Papers by Weigao Sun

4 papers
Native Hybrid Attention for Efficient Sequence Modeling (2026.acl-long)

Copied to clipboard

Challenge: Experimental results show that NHA surpasses Transformers on recall-intensive tasks.
Approach: They propose a hybrid architecture of linear and full attention that integrates both into a unified layer design.
Outcome: The proposed architecture surpasses Transformers and other hybrid baselines on recall-intensive and commonsense reasoning tasks.
CogniBench: A Legal-inspired Framework and Dataset for Assessing Cognitive Faithfulness of Large Language Models (2025.acl-long)

Copied to clipboard

Challenge: Existing benchmarks focus on “factual statements” that rephrase source materials, but ignore “cognitive statements” . evaluating and detecting "faithfulness hallucinations" remains challenging .
Approach: They propose a framework to assess faithfulness of cognitive statements and introduce a dataset to scale easily across models.
Outcome: The proposed framework assesses faithfulness of cognitive statements and scales easily across models.
Scaling Laws for Linear Complexity Language Models (2024.emnlp-main)

Copied to clipboard

Challenge: Existing scaling laws for large language models are unclear, but they are useful for scalability.
Approach: They propose scaling laws for linear complexity language models to establish a foundation for their scalability.
Outcome: The proposed models demonstrate superior linguistic proficiency and knowledge retention.
Nirvana: A Specialized Generalist Model With Task-Aware Memory Mechanism (2026.acl-long)

Copied to clipboard

Challenge: Existing models lack task-guided specialized memory mechanisms . specialized generalist models excel at general language tasks but struggle in specialized domains.
Approach: They propose a specialized generalist model with specialized memory and updater that can optimize for specialized domains.
Outcome: The proposed model matches or surpasses baselines on general benchmarks and achieves lowest perplexity across specialized domains.

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