Imagen de Portada

A Training-Free, Task-Agnostic Framework for Enhancing MLLM Performance on High-Resolution Images

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Lee, Jaeseong, Choi, Yeeun, Choi, Heechan, Kim, Hanjung, Kim, Seonjoo
Formato:	Preprint
Publicado:	2025
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

Fourier-Guided Attention Upsampling for Image Super-Resolution
por: Choi, Daejune, et al.
Publicado: (2025)

MambaEye: A Size-Agnostic Visual Encoder with Causal Sequential Processing
por: Choi, Changho, et al.
Publicado: (2025)

Training-Free Restoration of Pruned Neural Networks
por: Lee, Keonho, et al.
Publicado: (2025)

Addressing Diverging Training Costs using BEVRestore for High-resolution Bird's Eye View Map Construction
por: Kim, Minsu, et al.
Publicado: (2024)

Colorful Cutout: Enhancing Image Data Augmentation with Curriculum Learning
por: Choi, Juhwan, et al.
Publicado: (2024)

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

LD-Pruner: Efficient Pruning of Latent Diffusion Models using Task-Agnostic Insights
por: Castells, Thibault, et al.
Publicado: (2024)

FreeVA: Offline MLLM as Training-Free Video Assistant
por: Wu, Wenhao
Publicado: (2024)

Fair Generation without Unfair Distortions: Debiasing Text-to-Image Generation with Entanglement-Free Attention
por: Park, Jeonghoon, et al.
Publicado: (2025)

Generating Accurate and Detailed Captions for High-Resolution Images
por: Lee, Hankyeol, et al.
Publicado: (2025)

EuraGovExam: A Multilingual Multimodal Benchmark from Real-World Civil Service Exams
por: Kim, Jaeseong, et al.
Publicado: (2026)

Slot-MLLM: Object-Centric Visual Tokenization for Multimodal LLM
por: Chi, Donghwan, et al.
Publicado: (2025)

Safety Alignment Backfires: Preventing the Re-emergence of Suppressed Concepts in Fine-tuned Text-to-Image Diffusion Models
por: Kim, Sanghyun, et al.
Publicado: (2024)

Safeguard Text-to-Image Diffusion Models with Human Feedback Inversion
por: Kim, Sanghyun, et al.
Publicado: (2024)

Teacher as a Lenient Expert: Teacher-Agnostic Data-Free Knowledge Distillation
por: Shin, Hyunjune, et al.
Publicado: (2024)

Training-Free Global Geometric Association for 4D LiDAR Panoptic Segmentation
por: Oh, Gyeongrok, et al.
Publicado: (2025)

VisDoT : Enhancing Visual Reasoning through Human-Like Interpretation Grounding and Decomposition of Thought
por: Lee, Eunsoo, et al.
Publicado: (2026)

DiffExp: Efficient Exploration in Reward Fine-tuning for Text-to-Image Diffusion Models
por: Chae, Daewon, et al.
Publicado: (2025)

APT: Improving Diffusion Models for High Resolution Image Generation with Adaptive Path Tracing
por: Han, Sangmin, et al.
Publicado: (2025)

FIFO-Diffusion: Generating Infinite Videos from Text without Training
por: Kim, Jihwan, et al.
Publicado: (2024)

3D Occupancy Prediction with Low-Resolution Queries via Prototype-aware View Transformation
por: Oh, Gyeongrok, et al.
Publicado: (2025)

FreeSliders: Training-Free, Modality-Agnostic Concept Sliders for Fine-Grained Diffusion Control in Images, Audio, and Video
por: Ezra, Rotem, et al.
Publicado: (2025)

When Eyes Betray AI: Social Gaze Consistency as a Semantic Cue for AI-Generated Image Detection
por: Kim, Jihyeon, et al.
Publicado: (2026)

CLIP Tricks You: Training-free Token Pruning for Efficient Pixel Grounding in Large VIsion-Language Models
por: Lee, Sangin, et al.
Publicado: (2026)

RoAD Benchmark: How LiDAR Models Fail under Coupled Domain Shifts and Label Evolution
por: Lee, Subeen, et al.
Publicado: (2026)

RITUAL: Random Image Transformations as a Universal Anti-hallucination Lever in Large Vision Language Models
por: Woo, Sangmin, et al.
Publicado: (2024)

mEOL: Training-Free Instruction-Guided Multimodal Embedder for Vector Graphics and Image Retrieval
por: Kim, Kyeong Seon, et al.
Publicado: (2026)

Text-Guided Variational Image Generation for Industrial Anomaly Detection and Segmentation
por: Lee, Mingyu, et al.
Publicado: (2024)

Training-Free Reward-Guided Image Editing via Trajectory Optimal Control
por: Chang, Jinho, et al.
Publicado: (2025)

Evaluating Visual Prompts with Eye-Tracking Data for MLLM-Based Human Activity Recognition
por: Choi, Jae Young, et al.
Publicado: (2026)

Reciprocal Attention Mixing Transformer for Lightweight Image Restoration
por: Choi, Haram, et al.
Publicado: (2023)

CIPHER: Counterfeit Image Pattern High-level Examination via Representation
por: Kim, Kyeonghun, et al.
Publicado: (2026)

Free$^2$Guide: Training-Free Text-to-Video Alignment using Image LVLM
por: Kim, Jaemin, et al.
Publicado: (2024)

Culture-TRIP: Culturally-Aware Text-to-Image Generation with Iterative Prompt Refinement
por: Jeong, Suchae, et al.
Publicado: (2025)

Training-Free Label Space Alignment for Universal Domain Adaptation
por: Lee, Dujin, et al.
Publicado: (2025)

From Street to Orbit: Training-Free Cross-View Retrieval via Location Semantics and LLM Guidance
por: Min, Jeongho, et al.
Publicado: (2025)

StableSketcher: Enhancing Diffusion Model for Pixel-based Sketch Generation via Visual Question Answering Feedback
por: Park, Jiho, et al.
Publicado: (2025)

What Happens When: Learning Temporal Orders of Events in Videos
por: Ahn, Daechul, et al.
Publicado: (2025)

Focus, Don't Prune: Identifying Instruction-Relevant Regions for Information-Rich Image Understanding
por: Kwon, Mincheol, et al.
Publicado: (2026)

SceneAdapt: Scene-aware Adaptation of Human Motion Diffusion
por: Cho, Jungbin, et al.
Publicado: (2025)