# Research Papers — 2026-02 · bundle page 11 of 210

> Full-text markdown of papers #501–550 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/11
[← Previous bundle](https://aipod.dev/papers/archive/2026-02/page/10.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-02/page/12.md)

### Benchmarking BERT-based Models for Sentence-level Topic Classification in Nepali Language

Authors: Nischal Karki, Bipesh Subedi, Prakash Poudyal, Rupak Raj Ghimire, Bal Krishna Bal
Published: 2026-02-27
Categories: cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2602.23940v1

Transformer-based models such as BERT have significantly advanced Natural Language Processing (NLP) across many languages. However, Nepali, a low-resource language written in Devanagari script, remains relatively underexplored. This study benchmarks multilingual, Indic, Hindi, and Nepali BERT variants to evaluate their effectiveness in Nepali topic classification. Ten pre-trained models, including mBERT, XLM-R, MuRIL, DevBERT, HindiBERT, IndicBERT, and NepBERTa, were fine-tuned and tested on the balanced Nepali dataset containing 25,006 sentences across five conceptual domains and the performance was evaluated using accuracy, weighted precision, recall, F1-score, and AUROC metrics. The results reveal that Indic models, particularly MuRIL-large, achieved the highest F1-score of 90.60%, outperforming multilingual and monolingual models. NepBERTa also performed competitively with an F1-score of 88.26%. Overall, these findings establish a robust baseline for future document-level classification and broader Nepali NLP applications.

---

### Enhancing Vision-Language Navigation with Multimodal Event Knowledge from Real-World Indoor Tour Videos

Authors: Haoxuan Xu, Tianfu Li, Wenbo Chen, Yi Liu, Xingxing Zuo, Yaoxian Song, Haoang Li
Published: 2026-02-27
Categories: cs.RO, cs.CV
arXiv: https://arxiv.org/abs/2602.23937v1

Vision-Language Navigation (VLN) agents often struggle with long-horizon reasoning in unseen environments, particularly when facing ambiguous, coarse-grained instructions. While recent advances use knowledge graph to enhance reasoning, the potential of multimodal event knowledge inspired by human episodic memory remains underexplored. In this work, we propose an event-centric knowledge enhancement strategy for automated process knowledge mining and feature fusion to solve coarse-grained instruction and long-horizon reasoning in VLN task. First, we construct YE-KG, the first large-scale multimodal spatiotemporal knowledge graph, with over 86k nodes and 83k edges, derived from real-world indoor videos. By leveraging multimodal large language models (i.e., LLaVa, GPT4), we extract unstructured video streams into structured semantic-action-effect events to serve as explicit episodic memory. Second, we introduce STE-VLN, which integrates the above graph into VLN models via a Coarse-to-Fine Hierarchical Retrieval mechanism. This allows agents to retrieve causal event sequences and dynamically fuse them with egocentric visual observations. Experiments on REVERIE, R2R, and R2R-CE benchmarks demonstrate the efficiency of our event-centric strategy, outperforming state-of-the-art approaches across diverse action spaces. Our data and code are available on the project website https://sites.google.com/view/y-event-kg/.

---

### Green or Fast? Learning to Balance Cold Starts and Idle Carbon in Serverless Computing

Authors: Bowen Sun, Christos D. Antonopoulos, Evgenia Smirni, Bin Ren, Nikolaos Bellas, Spyros Lalis
Published: 2026-02-27
Categories: cs.DC, cs.AI, cs.PF
arXiv: https://arxiv.org/abs/2602.23935v1

Serverless computing simplifies cloud deployment but introduces new challenges in managing service latency and carbon emissions. Reducing cold-start latency requires retaining warm function instances, while minimizing carbon emissions favors reclaiming idle resources. This balance is further complicated by time-varying grid carbon intensity and varying workload patterns, under which static keep-alive policies are inefficient. We present LACE-RL, a latency-aware and carbon-efficient management framework that formulates serverless pod retention as a sequential decision problem. LACE-RL uses deep reinforcement learning to dynamically tune keep-alive durations, jointly modeling cold-start probability, function-specific latency costs, and real-time carbon intensity. Using the Huawei Public Cloud Trace, we show that LACE-RL reduces cold starts by 51.69% and idle keep-alive carbon emissions by 77.08% compared to Huawei's static policy, while achieving better latency-carbon trade-offs than state-of-the-art heuristic and single-objective baselines, approaching Oracle performance.

---

### Learning to Build: Autonomous Robotic Assembly of Stable Structures Without Predefined Plans

Authors: Jingwen Wang, Johannes Kirschner, Paul Rolland, Luis Salamanca, Stefana Parascho
Published: 2026-02-27
Categories: cs.RO, cs.LG
arXiv: https://arxiv.org/abs/2602.23934v1

This paper presents a novel autonomous robotic assembly framework for constructing stable structures without relying on predefined architectural blueprints. Instead of following fixed plans, construction tasks are defined through targets and obstacles, allowing the system to adapt more flexibly to environmental uncertainty and variations during the building process. A reinforcement learning (RL) policy, trained using deep Q-learning with successor features, serves as the decision-making component. As a proof of concept, we evaluate the approach on a benchmark of 15 2D robotic assembly tasks of discrete block construction. Experiments using a real-world closed-loop robotic setup demonstrate the feasibility of the method and its ability to handle construction noise. The results suggest that our framework offers a promising direction for more adaptable and robust robotic construction in real-world environments.

---

### The Astonishing Ability of Large Language Models to Parse Jabberwockified Language

Authors: Gary Lupyan, Senyi Yang
Published: 2026-02-27
Categories: cs.CL
arXiv: https://arxiv.org/abs/2602.23928v2

We show that large language models (LLMs) have an astonishing ability to recover meaning from severely degraded English texts. Texts in which content words have been randomly substituted by nonsense strings, e.g., "At the ghybe of the swuint, we are haiveed to Wourge Phrear-gwurr, who sproles into an ghitch flount with his crurp", can be translated to conventional English that is, in many cases, close to the original text, e.g., "At the start of the story, we meet a man, Chow, who moves into an apartment building with his wife." These results show that structural cues (e.g., morphosyntax, closed-class words) constrain lexical meaning to a much larger degree than imagined. Although the abilities of LLMs to make sense of "Jabberwockified" English are clearly superhuman, they are highly relevant to understanding linguistic structure and suggest that efficient language processing either in biological or artificial systems likely benefits from very tight integration between syntax, lexical semantics, and general world knowledge.

---

### Leveraging Geometric Prior Uncertainty and Complementary Constraints for High-Fidelity Neural Indoor Surface Reconstruction

Authors: Qiyu Feng, Jiwei Shan, Shing Shin Cheng, Hesheng Wang
Published: 2026-02-27
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.23926v1

Neural implicit surface reconstruction with signed distance function has made significant progress, but recovering fine details such as thin structures and complex geometries remains challenging due to unreliable or noisy geometric priors. Existing approaches rely on implicit uncertainty that arises during optimization to filter these priors, which is indirect and inefficient, and masking supervision in high-uncertainty regions further leads to under-constrained optimization. To address these issues, we propose GPU-SDF, a neural implicit framework for indoor surface reconstruction that leverages geometric prior uncertainty and complementary constraints. We introduce a self-supervised module that explicitly estimates prior uncertainty without auxiliary networks. Based on this estimation, we design an uncertainty-guided loss that modulates prior influence rather than discarding it, thereby retaining weak but informative cues. To address regions with high prior uncertainty, GPU-SDF further incorporates two complementary constraints: an edge distance field that strengthens boundary supervision and a multi-view consistency regularization that enforces geometric coherence. Extensive experiments confirm that GPU-SDF improves the reconstruction of fine details and serves as a plug-and-play enhancement for existing frameworks. Source code will be available at https://github.com/IRMVLab/GPU-SDF

---

### Topology-Driven Transferability Estimation of Medical Foundation Models for Segmentation

Authors: Jiaqi Tang, Shaoyang Zhang, Xiaoqi Wang, Jiaying Zhou, Yang Liu, Qingchao Chen
Published: 2026-02-27
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2602.23916v2

The advent of large-scale self-supervised learning (SSL) has produced a vast zoo of medical foundation models. However, selecting optimal medical foundation models for specific segmentation tasks remains a computational bottleneck. Existing Transferability Estimation (TE) metrics, primarily designed for classification, rely on global statistical assumptions and fail to capture the topological complexity essential for dense prediction. We propose a novel Topology-Driven Transferability Estimation framework that evaluates manifold tractability rather than statistical overlap. Our approach introduces three components: (1) Global Representation Topology Divergence (GRTD), utilizing Minimum Spanning Trees to quantify feature-label structural isomorphism; (2) Local Boundary-Aware Topological Consistency (LBTC), which assesses manifold separability specifically at critical anatomical boundaries; and (3) Task-Adaptive Fusion, which dynamically integrates global and local metrics based on the semantic cardinality of the target task. Validated on the large-scale OpenMind benchmark across diverse anatomical targets and SSL foundation models, our approach significantly outperforms state-of-the-art baselines by around 31% relative improvement in the weighted Kendall metric, providing a robust, training-free proxy for efficient model selection without the cost of fine-tuning. The code will be made publicly available upon acceptance.

