Oscar, Li's picture

Oscar, Li

liswei

·

https://www.csie.ntu.edu.tw/~r11944004/

AI & ML interests

Multimodal Deep Learning, Natural Language Processing, Efficient Fine-Tuning

Recent Activity

updated a model 29 days ago

liswei/emojilm-0.6b-GGUF

published a model 30 days ago

liswei/emojilm-0.6b-GGUF

updated a model 30 days ago

liswei/emojilm-0.6b

View all activity

Organizations

None yet

liswei's activity

upvoted a collection about 1 year ago

OpenELM Pretrained Models

4 items • Updated Oct 4, 2024 • 50

upvoted 3 papers over 1 year ago

Grandmaster-Level Chess Without Search

Paper • 2402.04494 • Published Feb 7, 2024 • 70

Alpha-CLIP: A CLIP Model Focusing on Wherever You Want

Paper • 2312.03818 • Published Dec 6, 2023 • 34

TEAL: Tokenize and Embed ALL for Multi-modal Large Language Models

Paper • 2311.04589 • Published Nov 8, 2023 • 23

upvoted 6 papers almost 2 years ago

FLIQS: One-Shot Mixed-Precision Floating-Point and Integer Quantization Search

Paper • 2308.03290 • Published Aug 7, 2023 • 6

AgentBench: Evaluating LLMs as Agents

Paper • 2308.03688 • Published Aug 7, 2023 • 25

Convolutions Die Hard: Open-Vocabulary Segmentation with Single Frozen Convolutional CLIP

Paper • 2308.02487 • Published Aug 4, 2023 • 13

From Sparse to Soft Mixtures of Experts

Paper • 2308.00951 • Published Aug 2, 2023 • 20

Unified Model for Image, Video, Audio and Language Tasks

Paper • 2307.16184 • Published Jul 30, 2023 • 15

EgoVLPv2: Egocentric Video-Language Pre-training with Fusion in the Backbone

Paper • 2307.05463 • Published Jul 11, 2023 • 11