Copertina

Learning to See What You Need: Gaze Attention for Multimodal Large Language Models

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Song, Junha, Heo, Byeongho, Gu, Geonmo, Choo, Jaegul, Han, Dongyoon, Yun, Sangdoo
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Computer Vision and Pattern Recognition
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

RL makes MLLMs see better than SFT
di: Song, Junha, et al.
Pubblicazione: (2025)

Rotary Position Embedding for Vision Transformer
di: Heo, Byeongho, et al.
Pubblicazione: (2024)

Masking meets Supervision: A Strong Learning Alliance
di: Heo, Byeongho, et al.
Pubblicazione: (2023)

Match me if you can: Semi-Supervised Semantic Correspondence Learning with Unpaired Images
di: Kim, Jiwon, et al.
Pubblicazione: (2023)

Token Bottleneck: One Token to Remember Dynamics
di: Kim, Taekyung, et al.
Pubblicazione: (2025)

Morphing Tokens Draw Strong Masked Image Models
di: Kim, Taekyung, et al.
Pubblicazione: (2023)

Temporal In-Context Fine-Tuning with Temporal Reasoning for Versatile Control of Video Diffusion Models
di: Kim, Kinam, et al.
Pubblicazione: (2025)

Learning with Unmasked Tokens Drives Stronger Vision Learners
di: Kim, Taekyung, et al.
Pubblicazione: (2023)

Towards Calibrated Robust Fine-Tuning of Vision-Language Models
di: Oh, Changdae, et al.
Pubblicazione: (2023)

DNNs May Determine Major Properties of Their Outputs Early, with Timing Possibly Driven by Bias
di: Park, Song, et al.
Pubblicazione: (2025)

DenseNets Reloaded: Paradigm Shift Beyond ResNets and ViTs
di: Kim, Donghyun, et al.
Pubblicazione: (2024)

SeiT++: Masked Token Modeling Improves Storage-efficient Training
di: Lee, Minhyun, et al.
Pubblicazione: (2023)

Language-only Efficient Training of Zero-shot Composed Image Retrieval
di: Gu, Geonmo, et al.
Pubblicazione: (2023)

MagiCapture: High-Resolution Multi-Concept Portrait Customization
di: Hyung, Junha, et al.
Pubblicazione: (2023)

Model Stock: All we need is just a few fine-tuned models
di: Jang, Dong-Hwan, et al.
Pubblicazione: (2024)

Oops, Wait: Token-Level Signals as a Lens into LLM Reasoning
di: Hwang, Jaehui, et al.
Pubblicazione: (2026)

Is user feedback always informative? Retrieval Latent Defending for Semi-Supervised Domain Adaptation without Source Data
di: Song, Junha, et al.
Pubblicazione: (2024)

MuCo: Multi-turn Contrastive Learning for Multimodal Embedding Model
di: Gu, Geonmo, et al.
Pubblicazione: (2026)

MaskRIS: Semantic Distortion-aware Data Augmentation for Referring Image Segmentation
di: Lee, Minhyun, et al.
Pubblicazione: (2024)

Exploring Conditions for Diffusion models in Robotic Control
di: Shin, Heeseong, et al.
Pubblicazione: (2025)

SelfSwapper: Self-Supervised Face Swapping via Shape Agnostic Masked AutoEncoder
di: Lee, Jaeseong, et al.
Pubblicazione: (2024)

Devil is in the Detail: Towards Injecting Fine Details of Image Prompt in Image Generation via Conflict-free Guidance and Stratified Attention
di: Jo, Kyungmin, et al.
Pubblicazione: (2025)

VisualScratchpad: Inference-time Visual Concepts Analysis in Vision Language Models
di: Lim, Hyesu, et al.
Pubblicazione: (2026)

Vector Prism: Animating Vector Graphics by Stratifying Semantic Structure
di: Yun, Jooyeol, et al.
Pubblicazione: (2025)

Scaling Up Personalized Image Aesthetic Assessment via Task Vector Customization
di: Yun, Jooyeol, et al.
Pubblicazione: (2024)

See What You Are Told: Visual Attention Sink in Large Multimodal Models
di: Kang, Seil, et al.
Pubblicazione: (2025)

MM-SeR: Multimodal Self-Refinement for Lightweight Image Captioning
di: Song, Junha, et al.
Pubblicazione: (2025)

DaWin: Training-free Dynamic Weight Interpolation for Robust Adaptation
di: Oh, Changdae, et al.
Pubblicazione: (2024)

Similarity of Neural Architectures using Adversarial Attack Transferability
di: Hwang, Jaehui, et al.
Pubblicazione: (2022)

Regularized Training with Generated Datasets for Name-Only Transfer of Vision-Language Models
di: Park, Minho, et al.
Pubblicazione: (2024)

Investigating Pre-Training Objectives for Generalization in Vision-Based Reinforcement Learning
di: Kim, Donghu, et al.
Pubblicazione: (2024)

HYPE: Hyperbolic Entailment Filtering for Underspecified Images and Texts
di: Kim, Wonjae, et al.
Pubblicazione: (2024)

CompoDiff: Versatile Composed Image Retrieval With Latent Diffusion
di: Gu, Geonmo, et al.
Pubblicazione: (2023)

Infinite-Homography as Robust Conditioning for Camera-Controlled Video Generation
di: Kim, Min-Jung, et al.
Pubblicazione: (2025)

Spatiotemporal Skip Guidance for Enhanced Video Diffusion Sampling
di: Hyung, Junha, et al.
Pubblicazione: (2024)

Scratching Visual Transformer's Back with Uniform Attention
di: Hyeon-Woo, Nam, et al.
Pubblicazione: (2022)

Describe What You See with Multimodal Large Language Models to Enhance Video Recommendations
di: De Nadai, Marco, et al.
Pubblicazione: (2025)

Attn-Adapter: Attention Is All You Need for Online Few-shot Learner of Vision-Language Model
di: Bui, Phuoc-Nguyen, et al.
Pubblicazione: (2025)

Grounding World Simulation Models in a Real-World Metropolis
di: Seo, Junyoung, et al.
Pubblicazione: (2026)

EgoX: Egocentric Video Generation from a Single Exocentric Video
di: Kang, Taewoong, et al.
Pubblicazione: (2025)