4 papers
Monkey Jump : MoE-Style PEFT for Efficient Multi-Task Learning
Nusrat Jahan Prottasha, Md Kowsher, Chun-Nam Yu +2
Mixture-of-experts variants of parameter-efficient fine-tuning enable per-token specialization, but they introduce additional trainable routers and expert parameters, increasing me…
LLMartini: Seamless and Interactive Leveraging of Multiple LLMs through Comparison and Composition
Yingtian Shi, Jinda Yang, Yuhan Wang +4
The growing diversity of large language models (LLMs) means users often need to compare and combine outputs from different models to obtain higher-quality or more comprehensive res…
Predicting Through Generation: Why Generation Is Better for Prediction
Md Kowsher, Nusrat Jahan Prottasha, Prakash Bhat +6
This paper argues that generating output tokens is more effective than using pooled representations for prediction tasks because token-level generation retains more mutual informat…
Does Self-Attention Need Separate Weights in Transformers?
Md Kowsher, Nusrat Jahan Prottasha, Chun-Nam Yu +2
The success of self-attention lies in its ability to capture long-range dependencies and enhance context understanding, but it is limited by its computational complexity and challe…