on this structure, we introduce a model-free actor-critic algorithm that learns policies and value functions for static or moving obstacles using gradient descent. We then compose multiple reach/avoid models via a quadratically constrained quadratic program (QCQP), yielding formal obstacle-avoidance guarantees in terms of value-function level sets, providing a model-free alternative to CLF/CBF-based controllers. Simulations demonstrate improved performance over a PPO baseline applied to a discrete-time approximation.

---

### Transformer-based CoVaR: Systemic Risk in Textual Information

Authors: Junyu Chen, Tom Boot, Lingwei Kong, Weining Wang
Published: 2026-02-13
Categories: econ.EM, q-fin.RM, stat.ML
arXiv: https://arxiv.org/abs/2602.12490v1

Conditional Value-at-Risk (CoVaR) quantifies systemic financial risk by measuring the loss quantile of one asset, conditional on another asset experiencing distress. We develop a Transformer-based methodology that integrates financial news articles directly with market data to improve CoVaR estimates. Unlike approaches that use predefined sentiment scores, our method incorporates raw text embeddings generated by a large language model (LLM). We prove explicit error bounds for our Transformer CoVaR estimator, showing that accurate CoVaR learning is possible even with small datasets. Using U.S. market returns and Reuters news items from 2006--2013, our out-of-sample results show that textual information impacts the CoVaR forecasts. With better predictive performance, we identify a pronounced negative dip during market stress periods across several equity assets when comparing the Transformer-based CoVaR to both the CoVaR without text and the CoVaR using traditional sentiment measures. Our results show that textual data can be used to effectively model systemic risk without requiring prohibitively large data sets.

---

### Insertion Network for Image Sequence Correspondence

Authors: Dingjie Su, Weixiang Hong, Benoit M. Dawant, Bennett A. Landman
Published: 2026-02-13
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.12489v1

We propose a novel method for establishing correspondence between two sequences of 2D images. One particular application of this technique is slice-level content navigation, where the goal is to localize specific 2D slices within a 3D volume or determine the anatomical coverage of a 3D scan based on its 2D slices. This serves as an important preprocessing step for various diagnostic tasks, as well as for automatic registration and segmentation pipelines. Our approach builds sequence correspondence by training a network to learn how to insert a slice from one sequence into the appropriate position in another. This is achieved by encoding contextual representations of each slice and modeling the insertion process using a slice-to-slice attention mechanism. We apply this method to localize manually labeled key slices in body CT scans and compare its performance to the current state-of-the-art alternative known as body part regression, which predicts anatomical position scores for individual slices. Unlike body part regression, which treats each slice independently, our method leverages contextual information from the entire sequence. Experimental results show that the insertion network reduces slice localization errors in supervised settings from 8.4 mm to 5.4 mm, demonstrating a substantial improvement in accuracy.

---

### Gradient-Enhanced Partitioned Gaussian Processes for Real-Time Quadrotor Dynamics Modeling

Authors: Xinhuan Sang, Adam Rozman, Sheryl Grace, Roberto Tron
Published: 2026-02-13
Categories: cs.RO, cs.LG
arXiv: https://arxiv.org/abs/2602.12487v1

We present a quadrotor dynamics Gaussian Process (GP) with gradient information that achieves real-time inference via state-space partitioning and approximation, and that includes aerodynamic effects using data from mid-fidelity potential flow simulations. While traditional GP-based approaches provide reliable Bayesian predictions with uncertainty quantification, they are computationally expensive and thus unsuitable for real-time simulations. To address this challenge, we integrate gradient information to improve accuracy and introduce a novel partitioning and approximation strategy to reduce online computational cost. In particular, for the latter, we associate a local GP with each non-overlapping region; by splitting the training data into local near and far subsets, and by using Schur complements, we show that a large part of the matrix inversions required for inference can be performed offline, enabling real-time inference at frequencies above 30 Hz on standard desktop hardware. To generate a training dataset that captures aerodynamic effects, such as rotor-rotor interactions and apparent wind direction, we use the CHARM code, which is a mid-fidelity aerodynamic solver. It is applied to the SUI Endurance quadrotor to predict force and torque, along with noise at three specified locations. The derivative information is obtained via finite differences. Experimental results demonstrate that the proposed partitioned GP with gradient conditioning achieves higher accuracy than standard partitioned GPs without gradient information, while greatly reducing computational time. This framework provides an efficient foundation for real-time aerodynamic prediction and control algorithms in complex and unsteady environments.

---

### SPIRE: Structure-Preserving Interpretable Retrieval of Evidence

Authors: Mike Rainey, Umut Acar, Muhammed Sezer
Published: 2026-02-12
Categories: cs.IR, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2604.20849v1

Retrieval-augmented generation over semi-structured sources such as HTML is constrained by a mismatch between document structure and the flat, sequence-based interfaces of today's embedding and generative models. Retrieval pipelines often linearize documents into fixed-size chunks before indexing, which obscures section structure, lists, and tables, and makes it difficult to return small, citation-ready evidence without losing the surrounding context that makes it interpretable. We present a structure-aware retrieval pipeline that operates over tree-structured documents. The core idea is to represent candidates as subdocuments: precise, addressable selections that preserve structural identity while deferring the choice of surrounding context. We define a small set of document primitives--paths and path sets, subdocument extraction by pruning, and two contextualization mechanisms. Global contextualization adds the non-local scaffolding needed to make a selection intelligible (e.g., titles, headers, list and table structure). Local contextualization expands a seed selection within its structural neighborhood to obtain a compact, context-rich view under a target budget. Building on these primitives, we describe an embedding-based candidate generator that indexes sentence-seeded subdocuments and a query-time, document-aware aggregation step that amortizes shared structural context. We then introduce a contextual filtering stage that re-scores retrieved candidates using locally contextualized views. Across experiments on HTML question-answering benchmarks, we find that preserving structure while contextualizing selections yields higher-quality, more diverse citations under fixed budgets than strong passage-based baselines, while maintaining scalability.