---

### Half-Truths Break Similarity-Based Retrieval

Authors: Bora Kargi, Arnas Uselis, Seong Joon Oh
Published: 2026-02-27
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.23906v1

When a text description is extended with an additional detail, image-text similarity should drop if that detail is wrong. We show that CLIP-style dual encoders often violate this intuition: appending a plausible but incorrect object or relation to an otherwise correct description can increase the similarity score. We call such cases half-truths. On COCO, CLIP prefers the correct shorter description only 40.6% of the time, and performance drops to 32.9% when the added detail is a relation. We trace this vulnerability to weak supervision on caption parts: contrastive training aligns full sentences but does not explicitly enforce that individual entities and relations are grounded. We propose CS-CLIP (Component-Supervised CLIP), which decomposes captions into entity and relation units, constructs a minimally edited foil for each unit, and fine-tunes the model to score the correct unit above its foil while preserving standard dual-encoder inference. CS-CLIP raises half-truth accuracy to 69.3% and improves average performance on established compositional benchmarks by 5.7 points, suggesting that reducing half-truth errors aligns with broader gains in compositional understanding. Code is publicly available at: https://github.com/kargibora/CS-CLIP

---

### SegMate: Asymmetric Attention-Based Lightweight Architecture for Efficient Multi-Organ Segmentation

Authors: Andrei-Alexandru Bunea, Dan-Matei Popovici, Radu Tudor Ionescu
Published: 2026-02-27
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2602.23903v1

State-of-the-art models for medical image segmentation achieve excellent accuracy but require substantial computational resources, limiting deployment in resource-constrained clinical settings. We present SegMate, an efficient 2.5D framework that achieves state-of-the-art accuracy, while considerably reducing computational requirements. Our efficient design is the result of meticulously integrating asymmetric architectures, attention mechanisms, multi-scale feature fusion, slice-based positional conditioning, and multi-task optimization. We demonstrate the efficiency-accuracy trade-off of our framework across three modern backbones (EfficientNetV2-M, MambaOut-Tiny, FastViT-T12). We perform experiments on three datasets: TotalSegmentator, SegTHOR and AMOS22. Compared with the vanilla models, SegMate reduces computation (GFLOPs) by up to 2.5x and memory footprint (VRAM) by up to 2.1x, while generally registering performance gains of around 1%. On TotalSegmentator, we achieve a Dice score of 93.51% with only 295MB peak GPU memory. Zero-shot cross-dataset evaluations on SegTHOR and AMOS22 demonstrate strong generalization, with Dice scores of up to 86.85% and 89.35%, respectively. We release our open-source code at https://github.com/andreibunea99/SegMate.

---

### ABPolicy: Asynchronous B-Spline Flow Policy for Real-Time and Smooth Robotic Manipulation

Authors: Fan Yang, Peiguang Jing, Kaihua Qu, Ningyuan Zhao, Yuting Su
Published: 2026-02-27
Categories: cs.RO, cs.CV
arXiv: https://arxiv.org/abs/2602.23901v1

Robotic manipulation requires policies that are smooth and responsive to evolving observations. However, synchronous inference in the raw action space introduces several challenges, including intra-chunk jitter, inter-chunk discontinuities, and stop-and-go execution. These issues undermine a policy's smoothness and its responsiveness to environmental changes. We propose ABPolicy, an asynchronous flow-matching policy that operates in a B-spline control-point action space. First, the B-spline representation ensures intra-chunk smoothness. Second, we introduce bidirectional action prediction coupled with refitting optimization to enforce inter-chunk continuity. Finally, by leveraging asynchronous inference, ABPolicy delivers real-time, continuous updates. We evaluate ABPolicy across seven tasks encompassing both static settings and dynamic settings with moving objects. Empirical results indicate that ABPolicy reduces trajectory jerk, leading to smoother motion and improved performance. Project website: https://teee000.github.io/ABPolicy/.

---

### Experience-Guided Self-Adaptive Cascaded Agents for Breast Cancer Screening and Diagnosis with Reduced Biopsy Referrals

Authors: Pramit Saha, Mohammad Alsharid, Joshua Strong, J. Alison Noble
Published: 2026-02-27
Categories: cs.CV, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2602.23899v1

We propose an experience-guided cascaded multi-agent framework for Breast Ultrasound Screening and Diagnosis, called BUSD-Agent, that aims to reduce diagnostic escalation and unnecessary biopsy referrals. Our framework models screening and diagnosis as a two-stage, selective decision-making process. A lightweight `screening clinic' agent, restricted to classification models as tools, selectively filters out benign and normal cases from further diagnostic escalation when malignancy risk and uncertainty are estimated as low. Cases that have higher risks are escalated to the `diagnostic clinic' agent, which integrates richer perception and radiological description tools to make a secondary decision on biopsy referral. To improve agent performance, past records of pathology-confirmed outcomes along with image embeddings, model predictions, and historical agent actions are stored in a memory bank as structured decision trajectories. For each new case, BUSD-Agent retrieves similar past cases based on image, model response and confidence similarity to condition the agent's current decision policy. This enables retrieval-conditioned in-context adaptation that dynamically adjusts model trust and escalation thresholds from prior experiences without parameter updates. Evaluation across 10 breast ultrasound datasets shows that the proposed experience-guided workflow reduces diagnostic escalation in BUSD-Agent from 84.95% to 58.72% and overall biopsy referrals from 59.50% to 37.08%, compared to the same architecture without trajectory conditioning, while improving average screening specificity by 68.48% and diagnostic specificity by 6.33%.

---

### Ref-Adv: Exploring MLLM Visual Reasoning in Referring Expression Tasks

Authors: Qihua Dong, Kuo Yang, Lin Ju, Handong Zhao, Yitian Zhang, Yizhou Wang, Huimin Zeng, Jianglin Lu, Yun Fu
Published: 2026-02-27
Categories: cs.CV, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2602.23898v1

Referring Expression Comprehension (REC) links language to region level visual perception. Standard benchmarks (RefCOCO, RefCOCO+, RefCOCOg) have progressed rapidly with multimodal LLMs but remain weak tests of visual reasoning and grounding: (i) many expressions are very short, leaving little reasoning demand; (ii) images often contain few distractors, making the target easy to find; and (iii) redundant descriptors enable shortcut solutions that bypass genuine text understanding and visual reasoning. We introduce Ref-Adv, a modern REC benchmark that suppresses shortcuts by pairing linguistically nontrivial expressions with only the information necessary to uniquely identify the target. The dataset contains referring expressions on real images, curated with hard distractors and annotated with reasoning facets including negation. We conduct comprehensive ablations (word order perturbations and descriptor deletion sufficiency) to show that solving Ref-Adv requires reasoning beyond simple cues, and we evaluate a broad suite of contemporary multimodal LLMs on Ref-Adv. Despite strong results on RefCOCO, RefCOCO+, and RefCOCOg, models drop markedly on Ref-Adv, revealing reliance on shortcuts and gaps in visual reasoning and grounding. We provide an in depth failure analysis and aim for Ref-Adv to guide future work on visual reasoning and grounding in MLLMs.

