AI & ML interests
None defined yet.
Recent Activity
Papers
onPanda: Efficient Annotation of On-Policy Alignment Data for LLMs and Agents via Token-Level Correction
StepAudio 3 Realtime Technical Report
step 3.5 models
-
Step-3.5-Flash Chatbot
🚀50Launch an interactive Streamlit web application
-
stepfun-ai/Step-3.5-Flash
Text Generation • 199B • Updated • 269k • • 840 -
stepfun-ai/Step-3.5-Flash-FP8
Text Generation • 199B • Updated • 632 • 53 -
stepfun-ai/Step-3.5-Flash-GGUF-Q4_K_S
Text Generation • 197B • Updated • 775 • 147
Step-Audio-R1 is the first audio language model to successfully unlock test-time compute scaling.
-
stepfun-ai/Step-3.7-Flash
Image-Text-to-Text • 201B • Updated • 18k • • 462 -
stepfun-ai/Step-3.7-Flash-FP8
Image-Text-to-Text • 201B • Updated • 3.98k • 21 -
stepfun-ai/Step-3.7-Flash-NVFP4
Image-Text-to-Text • 104B • Updated • 93.9k • 67 -
stepfun-ai/Step-3.7-Flash-GGUF
Image-Text-to-Text • 197B • Updated • 5.05k • 176
Learning to Scale Test-Time Compute with Parallel Coordinated Reasoning
-
stepfun-ai/PaCoRe-8B
Text Generation • 8B • Updated • 359 • 49 -
stepfun-ai/PaCoRe-Train-8k
Viewer • Updated • 7.52k • 764 • 81 -
stepfun-ai/RLVR-8B-0926
Text Generation • 8B • Updated • 347 • 9 -
PaCoRe: Learning to Scale Test-Time Compute with Parallel Coordinated Reasoning
Paper • 2601.05593 • Published • 89
Step-Audio-EditX
-
stepfun-ai/StepFun-Formalizer-7B
Text Generation • 8B • Updated • 451 • • 7 -
stepfun-ai/StepFun-Formalizer-32B
Text Generation • 33B • Updated • 266 • 12 -
StepFun-Formalizer: Unlocking the Autoformalization Potential of LLMs through Knowledge-Reasoning Fusion
Paper • 2508.04440 • Published • 10 -
stepfun-ai/StepFun-Formalizer-Training
Viewer • Updated • 188k • 176 • 6
Step-Audio model family, including Audio-Tokenizer, Audio-Chat and TTS
-
stepfun-ai/Step-3.7-Flash
Image-Text-to-Text • 201B • Updated • 18k • • 462 -
stepfun-ai/Step-3.7-Flash-FP8
Image-Text-to-Text • 201B • Updated • 3.98k • 21 -
stepfun-ai/Step-3.7-Flash-NVFP4
Image-Text-to-Text • 104B • Updated • 93.9k • 67 -
stepfun-ai/Step-3.7-Flash-GGUF
Image-Text-to-Text • 197B • Updated • 5.05k • 176
step 3.5 models
-
Step-3.5-Flash Chatbot
🚀50Launch an interactive Streamlit web application
-
stepfun-ai/Step-3.5-Flash
Text Generation • 199B • Updated • 269k • • 840 -
stepfun-ai/Step-3.5-Flash-FP8
Text Generation • 199B • Updated • 632 • 53 -
stepfun-ai/Step-3.5-Flash-GGUF-Q4_K_S
Text Generation • 197B • Updated • 775 • 147
Learning to Scale Test-Time Compute with Parallel Coordinated Reasoning
-
stepfun-ai/PaCoRe-8B
Text Generation • 8B • Updated • 359 • 49 -
stepfun-ai/PaCoRe-Train-8k
Viewer • Updated • 7.52k • 764 • 81 -
stepfun-ai/RLVR-8B-0926
Text Generation • 8B • Updated • 347 • 9 -
PaCoRe: Learning to Scale Test-Time Compute with Parallel Coordinated Reasoning
Paper • 2601.05593 • Published • 89
Step-Audio-R1 is the first audio language model to successfully unlock test-time compute scaling.
Step-Audio-EditX
-
stepfun-ai/StepFun-Formalizer-7B
Text Generation • 8B • Updated • 451 • • 7 -
stepfun-ai/StepFun-Formalizer-32B
Text Generation • 33B • Updated • 266 • 12 -
StepFun-Formalizer: Unlocking the Autoformalization Potential of LLMs through Knowledge-Reasoning Fusion
Paper • 2508.04440 • Published • 10 -
stepfun-ai/StepFun-Formalizer-Training
Viewer • Updated • 188k • 176 • 6
Step-Audio model family, including Audio-Tokenizer, Audio-Chat and TTS