Cover Image

From Failure to Feedback: Group Revision Unlocks Hard Cases in Object-Level Grounding

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Liu, Yuyuan, Ji, Yiping, Le, Anjie, Zhu, Jiayuan, Pan, Jiazhen, Peng, Can, Deng, Jiajun, Liu, Fengbei, Wu, Junde
Format:	Preprint
Published:	2026
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Ask Patients with Patience: Enabling LLMs for Human-Centric Medical Dialogue with Grounded Reasoning
by: Zhu, Jiayuan, et al.
Published: (2025)

POUR: A Provably Optimal Method for Unlearning Representations via Neural Collapse
by: Le, Anjie, et al.
Published: (2025)

Git Context Controller: Manage the Context of LLM-based Agents like Git
by: Wu, Junde, et al.
Published: (2025)

Agentic Reasoning: A Streamlined Framework for Enhancing LLM Reasoning with Agentic Tools
by: Wu, Junde, et al.
Published: (2025)

Evo: Autoregressive-Diffusion Large Language Models with Evolving Balance
by: Wu, Junde, et al.
Published: (2026)

Bridging Generative and Discriminative Noisy-Label Learning via Direction-Agnostic EM Formulation
by: Liu, Fengbei, et al.
Published: (2023)

MedUHIP: Towards Human-In-the-Loop Medical Segmentation
by: Zhu, Jiayuan, et al.
Published: (2024)

MedVLM-R1: Incentivizing Medical Reasoning Capability of Vision-Language Models (VLMs) via Reinforcement Learning
by: Pan, Jiazhen, et al.
Published: (2025)

Unraveling Instance Associations: A Closer Look for Audio-Visual Segmentation
by: Chen, Yuanhong, et al.
Published: (2023)

Translation Consistent Semi-supervised Segmentation for 3D Medical Images
by: Liu, Yuyuan, et al.
Published: (2022)

Mixture of Gaussian-distributed Prototypes with Generative Modelling for Interpretable and Trustworthy Image Recognition
by: Wang, Chong, et al.
Published: (2023)

AuralSAM2: Enabling SAM2 Hear Through Pyramid Audio-Visual Feature Prompting
by: Liu, Yuyuan, et al.
Published: (2025)

BioMedArena: An Open-source Toolkit for Building and Evaluating Biomedical Deep Research Agents
by: Wu, Jinge, et al.
Published: (2026)

On the Hardness of the $L_1-L_2$ Regularization Problem
by: Ouyang, Yuyuan, et al.
Published: (2024)

One-Prompt to Segment All Medical Images
by: Wu, Junde, et al.
Published: (2023)

Not just Birds and Cars: Generic, Scalable and Explainable Models for Professional Visual Recognition
by: Wu, Junde, et al.
Published: (2024)

Long-Term Preservation of Digital Information in China: Some Problems and Solutions
by: Liu, Jiazhen, et al.
Published: (2009)

SWE Context Bench: A Benchmark for Context Learning in Coding
by: Zhu, Jiayuan, et al.
Published: (2026)

Failure-Aware Multi-Robot Coordination for Resilient and Adaptive Target Tracking
by: Li, Peihan, et al.
Published: (2025)

RiskAgent: Synergizing Language Models with Validated Tools for Evidence-Based Risk Prediction
by: Liu, Fenglin, et al.
Published: (2025)

Client-Level Differential Privacy via Adaptive Intermediary in Federated Medical Imaging
by: Jiang, Meirui, et al.
Published: (2023)

Beyond Benchmarks: Dynamic, Automatic And Systematic Red-Teaming Agents For Trustworthy Medical Language Models
by: Pan, Jiazhen, et al.
Published: (2025)

Learning Human-Object Interaction as Groups
by: Hong, Jiajun, et al.
Published: (2025)

Empowering Small VLMs to Think with Dynamic Memorization and Exploration
by: Liu, Jiazhen, et al.
Published: (2025)

A Blocking Method for Overload‐Dominant Cascading Failures in Power Grid Based on Source and Load Collaborative Regulation
by: Ji Sun, et al.
Published: (2024)

Medical SAM 2: Segment medical images as video via Segment Anything Model 2
by: Zhu, Jiayuan, et al.
Published: (2024)

Unlocking Instructive In-Context Learning with Tabular Prompting for Relational Triple Extraction
by: Li, Guozheng, et al.
Published: (2024)

From Failure to Mastery: Generating Hard Samples for Tool-use Agents
by: Hao, Bingguang, et al.
Published: (2026)

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

Dynamic Decision Learning: Test-Time Evolution for Abnormality Grounding in Rare Diseases
by: Li, Jun, et al.
Published: (2026)

Talk is Cheap, Communication is Hard: Dynamic Grounding Failures and Repair in Multi-Agent Negotiation
by: Yao, Yiheng, et al.
Published: (2026)

Extrapolated Hard Thresholding Algorithms with Finite Length for Composite $\ell_0$ Penalized Problems
by: Wu, Fan, et al.
Published: (2025)

Cross- and Intra-image Prototypical Learning for Multi-label Disease Diagnosis and Interpretation
by: Wang, Chong, et al.
Published: (2024)

Neural Collapse-Inspired Multi-Label Federated Learning under Label-Distribution Skew
by: Peng, Can, et al.
Published: (2025)

Segmentation, Detection and Explanation: A Unified Framework for CT Appearance Reasoning
by: Liu, Yuyuan, et al.
Published: (2026)

BackSplit: The Importance of Sub-dividing the Background in Biomedical Lesion Segmentation
by: Saluja, Rachit, et al.
Published: (2025)

SPA: Efficient User-Preference Alignment against Uncertainty in Medical Image Segmentation
by: Zhu, Jiayuan, et al.
Published: (2024)

Enhancing targeted transferability via feature space fine-tuning
by: Zeng, Hui, et al.
Published: (2024)

Beyond Sample-Level Feedback: Using Reference-Level Feedback to Guide Data Synthesis
by: Mehri, Shuhaib, et al.
Published: (2025)

An Electrochemical/Thermodynamic Analytical Model for Hard‐Pack Lithium‐Ion Batteries in Engineering Education
by: Ligang Wang, et al.
Published: (2025)