# Research Papers — 2026-02 · bundle page 36 of 210

> Full-text markdown of papers #1751–1800 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/36
[← Previous bundle](https://aipod.dev/papers/archive/2026-02/page/35.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-02/page/37.md)

### LST-SLAM: A Stereo Thermal SLAM System for Kilometer-Scale Dynamic Environments

Authors: Zeyu Jiang, Kuan Xu, Changhao Chen
Published: 2026-02-24
Categories: cs.RO, cs.CV
arXiv: https://arxiv.org/abs/2602.20925v1

Thermal cameras offer strong potential for robot perception under challenging illumination and weather conditions. However, thermal Simultaneous Localization and Mapping (SLAM) remains difficult due to unreliable feature extraction, unstable motion tracking, and inconsistent global pose and map construction, particularly in dynamic large-scale outdoor environments. To address these challenges, we propose LST-SLAM, a novel large-scale stereo thermal SLAM system that achieves robust performance in complex, dynamic scenes. Our approach combines self-supervised thermal feature learning, stereo dual-level motion tracking, and geometric pose optimization. We also introduce a semantic-geometric hybrid constraint that suppresses potentially dynamic features lacking strong inter-frame geometric consistency. Furthermore, we develop an online incremental bag-of-words model for loop closure detection, coupled with global pose optimization to mitigate accumulated drift. Extensive experiments on kilometer-scale dynamic thermal datasets show that LST-SLAM significantly outperforms recent representative SLAM systems, including AirSLAM and DROID-SLAM, in both robustness and accuracy.

---

### Airavat: An Agentic Framework for Internet Measurement

Authors: Alagappan Ramanathan, Eunju Kang, Dongsu Han, Sangeetha Abdu Jyothi
Published: 2026-02-24
Categories: cs.NI, cs.AI, cs.SE
arXiv: https://arxiv.org/abs/2602.20924v1

Internet measurement faces twin challenges: complex analyses require expert-level orchestration of tools, yet even syntactically correct implementations can have methodological flaws and can be difficult to verify. Democratizing measurement capabilities thus demands automating both workflow generation and verification against methodological standards established through decades of research. We present Airavat, the first agentic framework for Internet measurement workflow generation with systematic verification and validation. Airavat coordinates a set of agents mirroring expert reasoning: three agents handle problem decomposition, solution design, and code implementation, with assistance from a registry of existing tools. Two specialized engines ensure methodological correctness: a Verification Engine evaluates workflows against a knowledge graph encoding five decades of measurement research, while a Validation Engine identifies appropriate validation techniques grounded in established methodologies. Through four Internet measurement case studies, we demonstrate that Airavat (i) generates workflows matching expert-level solutions, (ii) makes sound architectural decisions, (iii) addresses novel problems without ground truth, and (iv) identifies methodological flaws missed by standard execution-based testing.

---

### On the Generalization Behavior of Deep Residual Networks From a Dynamical System Perspective

Authors: Jinshu Huang, Mingfei Sun, Chunlin Wu
Published: 2026-02-24
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.20921v1

Deep neural networks (DNNs) have significantly advanced machine learning, with model depth playing a central role in their successes. The dynamical system modeling approach has recently emerged as a powerful framework, offering new mathematical insights into the structure and learning behavior of DNNs. In this work, we establish generalization error bounds for both discrete- and continuous-time residual networks (ResNets) by combining Rademacher complexity, flow maps of dynamical systems, and the convergence behavior of ResNets in the deep-layer limit. The resulting bounds are of order $O(1/\sqrt{S})$ with respect to the number of training samples $S$, and include a structure-dependent negative term, yielding depth-uniform and asymptotic generalization bounds under milder assumptions. These findings provide a unified understanding of generalization across both discrete- and continuous-time ResNets, helping to close the gap in both the order of sample complexity and assumptions between the discrete- and continuous-time settings.

---

### Predicting Sentence Acceptability Judgments in Multimodal Contexts

Authors: Hyewon Jang, Nikolai Ilinykh, Sharid Loáiciga, Jey Han Lau, Shalom Lappin
Published: 2026-02-24
Categories: cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2602.20918v1

Previous work has examined the capacity of deep neural networks (DNNs), particularly transformers, to predict human sentence acceptability judgments, both independently of context, and in document contexts. We consider the effect of prior exposure to visual images (i.e., visual context) on these judgments for humans and large language models (LLMs). Our results suggest that, in contrast to textual context, visual images appear to have little if any impact on human acceptability ratings. However, LLMs display the compression effect seen in previous work on human judgments in document contexts. Different sorts of LLMs are able to predict human acceptability judgments to a high degree of accuracy, but in general, their performance is slightly better when visual contexts are removed. Moreover, the distribution of LLM judgments varies among models, with Qwen resembling human patterns, and others diverging from them. LLM-generated predictions on sentence acceptability are highly correlated with their normalised log probabilities in general. However, the correlations decrease when visual contexts are present, suggesting that a higher gap exists between the internal representations of LLMs and their generated predictions in the presence of visual contexts. Our experimental work suggests interesting points of similarity and of difference between human and LLM processing of sentences in multimodal contexts.

---

### LongVideo-R1: Smart Navigation for Low-cost Long Video Understanding

Authors: Jihao Qiu, Lingxi Xie, Xinyue Huo, Qi Tian, Qixiang Ye
Published: 2026-02-24
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.20913v2

This paper addresses the critical and underexplored challenge of long video understanding with low computational budgets. We propose LongVideo-R1, an active, reasoning-equipped multimodal large language model (MLLM) agent designed for efficient video context navigation, avoiding the redundancy of exhaustive search. At the core of LongVideo-R1 lies a reasoning module that leverages high-level visual cues to infer the most informative video clip for subsequent processing. During inference, the agent initiates traversal from top-level visual summaries and iteratively refines its focus, immediately halting the exploration process upon acquiring sufficient knowledge to answer the query. To facilitate training, we first extract hierarchical video captions from CGBench, a video corpus with grounding annotations, and guide GPT-5 to generate 33K high-quality chain-of-thought-with-tool trajectories. The LongVideo-R1 agent is fine-tuned upon the Qwen-3-8B model through a two-stage paradigm: supervised fine-tuning (SFT) followed by reinforcement learning (RL), where RL employs a specifically designed reward function to maximize selective and efficient clip navigation. Experiments on multiple long video benchmarks validate the effectiveness of name, which enjoys superior tradeoff between QA accuracy and efficiency. All curated data and source code are provided in the supplementary material and will be made publicly available. Code and data are available at: https://github.com/qiujihao19/LongVideo-R1

---

### From Isolation to Integration: Building an Adaptive Expert Forest for Pre-Trained Model-based Class-Incremental Learning

Authors: Ruiqi Liu, Boyu Diao, Hangda Liu, Zhulin An, Fei Wang, Yongjun Xu
Published: 2026-02-24
Categories: cs.LG, cs.CV
arXiv: https://arxiv.org/abs/2602.20911v1

Class-Incremental Learning (CIL) requires models to learn new classes without forgetting old ones. A common method is to freeze a pre-trained model and train a new, lightweight adapter for each task. While this prevents forgetting, it treats the learned knowledge as a simple, unstructured collection and fails to use the relationships between tasks. To this end, we propose the Semantic-guided Adaptive Expert Forest (SAEF), a new method that organizes adapters into a structured hierarchy for better knowledge sharing. SAEF first groups tasks into conceptual clusters based on their semantic relationships. Then, within each cluster, it builds a balanced expert tree by creating new adapters from merging the adapters of similar tasks. At inference time, SAEF finds and activates a set of relevant experts from the forest for any given input. The final prediction is made by combining the outputs of these activated experts, weighted by how confident each expert is. Experiments on several benchmark datasets show that SAEF achieves SOTA performance.

