-
Mamba: Linear-Time Sequence Modeling with Selective State Spaces
Paper • 2312.00752 • Published • 138 -
Elucidating the Design Space of Diffusion-Based Generative Models
Paper • 2206.00364 • Published • 13 -
GLU Variants Improve Transformer
Paper • 2002.05202 • Published • 1 -
StarCoder 2 and The Stack v2: The Next Generation
Paper • 2402.19173 • Published • 132
Collections
Discover the best community collections!
Collections including paper arxiv:2404.07143
-
LLoCO: Learning Long Contexts Offline
Paper • 2404.07979 • Published • 19 -
LongRoPE: Extending LLM Context Window Beyond 2 Million Tokens
Paper • 2402.13753 • Published • 110 -
LongAgent: Scaling Language Models to 128k Context through Multi-Agent Collaboration
Paper • 2402.11550 • Published • 15 -
LongAlign: A Recipe for Long Context Alignment of Large Language Models
Paper • 2401.18058 • Published • 21
-
Megalodon: Efficient LLM Pretraining and Inference with Unlimited Context Length
Paper • 2404.08801 • Published • 62 -
Ring Attention with Blockwise Transformers for Near-Infinite Context
Paper • 2310.01889 • Published • 9 -
World Model on Million-Length Video And Language With RingAttention
Paper • 2402.08268 • Published • 36 -
Scaling Transformer to 1M tokens and beyond with RMT
Paper • 2304.11062 • Published • 2
-
Megalodon: Efficient LLM Pretraining and Inference with Unlimited Context Length
Paper • 2404.08801 • Published • 62 -
TransformerFAM: Feedback attention is working memory
Paper • 2404.09173 • Published • 43 -
Leave No Context Behind: Efficient Infinite Context Transformers with Infini-attention
Paper • 2404.07143 • Published • 103 -
Block Transformer: Global-to-Local Language Modeling for Fast Inference
Paper • 2406.02657 • Published • 36
-
The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits
Paper • 2402.17764 • Published • 590 -
BitNet: Scaling 1-bit Transformers for Large Language Models
Paper • 2310.11453 • Published • 96 -
Mixture-of-Depths: Dynamically allocating compute in transformer-based language models
Paper • 2404.02258 • Published • 103 -
TransformerFAM: Feedback attention is working memory
Paper • 2404.09173 • Published • 43