---

### IMAGAgent: Orchestrating Multi-Turn Image Editing via Constraint-Aware Planning and Reflection

Authors: Fei Shen, Chengyu Xie, Lihong Wang, Zhanyi Zhang, Xin Jiang, Xiaoyu Du, Jinhui Tang
Published: 2026-02-12
Categories: cs.GR, cs.AI, cs.CV, cs.MA
arXiv: https://arxiv.org/abs/2603.29602v1

Existing multi-turn image editing paradigms are often confined to isolated single-step execution. Due to a lack of context-awareness and closed-loop feedback mechanisms, they are prone to error accumulation and semantic drift during multi-turn interactions, ultimately resulting in severe structural distortion of the generated images. For that, we propose \textbf{IMAGAgent}, a multi-turn image editing agent framework based on a "plan-execute-reflect" closed-loop mechanism that achieves deep synergy among instruction parsing, tool scheduling, and adaptive correction within a unified pipeline. Specifically, we first present a constraint-aware planning module that leverages a vision-language model (VLM) to precisely decompose complex natural language instructions into a series of executable sub-tasks, governed by target singularity, semantic atomicity, and visual perceptibility. Then, the tool-chain orchestration module dynamically constructs execution paths based on the current image, the current sub-task, and the historical context, enabling adaptive scheduling and collaborative operation among heterogeneous operation models covering image retrieval, segmentation, detection, and editing. Finally, we devise a multi-expert collaborative reflection mechanism where a central large language model (LLM) receives the image to be edited and synthesizes VLM critiques into holistic feedback, simultaneously triggering fine-grained self-correction and recording feedback outcomes to optimize future decisions. Extensive experiments on our constructed \textbf{MTEditBench} and the MagicBrush dataset demonstrate that IMAGAgent achieves performance significantly superior to existing methods in terms of instruction consistency, editing precision, and overall quality. The code is available at https://github.com/hackermmzz/IMAGAgent.git.

---

### Your Robot Will Feel You Now: Empathy in Robots and Embodied Agents

Authors: Angelica Lim, Ö. Nilay Yalçin
Published: 2026-02-12
Categories: cs.RO, cs.AI, cs.CV
arXiv: https://arxiv.org/abs/2603.20200v1

The fields of human-robot interaction (HRI) and embodied conversational agents (ECAs) have long studied how empathy could be implemented in machines. One of the major drivers has been the goal of giving multimodal social and emotional intelligence to these artificially intelligent agents, which interact with people through facial expressions, body, gesture, and speech. What empathic behaviors and models have these fields implemented by mimicking human and animal behavior? In what ways have they explored creating machine-specific analogies? This chapter aims to review the knowledge from these studies, towards applying the lessons learned to today's ubiquitous, language-based agents such as ChatGPT.

---

### Quantifying Hallucinations in Language Language Models on Medical Textbooks

Authors: Brandon C. Colelough, Davis Bartels, Dina Demner-Fushman
Published: 2026-02-12
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2603.09986v3

Hallucinations, the tendency for large language models to provide responses with factually incorrect and unsupported claims, is a serious problem within natural language processing for which we do not yet have an effective solution to mitigate against. Existing benchmarks for medical QA rarely evaluate this behavior against a fixed evidence source. We ask how often hallucinations occur on textbook-grounded QA and how responses to medical QA prompts vary across models. We conduct two experiments, the first experiment to determine the prevalence of hallucinations for a prominent open source large language model (LLaMA-70B-Instruct) in medical QA given closed-source zero-shot prompts, and the second experiment to determine the prevalence of hallucinations and clinician preference to model responses. We observed, in experiment one, with the passages provided, LLaMA-70B-Instruct hallucinated in 19.7\% of answers (95\% CI 18.6 to 20.7) even though 98.8\% of prompt responses received maximal plausibility, and observed in experiment two, across models, lower hallucination rates aligned with higher usefulness scores ($ρ=-0.71$, $p=0.058$). Clinicians produced high agreement (quadratic weighted $κ=0.92$) and ($τ_b=0.06$ to $0.18$, $κ=0.57$ to $0.61$) for experiments 1 and 2 respectively. Our findings indicate that, across all scales and architectures tested, current large language models remain unfit for unsupervised clinical deployment, and that human expert oversight is both necessary and the dominant cost driver.

---

### The Dunning-Kruger Effect in Large Language Models: An Empirical Study of Confidence Calibration

Authors: Sudipta Ghosh, Mrityunjoy Panday
Published: 2026-02-12
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2603.09985v1

Large language models (LLMs) have demonstrated remarkable capabilities across diverse tasks, yet their ability to accurately assess their own confidence remains poorly understood. We present an empirical study investigating whether LLMs exhibit patterns reminiscent of the Dunning-Kruger effect -- a cognitive bias where individuals with limited competence tend to overestimate their abilities. We evaluate four state-of-the-art models (Claude Haiku 4.5, Gemini 2.5 Pro, Gemini 2.5 Flash, and Kimi K2) across four benchmark datasets totaling 24,000 experimental trials. Our results reveal striking calibration differences: Kimi K2 exhibits severe overconfidence with an Expected Calibration Error (ECE) of 0.726 despite only 23.3% accuracy, while Claude Haiku 4.5 achieves the best calibration (ECE = 0.122) with 75.4% accuracy. These findings demonstrate that poorly performing models display markedly higher overconfidence -- a pattern analogous to the Dunning-Kruger effect in human cognition. We discuss implications for safe deployment of LLMs in high-stakes applications.

