TreeSynth: Synthesizing Diverse Data from Scratch via Tree-Guided Subspace Partitioning
A spotlight paper at NeurIPS 2025 presenting TreeSynth, a method for synthesizing diverse data through tree-guided subspace partitioning.
QSpec: Speculative decoding with complementary quantization schemes
EMNLP 2025 main conference paper on efficient inference through speculative decoding.
juntao-zhao
MoS: Unleashing parameter efficiency of low-rank adaptation with mixture of shards
A paper at ICLR 2025 presenting MoS, a method for more parameter-efficient LoRA through mixture of shards.
PRoLoRA: Partial rotation empowers more parameter-efficient LoRA
A main conference paper at ACL 2024 presenting PRoLoRA for more parameter-efficient fine-tuning.
LoRA meets dropout under a unified framework
ACL 2024 Findings paper unifying LoRA and dropout in a single framework.