Multi-Teacher Self-Distillation Policy Optimization
MT-SDPO improves multi-domain LLM performance by 14.79 points on Qwen3-8B, offering better domain balance than single-teacher approaches.
#多教师蒸馏
2 stories · 0 in 7 days · 0 in 30 days
Stories, products and papers tagged "多教师蒸馏", newest first.
Sep 3
Jul 23
Chinese contentSolar Open 2: 250B MoE模型，1M上下文，专为长程智能体任务设计
Solar Open 2 发了，250B MoE 模型，1M token 超长上下文，专门跑复杂智能体任务。MMLU-Pro 和 LiveCodeBench 都领先，韩语能力还特别强，比 DeepSeek-V4-Pro 小很多但性能接近。