Papers by Zhenmei Shi

4 papers
Circuit Complexity Bounds for RoPE-based Transformer Architecture (2025.emnlp-main)

Copied to clipboard

Challenge: Recent studies provide the circuit complexity bounds to Transformer-like architectures. position embedding has emerged as a crucial technique in modern large language models.
Approach: They propose to use position embedding to improve Transformer-like architectures by analyzing their circuits and analyzing the results.
Outcome: The proposed model is able to solve canonical tasks without embedding positional information.
Discovering the Gems in Early Layers: Accelerating Long-Context LLMs with 1000x Input Token Reduction (2026.findings-acl)

Copied to clipboard

Challenge: Large Language Models (LLMs) have demonstrated remarkable capabilities in handling long context inputs, but this comes at the cost of increased computational resources and latency.
Approach: They propose an algorithm that uses early LLM layers as filters to select and compress input tokens, reducing the context length for subsequent processing.
Outcome: The proposed method outperforms existing techniques on the Needle in a Haystack task while demonstrating comparable performance on the LongBench challenge.
Conv-Basis: A New Paradigm for Efficient Attention Inference and Gradient Computation in Transformers (2025.findings-emnlp)

Copied to clipboard

Challenge: a large computational cost for attention computation in large language models is a major obstacle .
Approach: They propose a convolution-like structure for attention computation using convolution matrices . they then propose an efficient approximation method to approximate the attention matrix .
Outcome: The proposed method achieves nearly linear time complexity in n1+o(1) time.
Towards Infinite-Long Prefix in Transformer (2025.emnlp-main)

Copied to clipboard

Challenge: Prefix Learning is an empirically efficient and effective method for language models . but the theoretical understandings are limited on the performance of such methods .
Approach: They propose a method that can train an ultra-long prefix in a stylized setting using the Neural Tangent Kernel framework.
Outcome: The proposed method can achieve superior performance on vision, natural language, and math data.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations