Papers by Minghua Zhang

9 papers
Learning Universal Sentence Representations with Mean-Max Attention Autoencoder (D18-1)

Copied to clipboard

Challenge: Existing methods to learn universal sentence representations focus on supervised learning.
Approach: They propose a mean-max attention autoencoder that uses a multi-head mechanism to reconstruct the input sequence.
Outcome: The proposed model outperforms state-of-the-art unsupervised single methods on a wide range of 10 transfer tasks.
UFO: A UI-Focused Agent for Windows OS Interaction (2025.naacl-long)

Copied to clipboard

Challenge: UFO is a UI-Fcused agent designed to fulfill user requests tailored to Windows OS applications . it decomposes user requests using divide-and-conquer approach, enabling seamless navigation and addressing sub-tasks across multiple applications.
Approach: They propose a UI-Fcused Windows OS agent that decomposes user requests using a divide-and-conquer approach and incorporates a control interaction module tailored for Windows OS.
Outcome: The proposed agent decomposes user requests using divide-and-conquer approach, enabling seamless navigation and addressing sub-tasks across multiple applications.
Question-type Driven Question Generation (D19-1)

Copied to clipboard

Challenge: Existing work suffers from mismatching between question type and answer . existing work fails to generate questions with type how while answer is personal name .
Approach: They propose to automatically predict the question type based on the input answer and context.
Outcome: The proposed model improves on both SQuAD and MARCO datasets and improves accuracy on the input answer and context.
d-TreeRPO: Towards More Reliable Policy Optimization for Diffusion Language Models (2026.acl-long)

Copied to clipboard

Challenge: Existing RL methods suffer from reliability bottlenecks due to reward sparsity and intractable computations . d-TreeRPO provides fine-grained and verifiable step-wise reward signals .
Approach: They propose a reliable reinforcement learning framework for diffusion large language models that leverages tree-structured rollouts and bottom-up advantage computation based on verifiable outcome rewards.
Outcome: The proposed framework outperforms baseline models and achieves significant improvements across reasoning benchmarks.
MARK: Multi-agent Collaboration with Ranking Guidance for Text-attributed Graph Clustering (2025.findings-acl)

Copied to clipboard

Challenge: Existing approaches to cluster graphs with GNNs are limited due to label scarcity.
Approach: They propose to leverage large language models to enhance text-attributed graph clustering by using three LLMs as ranking-based supervision signals.
Outcome: The proposed approach generates reliable guidance using collaboration of three LLM-based agents as ranking-based supervision signals.
DUET: Joint Exploration of User–Item Profiles in Recommendation System (2026.findings-acl)

Copied to clipboard

Challenge: Existing LLMs are opaque and difficult to interpret, resulting in limited interpretability.
Approach: They propose an interaction-aware profile generator that jointly produces user and item profiles conditioned on both user history and item evidence.
Outcome: The proposed model outperforms baselines on three real-world datasets.
Everything of Thoughts: Defying the Law of Penrose Triangle for Thought Generation (2024.findings-acl)

Copied to clipboard

Challenge: Recent advances in Large Language Models (LLMs) have greatly advanced problem solving in diverse domains such as mathematical reasoning and knowledge reasoning.
Approach: They propose a thought prompting approach called 'Everything of Thoughts' it leverages pretrained reinforcement learning and Monte Carlo Tree Search to incorporate external domain knowledge and planning capability into thoughts.
Outcome: The proposed approach outperforms existing approaches on game of 24, 8-Puzzle, and Pocket Cube.
ExeCoder: Empowering Large Language Models with Executability Representation for Code Translation (2025.emnlp-main)

Copied to clipboard

Challenge: Existing code translation models only learn the contextual semantics of code during pre-training, neglecting executability information closely related to the execution state of the code.
Approach: They propose an LLM specifically designed for code translation called ExeCoder . it uses executability representations such as functional semantics and syntax structures to enhance LLMs' capabilities.
Outcome: The proposed model outperforms existing open-source code translation models on two metrics.
Multi-Task Learning with Language Modeling for Question Generation (D19-1)

Copied to clipboard

Challenge: Existing work on answer-aware questions generates a sentence and answer span as input . previous work on QG was mainly tackled by rule-based approach and neural-based one .
Approach: They propose to incorporate an auxiliary task of language modeling to help question generation in a hierarchical multi-task learning structure.
Outcome: The proposed model improves on SQuAD and MARCO datasets and human evaluation proves it.

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