Unverified50% confidenceFactExact time
RCSD uses the acceptance and rejection sequences naturally produced during speculative inference to construct implicit preference pairs as preference signals in reinforcement learning to optimize the draft model.
1
Sources
50%
Confidence
Long-term
Relevance
10/22/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedRCSD (Reinforcement and Continual Learning for Domain-Specific Speculative Decoding) is a training framework that directly aligns draft model optimization with a system-level objective (maximizing acceptance length).71% similarUnverified行为克隆（BC）将模仿学习简化为监督学习，直接拟合条件概率分布p(a|s)，但存在复合误差与分布偏移问题69% similarUnverifiedRLCD constructs positive and negative sample pairs for contrastive learning, combines reinforcement learning signals to distill model output distributions, and has advantages in scenarios that do not require manually annotated rewards.68% similarUnverified用户的点赞、纠错、重试、改写等行为本质上是隐式偏好信号，能持续校准模型的输出分布66% similarUnverified通过迭代反馈不断修正假设的模式在认知科学中被称为'主动推断'，可避免仅凭单次观测的确认偏误66% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1084553API
curl https://kongchang.com/api/v1/knowledge/claims/1084553MCP
get_claim(id=1084553)