Papers by Haihua Huang

2 papers
Specialization without Sparsity: Efficient and Expressive Split-Path Experts for LLM Fine-Tuning (2026.findings-acl)

Copied to clipboard

Challenge: Parameter-efficient fine-tuning (PEFT) is a low-cost alternative to full fine-timing due to the massive overhead.
Approach: They propose a Mixture-of-Experts approach that enhances specialization while maintaining low resource overhead.
Outcome: The proposed approach outperforms or matches state-of-the-art methods on GLUE, GSM8K, MBPP, and a text rewriting task from SmolTalk.
LCMA-SRT: Language-Conditional Mixture-of-Experts Adapters for Joint Multilingual Speech Recognition and Translation (2026.acl-long)

Copied to clipboard

Challenge: Existing hierarchical transducers suffer from negative transfer and unstable target-language generation, while training separate models for each direction is computationally prohibitive.
Approach: They propose a hierarchical transducer with language-conditional Mixture-of-Experts adapters to improve multilingual joint automatic speech recognition and speech translation.
Outcome: Experiments on Europarl-ST (9 languages, 72 directions) show that LCMA-SRT improves both ASR and ST within a single joint model, reducing average WER and improving BLEU and COMET over strong hierarchical transducer baselines.

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