👁️ Category

cs.CV

2947 papers

Generalization in Online Reinforcement Learning for Mobile Agents

This paper addresses the underexplored challenge of generalization in online reinforcement learning for mobile GUI agents by introducing the AndroidWorld-Generalization benchmark and a scalable GRPO-based training system, demonstrating that while RL significantly improves zero-shot performance on unseen task instances, generalization to new templates and applications remains difficult and benefits from test-time few-shot adaptation.

Li Gu, Zihuan Jiang, Zhixiang Chi, Huan Liu, Ziqiang Wang, Yuanhao Yu, Glen Berseth, Yang Wang2026-03-10🤖 cs.LG

DogWeave: High-Fidelity 3D Canine Reconstruction from a Single Image via Normal Fusion and Conditional Inpainting

DogWeave is a novel framework that reconstructs high-fidelity 3D canine models from a single RGB image by refining parametric meshes into detailed SDF representations via diffusion-enhanced normal optimization and generating view-consistent textures through conditional inpainting, thereby overcoming challenges like self-occlusion and fur detail to outperform existing state-of-the-art methods.

Shufan Sun, Chenchen Wang, Zongfu Yu2026-03-10💻 cs

Med-Evo: Test-time Self-evolution for Medical Multimodal Large Language Models

Med-Evo is a novel self-evolution framework for medical multimodal large language models that leverages label-free reinforcement learning, featuring Feature-driven Pseudo Labeling and Hard-Soft Reward mechanisms, to significantly enhance model performance on unlabeled test data without requiring additional annotated medical datasets.

Dunyuan Xu, Xikai Yang, Juzheng Miao, Yaoqian Li, Jinpeng Li, Pheng-Ann Heng2026-03-10💻 cs

SLNet: A Super-Lightweight Geometry-Adaptive Network for 3D Point Cloud Recognition

The paper introduces SLNet, a super-lightweight 3D point cloud recognition network utilizing Nonparametric Adaptive Point Embedding (NAPE) and Geometric Modulation Units (GMU) to achieve state-of-the-art accuracy on benchmarks like ModelNet40 and ScanObjectNN with significantly fewer parameters and computational costs compared to existing models.

Mohammad Saeid, Amir Salarpour, Pedram MohajerAnsari, Mert D. Pesé2026-03-10🤖 cs.LG

Selective Transfer Learning of Cross-Modality Distillation for Monocular 3D Object Detection

This paper introduces MonoSTL, a selective transfer learning framework that addresses the negative transfer caused by modality gaps in cross-modality distillation for monocular 3D object detection by employing similar architectures and novel depth-aware selective distillation modules to effectively transfer LiDAR depth information to image-based networks, achieving state-of-the-art performance on KITTI and NuScenes benchmarks.

Rui Ding, Meng Yang, Nanning Zheng2026-03-10💻 cs

Classifying Novel 3D-Printed Objects without Retraining: Towards Post-Production Automation in Additive Manufacturing

This paper introduces the ThingiPrint dataset and a contrastive fine-tuning approach that enables the classification of novel 3D-printed objects using their CAD models without requiring model retraining, thereby addressing a critical bottleneck in automating industrial post-production workflows.

Fanis Mathioulakis, Gorjan Radevski, Silke GC Cleuren, Michel Janssens, Brecht Das, Koen Schauwaert, Tinne Tuytelaars2026-03-10💻 cs

FedEU: Evidential Uncertainty-Driven Federated Fine-Tuning of Vision Foundation Models for Remote Sensing Image Segmentation

FedEU is a novel federated learning framework that enhances remote sensing image segmentation by integrating evidential uncertainty quantification and client-specific feature embeddings to guide adaptive global aggregation, thereby improving model robustness and reliability across heterogeneous distributed datasets.

Xiaokang Zhang, Xuran Xiong, Jianzhong Huang, Lefei Zhang2026-03-10💻 cs

RobustSCI: Beyond Reconstruction to Restoration for Snapshot Compressive Imaging under Real-World Degradations

This paper introduces RobustSCI, a pioneering framework that shifts snapshot compressive imaging from simple reconstruction to robust restoration by proposing a novel network architecture and a large-scale benchmark to effectively recover pristine scenes from real-world degraded measurements caused by motion blur and low light.

Hao Wang, Yuanfan Li, Qi Zhou, Zhankuo Xu, Jiong Ni, Xin Yuan2026-03-10💻 cs

RayD3D: Distilling Depth Knowledge Along the Ray for Robust Multi-View 3D Object Detection

The paper proposes RayD3D, a novel cross-modal distillation framework that transfers depth knowledge specifically along the camera-to-object ray to filter out irrelevant LiDAR information, thereby significantly enhancing the robustness of multi-view 3D object detection models against real-world data corruptions without increasing inference costs.

Rui Ding, Zhaonian Kuang, Zongwei Zhou, Meng Yang, Xinhu Zheng, Gang Hua2026-03-10💻 cs

DocCogito: Aligning Layout Cognition and Step-Level Grounded Reasoning for Document Understanding

DocCogito is a unified framework for document understanding that aligns global layout perception with structured, region-grounded reasoning through a lightweight layout tower and a deterministic Visual-Semantic Chain, achieving state-of-the-art performance on multiple benchmarks by enforcing systematic coupling between layout priors and evidence-based reasoning.

Yuchuan Wu, Minghan Zhuo, Teng Fu, Mengyang Zhao, Bin Li, Xiangyang Xue2026-03-10💻 cs

A Unified View of Drifting and Score-Based Models

This paper establishes a unified theoretical framework demonstrating that drifting models, which optimize kernel-based mean-shift discrepancies, are mathematically equivalent to score-matching objectives on kernel-smoothed distributions, thereby precisely connecting them to diffusion models and clarifying their relationship with Distribution Matching Distillation.

Chieh-Hsin Lai, Bac Nguyen, Naoki Murata, Yuhta Takida, Toshimitsu Uesaka, Yuki Mitsufuji, Stefano Ermon, Molei Tao2026-03-10🤖 cs.LG

EvolveReason: Self-Evolving Reasoning Paradigm for Explainable Deepfake Facial Image Identification

The paper proposes EvolveReason, a self-evolving reasoning paradigm that combines a human-like chain-of-thought framework, a forgery latent-space distribution capture module, and a reinforcement learning-based self-evolution strategy to enhance the accuracy, detail, and reliability of explainable deepfake facial image identification.

Binjia Zhou, Dawei Luo, Shuai Chen, Feng Xu, Seow, Haoyuan Li, Jiachi Wang, Jiawen Wang, Zunlei Feng, Yijun Bei2026-03-10💻 cs