Imagen de Portada

Residual Decoding: Mitigating Hallucinations in Large Vision-Language Models via History-Aware Residual Guidance

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Chen, Xinrong, Chu, Xu, Qiu, Yingmin, Zhang, Hengyuan, Xiong, Jing, Tang, Shiyu, Liu, Shuai, Yang, Shaokang, Yang, Cheng, So, Hayden Kwok-Hay, Wong, Ngai
Formato:	Preprint
Publicado:	2026
Materias:	Computer Vision and Pattern Recognition Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

GuiLoMo: Allocating Expert Number and Rank for LoRA-MoE via Bilevel Optimization with GuidedSelection Vectors
por: Zhang, Hengyuan, et al.
Publicado: (2025)

Beyond Outliers: A Data-Free Layer-wise Mixed-Precision Quantization Approach Driven by Numerical and Structural Dual-Sensitivity
por: Zhang, Hengyuan, et al.
Publicado: (2026)

Find Your Optimal Teacher: Personalized Data Synthesis via Router-Guided Multi-Teacher Distillation
por: Zhang, Hengyuan, et al.
Publicado: (2025)

TreeReview: A Dynamic Tree of Questions Framework for Deep and Efficient LLM-based Scientific Peer Review
por: Chang, Yuan, et al.
Publicado: (2025)

A Composable Dynamic Sparse Dataflow Architecture for Efficient Event-based Vision Processing on FPGA
por: Gao, Yizhao, et al.
Publicado: (2024)

Co-designing a Sub-millisecond Latency Event-based Eye Tracking System with Submanifold Sparse CNN
por: Zhang, Baoheng, et al.
Publicado: (2024)

Incremental Residual Concept Bottleneck Models
por: Shang, Chenming, et al.
Publicado: (2024)

Adaptive Residual-Update Steering for Low-Overhead Hallucination Mitigation in Large Vision Language Models
por: Zou, Zhengtao, et al.
Publicado: (2025)

INTER: Mitigating Hallucination in Large Vision-Language Models by Interaction Guidance Sampling
por: Dong, Xin, et al.
Publicado: (2025)

SpikeMOT: Event-based Multi-Object Tracking with Sparse Motion Features
por: Wang, Song, et al.
Publicado: (2023)

DyBit: Dynamic Bit-Precision Numbers for Efficient Quantized Neural Network Inference
por: Zhou, Jiajun, et al.
Publicado: (2023)

Mitigating Hallucinations in Large Vision-Language Models with Internal Fact-based Contrastive Decoding
por: Wang, Chao, et al.
Publicado: (2025)

Lifecycle Cost-Effectiveness Modeling for Redundancy-Enhanced Multi-Chiplet Architectures
por: Liu, Zizhen, et al.
Publicado: (2026)

SAVER: Mitigating Hallucinations in Large Vision-Language Models via Style-Aware Visual Early Revision
por: Li, Zhaoxu, et al.
Publicado: (2025)

SAGE: Sink-Aware Grounded Decoding for Multimodal Hallucination Mitigation
por: Shukla, Tripti, et al.
Publicado: (2026)

TATAA: Programmable Mixed-Precision Transformer Acceleration with a Transformable Arithmetic Architecture
por: Wu, Jiajun, et al.
Publicado: (2024)

SAKED: Mitigating Hallucination in Large Vision-Language Models via Stability-Aware Knowledge Enhanced Decoding
por: Li, Zhaoxu, et al.
Publicado: (2026)

Efficient Contrastive Decoding with Probabilistic Hallucination Detection - Mitigating Hallucinations in Large Vision Language Models -
por: Fieback, Laura, et al.
Publicado: (2025)

Mitigating Hallucinations in Large Vision-Language Models with Instruction Contrastive Decoding
por: Wang, Xintong, et al.
Publicado: (2024)

Thinking in Uncertainty: Mitigating Hallucinations in MLRMs with Latent Entropy-Aware Decoding
por: Xu, Zhongxing, et al.
Publicado: (2026)

First Logit Boosting: Visual Grounding Method to Mitigate Object Hallucination in Large Vision-Language Models
por: Ha, Jiwoo, et al.
Publicado: (2026)

Mitigating Diffusion Model Hallucinations with Dynamic Guidance
por: Triaridis, Kostas, et al.
Publicado: (2025)

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

CodeComp: Structural KV Cache Compression for Agentic Coding
por: Chen, Qiujiang, et al.
Publicado: (2026)

Mitigating Object Hallucination in Large Vision-Language Models via Image-Grounded Guidance
por: Zhao, Linxi, et al.
Publicado: (2024)

Mitigating Object Hallucinations in Vision-Language Models through Region-Aware Attention Recalibration
por: Xu, Yuanzhi, et al.
Publicado: (2026)

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

Delve into Visual Contrastive Decoding for Hallucination Mitigation of Large Vision-Language Models
por: Lee, Yi-Lun, et al.
Publicado: (2024)

Residual-Mass Accounting for Partial-KV Decoding
por: Hoshi, Yasuto, et al.
Publicado: (2026)

Mixture of Decoding: An Attention-Inspired Adaptive Decoding Strategy to Mitigate Hallucinations in Large Vision-Language Models
por: Chen, Xinlong, et al.
Publicado: (2025)

D-QRELO: Training- and Data-Free Delta Compression for Large Language Models via Quantization and Residual Low-Rank Approximation
por: Li, Junlin, et al.
Publicado: (2026)

Cooperative Advisory Residual Policies for Congestion Mitigation
por: Hasan, Aamir, et al.
Publicado: (2024)

MINT: Mitigating Hallucinations in Large Vision-Language Models via Token Reduction
por: Wang, Chao, et al.
Publicado: (2025)

Decoding by Perturbation: Mitigating MLLM Hallucinations via Dynamic Textual Perturbation
por: Jia, Sihang, et al.
Publicado: (2026)

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

SECOND: Mitigating Perceptual Hallucination in Vision-Language Models via Selective and Contrastive Decoding
por: Park, Woohyeon, et al.
Publicado: (2025)

Self-Correcting Decoding with Generative Feedback for Mitigating Hallucinations in Large Vision-Language Models
por: Zhang, Ce, et al.
Publicado: (2025)

Watch Closely: Mitigating Object Hallucinations in Large Vision-Language Models with Disentangled Decoding
por: Ma, Ruiqi, et al.
Publicado: (2025)

HELPD: Mitigating Hallucination of LVLMs by Hierarchical Feedback Learning with Vision-enhanced Penalty Decoding
por: Yuan, Fan, et al.
Publicado: (2024)

Retrieval Visual Contrastive Decoding to Mitigate Object Hallucinations in Large Vision-Language Models
por: Lee, Jihoon, et al.
Publicado: (2025)