Buchumschlag

CODE: Contrasting Self-generated Description to Combat Hallucination in Large Multi-modal Models

Fuente: arXiv

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Kim, Junho, Kim, Hyunjun, Kim, Yeonju, Ro, Yong Man
Format:	Preprint
Veröffentlicht:	2024
Schlagworte:	Computer Vision and Pattern Recognition Artificial Intelligence
Online-Zugang:	Acceder al recurso
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Ähnliche Einträge

What if...?: Thinking Counterfactual Keywords Helps to Mitigate Hallucination in Large Multi-modal Models
von: Kim, Junho, et al.
Veröffentlicht: (2024)

SALOVA: Segment-Augmented Long Video Assistant for Targeted Retrieval and Routing in Long-Form Video Analysis
von: Kim, Junho, et al.
Veröffentlicht: (2024)

ReFoCUS: Reinforcement-guided Frame Optimization for Contextual Understanding
von: Lee, Hosu, et al.
Veröffentlicht: (2025)

Look Every Frame All at Once: Video-Ma$^2$mba for Efficient Long-form Video Understanding with Multi-Axis Gradient Checkpointing
von: Lee, Hosu, et al.
Veröffentlicht: (2024)

Empathetic Response in Audio-Visual Conversations Using Emotion Preference Optimization and MambaCompressor
von: Kim, Yeonju, et al.
Veröffentlicht: (2024)

Causal Unsupervised Semantic Segmentation
von: Kim, Junho, et al.
Veröffentlicht: (2023)

STRIDE: When to Speak Meets Sequence Denoising for Streaming Video Understanding
von: Kim, Junho, et al.
Veröffentlicht: (2026)

DIP-R1: Deep Inspection and Perception with RL Looking Through and Understanding Complex Scenes
von: Park, Sungjune, et al.
Veröffentlicht: (2025)

AV-EmoDialog: Chat with Audio-Visual Users Leveraging Emotional Cues
von: Park, Se Jin, et al.
Veröffentlicht: (2024)

Robust Pedestrian Detection via Constructing Versatile Pedestrian Knowledge Bank
von: Park, Sungjune, et al.
Veröffentlicht: (2024)

Integrating Language-Derived Appearance Elements with Visual Cues in Pedestrian Detection
von: Park, Sungjune, et al.
Veröffentlicht: (2023)

Language-guided Learning for Object Detection Tackling Multiple Variations in Aerial Images
von: Park, Sungjune, et al.
Veröffentlicht: (2025)

Revealing Multi-View Hallucination in Large Vision-Language Models
von: Park, Wooje, et al.
Veröffentlicht: (2026)

Visual Hallucinations of Multi-modal Large Language Models
von: Huang, Wen, et al.
Veröffentlicht: (2024)

Remote Sensing Large Vision-Language Model: Semantic-augmented Multi-level Alignment and Semantic-aware Expert Modeling
von: Park, Sungjune, et al.
Veröffentlicht: (2025)

Pygmalion Effect in Vision: Image-to-Clay Translation for Reflective Geometry Reconstruction
von: Lee, Gayoung, et al.
Veröffentlicht: (2025)

Visual Delta Generator with Large Multi-modal Models for Semi-supervised Composed Image Retrieval
von: Jang, Young Kyun, et al.
Veröffentlicht: (2024)

Prompt Tuning of Deep Neural Networks for Speaker-adaptive Visual Speech Recognition
von: Kim, Minsu, et al.
Veröffentlicht: (2023)

Attention-space Contrastive Guidance for Efficient Hallucination Mitigation in LVLMs
von: Jo, Yujin, et al.
Veröffentlicht: (2026)

Visual Speech Recognition for Languages with Limited Labeled Data using Automatic Labels from Whisper
von: Yeo, Jeong Hun, et al.
Veröffentlicht: (2023)

Programmable-Room: Interactive Textured 3D Room Meshes Generation Empowered by Large Language Models
von: Kim, Jihyun, et al.
Veröffentlicht: (2025)

GCAgent: Long-Video Understanding via Schematic and Narrative Episodic Memory
von: Yeo, Jeong Hun, et al.
Veröffentlicht: (2025)

VG3T: Visual Geometry Grounded Gaussian Transformer
von: Kim, Junho, et al.
Veröffentlicht: (2025)

Simultaneous Long-tailed Recognition and Multi-modal Fusion for Highly Imbalanced Multi-modal Data
von: Yoon, Heegeon, et al.
Veröffentlicht: (2026)

How Blind and Low-Vision Individuals Prefer Large Vision-Language Model-Generated Scene Descriptions
von: An, Na Min, et al.
Veröffentlicht: (2025)

Let's Go Real Talk: Spoken Dialogue Model for Face-to-Face Conversation
von: Park, Se Jin, et al.
Veröffentlicht: (2024)

MGHanD: Multi-modal Guidance for authentic Hand Diffusion
von: Eum, Taehyeon, et al.
Veröffentlicht: (2025)

Robust Grounding with MLLMs Against Occlusion and Small Objects via Language-Guided Semantic Cues
von: Park, Beomchan, et al.
Veröffentlicht: (2026)

PruneHal: Reducing Hallucinations in Multi-modal Large Language Models through Adaptive KV Cache Pruning
von: Sun, Fengyuan, et al.
Veröffentlicht: (2025)

MSCoTDet: Language-driven Multi-modal Fusion for Improved Multispectral Pedestrian Detection
von: Kim, Taeheon, et al.
Veröffentlicht: (2024)

M4CXR: Exploring Multi-task Potentials of Multi-modal Large Language Models for Chest X-ray Interpretation
von: Park, Jonggwon, et al.
Veröffentlicht: (2024)

AV2AV: Direct Audio-Visual Speech to Audio-Visual Speech Translation with Unified Audio-Visual Speech Representation
von: Choi, Jeongsoo, et al.
Veröffentlicht: (2023)

DHCP: Detecting Hallucinations by Cross-modal Attention Pattern in Large Vision-Language Models
von: Zhang, Yudong, et al.
Veröffentlicht: (2024)

Solution for SMART-101 Challenge of CVPR Multi-modal Algorithmic Reasoning Task 2024
von: Ahn, Jinwoo, et al.
Veröffentlicht: (2024)

DETACH : Decomposed Spatio-Temporal Alignment for Exocentric Video and Ambient Sensors with Staged Learning
von: Yoon, Junho, et al.
Veröffentlicht: (2025)

Mitigating Hallucinations in Large Vision-Language Models via Summary-Guided Decoding
von: Min, Kyungmin, et al.
Veröffentlicht: (2024)

Revisiting Misalignment in Multispectral Pedestrian Detection: A Language-Driven Approach for Cross-modal Alignment Fusion
von: Kim, Taeheon, et al.
Veröffentlicht: (2024)

Preserving Pre-trained Representation Space: On Effectiveness of Prefix-tuning for Large Multi-modal Models
von: Kim, Donghoon, et al.
Veröffentlicht: (2024)

SDCD: Structure-Disrupted Contrastive Decoding for Mitigating Hallucinations in Large Vision-Language Models
von: Xia, Yuxuan, et al.
Veröffentlicht: (2026)

Mitigating Hallucinations in Video Large Language Models via Spatiotemporal-Semantic Contrastive Decoding
von: Gao, Yuansheng, et al.
Veröffentlicht: (2026)