Copertina

Attention Guided Alignment in Efficient Vision-Language Models

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Mahajan, Shweta, Le, Hoang, Park, Hyojin, Farhadzadeh, Farzad, Hayat, Munawar, Porikli, Fatih
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Computer Vision and Pattern Recognition Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

DDIL: Diversity Enhancing Diffusion Distillation With Imitation Learning
di: Garrepalli, Risheek, et al.
Pubblicazione: (2024)

Resolving the Identity Crisis in Text-to-Image Generation
di: Borse, Shubhankar, et al.
Pubblicazione: (2025)

Do-Undo Bench: Reversibility for Action Understanding in Image Generation
di: Mahajan, Shweta, et al.
Pubblicazione: (2025)

Generalized Contrastive Learning for Universal Multimodal Retrieval
di: Lee, Jungsoo, et al.
Pubblicazione: (2025)

LoRA-X: Bridging Foundation Models with Training-Free Cross-Model Adaptation
di: Farhadzadeh, Farzad, et al.
Pubblicazione: (2025)

PosSAM: Panoptic Open-vocabulary Segment Anything
di: VS, Vibashan, et al.
Pubblicazione: (2024)

MADI: Masking-Augmented Diffusion with Inference-Time Scaling for Visual Editing
di: Kadambi, Shreya, et al.
Pubblicazione: (2025)

Ar2Can: An Architect and an Artist Leveraging a Canvas for Multi-Human Generation
di: Borse, Shubhankar, et al.
Pubblicazione: (2025)

Sort-free Gaussian Splatting via Weighted Sum Rendering
di: Hou, Qiqi, et al.
Pubblicazione: (2024)

CustomKD: Customizing Large Vision Foundation for Edge Model Improvement via Knowledge Distillation
di: Lee, Jungsoo, et al.
Pubblicazione: (2025)

Neural Graphics Texture Compression Supporting Random Access
di: Farhadzadeh, Farzad, et al.
Pubblicazione: (2024)

Tripartite Weight-Space Ensemble for Few-Shot Class-Incremental Learning
di: Lee, Juntae, et al.
Pubblicazione: (2025)

HyperNet Fields: Efficiently Training Hypernetworks without Ground Truth by Learning Weight Trajectories
di: Hedlin, Eric, et al.
Pubblicazione: (2024)

Progressive Multi-granular Alignments for Grounded Reasoning in Large Vision-Language Models
di: Le, Quang-Hung, et al.
Pubblicazione: (2024)

ConsNoTrainLoRA: Data-driven Weight Initialization of Low-rank Adapters using Constraints
di: Das, Debasmit, et al.
Pubblicazione: (2025)

FLoC: Facility Location-Based Efficient Visual Token Compression for Long Video Understanding
di: Cho, Janghoon, et al.
Pubblicazione: (2025)

Personalized OVSS: Understanding Personal Concept in Open-Vocabulary Semantic Segmentation
di: Park, Sunghyun, et al.
Pubblicazione: (2025)

Object-Centric Diffusion for Efficient Video Editing
di: Kahatapitiya, Kumara, et al.
Pubblicazione: (2024)

ForeSea: AI Forensic Search with Multi-modal Queries for Video Surveillance
di: Park, Hyojin, et al.
Pubblicazione: (2026)

OCAI: Improving Optical Flow Estimation by Occlusion and Consistency Aware Interpolation
di: Jeong, Jisoo, et al.
Pubblicazione: (2024)

STAR: Stage-Wise Attention-Guided Token Reduction for Efficient Large Vision-Language Models Inference
di: Guo, Yichen, et al.
Pubblicazione: (2025)

Flashbacks to Harmonize Stability and Plasticity in Continual Learning
di: Mahmoodi, Leila, et al.
Pubblicazione: (2025)

Hidden Bias in the Machine: Stereotypes in Text-to-Image Models
di: Porikli, Sedat, et al.
Pubblicazione: (2025)

Memory-Efficient Fine-Tuning Diffusion Transformers via Dynamic Patch Sampling and Block Skipping
di: Park, Sunghyun, et al.
Pubblicazione: (2026)

Attention-aware Inference Optimizations for Large Vision-Language Models with Memory-efficient Decoding
di: Ilhan, Fatih, et al.
Pubblicazione: (2026)

ToSA: Token Selective Attention for Efficient Vision Transformers
di: Singh, Manish Kumar, et al.
Pubblicazione: (2024)

SubZero: Composing Subject, Style, and Action via Zero-Shot Personalization
di: Borse, Shubhankar, et al.
Pubblicazione: (2025)

Cycle Consistency as Reward: Learning Image-Text Alignment without Human Preferences
di: Bahng, Hyojin, et al.
Pubblicazione: (2025)

Low-Latency Neural Stereo Streaming
di: Hou, Qiqi, et al.
Pubblicazione: (2024)

MultiHuman-Testbench: Benchmarking Image Generation for Multiple Humans
di: Borse, Shubhankar, et al.
Pubblicazione: (2025)

Improved Alignment of Modalities in Large Vision Language Models
di: Jangra, Kartik, et al.
Pubblicazione: (2025)

Efficient Medical Vision-Language Alignment Through Adapting Masked Vision Models
di: Lian, Chenyu, et al.
Pubblicazione: (2025)

Enhancing Domain Adaptation through Prompt Gradient Alignment
di: Phan, Hoang, et al.
Pubblicazione: (2024)

LLM-Guided Diagnostic Evidence Alignment for Medical Vision-Language Pretraining under Limited Pairing
di: Yan, Huimin, et al.
Pubblicazione: (2026)

RadZero: Similarity-Based Cross-Attention for Explainable Vision-Language Alignment in Chest X-ray with Zero-Shot Multi-Task Capability
di: Park, Jonggwon, et al.
Pubblicazione: (2025)

ZIP: An Efficient Zeroth-order Prompt Tuning for Black-box Vision-Language Models
di: Park, Seonghwan, et al.
Pubblicazione: (2025)

CA-LoRA: Concept-Aware LoRA for Domain-Aligned Segmentation Dataset Generation
di: Park, Minho, et al.
Pubblicazione: (2025)

FLAVARS: A Multimodal Foundational Language and Vision Alignment Model for Remote Sensing
di: Corley, Isaac, et al.
Pubblicazione: (2025)

Synthesizer Based Efficient Self-Attention for Vision Tasks
di: Zhu, Guangyang, et al.
Pubblicazione: (2022)

Ultrasound Vision-Language Alignment via Contrastive Learning
di: Lyu, Zhuoyang, et al.
Pubblicazione: (2026)