Skip to content
#

long-context-llm

Star

Here are 5 public repositories matching this topic...

mohammadtavakoli78 / BEAM

Star 152

[ICLR 2026] Beyond a Million Tokens: Benchmarking and Enhancing Long-Term Memory in LLMs

light nlp benchmarking machine-learning natural-language-processing beam light-framework long-term-memory rag llm retrieval-augmented-generation long-context-evaluation long-context-llm long-context-llms beam-benchmark benchmark-long-context benchmark-long-term-memory long-term-memory-benchmark long-context-evaluation-benchmark long-term-memory-method
  • Updated Aug 31, 2026
  • Python

ShreyasVR2545 / probe_architecture_mechanics

Star 0

Silence of the RAM: constant-memory safety probing for long-context LLMs. A streaming hard-max probe with a measured Theta(min(C,N)) memory law (flat 19.1 MiB to N=131,072 vs 652.1 MiB for softmax pooling), the subgradient obstruction it creates, and the fragmentation attack that defeats it.

machine-learning pytorch ai-safety calibration-methods mechanistic-interpretability long-context-llm activation-probing cascading-classifiers
  • Updated Sep 10, 2026
  • Python

Add this topic to your repo

To associate your repository with the long-context-llm topic, visit your repo's landing page and select "manage topics."

Learn more