Papers by Xiao-Ming Wu

23 papers
MSEarth: A Multimodal Benchmark for Earth Science Phenomenon Discovery with MLLMs (2026.acl-long)

Copied to clipboard

Challenge: Existing datasets often rely on synthetic data or figure-caption pairs, failing to capture the depth and complexity of geoscientific reasoning.
Approach: They propose a multimodal scientific dataset and benchmark curated from open-access publications.
Outcome: MSEarth features over 289K figures with captions enriched by contextual discussions and reasoning from original papers.
LANID: LLM-assisted New Intent Discovery (2024.lrec-main)

Copied to clipboard

Challenge: Data annotation is expensive in Task-Oriented Dialogue systems.
Approach: They propose a framework that leverages Large Language Models' zero-shot capability to enhance the performance of a smaller text encoder on the NID task.
Outcome: The proposed framework surpasses all strong baselines in both unsupervised and semi-supervised settings.
FOREVER: Forgetting Curve-Inspired Memory Replay for Language Model Continual Learning (2026.acl-long)

Copied to clipboard

Challenge: Continual learning (CL) for large language models (LLMs) aims to enable sequential knowledge acquisition without catastrophic forgetting.
Approach: They propose a framework that aligns replay schedules with a model-centric notion of time.
Outcome: Experiments on three benchmarks show that FOREVER consistently mitigates catastrophic forgetting.
A Closer Look at Few-Shot Out-of-Distribution Intent Detection (2022.coling-1)

Copied to clipboard

Challenge: Existing methods for few-shot out-of-distribution (OOD) intent detection are not adequate . despite its importance, few- shot OOD intent detection is a challenging problem .
Approach: They propose a latent representation generation and self-supervision approach to solve few-shot OOD intent detection problem.
Outcome: The proposed approach is highly effective and could improve state-of-the-art methods for few-shot OOD intent detection.
Out-of-Scope Intent Detection with Self-Supervision and Discriminative Training (2021.acl-long)

Copied to clipboard

Challenge: Existing methods for out-of-scope intent detection rely on strong assumptions on data distribution and confidence threshold selection.
Approach: They propose a method to train an out-of-scope intent classifier in a fully end-to-end manner by simulating the test scenario in training.
Outcome: The proposed method improves on four benchmark dialogue datasets and improves over state-of-the-art methods.
Continual Dialogue State Tracking via Reason-of-Select Distillation (2024.findings-acl)

Copied to clipboard

Challenge: Existing research on dialogue systems has focused on domain-specific offline systems lacking adaptation abilities.
Approach: They propose a Reason-of-Select distillation method that enhances smaller models with a novel "meta-reasoning" capability.
Outcome: Experiments show that the proposed method significantly improves the performance and generalization capabilities of existing models.
Unknown Intent Detection Using Gaussian Mixture Model with an Application to Zero-shot Intent Classification (2020.acl-main)

Copied to clipboard

Challenge: Existing methods for unknown intent detection are limited by prior knowledge of class labels.
Approach: They propose to use a Gaussian mixture model to model utterance embeddings with a distribution and inject dynamic class semantic information into Gausssian means.
Outcome: The proposed model performs well on three real task-oriented dialogue datasets in two languages.
Recurrent Knowledge Identification and Fusion for Language Model Continual Learning (2025.acl-long)

Copied to clipboard

Challenge: Continual learning (CL) is crucial for large language models without costly retraining.
Approach: They propose a framework for recurrent knowledge identification and fusion that enables dynamic estimation of parameter importance distributions to enhance knowledge transfer.
Outcome: The proposed framework mitigates catastrophic forgetting and enhances knowledge transfer.
UniFashion: A Unified Vision-Language Model for Multimodal Fashion Retrieval and Generation (2024.emnlp-main)

Copied to clipboard

Challenge: e-commerce tasks such as multimodal retrieval and multimodal generation are largely ignored due to the diversity of the multimodal fashion domain.
Approach: They propose a framework that integrates image generation with retrieval and text generation tasks.
Outcome: The proposed framework outperforms state-of-the-art models across fashion tasks.
VI-OOD: A Unified Framework of Representation Learning for Textual Out-of-distribution Detection (2024.lrec-main)

Copied to clipboard

Challenge: Out-of-distribution (OOD) detection is a crucial part of deep neural networks.
Approach: They propose a variational inference framework which maximizes the likelihood of the joint distribution p(x, y) instead of p[y|x).
Outcome: The proposed framework maximizes the likelihood of the joint distribution p(x, y) instead of p[y|x).
New Intent Discovery with Pre-training and Contrastive Learning (2022.acl-long)

Copied to clipboard

Challenge: Existing methods for identifying intents from unlabeled utterances are label-intensive, inefficient, and inaccurate.
Approach: They propose a multi-task strategy to leverage unlabeled data and external labeled data for representation learning.
Outcome: The proposed method outperforms state-of-the-art methods on three intent recognition benchmarks.
Fine-tuning Pre-trained Language Models for Few-shot Intent Detection: Supervised Pre-training and Isotropization (2022.naacl-main)

Copied to clipboard

Challenge: Recent studies show that fine-tuning pre-trained language models with a small set of labeled utterances in a supervised manner is helpful, but it yields an anisotropic feature space, which may suppress the expressive power of the semantic representations.
Approach: They propose to regularize supervised pre-training towards isotropy by contrastive learning and correlation matrix regularizers.
Outcome: The proposed methods improve supervised pre-training by regularizing the feature space towards isotropy.
Towards LLM-driven Dialogue State Tracking (2023.emnlp-main)