---

### Transcoder Adapters for Reasoning-Model Diffing

Authors: Nathan Hu, Jake Ward, Thomas Icard, Christopher Potts
Published: 2026-02-24
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.20904v1

While reasoning models are increasingly ubiquitous, the effects of reasoning training on a model's internal mechanisms remain poorly understood. In this work, we introduce transcoder adapters, a technique for learning an interpretable approximation of the difference in MLP computation before and after fine-tuning. We apply transcoder adapters to characterize the differences between Qwen2.5-Math-7B and its reasoning-distilled variant, DeepSeek-R1-Distill-Qwen-7B. Learned adapters are faithful to the target model's internal computation and next-token predictions. When evaluated on reasoning benchmarks, adapters match the reasoning model's response lengths and typically recover 50-90% of the accuracy gains from reasoning fine-tuning. Adapter features are sparsely activating and interpretable. When examining adapter features, we find that only ~8% have activating examples directly related to reasoning behaviors. We deeply study one such behavior -- the production of hesitation tokens (e.g., "wait"). Using attribution graphs, we trace hesitation to only ~2.4% of adapter features (5.6k total) performing one of two functions. These features are necessary and sufficient for producing hesitation tokens; removing them reduces response length, often without affecting accuracy. Overall, our results provide insight into reasoning training and suggest transcoder adapters may be useful for studying fine-tuning more broadly.

---

### TextPecker: Rewarding Structural Anomaly Quantification for Enhancing Visual Text Rendering

Authors: Hanshen Zhu, Yuliang Liu, Xuecheng Wu, An-Lan Wang, Hao Feng, Dingkang Yang, Chao Feng, Can Huang, Jingqun Tang, Xiang Bai
Published: 2026-02-24
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.20903v3

Visual Text Rendering (VTR) remains a critical challenge in text-to-image generation, where even advanced models frequently produce text with structural anomalies such as distortion, blurriness, and misalignment. However, we find that leading MLLMs and specialist OCR models largely fail to perceive these structural anomalies, creating a critical bottleneck for both VTR evaluation and RL-based optimization. As a result, even state-of-the-art generators (e.g., Seedream4.0, Qwen-Image) still struggle to render structurally faithful text. To address this, we propose TextPecker, a plug-and-play structural anomaly perceptive RL strategy that mitigates noisy reward signals and works with any textto-image generator. To enable this capability, we construct a recognition dataset with character-level structural-anomaly annotations and develop a stroke-editing synthesis engine to expand structural-error coverage. Experiments show that TextPecker consistently improves diverse text-to-image models; even on the well-optimized Qwen-Image, it significantly yields average gains of 4% in structural fidelity and 8.7% in semantic alignment for Chinese text rendering, establishing a new state-of-the-art in high-fidelity VTR. Our work fills a gap in VTR optimization, providing a foundational step towards reliable and structural faithful visual text generation.

---

### SpatiaLQA: A Benchmark for Evaluating Spatial Logical Reasoning in Vision-Language Models

Authors: Yuechen Xie, Xiaoyan Zhang, Yicheng Shan, Hao Zhu, Rui Tang, Rong Wei, Mingli Song, Yuanyu Wan, Jie Song
Published: 2026-02-24
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2602.20901v1

Vision-Language Models (VLMs) have been increasingly applied in real-world scenarios due to their outstanding understanding and reasoning capabilities. Although VLMs have already demonstrated impressive capabilities in common visual question answering and logical reasoning, they still lack the ability to make reasonable decisions in complex real-world environments. We define this ability as spatial logical reasoning, which not only requires understanding the spatial relationships among objects in complex scenes, but also the logical dependencies between steps in multi-step tasks. To bridge this gap, we introduce Spatial Logical Question Answering (SpatiaLQA), a benchmark designed to evaluate the spatial logical reasoning capabilities of VLMs. SpatiaLQA consists of 9,605 question answer pairs derived from 241 real-world indoor scenes. We conduct extensive experiments on 41 mainstream VLMs, and the results show that even the most advanced models still struggle with spatial logical reasoning. To address this issue, we propose a method called recursive scene graph assisted reasoning, which leverages visual foundation models to progressively decompose complex scenes into task-relevant scene graphs, thereby enhancing the spatial logical reasoning ability of VLMs, outperforming all previous methods. Code and dataset are available at https://github.com/xieyc99/SpatiaLQA.

---

### Exa-PSD: a new Persian sentiment analysis dataset on Twitter

Authors: Seyed Himan Ghaderi, Saeed Sarbazi Azad, Mohammad Mehdi Jaziriyan, Ahmad Akbari
Published: 2026-02-24
Categories: cs.CL
arXiv: https://arxiv.org/abs/2602.20892v1

Today, Social networks such as Twitter are the most widely used platforms for communication of people. Analyzing this data has useful information to recognize the opinion of people in tweets. Sentiment analysis plays a vital role in NLP, which identifies the opinion of the individuals about a specific topic. Natural language processing in Persian has many challenges despite the adventure of strong language models. The datasets available in Persian are generally in special topics such as products, foods, hotels, etc while users may use ironies, colloquial phrases in social media To overcome these challenges, there is a necessity for having a dataset of Persian sentiment analysis on Twitter. In this paper, we introduce the Exa sentiment analysis Persian dataset, which is collected from Persian tweets. This dataset contains 12,000 tweets, annotated by 5 native Persian taggers. The aforementioned data is labeled in 3 classes: positive, neutral and negative. We present the characteristics and statistics of this dataset and use the pre-trained Pars Bert and Roberta as the base model to evaluate this dataset. Our evaluation reached a 79.87 Macro F-score, which shows the model and data can be adequately valuable for a sentiment analysis system.

---

### When Safety Collides: Resolving Multi-Category Harmful Conflicts in Text-to-Image Diffusion via Adaptive Safety Guidance

Authors: Yongli Xiang, Ziming Hong, Zhaoqing Wang, Xiangyu Zhao, Bo Han, Tongliang Liu
Published: 2026-02-24
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.20880v4

Text-to-Image (T2I) diffusion models have demonstrated significant advancements in generating high-quality images, while raising potential safety concerns regarding harmful content generation. Safety-guidance-based methods have been proposed to mitigate harmful outputs by steering generation away from harmful zones, where the zones are averaged across multiple harmful categories based on predefined keywords. However, these approaches fail to capture the complex interplay among different harm categories, leading to "harmful conflicts" where mitigating one type of harm may inadvertently amplify another, thus increasing overall harmful rate. To address this issue, we propose Conflict-aware Adaptive Safety Guidance (CASG), a training-free framework that dynamically identifies and applies the category-aligned safety direction during generation. CASG is composed of two components: (i) Conflict-aware Category Identification (CaCI), which identifies the harmful category most aligned with the model's evolving generative state, and (ii) Conflict-resolving Guidance Application (CrGA), which applies safety steering solely along the identified category to avoid multi-category interference. CASG can be applied to both latent-space and text-space safeguards. Experiments on T2I safety benchmarks demonstrate CASG's state-of-the-art performance, reducing the harmful rate by up to 15.4% compared to existing methods.

---

### Diagnosing Causal Reasoning in Vision-Language Models via Structured Relevance Graphs

Authors: Dhita Putri Pratama, Soyeon Caren Han, Yihao Ding
Published: 2026-02-24
Categories: cs.AI
arXiv: https://arxiv.org/abs/2602.20878v1

Large Vision-Language Models (LVLMs) achieve strong performance on visual question answering benchmarks, yet often rely on spurious correlations rather than genuine causal reasoning. Existing evaluations primarily assess the correctness of the answers, making it unclear whether failures arise from limited reasoning capability or from misidentifying causally relevant information. We introduce Vision-Language Causal Graphs (VLCGs), a structured, query-conditioned representation that explicitly encodes causally relevant objects, attributes, relations, and scene-grounded assumptions. Building on this representation, we present ViLCaR, a diagnostic benchmark comprising tasks for Causal Attribution, Causal Inference, and Question Answering, along with graph-aligned evaluation metrics that assess relevance identification beyond final answer accuracy. Experiments in state-of-the-art LVLMs show that injecting structured relevance information significantly improves attribution and inference consistency compared to zero-shot and standard in-context learning. These findings suggest that current limitations in LVLM causal reasoning stem primarily from insufficient structural guidance rather than a lack of reasoning capacity.

---

### E-MMKGR: A Unified Multimodal Knowledge Graph Framework for E-commerce Applications

Authors: Jiwoo Kang, Yeon-Chang Lee
Published: 2026-02-24
Categories: cs.IR, cs.AI
arXiv: https://arxiv.org/abs/2602.20877v1

Multimodal recommender systems (MMRSs) enhance collaborative filtering by leveraging item-side modalities, but their reliance on a fixed set of modalities and task-specific objectives limits both modality extensibility and task generalization. We propose E-MMKGR, a framework that constructs an e-commerce-specific Multimodal Knowledge Graph E-MMKG and learns unified item representations through GNN-based propagation and KG-oriented optimization. These representations provide a shared semantic foundation applicable to diverse tasks. Experiments on real-world Amazon datasets show improvements of up to 10.18% in Recall@10 for recommendation and up to 21.72% over vector-based retrieval for product search, demonstrating the effectiveness and extensibility of our approach.

