Toward Robust Hyper-Detailed Image Captioning: A Multiagent Approach and Dual Evaluation Metrics for Factuality and Coverage
Paper
•
2412.15484
•
Published
•
14
shin
chaehun
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
about 1 month ago
Unified Speech-Text Pretraining for Spoken Dialog Modeling
authored
a paper
about 1 month ago
Large-Scale Text-to-Image Model with Inpainting is a Zero-Shot
Subject-Driven Image Generator
Organizations
None yet
chaehun's activity
upvoted
a
paper
15 days ago
upvoted
a
paper
about 1 month ago
authored
a
paper
about 1 month ago
upvoted
a
paper
about 1 month ago
commented
a
paper
about 1 month ago
authored
5
papers
about 1 month ago
ControlDreamer: Stylized 3D Generation with Multi-View ControlNet
Paper
•
2312.01129
•
Published
•
5
PriorGrad: Improving Conditional Denoising Diffusion Models with Data-Dependent Adaptive Prior
Paper
•
2106.06406
•
Published
Perception Prioritized Training of Diffusion Models
Paper
•
2204.00227
•
Published
Disentangled Motion Modeling for Video Frame Interpolation
Paper
•
2406.17256
•
Published
Style-Friendly SNR Sampler for Style-Driven Generation
Paper
•
2411.14793
•
Published
•
36
upvoted
a
paper
about 1 month ago