Papers by Wei Ai

14 papers
MergeME: Model Merging Techniques for Homogeneous and Heterogeneous MoEs (2025.naacl-long)

Copied to clipboard

Challenge: State-of-the-art methods for merging expert models with different architectures do not address parameter interference and require extensive fine-tuning to restore performance.
Approach: They propose a method for merging experts with different architectures into a unified Mixture-of-Experts model with a goal of enhancing performance in each domain while retaining effectiveness on general tasks.
Outcome: Experiments across multiple domains show that the proposed methods reduce fine-tuning costs and improve performance over state-of-the-art methods.
InquireMobile: Teaching VLM-based Mobile Agent to Request Human Assistance via Reinforcement Fine-Tuning (2026.acl-long)

Copied to clipboard

Challenge: Recent advances in Vision-Language Models (VLMs) have enabled mobile agents to perceive and interact with real-world mobile environments based on human instructions.
Approach: They propose a vision-language model that actively seeks human confirmation at critical decision points and a model inspired by reinforcement learning.
Outcome: The proposed model achieves an improvement of 46.8% in inquiry success rate and the best overall success rate among existing baselines on InquireBench.
Explore Spurious Correlations at the Concept Level in Language Models for Text Classification (2024.acl-long)

Copied to clipboard

Challenge: Language models have demonstrated remarkable performance in numerous NLP tasks, employing both fine-tuning and in-context learning (ICL) methods.
Approach: They propose a method to assess concept bias in models during fine-tuning and in-context learning using ChatGPT.
Outcome: The proposed method outperforms token removal approaches and is validated through extensive testing.
Large Language Models and Causal Inference in Collaboration: A Comprehensive Survey (2025.findings-naacl)

Copied to clipboard

Challenge: Large Language Models (LLMs) have shown great potential to enhance Natural Language Processing (NLP) models in areas such as predictive accuracy, fairness, robustness, and explainability.
Approach: They evaluate or improve generative Large Language Models from a causal perspective in areas such as reasoning capacity, fairness and safety issues, explainability, and handling multimodality.
Outcome: The proposed models can be used to perform causal relationship discovery and causal effect estimation tasks.
DISCO Balances the Scales: Adaptive Domain- and Difficulty-Aware Reinforcement Learning on Imbalanced Data (2025.findings-emnlp)

Copied to clipboard

Challenge: Large Language Models (LLMs) are increasingly aligned with human preferences through Reinforcement Learning from Human Feedback (RLHF).
Approach: a new study proposes a domain-informed self-consistency policy optimization extension to GRPO that addresses inter-group imbalance.
Outcome: a new extension of GRPO addresses inter-group imbalance with two key innovations . the proposed method outperforms existing GR PO variants by 5% on Qwen3 models .
VietMix: A Naturally-Occurring Parallel Corpus and Augmentation Framework for Vietnamese-English Code-Mixed Machine Translation (2026.eacl-long)

Copied to clipboard

Challenge: Existing approaches to machine translation (MT) systems degrade when faced with code-mixed text.
Approach: They propose a system that can augment Vietnamese-English code-mixed text with iterative fine-tuning and targeted filtering.
Outcome: The proposed framework outperforms strong back-translation baselines and improves zero-shot models by up to +11.9 points.
Skill Discovery for Software Scripting Automation via Offline Simulations with LLMs (2026.findings-eacl)

Copied to clipboard

Challenge: Large Language Models (LLMs) can generate code from natural language queries, but runtime code generation is limited due to unverified code, security risks, longer response times, and higher computational costs.
Approach: They propose an offline simulation framework to curate a software-specific skillset by exploiting large language models and publicly available scripting guides.
Outcome: The proposed framework significantly improves automation success rates, reduces response time, and saves runtime token costs compared to traditional runtime code generation.
LegalAgentBench: Evaluating LLM Agents in Legal Domain (2025.acl-long)

Copied to clipboard

Challenge: Existing general-domain benchmarks do not capture complexity of real-world judicial cognition and decision-making.
Approach: They propose a benchmark specifically designed to evaluate LLM Agents in the legal domain.
Outcome: The proposed benchmark includes 17 corpora from real-world legal scenarios and provides 37 tools for interacting with external knowledge.
Dynamic Graph Neural ODE Network for Multi-modal Emotion Recognition in Conversation (2025.coling-main)

Copied to clipboard

Challenge: Existing graph-based multimodal emotion recognition methods fail to capture dynamic changes in emotions.
Approach: They propose a Dynamic Graph Neural Ordinary Differential Equation Network (DGODE) which combines dynamic changes of emotions to capture temporal dependencies of speakers’ emotions.
Outcome: The proposed model can capture the temporal dependencies caused by dynamic changes in emotions and can improve on two publicly available multimodal emotion recognition datasets.
Multi-Stage Balanced Distillation: Addressing Long-Tail Challenges in Sequence-Level Knowledge Distillation (2024.findings-emnlp)

Copied to clipboard

Challenge: Knowledge distillation (KD) is a promising solution for large language models, but their deployment remains computationally expensive.
Approach: They propose a framework which iteratively balances training data within a fixed computational budget and enables the transfer of knowledge from expensive teacher LLMs to smaller student models.
Outcome: The proposed framework achieves state-of-the-art performance across diverse long-tailed datasets, enhancing both the efficiency and efficacy of the distilled models.
TeCES: Collaborative Geometric Knowledge Representation Framework under Evolving Fact Snapshots (2026.acl-long)

Copied to clipboard

Challenge: Existing knowledge graphs represent static facts but lack collaborative modeling of both . e.g., existing knowledge graph models lack a framework for integrating snapshots into knowledge graph.
Approach: They propose a framework for high-fidelity modeling of evolving snapshots using concept of snapshots.
Outcome: The proposed framework outperforms existing models on six benchmarks.
Teaching-Assistant-in-the-Loop: Improving Knowledge Distillation from Imperfect Teacher Models in Low-Budget Scenarios (2024.findings-acl)

Copied to clipboard

Challenge: Large language models (LLMs) have demonstrated state-of-the-art (SOTA) performance across a wide spectrum of tasks.
Approach: They propose a framework that leverages three signal types to improve efficiency within resource-constrained, imperfect teacher scenarios.
Outcome: The proposed framework improves on four complex reasoning tasks by 20.79% compared to fine-tuning without any signals across datasets.
The Promises and Pitfalls of Using Language Models to Measure Instruction Quality in Education (2024.naacl-long)

Copied to clipboard

Challenge: Existing methods to assess instruction quality require trained raters to observe classrooms based on established criteria.
Approach: They propose to use Natural Language Processing techniques to assess multiple high-inference instructional practices in in-person K-12 classrooms and simulated performance tasks for pre-service teachers.
Outcome: The proposed method is able to assess multiple high-inference instructional practices in two educational settings: in-person K-12 classrooms and simulated performance tasks for pre-service teachers.
Mobile-R1: Towards Interactive Capability for VLM-Based Mobile Agent via Systematic Training (2026.acl-long)

Copied to clipboard

Challenge: Existing approaches to training agents for visual-language models trap them in local optima, hindering exploration and error correction with the environment.
Approach: They propose a hierarchical training recipe that bridges atomic action execution and strategic task completion.
Outcome: The proposed training recipe bridges atomic action execution and strategic task completion.

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