---

### Efficient Online Learning in Interacting Particle Systems

Authors: Louis Sharrock, Nikolas Kantas, Grigorios A. Pavliotis
Published: 2026-02-24
Categories: math.ST, math.OC, math.PR, stat.ME, stat.ML
arXiv: https://arxiv.org/abs/2602.20875v1

We introduce a new method for online parameter estimation in stochastic interacting particle systems, based on continuous observation of a small number of particles from the system. Our method recursively updates the model parameters using a stochastic approximation of the gradient of the asymptotic log likelihood, which is computed using the continuous stream of observations. Under suitable assumptions, we rigorously establish convergence of our method to the stationary points of the asymptotic log-likelihood of the interacting particle system. We consider asymptotics both in the limit as the time horizon $t\rightarrow\infty$, for a fixed and finite number of particles, and in the joint limit as the number of particles $N\rightarrow\infty$ and the time horizon $t\rightarrow\infty$. Under additional assumptions on the asymptotic log-likelihood, we also establish an $\mathrm{L}^2$ convergence rate and a central limit theorem. Finally, we present several numerical examples of practical interest, including a model for systemic risk, a model of interacting FitzHugh--Nagumo neurons, and a Cucker--Smale flocking model. Our numerical results corroborate our theoretical results, and also suggest that our estimator is effective even in cases where the assumptions required for our theoretical analysis do not hold.

---

### MUSE: Harnessing Precise and Diverse Semantics for Few-Shot Whole Slide Image Classification

Authors: Jiahao Xu, Sheng Huang, Xin Zhang, Zhixiong Nan, Jiajun Dong, Nankun Mu
Published: 2026-02-24
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.20873v1

In computational pathology, few-shot whole slide image classification is primarily driven by the extreme scarcity of expert-labeled slides. Recent vision-language methods incorporate textual semantics generated by large language models, but treat these descriptions as static class-level priors that are shared across all samples and lack sample-wise refinement. This limits both the diversity and precision of visual-semantic alignment, hindering generalization under limited supervision. To overcome this, we propose the stochastic MUlti-view Semantic Enhancement (MUSE), a framework that first refines semantic precision via sample-wise adaptation and then enhances semantic richness through retrieval-augmented multi-view generation. Specifically, MUSE introduces Sample-wise Fine-grained Semantic Enhancement (SFSE), which yields a fine-grained semantic prior for each sample through MoE-based adaptive visual-semantic interaction. Guided by this prior, Stochastic Multi-view Model Optimization (SMMO) constructs an LLM-generated knowledge base of diverse pathological descriptions per class, then retrieves and stochastically integrates multiple matched textual views during training. These dynamically selected texts serve as enriched semantic supervisions to stochastically optimize the vision-language model, promoting robustness and mitigating overfitting. Experiments on three benchmark WSI datasets show that MUSE consistently outperforms existing vision-language baselines in few-shot settings, demonstrating that effective few-shot pathology learning requires not only richer semantic sources but also their active and sample-aware semantic optimization. Our code is available at: https://github.com/JiahaoXu-god/CVPR2026_MUSE.

---

### SoK: Agentic Skills -- Beyond Tool Use in LLM Agents

Authors: Yanna Jiang, Delong Li, Haiyu Deng, Baihe Ma, Xu Wang, Qin Wang, Guangsheng Yu
Published: 2026-02-24
Categories: cs.CR, cs.AI, cs.CE, cs.ET
arXiv: https://arxiv.org/abs/2602.20867v1

Agentic systems increasingly rely on reusable procedural capabilities, \textit{a.k.a., agentic skills}, to execute long-horizon workflows reliably. These capabilities are callable modules that package procedural knowledge with explicit applicability conditions, execution policies, termination criteria, and reusable interfaces. Unlike one-off plans or atomic tool calls, skills operate (and often do well) across tasks. This paper maps the skill layer across the full lifecycle (discovery, practice, distillation, storage, composition, evaluation, and update) and introduces two complementary taxonomies. The first is a system-level set of \textbf{seven design patterns} capturing how skills are packaged and executed in practice, from metadata-driven progressive disclosure and executable code skills to self-evolving libraries and marketplace distribution. The second is an orthogonal \textbf{representation $\times$ scope} taxonomy describing what skills \emph{are} (natural language, code, policy, hybrid) and what environments they operate over (web, OS, software engineering, robotics). We analyze the security and governance implications of skill-based agents, covering supply-chain risks, prompt injection via skill payloads, and trust-tiered execution, grounded by a case study of the ClawHavoc campaign in which nearly 1{,}200 malicious skills infiltrated a major agent marketplace, exfiltrating API keys, cryptocurrency wallets, and browser credentials at scale. We further survey deterministic evaluation approaches, anchored by recent benchmark evidence that curated skills can substantially improve agent success rates while self-generated skills may degrade them. We conclude with open challenges toward robust, verifiable, and certifiable skills for real-world autonomous agents.

---

### DA-Cal: Towards Cross-Domain Calibration in Semantic Segmentation

Authors: Wangkai Li, Rui Sun, Zhaoyang Li, Yujia Chen, Tianzhu Zhang
Published: 2026-02-24
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.20860v2

While existing unsupervised domain adaptation (UDA) methods greatly enhance target domain performance in semantic segmentation, they often neglect network calibration quality, resulting in misalignment between prediction confidence and actual accuracy---a significant risk in safety-critical applications. Our key insight emerges from observing that performance degrades substantially when soft pseudo-labels replace hard pseudo-labels in cross-domain scenarios due to poor calibration, despite the theoretical equivalence of perfectly calibrated soft pseudo-labels to hard pseudo-labels. Based on this finding, we propose DA-Cal, a dedicated cross-domain calibration framework that transforms target domain calibration into soft pseudo-label optimization. DA-Cal introduces a Meta Temperature Network to generate pixel-level calibration parameters and employs bi-level optimization to establish the relationship between soft pseudo-labels and UDA supervision, while utilizing complementary domain-mixing strategies to prevent overfitting and reduce domain discrepancies. Experiments demonstrate that DA-Cal seamlessly integrates with existing self-training frameworks across multiple UDA segmentation benchmarks, significantly improving target domain calibration while delivering performance gains without inference overhead.

---

### DA-Cal: Towards Cross-Domain Calibration in Semantic Segmentation

Authors: Wangkai Li, Rui Sun, Zhaoyang Li, Yujia Chen, Tianzhu Zhang
Published: 2026-02-24
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.20860v1

While existing unsupervised domain adaptation (UDA) methods greatly enhance target domain performance in semantic segmentation, they often neglect network calibration quality, resulting in misalignment between prediction confidence and actual accuracy -- a significant risk in safety-critical applications. Our key insight emerges from observing that performance degrades substantially when soft pseudo-labels replace hard pseudo-labels in cross-domain scenarios due to poor calibration, despite the theoretical equivalence of perfectly calibrated soft pseudo-labels to hard pseudo-labels. Based on this finding, we propose DA-Cal, a dedicated cross-domain calibration framework that transforms target domain calibration into soft pseudo-label optimization. DA-Cal introduces a Meta Temperature Network to generate pixel-level calibration parameters and employs bi-level optimization to establish the relationship between soft pseudo-labels and UDA supervision, while utilizing complementary domain-mixing strategies to prevent overfitting and reduce domain discrepancies. Experiments demonstrate that DA-Cal seamlessly integrates with existing self-training frameworks across multiple UDA segmentation benchmarks, significantly improving target domain calibration while delivering performance gains without inference overhead. The code will be released.

---

### FinAnchor: Aligned Multi-Model Representations for Financial Prediction

Authors: Zirui He, Huopu Zhang, Yanguang Liu, Sirui Wu, Mengnan Du
Published: 2026-02-24
Categories: cs.CL
arXiv: https://arxiv.org/abs/2602.20859v1

Financial prediction from long documents involves significant challenges, as actionable signals are often sparse and obscured by noise, and the optimal LLM for generating embeddings varies across tasks and time periods. In this paper, we propose FinAnchor(Financial Anchored Representations), a lightweight framework that integrates embeddings from multiple LLMs without fine-tuning the underlying models. FinAnchor addresses the incompatibility of feature spaces by selecting an anchor embedding space and learning linear mappings to align representations from other models into this anchor. These aligned features are then aggregated to form a unified representation for downstream prediction. Across multiple financial NLP tasks, FinAnchor consistently outperforms strong single-model baselines and standard ensemble methods, demonstrating the effectiveness of anchoring heterogeneous representations for robust financial prediction.