---

### An Efficient Hybrid Deep Learning Approach for Detecting Online Abusive Language

Authors: Vuong M. Ngo, Cach N. Dang, Kien V. Nguyen, Mark Roantree
Published: 2026-02-12
Categories: cs.CL
arXiv: https://arxiv.org/abs/2603.09984v1

The digital age has expanded social media and online forums, allowing free expression for nearly 45% of the global population. Yet, it has also fueled online harassment, bullying, and harmful behaviors like hate speech and toxic comments across social networks, messaging apps, and gaming communities. Studies show 65% of parents notice hostile online behavior, and one-third of adolescents in mobile games experience bullying. A substantial volume of abusive content is generated and shared daily, not only on the surface web but also within dark web forums. Creators of abusive comments often employ specific words or coded phrases to evade detection and conceal their intentions. To address these challenges, we propose a hybrid deep learning model that integrates BERT, CNN, and LSTM architectures with a ReLU activation function to detect abusive language across multiple online platforms, including YouTube comments, online forum discussions, and dark web posts. The model demonstrates strong performance on a diverse and imbalanced dataset containing 77,620 abusive and 272,214 non-abusive text samples (ratio 1:3.5), achieving approximately 99% across evaluation metrics such as Precision, Recall, Accuracy, F1-score, and AUC. This approach effectively captures semantic, contextual, and sequential patterns in text, enabling robust detection of abusive content even in highly skewed datasets, as encountered in real-world scenarios.

---

### MoE-SpAc: Efficient MoE Inference Based on Speculative Activation Utility in Heterogeneous Edge Scenarios

Authors: Shuhuai Li, Jianghao Lin, Dongdong Ge, Yinyu Ye
Published: 2026-02-12
Categories: cs.LG, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2603.09983v1

Mixture-of-Experts (MoE) models enable scalable performance but face severe memory constraints on edge devices. Existing offloading strategies struggle with I/O bottlenecks due to the dynamic, low-information nature of autoregressive expert activation. In this paper, we propose to repurpose Speculative Decoding (SD) not merely as a compute accelerator, but as an informative lookahead sensor for memory management, supported by our theoretical and empirical analyses. Hence, we introduce MoE-SpAc, an MoE inference framework that integrates a Speculative Utility Estimator to track expert demand, a Heterogeneous Workload Balancer to dynamically partition computation via online integer optimization, and an Asynchronous Execution Engine to unify the prefetching and eviction in the same utility space. Extensive experiments on seven benchmarks demonstrate that MoE-SpAc achieves a 42% improvement in TPS over the SOTA SD-based baseline, and an average 4.04x speedup over all standard baselines. Code is available at https://github.com/lshAlgorithm/MoE-SpAc .

---

### ALADIN: Accuracy-Latency-Aware Design-space Inference Analysis for Embedded AI Accelerators

Authors: T. Baldi, D. Casini, A. Biondi
Published: 2026-02-12
Categories: cs.AR, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2603.08722v1

The inference of deep neural networks (DNNs) on resource-constrained embedded systems introduces non-trivial trade-offs among model accuracy, computational latency, and hardware limitations, particularly when real-time constraints must be satisfied. This paper presents ALADIN, an accuracy-latency-aware design-space inference analysis framework for mixed-precision quantized neural networks (QNNs) targeting scratchpad-based AI accelerators. ALADIN enables the evaluation and analysis of inference bottlenecks and design trade-offs across accuracy, latency, and resource consumption without requiring deployment on the target platform, thereby significantly reducing development time and cost. The framework introduces a progressive refinement process that transforms a canonical QONNX model into platform-aware representations by integrating both platform-independent implementation details and hardware-specific characteristics. ALADIN is validated using a cycle-accurate simulator of a RISC-V based platform specialized for AI workloads, demonstrating its effectiveness as a tool for quantitative inference analysis and hardware-software co-design. Experimental results highlight how architectural decisions and mixed-precision quantization strategies impact accuracy, latency, and resource usage, and show that these effects can be precisely evaluated and compared using ALADIN, while also revealing subtle optimization tensions.

---

### The Value Sensitivity Gap: How Clinical Large Language Models Respond to Patient Preference Statements in Shared Decision-Making

Authors: Sanjay Basu
Published: 2026-02-12
Categories: cs.CY, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2603.00076v1

Large language models (LLMs) are entering clinical workflows as decision support tools, yet how they respond to explicit patient value statements -- the core content of shared decision-making -- remains unmeasured. We conducted a factorial experiment using clinical vignettes derived from 98,759 de-identified Medicaid encounter notes. We tested four LLM families (GPT-5.2, Claude 4.5 Sonnet, Gemini 3 Pro, and DeepSeek-R1) across 13 value conditions in two clinical domains, yielding 104 trials. Default value orientations differed across model families (aggressiveness range 2.0 to 3.5 on a 1-to-5 scale). Value sensitivity indices ranged from 0.13 to 0.27, and directional concordance with patient-stated preferences ranged from 0.625 to 1.0. All models acknowledged patient values in 100% of non-control trials, yet actual recommendation shifting remained modest. Decision-matrix and VIM self-report mitigations each improved directional concordance by 0.125 in a 78-trial Phase 2 evaluation. These findings provide empirical data for populating value disclosure labels proposed by clinical AI governance frameworks.

---

### Tensor Network Generator-Enhanced Optimization for Traveling Salesman Problem

Authors: Ryo Sakai, Chen-Yu Liu
Published: 2026-02-12
Categories: cs.LG, math.OC, quant-ph
arXiv: https://arxiv.org/abs/2602.20175v1

We present an application of the tensor network generator-enhanced optimization (TN-GEO) framework to address the traveling salesman problem (TSP), a fundamental combinatorial optimization challenge. Our approach employs a tensor network Born machine based on automatically differentiable matrix product states (MPS) as the generative model, using the Born rule to define probability distributions over candidate solutions. Unlike approaches based on binary encoding, which require $N^2$ variables and penalty terms to enforce valid tour constraints, we adopt a permutation-based formulation with integer variables and use autoregressive sampling with masking to guarantee that every generated sample is a valid tour by construction. We also introduce a $k$-site MPS variant that learns distributions over $k$-grams (consecutive city subsequences) using a sliding window approach, enabling parameter-efficient modeling for larger instances. Experimental validation on TSPLIB benchmark instances with up to 52 cities demonstrates that TN-GEO can outperform classical heuristics including swap and 2-opt hill-climbing. The $k$-site variants, which put more focus on local correlations, show better results compared to the full-MPS case.

