Joya Chen's picture

Joya Chen PRO

chenjoya

·

https://chenjoya.github.io/

chenjoya

AI & ML interests

Video LLM

Recent Activity

upvoted a paper 1 day ago

Revisiting Multimodal Positional Encoding in Vision-Language Models

upvoted a paper 2 days ago

VCode: a Multimodal Coding Benchmark with SVG as Symbolic Visual Representation

upvoted a paper 8 days ago

ChronoPlay: A Framework for Modeling Dual Dynamics and Authenticity in Game RAG Benchmarks

View all activity

Organizations

chenjoya 's models 5

chenjoya/LiveCC-7B-Base

8B • Updated Apr 25 • 12 • 6

chenjoya/LiveCC-7B-Instruct

8B • Updated Apr 25 • 796 • 40

chenjoya/Qwen2-VL-7B-LLaVAInstruct

8B • Updated Apr 16 • 4 • 1

chenjoya/Qwen2-VL-7B-LiveCCInstruct

8B • Updated Apr 14 • 1 • 1

chenjoya/videollm-online-8b-v1plus

Video-Text-to-Text • Updated Jul 13, 2024 • 13.3k • 30