---

### Segmented Continuous Optimization

Authors: Teymur Aghayev
Published: 2026-02-24
Categories: eess.SP, cs.LG
arXiv: https://arxiv.org/abs/2602.20857v2

Segmented curve fitting remains an essential approach for the comprehensive analysis of local patterns in non-stationary time-series data. However, traditional regression algorithms primarily focus on linear or polynomial functions, which can be insufficient for analyzing raw signals with oscillatory or transcendental behavior. In this paper, we propose Segmented Continuous Optimization (SCO), a framework that performs piecewise continuous curve fitting on various non-linear models, including trigonometric, polynomial, and exponential. SCO presents a novel signal representation by optimizing a user-defined model in segments with $C^1$ continuity to properly analyze the data's local and global trends. The framework is tested for accuracy and efficiency across all included models. Finally, we provide examples using velocity and EEG datasets to demonstrate the algorithm's practical usage in examining signal patterns, optimized parameters, derivatives, and integrals of the final fit.

---

### Stochastic Discount Factors with Cross-Asset Spillovers

Authors: Doron Avramov, Xin He
Published: 2026-02-24
Categories: q-fin.CP, econ.EM, q-fin.PM, stat.ML
arXiv: https://arxiv.org/abs/2602.20856v1

This paper develops a unified framework that links firm-level predictive signals, cross-asset spillovers, and the stochastic discount factor (SDF). Signals and spillovers are jointly estimated by maximizing the Sharpe ratio, yielding an interpretable SDF that both ranks characteristic relevance and uncovers the direction of predictive influence across assets. Out-of-sample, the SDF consistently outperforms self-predictive and expected-return benchmarks across investment universes and market states. The inferred information network highlights large, low-turnover firms as net transmitters. The framework offers a clear, economically grounded view of the informational architecture underlying cross-sectional return dynamics.

---

### On the Explainability of Vision-Language Models in Art History

Authors: Stefanie Schneider
Published: 2026-02-24
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.20853v1

Vision-Language Models (VLMs) transfer visual and textual data into a shared embedding space. In so doing, they enable a wide range of multimodal tasks, while also raising critical questions about the nature of machine 'understanding.' In this paper, we examine how Explainable Artificial Intelligence (XAI) methods can render the visual reasoning of a VLM - namely, CLIP - legible in art-historical contexts. To this end, we evaluate seven methods, combining zero-shot localization experiments with human interpretability studies. Our results indicate that, while these methods capture some aspects of human interpretation, their effectiveness hinges on the conceptual stability and representational availability of the examined categories.

---

### Hybrid Fusion: One-Minute Efficient Training for Zero-Shot Cross-Domain Image Fusion

Authors: Ran Zhang, Xuanhua He, Liu Liu
Published: 2026-02-24
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.20851v1

Image fusion seeks to integrate complementary information from multiple sources into a single, superior image. While traditional methods are fast, they lack adaptability and performance. Conversely, deep learning approaches achieve state-of-the-art (SOTA) results but suffer from critical inefficiencies: their reliance on slow, resource-intensive, patch-based training introduces a significant gap with full-resolution inference. We propose a novel hybrid framework that resolves this trade-off. Our method utilizes a learnable U-Net to generate a dynamic guidance map that directs a classic, fixed Laplacian pyramid fusion kernel. This decoupling of policy learning from pixel synthesis enables remarkably efficient full-resolution training, eliminating the train-inference gap. Consequently, our model achieves SOTA-comparable performance in about one minute on a RTX 4090 or two minutes on a consumer laptop GPU from scratch without any external model and demonstrates powerful zero-shot generalization across diverse tasks, from infrared-visible to medical imaging. By design, the fused output is linearly constructed solely from source information, ensuring high faithfulness for critical applications. The codes are available at https://github.com/Zirconium233/HybridFusion

---

### Body-Reservoir Governance in Repeated Games: Embodied Decision-Making, Dynamic Sentinel Adaptation, and Complexity-Regularized Optimization

Authors: Yuki Nakamura
Published: 2026-02-24
Categories: cs.GT, cs.MA, cs.NE, nlin.AO
arXiv: https://arxiv.org/abs/2602.20846v1

Standard game theory explains cooperation in repeated games through conditional strategies such as Tit-for-Tat (TfT), but these require continuous computation that imposes physical costs on embodied agents. We propose a three-layer Body-Reservoir Governance (BRG) architecture: (1) a body reservoir (echo state network) whose $d$-dimensional state performs implicit inference over interaction history, serving as both decision-maker and anomaly detector, (2) a cognitive filter providing costly strategic tools activated on demand, and (3) a metacognitive governance layer with receptivity parameter $α\in (0,1)$. At full body governance ($α=1$), closed-loop dynamics satisfy a self-consistency equation: cooperation is expressed as the reservoir's fixed point, not computed. Strategy complexity cost is defined as the KL divergence between the reservoir's state distribution and its habituated baseline. Body governance reduces this cost, with action variance decreasing up to $1600\times$ with dimension $d$. A dynamic sentinel generates a composite discomfort signal from the reservoir's own state, driving adaptive $α(t)$: near baseline during cooperation, rapidly dropping upon defection to activate cognitive retaliation. Overriding the body incurs thermodynamic cost proportional to internal state distortion. The sentinel achieves the highest payoff across all conditions, outperforming static body governance, TfT, and EMA baselines. A dimension sweep ($d \in \{5,\ldots,100\}$) shows implicit inference scales with bodily richness ($23\times$ to $1600\times$ variance reduction), attributable to reservoir dynamics. A phase diagram in $(d, τ_{\mathrm{env}})$ space reveals governance regime transitions near $d \approx 20$. The framework reinterprets cooperation as the minimum-dissipation response of an adapted dynamical system -- emergent from embodied dynamics rather than computed.

---

### FLIM Networks with Bag of Feature Points

Authors: João Deltregia Martinelli, Marcelo Luis Rodrigues Filho, Felipe Crispim da Rocha Salvagnini, Gilson Junior Soares, Jefersson A. dos Santos, Alexandre X. Falcão
Published: 2026-02-24
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.20845v1

Convolutional networks require extensive image annotation, which can be costly and time-consuming. Feature Learning from Image Markers (FLIM) tackles this challenge by estimating encoder filters (i.e., kernel weights) from user-drawn markers on discriminative regions of a few representative images without traditional optimization. Such an encoder combined with an adaptive decoder comprises a FLIM network fully trained without backpropagation. Prior research has demonstrated their effectiveness in Salient Object Detection (SOD), being significantly lighter than existing lightweight models. This study revisits FLIM SOD and introduces FLIM-Bag of Feature Points (FLIM-BoFP), a considerably faster filter estimation method. The previous approach, FLIM-Cluster, derives filters through patch clustering at each encoder's block, leading to computational overhead and reduced control over filter locations. FLIM-BoFP streamlines this process by performing a single clustering at the input block, creating a bag of feature points, and defining filters directly from mapped feature points across all blocks. The paper evaluates the benefits in efficiency, effectiveness, and generalization of FLIM-BoFP compared to FLIM-Cluster and other state-of-the-art baselines for parasite detection in optical microscopy images.

---

### Maximum entropy based testing in network models: ERGMs and constrained optimization

Authors: Subhro Ghosh, Rathindra Nath Karmakar, Samriddha Lahiry
Published: 2026-02-24
Categories: math.ST, cs.IT, math.PR, stat.ME, stat.ML
arXiv: https://arxiv.org/abs/2602.20844v2

Stochastic network models play a central role across a wide range of scientific disciplines, and questions of statistical inference arise naturally in this context. In this paper we investigate goodness-of-fit and two-sample testing procedures for statistical networks based on the principle of maximum entropy (MaxEnt). Our approach formulates a constrained entropy-maximization problem on the space of networks, subject to prescribed structural constraints. The resulting test statistics are defined through the Lagrange multipliers associated with the constrained optimization problem, which, to our knowledge, is novel in the statistical networks literature. We establish consistency in the classical regime where the number of vertices is fixed. We then consider asymptotic regimes in which the graph size grows with the sample size, developing tests for both dense and sparse settings. In the dense case, we analyze exponential random graph models (ERGM) (including the Erdös-Rènyi models), while in the sparse regime our theory applies to Erd{ö}s-R{è}nyi graphs. Our analysis leverages recent advances in nonlinear large deviation theory for random graphs. We further show that the proposed Lagrange-multiplier framework connects naturally to classical score tests for constrained maximum likelihood estimation. The results provide a unified entropy-based framework for network model assessment across diverse growth regimes.