---

### Vibe Coding on Trial: Operating Characteristics of Unanimous LLM Juries

Authors: Muhammad Aziz Ullah, Abdul Serwadda
Published: 2026-02-12
Categories: cs.DB, cs.AI, cs.CL, cs.SE
arXiv: https://arxiv.org/abs/2602.18492v2

Large Language Models (LLMs) are now good enough at coding that developers can describe intent in plain language and let the tool produce the first code draft, a workflow increasingly built into tools like GitHub Copilot, Cursor, and Replit. What is missing is a reliable way to tell which model written queries are safe to accept without sending everything to a human. We study the application of an LLM jury to run this review step. We first benchmark 15 open models on 82 MySQL text to SQL tasks using an execution grounded protocol to get a clean baseline of which models are strong. From the six best models we build unanimous committees of sizes 1 through 6 that see the prompt, schema, and candidate SQL and accept it only when every member says it is correct. This rule matches safety first deployments where false accepts are more costly than false rejects. We measure true positive rate, false positive rate and Youden J and we also look at committees per generator. Our results show that single model judges are uneven, that small unanimous committees of strong models can cut false accepts while still passing many good queries, and that the exact committee composition matters significantly.

---

### Vibe Coding on Trial: Operating Characteristics of Unanimous LLM Juries

Authors: Muhammad Aziz Ullah, Abdul Serwadda
Published: 2026-02-12
Categories: cs.DB, cs.AI, cs.CL, cs.SE
arXiv: https://arxiv.org/abs/2602.18492v1

Large Language Models (LLMs) are now good enough at coding that developers can describe intent in plain language and let the tool produce the first code draft, a workflow increasingly built into tools like GitHub Copilot, Cursor, and Replit. What is missing is a reliable way to tell which model written queries are safe to accept without sending everything to a human. We study the application of an LLM jury to run this review step. We first benchmark 15 open models on 82 MySQL text to SQL tasks using an execution grounded protocol to get a clean baseline of which models are strong. From the six best models we build unanimous committees of sizes 1 through 6 that see the prompt, schema, and candidate SQL and accept it only when every member says it is correct. This rule matches safety first deployments where false accepts are more costly than false rejects. We measure true positive rate, false positive rate and Youden J and we also look at committees per generator. Our results show that single model judges are uneven, that small unanimous committees of strong models can cut false accepts while still passing many good queries, and that the exact committee composition matters significantly.

---

### Spectral Homogenization of the Radiative Transfer Equation via Low-Rank Tensor Train Decomposition

Authors: Y. Sungtaek Ju
Published: 2026-02-12
Categories: physics.chem-ph, astro-ph.IM, cs.LG, physics.ao-ph, physics.comp-ph, physics.plasm-ph
arXiv: https://arxiv.org/abs/2602.17708v1

Radiative transfer in absorbing-scattering media requires solving a transport equation across a spectral domain with 10^5 - 10^6 molecular absorption lines. Line-by-line (LBL) computation is prohibitively expensive, while existing approximations sacrifice spectral fidelity. We show that the Young-measure homogenization framework produces solution tensors I that admit low-rank tensor-train (TT) decompositions whose bond dimensions remain bounded as the spectral resolution Ns increases. Using molecular line parameters from the HITRAN database for H2O and CO2, we demonstrate that: (i) the TT rank saturates at r = 8 (at tolerance e = 10^-6) from Ns = 16 to 4096, independent of single-scattering albedo, Henyey-Greenstein asymmetry, temperature, and pressure; (ii) quantized tensor-train (QTT) representations achieve sub-linear storage scaling; (iii) in a controlled comparison using identical opacity data and transport solver, the homogenized approach achieves over an order of magnitude lower L2 error than the correlated-k distribution at equal cost; and (iv) for atomic plasma opacity (aluminum at 60 eV, TOPS database), the TT rank saturates at r = 15 with fundamentally different spectral structure (bound-bound and bound-free transitions spanning 12 decades of dynamic range), confirming that rank boundedness is a property of the transport equation rather than any particular opacity source. These results establish that the spectral complexity of radiative transfer has a finite effective rank exploitable by tensor decomposition, complementing the spatial-angular compression achieved by existing TT and dynamical low-rank approaches.

---

### Reconstructing Carbon Monoxide Reanalysis with Machine Learning

Authors: Paula Harder, Johannes Flemming
Published: 2026-02-12
Categories: physics.ao-ph, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2602.15056v1

The Copernicus Atmospheric Monitoring Service provides reanalysis products for atmospheric composition by combining model simulations with satellite observations. The quality of these products depends strongly on the availability of the observational data, which can vary over time as new satellite instruments become available or are discontinued, such as Carbon Monoxide (CO) observations of the Measurements Of Pollution In The Troposphere (MOPITT) satellite in early 2025. Machine learning offers a promising approach to compensate for such data losses by learning systematic discrepancies between model configurations. In this study, we investigate machine learning methods to predict monthly-mean total column of Carbon Monoxide re-analysis from a control model simulation.

---

### A Formal Framework for the Explanation of Finite Automata Decisions

Authors: Jaime Cuartas Granada, Alexey Ignatiev, Peter J. Stuckey
Published: 2026-02-12
Categories: cs.AI, cs.FL, cs.LO
arXiv: https://arxiv.org/abs/2602.13351v2

Finite automata (FA) are a fundamental computational abstraction that is widely used in practice for various tasks in computer science, linguistics, biology, electrical engineering, and artificial intelligence. Given an input word, an FA maps the word to a result, in the simple case "accept" or "reject", but in general to one of a finite set of results. A question that then arises is: why? Another question is: how can we modify the input word so that it is no longer accepted? One may think that the automaton itself is an adequate explanation of its behaviour, but automata can be very complex and difficult to make sense of directly. In this work, we investigate how to explain the behaviour of an FA on an input word in terms of the word's characters. In particular, we are interested in minimal explanations: what is the minimal set of input characters that explains the result, and what are the minimal changes needed to alter the result? In this paper, we propose an efficient method to determine all minimal explanations for the behaviour of an FA on a particular word. This allows us to give unbiased explanations about which input features are responsible for the result. Experiments show that our approach scales well, even when the underlying problem is challenging.

