4 papers · 1 filter
LoRi: Low-Rank Distillation for Implicit Reasoning
Ryan Solgi, Jiayi Tian, Zheng Zhang
Implicit chain-of-thought (iCoT) methods aim to internalize reasoning in large language models, but often underperform explicit CoT prompting. We empirically find that hidden-state…
Activation-Informed Pareto-Guided Low-Rank Compression for Efficient LLM/VLM
Ryan Solgi, Parsa Madinei, Jiayi Tian +4
Large language models (LLM) and vision-language models (VLM) have achieved state-of-the-art performance, but they impose significant memory and computing challenges in deployment.…
FLAT-LLM: Fine-grained Low-rank Activation Space Transformation for Large Language Model Compression
Jiayi Tian, Ryan Solgi, Jinming Lu +3
Large Language Models (LLMs) have enabled remarkable progress in natural language processing, yet their high computational and memory demands pose challenges for deployment in reso…
Saten: Sparse Augmented Tensor Networks for Post-Training Compression of Large Language Models
Ryan Solgi, Kai Zhen, Rupak Vignesh Swaminathan +4
The efficient implementation of large language models (LLMs) is crucial for deployment on resource-constrained devices. Low-rank tensor compression techniques, such as tensor-train…