Tianyi Jiang

LumosJiang

·

AI & ML interests

None yet

Recent Activity

upvoted a paper about 17 hours ago

SearchEyes: Towards Frontier Multimodal Deep Search Intelligence via Search World Simulation

upvoted a paper about 1 month ago

Rethinking VLM Representation for VLA Initialization

upvoted a paper about 2 months ago

DelTA: Discriminative Token Credit Assignment for Reinforcement Learning from Verifiable Rewards

View all activity

Organizations

None yet

LumosJiang 's models 4

LumosJiang/qwen3-8b-base-sft-open-thoughts-114k-800steps

8B • Updated May 14 • 1

LumosJiang/qwen3-8b-base-sft-open-thoughts-114k-400steps

8B • Updated May 11 • 1

LumosJiang/Qwen3-8B-Base-SFT-AM-Thinking-v1-Distilled-Code-600steps

Text Generation • 8B • Updated Apr 22 • 7

LumosJiang/Qwen3-8B-Base-SFT-AM-Thinking-v1-Distilled-Code-1800steps

Text Generation • 8B • Updated Apr 22 • 6