---

### SelfOccFlow: Towards end-to-end self-supervised 3D Occupancy Flow prediction

Authors: Xavier Timoneda, Markus Herb, Fabian Duerr, Daniel Goehring
Published: 2026-02-27
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.23894v1

Estimating 3D occupancy and motion at the vehicle's surroundings is essential for autonomous driving, enabling situational awareness in dynamic environments. Existing approaches jointly learn geometry and motion but rely on expensive 3D occupancy and flow annotations, velocity labels from bounding boxes, or pretrained optical flow models. We propose a self-supervised method for 3D occupancy flow estimation that eliminates the need for human-produced annotations or external flow supervision. Our method disentangles the scene into separate static and dynamic signed distance fields and learns motion implicitly through temporal aggregation. Additionally, we introduce a strong self-supervised flow cue derived from features' cosine similarities. We demonstrate the efficacy of our 3D occupancy flow method on SemanticKITTI, KITTI-MOT, and nuScenes.

---

### AoE: Always-on Egocentric Human Video Collection for Embodied AI

Authors: Bowen Yang, Zishuo Li, Yang Sun, Changtao Miao, Yifan Yang, Man Luo, Xiaotong Yan, Feng Jiang, Jinchuan Shi, Yankai Fu, Ning Chen, Junkai Zhao et al.
Published: 2026-02-27
Categories: cs.CV, cs.RO
arXiv: https://arxiv.org/abs/2602.23893v2

Embodied foundation models require large-scale, high-quality real-world interaction data for pre-training and scaling. However, existing data collection methods suffer from high infrastructure costs, complex hardware dependencies, and limited interaction scope, making scalable expansion challenging. In fact, humans themselves are ideal physically embodied agents. Therefore, obtaining egocentric real-world interaction data from globally distributed "human agents" offers advantages of low cost and sustainability. To this end, we propose the Always-on Egocentric (AoE) data collection system, which aims to simplify hardware dependencies by leveraging humans themselves and their smartphones, enabling low-cost, highly efficient, and scene-agnostic real-world interaction data collection to address the challenge of data scarcity. Specifically, we first employ an ergonomic neck-mounted smartphone holder to enable low-barrier, large-scale egocentric data collection through a cloud-edge collaborative architecture. Second, we develop a cross-platform mobile APP that leverages on-device compute for real-time processing, while the cloud hosts automated labeling and filtering pipelines that transform raw videos into high-quality training data. Finally, the AoE system supports distributed Ego video data collection by anyone, anytime, and anywhere. We evaluate AoE on data preprocessing quality and downstream tasks, demonstrating that high-quality egocentric data significantly boosts real-world generalization.

---

### DACESR: Degradation-Aware Conditional Embedding for Real-World Image Super-Resolution

Authors: Xiaoyan Lei, Wenlong Zhang, Biao Luo, Hui Liang, Weifeng Cao, Qiuting Lin
Published: 2026-02-27
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.23890v1

Multimodal large models have shown excellent ability in addressing image super-resolution in real-world scenarios by leveraging language class as condition information, yet their abilities in degraded images remain limited. In this paper, we first revisit the capabilities of the Recognize Anything Model (RAM) for degraded images by calculating text similarity. We find that directly using contrastive learning to fine-tune RAM in the degraded space is difficult to achieve acceptable results. To address this issue, we employ a degradation selection strategy to propose a Real Embedding Extractor (REE), which achieves significant recognition performance gain on degraded image content through contrastive learning. Furthermore, we use a Conditional Feature Modulator (CFM) to incorporate the high-level information of REE for a powerful Mamba-based network, which can leverage effective pixel information to restore image textures and produce visually pleasing results. Extensive experiments demonstrate that the REE can effectively help image super-resolution networks balance fidelity and perceptual quality, highlighting the great potential of Mamba in real-world applications. The source code of this work will be made publicly available at: https://github.com/nathan66666/DACESR.git

---

### Uncovering sustainable personal care ingredient combinations using scientific modelling

Authors: Sandip Bhattacharya, Vanessa da Silva, Christina Kohlmann
Published: 2026-02-27
Categories: physics.chem-ph, cs.AI, stat.AP
arXiv: https://arxiv.org/abs/2602.23887v1

Personal care formulations often contain synthetic and non-biodegradable ingredients, such as silicone and mineral oils, which can offer a unique performance. However, due to regulations like the EU ban of Octamethylcyclotetrasiloxane (D4), Decamethyl-cyclopentasiloxane (D5), Dodecamethylcyclohexasiloxane (D6) already in effect for rinse off and for leave on cosmetics by June 2027 coupled with growing consumer awareness and expectations on sustainability, personal care brands face significant pressure to replace these synthetic ingredients with natural alternatives without compromising performance and cost. As a result, formulators are confronted with the challenge to find natural-based solutions within a short timeframe. In this study, we propose a pioneering approach that utilizes predicting modelling and simulation-based digital services to obtain natural-based ingredient combinations as recommendations to commonly used synthetic ingredients. We will demonstrate the effectiveness of our predictions through the application of these proposals in specific formulations. By offering a platform of digital services, it is aimed to empower formulators to explore good performing novel and environmentally friendly alternatives, ultimately driving a substantial and genuine transformation in the personal care industry.

---

### LK Losses: Direct Acceptance Rate Optimization for Speculative Decoding

Authors: Alexander Samarin, Sergei Krutikov, Anton Shevtsov, Sergei Skvortsov, Filipp Fisin, Alexander Golubev
Published: 2026-02-27
Categories: cs.LG, cs.CL
arXiv: https://arxiv.org/abs/2602.23881v2

Speculative decoding accelerates autoregressive large language model (LLM) inference by using a lightweight draft model to propose candidate tokens that are then verified in parallel by the target model. The speedup is significantly determined by the acceptance rate, yet standard training minimizes Kullback-Leibler (KL) divergence as a proxy objective. While KL divergence and acceptance rate share the same global optimum, small draft models, having limited capacity, typically converge to suboptimal solutions where minimizing KL does not guarantee maximizing acceptance rate. To address this issue, we propose LK losses, special training objectives that directly target acceptance rate. Comprehensive experiments across four draft architectures and six target models, ranging from 8B to 685B parameters, demonstrate consistent improvements in acceptance metrics across all configurations compared to the standard KL-based training. We evaluate our approach on general, coding and math domains and report gains of up to 8-10% in average acceptance length. LK losses are easy to implement, introduce no computational overhead and can be directly integrated into any existing speculator training framework, making them a compelling alternative to the existing draft training objectives.

---

### A Theory of Random Graph Shift in Truncated-Spectrum vRKHS

Authors: Zhang Wan, Tingting Mu, Samuel Kaski
Published: 2026-02-27
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.23880v1

This paper develops a theory of graph classification under domain shift through a random-graph generative lens, where we consider intra-class graphs sharing the same random graph model (RGM) and the domain shift induced by changes in RGM components. While classic domain adaptation (DA) theories have well-underpinned existing techniques to handle graph distribution shift, the information of graph samples, which are itself structured objects, is less explored. The non-Euclidean nature of graphs and specialized architectures for graph learning further complicate a fine-grained analysis of graph distribution shifts. In this paper, we propose a theory that assumes RGM as the data generative process, exploiting its connection to hypothesis complexity in function space perspective for such fine-grained analysis. Building on a vector-valued reproducing kernel Hilbert space (vRKHS) formulation, we derive a generalization bound whose shift penalty admits a factorization into (i) a domain discrepancy term, (ii) a spectral-geometry term summarized by the accessible truncated spectrum, and (iii) an amplitude term that aggregates convergence and construction-stability effects. We empirically verify the insights on these terms in both real data and simulations.

---

### RF-Agent: Automated Reward Function Design via Language Agent Tree Search

Authors: Ning Gao, Xiuhui Zhang, Xingyu Jiang, Mukang You, Mohan Zhang, Yue Deng
Published: 2026-02-27
Categories: cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2602.23876v1

Designing efficient reward functions for low-level control tasks is a challenging problem. Recent research aims to reduce reliance on expert experience by using Large Language Models (LLMs) with task information to generate dense reward functions. These methods typically rely on training results as feedback, iteratively generating new reward functions with greedy or evolutionary algorithms. However, they suffer from poor utilization of historical feedback and inefficient search, resulting in limited improvements in complex control tasks. To address this challenge, we propose RF-Agent, a framework that treats LLMs as language agents and frames reward function design as a sequential decision-making process, enhancing optimization through better contextual reasoning. RF-Agent integrates Monte Carlo Tree Search (MCTS) to manage the reward design and optimization process, leveraging the multi-stage contextual reasoning ability of LLMs. This approach better utilizes historical information and improves search efficiency to identify promising reward functions. Outstanding experimental results in 17 diverse low-level control tasks demonstrate the effectiveness of our method. The source code is available at https://github.com/deng-ai-lab/RF-Agent.

