4 papers · 1 filter
Dynamic Short Convolutions Improve Transformers
Oliver Sieberling, Bharat Runwal, Rameswar Panda +1
Transformers have become the dominant architecture for large language models, largely due to the scalability and flexibility of attention, feed-forward layers, residual connections…
PRISM: Demystifying Retention and Interaction in Mid-Training
Bharat Runwal, Ashish Agrawal, Anurag Roy +1
We present PRISM, a comprehensive empirical study of mid-training design choices for large language models. Through controlled experiments across seven base models spanning four fa…
From PEFT to DEFT: Parameter Efficient Finetuning for Reducing Activation Density in Transformers
Bharat Runwal, Tejaswini Pedapati, Pin-Yu Chen
Pretrained Language Models (PLMs) have become the de facto starting point for fine-tuning on downstream tasks. However, as model sizes continue to increase, traditional fine-tuning…
SOUL: Unlocking the Power of Second-Order Optimization for LLM Unlearning
Jinghan Jia, Yihua Zhang, Yimeng Zhang +5
Large Language Models (LLMs) have highlighted the necessity of effective unlearning mechanisms to comply with data regulations and ethical AI practices. LLM unlearning aims at remo…