---

### Training-Free Multi-Concept Image Editing

Authors: Niki Foteinopoulou, Ignas Budvytis, Stephan Liwicki
Published: 2026-02-24
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.20839v3

Training-free image editing with diffusion models is highly desirable yet is complex and remains a significant challenge. While recent optimisation-based methods achieve strong zero-shot edits from text, they still struggle to preserve identity and capture intricate details, such as facial structure, surface texture, or object-specific geometry, that exist below the level of linguistic abstraction. To address this fundamental gap, we propose Concept Distillation Sampling (CDS). To the best of our knowledge, we are the first to introduce a unified, training-free framework for target-less, multi-concept image editing. CDS overcomes this linguistic bottleneck of previous methods by anchoring the editing process in the certainty of pretrained LoRA adapters. We integrate a highly stable distillation backbone (featuring ordered timesteps, regularisation, and negative-prompt guidance) with a novel dynamic weighting mechanism. This approach enables the composition and control of multiple visual concepts directly within the diffusion process, utilising spatially-aware priors from pretrained LoRA adapters without causing concept clashing. Our method preserves instance concept identity without requiring reference samples of the desired edit. Extensive quantitative and qualitative evaluations demonstrate that CDS establishes a new state-of-the-art over existing training-free editing and multi-LoRA composition methods on the InstructPix2Pix and ComposLoRA benchmarks. Project Page: https://nickyfot.github.io/cds/.

---

### Training-Free Multi-Concept Image Editing

Authors: Niki Foteinopoulou, Ignas Budvytis, Stephan Liwicki
Published: 2026-02-24
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.20839v2

Editing images with diffusion models under strict training-free constraints remains a significant challenge. While recent optimisation-based methods achieve strong zero-shot edits from text, they struggle to preserve identity and capture intricate details, such as facial structure, material texture, or object-specific geometry, that exist below the level of linguistic abstraction. To address this fundamental gap, we propose Concept Distillation Sampling (CDS). To the best of our knowledge, we are the first to introduce a unified, training-free framework for target-less, multi-concept image editing. CDS overcomes the linguistic bottleneck of previous methods by integrating a highly stable distillation backbone (featuring ordered timesteps, regularisation, and negative-prompt guidance), with a dynamic weighting mechanism. This approach enables the seamless composition and control of multiple visual concepts directly within the diffusion process, utilising spatially-aware priors from pretrained LoRA adapters without spatial interference. Our method preserves instance fidelity without requiring reference samples of the desired edit. Extensive quantitative and qualitative evaluations demonstrate consistent state-of-the-art performance over existing training-free editing and multi-LoRA composition methods on the InstructPix2Pix and ComposLoRA benchmarks. Code will be made publicly available.

---

### DRESS: A Continuous Framework for Structural Graph Refinement

Authors: Eduar Castrillo Velilla
Published: 2026-02-24
Categories: cs.DS, cs.LG
arXiv: https://arxiv.org/abs/2602.20833v6

We introduce DRESS, a deterministic, parameter-free framework that iteratively refines the structural similarity of edges in a graph to produce a canonical fingerprint: a real-valued edge vector, obtained by converging a non-linear dynamical system to its unique fixed point. The fingerprint is isomorphism-invariant by construction, numerically stable (strictly bounded, precision-preserving, and mathematically well-posed), fast and embarrassingly parallel to compute: DRESS total runtime is $\mathcal{O}(I \cdot m \cdot d_{\max})$ for $I$ iterations to convergence, and convergence is guaranteed by Birkhoff contraction. We generalize the original equation to Motif-DRESS (arbitrary structural motifs) and Generalized-DRESS (abstract aggregation template), and introduce $Δ$-DRESS, which runs DRESS on each vertex-deleted subgraph to boost expressiveness. $Δ$-DRESS empirically separates all 7,983 graphs in a comprehensive Strongly Regular Graph benchmark, and on the tested CFI instances ($k = 0,1,2,3$), $k$-deletion ($Δ^k$-DRESS) empirically matches the $(k{+}2)$-WL boundary.

---

### GatedCLIP: Gated Multimodal Fusion for Hateful Memes Detection

Authors: Yingying Guo, Ke Zhang, Zirong Zeng
Published: 2026-02-24
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.20818v1

Detecting hateful content in multimodal memes presents unique challenges, as harmful messages often emerge from the complex interplay between benign images and text. We propose GatedCLIP, a Vision-Language model that enhances CLIP's multimodal capabilities with specialized architectural improvements for hateful memes detection. Our approach introduces learned projection heads that map CLIP embeddings to a task-optimized semantic space, a dynamic gated fusion mechanism that adaptively weights visual and textual features, and a contrastive learning objective that maintains cross-modal semantic alignment. Experiments on the Hateful Memes dataset demonstrate that GatedCLIP achieves an AUROC of 0.66, substantially outperforming the CLIP baseline (AUROC 0.49) while maintaining computational efficiency with only 350K trainable parameters.

---

### Don't Ignore the Tail: Decoupling top-K Probabilities for Efficient Language Model Distillation

Authors: Sayantan Dasgupta, Trevor Cohn, Timothy Baldwin
Published: 2026-02-24
Categories: cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2602.20816v3

The core learning signal used in language model distillation is the standard Kullback-Leibler (KL) divergence between the student and teacher distributions. Traditional KL divergence tends to be dominated by the next tokens with the highest probabilities, i.e., the teacher's modes, thereby diminishing the influence of less probable yet potentially informative components of the output distribution. We propose a new tail-aware divergence that decouples the contribution of the teacher model's top-K predicted probabilities from that of lower-probability predictions, while maintaining the same computational profile as the KL Divergence. Our decoupled approach reduces the impact of the teacher modes and, consequently, increases the contribution of the tail of the distribution. Experimental results demonstrate that our modified distillation method yields competitive performance in both pre-training and supervised distillation of decoder models across various datasets. Furthermore, the distillation process is efficient and can be performed with a modest academic budget for large datasets, eliminating the need for industry-scale computing.

---

### Pressure Reveals Character: Behavioural Alignment Evaluation at Depth

Authors: Nora Petrova, John Burden
Published: 2026-02-24
Categories: cs.AI
arXiv: https://arxiv.org/abs/2602.20813v1

Evaluating alignment in language models requires testing how they behave under realistic pressure, not just what they claim they would do. While alignment failures increasingly cause real-world harm, comprehensive evaluation frameworks with realistic multi-turn scenarios remain lacking. We introduce an alignment benchmark spanning 904 scenarios across six categories -- Honesty, Safety, Non-Manipulation, Robustness, Corrigibility, and Scheming -- validated as realistic by human raters. Our scenarios place models under conflicting instructions, simulated tool access, and multi-turn escalation to reveal behavioural tendencies that single-turn evaluations miss. Evaluating 24 frontier models using LLM judges validated against human annotations, we find that even top-performing models exhibit gaps in specific categories, while the majority of models show consistent weaknesses across the board. Factor analysis reveals that alignment behaves as a unified construct (analogous to the g-factor in cognitive research) with models scoring high on one category tending to score high on others. We publicly release the benchmark and an interactive leaderboard to support ongoing evaluation, with plans to expand scenarios in areas where we observe persistent weaknesses and to add new models as they are released.

