Search Results for author:
Found 13 papers, 8 papers with code
Activation Steering for Robust Type Prediction in CodeLLMs
We apply our approach to the task of type prediction for the gradually typed languages Python and TypeScript.
StarCoder 2 and The Stack v2: The Next Generation
Our large model, StarCoder2- 15B, significantly outperforms other models of comparable size.
Ranked #25 on
Code Generation
on MBPP
Can It Edit? Evaluating the Ability of Large Language Models to Follow Code Editing Instructions
These are tasks in which the model is provided a block of code and an instruction to modify the code.
Knowledge Transfer from High-Resource to Low-Resource Programming Languages for Code LLMs
We apply this approach to generate tens of thousands of validated training items for Julia, Lua, OCaml, R, and Racket.
StudentEval: A Benchmark of Student-Written Prompts for Large Language Models of Code
We use StudentEval to evaluate 5 Code LLMs and find that StudentEval is a better discriminator of model performance than existing benchmarks.
Type Prediction With Program Decomposition and Fill-in-the-Type Training
TypeScript and Python are two programming languages that support optional type annotations, which are useful but tedious to introduce and maintain.
StarCoder: may the source be with you!
The BigCode community, an open-scientific collaboration working on the responsible development of Large Language Models for Code (Code LLMs), introduces StarCoder and StarCoderBase: 15. 5B parameter models with 8K context length, infilling capabilities and fast large-batch inference enabled by multi-query attention.
Ranked #43 on
Code Generation
on MBPP
SantaCoder: don't reach for the stars!
The BigCode project is an open-scientific collaboration working on the responsible development of large language models for code.
MultiPL-E: A Scalable and Extensible Approach to Benchmarking Neural Code Generation
Using these new parallel benchmarks, we evaluate the multi-language performance of three state-of-the-art code generation models: Codex, CodeGen, and InCoder.
Iterative Program Synthesis for Adaptable Social Navigation
Robot social navigation is influenced by human preferences and environment-specific scenarios such as elevators and doors, thus necessitating end-user adaptability.
Program Synthesis
Robotics
Programming Languages
Accelerating Graph Sampling for Graph Machine Learning using GPUs
Several representation learning algorithms for graph data, such as DeepWalk, node2vec, and GraphSAGE, sample the graph to produce mini-batches that are suitable for training a DNN.
Robot Action Selection Learning via Layered Dimension Informed Program Synthesis
Action selection policies (ASPs), used to compose low-level robot skills into complex high-level tasks are commonly represented as neural networks (NNs) in the state of the art.
Interactive Robot Transition Repair With SMT
Complex robot behaviors are often structured as state machines, where states encapsulate actions and a transition function switches between states.
Robotics Programming Languages
