Yi-Lin Sung

a2889184's activity

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

authored 9 papers 4 days ago

Unified Coarse-to-Fine Alignment for Video-Text Retrieval

Paper • 2309.10091 • Published Sep 18, 2023

Merge, Then Compress: Demystify Efficient SMoE with Hints from Its Routing Policy

Paper • 2310.01334 • Published Oct 2, 2023 • 3

ECoFLaP: Efficient Coarse-to-Fine Layer-Wise Pruning for Vision-Language Models

Paper • 2310.02998 • Published Oct 4, 2023 • 1

Training Neural Networks with Fixed Sparse Masks

Paper • 2111.09839 • Published Nov 18, 2021 • 1

VL-Adapter: Parameter-Efficient Transfer Learning for Vision-and-Language Tasks

Paper • 2112.06825 • Published Dec 13, 2021

SELMA: Learning and Merging Skill-Specific Text-to-Image Experts with Auto-Generated Data

Paper • 2403.06952 • Published Mar 11, 2024

Glider: Global and Local Instruction-Driven Expert Router

Paper • 2410.07172 • Published Oct 9, 2024

RSQ: Learning from Important Tokens Leads to Better Quantized LLMs

Paper • 2503.01820 • Published 5 days ago • 2

LST: Ladder Side-Tuning for Parameter and Memory Efficient Transfer Learning

Paper • 2206.06522 • Published Jun 13, 2022

upvoted a paper 4 days ago

RSQ: Learning from Important Tokens Leads to Better Quantized LLMs

Paper • 2503.01820 • Published 5 days ago • 2

commented a paper 4 days ago

RSQ: Learning from Important Tokens Leads to Better Quantized LLMs

Paper • 2503.01820 • Published 5 days ago • 2 •

3

New activity in meta-llama/Llama-3.1-405B 5 months ago

Can someone reproduce the accuracy of Llama 3.1 models?

2

#11 opened 8 months ago by

damoict

Can someone reproduce the accuracy of Llama 3.1 models?

2

#11 opened 8 months ago by

damoict