---

### Qwen-BIM: developing large language model for BIM-based design with domain-specific benchmark and dataset

Authors: Jia-Rui Lin, Yun-Hong Cai, Xiang-Rui Ni, Shaojie Zhou, Peng Pan
Published: 2026-02-24
Categories: cs.AI
arXiv: https://arxiv.org/abs/2602.20812v1

As the construction industry advances toward digital transformation, BIM (Building Information Modeling)-based design has become a key driver supporting intelligent construction. Despite Large Language Models (LLMs) have shown potential in promoting BIM-based design, the lack of specific datasets and LLM evaluation benchmarks has significantly hindered the performance of LLMs. Therefore, this paper addresses this gap by proposing: 1) an evaluation benchmark for BIM-based design together with corresponding quantitative indicators to evaluate the performance of LLMs, 2) a method for generating textual data from BIM and constructing corresponding BIM-derived datasets for LLM evaluation and fine-tuning, and 3) a fine-tuning strategy to adapt LLMs for BIM-based design. Results demonstrate that the proposed domain-specific benchmark effectively and comprehensively assesses LLM capabilities, highlighting that general LLMs are still incompetent for domain-specific tasks. Meanwhile, with the proposed benchmark and datasets, Qwen-BIM is developed and achieves a 21.0% average increase in G-Eval score compared to the base LLM model. Notably, with only 14B parameters, performance of Qwen-BIM is comparable to that of general LLMs with 671B parameters for BIM-based design tasks. Overall, this study develops the first domain-specific LLM for BIM-based design by introducing a comprehensive benchmark and high-quality dataset, which provide a solid foundation for developing BIM-related LLMs in various fields.

---

### POMDPPlanners: Open-Source Package for POMDP Planning

Authors: Yaacov Pariente, Vadim Indelman
Published: 2026-02-24
Categories: cs.AI
arXiv: https://arxiv.org/abs/2602.20810v1

We present POMDPPlanners, an open-source Python package for empirical evaluation of Partially Observable Markov Decision Process (POMDP) planning algorithms. The package integrates state-of-the-art planning algorithms, a suite of benchmark environments with safety-critical variants, automated hyperparameter optimization via Optuna, persistent caching with failure recovery, and configurable parallel simulation -- reducing the overhead of extensive simulation studies. POMDPPlanners is designed to enable scalable, reproducible research on decision-making under uncertainty, with particular emphasis on risk-sensitive settings where standard toolkits fall short.

---

### Regret-Guided Search Control for Efficient Learning in AlphaZero

Authors: Yun-Jui Tsai, Wei-Yu Chen, Yan-Ru Ju, Yu-Hung Chang, Ti-Rong Wu
Published: 2026-02-24
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2602.20809v1

Reinforcement learning (RL) agents achieve remarkable performance but remain far less learning-efficient than humans. While RL agents require extensive self-play games to extract useful signals, humans often need only a few games, improving rapidly by repeatedly revisiting states where mistakes occurred. This idea, known as search control, aims to restart from valuable states rather than always from the initial state. In AlphaZero, prior work Go-Exploit applies this idea by sampling past states from self-play or search trees, but it treats all states equally, regardless of their learning potential. We propose Regret-Guided Search Control (RGSC), which extends AlphaZero with a regret network that learns to identify high-regret states, where the agent's evaluation diverges most from the actual outcome. These states are collected from both self-play trajectories and MCTS nodes, stored in a prioritized regret buffer, and reused as new starting positions. Across 9x9 Go, 10x10 Othello, and 11x11 Hex, RGSC outperforms AlphaZero and Go-Exploit by an average of 77 and 89 Elo, respectively. When training on a well-trained 9x9 Go model, RGSC further improves the win rate against KataGo from 69.3% to 78.2%, while both baselines show no improvement. These results demonstrate that RGSC provides an effective mechanism for search control, improving both efficiency and robustness of AlphaZero training. Our code is available at https://rlg.iis.sinica.edu.tw/papers/rgsc.

---

### RU4D-SLAM: Reweighting Uncertainty in Gaussian Splatting SLAM for 4D Scene Reconstruction

Authors: Yangfan Zhao, Hanwei Zhang, Ke Huang, Qiufeng Wang, Zhenzhou Shao, Dengyu Wu
Published: 2026-02-24
Categories: cs.CV, cs.RO
arXiv: https://arxiv.org/abs/2602.20807v2

Combining 3D Gaussian splatting with Simultaneous Localization and Mapping (SLAM) has gained popularity as it enables continuous 3D environment reconstruction during motion. However, existing methods struggle in dynamic environments, particularly moving objects complicate 3D reconstruction and, in turn, hinder reliable tracking. The emergence of 4D reconstruction, especially 4D Gaussian splatting, offers a promising direction for addressing these challenges, yet its potential for 4D-aware SLAM remains largely underexplored. Along this direction, we propose a robust and efficient framework, namely Reweighting Uncertainty in Gaussian Splatting SLAM (RU4D-SLAM) for 4D scene reconstruction, that introduces temporal factors into spatial 3D representation while incorporating uncertainty-aware perception of scene changes, blurred image synthesis, and dynamic scene reconstruction. We enhance dynamic scene representation by integrating motion blur rendering, and improve uncertainty-aware tracking by extending per-pixel uncertainty modeling, which is originally designed for static scenarios, to handle blurred images. Furthermore, we propose a semantic-guided reweighting mechanism for per-pixel uncertainty estimation in dynamic scenes, and introduce a learnable opacity weight to support adaptive 4D mapping. Extensive experiments on standard benchmarks demonstrate that our method substantially outperforms state-of-the-art approaches in both trajectory accuracy and 4D scene reconstruction, particularly in dynamic environments with moving objects and low-quality inputs. Code available: https://ru4d-slam.github.io

---

### Assessing the Impact of Speaker Identity in Speech Spoofing Detection

Authors: Anh-Tuan Dao, Driss Matrouf, Nicholas Evans
Published: 2026-02-24
Categories: cs.SD, cs.LG
arXiv: https://arxiv.org/abs/2602.20805v1

Spoofing detection systems are typically trained using diverse recordings from multiple speakers, often assuming that the resulting embeddings are independent of speaker identity. However, this assumption remains unverified. In this paper, we investigate the impact of speaker information on spoofing detection systems. We propose two approaches within our Speaker-Invariant Multi-Task framework, one that models speaker identity within the embeddings and another that removes it. SInMT integrates multi-task learning for joint speaker recognition and spoofing detection, incorporating a gradient reversal layer. Evaluated using four datasets, our speaker-invariant model reduces the average equal error rate by 17% compared to the baseline, with up to 48% reduction for the most challenging attacks (e.g., A11).

---

### Probing Dec-POMDP Reasoning in Cooperative MARL

Authors: Kale-ab Tessera, Leonard Hinckeldey, Riccardo Zamboni, David Abel, Amos Storkey
Published: 2026-02-24
Categories: cs.LG, cs.MA
arXiv: https://arxiv.org/abs/2602.20804v2

Cooperative multi-agent reinforcement learning (MARL) is typically framed as a decentralised partially observable Markov decision process (Dec-POMDP), a setting whose hardness stems from two key challenges: partial observability and decentralised coordination. Genuinely solving such tasks requires Dec-POMDP reasoning, where agents use history to infer hidden states and coordinate based on local information. Yet it remains unclear whether popular benchmarks actually demand this reasoning or permit success via simpler strategies. We introduce a diagnostic suite combining statistically grounded performance comparisons and information-theoretic probes to audit the behavioural complexity of baseline policies (IPPO and MAPPO) across 37 scenarios spanning MPE, SMAX, Overcooked, Hanabi, and MaBrax. Our diagnostics reveal that success on these benchmarks rarely requires genuine Dec-POMDP reasoning. Reactive policies match the performance of memory-based agents in over half the scenarios, and emergent coordination frequently relies on brittle, synchronous action coupling rather than robust temporal influence. These findings suggest that some widely used benchmarks may not adequately test core Dec-POMDP assumptions under current training paradigms, potentially leading to over-optimistic assessments of progress. We release our diagnostic tooling to support more rigorous environment design and evaluation in cooperative MARL.

---

### Exploring the Impact of Parameter Update Magnitude on Forgetting and Generalization of Continual Learning

Authors: JinLi He, Liang Bai, Xian Yang
Published: 2026-02-24
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.20796v1

The magnitude of parameter updates are considered a key factor in continual learning. However, most existing studies focus on designing diverse update strategies, while a theoretical understanding of the underlying mechanisms remains limited. Therefore, we characterize model's forgetting from the perspective of parameter update magnitude and formalize it as knowledge degradation induced by task-specific drift in the parameter space, which has not been fully captured in previous studies due to their assumption of a unified parameter space. By deriving the optimal parameter update magnitude that minimizes forgetting, we unify two representative update paradigms, frozen training and initialized training, within an optimization framework for constrained parameter updates. Our theoretical results further reveals that sequence tasks with small parameter distances exhibit better generalization and less forgetting under frozen training rather than initialized training. These theoretical insights inspire a novel hybrid parameter update strategy that adaptively adjusts update magnitude based on gradient directions. Experiments on deep neural networks demonstrate that this hybrid approach outperforms standard training strategies, providing new theoretical perspectives and practical inspiration for designing efficient and scalable continual learning algorithms.

