mkly (Mike)

upvoted a paper 3 months ago

Large Language Models as Optimizers

Paper • 2309.03409 • Published Sep 7, 2023 • 75

upvoted 4 papers 9 months ago

Copilot Evaluation Harness: Evaluating LLM-Guided Software Programming

Paper • 2402.14261 • Published Feb 22 • 10

TofuEval: Evaluating Hallucinations of LLMs on Topic-Focused Dialogue Summarization

Paper • 2402.13249 • Published Feb 20 • 11

Membership Inference Attacks From First Principles

Paper • 2112.03570 • Published Dec 7, 2021 • 1

Assessing Language Model Deployment with Risk Cards

Paper • 2303.18190 • Published Mar 31, 2023 • 1

upvoted 4 papers 10 months ago

Self-Discover: Large Language Models Self-Compose Reasoning Structures

Paper • 2402.03620 • Published Feb 6 • 109

Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection

Paper • 2310.11511 • Published Oct 17, 2023 • 74

Generate rather than Retrieve: Large Language Models are Strong Context Generators

Paper • 2209.10063 • Published Sep 21, 2022 • 1

WaveCoder: Widespread And Versatile Enhanced Instruction Tuning with Refined Data Generation

Paper • 2312.14187 • Published Dec 20, 2023 • 49

upvoted 4 papers 11 months ago

Blending Is All You Need: Cheaper, Better Alternative to Trillion-Parameters LLM

Paper • 2401.02994 • Published Jan 4 • 48

DocLLM: A layout-aware generative language model for multimodal document understanding

Paper • 2401.00908 • Published Dec 31, 2023 • 181

AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration

Paper • 2306.00978 • Published Jun 1, 2023 • 8

Time is Encoded in the Weights of Finetuned Language Models

Paper • 2312.13401 • Published Dec 20, 2023 • 19

upvoted 7 papers about 1 year ago

Mike

AI & ML interests

Organizations

mkly's activity

Large Language Models as Optimizers

Copilot Evaluation Harness: Evaluating LLM-Guided Software Programming

TofuEval: Evaluating Hallucinations of LLMs on Topic-Focused Dialogue Summarization

Membership Inference Attacks From First Principles

Assessing Language Model Deployment with Risk Cards

Self-Discover: Large Language Models Self-Compose Reasoning Structures

Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection

Generate rather than Retrieve: Large Language Models are Strong Context Generators

WaveCoder: Widespread And Versatile Enhanced Instruction Tuning with Refined Data Generation

Blending Is All You Need: Cheaper, Better Alternative to Trillion-Parameters LLM

DocLLM: A layout-aware generative language model for multimodal document understanding

AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration

Time is Encoded in the Weights of Finetuned Language Models

CodePlan: Repository-level Coding using LLMs and Planning

Diff2Lip: Audio Conditioned Diffusion Models for Lip-Synchronization

RLAIF: Scaling Reinforcement Learning from Human Feedback with AI Feedback

YaRN: Efficient Context Window Extension of Large Language Models

RoFormer: Enhanced Transformer with Rotary Position Embedding

SoTaNa: The Open-Source Software Development Assistant

Nougat: Neural Optical Understanding for Academic Documents