Miao Li

oaimli

1 1

AI & ML interests

Natural Language Processing

Recent Activity

updated a model 12 days ago

oaimli/sft_longpt_full_qwen3_4b_instruct_2507

published a model 12 days ago

oaimli/sft_longpt_full_qwen3_4b_instruct_2507

updated a model 13 days ago

oaimli/sft_longpt_full_gemma3_4b_it

View all activity

Organizations

None yet

oaimli 's models 37

oaimli/sft_longpt_full_qwen3_4b_instruct_2507

Text Generation • 4B • Updated 12 days ago • 877 • 1

oaimli/sft_longpt_full_gemma3_4b_it

Image-Text-to-Text • 4B • Updated 13 days ago • 369

oaimli/sft_longpt_full_qwen3_4b_instruct_2507_no_starting_think

Text Generation • 4B • Updated 14 days ago • 8

oaimli/sft_longpt_full_gemma3_4b_it_no_starting_think

Image-Text-to-Text • 4B • Updated 15 days ago • 1

oaimli/grpo_longpt_direct_gemma3_4b_it

Image-Text-to-Text • 4B • Updated 15 days ago • 32

oaimli/scitrek_grpo_full_longrlvr_qwen3_4b_instruct_2507_660

Text Generation • 4B • Updated 25 days ago • 31

oaimli/scitrek_grpo_full_longrlvr_qwen3_4b_instruct_2507_280

Text Generation • 4B • Updated Jul 20 • 10

oaimli/pgpo_grpo_proxy_scitrek_gemma3_4b_it

Image-Text-to-Text • 4B • Updated Jul 17 • 31

oaimli/scitrek_grpo_full_loongrl_qwen3_4b_instruct_2507

Text Generation • 4B • Updated Jul 16 • 112

oaimli/pgpo_grpo_proxy_scitrek_qwen3_4b_instruct_2507

Text Generation • 4B • Updated Jul 12 • 75

oaimli/longtune_scitrek_grounding_reinforcement_gemma_0

Image-Text-to-Text • 4B • Updated Jul 9 • 10

oaimli/longtune_scitrek_simple_sft_gemma

Image-Text-to-Text • 4B • Updated Jul 9 • 2

oaimli/longtune_scitrek_simple_sft_qwen

Text Generation • 4B • Updated Jul 9 • 9

oaimli/pgpo_grpo_full_scitrek_gemma3_4b_it

Image-Text-to-Text • 4B • Updated Jul 9 • 15

oaimli/pgpo_grpo_full_scitrek_qwen3_4b_instruct_2507

Text Generation • 4B • Updated Jul 9 • 79

oaimli/scitrek_qwen25_7b_instruct_1m_sft_input_length

Text Generation • 8B • Updated Jul 8 • 33

oaimli/scitrek_qwen25_7b_instruct_1m_grpo_curriculum_192

Text Generation • 8B • Updated Jul 8 • 25

oaimli/longpt_trace_qwen3_4b_instruct_00

Text Generation • 4B • Updated May 19 • 11

oaimli/longtune_scitrek_grounding_reinforcement_gemma_5

Image-Text-to-Text • 4B • Updated Feb 17 • 4

oaimli/longtune_scitrek_direct_grounding_gemma

Image-Text-to-Text • 4B • Updated Feb 17 • 5

oaimli/longtune_hotpotqa_direct_grounding_qwen

Text Generation • 4B • Updated Feb 17 • 14

oaimli/longtune_hotpotqa_simple_rl_qwen

Text Generation • 4B • Updated Dec 22, 2025 • 8

oaimli/longtune_scitrek_grounding_reinforcement_gemma_5_alex

Image-Text-to-Text • 4B • Updated Dec 22, 2025 • 6

oaimli/longtune_hotpotqa_grounding_reinforcement_qwen_5_225

Text Generation • 4B • Updated Dec 22, 2025 • 5

oaimli/longtune_hotpotqa_simple_sft_qwen

Text Generation • 4B • Updated Dec 22, 2025 • 6

oaimli/longtune_hotpotqa_reasoning_reinforcement_qwen

Text Generation • 4B • Updated Dec 11, 2025 • 5

oaimli/longtune_scitrek_simple_rl_qwen

Text Generation • 4B • Updated Dec 2, 2025 • 6

oaimli/longtune_scitrek_grounding_reinforcement_qwen_5_500

Text Generation • 4B • Updated Dec 2, 2025 • 8

oaimli/longtune_scitrek_grounding_reinforcement_qwen_0_500

Text Generation • 4B • Updated Dec 2, 2025 • 11

oaimli/longtune_scitrek_direct_grounding_qwen

Text Generation • 4B • Updated Dec 2, 2025 • 4