---

### Detecting Brick Kiln Infrastructure at Scale: Graph, Foundation, and Remote Sensing Models for Satellite Imagery Data

Authors: Usman Nazir, Xidong Chen, Hafiz Muhammad Abubakar, Hadia Abu Bakar, Raahim Arbaz, Fezan Rasool, Bin Chen, Sara Khalid
Published: 2026-02-12
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2602.13350v1

Brick kilns are a major source of air pollution and forced labor in South Asia, yet large-scale monitoring remains limited by sparse and outdated ground data. We study brick kiln detection at scale using high-resolution satellite imagery and curate a multi city zoom-20 (0.149 meters per pixel) resolution dataset comprising over 1.3 million image tiles across five regions in South and Central Asia. We propose ClimateGraph, a region-adaptive graph-based model that captures spatial and directional structure in kiln layouts, and evaluate it against established graph learning baselines. In parallel, we assess a remote sensing based detection pipeline and benchmark it against recent foundation models for satellite imagery. Our results highlight complementary strengths across graph, foundation, and remote sensing approaches, providing practical guidance for scalable brick kiln monitoring from satellite imagery.

---

### From Prompt to Production:Automating Brand-Safe Marketing Imagery with Text-to-Image Models

Authors: Parmida Atighehchian, Henry Wang, Andrei Kapustin, Boris Lerner, Tiancheng Jiang, Taylor Jensen, Negin Sokhandan
Published: 2026-02-12
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2602.13349v1

Text-to-image models have made significant strides, producing impressive results in generating images from textual descriptions. However, creating a scalable pipeline for deploying these models in production remains a challenge. Achieving the right balance between automation and human feedback is critical to maintain both scale and quality. While automation can handle large volumes, human oversight is still an essential component to ensure that the generated images meet the desired standards and are aligned with the creative vision. This paper presents a new pipeline that offers a fully automated, scalable solution for generating marketing images of commercial products using text-to-image models. The proposed system maintains the quality and fidelity of images, while also introducing sufficient creative variation to adhere to marketing guidelines. By streamlining this process, we ensure a seamless blend of efficiency and human oversight, achieving a $30.77\%$ increase in marketing object fidelity using DINOV2 and a $52.00\%$ increase in human preference over the generated outcome.

---

### Exploring the Performance of ML/DL Architectures on the MNIST-1D Dataset

Authors: Michael Beebe, GodsGift Uzor, Manasa Chepuri, Divya Sree Vemula, Angel Ayala
Published: 2026-02-12
Categories: cs.LG, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2602.13348v1

Small datasets like MNIST have historically been instrumental in advancing machine learning research by providing a controlled environment for rapid experimentation and model evaluation. However, their simplicity often limits their utility for distinguishing between advanced neural network architectures. To address these challenges, Greydanus et al. introduced the MNIST-1D dataset, a one-dimensional adaptation of MNIST designed to explore inductive biases in sequential data. This dataset maintains the advantages of small-scale datasets while introducing variability and complexity that make it ideal for studying advanced architectures. In this paper, we extend the exploration of MNIST-1D by evaluating the performance of Residual Networks (ResNet), Temporal Convolutional Networks (TCN), and Dilated Convolutional Neural Networks (DCNN). These models, known for their ability to capture sequential patterns and hierarchical features, were implemented and benchmarked alongside previously tested architectures such as logistic regression, MLPs, CNNs, and GRUs. Our experimental results demonstrate that advanced architectures like TCN and DCNN consistently outperform simpler models, achieving near-human performance on MNIST-1D. ResNet also shows significant improvements, highlighting the importance of leveraging inductive biases and hierarchical feature extraction in small structured datasets. Through this study, we validate the utility of MNIST-1D as a robust benchmark for evaluating machine learning architectures under computational constraints. Our findings emphasize the role of architectural innovations in improving model performance and offer insights into optimizing deep learning models for resource-limited environments.

---

### Visual Foresight for Robotic Stow: A Diffusion-Based World Model from Sparse Snapshots

Authors: Lijun Zhang, Nikhil Chacko, Petter Nilsson, Ruinian Xu, Shantanu Thakar, Bai Lou, Harpreet Sawhney, Zhebin Zhang, Mudit Agrawal, Bhavana Chandrashekhar, Aaron Parness
Published: 2026-02-12
Categories: cs.CV, cs.AI, cs.RO
arXiv: https://arxiv.org/abs/2602.13347v1

Automated warehouses execute millions of stow operations, where robots place objects into storage bins. For these systems it is valuable to anticipate how a bin will look from the current observations and the planned stow behavior before real execution. We propose FOREST, a stow-intent-conditioned world model that represents bin states as item-aligned instance masks and uses a latent diffusion transformer to predict the post-stow configuration from the observed context. Our evaluation shows that FOREST substantially improves the geometric agreement between predicted and true post-stow layouts compared with heuristic baselines. We further evaluate the predicted post-stow layouts in two downstream tasks, in which replacing the real post-stow masks with FOREST predictions causes only modest performance loss in load-quality assessment and multi-stow reasoning, indicating that our model can provide useful foresight signals for warehouse planning.

