-
Language Modeling Is Compression
Paper • 2309.10668 • Published • 83 -
Sorted LLaMA: Unlocking the Potential of Intermediate Layers of Large Language Models for Dynamic Inference Using Sorted Fine-Tuning (SoFT)
Paper • 2309.08968 • Published • 23 -
Vision Transformers Need Registers
Paper • 2309.16588 • Published • 83 -
Localizing and Editing Knowledge in Text-to-Image Generative Models
Paper • 2310.13730 • Published • 7
Sean Tseng
seantyh
·
AI & ML interests
Computational linguistics, psycholinguistics, NLP, lexical semantics, lexical resources
Organizations
RL
Prompt
Multilingual
Multimodal
-
Multimodal Foundation Models: From Specialists to General-Purpose Assistants
Paper • 2309.10020 • Published • 40 -
Kosmos-2.5: A Multimodal Literate Model
Paper • 2309.11419 • Published • 55 -
AnyMAL: An Efficient and Scalable Any-Modality Augmented Language Model
Paper • 2309.16058 • Published • 56 -
Jointly Training Large Autoregressive Multimodal Models
Paper • 2309.15564 • Published • 8
LLM-mechanics
-
Language Modeling Is Compression
Paper • 2309.10668 • Published • 83 -
Sorted LLaMA: Unlocking the Potential of Intermediate Layers of Large Language Models for Dynamic Inference Using Sorted Fine-Tuning (SoFT)
Paper • 2309.08968 • Published • 23 -
Vision Transformers Need Registers
Paper • 2309.16588 • Published • 83 -
Localizing and Editing Knowledge in Text-to-Image Generative Models
Paper • 2310.13730 • Published • 7
Multilingual
RL
Multimodal
-
Multimodal Foundation Models: From Specialists to General-Purpose Assistants
Paper • 2309.10020 • Published • 40 -
Kosmos-2.5: A Multimodal Literate Model
Paper • 2309.11419 • Published • 55 -
AnyMAL: An Efficient and Scalable Any-Modality Augmented Language Model
Paper • 2309.16058 • Published • 56 -
Jointly Training Large Autoregressive Multimodal Models
Paper • 2309.15564 • Published • 8
Prompt