AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

Coda: An End-to-End Neural Program Decompiler

Cheng Fu, Huili Chen, Haolan Liu, Xinyun Chen, Yuandong Tian, Farinaz Koushanfar, Jishen Zhao

NeurIPS 2019 · Architectures and efficiency › RNNs and normalization · approach: Neural-symbolic reasoning · 22 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 attention feeding (ablation)Inst2AST · NEStoken accuracy (%): 55.59 -> 94.66Improved
replace sequence decoder with AST tree decoder (ablation)Inst2seq+Attn · NELtoken accuracy (%): 85.97 -> 91.92Improved
replace sequence encoder with instruction-type-aware encoder (ablation)Seq2AST+Attn · NELtoken accuracy (%): 85.92 -> 91.92Improved
use Inst2AST+Attn instead of Seq2Seq+Attn (ablation)Coda sketch · (Math+NE)Ltoken accuracy (%): 81.56 -> 93.20Improved
add iterative error correction (ablation)Inst2AST+Attn · NELprogram accuracy (%): 2.6 -> 56.4Improved
add iterative error correction (ablation)Inst2AST+Attn · MathSprogram accuracy (%): 64.8 -> 100.0Improved
add iterative error correction (ablation)Seq2Seq+Attn · NESprogram accuracy (%): 6.6 -> 53.0Improved
increase number of ensembled error predictors from 1 to 10 (ablation)Inst2AST EP · NESfirst error detection rate (%): 67.6 -> 88.7Improved
use Inst2AST sketch generator for the error predictor instead of Seq2Seq (ablation)EP · NESfirst error detection rate (%): 83.5 -> 88.7Improved
use Coda vs RetDec/Seq2Seq-based decompiler of Katz et al. (ablation)Coda · Math+NEprogram accuracy (%): 0% -> 82%Improved

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