Adaptive Computation Modules: Granular Conditional Computation For Efficient Inference Paper • 2312.10193 • Published Dec 15, 2023 • 1
A Simple and Effective $L_2$ Norm-Based Strategy for KV Cache Compression Paper • 2406.11430 • Published Jun 17 • 22
Steering Knowledge Selection Behaviours in LLMs via SAE-Based Representation Engineering Paper • 2410.15999 • Published Oct 21 • 19
Analysing the Residual Stream of Language Models Under Knowledge Conflicts Paper • 2410.16090 • Published Oct 21 • 7
Steering Knowledge Selection Behaviours in LLMs via SAE-Based Representation Engineering Paper • 2410.15999 • Published Oct 21 • 19
A Simple and Effective L_2 Norm-Based Strategy for KV Cache Compression Paper • 2406.11430 • Published Jun 17 • 22