---

### Exploring Robust Intrusion Detection: A Benchmark Study of Feature Transferability in IoT Botnet Attack Detection

Authors: Alejandro Guerra-Manzanares, Jialin Huang
Published: 2026-02-27
Categories: cs.CR, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2602.23874v1

Cross-domain intrusion detection remains a critical challenge due to significant variability in network traffic characteristics and feature distributions across environments. This study evaluates the transferability of three widely used flow-based feature sets (Argus, Zeek and CICFlowMeter) across four widely used datasets representing heterogeneous IoT and Industrial IoT network conditions. Through extensive experiments, we evaluate in- and cross-domain performance across multiple classification models and analyze feature importance using SHapley Additive exPlanations (SHAP). Our results show that models trained on one domain suffer significant performance degradation when applied to a different target domain, reflecting the sensitivity of IoT intrusion detection systems to distribution shifts. Furthermore, the results evidence that the choice of classification algorithm and feature representations significantly impact transferability. Beyond reporting performance differences and thorough analysis of the transferability of features and feature spaces, we provide practical guidelines for feature engineering to improve robustness under domain variability. Our findings suggest that effective intrusion detection requires both high in-domain performance and resilience to cross-domain variability, achievable through careful feature space design, appropriate algorithm selection and adaptive strategies.

---

### Altitude-Adaptive Vision-Only Geo-Localization for UAVs in GPS-Denied Environments

Authors: Xingyu Shao, Mengfan He, Liangzheng Sun, Chunyu Li, Ziyang Meng
Published: 2026-02-27
Categories: cs.CV, cs.RO
arXiv: https://arxiv.org/abs/2602.23872v4

Matching downward-looking unmanned aerial vehicle (UAV) images to georeferenced satellite or aerial map tiles supports local earth observation, map-based interpretation, and coarse geo-initialization when direct positioning signals are degraded or unavailable. A major difficulty in this cross-platform matching task is the scale mismatch caused by large variations in UAV altitude. To address this problem, we propose an altitude-adaptive aerial visual place recognition framework. The method first estimates relative altitude from a single downward-looking image by transforming the input into the frequency domain and formulating altitude estimation as a regression-as-classification problem. The estimated altitude is then used to crop the query image to a canonical scale, after which a classification-then-retrieval visual place recognition module performs coarse map localization. To improve retrieval robustness under varying image quality, we further introduce a quality-adaptive margin classifier and refine the final location by weighted coordinate estimation over the top retrieved candidates. Experiments on two synthetic datasets and two real-flight datasets show that the relative altitude estimation module improves downstream retrieval performance under substantial altitude changes. With our visual place recognition module, altitude adaptation improves average R@1 and R@5 by 41.50 and 56.83 percentage points, respectively, compared with using the same retrieval pipeline without altitude normalization, and the main retrieval pipeline runs at 13.3 frames/s on the workstation used for evaluation. These results indicate that relative altitude estimation provides a useful scale prior for cross-altitude UAV-to-map image matching using georeferenced remote sensing imagery.

---

### Bandwidth-adaptive Cloud-Assisted 360-Degree 3D Perception for Autonomous Vehicles

Authors: Faisal Hawladera, Rui Meireles, Gamal Elghazaly, Ana Aguiar, Raphaël Frank
Published: 2026-02-27
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2602.23871v1

A key challenge for autonomous driving lies in maintaining real-time situational awareness regarding surrounding obstacles under strict latency constraints. The high processing requirements coupled with limited onboard computational resources can cause delay issues, particularly in complex urban settings. To address this, we propose leveraging Vehicle-to-Everything (V2X) communication to partially offload processing to the cloud, where compute resources are abundant, thus reducing overall latency. Our approach utilizes transformer-based models to fuse multi-camera sensor data into a comprehensive Bird's-Eye View (BEV) representation, enabling accurate 360-degree 3D object detection. The computation is dynamically split between the vehicle and the cloud based on the number of layers processed locally and the quantization level of the features. To further reduce network load, we apply feature vector clipping and compression prior to transmission. In a real-world experimental evaluation, our hybrid strategy achieved a 72 \% reduction in end-to-end latency compared to a traditional onboard solution. To adapt to fluctuating network conditions, we introduce a dynamic optimization algorithm that selects the split point and quantization level to maximize detection accuracy while satisfying real-time latency constraints. Trace-based evaluation under realistic bandwidth variability shows that this adaptive approach improves accuracy by up to 20 \% over static parameterization with the same latency performance.

---

### Open-Vocabulary Semantic Segmentation in Remote Sensing via Hierarchical Attention Masking and Model Composition

Authors: Mohammadreza Heidarianbaei, Mareike Dorozynski, Hubert Kanyamahanga, Max Mehltretter, Franz Rottensteiner
Published: 2026-02-27
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.23869v1

In this paper, we propose ReSeg-CLIP, a new training-free Open-Vocabulary Semantic Segmentation method for remote sensing data. To compensate for the problems of vision language models, such as CLIP in semantic segmentation caused by inappropriate interactions within the self-attention layers, we introduce a hierarchical scheme utilizing masks generated by SAM to constrain the interactions at multiple scales. We also present a model composition approach that averages the parameters of multiple RS-specific CLIP variants, taking advantage of a new weighting scheme that evaluates representational quality using varying text prompts. Our method achieves state-of-the-art results across three RS benchmarks without additional training.

---

### SWE-rebench V2: Language-Agnostic SWE Task Collection at Scale

Authors: Ibragim Badertdinov, Maksim Nekrashevich, Anton Shevtsov, Alexander Golubev
Published: 2026-02-27
Categories: cs.SE, cs.CL
arXiv: https://arxiv.org/abs/2602.23866v2

Software engineering agents (SWE) are improving rapidly, with recent gains largely driven by reinforcement learning (RL). However, RL training is constrained by the scarcity of large-scale task collections with reproducible execution environments and reliable test suites. Although a growing number of benchmarks have emerged, datasets suitable for training remain limited in scale and diversity or often target a limited set of high-resource language ecosystems. We introduce SWE-rebench V2, a language-agnostic automated pipeline for harvesting executable real-world SWE tasks and constructing RL training environments at scale. The pipeline synthesizes repository-specific installation and test procedures via an interactive setup agent, and filters unsound instances using an ensemble of LLM judges, validated against human-verified SWE-bench annotations. Using this pipeline, we construct a dataset of 32,079 tasks spanning 20 languages and 3,617 repositories, with pre-built images for reproducible execution. To further scale training data, we additionally release 120,000+ tasks with installation instructions, fail-to-pass tests and rich metadata, where the problem statement is generated based on the original pull request description. We validate the collected instances through a diagnostic study that covers a subset of tasks in five programming languages across seven popular models, and provide instance-level metadata that flags common confounders such as overly restrictive tests and underspecified descriptions. We release the datasets, the collection and execution code, and associated artifacts to enable large-scale training of SWE agents across diverse languages and repositories.

---

### RUMAD: Reinforcement-Unifying Multi-Agent Debate

Authors: Chao Wang, Han Lin, Huaze Tang, Huijing Lin, Wenbo Ding
Published: 2026-02-27
Categories: cs.AI
arXiv: https://arxiv.org/abs/2602.23864v1

Multi-agent debate (MAD) systems leverage collective intelligence to enhance reasoning capabilities, yet existing approaches struggle to simultaneously optimize accuracy, consensus formation, and computational efficiency. Static topology methods lack adaptability to task complexity variations, while external LLM-based coordination risks introducing privileged knowledge that compromises debate neutrality. This work presents RUMAD (Reinforcement-Unifying Multi-Agent Debate), a novel framework that formulates dynamic communication topology control in MAD as a reinforcement learning (RL) problem. RUMAD employs a content-agnostic observation scheme that captures high-level debate dynamics avoiding access to raw agent reasoning content. RUMAD uses a multi-objective reward to model solution quality, cohesion and efficiency. A PPO-trained controller dynamically adjusts edge weights in the communication graph, while a dual-threshold mechanism enables fine-grained control over both agent activation and information visibility. Experimental evaluation across MMLU, GSM8K, and GPQA benchmarks demonstrates that RUMAD achieves substantial efficiency gains, reducing token costs by over 80\%, while still improving reasoning accuracy compared to single LLM model and multiple MAD baselines. Notably, RUMAD trained exclusively on MMLU exhibits robust zero-shot generalization to out-of-domain (OOD) tasks, indicating that the learned communication strategies capture task-independent principles of effective multi-agent coordination. These results establish RUMAD as a efficient and robust approach for deploying multi-agent reasoning application with practical resource constraints.

