Miao Li

oaimli's activity

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

updated a collection 4 days ago

SciTrek

Collection

Models for the paper of "Who Gets Cited Most? Benchmarking Long-Context Language Models on Scientific Articles" • 7 items • Updated 4 days ago

updated a model 4 days ago

oaimli/scitrek_grpo_full_longrlvr_qwen3_4b_instruct_2507_660

Text Generation • 4B • Updated 4 days ago • 30

published a model 4 days ago

oaimli/scitrek_grpo_full_longrlvr_qwen3_4b_instruct_2507_660

Text Generation • 4B • Updated 4 days ago • 30

updated a collection 14 days ago

SciTrek

Collection

Models for the paper of "Who Gets Cited Most? Benchmarking Long-Context Language Models on Scientific Articles" • 7 items • Updated 4 days ago

updated a model 14 days ago

oaimli/scitrek_grpo_full_longrlvr_qwen3_4b_instruct_2507_280

Text Generation • 4B • Updated 14 days ago • 59

published a model 14 days ago

oaimli/scitrek_grpo_full_longrlvr_qwen3_4b_instruct_2507_280

Text Generation • 4B • Updated 14 days ago • 59

updated a collection 17 days ago

PGPO

Collection

4 items • Updated 17 days ago

updated a model 17 days ago

oaimli/pgpo_grpo_proxy_scitrek_gemma3_4b_it

Image-Text-to-Text • 4B • Updated 17 days ago • 88

published a model 17 days ago

oaimli/pgpo_grpo_proxy_scitrek_gemma3_4b_it

Image-Text-to-Text • 4B • Updated 17 days ago • 88

updated a collection 17 days ago

PGPO

Collection

4 items • Updated 17 days ago

updated a model 18 days ago

oaimli/scitrek_grpo_full_loongrl_qwen3_4b_instruct_2507

Text Generation • 4B • Updated 18 days ago • 408

published a model 18 days ago

oaimli/scitrek_grpo_full_loongrl_qwen3_4b_instruct_2507

Text Generation • 4B • Updated 18 days ago • 408

updated a model 22 days ago

oaimli/pgpo_grpo_proxy_scitrek_qwen3_4b_instruct_2507

Text Generation • 4B • Updated 22 days ago • 266

published a model 22 days ago

oaimli/pgpo_grpo_proxy_scitrek_qwen3_4b_instruct_2507

Text Generation • 4B • Updated 22 days ago • 266

updated a model 25 days ago

oaimli/longtune_scitrek_grounding_reinforcement_gemma_0

Image-Text-to-Text • 4B • Updated 25 days ago • 45

updated a collection 25 days ago

ProxyCoT

Collection

Models for Long-Context Reasoning Through Proxy-Based Chain-of-Thought Tuning (ACL 2026) • 18 items • Updated 25 days ago

updated a model 25 days ago

oaimli/longtune_scitrek_simple_sft_gemma

Image-Text-to-Text • 4B • Updated 25 days ago • 82

published a model 25 days ago

oaimli/longtune_scitrek_simple_sft_gemma

Image-Text-to-Text • 4B • Updated 25 days ago • 82

updated a collection 25 days ago

ProxyCoT

Collection

Models for Long-Context Reasoning Through Proxy-Based Chain-of-Thought Tuning (ACL 2026) • 18 items • Updated 25 days ago