1 citations · 1 across the 5 of their papers we have counts for
6 papers
STR: Supervised Transcoder Replacement for Reducing Steering Side Effects
Haonan Yu, Junhao Liu, Zhenyu Yan +2
Model steering can strengthen a target behavior while degrading other useful behaviors. We introduce Supervised Transcoder Replacement (STR) to reduce these side effects for existi…
Scalarizations of magnetized Reissner-Nordström black holes induced by parity-violating and parity-preserving interactions
Hao-Jie Lin, Tao Zhu, Jing-Fei Zhang +1
We study spontaneous scalarization of a scalar field in the magnetized Reissner--Nordström spacetime induced by parity-violating and parity-preserving interactions, represented by…
WASD: Locating Critical Neurons as Sufficient Conditions for Explaining and Controlling LLM Behavior
Haonan Yu, Junhao Liu, Zhenyu Yan +2
Precise behavioral control of large language models (LLMs) is critical for complex applications. However, existing methods often incur high training costs, lack natural language co…
HAP: Hybrid Adaptive Parallelism for Efficient Mixture-of-Experts Inference
Haoran Lin, Xianzhi Yu, Kang Zhao +7
Current inference systems for Mixture-of-Experts (MoE) models primarily employ static parallelization strategies. However, these static approaches cannot consistently achieve optim…
FastAttention: Extend FlashAttention2 to NPUs and Low-resource GPUs
Haoran Lin, Xianzhi Yu, Kang Zhao +17
FlashAttention series has been widely applied in the inference of large language models (LLMs). However, FlashAttention series only supports the high-level GPU architectures, e.g.,…
O2ATH: An OpenMP Offloading Toolkit for the Sunway Heterogeneous Manycore Platform
Haoran Lin, Lifeng Yan, Qixin Chang +13
The next generation Sunway supercomputer employs the SW26010pro processor, which features a specialized on-chip heterogeneous architecture. Applications with significant hotspots c…