---

### NAU-QMUL: Utilizing BERT and CLIP for Multi-modal AI-Generated Image Detection

Authors: Xiaoyu Guo, Arkaitz Zubiaga
Published: 2026-02-27
Categories: cs.CV, cs.CL
arXiv: https://arxiv.org/abs/2602.23863v1

With the aim of detecting AI-generated images and identifying the specific models responsible for their generation, we propose a multi-modal multi-task model. The model leverages pre-trained BERT and CLIP Vision encoders for text and image feature extraction, respectively, and employs cross-modal feature fusion with a tailored multi-task loss function. Additionally, a pseudo-labeling-based data augmentation strategy was utilized to expand the training dataset with high-confidence samples. The model achieved fifth place in both Tasks A and B of the `CT2: AI-Generated Image Detection' competition, with F1 scores of 83.16\% and 48.88\%, respectively. These findings highlight the effectiveness of the proposed architecture and its potential for advancing AI-generated content detection in real-world scenarios. The source code for our method is published on https://github.com/xxxxxxxxy/AIGeneratedImageDetection.

---

### A distributed semismooth Newton based augmented Lagrangian method for distributed optimization

Authors: Qihao Ma, Chengjing Wang, Peipei Tang, Dunbiao Niu, Aimin Xu
Published: 2026-02-27
Categories: math.OC, cs.LG, math.NA, stat.ML
arXiv: https://arxiv.org/abs/2602.23854v1

This paper proposes a novel distributed semismooth Newton based augmented Lagrangian method for solving a class of optimization problems over networks, where the global objective is defined as the sum of locally held cost functions, and communication is restricted to neighboring agents. Specifically, we employ the augmented Lagrangian method to solve an equivalently reformulated constrained version of the original problem. Each resulting subproblem is solved inexactly via a distributed semismooth Newton method. By fully leveraging the structure of the generalized Hessian, a distributed accelerated proximal gradient method is proposed to compute the Newton direction efficiently, eliminating the need to communicate with full Hessian matrices. Theoretical results are also obtained to guarantee the convergence of the proposed algorithm. Numerical experiments demonstrate the efficiency and superiority of our algorithm compared to state-of-the-art distributed algorithms.

---

### ULW-SleepNet: An Ultra-Lightweight Network for Multimodal Sleep Stage Scoring

Authors: Zhaowen Wang, Dongdong Zhou, Qi Xu, Fengyu Cong, Mohammad Al-Sa'd, Jenni Raitoharju
Published: 2026-02-27
Categories: cs.LG, eess.SP
arXiv: https://arxiv.org/abs/2602.23852v1

Automatic sleep stage scoring is crucial for the diagnosis and treatment of sleep disorders. Although deep learning models have advanced the field, many existing models are computationally demanding and designed for single-channel electroencephalography (EEG), limiting their practicality for multimodal polysomnography (PSG) data. To overcome this, we propose ULW-SleepNet, an ultra-lightweight multimodal sleep stage scoring framework that efficiently integrates information from multiple physiological signals. ULW-SleepNet incorporates a novel Dual-Stream Separable Convolution (DSSC) Block, depthwise separable convolutions, channel-wise parameter sharing, and global average pooling to reduce computational overhead while maintaining competitive accuracy. Evaluated on the Sleep-EDF-20 and Sleep-EDF-78 datasets, ULW-SleepNet achieves accuracies of 86.9% and 81.4%, respectively, with only 13.3K parameters and 7.89M FLOPs. Compared to state-of-the-art methods, our model reduces parameters by up to 98.6% with only marginal performance loss, demonstrating its strong potential for real-time sleep monitoring on wearable and IoT devices. The source code for this study is publicly available at https://github.com/wzw999/ULW-SLEEPNET.

---

### Polarization Uncertainty-Guided Diffusion Model for Color Polarization Image Demosaicking

Authors: Chenggong Li, Yidong Luo, Junchao Zhang, Degui Yang
Published: 2026-02-27
Categories: eess.IV, cs.CV
arXiv: https://arxiv.org/abs/2602.23847v1

Color polarization demosaicking (CPDM) aims to reconstruct full-resolution polarization images of four directions from the color-polarization filter array (CPFA) raw image. Due to the challenge of predicting numerous missing pixels and the scarcity of high-quality training data, existing network-based methods, despite effectively recovering scene intensity information, still exhibit significant errors in reconstructing polarization characteristics (degree of polarization, DOP, and angle of polarization, AOP). To address this problem, we introduce the image diffusion prior from text-to-image (T2I) models to overcome the performance bottleneck of network-based methods, with the additional diffusion prior compensating for limited representational capacity caused by restricted data distribution. To effectively leverage the diffusion prior, we explicitly model the polarization uncertainty during reconstruction and use uncertainty to guide the diffusion model in recovering high error regions. Extensive experiments demonstrate that the proposed method accurately recovers scene polarization characteristics with both high fidelity and strong visual perception.

---

### MI$^2$DAS: A Multi-Layer Intrusion Detection Framework with Incremental Learning for Securing Industrial IoT Networks

Authors: Wei Lian, Alejandro Guerra-Manzanares
Published: 2026-02-27
Categories: cs.CR, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2602.23846v1

The rapid expansion of Industrial IoT (IIoT) systems has amplified security challenges, as heterogeneous devices and dynamic traffic patterns increase exposure to sophisticated and previously unseen cyberattacks. Traditional intrusion detection systems often struggle in such environments due to their reliance on extensive labeled data and limited ability to detect new threats. To address these challenges, we propose MI$^2$DAS, a multi-layer intrusion detection framework that integrates anomaly-based hierarchical traffic pooling, open-set recognition to distinguish between known and unknown attacks and incremental learning for adapting to novel attack types with minimal labeling. Experiments conducted on the Edge-IIoTset dataset demonstrate strong performance across all layers. In the first layer, GMM achieves superior normal-attack discrimination (accuracy = 0.953, TPR = 1.000). In open-set recognition, GMM attains a recall of 0.813 for known attacks, while LOF achieves 0.882 recall for unknown attacks. For fine-grained classification of known attacks, Random Forest achieves a macro-F1 of 0.941. Finally, the incremental learning module maintains robust performance when incorporation novel attack classes, achieving a macro-F1 of 0.8995. These results showcase MI$^2$DAS as an effective, scalable and adaptive framework for enhancing IIoT security against evolving threats.

---

### CLFEC: A New Task for Unified Linguistic and Factual Error Correction in paragraph-level Chinese Professional Writing

Authors: Jian Kai, Zidong Zhang, Jiwen Chen, Zhengxiang Wu, Songtao Sun, Fuyang Li, Yang Cao, Qiang Liu
Published: 2026-02-27
Categories: cs.CL
arXiv: https://arxiv.org/abs/2602.23845v2

Chinese text correction has traditionally focused on spelling and grammar, while factual error correction is usually treated separately. However, in paragraph-level Chinese professional writing, linguistic (word/grammar/punctuation) and factual errors frequently co-occur and interact, while many draft-level errors are sparsely observable in published texts after editorial review, making unified correction both necessary and controlled benchmark construction essential. This paper introduces CLFEC (Chinese Linguistic \& Factual Error Correction), a new task for joint linguistic and factual correction. We construct a mixed, multi-domain Chinese professional writing dataset spanning current affairs, finance, law, and medicine. We then conduct a systematic study of LLM-based correction paradigms, from prompting to retrieval-augmented generation (RAG) and agentic workflows. The analysis reveals practical challenges, including limited generalization of specialized correction models, the need for evidence grounding for factual repair, the difficulty of mixed-error paragraphs, and over-correction on clean inputs. Results further show that handling linguistic and factual errors within the same context outperforms decoupled pipelines, and that agentic workflows can be effective with suitable backbone models. Overall, CLFEC provides a new benchmark for Chinese text correction research and practical guidance for proofreading systems.

