Picture for Junjie Ke

Junjie Ke

Calibrated Multi-Preference Optimization for Aligning Diffusion Models

Add code
Feb 04, 2025
Viaarxiv icon

Cropper: Vision-Language Model for Image Cropping through In-Context Learning

Add code
Aug 14, 2024
Figure 1 for Cropper: Vision-Language Model for Image Cropping through In-Context Learning
Figure 2 for Cropper: Vision-Language Model for Image Cropping through In-Context Learning
Figure 3 for Cropper: Vision-Language Model for Image Cropping through In-Context Learning
Figure 4 for Cropper: Vision-Language Model for Image Cropping through In-Context Learning
Viaarxiv icon

ArtVLM: Attribute Recognition Through Vision-Based Prefix Language Modeling

Add code
Aug 07, 2024
Figure 1 for ArtVLM: Attribute Recognition Through Vision-Based Prefix Language Modeling
Figure 2 for ArtVLM: Attribute Recognition Through Vision-Based Prefix Language Modeling
Figure 3 for ArtVLM: Attribute Recognition Through Vision-Based Prefix Language Modeling
Figure 4 for ArtVLM: Attribute Recognition Through Vision-Based Prefix Language Modeling
Viaarxiv icon

Optical Diffusion Models for Image Generation

Add code
Jul 15, 2024
Viaarxiv icon

Parrot: Pareto-optimal Multi-Reward Reinforcement Learning Framework for Text-to-Image Generation

Add code
Jan 11, 2024
Figure 1 for Parrot: Pareto-optimal Multi-Reward Reinforcement Learning Framework for Text-to-Image Generation
Figure 2 for Parrot: Pareto-optimal Multi-Reward Reinforcement Learning Framework for Text-to-Image Generation
Figure 3 for Parrot: Pareto-optimal Multi-Reward Reinforcement Learning Framework for Text-to-Image Generation
Figure 4 for Parrot: Pareto-optimal Multi-Reward Reinforcement Learning Framework for Text-to-Image Generation
Viaarxiv icon

Rich Human Feedback for Text-to-Image Generation

Add code
Dec 15, 2023
Figure 1 for Rich Human Feedback for Text-to-Image Generation
Figure 2 for Rich Human Feedback for Text-to-Image Generation
Figure 3 for Rich Human Feedback for Text-to-Image Generation
Figure 4 for Rich Human Feedback for Text-to-Image Generation
Viaarxiv icon

Forward-Forward Training of an Optical Neural Network

Add code
May 30, 2023
Viaarxiv icon

MRET: Multi-resolution Transformer for Video Quality Assessment

Add code
Mar 29, 2023
Viaarxiv icon

VILA: Learning Image Aesthetics from User Comments with Vision-Language Pretraining

Add code
Mar 24, 2023
Figure 1 for VILA: Learning Image Aesthetics from User Comments with Vision-Language Pretraining
Figure 2 for VILA: Learning Image Aesthetics from User Comments with Vision-Language Pretraining
Figure 3 for VILA: Learning Image Aesthetics from User Comments with Vision-Language Pretraining
Figure 4 for VILA: Learning Image Aesthetics from User Comments with Vision-Language Pretraining
Viaarxiv icon

MUSIQ: Multi-scale Image Quality Transformer

Add code
Aug 12, 2021
Figure 1 for MUSIQ: Multi-scale Image Quality Transformer
Figure 2 for MUSIQ: Multi-scale Image Quality Transformer
Figure 3 for MUSIQ: Multi-scale Image Quality Transformer
Figure 4 for MUSIQ: Multi-scale Image Quality Transformer
Viaarxiv icon