Joey

joeysun98

6 4

·

AI & ML interests

Diffusion models, text-to-image generation, vision-language models, image editing

Recent Activity

upvoted a paper 3 days ago

StudentSim: Training LLM-based Student Simulators

liked a model 3 days ago

Image-editing/Emu3-Base-SFT-reasoning_super_concise-Apr17_rinp_lr1e-5-checkpoint-24000

upvoted a paper 3 days ago

StableVQ: Practical Guidelines for Stable Vector-Quantized Tokenizer Training

View all activity

Organizations

None yet

upvoted a paper 3 days ago

StudentSim: Training LLM-based Student Simulators

Paper • 2609.01591 • Published 27 days ago • 427

liked a model 3 days ago

Image-editing/Emu3-Base-SFT-reasoning_super_concise-Apr17_rinp_lr1e-5-checkpoint-24000

8B • Updated Apr 22, 2025 • 7 • 4

upvoted a paper 3 days ago

StableVQ: Practical Guidelines for Stable Vector-Quantized Tokenizer Training

Paper • 2609.26774 • Published 6 days ago • 55

liked 2 datasets 3 days ago

nateraw/midjourney-texttoimage-new

Updated Sep 8, 2022 • 261 • 21

egezort/imageGeneration

Updated Nov 4, 2022 • 17 • 3

upvoted a paper 3 days ago

Jev-Mem: System-One-Controlled Agentic Memory for Efficient AI Agents

Paper • 2609.23986 • Published 7 days ago • 27

liked a dataset 5 days ago

qwertyaditya/rick_and_morty_text_to_image

Viewer • Updated Sep 1, 2023 • 40 • 18 • 6

upvoted 3 papers 5 days ago

Refinement Is Inherently Editable: Training-Free Prompt-to-Prompt Image Editing with Generative Refinement Network

Paper • 2609.20633 • Published 11 days ago • 13

Paint-Anything: Unified Any-Color Control for Image Generation and Editing

Paper • 2609.20816 • Published 11 days ago • 56

Grounded Skill Synthesis from Code at Scale for Agentic Intelligence

Paper • 2609.05571 • Published 24 days ago • 118