← Search

Shubham Katiyar

2 accepted papers

2025

Compress, Gather, and Recompute: REFORMing Long-Context Processing in Transformers

NeurIPS 2025poster

As large language models increasingly gain popularity in real-world applications, processing extremely long contexts, often exceeding the model’s pre-trained context limits, has emerged as a critical challenge. While existing approaches to efficient long-context processing show promise, recurrent co…

Cited by 0SourceScholar
2025

Mamba Drafters for Speculative Decoding

EMNLP 2025

Speculative decoding has emerged as a promising approach to accelerating large language model (LLM) generation using a fast drafter while maintaining alignment with the target model’s distribution. However, existing approaches face a trade-off: external drafters offer flexibility but can suffer from