Cover Image

Learning to Focus and Precise Cropping: A Reinforcement Learning Framework with Information Gaps and Grounding Loss for MLLMs

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhao, Xuanpu, Tan, Zhentao, Sheng, Dianmo, Chen, Tianxiang, Liu, Yao, Wu, Yue, Gong, Tao, Chu, Qi, Yu, Nenghai
Format:	Preprint
Published:	2026
Subjects:	Computer Vision and Pattern Recognition Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Towards More Unified In-context Visual Understanding
by: Sheng, Dianmo, et al.
Published: (2023)

TCI-Former: Thermal Conduction-Inspired Transformer for Infrared Small Target Detection
by: Chen, Tianxiang, et al.
Published: (2024)

Flora: Effortless Context Construction to Arbitrary Length and Scale
by: Chen, Tianxiang, et al.
Published: (2025)

Llama SLayer 8B: Shallow Layers Hold the Key to Knowledge Injection
by: Chen, Tianxiang, et al.
Published: (2024)

SAPL: Semantic-Agnostic Prompt Learning in CLIP for Weakly Supervised Image Manipulation Localization
by: Wang, Xinghao, et al.
Published: (2026)

Bootstrapping Audio-Visual Segmentation by Strengthening Audio Cues
by: Chen, Tianxiang, et al.
Published: (2024)

MiM-ISTD: Mamba-in-Mamba for Efficient Infrared Small Target Detection
by: Chen, Tianxiang, et al.
Published: (2024)

Transformer based Pluralistic Image Completion with Reduced Information Loss
by: Liu, Qiankun, et al.
Published: (2024)

Multi-spectral Class Center Network for Face Manipulation Detection and Localization
by: Miao, Changtao, et al.
Published: (2023)

Mixture-of-Noises Enhanced Forgery-Aware Predictor for Multi-Face Manipulation Detection and Localization
by: Miao, Changtao, et al.
Published: (2024)

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

Mean-squared Energy Difference for Exploring Potential Energy Landscapes of Supercooled Liquids
by: Zhang, Dianmo, et al.
Published: (2025)

Context-Aware Weakly Supervised Image Manipulation Localization with SAM Refinement
by: Wang, Xinghao, et al.
Published: (2025)

SPARROW: Learning Spatial Precision and Temporal Referential Consistency in Pixel-Grounded Video MLLMs
by: Alansari, Mohamad, et al.
Published: (2026)

GroundingME: Exposing the Visual Grounding Gap in MLLMs through Multi-Dimensional Evaluation
by: Li, Rang, et al.
Published: (2025)

Precision Agriculture: Crop Mapping using Machine Learning and Sentinel-2 Satellite Imagery
by: Zhao, Kui, et al.
Published: (2023)

Precision-Focused Reinforcement Learning Model for Robotic Object Pushing
by: Bergmann, Lara, et al.
Published: (2024)

Exploiting Modality-Specific Features For Multi-Modal Manipulation Detection And Grounding
by: Wang, Jiazhen, et al.
Published: (2023)

Learning Solution-Aware Transformers for Efficiently Solving Quadratic Assignment Problem
by: Tan, Zhentao, et al.
Published: (2024)

Injecting Distributional Awareness into MLLMs via Reinforcement Learning for Deep Imbalanced Regression
by: Du, Yao, et al.
Published: (2026)

UDQL: Bridging The Gap between MSE Loss and The Optimal Value Function in Offline Reinforcement Learning
by: Zhang, Yu, et al.
Published: (2024)

TimeSuite: Improving MLLMs for Long Video Understanding via Grounded Tuning
by: Zeng, Xiangyu, et al.
Published: (2024)

FishBEV: Distortion-Resilient Bird's Eye View Segmentation with Surround-View Fisheye Cameras
by: Li, Hang, et al.
Published: (2025)

Observe-R1: Unlocking Reasoning Abilities of MLLMs with Dynamic Progressive Reinforcement Learning
by: Guo, Zirun, et al.
Published: (2025)

When Agents Look the Same: Quantifying Distillation-Induced Similarity in Tool-Use Behaviors
by: Yang, Chenghao, et al.
Published: (2026)

Robust Losses for Decision-Focused Learning
by: Schutte, Noah, et al.
Published: (2023)

Radial 3D Focusing Energy Critical INLS equations with defocusing perturbation: Ground states, Scattering, and Blow-up
by: Gou, Tianxiang, et al.
Published: (2024)

VideoZoomer: Reinforcement-Learned Temporal Focusing for Long Video Reasoning
by: Ding, Yang, et al.
Published: (2025)

Video-R1: Reinforcing Video Reasoning in MLLMs
by: Feng, Kaituo, et al.
Published: (2025)

PsychēChat: An Empathic Framework Focused on Emotion Shift Tracking and Safety Risk Analysis in Psychological Counseling
by: Xia, Zhentao, et al.
Published: (2026)

LAKAN: Landmark-assisted Adaptive Kolmogorov-Arnold Network for Face Forgery Detection
by: Jiang, Jiayao, et al.
Published: (2025)

STI-Bench: Are MLLMs Ready for Precise Spatial-Temporal World Understanding?
by: Li, Yun, et al.
Published: (2025)

ClaHF: A Human Feedback-inspired Reinforcement Learning Framework for Improving Classification Tasks
by: Xu, Tianxiang, et al.
Published: (2026)

Prediction Loss Guided Decision-Focused Learning
by: Jeon, Haeun, et al.
Published: (2025)

Learning Where, What and How to Transfer: A Multi-Role Reinforcement Learning Approach for Evolutionary Multitasking
by: Zhan, Jiajun, et al.
Published: (2025)

Training-Free In-Context Forensic Chain for Image Manipulation Detection and Localization
by: Chen, Rui, et al.
Published: (2025)

GuardTrace-VL: Detecting Unsafe Multimodel Reasoning via Iterative Safety Supervision
by: Xiang, Yuxiao, et al.
Published: (2025)

Compositional Learning of Visually-Grounded Concepts Using Reinforcement
by: Lin, Zijun, et al.
Published: (2023)

Horizon Reduction as Information Loss in Offline Reinforcement Learning
by: Nidadala, Uday Kumar, et al.
Published: (2025)

Cost-Effective Cyber-Physical System Prototype for Precision Agriculture with a Focus on Crop Growth
by: Kumar, Pawan, et al.
Published: (2024)