InfLLM: Unveiling the Intrinsic Capacity of LLMs for Understanding Extremely Long Sequences with Training-Free Memory Paper • 2402.04617 • Published Feb 7 • 4
BurstAttention: An Efficient Distributed Attention Framework for Extremely Long Sequences Paper • 2403.09347 • Published Mar 14 • 20
Resonance RoPE: Improving Context Length Generalization of Large Language Models Paper • 2403.00071 • Published Feb 29 • 22
Training-Free Long-Context Scaling of Large Language Models Paper • 2402.17463 • Published Feb 27 • 19
Same Task, More Tokens: the Impact of Input Length on the Reasoning Performance of Large Language Models Paper • 2402.14848 • Published Feb 19 • 18
LongRoPE: Extending LLM Context Window Beyond 2 Million Tokens Paper • 2402.13753 • Published Feb 21 • 109
LongAgent: Scaling Language Models to 128k Context through Multi-Agent Collaboration Paper • 2402.11550 • Published Feb 18 • 14
In Search of Needles in a 10M Haystack: Recurrent Memory Finds What LLMs Miss Paper • 2402.10790 • Published Feb 16 • 40