Copertina

POPEN: Preference-Based Optimization and Ensemble for LVLM-Based Reasoning Segmentation

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Zhu, Lanyun, Chen, Tianrun, Xu, Qianxiong, Liu, Xuanyi, Ji, Deyi, Wu, Haiyang, Soh, De Wen, Liu, Jun
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Computer Vision and Pattern Recognition
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Retrv-R1: A Reasoning-Driven MLLM Framework for Universal and Efficient Multimodal Retrieval
di: Zhu, Lanyun, et al.
Pubblicazione: (2025)

LLaFS: When Large Language Models Meet Few-Shot Segmentation
di: Zhu, Lanyun, et al.
Pubblicazione: (2023)

Not Every Patch is Needed: Towards a More Efficient and Effective Backbone for Video-based Person Re-identification
di: Zhu, Lanyun, et al.
Pubblicazione: (2025)

Hybrid Mamba for Few-Shot Segmentation
di: Xu, Qianxiong, et al.
Pubblicazione: (2024)

Unlocking the Power of SAM 2 for Few-Shot Segmentation
di: Xu, Qianxiong, et al.
Pubblicazione: (2025)

IBD: Alleviating Hallucinations in Large Vision-Language Models via Image-Biased Decoding
di: Zhu, Lanyun, et al.
Pubblicazione: (2024)

StreamCacheVGGT: Streaming Visual Geometry Transformers with Robust Scoring and Hybrid Cache Compression
di: Liu, Xuanyi, et al.
Pubblicazione: (2026)

Video-Zero: Self-Evolution Video Understanding
di: Zhang, Ruixu, et al.
Pubblicazione: (2026)

Breaking the Box: Enhancing Remote Sensing Image Segmentation with Freehand Sketches
di: Zang, Ying, et al.
Pubblicazione: (2025)

SAM3-Adapter: Efficient Adaptation of Segment Anything 3 for Camouflage Object Segmentation, Shadow Detection, and Medical Image Segmentation
di: Chen, Tianrun, et al.
Pubblicazione: (2025)

xLSTM-UNet can be an Effective 2D & 3D Medical Image Segmentation Backbone with Vision-LSTM (ViL) better than its Mamba Counterpart
di: Chen, Tianrun, et al.
Pubblicazione: (2024)

4DVGGT-D: 4D Visual Geometry Transformer with Improved Dynamic Depth Estimation
di: Zang, Ying, et al.
Pubblicazione: (2026)

Reasoning3D -- Grounding and Reasoning in 3D: Fine-Grained Zero-Shot Open-Vocabulary 3D Reasoning Part Segmentation via Large Vision-Language Models
di: Chen, Tianrun, et al.
Pubblicazione: (2024)

SAM2-Adapter: Evaluating & Adapting Segment Anything 2 in Downstream Tasks: Camouflage, Shadow, Medical Image Segmentation, and More
di: Chen, Tianrun, et al.
Pubblicazione: (2024)

Discrete Latent Perspective Learning for Segmentation and Detection
di: Ji, Deyi, et al.
Pubblicazione: (2024)

Let Human Sketches Help: Empowering Challenging Image Segmentation Task with Freehand Sketches
di: Zang, Ying, et al.
Pubblicazione: (2025)

SAMITE: Position Prompted SAM2 with Calibrated Memory for Visual Object Tracking
di: Xu, Qianxiong, et al.
Pubblicazione: (2025)

From Air to Wear: Personalized 3D Digital Fashion with AR/VR Immersive 3D Sketching
di: Zang, Ying, et al.
Pubblicazione: (2025)

RAVEN: Robust Advertisement Video Violation Temporal Grounding via Reinforcement Reasoning
di: Ji, Deyi, et al.
Pubblicazione: (2025)

Uncertainty-Based Ensemble Learning in CMR Semantic Segmentation
di: Liu, Yiwei, et al.
Pubblicazione: (2025)

RESMatch: Referring Expression Segmentation in a Semi-Supervised Manner
di: Zang, Ying, et al.
Pubblicazione: (2024)

Robust 4D Visual Geometry Transformer with Uncertainty-Aware Priors
di: Zang, Ying, et al.
Pubblicazione: (2026)

StreamSense: Streaming Social Task Detection with Selective Vision-Language Model Routing
di: Wang, Han, et al.
Pubblicazione: (2026)

ID-Selection: Importance-Diversity Based Visual Token Selection for Efficient LVLM Inference
di: Huang, Zhaohong, et al.
Pubblicazione: (2026)

Fooling the LVLM Judges: Visual Biases in LVLM-Based Evaluation
di: Hwang, Yerin, et al.
Pubblicazione: (2025)

IADGPT: Unified LVLM for Few-Shot Industrial Anomaly Detection, Localization, and Reasoning via In-Context Learning
di: Zhao, Mengyang, et al.
Pubblicazione: (2025)

HD-VGGT: High-Resolution Visual Geometry Transformer
di: Chen, Tianrun, et al.
Pubblicazione: (2026)

LVLM_CSP: Accelerating Large Vision Language Models via Clustering, Scattering, and Pruning for Reasoning Segmentation
di: Chen, Hanning, et al.
Pubblicazione: (2025)

Bridging Semantics and Geometry: A Decoupled LVLM-SAM Framework for Reasoning Segmentation in Optical Remote Sensing
di: Zhang, Xu, et al.
Pubblicazione: (2025)

Language-Instructed Reasoning for Group Activity Detection via Multimodal Large Language Model
di: Peng, Jihua, et al.
Pubblicazione: (2025)

PRISM: Programmatic Reasoning with Image Sequence Manipulation for LVLM Jailbreaking
di: Zou, Quanchen, et al.
Pubblicazione: (2025)

View-Centric Multi-Object Tracking with Homographic Matching in Moving UAV
di: Ji, Deyi, et al.
Pubblicazione: (2024)

MedM-VL: What Makes a Good Medical LVLM?
di: Shi, Yiming, et al.
Pubblicazione: (2025)

Structural and Statistical Texture Knowledge Distillation and Learning for Segmentation
di: Ji, Deyi, et al.
Pubblicazione: (2025)

Syllables to Scenes: Literary-Guided Free-Viewpoint 3D Scene Synthesis from Japanese Haiku
di: Yu, Chunan, et al.
Pubblicazione: (2025)

Eliminating Feature Ambiguity for Few-Shot Segmentation
di: Xu, Qianxiong, et al.
Pubblicazione: (2024)

PPTFormer: Pseudo Multi-Perspective Transformer for UAV Segmentation
di: Ji, Deyi, et al.
Pubblicazione: (2024)

ReasonGrounder: LVLM-Guided Hierarchical Feature Splatting for Open-Vocabulary 3D Visual Grounding and Reasoning
di: Liu, Zhenyang, et al.
Pubblicazione: (2025)

Unlocking Compositional Control: Self-Supervision for LVLM-Based Image Generation
di: Garcia, Fernando Gabriela, et al.
Pubblicazione: (2025)

Fine-Grained Preference Optimization Improves Spatial Reasoning in VLMs
di: Shen, Yifan, et al.
Pubblicazione: (2025)