Copied to clipboard

Challenge: emergence of large language models (LLMs) such as GPT3 and ChatGPT has sparked considerable interest in assessing their efficacy across diverse applications.
Approach: They present a framework for a domain-slot instruction tuning method that allows LDST to achieve performance on par with ChatGPT.
Outcome: The proposed framework performs better in zero-shot and few-shot settings than previous SOTA methods.
Revisit Few-shot Intent Classification with PLMs: Direct Fine-tuning vs. Continual Pre-training (2023.findings-acl)

Copied to clipboard

Challenge: Recent progress in intent detection relies on deep models and datasets with well-crafted annotations.
Approach: They propose a continual pre-training approach to train deep learning models . they propose augmentation method and sequential self-distillation to boost performance .
Outcome: The proposed method outperforms methods that employ continual pre-training on labeled datasets on few-shot intent detection tasks.
EasyGen: Easing Multimodal Generation with BiDiffuser and LLMs (2024.acl-long)

Copied to clipboard

Challenge: Existing multimodal models that depend on encoders like CLIP or ImageBind need ample amounts of training data to bridge modalities.
Approach: They propose an efficient model that leverages bidirectional conditional diffusion model to foster more efficient modality interactions.
Outcome: The proposed model is able to train a projection layer linking an LLM and an adapter to align the LLM’s text space with the bidirectional diffusion model.
TaSL: Continual Dialog State Tracking via Task Skill Localization and Consolidation (2024.acl-long)

Copied to clipboard

Challenge: Current methods for Continual Dialogue State Tracking (DST) struggle with catastrophic forgetting and knowledge transfer between tasks.
Approach: They propose a framework for task skill localization and consolidation that enables effective knowledge transfer without relying on memory replay.
Outcome: The proposed framework shows a 7.6% increase in Avg. JGA and 11% rise in BWT metrics over existing state-of-the-art methods.
Boosting Deep CTR Prediction with a Plug-and-Play Pre-trainer for News Recommendation (2022.coling-1)

Copied to clipboard

Challenge: Personalized news recommendation is a ubiquitous channel in various online applications, such as Google News and MSN News.
Approach: They propose a plug-and-play pre-trainer to learn both user and news encoders through multi-task pre-training.
Outcome: The proposed model improves on existing models and improves inference and updating time.
Reconstructing Capsule Networks for Zero-shot Intent Classification (D19-1)

Copied to clipboard

Challenge: Existing methods for intent classification are limited due to fast-emerging intents . a recent study shows that existing methods are not effective in recognizing unseen intents.
Approach: They propose to reconstruct capsule networks for zero-shot intent classification by using latent information from labeled utterances.
Outcome: The proposed method outperforms existing methods on two task-oriented dialogue datasets in different languages.
GeoEdit: Geometric Knowledge Editing for Large Language Models (2025.emnlp-main)

Copied to clipboard

Challenge: Existing training-based model editing methods struggle to incorporate new knowledge while preserving unrelated general knowledge.
Approach: They propose a framework that uses geometric relationships to differentiate between neurons associated with new knowledge updates and those related to general knowledge perturbations.
Outcome: The proposed framework avoids updating neurons with directions approximately orthogonal to existing knowledge, thus preserving the model’s generalization ability.
How Good Are LLMs at Out-of-Distribution Detection? (2024.lrec-main)

Copied to clipboard

Challenge: Out-of-distribution (OOD) detection is crucial for ensuring AI safety . large language models (LLMs) are becoming more prevalent due to their scale, pre-training objectives, and paradigms used for inference.
Approach: They propose to use large language models to investigate out-of-distribution (OOD) detection in machine learning.
Outcome: The proposed method outperforms other OOD detectors in zero-grad and fine-tuning scenarios.
AIMMerging: Adaptive Iterative Model Merging Using Training Trajectories for Language Model Continual Learning (2025.emnlp-main)

Copied to clipboard

Challenge: Recent model merging-based methods struggle to effectively manage the trade-off between learning new knowledge and preventing catastrophic forgetting.
Approach: They propose a model merging framework that utilizes learning and forgetting signals from the training trajectory to dynamically monitor the model’s training status.
Outcome: The proposed framework achieves significant performance improvements over existing state-of-the-art methods on three CL benchmarks with various model sizes (from 770M to 13B).
Zero-shot Cross-domain Dialogue State Tracking via Context-aware Auto-prompting and Instruction-following Contrastive Decoding (2024.emnlp-main)

Copied to clipboard

Challenge: Previous studies have implemented slot-based input improvements, such as schema-driven descriptions and question-answering formats, but still suffer from negative transfer for seen slots and inefficient transfer for unseen slots due to the significant source-target domain gap.
Approach: They propose a framework that generates dynamic, context-aware slot queries to improve model transferability by penalizing deviations from the provided instructions.
Outcome: Experiments on two datasets show that the proposed model performs better than existing models on the restaurant domain.
Effectiveness of Pre-training for Few-shot Intent Classification (2021.findings-emnlp)

Copied to clipboard

Challenge: Existing paradigms further pre-train language models such as BERT on vast amount of unlabeled corpus, but we find it highly effective and efficient to simply fine-tune BERT with roughly 1,000 labeled utterances from public datasets.
Approach: They propose to fine-tune BERT with a small set of labeled utterances from public datasets to achieve a pre-trained model based on a set of 1,000 labeles.
Outcome: The proposed model can outperform existing models on domains with very different semantics on novel 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