REVIEW 3 cited by
Fast and Memory-Efficient Neural Code Completion
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Code completion is one of the most widely used features of modern integrated development environments (IDEs). While deep learning has made significant progress in the statistical prediction of source code, state-of-the-art neural network models consume hundreds of megabytes of memory, bloating the development environment. We address this in two steps: first we present a modular neural framework for code completion. This allows us to explore the design space and evaluate different techniques. Second, within this framework we design a novel reranking neural completion model that combines static analysis with granular token encodings. The best neural reranking model consumes just 6 MB of RAM, - 19x less than previous models - computes a single completion in 8 ms, and achieves 90% accuracy in its top five suggestions.
Forward citations
Cited by 3 Pith papers
-
Ultrastable, low-error dynamic polarization encoding of deterministically generated single photons
A free-space Sagnac polarization encoder for quantum-dot single photons achieves a 0.69% quantum bit error rate at 152 MHz, the lowest reported for high-speed single-photon encoding, with 60-hour stability.
-
Security of deterministic key distribution with higher-dimensional systems
Higher-dimensional two-way QKD protocols using mutually unbiased bases and Heisenberg-Weyl operators yield secret keys for stronger individual attacks and improved robustness to collective eavesdropping via entropic u...
-
AML-QKD: Adaptive Machine Learning Framework for Real-time Parameter Tuning in QKD
ML-based TCN+PPO controller raises simulated QKD key rates by 14-25% and cuts QBER roughly in half across BB84, E91, and COW, with a separate exploratory QRL variant reporting a 29.2% E91 throughput gain.
Discussion (0). Sign in to comment.