Unverified50% confidenceFactExact time
MoPrO-SD investigates three refinement strategies: instruction-only optimization (I), instruction plus reasoning (I+R), and instruction plus per-example reasoning (I+R+E).
1
Sources
50%
Confidence
Long-term
Relevance
10/12/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe core approach of MoPrO-SD is to decompose prompts into functional semantic modules and then sequentially refine these modules using the LLM's own feedback.78% similarUnverifiedThe paper proposes a three-stage MoR-Tuning procedure that progressively guides the model to perform reasonable recursive sparsity on multimodal inputs.73% similarUnverifiedAdam、RMSProp等自适应优化器的设计逻辑来自对梯度一阶矩与二阶矩的估计67% similarUnverifiedMoFlow models workflow generation as a multi-objective Markov decision process65% similarUnverifiedReact 采用基于启发式假设的 O(n) Diff 算法，而非理论最优的 O(n³) 树编辑距离算法64% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1001297API
curl https://kongchang.com/api/v1/knowledge/claims/1001297MCP
get_claim(id=1001297)