@liliana_hotsko: How do you give a code LLM knowledge of an entire repository without paying for it at every single query? We introduce …
Summary
Introduces Code2LoRA, a hypernetwork that converts an entire code repository into a LoRA adapter for code LLMs, eliminating inference-time token overhead for repository-level knowledge.
View Cached Full Text
Cached at: 06/13/26, 02:46 PM
How do you give a code LLM knowledge of an entire repository without paying for it at every single query?
We introduce Code2LoRA: a hypernetwork that turns a repository into its own LoRA adapter. Repo knowledge baked into weights → zero inference-time token overhead. https://t.co/T3hnxCVkna
Similar Articles
Show HN: MultiMatte, a Promptable Image Background Removal Model
MultiMatte is a promptable image background removal model fine-tuned from SAM 3 using LoRA, achieving higher accuracy on benchmarks by outputting alpha mattes for better handling of fuzzy boundaries.
FANS: Federated Adaptive Network Search Learning for Heterogeneous Devices
The article introduces FANS, a hypernetwork-based framework for heterogeneous federated learning that learns a shared architecture space and uses parallel training with self-distillation to optimize model selection across diverse devices.
ACE: Adapter Consolidation across Experts for Parameter-Efficient Fine-Tuning of MoE LLMs
ACE introduces a method to consolidate redundant adapters across experts in MoE large language models for more efficient parameter-efficient fine-tuning, achieving up to 1.48× training speedup without increasing peak memory.
One Rate Is Not Enough: Adaptive Anisotropic Learning Rates for LoRA Fine-Tuning
This paper introduces an adaptive anisotropic learning-rate model for LoRA fine-tuning to address within-module heterogeneity, improving performance and rank capacity utilization across benchmarks.
$\Phi$-Bench: Can Large Language Models Engineer the Infrastructure That Powers Them?
Φ-Bench is a new benchmark for evaluating large language models on engineering and optimizing AI infrastructure, covering tasks from kernel-level code completion to end-to-end system optimization.