AI Paper Atlas

Research map / Large language models / Language, safety and interpretability

LLMCO4MR: LLMs-aided Neural Combinatorial Optimization for Ancient Manuscript Restoration from Fragments with Case Studies on Dunhuang

Yuqing Zhang, Hangqi Li, Shengyu Zhang, Runzhong Wang, Baoyi He, Huaiyong Dou, Junchi Yan, Yongquan Zhang, Fei Wu

ECCV 2024 · Large language models › Language, safety and interpretability · approach: LLM pruning and scaling data · 6 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add OT layer (cardinality constraint) to GNN fragment selection instead of greedy top-K (ablation)CO solver · Synthetic 2x2 selection (pool 15)selection accuracy: 0.3125 -> 0.5825Improved
add OT layer to GNN selection (ablation)CO solver · Synthetic 3x3 selection (pool 30)selection accuracy: 0.5389 -> 0.6044Improved
add second-order matching strategy to Top-9 selection (ablation)CO solver · Synthetic Top-9 of 30selection accuracy: 0.6044 -> 0.6633Improved
add second-order matching strategy (ablation)CO solver · Synthetic Top-9 of 20selection accuracy: 0.7256 -> 0.7311No clear effect
add MLLM (GPT-4V) pairwise matching after CO solver selection (ablation)LLMCO4MR · Dunhuang case study (2x2, pool 10)success rate: 0.5750 -> 0.6750Improved
add MLLM matching on top of CO solver for larger 3x3 pool (ablation)LLMCO4MR · Dunhuang case study (3x3, pool 25)success rate: 0.4667 -> 0.5556Improved
add CO solver outlier filtering before GPT-4V matching (ablation)GPT-4V · Dunhuang case study (2x2, pool 15)success rate: 0.1750 -> 0.6250Improved
increase negative pairs in siamese training (ratio 1:2 vs 1:1) (ablation)Siamese network · Top-4 performance, 120K samplesTop-4 performance: 0.7525 -> 0.7800Improved
increase siamese training data from 40K to 120K (ratio 1:2) (ablation)Siamese network · Top-4 performanceTop-4 performance: 0.7100 -> 0.7800Improved
use full LLMCO4MR instead of prior restoration methodsLLMCO4MR · Dunhuang case study (3x3, pool 25)success rate: 0.4111 -> 0.5556Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy