arXiv:2507.12415
Mingzhe Du PRO
Elfsong
AI & ML interests
Code Generation / Preference Alignment / Bias Mitigation
Recent Activity
upvoted
a
paper
about 16 hours ago
Reasoning with Confidence: Efficient Verification of LLM Reasoning Steps
via Uncertainty Heads
upvoted
a
paper
about 1 month ago
Towards Agentic RAG with Deep Reasoning: A Survey of RAG-Reasoning
Systems in LLMs
upvoted
a
paper
about 1 month ago
ExGRPO: Learning to Reason from Experience
Organizations
spaces
10
models
34
Elfsong/Llama-3.1-8B-Instruct-QG-SFT-Model
Text Generation
•
8B
•
Updated
•
13
Elfsong/Afterburner_3B_100
3B
•
Updated
Elfsong/Afterburner_3B_120
3B
•
Updated
•
1
Elfsong/Qwen2.5-Coder-3B-Instruct-Venus-Cold-Start
Text Generation
•
3B
•
Updated
•
2
Elfsong/qwen_3b_sft_dpo_batch_2_ga_8_lr_4e5_checkpoint_1200
Text Generation
•
3B
•
Updated
•
2
Elfsong/Qwen2.5-3B-DPO-Batch-8-LR-4e-5
Text Generation
•
3B
•
Updated
Elfsong/Qwen2.5-3B-SFT-Batch-8-LR-3e-5
Text Generation
•
3B
•
Updated
Elfsong/Qwen2.5-3B-Instruct-DPO-Venus
Text Generation
•
3B
•
Updated
•
2
Elfsong/Qwen2.5-Coder-7B-Instruct-GRPO-test
Updated
Elfsong/Qwen2.5-Coder-14B-Instruct-GRPO-test
Updated
datasets
79
Elfsong/swe-perf-reasoning
Viewer
•
Updated
•
292
•
76
•
1
Elfsong/swe-perf
Updated
•
4
Elfsong/cisco_cr
Viewer
•
Updated
•
104
•
2
Elfsong/Venus
Viewer
•
Updated
•
9.3k
•
109
•
6
Elfsong/new_cisco_cr_uc3
Viewer
•
Updated
•
39
•
9
Elfsong/Venus_Anotation
Viewer
•
Updated
•
12
•
41
Elfsong/cisco-cr-changes
Viewer
•
Updated
•
52
•
4
Elfsong/cisco-cr
Viewer
•
Updated
•
39
•
10
Elfsong/Venus_Python
Viewer
•
Updated
•
1.28k
•
47
Elfsong/Venus_Python_GRPO_Reasoning_Cold_Start
Viewer
•
Updated
•
898
•
7