Miao Li

oaimli's activity

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

updated a collection about 1 month ago

LongPT

Collection

Long-context post-training • 1 item • Updated May 19

updated a model about 1 month ago

oaimli/longpt_trace_qwen3_4b_instruct_00

Text Generation • 4B • Updated May 19 • 52

published a model about 1 month ago

oaimli/longpt_trace_qwen3_4b_instruct_00

Text Generation • 4B • Updated May 19 • 52

updated a model 4 months ago

oaimli/longtune_scitrek_grounding_reinforcement_gemma_5

4B • Updated Feb 17 • 2

published a model 4 months ago

oaimli/longtune_scitrek_grounding_reinforcement_gemma_5

4B • Updated Feb 17 • 2

updated a model 4 months ago

oaimli/longtune_scitrek_grounding_reinforcement_gemma_0

4B • Updated Feb 17 • 2

published a model 4 months ago

oaimli/longtune_scitrek_grounding_reinforcement_gemma_0

4B • Updated Feb 17 • 2

updated a model 4 months ago

oaimli/longtune_scitrek_direct_grounding_gemma

4B • Updated Feb 17 • 2

published a model 4 months ago

oaimli/longtune_scitrek_direct_grounding_gemma

4B • Updated Feb 17 • 2

updated a model 4 months ago

oaimli/longtune_hotpotqa_direct_grounding_qwen

Text Generation • 4B • Updated Feb 17 • 3

published a model 4 months ago

oaimli/longtune_hotpotqa_direct_grounding_qwen

Text Generation • 4B • Updated Feb 17 • 3

upvoted a paper 5 months ago

EvoCUA: Evolving Computer Use Agents via Learning from Scalable Synthetic Experience

Paper • 2601.15876 • Published Jan 22 • 92

updated a collection 6 months ago

ProxyCoT

Collection

Models for Long-Context Reasoning Through Proxy-Based Chain-of-Thought Tuning (ACL 2026) • 11 items • Updated 26 days ago

updated a model 6 months ago

oaimli/longtune_hotpotqa_simple_rl_qwen

Text Generation • 4B • Updated Dec 22, 2025 • 3

published a model 6 months ago

oaimli/longtune_hotpotqa_simple_rl_qwen

Text Generation • 4B • Updated Dec 22, 2025 • 3

updated a model 6 months ago

oaimli/longtune_scitrek_grounding_reinforcement_gemma_5_alex

4B • Updated Dec 22, 2025 • 2

updated a collection 6 months ago

ProxyCoT

Collection

Models for Long-Context Reasoning Through Proxy-Based Chain-of-Thought Tuning (ACL 2026) • 11 items • Updated 26 days ago

published a model 6 months ago

oaimli/longtune_scitrek_grounding_reinforcement_gemma_5_alex

4B • Updated Dec 22, 2025 • 2