AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Behavioral Embeddings of Programs: A Quasi-Dynamic Approach for Optimization Prediction

Haolin Pan, Dong Jinyuan, Hongbin Zhang, Hongyu Lin, Mingjie Xing, Yanjun Wu

ICLR 2026 · Label-efficient and robust learning › Recognition and long-tail · approach: Dense features and foundation priors · 0 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 scale-invariant logarithmic ratio quantification (vs absolute differences) (ablation)Behavioral-PQ · -Oz Benefit Prediction (test)MAE (%): 10.96 -> 8.19Improved
add scale-invariant logarithmic ratio quantification (vs absolute differences) (ablation)Behavioral-PQ · Best Pass Prediction (test)Top-5 accuracy (%): 94.33 -> 89.55Hurt
add Transformer encoder (vs pooling sub-embeddings) (ablation)Behavioral-PQ · -Oz Benefit Prediction (test)MAE (%): 10.08 -> 8.19Improved
add Transformer encoder (vs pooling sub-embeddings) (ablation)Behavioral-PQ · Best Pass Prediction (test)Top-5 accuracy (%): 87.46 -> 89.55Improved
use Product Quantization instead of K-Means on full vectors (ablation)Behavioral-PQ · -Oz Benefit Prediction (test)MAE (%): 8.24 -> 8.19Improved
use Product Quantization instead of K-Means on full vectors (ablation)Behavioral-PQ · Best Pass Prediction (test)Top-5 accuracy (%): 93.43 -> 89.55Hurt
use Product Quantization instead of K-Means on full vectors (ablation)Behavioral-PQ · Best Pass Prediction (validation)Top-5 accuracy (%): 98.48 -> 99.08Improved
use behavioral embedding instead of static embeddingsembedding · Best Pass Prediction (test)Top-1 accuracy (%): 39.27 -> 64.48Improved
use behavioral embedding instead of static embeddingsembedding · -Oz Benefit Prediction (test)MAE (%): 16.23 -> 8.19Improved
use behavioral embedding instead of InstCount for K-NNembedding · Best Pass K-NNTop-1 accuracy (%): 75.82 -> 79.70Improved
use specialized Behavioral-PQ instead of zero-shot LLMspredictor · Best Pass Prediction (test)Top-5 accuracy (%): 59.10 -> 89.55Improved
use zero-shot LLM instead of Autophase featurespredictor · Best Pass Prediction (test)Top-1 accuracy (%): 38.51 -> 35.52Hurt

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