---

### VGGDrive: Empowering Vision-Language Models with Cross-View Geometric Grounding for Autonomous Driving

Authors: Jie Wang, Guang Li, Zhijian Huang, Chenxu Dang, Hangjun Ye, Yahong Han, Long Chen
Published: 2026-02-24
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.20794v1

The significance of cross-view 3D geometric modeling capabilities for autonomous driving is self-evident, yet existing Vision-Language Models (VLMs) inherently lack this capability, resulting in their mediocre performance. While some promising approaches attempt to mitigate this by constructing Q&A data for auxiliary training, they still fail to fundamentally equip VLMs with the ability to comprehensively handle diverse evaluation protocols. We thus chart a new course, advocating for the infusion of VLMs with the cross-view geometric grounding of mature 3D foundation models, closing this critical capability gap in autonomous driving. In this spirit, we propose a novel architecture, VGGDrive, which empowers Vision-language models with cross-view Geometric Grounding for autonomous Driving. Concretely, to bridge the cross-view 3D geometric features from the frozen visual 3D model with the VLM's 2D visual features, we introduce a plug-and-play Cross-View 3D Geometric Enabler (CVGE). The CVGE decouples the base VLM architecture and effectively empowers the VLM with 3D features through a hierarchical adaptive injection mechanism. Extensive experiments show that VGGDrive enhances base VLM performance across five autonomous driving benchmarks, including tasks like cross-view risk perception, motion prediction, and trajectory planning. It's our belief that mature 3D foundation models can empower autonomous driving tasks through effective integration, and we hope our initial exploration demonstrates the potential of this paradigm to the autonomous driving community.

---

### SIMSPINE: A Biomechanics-Aware Simulation Framework for 3D Spine Motion Annotation and Benchmarking

Authors: Muhammad Saif Ullah Khan, Didier Stricker
Published: 2026-02-24
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.20792v3

Modeling spinal motion is fundamental to understanding human biomechanics, yet remains underexplored in computer vision due to the spine's complex multi-joint kinematics and the lack of large-scale 3D annotations. We present a biomechanics-aware keypoint simulation framework that augments existing human pose datasets with anatomically consistent 3D spinal keypoints derived from musculoskeletal modeling. Using this framework, we create the first open dataset, named SIMSPINE, which provides sparse vertebra-level 3D spinal annotations for natural full-body motions in indoor multi-camera capture without external restraints. With 2.14 million frames, this enables data-driven learning of vertebral kinematics from subtle posture variations and bridges the gap between musculoskeletal simulation and computer vision. In addition, we release pretrained baselines covering fine-tuned 2D detectors, monocular 3D pose lifting models, and multi-view reconstruction pipelines, establishing a unified benchmark for biomechanically valid spine motion estimation. Specifically, our 2D spine baselines improve the state-of-the-art from 0.63 to 0.80 AUC in controlled environments, and from 0.91 to 0.93 AP for in-the-wild spine tracking. Together, the simulation framework and SIMSPINE dataset advance research in vision-based biomechanics, motion analysis, and digital human modeling by enabling reproducible, anatomically grounded 3D spine estimation under natural conditions.

---

### Understanding the Role of Rehearsal Scale in Continual Learning under Varying Model Capacities

Authors: JinLi He, Liang Bai, Xian Yang
Published: 2026-02-24
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.20791v1

Rehearsal is one of the key techniques for mitigating catastrophic forgetting and has been widely adopted in continual learning algorithms due to its simplicity and practicality. However, the theoretical understanding of how rehearsal scale influences learning dynamics remains limited. To address this gap, we formulate rehearsal-based continual learning as a multidimensional effectiveness-driven iterative optimization problem, providing a unified characterization across diverse performance metrics. Within this framework, we derive a closed-form analysis of adaptability, memorability, and generalization from the perspective of rehearsal scale. Our results uncover several intriguing and counterintuitive findings. First, rehearsal can impair model's adaptability, in sharp contrast to its traditionally recognized benefits. Second, increasing the rehearsal scale does not necessarily improve memory retention. When tasks are similar and noise levels are low, the memory error exhibits a diminishing lower bound. Finally, we validate these insights through numerical simulations and extended analyses on deep neural networks across multiple real-world datasets, revealing statistical patterns of rehearsal mechanisms in continual learning.

---

### Real-time Motion Segmentation with Event-based Normal Flow

Authors: Sheng Zhong, Zhongyang Ren, Xiya Zhu, Dehao Yuan, Cornelia Fermuller, Yi Zhou
Published: 2026-02-24
Categories: cs.CV, cs.RO
arXiv: https://arxiv.org/abs/2602.20790v1

Event-based cameras are bio-inspired sensors with pixels that independently and asynchronously respond to brightness changes at microsecond resolution, offering the potential to handle visual tasks in challenging scenarios. However, due to the sparse information content in individual events, directly processing the raw event data to solve vision tasks is highly inefficient, which severely limits the applicability of state-of-the-art methods in real-time tasks, such as motion segmentation, a fundamental task for dynamic scene understanding. Incorporating normal flow as an intermediate representation to compress motion information from event clusters within a localized region provides a more effective solution. In this work, we propose a normal flow-based motion segmentation framework for event-based vision. Leveraging the dense normal flow directly learned from event neighborhoods as input, we formulate the motion segmentation task as an energy minimization problem solved via graph cuts, and optimize it iteratively with normal flow clustering and motion model fitting. By using a normal flow-based motion model initialization and fitting method, the proposed system is able to efficiently estimate the motion models of independently moving objects with only a limited number of candidate models, which significantly reduces the computational complexity and ensures real-time performance, achieving nearly a 800x speedup in comparison to the open-source state-of-the-art method. Extensive evaluations on multiple public datasets fully demonstrate the accuracy and efficiency of our framework.

---

### On Electric Vehicle Energy Demand Forecasting and the Effect of Federated Learning

Authors: Andreas Tritsarolis, Gil Sampaio, Nikos Pelekis, Yannis Theodoridis
Published: 2026-02-24
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.20782v1

The wide spread of new energy resources, smart devices, and demand side management strategies has motivated several analytics operations, from infrastructure load modeling to user behavior profiling. Energy Demand Forecasting (EDF) of Electric Vehicle Supply Equipments (EVSEs) is one of the most critical operations for ensuring efficient energy management and sustainability, since it enables utility providers to anticipate energy/power demand, optimize resource allocation, and implement proactive measures to improve grid reliability. However, accurate EDF is a challenging problem due to external factors, such as the varying user routines, weather conditions, driving behaviors, unknown state of charge, etc. Furthermore, as concerns and restrictions about privacy and sustainability have grown, training data has become increasingly fragmented, resulting in distributed datasets scattered across different data silos and/or edge devices, calling for federated learning solutions. In this paper, we investigate different well-established time series forecasting methodologies to address the EDF problem, from statistical methods (the ARIMA family) to traditional machine learning models (such as XGBoost) and deep neural networks (GRU and LSTM). We provide an overview of these methods through a performance comparison over four real-world EVSE datasets, evaluated under both centralized and federated learning paradigms, focusing on the trade-offs between forecasting fidelity, privacy preservation, and energy overheads. Our experimental results demonstrate, on the one hand, the superiority of gradient boosted trees (XGBoost) over statistical and NN-based models in both prediction accuracy and energy efficiency and, on the other hand, an insight that Federated Learning-enabled models balance these factors, offering a promising direction for decentralized energy demand forecasting.

