Long-context post-training
Miao Li
oaimli
AI & ML interests
Natural Language Processing
Recent Activity
updated a collection 27 days ago
LongPT updated a model 27 days ago
oaimli/longpt_trace_qwen3_4b_instruct_00 published a model 27 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 -
oaimli/longtune_scitrek_grounding_reinforcement_qwen_5_300
Text Generation • 4B • Updated • 2 -
oaimli/longtune_scitrek_grounding_reinforcement_qwen_0_300
Text Generation • 4B • Updated • 4 -
oaimli/longtune_scitrek_reasoning_reinforcement_gemma
Image-Text-to-Text • 4B • Updated • 2
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 -
oaimli/longtune_scitrek_grounding_reinforcement_qwen_5_300
Text Generation • 4B • Updated • 2 -
oaimli/longtune_scitrek_grounding_reinforcement_qwen_0_300
Text Generation • 4B • Updated • 4 -
oaimli/longtune_scitrek_reasoning_reinforcement_gemma
Image-Text-to-Text • 4B • Updated • 2
models 24
oaimli/longpt_trace_qwen3_4b_instruct_00
Text Generation • 4B • Updated • 75
oaimli/longtune_scitrek_grounding_reinforcement_gemma_5
4B • Updated • 2
oaimli/longtune_scitrek_grounding_reinforcement_gemma_0
4B • Updated • 2
oaimli/longtune_scitrek_direct_grounding_gemma
4B • Updated • 1
oaimli/longtune_hotpotqa_direct_grounding_qwen
Text Generation • 4B • Updated • 2
oaimli/longtune_hotpotqa_simple_rl_qwen
Text Generation • 4B • Updated • 3
oaimli/longtune_scitrek_grounding_reinforcement_gemma_5_alex
4B • Updated • 3
oaimli/longtune_hotpotqa_grounding_reinforcement_qwen_5_225
Text Generation • 4B • Updated • 3
oaimli/longtune_hotpotqa_simple_sft_qwen
Text Generation • 4B • Updated • 3
oaimli/longtune_hotpotqa_reasoning_reinforcement_qwen
Text Generation • 4B • Updated • 3