steve z's picture

steve z PRO

stzhao

·

https://zhaoshitian.github.io/

zhaoshitian

AI & ML interests

None yet

Recent Activity

upvoted a paper 2 days ago

MineWorld: a Real-Time and Open-Source Interactive World Model on Minecraft

authored a paper 5 days ago

OmniCaptioner: One Captioner to Rule Them All

upvoted a paper 5 days ago

OmniCaptioner: One Captioner to Rule Them All

View all activity

Organizations

stzhao's activity

upvoted a paper 2 days ago

MineWorld: a Real-Time and Open-Source Interactive World Model on Minecraft

Paper • 2504.08388 • Published 5 days ago • 37

upvoted a paper 5 days ago

OmniCaptioner: One Captioner to Rule Them All

Paper • 2504.07089 • Published 7 days ago • 17

upvoted a collection 7 days ago

Kimi-VL-A3B

Moonshot's efficient MoE VLMs, exceptional on agent, long-context, and thinking • 6 items • Updated 4 days ago • 58

upvoted a collection 15 days ago

LeX-Art

8 items • Updated 15 days ago • 3

upvoted 2 papers 19 days ago

LeX-Art: Rethinking Text Generation via Scalable High-Quality Data Synthesis

Paper • 2503.21749 • Published 20 days ago • 25

Lumina-Image 2.0: A Unified and Efficient Image Generative Framework

Paper • 2503.21758 • Published 20 days ago • 18

upvoted 2 papers 26 days ago

Med-R1: Reinforcement Learning for Generalizable Medical Reasoning in Vision-Language Models

Paper • 2503.13939 • Published 29 days ago • 4

CLS-RL: Image Classification with Rule-Based Reinforcement Learning

Paper • 2503.16188 • Published 27 days ago • 9

upvoted an article 2 months ago

Article

Open-source DeepResearch – Freeing our search agents

Feb 4

• 1.22k

upvoted a paper 3 months ago

IMAGINE-E: Image Generation Intelligence Evaluation of State-of-the-art Text-to-Image Models

Paper • 2501.13920 • Published Jan 23 • 17

upvoted 2 collections 3 months ago

Flux_SD3_MJ_Dalle_Human_Annotation_Sets

A Datatest of a 2M+ human annotations that was split into three modalities: Preference, Coherence, Text-to-Image Alignment • 3 items • Updated Dec 12, 2024 • 3

Rapidata Benchmark Data

The data that powers our text-2-image leaderboard • 8 items • Updated Mar 11 • 5

upvoted a collection 4 months ago

Open Image Preferences

Containing all artifacts for the Stable Diffusion 3.5L vs Flux Dev image preference community sprint. • 14 items • Updated Dec 19, 2024 • 9

upvoted 3 papers 6 months ago

Boosting Open-Domain Continual Learning via Leveraging Intra-domain Category-aware Prototype

Paper • 2408.09984 • Published Aug 19, 2024 • 1

Causal-CoG: A Causal-Effect Look at Context Generation for Boosting Multi-modal Language Models

Paper • 2312.06685 • Published Dec 9, 2023 • 1

Unleashing the Potentials of Likelihood Composition for Multi-modal Language Models

Paper • 2410.00363 • Published Oct 1, 2024 • 1

upvoted 3 collections 6 months ago

M-A-P Full Paper List

26 items • Updated Oct 8, 2024 • 7

MulitUI

MultiUI: 7M multimodal UI instructions • 5 items • Updated Oct 19, 2024 • 7

From screenshots to HTML

WebSight is a dataset of 823,000 HTML/CSS codes representing synthetically generated English websites, each accompanied by a corresponding screenshot. • 4 items • Updated Apr 15, 2024 • 21

upvoted a paper 6 months ago

Diffusion Models Are Real-Time Game Engines

Paper • 2408.14837 • Published Aug 27, 2024 • 126