InlineCoder reframes repository-level code generation as function-level coding by using a draft anchor to inline the target function into its call graph for upstream usage and downstream dependency context.
Code- optimise: Self-generated preference data for correctness and efficiency.arXiv preprint arXiv:2406.12502
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
CROP uses compositional reasoning and expert preference alignment in VLMs to produce aesthetic crops that match human experts more closely than previous methods.
citing papers explorer
-
In Line with Context: Repository-Level Code Generation via Context Inlining
InlineCoder reframes repository-level code generation as function-level coding by using a draft anchor to inline the target function into its call graph for upstream usage and downstream dependency context.
-
CROP: Expert-Aligned Image Cropping via Compositional Reasoning and Optimizing Preference
CROP uses compositional reasoning and expert preference alignment in VLMs to produce aesthetic crops that match human experts more closely than previous methods.