Haocheng Xi
1 indexed paper
Recent (6 mo)
1With code
0Influential cites
0Benchmarked
0Publications per year
126
Top categories
ML×1AI×1
Frequent co-authors
Research Timeline
2026
LeapQuant: Efficient Linear Attention with Accurate Recurrent State Quantization
The paper proposes LeapQuant, a training-free method that achieves near-lossless performance under 8-bit recurrent-state quantization for LLMs.
Highlighted terms show continued research focus across papers
Papers
cs.LGcs.AIEmpiricalRecentSep 29, 2026
LeapQuant: Efficient Linear Attention with Accurate Recurrent State Quantization
Yi Pan, Haocheng Xi, Kan Zhu, Xingyang Li +9 more
The paper proposes LeapQuant, a training-free method that achieves near-lossless performance under 8-bit recurrent-state quantization for LLMs.
View →