Yixin Song

yixinsong's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes

upvoted a paper about 2 months ago

Configurable Foundation Models: Building LLMs from a Modular Perspective

Paper • 2409.02877 • Published Sep 4 • 27

upvoted 3 papers 3 months ago

Dolphin: Long Context as a New Modality for Energy-Efficient On-Device Language Models

Paper • 2408.15518 • Published Aug 28 • 42

Scaling Synthetic Data Creation with 1,000,000,000 Personas

Paper • 2406.20094 • Published Jun 28 • 94

Magpie: Alignment Data Synthesis from Scratch by Prompting Aligned LLMs with Nothing

Paper • 2406.08464 • Published Jun 12 • 65

upvoted 2 papers 4 months ago

Q-Sparse: All Large Language Models can be Fully Sparsely-Activated

Paper • 2407.10969 • Published Jul 15 • 20

Qwen2 Technical Report

Paper • 2407.10671 • Published Jul 15 • 155

upvoted 3 papers 5 months ago

ReLU^2 Wins: Discovering Efficient Activation Functions for Sparse LLMs

Paper • 2402.03804 • Published Feb 6 • 2

PowerInfer-2: Fast Large Language Model Inference on a Smartphone

Paper • 2406.06282 • Published Jun 10 • 36

Turbo Sparse: Achieving LLM SOTA Performance with Minimal Activated Parameters

Paper • 2406.05955 • Published Jun 10 • 22

upvoted a paper 7 months ago

Physics of Language Models: Part 3.2, Knowledge Manipulation

Paper • 2309.14402 • Published Sep 25, 2023 • 6

upvoted a paper 9 months ago

The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits

Paper • 2402.17764 • Published Feb 27 • 602

upvoted a collection 10 months ago

BrockportGPT v2

Collection

The improved version of BrockportGPT v1. This generation has enhanced datasets that are more usable. See https://github.com/msaad02/honors-thesis • 7 items • Updated Mar 18 • 1

upvoted a paper 11 months ago

PIA: Your Personalized Image Animator via Plug-and-Play Modules in Text-to-Image Models

Paper • 2312.13964 • Published Dec 21, 2023 • 18