28 409 18

Fangyuan Yu PRO

Ksgk-fy

fangyuan-ksgk

AI & ML interests

AGI

Recent Activity

updated a collection 6 days ago

Cognition

upvoted a paper 6 days ago

Over-Tokenized Transformer: Vocabulary is Generally Worth Scaling

updated a collection 7 days ago

Cognition

View all activity

Organizations

Ksgk-fy's activity

updated a collection 6 days ago

Cognition

Collection

Perception and abstraction. Each modality is tokenized and embedded into vectors for model to comprehend. • 178 items • Updated 6 days ago • 4

upvoted a paper 6 days ago

Over-Tokenized Transformer: Vocabulary is Generally Worth Scaling

Paper • 2501.16975 • Published 22 days ago • 26

updated a collection 7 days ago

Cognition

Collection

Perception and abstraction. Each modality is tokenized and embedded into vectors for model to comprehend. • 178 items • Updated 6 days ago • 4

upvoted 2 papers 7 days ago

CoS: Chain-of-Shot Prompting for Long Video Understanding

Paper • 2502.06428 • Published 9 days ago • 9

CodeI/O: Condensing Reasoning Patterns via Code Input-Output Prediction

Paper • 2502.07316 • Published 8 days ago • 37

upvoted a paper 13 days ago

VideoJAM: Joint Appearance-Motion Representations for Enhanced Motion Generation in Video Models

Paper • 2502.02492 • Published 15 days ago • 55

upvoted an article 14 days ago

Article

Open-source DeepResearch – Freeing our search agents

15 days ago

• 1.03k

updated a model 21 days ago

Ksgk-fy/kanji_inception_finetune_less_concept_longer

Text-to-Image • Updated 21 days ago • 2

published 3 models 21 days ago

updated 3 models 21 days ago

Ksgk-fy/kanji_inception_finetune_mix_05_concept

Text-to-Image • Updated 21 days ago • 2

Ksgk-fy/kanji_inception_finetune_mixed_concept

Text-to-Image • Updated 21 days ago • 3

Ksgk-fy/kanji_inception_finetune_low_concept

Text-to-Image • Updated 21 days ago • 1

published 2 models 22 days ago

Ksgk-fy/kanji_inception_finetune_mix_05_concept

Text-to-Image • Updated 21 days ago • 2

Ksgk-fy/kanji_inception_finetune_low_concept

Text-to-Image • Updated 21 days ago • 1

updated a dataset 22 days ago

Ksgk-fy/inception-kanji-dataset-512

Viewer • Updated 22 days ago • 31.3k • 39

published a dataset 22 days ago

Ksgk-fy/inception-kanji-dataset-512

Viewer • Updated 22 days ago • 31.3k • 39

updated 2 models 22 days ago

Ksgk-fy/kanji_i2t_finetune

Text-to-Image • Updated 22 days ago • 2

Ksgk-fy/kanji_sdxl_lora_train_text_encoder

Text-to-Image • Updated 22 days ago • 6 •