---

### CellMaster: Collaborative Cell Type Annotation in Single-Cell Analysis

Authors: Zhen Wang, Yiming Gao, Jieyuan Liu, Enze Ma, Jefferson Chen, Mark Antkowiak, Mengzhou Hu, JungHo Kong, Dexter Pratt, Zhiting Hu, Wei Wang, Trey Ideker et al.
Published: 2026-02-12
Categories: q-bio.GN, cs.AI, cs.CV
arXiv: https://arxiv.org/abs/2602.13346v1

Single-cell RNA-seq (scRNA-seq) enables atlas-scale profiling of complex tissues, revealing rare lineages and transient states. Yet, assigning biologically valid cell identities remains a bottleneck because markers are tissue- and state-dependent, and novel states lack references. We present CellMaster, an AI agent that mimics expert practice for zero-shot cell-type annotation. Unlike existing automated tools, CellMaster leverages LLM-encoded knowledge (e.g., GPT-4o) to perform on-the-fly annotation with interpretable rationales, without pre-training or fixed marker databases. Across 9 datasets spanning 8 tissues, CellMaster improved accuracy by 7.1% over best-performing baselines (including CellTypist and scTab) in automatic mode. With human-in-the-loop refinement, this advantage increased to 18.6%, with a 22.1% gain on subtype populations. The system demonstrates particular strength in rare and novel cell states where baselines often fail. Source code and the web application are available at \href{https://github.com/AnonymousGym/CellMaster}{https://github.com/AnonymousGym/CellMaster}.

---

### BLUEPRINT Rebuilding a Legacy: Multimodal Retrieval for Complex Engineering Drawings and Documents

Authors: Ethan Seefried, Ran Eldegaway, Sanjay Das, Nathaniel Blanchard, Tirthankar Ghosal
Published: 2026-02-12
Categories: cs.LG, cs.IR, cs.MA
arXiv: https://arxiv.org/abs/2602.13345v1

Decades of engineering drawings and technical records remain locked in legacy archives with inconsistent or missing metadata, making retrieval difficult and often manual. We present Blueprint, a layout-aware multimodal retrieval system designed for large-scale engineering repositories. Blueprint detects canonical drawing regions, applies region-restricted VLM-based OCR, normalizes identifiers (e.g., DWG, part, facility), and fuses lexical and dense retrieval with a lightweight region-level reranker. Deployed on ~770k unlabeled files, it automatically produces structured metadata suitable for cross-facility search. We evaluate Blueprint on a 5k-file benchmark with 350 expert-curated queries using pooled, graded (0/1/2) relevance judgments. Blueprint delivers a 10.1% absolute gain in Success@3 and an 18.9% relative improvement in nDCG@3 over the strongest vision-language baseline}, consistently outperforming across vision, text, and multimodal intents. Oracle ablations reveal substantial headroom under perfect region detection and OCR. We release all queries, runs, annotations, and code to facilitate reproducible evaluation on legacy engineering archives.

---

### FireRed-Image-Edit-1.0 Technical Report

Authors: Super Intelligence Team, Changhao Qiao, Chao Hui, Chen Li, Cunzheng Wang, Dejia Song, Jiale Zhang, Jing Li, Qiang Xiang, Runqi Wang, Shuang Sun, Wei Zhu et al.
Published: 2026-02-12
Categories: cs.CV, eess.IV
arXiv: https://arxiv.org/abs/2602.13344v2

We present FireRed-Image-Edit, a diffusion transformer for instruction-based image editing that achieves state-of-the-art performance through systematic optimization of data curation, training methodology, and evaluation design. We construct a 1.6B-sample training corpus, comprising 900M text-to-image and 700M image editing pairs from diverse sources. After rigorous cleaning, stratification, auto-labeling, and two-stage filtering, we retain over 100M high-quality samples balanced between generation and editing, ensuring strong semantic coverage and instruction alignment. Our multi-stage training pipeline progressively builds editing capability via pre-training, supervised fine-tuning, and reinforcement learning. To improve data efficiency, we introduce a Multi-Condition Aware Bucket Sampler for variable-resolution batching and Stochastic Instruction Alignment with dynamic prompt re-indexing. To stabilize optimization and enhance controllability, we propose Asymmetric Gradient Optimization for DPO, DiffusionNFT with layout-aware OCR rewards for text editing, and a differentiable Consistency Loss for identity preservation. We further establish REDEdit-Bench, a comprehensive benchmark spanning 15 editing categories, including newly introduced beautification and low-level enhancement tasks. Extensive experiments on REDEdit-Bench and public benchmarks (ImgEdit and GEdit) demonstrate competitive or superior performance against both open-source and proprietary systems. To support future research, our code, models, and benchmark suite are publicly available at https://github.com/FireRedTeam/FireRed-Image-Edit/ .

---

### An Integrated Causal Inference Framework for Traffic Safety Modeling with Semantic Street-View Visual Features

Authors: Lishan Sun, Yujia Cheng, Pengfei Cui, Lei Han, Mohamed Abdel-Aty, Yunhan Zheng, Xingchen Zhang
Published: 2026-02-12
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2602.13339v1

Macroscopic traffic safety modeling aims to identify critical risk factors for regional crashes, thereby informing targeted policy interventions for safety improvement. However, current approaches rely heavily on static sociodemographic and infrastructure metrics, frequently overlooking the impacts from drivers' visual perception of driving environment. Although visual environment features have been found to impact driving and traffic crashes, existing evidence remains largely observational, failing to establish the robust causality for traffic policy evaluation under complex spatial environment. To fill these gaps, we applied semantic segmentation on Google Street View imageries to extract visual environmental features and proposed a Double Machine Learning framework to quantify their causal effects on regional crashes. Meanwhile, we utilized SHAP values to characterize the nonlinear influence mechanisms of confounding variables in the models and applied causal forests to estimate conditional average treatment effects. Leveraging crash records from the Miami metropolitan area, Florida, and 220,000 street view images, evidence shows that greenery proportion exerts a significant and robust negative causal effect on traffic crashes (Average Treatment Effect = -6.38, p = 0.005). This protective effect exhibits spatial heterogeneity, being most pronounced in densely populated and socially vulnerable urban cores. While greenery significantly mitigates angle and rear-end crashes, its protective benefit for vulnerable road users (VRUs) remains limited. Our findings provide causal evidence for greening as a potential safety intervention, prioritizing hazardous visual environments while highlighting the need for distinct design optimizations to protect VRUs.

