Research map / Detection and segmentation / Open-set and few-shot detection
Learning to Align the Source Code to the Compiled Object Code
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 changed | Where | Measured | Effect |
|---|---|---|---|
| use Convolutional Grid Decoder instead of Ptr2 | alignment network · GNU C, ALL | accuracy: 85.95% -> 90.86% | Helped |
| use Convolutional Grid Decoder instead of inner-product grid | Grid Decoder · GNU C, ALL | accuracy: 89.09% -> 90.86% | Helped |
| use Convolutional Grid Decoder instead of local grid (ablation) | Grid Decoder · GNU C, ALL | accuracy: 88.64% -> 90.86% | Helped |
| use local grid instead of inner-product grid (ablation) | Grid Decoder · GNU C, ALL | accuracy: 89.09% -> 88.64% | Hurt |
| use Grid Decoder instead of Ptr1/Ptr2/Match-LSTM | alignment network · GNU C, ALL | accuracy: 85.36% -> 90.86% | Helped |
| use Convolutional Grid Decoder instead of Ptr1 | alignment network · Synthetic C, ALL | accuracy: 98.70% -> 99.08% | Helped |
| use Ptr1 vs Ptr2 vs Match-LSTM | baselines · GNU C, ALL | accuracy: 84.91% / 85.95% / 85.36% | No clear effect |
| use optimization level -O1 instead of -O3 with Ptr1 (ablation) | Ptr1 · GNU C | accuracy: 86.90% vs 83.77% | Mixed |
| use Grid Decoder instead of Ptr-Net | TSP · TSP n=5, n=10 | average route length: 2.88 vs 2.88 | No clear effect |
| randomly permute point IDs each epoch (augmentation) (ablation) | TSP training · TSP | route length | Helped |
Closest papers by meaning
- SelfCodeAlign: Self-Alignment for Code Generation (NeurIPS 2024 · similarity 0.85)
- ASAP: Assembly-Source Aligned Pseudocode Refinement For Binary Decompilation (NeurIPS 2026 · similarity 0.84)
- Guess & Sketch: Language Model Guided Transpilation (ICLR 2024 · similarity 0.84)
- QiMeng-NeuComBack: Self-Evolving Translation from IR to Assembly Code (NeurIPS 2025 · similarity 0.83)
- A Unified Graph Language Model for Multi-Domain Multi-Task Graph Alignment Instruction Tuning (NeurIPS 2026 · similarity 0.83)
- LILO: Learning Interpretable Libraries by Compressing and Documenting Code (ICLR 2024 · similarity 0.83)
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.