---
title: "Geometric Relevance Is Not Sufficient: Evaluating Focused Post-Training Supervision in Diffusion Docking"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2611.08249v1"
permalink: "https://feed.astralor.com/items/itm_313c3a1f7eb7b33249b772ed"
published: "2026-11-05T16:26:44.000Z"
score: 58
channel: "ai"
tags: ["推理效率","RAG","多模态","Geometric Relevance","Not Sufficient","Evaluating Focused Post-Training","Supervision","Diffusion Docking Diffusion-based"]
---

# Geometric Relevance Is Not Sufficient: Evaluating Focused Post-Training Supervision in Diffusion Docking

## 速览

Diffusion-based molecular docking requires learning a corrective score field across a broad corruption distribution, yet individual pose errors can differ substantially in their structural consequences. This creates a p…

## 关键点

- Diffusion-based molecular docking requires learning a corrective score field across a broad corruption distribution, yet individual pose errors can differ substantially in their structural consequences.
- This creates a post-training conflict between preserving broad score-field coverage and concentrating supervision on corrections that appear more relevant to docking geometry.
- Using DiffDock, a fixed-budget study compares broad continuation with torsional supervision focused on Cartesian consequence or conditional target consistency, and with a broad/focused mixture.

## 全文

Diffusion-based molecular docking requires learning a corrective score field across a broad corruption distribution, yet individual pose errors can differ substantially in their structural consequences. This creates a post-training conflict between preserving broad score-field coverage and concentrating supervision on corrections that appear more relevant to docking geometry. Using DiffDock, a fixed-budget study compares broad continuation with torsional supervision focused on Cartesian consequence or conditional target consistency, and with a broad/focused mixture. Evaluation separates fixed score fidelity, generated-pose quality, best-of-10 sampling capacity, and confidence-selected Top-1 docking performance. At <5 Angstrom, broad continuation had the highest mean Top-1 success among trained policies, and focused or mixed supervision showed no consistent advantage under the tested budget. The starting model had better fixed score fidelity, whereas the evaluated broad-continuation model had higher mean Top-1 success with the same aggregate best-of-10 recovery. Focusing supervision on structurally consequential or more consistently specified corrections did not consistently improve returned-pose success over broad continuation.

---

引用前请核对原文;本文由星际流动整理:https://feed.astralor.com/items/itm_313c3a1f7eb7b33249b772ed