---

### Curriculum Learning and Pseudo-Labeling Improve the Generalization of Multi-Label Arabic Dialect Identification Models

Authors: Ali Mekky, Mohamed El Zeftawy, Lara Hassan, Amr Keleg, Preslav Nakov
Published: 2026-02-12
Categories: cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2602.12937v2

Being modeled as a single-label classification task for a long time, recent work has argued that Arabic Dialect Identification (ADI) should be framed as a multi-label classification task. However, ADI remains constrained by the availability of single-label datasets, with no large-scale multi-label resources available for training. By analyzing models trained on single-label ADI data, we show that the main difficulty in repurposing such datasets for Multi-Label Arabic Dialect Identification (MLADI) lies in the selection of negative samples, as many sentences treated as negative could be acceptable in multiple dialects. To address these issues, we construct a multi-label dataset by generating automatic multi-label annotations using GPT-4o and binary dialect acceptability classifiers, with aggregation guided by the Arabic Level of Dialectness (ALDi). Afterward, we train a BERT-based multi-label classifier using curriculum learning strategies aligned with dialectal complexity and label cardinality. On the MLADI leaderboard, our best-performing LAHJATBERT model achieves a macro F1 of 0.69, compared to 0.55 for the strongest previously reported system. Code and data are available at https://mohamedalaa9.github.io/lahjatbert/.

---

### Human-Like Coarse Object Representations in Vision Models

Authors: Andrey Gizdov, Andrea Procopio, Yichen Li, Daniel Harari, Tomer Ullman
Published: 2026-02-12
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2602.12486v1

Humans appear to represent objects for intuitive physics with coarse, volumetric bodies'' that smooth concavities - trading fine visual details for efficient physical predictions - yet their internal structure is largely unknown. Segmentation models, in contrast, optimize pixel-accurate masks that may misalign with such bodies. We ask whether and when these models nonetheless acquire human-like bodies. Using a time-to-collision (TTC) behavioral paradigm, we introduce a comparison pipeline and alignment metric, then vary model training time, size, and effective capacity via pruning. Across all manipulations, alignment with human behavior follows an inverse U-shaped curve: small/briefly trained/pruned models under-segment into blobs; large/fully trained models over-segment with boundary wiggles; and an intermediate ideal body granularity'' best matches humans. This suggests human-like coarse bodies emerge from resource constraints rather than bespoke biases, and points to simple knobs - early checkpoints, modest architectures, light pruning - for eliciting physics-efficient representations. We situate these results within resource-rational accounts balancing recognition detail against physical affordances.

---

### A Lightweight and Explainable DenseNet-121 Framework for Grape Leaf Disease Classification

Authors: Md. Ehsanul Haque, Md. Saymon Hosen Polash, Rakib Hasan Ovi, Aminul Kader Bulbul, Md Kamrul Siam, Tamim Hasan Saykat
Published: 2026-02-12
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2602.12484v1

Grapes are among the most economically and culturally significant fruits on a global scale, and table grapes and wine are produced in significant quantities in Europe and Asia. The production and quality of grapes are significantly impacted by grape diseases such as Bacterial Rot, Downy Mildew, and Powdery Mildew. Consequently, the sustainable management of a vineyard necessitates the early and precise identification of these diseases. Current automated methods, particularly those that are based on the YOLO framework, are often computationally costly and lack interpretability that makes them unsuitable for real-world scenarios. This study proposes grape leaf disease classification using Optimized DenseNet 121. Domain-specific preprocessing and extensive connectivity reveal disease-relevant characteristics, including veins, edges, and lesions. An extensive comparison with baseline CNN models, including ResNet18, VGG16, AlexNet, and SqueezeNet, demonstrates that the proposed model exhibits superior performance. It achieves an accuracy of 99.27%, an F1 score of 99.28%, a specificity of 99.71%, and a Kappa of 98.86%, with an inference time of 9 seconds. The cross-validation findings show a mean accuracy of 99.12%, indicating strength and generalizability across all classes. We also employ Grad-CAM to highlight disease-related regions to guarantee the model is highlighting physiologically relevant aspects and increase transparency and confidence. Model optimization reduces processing requirements for real-time deployment, while transfer learning ensures consistency on smaller and unbalanced samples. An effective architecture, domain-specific preprocessing, and interpretable outputs make the proposed framework scalable, precise, and computationally inexpensive for detecting grape leaf diseases.

---

### Geometric separation and constructive universal approximation with two hidden layers

Authors: Chanyoung Sung
Published: 2026-02-12
Categories: cs.LG, math.CA
arXiv: https://arxiv.org/abs/2602.12482v1

We give a geometric construction of neural networks that separate disjoint compact subsets of $\Bbb R^n$, and use it to obtain a constructive universal approximation theorem. Specifically, we show that networks with two hidden layers and either a sigmoidal activation (i.e., strictly monotone bounded continuous) or the ReLU activation can approximate any real-valued continuous function on an arbitrary compact set $K\subset\Bbb R^n$ to any prescribed accuracy in the uniform norm. For finite $K$, the construction simplifies and yields a sharp depth-2 (single hidden layer) approximation result.

---

### Task- and Metric-Specific Signal Quality Indices for Medical Time Series

Authors: Jad Haidamous, Christoph Hoog Antink
Published: 2026-02-12
Categories: eess.SP, cs.LG
arXiv: https://arxiv.org/abs/2602.12478v1

Medical time series such as electrocardiograms (ECGs) and photoplethysmograms (PPGs) are frequently affected by measurement artifacts due to challenging acquisition environments, such as in ambulances and during routine daily activities. Since automated algorithms for analyzing such signals increasingly inform clinically relevant decisions, identifying signal segments on which these algorithms may produce unreliable outputs is of critical importance. Signal quality indices (SQIs) are commonly used for this purpose. However, most existing SQIs are task agnostic and do not account for the specific algorithm and performance metric used downstream. In this work, we formalize signal quality as a task- and metric-dependent concept and propose a perturbation-based SQI (pSQI) that aims to detect an algorithm's performance degradation on an input signal with respect to a metric. The pSQI is defined as the worst-case value of the performance metric under an additive, colored Gaussian noise perturbation with a lower-bounded signal-to-noise ratio. We introduce formal requirements for task- and metric-specific SQIs, including monotonicity of the metric in expectation and maximal separation under thresholding. Experiments on R-peak detection and atrial fibrillation classification benchmarks demonstrate that the proposed pSQI consistently outperforms existing feature- and deep learning-based SQIs in identifying unreliable inputs without requiring training.

