Code2LoRA: Hypernetwork-Generated Adapters for Code Language Models under Software Evolution
cs.SE, cs.AI, cs.CL
Submitted: 2026-06-04
Updated: 2026-10-27
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Zhyper: Factorized Hypernetworks for Conditioned LLM Fine-Tuning
- Doc-to-LoRA: Learning to Instantly Internalize Contexts
- R2C2-Coder: Enhancing and Benchmarking Real-world Repository-level Code Completion Abilities of Code Large Language Models
- DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligence
- LoraHub: Efficient Cross-Task Generalization via Dynamic LoRA Composition
- Qwen2.5-Coder Technical Report
- StarCoder: may the source be with you!
- CodeBLEU: a Method for Automatic Evaluation of Code Synthesis
- Code Llama: Open Foundation Models for Code
- RepoFusion: Training Code Models to Understand Your Repository
- Repoformer: Selective Retrieval for Repository-Level Code Completion
- Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models
Related papers
- ArkEval: Benchmarking and Evaluating Automated CodeRepair for ArkTS
- TestPrism: Rethinking Test Evaluation Beyond a Single Reference
- Mining Workflow Graphs for Black-Box Boundary Testing of Conversational LLM Agents
- Falsification-Based Verification of LLM-Generated Optimization Models: Sound Test Batteries and Their Detection Limits
- GitSkills: A Dataset of Agent Skills on GitHub
- For Coding Agents, the Repository Matters