StepFun

company

https://www.stepfun.com/

AI & ML interests

None defined yet.

Recent Activity

Kangheng submitted a paper 9 days ago

MentalThink: Shaping Thoughts in Mental SVG World

PY007 authored a paper 11 days ago

Attn-QAT: 4-Bit Attention With Quantization-Aware Training

apohelios new activity about 1 month ago

stepfun-ai/Step-3.7-Flash-GGUF:Some practical tips for using Step 3.7 GGUFs

View all activity

Papers

ShutterMuse: Capture-Time Photography Guidance with MLLMs

Boosting Omni-Modal Language Models: Staged Post-Training with Visually Debiased Evaluation

View all Papers

submitted a paper to Daily Papers 9 days ago

MentalThink: Shaping Thoughts in Mental SVG World

Paper • 2607.03530 • Published 14 days ago • 14

authored a paper 11 days ago

Attn-QAT: 4-Bit Attention With Quantization-Aware Training

Paper • 2603.00040 • Published Mar 6 • 2

in stepfun-ai/Step-3.7-Flash-GGUF about 1 month ago

Some practical tips for using Step 3.7 GGUFs

#6 opened about 2 months ago by

authored a paper about 1 month ago

SpatialWorld: Benchmarking Interactive Spatial Reasoning of Multimodal Agents in Real-World Tasks

Paper • 2606.09669 • Published Jun 8 • 47

in stepfun-ai/Step-3.7-Flash-NVFP4 about 1 month ago

MTP-layer weights?

#1 opened about 2 months ago by

RuntimeError: The size of tensor a (2048) must match the size of tensor b (4096) at non-singleton dimension 1

#4 opened about 1 month ago by

What's the suggested model settings?

#3 opened about 1 month ago by

updated a model about 1 month ago

stepfun-ai/Step-3.7-Flash-GGUF

Image-Text-to-Text • 197B • Updated Jun 3 • 35.7k • 148

in stepfun-ai/Step-3.7-Flash about 1 month ago

add cache_position to mask_kwargs in modeling_step3p7.py

#13 opened about 1 month ago by

authored 3 papers about 2 months ago

Step-Audio-R1.5 Technical Report

Paper • 2604.25719 • Published Apr 28 • 15

Evaluating and Rewarding LALMs for Expressive Role-Play TTS via Mean Continuation Log-Probability

Paper • 2601.22661 • Published Jan 30

StepAudio 2.5 Technical Report

Paper • 2605.23463 • Published May 22 • 49

updated a model about 2 months ago

stepfun-ai/Step-3.7-Flash-NVFP4

Image-Text-to-Text • 104B • Updated Jun 1 • 58.6k • 59

in stepfun-ai/Step-3.7-Flash-GGUF about 2 months ago

Recommended settings

#2 opened about 2 months ago by

updated 3 models about 2 months ago

stepfun-ai/Step-3.7-Flash-NVFP4

Image-Text-to-Text • 104B • Updated Jun 1 • 58.6k • 59

stepfun-ai/Step-3.7-Flash-FP8

Image-Text-to-Text • 201B • Updated Jun 1 • 17.1k • 16

stepfun-ai/Step-3.7-Flash

Image-Text-to-Text • 201B • Updated Jun 3 • 140k • • 413

in stepfun-ai/Step-3.7-Flash-dev about 2 months ago

fix examples

#1 opened about 2 months ago by

in stepfun-ai/Step-3.7-Flash-GGUF about 2 months ago

how to prevent the model from reasoning

#1 opened about 2 months ago by

Could you please provide a visual model for version Q8?

#5 opened about 2 months ago by