National Deep Inference Fabric

university

https://ndif.us

AI & ML interests

None defined yet.

authored 3 papers 7 months ago

Substance Beats Style: Why Beginning Students Fail to Code with LLMs

Paper • 2410.19792 • Published Oct 15, 2024

SelfCodeAlign: Self-Alignment for Code Generation

Paper • 2410.24198 • Published Oct 31, 2024 • 25

AgentPack: A Dataset of Code Changes, Co-Authored by Agents and Humans

Paper • 2509.21891 • Published Sep 26, 2025

authored a paper about 1 year ago

PhD Knowledge Not Required: A Reasoning Challenge for Large Language Models

Paper • 2502.01584 • Published Feb 3, 2025 • 9

authored 2 papers about 1 year ago

SliderSpace: Decomposing the Visual Capabilities of Diffusion Models

Paper • 2502.01639 • Published Feb 3, 2025 • 26

Open Problems in Mechanistic Interpretability

Paper • 2501.16496 • Published Jan 27, 2025 • 22

authored 2 papers over 1 year ago

Art-Free Generative Models: Art Creation Without Graphic Art Knowledge

Paper • 2412.00176 • Published Nov 29, 2024 • 9

Measuring Progress in Dictionary Learning for Language Model Interpretability with Board Game Models

Paper • 2408.00113 • Published Jul 31, 2024 • 8

authored a paper almost 2 years ago

NNsight and NDIF: Democratizing Access to Foundation Model Internals

Paper • 2407.14561 • Published Jul 18, 2024 • 35

authored a paper almost 2 years ago

NNsight and NDIF: Democratizing Access to Foundation Model Internals

Paper • 2407.14561 • Published Jul 18, 2024 • 35

authored a paper almost 2 years ago

NNsight and NDIF: Democratizing Access to Foundation Model Internals

Paper • 2407.14561 • Published Jul 18, 2024 • 35

authored 2 papers almost 2 years ago

Token Erasure as a Footprint of Implicit Vocabulary Items in LLMs

Paper • 2406.20086 • Published Jun 28, 2024 • 6

Customizing Text-to-Image Models with a Single Image Pair

Paper • 2405.01536 • Published May 2, 2024 • 22

authored 7 papers about 2 years ago

Activation Steering for Robust Type Prediction in CodeLLMs

Paper • 2404.01903 • Published Apr 2, 2024 • 2

StarCoder 2 and The Stack v2: The Next Generation

Paper • 2402.19173 • Published Feb 29, 2024 • 156

Can It Edit? Evaluating the Ability of Large Language Models to Follow Code Editing Instructions

Paper • 2312.12450 • Published Dec 11, 2023 • 2

Type Prediction With Program Decomposition and Fill-in-the-Type Training

Paper • 2305.17145 • Published May 25, 2023

Knowledge Transfer from High-Resource to Low-Resource Programming Languages for Code LLMs

Paper • 2308.09895 • Published Aug 19, 2023 • 1

StudentEval: A Benchmark of Student-Written Prompts for Large Language Models of Code

Paper • 2306.04556 • Published Jun 7, 2023

MultiPL-E: A Scalable and Extensible Approach to Benchmarking Neural Code Generation

Paper • 2208.08227 • Published Aug 17, 2022 • 1