StepFun · 9 records

dateidtitleauthorsvenue↑
2026-11-062611.04386StepX-OPD: Rethinking Multi-Teacher On-Policy Distillation in Diffusion ModelsChenru Wang et al.arXiv4
2026-11-022611.03953P^2-MOPD: Accelerating Multi-Teacher On-Policy Distillation via Parameter PriorsSinuo Wang et al.arXiv51
2026-09-222609.24983onPanda: Efficient Annotation of On-Policy Alignment Data for LLMs and Agents via Token-Level CorrectionLei Yang et al.arXiv52
2026-09-162609.14005StepAudio 3 Realtime Technical ReportBin Lin et al.arXiv120
2026-09-162609.16034StepAudio 3 Music Technical ReportChengli Feng et al.arXiv103
2026-09-102609.10226Φ-Bench: Can Large Language Models Engineer the Infrastructure That Powers Them?Leilei Ding et al.arXiv16
2026-09-012608.29137Chat-Edit-3D++: Interactive 3D and 4D Scene Editing via Large Language ModelsShuangkang Fang et al.arXiv4
2026-06-252606.25763ShutterMuse: Capture-Time Photography Guidance with MLLMsJiayu Li et al.arXiv44
2026-05-152605.12034Boosting Omni-Modal Language Models: Staged Post-Training with Visually Debiased EvaluationChe Liu et al.arXiv5