Fangyuan Yu's picture

Fangyuan Yu PRO

Ksgk-fy

·

fangyuan-ksgk

AI & ML interests

AGI

Recent Activity

upvoted a paper 3 days ago

Divot: Diffusion Powers Video Tokenizer for Comprehension and Generation

updated a collection 3 days ago

updated a collection 3 days ago

View all activity

Organizations

Ksgk-fy's activity

upvoted a paper 3 days ago

Divot: Diffusion Powers Video Tokenizer for Comprehension and Generation

Paper • 2412.04432 • Published 20 days ago • 14

updated a collection 3 days ago

Cognition

Perception and abstraction. Each modality is tokenized and embedded into vectors for model to comprehend. • 171 items • Updated 3 days ago • 4

upvoted 2 papers 3 days ago

Feather the Throttle: Revisiting Visual Token Pruning for Vision-Language Model Acceleration

Paper • 2412.13180 • Published 8 days ago • 12

Emergence of Abstractions: Concept Encoding and Decoding Mechanism for In-Context Learning in Transformers

Paper • 2412.12276 • Published 9 days ago • 15

updated a collection 3 days ago

Cognition

Perception and abstraction. Each modality is tokenized and embedded into vectors for model to comprehend. • 171 items • Updated 3 days ago • 4

updated a collection 12 days ago

Cognition

Perception and abstraction. Each modality is tokenized and embedded into vectors for model to comprehend. • 171 items • Updated 3 days ago • 4

upvoted a paper 12 days ago

Human Expertise in Algorithmic Prediction

Paper • 2402.00793 • Published Feb 1 • 1

updated a collection 13 days ago

Cognition

Perception and abstraction. Each modality is tokenized and embedded into vectors for model to comprehend. • 171 items • Updated 3 days ago • 4

upvoted a paper 13 days ago

AmoebaLLM: Constructing Any-Shape Large Language Models for Efficient and Instant Deployment

Paper • 2411.10606 • Published Nov 15 • 1

updated a collection 14 days ago

Cognition

Perception and abstraction. Each modality is tokenized and embedded into vectors for model to comprehend. • 171 items • Updated 3 days ago • 4

upvoted a paper 14 days ago

MaestroMotif: Skill Design from Artificial Intelligence Feedback

Paper • 2412.08542 • Published 14 days ago • 1

updated a collection 14 days ago

Cognition

Perception and abstraction. Each modality is tokenized and embedded into vectors for model to comprehend. • 171 items • Updated 3 days ago • 4

upvoted a paper 14 days ago

CMT: A Memory Compression Method for Continual Knowledge Learning of Large Language Models

Paper • 2412.07393 • Published 15 days ago • 2

updated a collection 14 days ago

Cognition

Perception and abstraction. Each modality is tokenized and embedded into vectors for model to comprehend. • 171 items • Updated 3 days ago • 4

upvoted a paper 14 days ago

Video Token Merging for Long-form Video Understanding

Paper • 2410.23782 • Published Oct 31 • 2