---

### Enhancing Continual Learning for Software Vulnerability Prediction: Addressing Catastrophic Forgetting via Hybrid-Confidence-Aware Selective Replay for Temporal LLM Fine-Tuning

Authors: Xuhui Dou, Hayretdin Bahsi, Alejandro Guerra-Manzanares
Published: 2026-02-27
Categories: cs.CR, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2602.23834v1

Recent work applies Large Language Models (LLMs) to source-code vulnerability detection, but most evaluations still rely on random train-test splits that ignore time and overestimate real-world performance. In practice, detectors are deployed on evolving code bases and must recognise future vulnerabilities under temporal distribution shift. This paper investigates continual fine-tuning of a decoder-style language model (microsoft/phi-2 with LoRA) on a CVE-linked dataset spanning 2018-2024, organised into bi-monthly windows. We evaluate eight continual learning strategies, including window-only and cumulative training, replay-based baselines and regularisation-based variants. We propose Hybrid Class-Aware Selective Replay (Hybrid-CASR), a confidence-aware replay method for binary vulnerability classification that prioritises uncertain samples while maintaining a balanced ratio of VULNERABLE and FIXED functions in the replay buffer. On bi-monthly forward evaluation Hybrid-CASR achieves a Macro-F1 of 0.667, improving on the window-only baseline (0.651) by 0.016 with statistically significant gains ($p = 0.026$) and stronger backward retention (IBR@1 of 0.741). Hybrid-CASR also reduces training time per window by about 17 percent compared to the baseline, whereas cumulative training delivers only a minor F1 increase (0.661) at a 15.9-fold computational cost. Overall, the results show that selective replay with class balancing offers a practical accuracy-efficiency trade-off for LLM-based temporal vulnerability detection under continuous temporal drift.

---

### Revisiting Integration of Image and Metadata for DICOM Series Classification: Cross-Attention and Dictionary Learning

Authors: Tuan Truong, Melanie Dohmen, Sara Lorio, Matthias Lenga
Published: 2026-02-27
Categories: eess.IV, cs.CV
arXiv: https://arxiv.org/abs/2602.23833v2

Automated identification of DICOM image series is essential for large-scale medical image analysis, quality control, protocol harmonization, and reliable downstream processing. However, DICOM series classification remains challenging due to heterogeneous slice content, variable series length, and entirely missing, incomplete or inconsistent DICOM metadata. We propose an end-to-end multimodal framework for DICOM series classification that jointly models image content and acquisition metadata while explicitly accounting for all these challenges. (i) Images and metadata are encoded with modality-aware modules and fused using a bi-directional cross-modal attention mechanism. (ii) Metadata is processed by a sparse, missingness-aware encoder based on learnable feature dictionaries and value-conditioned modulation. By design, the approach does not require any form of imputation. (iii) Variability in series length and image data dimensions is handled via a 2.5D visual encoder and attention operating on equidistantly sampled slices. We evaluate the proposed approach on the publicly available Duke Liver MRI dataset and a large multi-institutional in-house cohort, assessing both in-domain performance and out-of-domain generalization. Across all evaluation settings, the proposed method consistently outperforms relevant image only, metadata-only and multimodal 2D/3D baselines. The results demonstrate that explicitly modeling metadata sparsity and cross-modal interactions improves robustness for DICOM series classification.

---

### FedNSAM:Consistency of Local and Global Flatness for Federated Learning

Authors: Junkang Liu, Fanhua Shang, Yuxuan Tian, Hongying Liu, Yuanyuan Liu
Published: 2026-02-27
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2602.23827v1

In federated learning (FL), multi-step local updates and data heterogeneity usually lead to sharper global minima, which degrades the performance of the global model. Popular FL algorithms integrate sharpness-aware minimization (SAM) into local training to address this issue. However, in the high data heterogeneity setting, the flatness in local training does not imply the flatness of the global model. Therefore, minimizing the sharpness of the local loss surfaces on the client data does not enable the effectiveness of SAM in FL to improve the generalization ability of the global model. We define the \textbf{flatness distance} to explain this phenomenon. By rethinking the SAM in FL and theoretically analyzing the \textbf{flatness distance}, we propose a novel \textbf{FedNSAM} algorithm that accelerates the SAM algorithm by introducing global Nesterov momentum into the local update to harmonize the consistency of global and local flatness. \textbf{FedNSAM} uses the global Nesterov momentum as the direction of local estimation of client global perturbations and extrapolation. Theoretically, we prove a tighter convergence bound than FedSAM by Nesterov extrapolation. Empirically, we conduct comprehensive experiments on CNN and Transformer models to verify the superior performance and efficiency of \textbf{FedNSAM}. The code is available at https://github.com/junkangLiu0/FedNSAM.

---

### GLUScope: A Tool for Analyzing GLU Neurons in Transformer Language Models

Authors: Sebastian Gerstner, Hinrich Schütze
Published: 2026-02-27
Categories: cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2602.23826v1

We present GLUScope, an open-source tool for analyzing neurons in Transformer-based language models, intended for interpretability researchers. We focus on more recent models than previous tools do; specifically we consider gated activation functions such as SwiGLU. This introduces a new challenge: understanding positive activations is not enough. Instead, both the gate and the in activation of a neuron can be positive or negative, leading to four different possible sign combinations that in some cases have quite different functionalities. Accordingly, for any neuron, our tool shows text examples for each of the four sign combinations, and indicates how often each combination occurs. We describe examples of how our tool can lead to novel insights. A demo is available at https: //sjgerstner.github.io/gluscope.

---

### Inferring Chronic Treatment Onset from ePrescription Data: A Renewal Process Approach

Authors: Pavlin G. Poličar, Dalibor Stanimirović, Blaž Zupan
Published: 2026-02-27
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.23824v1

Longitudinal electronic health record (EHR) data are often left-censored, making diagnosis records incomplete and unreliable for determining disease onset. In contrast, outpatient prescriptions form renewal-based trajectories that provide a continuous signal of disease management. We propose a probabilistic framework to infer chronic treatment onset by modeling prescription dynamics as a renewal process and detecting transitions from sporadic to sustained therapy via change-point detection between a baseline Poisson (sporadic prescribing) regime and a regime-specific Weibull (sustained therapy) renewal model. Using a nationwide ePrescription dataset of 2.4 million individuals, we show that the approach yields more temporally plausible onset estimates than naive rule-based triggering, substantially reducing implausible early detections under strong left censoring. Detection performance varies across diseases and is strongly associated with prescription density, highlighting both the strengths and limits of treatment-based onset inference.

---

### APPO: Attention-guided Perception Policy Optimization for Video Reasoning

Authors: Henghui Du, Chang Zhou, Xi Chen, Di Hu
Published: 2026-02-27
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.23823v2

Complex video reasoning, actually, relies excessively on fine-grained perception rather than on expert (e.g., Ph.D, Science)-level reasoning. Through extensive empirical observation, we have recognized the critical impact of perception. In particular, when perception ability is almost fixed, enhancing reasoning from Qwen3-8B to OpenAI-o3 yields only 0.7% performance improvement. Conversely, even minimal change in perception model scale (from 7B to 32B) boosts performance by 1.4%, indicating enhancing perception, rather than reasoning, is more critical to improve performance. Therefore, exploring how to enhance perception ability through reasoning without the need for expensive fine-grained annotation information is worthwhile. To achieve this goal, we specially propose APPO, the Attention-guided Perception Policy Optimization algorithm that leverages token-level dense rewards to improve model's fine-grained perception. The core idea behind APPO is to optimize those tokens from different responses that primarily focus on the same crucial video frame (called intra-group perception tokens). Experimental results on diverse video benchmarks and models with different scales (3/7B) demonstrate APPO consistently outperforms GRPO and DAPO (0.5%~4%). We hope our work provides a promising approach to effectively enhance model's perception abilities through reasoning in a low-cost manner, serving diverse scenarios and demands.

---

### RSTNet: Enhancing Small-Target Recognition in Noisy SAR Imagery via Robust Feature Learning and Distribution-Aware Regression

Authors: Xiaojing Zhao, Shiyang Li, Zenan Chu, Ying Zhang, Peinan Hao, Tianzi Yan, Jiajia Chen, Huicong Ning
Published: 2026-02-27
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.23820v2

SAR supports all-day-and-night oceanic observation, yet vessel identification from SAR images is hampered by speckle noise, intricate land-sea backgrounds and dim miniature vessels, yielding numerous false identifications and missed targets. We develop an SAR-adaptive stable detection model RSTNet based on YOLOv8. A large-kernel channel-separated denoising unit eliminates noise and reserves delicate vessel features; parallel patch-aware attention enhances multi-scale feature extraction for miniature objects; NWD loss substitutes conventional IoU loss to achieve accurate bounding box regression. The proposed model outperforms the original YOLOv8 on the SSDD dataset with 97.0% precision, 95.1% recall and 98.9% mAP@0.5. Validations on the HRSID dataset verify its favorable generalization capacity for coastal miniature vessels. Therefore, our work delivers an effective technical scheme for ocean observation imaging with noisy miniature targets. The source code is available at https://github.com/renhcmhx/SAR.git.

