Papers by Mingzhu Huang

4 papers
Distributional Clarity: The Hidden Driver of RL-Friendliness in Large Language Models (2026.acl-long)

Copied to clipboard

Challenge: RL-friendly models exhibit intra-class compactness and inter-class separation in probability assignments . under identical training, Qwen models achieve substantial gains, while others like Llama yield limited improvements.
Approach: They propose a method to quantify distributional clarity in probability space . they show distributional clearness is a trainable property underlying RL-Friendliness .
Outcome: The proposed model families achieve substantial gains under identical training, while others like Llama yield limited improvements.
MMAG: Multimodal Learning for Mucus Anomaly Grading in Nasal Endoscopy via Semantic Attribute Prompting (2025.emnlp-main)

Copied to clipboard

Challenge: Accurate grading of rhinitis severity relies heavily on the characterization of key secretions, notably clear nasal discharge (CND) and purulent nasal secretion (PUS).
Approach: They propose a framework that integrates structured prompts with rank-aware vision-language modeling for joint detection and grading.
Outcome: The proposed model improves AUC and F1 scores on CND and PUS datasets by 6.31% and 4.79%.
MeepleLM: A Virtual Playtester Simulating Diverse Subjective Experiences (2026.acl-long)

Copied to clipboard

Challenge: Recent advances in large language models have expanded the role of board games as creative co-designers . however, current systems lack the capacity to offer constructive critique grounded in the emergent user experience .
Approach: They propose a large language model that internalizes persona-specific reasoning patterns to accurately simulate the subjective feedback of diverse player archetypes.
Outcome: The proposed model outperforms commercial models in community alignment and critique quality.
Query Enhanced Knowledge-Intensive Conversation via Unsupervised Joint Modeling (2023.acl-long)

Copied to clipboard

Challenge: Existing methods to retrieve knowledge-intensive conversations are based on external resources such as Wikipedia databases or search engine results.
Approach: They propose an unsupervised query enhanced approach for knowledge-intensive conversations . they conduct experiments on three knowledge- intensive conversation datasets .
Outcome: The proposed approach performs better than all unsupervised methods across three datasets and achieves competitive performance compared to supervised methods.

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