Long-context post-training
Miao Li
oaimli
AI & ML interests
Natural Language Processing
Recent Activity
updated a collection 15 days ago
LongPT updated a model 15 days ago
oaimli/longpt_trace_qwen3_4b_instruct_00 published a model 15 days ago
oaimli/longpt_trace_qwen3_4b_instruct_00Organizations
None yet
Models for Long-Context Reasoning Through Proxy-Based Chain-of-Thought Tuning (ACL 2026)
-
oaimli/longtune_scitrek_reasoning_reinforcement_qwen
Text Generation • 4B • Updated • 1 -
oaimli/longtune_scitrek_grounding_reinforcement_qwen_5_300
Text Generation • 4B • Updated • 1 -
oaimli/longtune_scitrek_grounding_reinforcement_qwen_0_300
Text Generation • 4B • Updated • 2 -
oaimli/longtune_scitrek_reasoning_reinforcement_gemma
Image-Text-to-Text • 4B • Updated • 3
Long-context post-training
Models for Long-Context Reasoning Through Proxy-Based Chain-of-Thought Tuning (ACL 2026)
-
oaimli/longtune_scitrek_reasoning_reinforcement_qwen
Text Generation • 4B • Updated • 1 -
oaimli/longtune_scitrek_grounding_reinforcement_qwen_5_300
Text Generation • 4B • Updated • 1 -
oaimli/longtune_scitrek_grounding_reinforcement_qwen_0_300
Text Generation • 4B • Updated • 2 -
oaimli/longtune_scitrek_reasoning_reinforcement_gemma
Image-Text-to-Text • 4B • Updated • 3
Models for the paper of "Who Gets Cited Most? Benchmarking Long-Context Language Models on Scientific Articles"