Miao Li

oaimli's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

updated a model 2 days ago

oaimli/pgpo_grpo_proxy_scitrek_qwen3_4b_instruct_2507

Text Generation • 4B • Updated 2 days ago • 208

published a model 2 days ago

oaimli/pgpo_grpo_proxy_scitrek_qwen3_4b_instruct_2507

Text Generation • 4B • Updated 2 days ago • 208

updated a model 5 days ago

oaimli/longtune_scitrek_grounding_reinforcement_gemma_0

Image-Text-to-Text • 4B • Updated 5 days ago • 40

updated a collection 5 days ago

ProxyCoT

Collection

Models for Long-Context Reasoning Through Proxy-Based Chain-of-Thought Tuning (ACL 2026) • 18 items • Updated 5 days ago

updated a model 5 days ago

oaimli/longtune_scitrek_simple_sft_gemma

Image-Text-to-Text • 4B • Updated 5 days ago • 65

published a model 5 days ago

oaimli/longtune_scitrek_simple_sft_gemma

Image-Text-to-Text • 4B • Updated 5 days ago • 65

updated a collection 5 days ago

ProxyCoT

Collection

Models for Long-Context Reasoning Through Proxy-Based Chain-of-Thought Tuning (ACL 2026) • 18 items • Updated 5 days ago

updated a model 5 days ago

oaimli/longtune_scitrek_simple_sft_qwen

Text Generation • 4B • Updated 5 days ago • 161

published a model 5 days ago

oaimli/longtune_scitrek_simple_sft_qwen

Text Generation • 4B • Updated 5 days ago • 161

updated a collection 5 days ago

PGPO

Collection

2 items • Updated 5 days ago

updated a model 5 days ago

oaimli/pgpo_grpo_full_scitrek_gemma3_4b_it

Image-Text-to-Text • 4B • Updated 5 days ago • 78

published a model 5 days ago

oaimli/pgpo_grpo_full_scitrek_gemma3_4b_it

Image-Text-to-Text • 4B • Updated 5 days ago • 78

updated a model 5 days ago

oaimli/pgpo_grpo_full_scitrek_qwen3_4b_instruct_2507

Text Generation • 4B • Updated 5 days ago • 373

published a model 5 days ago

oaimli/pgpo_grpo_full_scitrek_qwen3_4b_instruct_2507

Text Generation • 4B • Updated 5 days ago • 373

updated a collection 5 days ago

ProxyCoT

Collection

Models for Long-Context Reasoning Through Proxy-Based Chain-of-Thought Tuning (ACL 2026) • 18 items • Updated 5 days ago

updated 2 models 6 days ago

oaimli/scitrek_qwen25_7b_instruct_1m_sft_input_length

Text Generation • 8B • Updated 6 days ago • 141

oaimli/scitrek_qwen25_7b_instruct_1m_grpo_curriculum_192

Text Generation • 8B • Updated 6 days ago • 124

updated a collection 6 days ago

ProxyCoT

Collection

Models for Long-Context Reasoning Through Proxy-Based Chain-of-Thought Tuning (ACL 2026) • 18 items • Updated 5 days ago