20260601
This commit is contained in:
40
concepts/gram-generative-recursive-reasoning.md
Normal file
40
concepts/gram-generative-recursive-reasoning.md
Normal file
@@ -0,0 +1,40 @@
|
||||
---
|
||||
title: "GRAM(Generative Recursive reAsoning Models)"
|
||||
created: 2026-05-23
|
||||
updated: 2026-05-23
|
||||
type: concept
|
||||
tags: [reasoning, recursive, generative, latent-variable]
|
||||
sources: [raw/papers/gram-generative-recursive-reasoning-2026.md]
|
||||
confidence: high
|
||||
---
|
||||
|
||||
# GRAM (Generative Recursive reAsoning Models)
|
||||
|
||||
> 将递归潜在推理转化为概率性多轨迹计算:每个递归步采样条件转移(而非确定性更新),通过边缘化所有轨迹得到最终预测。
|
||||
|
||||
## 三大贡献
|
||||
|
||||
1. **潜在变量生成过程**:将递归推理形式化为 p(y|x)
|
||||
2. **宽度推理扩展**:推理不仅通过递归深度扩展,还通过**并行轨迹采样数**扩展
|
||||
3. **经验验证**:在结构化推理、多解恢复和无条件生成上超越确定性 baseline
|
||||
|
||||
## 架构核心
|
||||
|
||||
- **双层递归**:Inner loop (低层精炼) + Outer loop (supervision step 叠加)
|
||||
- **随机引导**:高层更新产生确定性提议 u_t,加上随机项 eps_t -> h_t = u_t + eps_t
|
||||
- **训练**:[[amortized-variational-inference]](CE + KL divergence)
|
||||
|
||||
## 与现有推理方向的对比
|
||||
|
||||
| 方法 | 扩展维度 | 表示空间 |
|
||||
|------|---------|---------|
|
||||
| Chain-of-Thought | Token 序列 | 显式文本 |
|
||||
| Diffusion Reasoning | 扩散步数 | 连续状态 |
|
||||
| **GRAM** | **递归深度 x 轨迹宽度** | **离散潜在空间** |
|
||||
|
||||
## 相关概念
|
||||
|
||||
- [[stochastic-latent-trajectory]] — 随机轨迹
|
||||
- [[inference-time-scaling]] — 推理时扩展
|
||||
- [[deep-and-wide-reasoning]] — Deep & Wide
|
||||
- [[gram-generative-recursive-reasoning-paper|GRAM 论文]]
|
||||
Reference in New Issue
Block a user