Cover Image

Explore How to Inject Beneficial Noise in MLLMs

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhu, Ruishu, Huang, Sida, Jiao, Ziheng, Zhang, Hongyuan
Format:	Preprint
Published:	2025
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

Variational Positive-incentive Noise: How Noise Benefits Models
by: Zhang, Hongyuan, et al.
Published: (2023)

Enhance Vision-Language Alignment with Noise
by: Huang, Sida, et al.
Published: (2024)

CNN2GNN: How to Bridge CNN with GNN
by: Jiao, Ziheng, et al.
Published: (2024)

Data Augmentation of Contrastive Learning is Estimating Positive-incentive Noise
by: Zhang, Hongyuan, et al.
Published: (2024)

ViewMask-1-to-3: Multi-View Consistent Image Generation via Multimodal Diffusion Models
by: Zhu, Ruishu, et al.
Published: (2025)

Laytrol: Preserving Pretrained Knowledge in Layout Control for Multimodal Diffusion Transformers
by: Huang, Sida, et al.
Published: (2025)

SpatialTree: How Spatial Abilities Branch Out in MLLMs
by: Xiao, Yuxi, et al.
Published: (2025)

GRPO-RM: Fine-Tuning Representation Models via GRPO-Driven Reinforcement Learning
by: Xu, Yanchen, et al.
Published: (2025)

Mitigating Backdoor Attack by Injecting Proactive Defensive Backdoor
by: Wei, Shaokui, et al.
Published: (2024)

SAILViT: Towards Robust and Generalizable Visual Backbones for MLLMs via Gradual Feature Refinement
by: Yin, Weijie, et al.
Published: (2025)

GOBench: Benchmarking Geometric Optics Generation and Understanding of MLLMs
by: Zhu, Xiaorong, et al.
Published: (2025)

Noise-Injected Spiking Graph Convolution for Energy-Efficient 3D Point Cloud Denoising
by: Li, Zikuan, et al.
Published: (2025)

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

Multimodal Continual Learning with MLLMs from Multi-scenario Perspectives
by: Jiang, Kai, et al.
Published: (2025)

Exploring the Design Space of Visual Context Representation in Video MLLMs
by: Du, Yifan, et al.
Published: (2024)

Revisiting Cross-Attention Mechanisms: Leveraging Beneficial Noise for Domain-Adaptive Learning
by: Zang, Zelin, et al.
Published: (2026)

SegAgent: Exploring Pixel Understanding Capabilities in MLLMs by Imitating Human Annotator Trajectories
by: Zhu, Muzhi, et al.
Published: (2025)

X-Stream: Exploring MLLMs as Multiplexers for Multi-Stream Understanding
by: Sun, Peiwen, et al.
Published: (2026)

Explore the Hallucination on Low-level Perception for MLLMs
by: Sun, Yinan, et al.
Published: (2024)

Research on World Models Is Not Merely Injecting World Knowledge into Specific Tasks
by: Zeng, Bohan, et al.
Published: (2026)

The Unseen Bias: How Norm Discrepancy in Pre-Norm MLLMs Leads to Visual Information Loss
by: Li, Bozhou, et al.
Published: (2025)

Human Cognitive Benchmarks Reveal Foundational Visual Gaps in MLLMs
by: Huang, Jen-Tse, et al.
Published: (2025)

Exploring How Generative MLLMs Perceive More Than CLIP with the Same Vision Encoder
by: Li, Siting, et al.
Published: (2024)

Towards Universal Video MLLMs with Attribute-Structured and Quality-Verified Instructions
by: Li, Yunheng, et al.
Published: (2026)

Touch-R1: Reinforcing Touch Reasoning in MLLMs
by: Lai, Yingxin, et al.
Published: (2026)

From Training-Free to Adaptive: Empirical Insights into MLLMs' Understanding of Detection Information
by: Jiao, Qirui, et al.
Published: (2024)

Mixture of Noise for Pre-Trained Model-Based Class-Incremental Learning
by: Jiang, Kai, et al.
Published: (2025)

Aesthetic Image Captioning with Saliency Enhanced MLLMs
by: Tao, Yilin, et al.
Published: (2025)

VER-Bench: Evaluating MLLMs on Reasoning with Fine-Grained Visual Evidence
by: Qiang, Chenhui, et al.
Published: (2025)

Linking Perception, Confidence and Accuracy in MLLMs
by: Du, Yuetian, et al.
Published: (2026)

DetailCLIP: Injecting Image Details into CLIP's Feature Space
by: Zhang, Zilun, et al.
Published: (2022)

City Navigation in the Wild: Exploring Emergent Navigation from Web-Scale Knowledge in MLLMs
by: Dalal, Dwip, et al.
Published: (2025)

MedQ-Bench: Evaluating and Exploring Medical Image Quality Assessment Abilities in MLLMs
by: Liu, Jiyao, et al.
Published: (2025)

EOC-Bench: Can MLLMs Identify, Recall, and Forecast Objects in an Egocentric World?
by: Yuan, Yuqian, et al.
Published: (2025)

Reasoning over Video: Evaluating How MLLMs Extract, Integrate, and Reconstruct Spatiotemporal Evidence
by: Bang, Seunghwan, et al.
Published: (2026)

INoD: Injected Noise Discriminator for Self-Supervised Representation Learning in Agricultural Fields
by: Hindel, Julia, et al.
Published: (2023)

Video-MSR: Benchmarking Multi-hop Spatial Reasoning Capabilities of MLLMs
by: Zhu, Rui, et al.
Published: (2026)

FreeRet: MLLMs as Training-Free Retrievers
by: Zhu, Yuhan, et al.
Published: (2025)

When MLLMs Meet Compression Distortion: A Coding Paradigm Tailored to MLLMs
by: Liu, Jinming, et al.
Published: (2025)

EgoCoT-Bench: Benchmarking Grounded and Verifiable Operation-Centric Chain of Thought Reasoning for MLLMs
by: Dai, Yang, et al.
Published: (2026)