Complexity-based code embeddings

2026-01-01 · Rares Folea, Radu Iacob, Emil Slusanschi, Traian Rebedea arxiv

This paper presents a generic method for transforming the source code of various algorithms to numerical embeddings, by dynamically analysing the behaviour of computer programs against different inputs and by tailoring multiple generic complexity functions for the analysed metrics. The used algorithms embeddings are based on r-Complexity . Using the proposed code embeddings, we present an implementation of the XGBoost algorithm that achieves an average F1-score on a multi-label dataset with 11 classes, built using real-world code snippets submitted for programming competitions on the Codeforces platform.

📄 PDF Abstract BibTeX arXiv:2601.00924

Code (0)

등록된 구현이 없습니다.

Text Simplification with Sentence Embeddings

2025-10-28 · Matthew Shardlow arxiv

Sentence embeddings can be decoded to give approximations of the original texts used to create them. We explore this effect in the context of text simplification, demonstrating that reconstructed text embeddings preserve…

Text Simplification

Decoding Molecular Graph Embeddings with Reinforcement Learning

2019-04-18 · Steven Kearnes, Li Li, Patrick Riley

We present RL-VAE, a graph-to-graph variational autoencoder that uses reinforcement learning to decode molecular graphs from latent embeddings. Methods have been described previously for graph-to-graph autoencoding, but …

Graph Matching reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Inducing Systematicity in Transformers by Attending to Structurally Quantized Embeddings

2024-02-09 · Yichen Jiang, Xiang Zhou, Mohit Bansal

Transformers generalize to novel compositions of structures and entities after being trained on a complex dataset, but easily overfit on datasets of insufficient complexity. We observe that when the training set is suffi…

Machine Translation Quantization Semantic Parsing Word Embeddings

How can embedding models bind concepts?

2026-05-29 · Arnas Uselis, Darina Koishigarina, Seong Joon Oh arxiv

Humans easily determine which color belongs to which shape in multi-object scenes, an ability known as concept binding. Vision-language embedding models such as CLIP struggle with binding: they recognize individual conce…

Cross-Modal Retrieval

Hyperparameter Learning for Conditional Kernel Mean Embeddings with Rademacher Complexity Bounds

2018-09-01 · Kelvin Hsu, Richard Nock, Fabio Ramos

Conditional kernel mean embeddings are nonparametric models that encode conditional expectations in a reproducing kernel Hilbert space. While they provide a flexible and powerful framework for probabilistic inference, th…