mlsanityData to 14 Oct 2026

Efficient Code Embeddings from Code Generation Models

arXiv 2508.21290 ↗First posted 29 Aug 2025cs.CL cs.AI cs.IRcited by 13

Not on the map. Why?

Abstract (arXiv)

jina-code-embeddings is a novel code embedding model suite designed to retrieve code from natural language queries, perform technical question-answering, and identify semantically similar code snippets across programming languages. It makes innovative use of an autoregressive backbone pre-trained on both text and code, generating embeddings via last-token pooling. We outline the training recipe and demonstrate state-of-the-art performance despite the relatively small size of the models, validating this approach to code embedding model construction.

Key facts. Cited by 13 papers in the map (data through 14 Oct 2026). Builds on 19 of its 20 references that are in the map. First posted on arXiv 29 Aug 2025.

Builds on

19 of 20 references.

References · 19

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  3. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,170
  4. 2018Representation Learning with Contrastive Predictive Codingcited by 7,777
  5. 2024GPT-4o System Cardcited by 4,588
  6. 2020CodeBERT: A Pre-Trained Model for Programming and Natural Languagescited by 1,310
  7. 2025Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Modelscited by 1,261
  8. 2024Qwen2.5-Coder Technical Reportcited by 1,203
  9. 2019CodeSearchNet Challenge: Evaluating the State of Semantic Code Searchcited by 654
  10. 2024NV-Embed: Improved Techniques for Training LLMs as Generalist Embedding Modelscited by 472
  11. 2022One Embedder, Any Task: Instruction-Finetuned Text Embeddingscited by 333
  12. 2023Improving Text Embeddings with Large Language Modelscited by 303
7 more
  1. 2022Matryoshka Representation Learningcited by 282
  2. 2024jina-embeddings-v3: Multilingual Embeddings With Task LoRAcited by 141
  3. 2025MMTEB: Massive Multilingual Text Embedding Benchmarkcited by 125
  4. 2023Jina Embeddings 2: 8192-Token General-Purpose Text Embeddings for Long Documentscited by 104
  5. 2025Gemini Embedding: Generalizable Embeddings from Geminicited by 94
  6. 2025jina-embeddings-v4: Universal Embeddings for Multimodal Multilingual Retrievalcited by 76
  7. 2024CoIR: A Comprehensive Benchmark for Code Information Retrieval Modelscited by 60

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 13.

13 papers.

Sort:

By area:

  1. 2026R-Diverse: Mitigating Diversity Illusion in Self-Play LLM Trainingcited by 10
  2. 2026CORE-Bench: A Comprehensive Benchmark for Code Retrieval in the Era of Agentic Codingcited by 7
  3. 2026SiliconMind-V1: Multi-Agent Distillation and Debug-Reasoning Workflows for Verilog Code Generationcited by 4
  4. 2026MARTI-MARS2: Scaling Multi-Agent Self-Search via Reinforcement Learning for Code Generationcited by 3
  5. 2026Agent Retrieval Bench: Evaluating Repository Context Retrieval for Coding Agentscited by 2
  6. 2026MARS2: Scaling Multi-Agent Tree Search via Reinforcement Learning for Code Generationcited by 1
  7. 2026Beyond Retrieval: A Multitask Benchmark and Model for Code Searchcited by 1
  8. 2026Beyond pass@k: Redundancy-Aware RLVR for Multi-Sample Code Generationcited by 1
  9. 2026NeSy-RAG: Neuro-Symbolic RAG for Explainable Question Answeringcited by 1
  10. 2026CodeNib: A Multi-View Data System for Serving Repository Context to Coding Agentscited by 0
  11. 2026Stop Indexing at Full Precision: Revisiting Clustering for Vector Embeddingscited by 0
  12. 2026Invariant Pretraining for Robust Code Representationscited by 0
1 more
  1. 2026Questioning the Questions: Sustaining Self-Evolution in Reasoning Modelscited by 0