Fill-in-the-Middle (FIM) models play a vital role in code completion tasks, leveraging both prefix and suffix context to provide more accurate and contextually relevant suggestions. This paper presents approaches to improve FIM code completion while addressing the challenge of maintaining low latency for real-time coding assistance. We enhance FIM code completion by incorporating context and curriculum examples in the training process. We identify patterns where completion suggestions fail more frequently, revealing complexities that smaller language models struggle with. To address these challenges, we develop a curriculum dataset by extracting hard-to-complete patterns from code repositories and generate context examples using semantic and static analysis tools (e.g. TSC compiler). We fine-tune various sized models, including StarCoder and DeepSeek, on this enhanced dataset. Our evaluation encompasses three key dimensions: the Santa Coder FIM task, the Amazon CCEval benchmark, and a new Multi-Line Infilling evaluation benchmark derived from SWE-bench. Comprehensive ablation studies across multiple model sizes reveal that while all fine-tuned models show improvements, the performance gains are more pronounced for smaller parameter models and that incorporating difficult-to-complete examples as part of curriculum learning improves completion performance. This finding is particularly sig- nificant given the latency constraints of code completion tasks. While larger models like GPT and Claude perform well in multi- line completions but are prohibitively challenging to use given high latency, and our fine-tuned models achieve a balance between per- formance and latency. Finally, we validate our approach through online A/B testing, demonstrating tangible improvements in Completion Acceptance Rate (CAR) and Completion Persistence Rate (CPR), with zero latency impact.

We consider the problem of estimating the depth of each pixel in a scene from a single monocular image. Unlike traditional approaches, which attempt to map from appearance features to depth directly, we first perform a semantic segmentation of the scene and use the semantic labels to guide the 3D reconstruction. This approach provides several advantages: By knowing the semantic class of a pixel or region, depth and geometry constraints can be easily enforced (e.g., “sky” is far away and “ground” is horizontal). In addition, depth can be more readily predicted by measuring the difference in appearance with respect to a given semantic class. For example, a tree will have more uniform appearance in the distance than it does close up. Finally, the incorporation of semantic features allows us to achieve state-of-the-art results with a significantly simpler model than previous works.