4 papers
Know When To Fold 'Em: Token-Efficient LLM Synthetic Data Generation via Multi-Stage In-Flight Rejection
Anjir Ahmed Chowdhury, Syed Zawad, Feng Yan
While synthetic data generation with large language models (LLMs) is widely used in post-training pipelines, existing approaches typically generate full outputs before applying qua…
PEML: Parameter-efficient Multi-Task Learning with Optimized Continuous Prompts
Anjir Ahmed Chowdhury, Syed Zawad, Xiaolong Ma +2
Parameter-Efficient Fine-Tuning (PEFT) is widely used for adapting Large Language Models (LLMs) for various tasks. Recently, there has been an increasing demand for fine-tuning a s…
SOLAR: Communication-Efficient Model Adaptation via Subspace-Oriented Latent Adapter Reparametrization
Seyed Mahmoud Sajjadi Mohammadabadi, Xiaolong Ma, Lei Yang +2
Parameter-efficient fine-tuning (PEFT) methods, such as LoRA, enable scalable adaptation of foundation models by injecting low-rank adapters. However, their communication and stora…
Diffusion-Based, Data-Assimilation-Enabled Super-Resolution of Hub-height Winds
Xiaolong Ma, Xu Dong, Ashley Tarrant +5
High-quality observations of hub-height winds are valuable but sparse in space and time. Simulations are widely available on regular grids but are generally biased and too coarse t…