Showing 2025Show all
3 papers · 1 filter
cs.CV2025
SliceFine: The Universal Winning-Slice Hypothesis for Pretrained Networks
Md Kowsher, Ali O. Polat, Ehsan Mohammady Ardehaly +4
This paper presents a theoretical framework explaining why fine tuning small, randomly selected subnetworks (slices) within pre trained models can be sufficient for downstream adap…
cs.CL2025
FlowNIB: An Information Bottleneck Analysis of Bidirectional vs. Unidirectional Language Models
Md Kowsher, Nusrat Jahan Prottasha, Shiyun Xu +4
Bidirectional language models have better context understanding and perform better than unidirectional models on natural language understanding tasks, yet the theoretical reasons b…
cs.CL2025
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…