---

### Not a Silver Bullet for Loneliness: How Attachment and Age Shape Intimacy with AI Companions

Authors: Raffaele Ciriello, Uri Gal, Ofir Turel
Published: 2026-02-12
Categories: cs.CY, cs.AI, cs.HC
arXiv: https://arxiv.org/abs/2602.12476v1

Artificial intelligence (AI) companions are increasingly promoted as solutions for loneliness, often overlooking how personal dispositions and life-stage conditions shape artificial intimacy. Because intimacy is a primary coping mechanism for loneliness that varies by attachment style and age, we examine how different types of users form intimate relationships with AI companions in response to loneliness. Drawing on a hermeneutic literature review and a survey of 277 active AI companion users, we develop and test a model in which loneliness predicts intimacy, moderated by attachment insecurity and conditioned by age. Although the cross-sectional data limits causal inference, the results reveal a differentiated pattern. Loneliness is paradoxically associated with reduced intimacy for securely attached users but with increased intimacy for avoidant and ambivalent users, while anxious users show mixed effects. Older adults report higher intimacy even at lower loneliness levels. These findings challenge portrayals of AI companions as universal remedies for loneliness. Instead, artificial intimacy emerges as a sociotechnical process shaped by psychological dispositions and demographic conditions. The study clarifies who is most likely to form intimate relationships with AI companions and highlights ethical risks in commercial models that may capitalise on user vulnerability.

---

### Tight Bounds for Logistic Regression with Large Stepsize Gradient Descent in Low Dimension

Authors: Michael Crawshaw, Mingrui Liu
Published: 2026-02-12
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.12471v2

We consider the optimization problem of minimizing the logistic loss with gradient descent to train a linear model for binary classification with separable data. With a budget of $T$ iterations, it was recently shown that an accelerated $1/T^2$ rate is possible by choosing a large stepsize $η= Θ(γ^2 T)$ (where $γ$ is the dataset's margin) despite the resulting non-monotonicity of the loss. In this paper, we provide a tighter analysis of gradient descent for this problem when the data is two-dimensional: we show that GD with a sufficiently large learning rate $η$ finds a point with loss smaller than $\mathcal{O}(1/(ηγ^2 T))$, as long as $T \geq Ω(n/γ+ 1/γ^2)$, where $n$ is the dataset size. Our improved rate comes from a tighter bound on the time $τ$ that it takes for GD to transition from unstable (non-monotonic loss) to stable (monotonic loss), via a fine-grained analysis of the oscillatory dynamics of GD in the subspace orthogonal to the max-margin classifier. We also provide a lower bound of $τ$ matching our upper bound up to logarithmic factors, showing that our analysis is tight.

---

### Designing RNAs with Language Models

Authors: Milan Gautam, Ning Dai, Tianshuo Zhou, Bowen Xie, David Mathews, Liang Huang
Published: 2026-02-12
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2602.12470v1

RNA design, the task of finding a sequence that folds into a target secondary structure, has broad biological and biomedical impact but remains computationally challenging due to the exponentially large sequence space and exponentially many competing folds. Traditional approaches treat it as an optimization problem, relying on per-instance heuristics or constraint-based search. We instead reframe RNA design as conditional sequence generation and introduce a reusable neural approximator, instantiated as an autoregressive language model (LM), that maps target structures directly to sequences. We first train our model in a supervised setting on random-induced structure-sequence pairs, and then use reinforcement learning (RL) to optimize end-to-end metrics. We also propose methods to select a small subset for RL that greatly improves RL efficiency and quality. Across four datasets, our approach outperforms state-of-the-art systems on key metrics such as Boltzmann probability while being 1.7x faster, establishing conditional LM generation as a scalable, task-agnostic alternative to per-instance optimization for RNA design. Our code and data are available at https://github.com/KuNyaa/RNA-Design-LM.

---

### Regularized Meta-Learning for Improved Generalization

Authors: Noor Islam S. Mohammad, Md Muntaqim Meherab
Published: 2026-02-12
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.12469v2

Deep ensemble methods often improve predictive performance, yet they suffer from three practical limitations: redundancy among base models that inflates computational cost and degrades conditioning, unstable weighting under multicollinearity, and overfitting in meta-learning pipelines. We propose a regularized meta-learning framework that addresses these challenges through a four-stage pipeline combining redundancy-aware projection, statistical meta-feature augmentation, and cross-validated regularized meta-models (Ridge, Lasso, and ElasticNet). Our multi-metric de-duplication strategy removes near-collinear predictors using correlation and MSE thresholds ($τ_{\text{corr}}=0.95$), reducing the effective condition number of the meta-design matrix while preserving predictive diversity. Engineered ensemble statistics and interaction terms recover higher-order structure unavailable to raw prediction columns. A final inverse-RMSE blending stage mitigates regularizer-selection variance. On the Playground Series S6E1 benchmark (100K samples, 72 base models), the proposed framework achieves an out-of-fold RMSE of 8.582, improving over simple averaging (8.894) and conventional Ridge stacking (8.627), while matching greedy hill climbing (8.603) with substantially lower runtime (4 times faster). Conditioning analysis shows a 53.7\% reduction in effective matrix condition number after redundancy projection. Comprehensive ablations demonstrate consistent contributions from de-duplication, statistical meta-features, and meta-ensemble blending. These results position regularized meta-learning as a stable and deployment-efficient stacking strategy for high-dimensional ensemble systems.

---