zhangchenxu/RB-Qwen2.5-VL-7B-Instruct-vlr_syn_filtered_10k_exp6_hybrid_nothink-GRPO_step256
8B • Updated • 2
Zhangchen Xu PRO
zhangchenxu
AI & ML interests
LLM Data, Alignment, Post-Training, Safety
Recent Activity
authored a paper about 1 month ago
SOSBENCH: Benchmarking Safety Alignment on Scientific Knowledge authored a paper about 1 month ago
Building a Foundational Guardrail for General Agentic Systems via
Synthetic Data authored a paper about 1 month ago
PersonaMem-v2: Towards Personalized Intelligence via Learning Implicit User Personas and Agentic MemoryOrganizations
zhangchenxu/RB-Qwen2.5-VL-7B-Instruct-vlr_syn_filtered_10k_exp6_hybrid_nothink-GRPO_step144
8B • Updated • 4
zhangchenxu/Qwen2.5-VL-7B-Instruct-SFT-visualsphinx_10k_random-LR2.0e-5-EPOCHS3-LF
Image-Text-to-Text • 8B • Updated • 1
zhangchenxu/Qwen2.5-VL-7B-Instruct-SFT-visualsphinx_10k_reject-LR2.0e-5-EPOCHS3-LF
Image-Text-to-Text • 8B • Updated • 1
zhangchenxu/TinyV-1.5B-Think
Text Generation • 2B • Updated • 5
zhangchenxu/TinyV-Qwen3-1.7B-Think
Text Generation • 2B • Updated • 10 • 3
zhangchenxu/TinyV-Qwen3-1.7B
Text Generation • 2B • Updated • 13
zhangchenxu/TinyV-1.5B
Text Generation • 2B • Updated • 181 • • 1
zhangchenxu/Qwen2.5-VL-7B-Instruct-vlr_syn_filtered_10k_exp12_nothink-GRPO-01_step256
8B • Updated • 2
zhangchenxu/gemma-2-2b-magpie-gemma2-9b-flash
Text Generation • 3B • Updated • 3
zhangchenxu/Llama-2-7b-Alpaca52k-GPT4
Text Generation • 7B • Updated • 4
zhangchenxu/Llama-2-7b-Alpaca52k
Text Generation • 7B • Updated • 3