---

### Footprint-Guided Exemplar-Free Continual Histopathology Report Generation

Authors: Pratibha Kumari, Daniel Reisenbüchler, Afshin Bozorgpour, yousef Sadegheih, Priyankar Choudhary, Dorit Merhof
Published: 2026-02-27
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.23817v1

Rapid progress in vision-language modeling has enabled pathology report generation from gigapixel whole-slide images, but most approaches assume static training with simultaneous access to all data. In clinical deployment, however, new organs, institutions, and reporting conventions emerge over time, and sequential fine-tuning can cause catastrophic forgetting. We introduce an exemplar-free continual learning framework for WSI-to-report generation that avoids storing raw slides or patch exemplars. The core idea is a compact domain footprint built in a frozen patch-embedding space: a small codebook of representative morphology tokens together with slide-level co-occurrence summaries and lightweight patch-count priors. These footprints support generative replay by synthesizing pseudo-WSI representations that reflect domain-specific morphological mixtures, while a teacher snapshot provides pseudo-reports to supervise the updated model without retaining past data. To address shifting reporting conventions, we distill domain-specific linguistic characteristics into a compact style descriptor and use it to steer generation. At inference, the model identifies the most compatible descriptor directly from the slide signal, enabling domain-agnostic setup without requiring explicit domain identifiers. Evaluated across multiple public continual learning benchmarks, our approach outperforms exemplar-free and limited-buffer rehearsal baselines, highlighting footprint-based generative replay as a practical solution for deployment in evolving clinical settings.

---

### Learning to maintain safety through expert demonstrations in settings with unknown constraints: A Q-learning perspective

Authors: George Papadopoulos, George A. Vouros
Published: 2026-02-27
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2602.23816v1

Given a set of trajectories demonstrating the execution of a task safely in a constrained MDP with observable rewards but with unknown constraints and non-observable costs, we aim to find a policy that maximizes the likelihood of demonstrated trajectories trading the balance between being conservative and increasing significantly the likelihood of high-rewarding trajectories but with potentially unsafe steps. Having these objectives, we aim towards learning a policy that maximizes the probability of the most $promising$ trajectories with respect to the demonstrations. In so doing, we formulate the ``promise" of individual state-action pairs in terms of $Q$ values, which depend on task-specific rewards as well as on the assessment of states' safety, mixing expectations in terms of rewards and safety. This entails a safe Q-learning perspective of the inverse learning problem under constraints: The devised Safe $Q$ Inverse Constrained Reinforcement Learning (SafeQIL) algorithm is compared to state-of-the art inverse constraint reinforcement learning algorithms to a set of challenging benchmark tasks, showing its merits.

---

### Action-Geometry Prediction with 3D Geometric Prior for Bimanual Manipulation

Authors: Chongyang Xu, Haipeng Li, Shen Cheng, Jingyu Hu, Haoqiang Fan, Ziliang Feng, Shuaicheng Liu
Published: 2026-02-27
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.23814v1

Bimanual manipulation requires policies that can reason about 3D geometry, anticipate how it evolves under action, and generate smooth, coordinated motions. However, existing methods typically rely on 2D features with limited spatial awareness, or require explicit point clouds that are difficult to obtain reliably in real-world settings. At the same time, recent 3D geometric foundation models show that accurate and diverse 3D structure can be reconstructed directly from RGB images in a fast and robust manner. We leverage this opportunity and propose a framework that builds bimanual manipulation directly on a pre-trained 3D geometric foundation model. Our policy fuses geometry-aware latents, 2D semantic features, and proprioception into a unified state representation, and uses diffusion model to jointly predict a future action chunk and a future 3D latent that decodes into a dense pointmap. By explicitly predicting how the 3D scene will evolve together with the action sequence, the policy gains strong spatial understanding and predictive capability using only RGB observations. We evaluate our method both in simulation on the RoboTwin benchmark and in real-world robot executions. Our approach consistently outperforms 2D-based and point-cloud-based baselines, achieving state-of-the-art performance in manipulation success, inter-arm coordination, and 3D spatial prediction accuracy. Code is available at https://github.com/Chongyang-99/GAP.git.

---

### Beyond State-Wise Mirror Descent: Offline Policy Optimization with Parametric Policies

Authors: Xiang Li, Yuheng Zhang, Nan Jiang
Published: 2026-02-27
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2602.23811v4

We investigate the theoretical aspects of offline reinforcement learning (RL) under general function approximation. While prior works (e.g., Xie et al., 2021) have established the theoretical foundations of learning a good policy from offline data via pessimism, existing algorithms that are computationally tractable (often in an oracle-efficient sense), such as PSPI, only apply to finite and small action spaces. Moreover, these algorithms rely on state-wise mirror descent and require actors to be implicitly induced from the critic functions, failing to accommodate standalone policy parameterization which is ubiquitous in practice. In this work, we address these limitations and extend the theoretical guarantees to parameterized policy classes over large or continuous action spaces. When extending mirror descent to parameterized policies, we identify contextual coupling as the core difficulty, and show how connecting mirror descent to natural policy gradient leads to novel analyses, guarantees, and algorithmic insights, including a surprising unification between offline RL and imitation learning.

---

### ReasonX: Declarative Reasoning on Explanations

Authors: Laura State, Salvatore Ruggieri, Franco Turini
Published: 2026-02-27
Categories: cs.CY, cs.LG
arXiv: https://arxiv.org/abs/2602.23810v1

Explaining opaque Machine Learning (ML) models has become an increasingly important challenge. However, current eXplanation in AI (XAI) methods suffer several shortcomings, including insufficient abstraction, limited user interactivity, and inadequate integration of symbolic knowledge. We propose ReasonX, an explanation tool based on expressions (or, queries) in a closed algebra of operators over theories of linear constraints. ReasonX provides declarative and interactive explanations for decision trees, which may represent the ML models under analysis or serve as global or local surrogate models for any black-box predictor. Users can express background or common sense knowledge as linear constraints. This allows for reasoning at multiple levels of abstraction, ranging from fully specified examples to under-specified or partially constrained ones. ReasonX leverages Mixed-Integer Linear Programming (MILP) to reason over the features of factual and contrastive instances. We present here the architecture of ReasonX, which consists of a Python layer, closer to the user, and a Constraint Logic Programming (CLP) layer, which implements a meta-interpreter of the query algebra. The capabilities of ReasonX are demonstrated through qualitative examples, and compared to other XAI tools through quantitative experiments.

---

### See, Act, Adapt: Active Perception for Unsupervised Cross-Domain Visual Adaptation via Personalized VLM-Guided Agent

Authors: Tianci Tang, Tielong Cai, Hongwei Wang, Gaoang Wang
Published: 2026-02-27
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2602.23806v1

Pre-trained perception models excel in generic image domains but degrade significantly in novel environments like indoor scenes. The conventional remedy is fine-tuning on downstream data which incurs catastrophic forgetting of prior knowledge and demands costly, scene-specific annotations. We propose a paradigm shift through Sea$^2$ (See, Act, Adapt): rather than adapting the perception modules themselves, we adapt how they are deployed through an intelligent pose-control agent. Sea$^2$ keeps all perception modules frozen, requiring no downstream labels during training, and uses only scalar perceptual feedback to navigate the agent toward informative viewpoints. Specially, we transform a vision-language model (VLM) into a low-level pose controller through a two-stage training pipeline: first fine-tuning it on rule-based exploration trajectories that systematically probe indoor scenes, and then refining the policy via unsupervised reinforcement learning that constructs rewards from the perception module's outputs and confidence. Unlike prior active perception methods that couple exploration with specific models or collect data for retraining them, Sea$^2$ directly leverages off-the-shelf perception models for various tasks without the need for retraining. We conducted experiments on three visual perception tasks, including visual grounding, segmentation and 3D box estimation, with performance improvements of 13.54%, 15.92% and 27.68% respectively on dataset ReplicaCAD.

