21 citations · 27 across the 12 of their papers we have counts for
9 papers · 1 filter
PEFT-Arena: Understanding Parameter-Efficient Finetuning from a Stability-Plasticity Perspective
Yangyi Huang, Ruotian Peng, Zeju Qiu +4
Parameter-efficient finetuning (PEFT) has become the standard approach for adapting large language models, yet evaluations largely emphasize downstream accuracy while overlooking t…
Pion: A Spectrum-Preserving Optimizer via Orthogonal Equivalence Transformation
Kexuan Shi, Hanxuan Li, Zeju Qiu +3
We introduce Pion, a spectrum-preserving optimizer for large language model (LLM) training based on orthogonal equivalence transformation. Unlike additive optimizers such as Adam a…
Rigidity-Aware Geometric Pretraining for Protein Design and Conformational Ensembles
Zhanghan Ni, Yanjing Li, Zeju Qiu +4
Generative models have recently advanced protein design by learning the statistical regularities of natural structures. However, current approaches face three ke…
POET-X: Memory-efficient LLM Training by Scaling Orthogonal Transformation
Zeju Qiu, Lixin Liu, Adrian Weller +2
Efficient and stable training of large language models (LLMs) remains a core challenge in modern machine learning systems. To address this challenge, Reparameterized Orthogonal Equ…
Orthogonal Finetuning Made Scalable
Zeju Qiu, Weiyang Liu, Adrian Weller +1
Orthogonal finetuning (OFT) offers highly parameter-efficient adaptation while preventing catastrophic forgetting, but its high runtime and memory demands limit practical deploymen…
Reparameterized LLM Training via Orthogonal Equivalence Transformation
Zeju Qiu, Simon Buchholz, Tim Z. Xiao +3
While large language models (LLMs) are driving the rapid advancement of artificial intelligence, effectively and reliably training these large models remains one of the field's mos…
Can Large Language Models Understand Symbolic Graphics Programs?
Zeju Qiu, Weiyang Liu, Haiwen Feng +7
Against the backdrop of enthusiasm for large language models (LLMs), there is a growing need to scientifically assess their capabilities and shortcomings. This is nontrivial in par…
Parameter-Efficient Orthogonal Finetuning via Butterfly Factorization
Weiyang Liu, Zeju Qiu, Yao Feng +11
Large foundation models are becoming ubiquitous, but training them from scratch is prohibitively expensive. Thus, efficiently adapting these powerful models to downstream tasks is…
Iterative Teaching by Data Hallucination
Zeju Qiu, Weiyang Liu, Tim Z. Xiao +5
We consider the problem of iterative machine teaching, where a teacher sequentially provides examples based on the status of a learner under a discrete input space (i.e., a pool of…