Accordion-Thinking: Self-Regulated Step Summaries for Efficient and Readable LLM Reasoning (https://arxiv.org/abs/2602.03249)
Zhicheng YANG
yangzhch6
AI & ML interests
reasoning with LLMs
Recent Activity
updated a model 7 days ago
yangzhch6/qwen3-4b-envfactory-nonthinking updated a model 7 days ago
yangzhch6/qwen3-4b-envfactory-thinkingOrganizations
None yet
models 45
yangzhch6/qwen3-4b-envfactory-nonthinking
4B • Updated • 15
yangzhch6/qwen3-4b-envfactory-thinking
4B • Updated • 19
yangzhch6/Qwen3-4B-Base-DeleThink
4B • Updated • 4
yangzhch6/Qwen2.5-Math-7B-DeleThink
8B • Updated • 3
yangzhch6/Qwen3-4B-Base-AccordionThinking-MixRL
4B • Updated • 3
yangzhch6/Qwen2.5-Math-7B-AccordionThinking-MixRL
8B • Updated • 3
yangzhch6/Qwen3-4B-n8-sglang-no_kl-grpo-0.5-1e-6-step340
4B • Updated • 1
yangzhch6/Qwen3-4B-n8-sglang-no_kl-grpo-0.5-1e-6-step300
4B • Updated • 1
yangzhch6/mcpfactory-qwen3-8b-newreward-step340
8B • Updated • 4
yangzhch6/mcpfactory-qwen3-8b-newreward-step300
8B • Updated
datasets 16
yangzhch6/Accordion-Thinking-Synthetic-Data
Viewer • Updated • 14.7k • 38
yangzhch6/DeepInformal-DeepTheorem-Synthetic
Viewer • Updated • 404k • 150 • 1
yangzhch6/DeepInformal-Openr1-Math-46K-Synthetic
Viewer • Updated • 165k • 131
yangzhch6/compare-openr1
Viewer • Updated • 45.8k • 38
yangzhch6/Align-Openr1-Math-46k
Viewer • Updated • 45.8k • 44
yangzhch6/DeepInformal-test
Viewer • Updated • 405 • 9
yangzhch6/DeepInformal-Putnam-1995-2024
Viewer • Updated • 356 • 8 • 1
yangzhch6/DeepInformal-DeepTheorem-DeepSeek-84k
Viewer • Updated • 84.1k • 111
yangzhch6/Putnam-Informal-1995-2024
Viewer • Updated • 360 • 14 • 1
yangzhch6/cuda-12.8-tar
Updated • 2