7 papers
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.…
RankGuide: Tensor-Rank-Guided Routing and Steering for Efficient Reasoning
Jiayi Tian, Yupeng Su, Ryan Solgi +2
Large reasoning models (LRMs) enhance problem-solving capabilities by generating explicit multi-step chains of thought (CoT) reasoning; however, they incur substantial inference la…
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…
INTERLACE: Interleaved Layer Pruning and Efficient Adaptation in Large Vision-Language Models
Parsa Madinei, Ryan Solgi, Ziqi Wen +3
We introduce INTERLACE, a novel framework that prunes redundant layers in VLMs while maintaining performance through sample-efficient finetuning. Existing layer pruning methods lea…
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…