arxiv:2506.11930
Jiang
Dongwei
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
1 day ago
The Alignment Waltz: Jointly Training Agents to Collaborate for Safety
upvoted
a
paper
8 days ago
IA2: Alignment with ICL Activations Improves Supervised Fine-Tuning
upvoted
an
article
17 days ago
SmolLM3: smol, multilingual, long-context reasoner
Organizations
models
17
Dongwei/Qwen-2.5-7B_Base_Math_smalllr_newdata
Text Generation
•
8B
•
Updated
Dongwei/Qwen-2.5-7B_Base_Math_smalllr_longer
Text Generation
•
8B
•
Updated
•
1
Dongwei/Qwen-2.5-7B_Base_Math_smallestlr
Text Generation
•
8B
•
Updated
•
2
Dongwei/Qwen-2.5-7B_Base_Math_smallestlr_newdata
Text Generation
•
8B
•
Updated
•
3
Dongwei/Qwen-2.5-7B_Base_Math_smalllr
Text Generation
•
8B
•
Updated
•
1
•
6
Dongwei/DeepSeek-R1-Distill-Qwen-7B-GRPO_Math_lowlr
Text Generation
•
8B
•
Updated
•
3
Dongwei/DeepSeek-R1-Distill-Qwen-1.5B-GRPO_Math_smalllr
Text Generation
•
2B
•
Updated
•
3
Dongwei/Qwen2.5-1.5B-Open-R1-GRPO_Math_smalllr
Text Generation
•
2B
•
Updated
•
2
Dongwei/Qwen-2.5-7B_Math_smalllr
Text Generation
•
8B
•
Updated
Dongwei/DeepSeek-R1-Distill-Qwen-7B-GRPO_Math
Text Generation
•
8B
•
Updated
•
2