---

### Actor-Critic Pretraining for Proximal Policy Optimization

Authors: Andreas Kernbach, Amr Elsheikh, Nicolas Grupp, René Nagel, Marco F. Huber
Published: 2026-02-27
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.23804v1

Reinforcement learning (RL) actor-critic algorithms enable autonomous learning but often require a large number of environment interactions, which limits their applicability in robotics. Leveraging expert data can reduce the number of required environment interactions. A common approach is actor pretraining, where the actor network is initialized via behavioral cloning on expert demonstrations and subsequently fine-tuned with RL. In contrast, the initialization of the critic network has received little attention, despite its central role in policy optimization. This paper proposes a pretraining approach for actor-critic algorithms like Proximal Policy Optimization (PPO) that uses expert demonstrations to initialize both networks. The actor is pretrained via behavioral cloning, while the critic is pretrained using returns obtained from rollouts of the pretrained policy. The approach is evaluated on 15 simulated robotic manipulation and locomotion tasks. Experimental results show that actor-critic pretraining improves sample efficiency by 86.1% on average compared to no pretraining and by 30.9% to actor-only pretraining.

---

### BiM-GeoAttn-Net: Linear-Time Depth Modeling with Geometry-Aware Attention for 3D Aortic Dissection CTA Segmentation

Authors: Yuan Zhang, Lei Liu, Jialin Zhang, Ya-Nan Zhang, Ling Wang, Nan Mu
Published: 2026-02-27
Categories: eess.IV, cs.CV
arXiv: https://arxiv.org/abs/2602.23803v1

Accurate segmentation of aortic dissection (AD) lumens in CT angiography (CTA) is essential for quantitative morphological assessment and clinical decision-making. However, reliable 3D delineation remains challenging due to limited long-range context modeling, which compromises inter-slice coherence, and insufficient structural discrimination under low-contrast conditions. To address these limitations, we propose BiM-GeoAttn-Net, a lightweight framework that integrates linear-time depth-wise state-space modeling with geometry-aware vessel refinement. Our approach is featured by Bidirectional Depth Mamba (BiM) to efficiently capture cross-slice dependencies and Geometry-Aware Vessel Attention (GeoAttn) module that employs orientation-sensitive anisotropic filtering to refine tubular structures and sharpen ambiguous boundaries. Extensive experiments on a multi-source AD CTA dataset demonstrate that BiM-GeoAttn-Net achieves a Dice score of 93.35% and an HD95 of 12.36 mm, outperforming representative CNN-, Transformer-, and SSM-based baselines in overlap metrics while maintaining competitive boundary accuracy. These results suggest that coupling linear-time depth modeling with geometry-aware refinement provides an effective, computationally efficient solution for robust 3D AD segmentation.

---

### EMO-R3: Reflective Reinforcement Learning for Emotional Reasoning in Multimodal Large Language Models

Authors: Yiyang Fang, Wenke Huang, Pei Fu, Yihao Yang, Kehua Su, Zhenbo Luo, Jian Luan, Mang Ye
Published: 2026-02-27
Categories: cs.AI, cs.CV
arXiv: https://arxiv.org/abs/2602.23802v2

Multimodal Large Language Models (MLLMs) have shown remarkable progress in visual reasoning and understanding tasks but still struggle to capture the complexity and subjectivity of human emotions. Existing approaches based on supervised fine-tuning often suffer from limited generalization and poor interpretability, while reinforcement learning methods such as Group Relative Policy Optimization fail to align with the intrinsic characteristics of emotional cognition. To address these challenges, we propose Reflective Reinforcement Learning for Emotional Reasoning (EMO-R3), a framework designed to enhance the emotional reasoning ability of MLLMs. Specifically, we introduce Structured Emotional Thinking to guide the model to perform step-by-step emotional reasoning in a structured and interpretable manner, and design a Reflective Emotional Reward that enables the model to re-evaluate its reasoning based on visual-text consistency and emotional coherence. Extensive experiments demonstrate that EMO-R3 significantly improves both the interpretability and emotional intelligence of MLLMs, achieving superior performance across multiple visual emotional understanding benchmarks.

---

### Operationalizing Longitudinal Causal Discovery Under Real-World Workflow Constraints

Authors: Tadahisa Okuda, Shohei Shimizu, Thong Pham, Tatsuyoshi Ikenoue, Shingo Fukuma
Published: 2026-02-27
Categories: stat.ME, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2602.23800v1

Causal discovery has achieved substantial theoretical progress, yet its deployment in large-scale longitudinal systems remains limited. A key obstacle is that operational data are generated under institutional workflows whose induced partial orders are rarely formalized, enlarging the admissible graph space in ways inconsistent with the recording process. We characterize a workflow-induced constraint class for longitudinal causal discovery that restricts the admissible directed acyclic graph space through protocol-derived structural masks and timeline-aligned indexing. Rather than introducing a new optimization algorithm, we show that explicitly encoding workflow-consistent partial orders reduces structural ambiguity, especially in mixed discrete--continuous panels where within-time orientation is weakly identified. The framework combines workflow-derived admissible-edge constraints, measurement-aligned time indexing and block structure, bootstrap-based uncertainty quantification for lagged total effects, and a dynamic representation supporting intervention queries. In a nationwide annual health screening cohort in Japan with 107,261 individuals and 429,044 person-years, workflow-constrained longitudinal LiNGAM yields temporally consistent within-time substructures and interpretable lagged total effects with explicit uncertainty. Sensitivity analyses using alternative exposure and body-composition definitions preserve the main qualitative patterns. We argue that formalizing workflow-derived constraint classes improves structural interpretability without relying on domain-specific edge specification, providing a reproducible bridge between operational workflows and longitudinal causal discovery under standard identifiability assumptions.

---

### MPU: Towards Secure and Privacy-Preserving Knowledge Unlearning for Large Language Models

Authors: Tiantong Wang, Xinyu Yan, Tiantong Wu, Yurong Hao, Pengjun Xie, Wei Yang Bryan Lim
Published: 2026-02-27
Categories: cs.LG, cs.AI, cs.CR, cs.DC
arXiv: https://arxiv.org/abs/2602.23798v2

Machine unlearning for large language models often faces a privacy dilemma in which strict constraints prohibit sharing either the server's parameters or the client's forget set. To address this dual non-disclosure constraint, we propose MPU, an algorithm-agnostic privacy-preserving Multiple Perturbed Copies Unlearning framework that primarily introduces two server-side modules: Pre-Process for randomized copy generation and Post-Process for update aggregation. In Pre-Process, the server distributes multiple perturbed and reparameterized model instances, allowing the client to execute unlearning locally on its private forget set without accessing the server's exact original parameters. After local unlearning, the server performs Post-Process by inverting the reparameterization and aggregating updates with a harmonic denoising procedure to alleviate the impact of perturbation. Experiments with seven unlearning algorithms show that MPU achieves comparable unlearning performance to noise-free baselines, with most algorithms' average degradation well below 1% up to 10% noise, and can even outperform the noise-free baseline for some algorithms under 1% noise. Code is available at https://github.com/Tristan0318/MPU.

---

### GRAIL: Post-hoc Compensation by Linear Reconstruction for Compressed Networks

Authors: Wenwu Tang, Dong Wang, Lothar Thiele, Olga Saukh
Published: 2026-02-27
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.23795v2

Structured deep model compression methods are hardware-friendly and substantially reduce memory and inference costs. However, under aggressive compression, the resulting accuracy degradation often necessitates post-compression finetuning, which can be impractical due to missing labeled data or high training cost. We propose post-hoc blockwise compensation, called GRAIL, a simple zero-finetuning step applied after model compression that restores each block's input-output behavior using a small calibration set. The method summarizes hidden activations via a Gram matrix and applies ridge regression to linearly reconstruct the original hidden representation from the reduced one. The resulting reconstruction map is absorbed into the downstream projection weights, while the upstream layer is compressed. The approach is selector-agnostic (Magnitude, Wanda, Gram-based selection, or folding), data-aware (requiring only a few forward passes without gradients or labels), and recovers classic pruning or folding when the Gram matrix is near identity, indicating weak inter-channel correlations. Across ResNets, ViTs, and decoder-only LLMs, GRAIL consistently improves accuracy or perplexity over data-free and data-aware pruning or folding baselines in practical compression regimes, with manageable overhead and no backpropagation. The code is available at https://github.com/TWWinde/GRAIL_Compensation.

---