Cover Image

Kestrel: Grounding Self-Refinement for LVLM Hallucination Mitigation

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Mao, Jiawei, Chen, Hardy, Tu, Haoqin, Wang, Yuhan, Zhang, Letian, Zheng, Zeyu, Yao, Huaxiu, Wang, Zirui, Xie, Cihang, Zhou, Yuyin
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

OpenVision 2: A Family of Generative Pretrained Visual Encoders for Multimodal Learning
by: Liu, Yanqing, et al.
Published: (2025)

ClinSeekAgent: Automating Multimodal Evidence Seeking for Agentic Clinical Reasoning
by: Wu, Juncheng, et al.
Published: (2026)

Where on Earth? A Vision-Language Benchmark for Probing Model Geolocation Skills Across Scales
by: Qian, Zhaofang, et al.
Published: (2025)

Story-Iter: A Training-free Iterative Paradigm for Long Story Visualization
by: Mao, Jiawei, et al.
Published: (2024)

GPT-IMAGE-EDIT-1.5M: A Million-Scale, GPT-Generated Image Dataset
by: Wang, Yuhan, et al.
Published: (2025)

From Seeing to Thinking: Decoupling Perception and Reasoning Improves Post-Training of Vision-Language Models
by: Wu, Juncheng, et al.
Published: (2026)

Sculpting Holistic 3D Representation in Contrastive Language-Image-3D Pre-training
by: Gao, Yipeng, et al.
Published: (2023)

ViLBench: A Suite for Vision-Language Process Reward Modeling
by: Tu, Haoqin, et al.
Published: (2025)

Your Agent, Their Asset: A Real-World Safety Analysis of OpenClaw
by: Wang, Zijun, et al.
Published: (2026)

SpatialThinker: Reinforcing 3D Reasoning in Multimodal LLMs via Spatial Rewards
by: Batra, Hunar, et al.
Published: (2025)

What If We Recaption Billions of Web Images with LLaMA-3?
by: Li, Xianhang, et al.
Published: (2024)

SFT or RL? An Early Investigation into Training R1-Like Reasoning Large Vision-Language Models
by: Chen, Hardy, et al.
Published: (2025)

Adversarial Orthogonal Disentanglement for LVLM Hallucination Mitigation
by: Cheng, Ruoxi, et al.
Published: (2026)

OpenVision: A Fully-Open, Cost-Effective Family of Advanced Vision Encoders for Multimodal Learning
by: Li, Xianhang, et al.
Published: (2025)

When Visualizing is the First Step to Reasoning: MIRA, a Benchmark for Visual Chain-of-Thought
by: Zhou, Yiyang, et al.
Published: (2025)

Cross-Modal Attention Calibration for LVLM Hallucination Mitigation
by: Li, Jiaming, et al.
Published: (2025)

Intervene-All-Paths: Unified Mitigation of LVLM Hallucinations across Alignment Formats
by: Qian, Jiaye, et al.
Published: (2025)

Beyond the Global Scores: Fine-Grained Token Grounding as a Robust Detector of LVLM Hallucinations
by: Nguyen, Tuan Dung, et al.
Published: (2026)

VHELM: A Holistic Evaluation of Vision Language Models
by: Lee, Tony, et al.
Published: (2024)

Antidote: A Unified Framework for Mitigating LVLM Hallucinations in Counterfactual Presupposition and Object Perception
by: Wu, Yuanchen, et al.
Published: (2025)

AFTER: Mitigating the Object Hallucination of LVLM via Adaptive Factual-Guided Activation Editing
by: Wang, Tianbo, et al.
Published: (2026)

OpenVision 3: A Family of Unified Visual Encoder for Both Understanding and Generation
by: Zhang, Letian, et al.
Published: (2026)

A Unified and Controllable Framework for Layered Image Generation with Visual Effects
by: Yang, Jinrui, et al.
Published: (2026)

VideoHallucer: Evaluating Intrinsic and Extrinsic Hallucinations in Large Video-Language Models
by: Wang, Yuxuan, et al.
Published: (2024)

ARFlow: Autoregressive Flow with Hybrid Linear Attention
by: Hui, Mude, et al.
Published: (2025)

Kestrel: 3D Multimodal LLM for Part-Aware Grounded Description
by: Ahmed, Mahmoud, et al.
Published: (2024)

MetaClaw: Just Talk -- An Agent That Meta-Learns and Evolves in the Wild
by: Xia, Peng, et al.
Published: (2026)

Omni-MMSI: Toward Identity-attributed Social Interaction Understanding
by: Li, Xinpeng, et al.
Published: (2026)

HALC: Object Hallucination Reduction via Adaptive Focal-Contrast Decoding
by: Chen, Zhaorun, et al.
Published: (2024)

VLAA-GUI: Knowing When to Stop, Recover, and Search, A Modular Framework for GUI Automation
by: Han, Qijun, et al.
Published: (2026)

AdaIAT: Adaptively Increasing Attention to Generated Text to Alleviate Hallucinations in LVLM
by: Zhong, Li'an, et al.
Published: (2026)

Analyzing and Mitigating Object Hallucination in Large Vision-Language Models
by: Zhou, Yiyang, et al.
Published: (2023)

On the Adversarial Robustness of Camera-based 3D Object Detection
by: Xie, Shaoyuan, et al.
Published: (2023)

MaskCD: Mitigating LVLM Hallucinations by Image Head Masked Contrastive Decoding
by: Deng, Jingyuan, et al.
Published: (2025)

DAMRO: Dive into the Attention Mechanism of LVLM to Reduce Object Hallucination
by: Gong, Xuan, et al.
Published: (2024)

Double Visual Defense: Adversarial Pre-training and Instruction Tuning for Improving Vision-Language Model Robustness
by: Wang, Zeyu, et al.
Published: (2025)

Revisiting Adversarial Training at Scale
by: Wang, Zeyu, et al.
Published: (2024)

Fighting Hallucinations with Counterfactuals: Diffusion-Guided Perturbations for LVLM Hallucination Suppression
by: Dastmalchi, Hamidreza, et al.
Published: (2026)

Scaling Laws in Patchification: An Image Is Worth 50,176 Tokens And More
by: Wang, Feng, et al.
Published: (2025)

Dehallu3D: Hallucination-Mitigated 3D Generation from Single Image via Cyclic View Consistency Refinement
by: Wang, Xiwen, et al.
Published: (2026)