---

### Federated Learning for Cross-Modality Medical Image Segmentation via Augmentation-Driven Generalization

Authors: Sachin Dudda Nagaraju, Ashkan Moradi, Bendik Skarre Abrahamsen, Mattijs Elschot
Published: 2026-02-24
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.20773v2

Purpose: Developing generalizable medical image segmentation models is challenging because imaging data are distributed across institutions and differ in modality and acquisition protocol. Federated learning (FL) enables collaborative training without centralizing raw medical images, but cross-modality domain shifts between computed tomography (CT) and magnetic resonance imaging (MRI) can substantially reduce model performance. This study investigates augmentation-driven cross-modality FL for abdominal organ and whole-heart segmentation. Methods: We evaluate convolution-based spatial augmentation, frequency-domain argumentation, domain-specific normalization, and global intensity nonlinear (GIN) augmentation for multimodal segmentation. Abdominal organ segmentation and whole-heart segmentation are first evaluated using a 2D U-Net framework. For whole-heart segmentation, we additionally perform native 3D experiments using a self-configuring nnU-Net architecture on the CARE-WHS 2026 dataset, enabling evaluation of whether the observed cross-modality FL behavior persists when moving from slice-based 2D segmentation to volumetric 3D segmentation. Results: GIN provides the most consistent cross-modality performance among the evaluated approaches in the original 2D experiments. For pancreas segmentation, the Dice similarity coefficient (DSC) improved from 0.073 to 0.437 when CT data were incorporated through federated cross-modality training. In 3D whole-heart segmentation, FedGIN improved mean DSC over FedAvg from 0.8696 to 0.8901 on the unseen CT center and from 0.7160 to 0.7956 on the unseen MRI center. Relative to centralized GIN training, FedGIN retained 92.4\% of performance on unseen CT data and achieved comparable performance on unseen MRI data (0.7956 versus 0.7937).

---

### Federated Learning for Cross-Modality Medical Image Segmentation via Augmentation-Driven Generalization

Authors: Sachin Dudda Nagaraju, Ashkan Moradi, Bendik Skarre Abrahamsen, Mattijs Elschot
Published: 2026-02-24
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.20773v1

Artificial intelligence has emerged as a transformative tool in medical image analysis, yet developing robust and generalizable segmentation models remains difficult due to fragmented, privacy-constrained imaging data siloed across institutions. While federated learning (FL) enables collaborative model training without centralizing data, cross-modality domain shifts pose a critical challenge, particularly when models trained on one modality fail to generalize to another. Many existing solutions require paired multimodal data per patient or rely on complex architectures, both of which are impractical in real clinical settings. In this work, we consider a realistic FL scenario where each client holds single-modality data (CT or MRI), and systematically investigate augmentation strategies for cross-modality generalization. Using abdominal organ segmentation and whole-heart segmentation as representative multi-class and binary segmentation benchmarks, we evaluate convolution-based spatial augmentation, frequency-domain manipulation, domain-specific normalization, and global intensity nonlinear (GIN) augmentation. Our results show that GIN consistently outperforms alternatives in both centralized and federated settings by simulating cross-modality appearance variations while preserving anatomical structure. For the pancreas, Dice score improved from 0.073 to 0.437, a 498% gain. Our federated approach achieves 93-98% of centralized training accuracy, demonstrating strong cross-modality generalization without compromising data privacy, pointing toward feasible federated AI deployment across diverse healthcare systems.

---

### Pipeline for Verifying LLM-Generated Mathematical Solutions

Authors: Varvara Sazonova, Dmitri Shmelkin, Stanislav Kikot, Vasily Motolygin
Published: 2026-02-24
Categories: cs.AI
arXiv: https://arxiv.org/abs/2602.20770v1

With the growing popularity of Large Reasoning Models and their results in solving mathematical problems, it becomes crucial to measure their capabilities. We introduce a pipeline for both automatic and interactive verification as a more accurate alternative to only checking the answer which is currently the most popular approach for benchmarks. The pipeline can also be used as a generator of correct solutions both in formal and informal languages. 3 AI agents, which can be chosen for the benchmark accordingly, are included in the structure. The key idea is the use of prompts to obtain the solution in the specific form which allows for easier verification using proof assistants and possible use of small models ($\le 8B$). Experiments on several datasets suggest low probability of False Positives. The open-source implementation with instructions on setting up a server is available at https://github.com/LogicEnj/lean4_verification_pipeline.

---

### Overton Pluralistic Reinforcement Learning for Large Language Models

Authors: Yu Fu, Seongho Son, Ilija Bogunovic
Published: 2026-02-24
Categories: cs.CL
arXiv: https://arxiv.org/abs/2602.20759v1

Existing alignment paradigms remain limited in capturing the pluralistic nature of human values. Overton Pluralism addresses this gap by generating responses with diverse perspectives from a single query. This paper introduces OP-GRPO (Overton Pluralistic Group Relative Policy Optimization), a reinforcement learning framework for implicit Overton Pluralism that enables a single large language model to produce pluralistic responses without explicit prompting or modular orchestration. Our workflow consists of two main steps. First, similarity estimator training fine-tunes a Sentence Transformer for Overton Pluralism tasks to provide more accurate coverage evaluation of generated responses. Second, OP-GRPO training incorporates this similarity estimator into a dual-reward system designed to ensure both broad coverage of genuine human perspectives and the uniqueness of each perspective, thereby promoting diversity. Empirical results demonstrate a "small models, big perspective coverage" effect. The trained Qwen2.5-3B-Instruct model surpasses a 20B GPT-OSS baseline with a 37.4 percent relative accuracy gain on a Natural Language Inference benchmark, and also outperforms a modular architecture baseline with a 19.1 percent relative improvement. Additional evaluations using GPT-4.1 as a large language model judge further confirm the robustness of the approach.

---

### Deep unfolding of MCMC kernels: scalable, modular & explainable GANs for high-dimensional posterior sampling

Authors: Jonathan Spence, Tobías I. Liaudat, Konstantinos Zygalakis, Marcelo Pereyra
Published: 2026-02-24
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.20758v1

Markov chain Monte Carlo (MCMC) methods are fundamental to Bayesian computation, but can be computationally intensive, especially in high-dimensional settings. Push-forward generative models, such as generative adversarial networks (GANs), variational auto-encoders and normalising flows offer a computationally efficient alternative for posterior sampling. However, push-forward models are opaque as they lack the modularity of Bayes Theorem, leading to poor generalisation with respect to changes in the likelihood function. In this work, we introduce a novel approach to GAN architecture design by applying deep unfolding to Langevin MCMC algorithms. This paradigm maps fixed-step iterative algorithms onto modular neural networks, yielding architectures that are both flexible and amenable to interpretation. Crucially, our design allows key model parameters to be specified at inference time, offering robustness to changes in the likelihood parameters. We train these unfolded samplers end-to-end using a supervised regularized Wasserstein GAN framework for posterior sampling. Through extensive Bayesian imaging experiments, we demonstrate that our proposed approach achieves high sampling accuracy and excellent computational efficiency, while retaining the physics consistency, adaptability and interpretability of classical MCMC strategies.

---

### OrthoDiffusion: A Generalizable Multi-Task Diffusion Foundation Model for Musculoskeletal MRI Interpretation

Authors: Tian Lan, Lei Xu, Zimu Yuan, Shanggui Liu, Jiajun Liu, Jiaxin Liu, Weilai Xiang, Hongyu Yang, Dong Jiang, Jianxin Yin, Dingyu Wang
Published: 2026-02-24
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2602.20752v1

Musculoskeletal disorders represent a significant global health burden and are a leading cause of disability worldwide. While MRI is essential for accurate diagnosis, its interpretation remains exceptionally challenging. Radiologists must identify multiple potential abnormalities within complex anatomical structures across different imaging planes, a process that requires significant expertise and is prone to variability. We developed OrthoDiffusion, a unified diffusion-based foundation model designed for multi-task musculoskeletal MRI interpretation. The framework utilizes three orientation-specific 3D diffusion models, pre-trained in a self-supervised manner on 15,948 unlabeled knee MRI scans, to learn robust anatomical features from sagittal, coronal, and axial views. These view-specific representations are integrated to support diverse clinical tasks, including anatomical segmentation and multi-label diagnosis. Our evaluation demonstrates that OrthoDiffusion achieves excellent performance in the segmentation of 11 knee structures and the detection of 8 knee abnormalities. The model exhibited remarkable robustness across different clinical centers and MRI field strengths, consistently outperforming traditional supervised models. Notably, in settings where labeled data was scarce, OrthoDiffusion maintained high diagnostic precision using only 10\% of training labels. Furthermore, the anatomical representations learned from knee imaging proved highly transferable to other joints, achieving strong diagnostic performance across 11 diseases of the ankle and shoulder. These findings suggest that diffusion-based foundation models can serve as a unified platform for multi-disease diagnosis and anatomical segmentation, potentially improving the efficiency and accuracy of musculoskeletal MRI interpretation in real-world clinical workflows.

---