Imagen de Portada

IVR-R1: Refining Trajectories through Iterative Visual-Grounded Reasoning in Reinforcement Learning

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Li, Chenghao, Hao, Fusheng, Zhang, Xikai, Xiao, Likang, Ren, Yanwei, Wu, Fuxiang, Chen, Quan, Liu, Liu
Formato:	Preprint
Publicado:	2026
Materias:	Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Gradient-based Fine-Tuning through Pre-trained Model Regularization
por: Liu, Xuanbo, et al.
Publicado: (2025)

Improving the Reasoning of Multi-Image Grounding in MLLMs via Reinforcement Learning
por: Zhang, Bob, et al.
Publicado: (2025)

Improving Visual Reasoning with Iterative Evidence Refinement
por: Shi, Zeru, et al.
Publicado: (2026)

VG-Refiner: Towards Tool-Refined Referring Grounded Reasoning via Agentic Reinforcement Learning
por: Wang, Yuji, et al.
Publicado: (2025)

Ground-R1: Incentivizing Grounded Visual Reasoning via Reinforcement Learning
por: Cao, Meng, et al.
Publicado: (2025)

UniVG-R1: Reasoning Guided Universal Visual Grounding with Reinforcement Learning
por: Bai, Sule, et al.
Publicado: (2025)

Grounded Reinforcement Learning for Visual Reasoning
por: Sarch, Gabriel, et al.
Publicado: (2025)

Bootstrapping Physics-Grounded Video Generation through VLM-Guided Iterative Self-Refinement
por: Liu, Yang, et al.
Publicado: (2025)

VTPerception-R1: Enhancing Multimodal Reasoning via Explicit Visual and Textual Perceptual Grounding
por: Ding, Yizhuo, et al.
Publicado: (2025)

Exploring Iterative Refinement with Diffusion Models for Video Grounding
por: Liang, Xiao, et al.
Publicado: (2023)

Visual Reasoning through Tool-supervised Reinforcement Learning
por: Dong, Qihua, et al.
Publicado: (2026)

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

High-Resolution Visual Reasoning via Multi-Turn Grounding-Based Reinforcement Learning
por: Huang, Xinyu, et al.
Publicado: (2025)

PrecisionCUA: Iterative Visual Refinement for Pixel-Precise Cursor Grounding in Code Editors
por: Mittal, Himangi, et al.
Publicado: (2026)

ViaRL: Adaptive Temporal Grounding via Visual Iterated Amplification Reinforcement Learning
por: Xu, Ziqiang, et al.
Publicado: (2025)

See It, Say It, Sorted: An Iterative Training-Free Framework for Visually-Grounded Multimodal Reasoning in LVLMs
por: Zhang, Yongchang, et al.
Publicado: (2026)

Chain-of-Ground: Improving GUI Grounding via Iterative Reasoning and Reference Feedback
por: Li, Aiden Yiliu, et al.
Publicado: (2025)

Visual Reasoning Tracer: Object-Level Grounded Reasoning Benchmark
por: Yuan, Haobo, et al.
Publicado: (2025)

iSeg: An Iterative Refinement-based Framework for Training-free Segmentation
por: Sun, Lin, et al.
Publicado: (2024)

SpaceR: Reinforcing MLLMs in Video Spatial Reasoning
por: Ouyang, Kun, et al.
Publicado: (2025)

\textsc{GUI-Spotlight}: Adaptive Iterative Focus Refinement for Enhanced GUI Visual Grounding
por: Lei, Bin, et al.
Publicado: (2025)

PathVLM-R1: A Reinforcement Learning-Driven Reasoning Model for Pathology Visual-Language Tasks
por: Wu, Jianyu, et al.
Publicado: (2025)

RSGround-R1: Rethinking Remote Sensing Visual Grounding through Spatial Reasoning
por: Huang, Shiqi, et al.
Publicado: (2026)

RGBX-R1: Visual Modality Chain-of-Thought Guided Reinforcement Learning for Multimodal Grounding
por: Wu, Jiahe, et al.
Publicado: (2026)

MIRG-RL: Multi-Image Reasoning and Grounding with Reinforcement Learning
por: Zheng, Lihao, et al.
Publicado: (2025)

A Neural Representation Framework with LLM-Driven Spatial Reasoning for Open-Vocabulary 3D Visual Grounding
por: Liu, Zhenyang, et al.
Publicado: (2025)

VGent: Visual Grounding via Modular Design for Disentangling Reasoning and Prediction
por: Kang, Weitai, et al.
Publicado: (2025)

VideoChat-R1.5: Visual Test-Time Scaling to Reinforce Multimodal Reasoning by Iterative Perception
por: Yan, Ziang, et al.
Publicado: (2025)

Med-R2: An Adversarial Benchmark for Evidence-Grounded Reasoning in Medical VLMs
por: Ma, Wen, et al.
Publicado: (2026)

TerraScope: Pixel-Grounded Visual Reasoning for Earth Observation
por: Shu, Yan, et al.
Publicado: (2026)

Wan-R1: Verifiable-Reinforcement Learning for Video Reasoning
por: Liu, Ming, et al.
Publicado: (2026)

VisionReasoner: Unified Reasoning-Integrated Visual Perception via Reinforcement Learning
por: Liu, Yuqi, et al.
Publicado: (2025)

Visionary-R1: Mitigating Shortcuts in Visual Reasoning with Reinforcement Learning
por: Xia, Jiaer, et al.
Publicado: (2025)

VGR: Visual Grounded Reasoning
por: Wang, Jiacong, et al.
Publicado: (2025)

$R^2$-Mesh: Reinforcement Learning Powered Mesh Reconstruction via Geometry and Appearance Refinement
por: Wang, Haoyang, et al.
Publicado: (2024)

Omni-R1: Reinforcement Learning for Omnimodal Reasoning via Two-System Collaboration
por: Zhong, Hao, et al.
Publicado: (2025)

RegionReasoner: Region-Grounded Multi-Round Visual Reasoning
por: Sun, Wenfang, et al.
Publicado: (2026)

Point-RFT: Improving Multimodal Reasoning with Visually Grounded Reinforcement Finetuning
por: Ni, Minheng, et al.
Publicado: (2025)

STVG-R1: Incentivizing Instance-Level Reasoning and Grounding in Videos via Reinforcement Learning
por: Zhang, Xiaowen, et al.
Publicado: (2026)

VisualQuality-R1: Reasoning-Induced Image Quality Assessment via Reinforcement Learning to Rank
por: Wu, Tianhe, et al.
Publicado: (2025)