Papers by Zhiming Wang

13 papers
UniTRec: A Unified Text-to-Text Transformer and Joint Contrastive Learning Framework for Text-based Recommendation (2023.acl-short)

Copied to clipboard

Challenge: Existing text-based recommendation frameworks that use pretrained language models (PLMs) can improve performance on text-related tasks.
Approach: They propose a unified local- and global-attention Transformer encoder to better model two-level contexts of user history.
Outcome: The proposed framework improves on three text-based recommendation tasks.
An Efficient Framework for Whole-Page Reranking via Single-Modal Supervision (2026.acl-industry)

Copied to clipboard

Challenge: Existing whole-page reranking methods require large-scale expert annotations to achieve high-quality results.
Approach: They propose a whole-page reranking framework that converts single-modal rankers into page-level guidance by constructing budget-aware candidates for cross-modal annotations and distilling intra-modality preferences to align relevance scales across modalities.
Outcome: The proposed framework reduces annotation costs by 70-90% while outperforming fully-annotated reranking baselines.
Dynamic Online Conversation Recommendation (2020.acl-main)

Copied to clipboard

Challenge: Existing models that assume static user interests are unable to capture the temporal aspects of user interactions and interest changes over time.
Approach: They propose a neural architecture to exploit changes of user interactions and interests over time to predict which discussions they are likely to enter.
Outcome: The proposed model outperforms state-of-the-art models that assume static user interests and handle future conversations that are unseen during training time.
MindRef: Mimicking Human Memory for Hierarchical Reference Retrieval with Fine-Grained Location Awareness (2025.acl-short)

Copied to clipboard

Challenge: Existing methods require pre-segmented article chunks, limiting reference flexibility like human memory.
Approach: They propose a framework that leverages parameterized knowledge stored during the pre-training phase of large language models to recall reference passages from any starting position independently.
Outcome: The proposed framework can recall reference passages from any starting position independently.
DIGAT: Modeling News Recommendation with Dual-Graph Interaction (2022.findings-emnlp)

Copied to clipboard

Challenge: Existing news recommendation methods lack effective news-user feature interaction.
Approach: They propose to use news-graph and user-graph channels to enhance news encodings . they also propose to perform effective feature interaction between news and user graphs based on semantic-augmented graphs.
Outcome: The proposed graph attention networks outperform existing NR methods on the benchmark dataset MIND.
Detecting Stealthy Backdoor Samples based on Intra-class Distance for Large Language Models (2025.findings-emnlp)

Copied to clipboard

Challenge: Existing detectors use classifier-style probability signals or rely on rewriting, which can degrade quality and introduce new triggers.
Approach: They propose to efficiently remove poisoned examples before or during fine-tuning .
Outcome: The proposed method outperforms prior detectors on two machine translation datasets and one QA dataset.
LearnAct: Few-Shot Mobile GUI Agent with a Unified Demonstration Benchmark (2026.findings-acl)

Copied to clipboard

Challenge: Mobile GUI agents show promise in automating tasks but face significant generalization challenges in long-tail scenarios.
Approach: They propose a benchmark framework for mobile GUI agents that measures the performance of GUI agents by analyzing their performance.
Outcome: The LearnGUI benchmark outperforms existing methods in offline and online evaluations and demonstrates consistent gains across model architectures.
Beyond the Surface: A Solution-Aware Retrieval Model for Competition-level Code Generation (2025.findings-emnlp)

Copied to clipboard

Challenge: Existing retrieval models emphasize surface-level semantic similarity, neglecting deeper solution-level logical similarities.
Approach: They propose a solution-aware ranking model empowered by synthetic data for competitive programming tasks.
Outcome: The proposed ranking model outperforms existing retrieval models in precision and recall metrics.
Vulnerability of Text-to-Image Models to Prompt Template Stealing: A Differential Evolution Approach (2025.findings-acl)

Copied to clipboard

Challenge: Prompt trading has emerged as a significant intellectual property concern in recent years, where vendors entice users by showcasing sample images before selling prompt templates that can generate similar images.
Approach: They propose a prompt-stealing benchmark consisting of 50 templates and 450 images organized into Easy and Hard difficulty levels.
Outcome: The proposed method outperforms baseline methods with an average improvement of over 10%.
Language Models as Continuous Self-Evolving Data Engineers (2025.emnlp-main)

Copied to clipboard

Challenge: Large Language Models (LLMs) have demonstrated remarkable capabilities, yet their further evolution is often hampered by the scarcity of high-quality training data and the heavy reliance of traditional methods on expert-labeled data.
Approach: They propose a paradigm that enables LLMs to train themselves by generating, cleaning, reviewing and annotating data with preference information.
Outcome: The proposed model can generate, clean, review, and annotate data with preference information significantly reducing time and cost of post-training data construction.
SAFE-QAQ: End-to-End Slow-Thinking Audio-Text Fraud Detection via Reinforcement Learning (2026.acl-long)

Copied to clipboard

Challenge: Existing methods for fraud detection rely on transcribed text, lacking acoustic cues . a proposed framework for audio-based slow-thinking fraud detection eliminates transcription errors .
Approach: They propose a framework for audio-based slow-thinking fraud detection that eliminates transcription errors and rewards slow-thought reasoning by capturing fine-grained audio details.
Outcome: The proposed method improves accuracy, inference efficiency, and real-time processing capabilities.
SpeechFake: A Large-Scale Multilingual Speech Deepfake Dataset Incorporating Cutting-Edge Generation Methods (2025.acl-long)

Copied to clipboard

Challenge: Existing speech deepfake datasets are limited in scale and diversity, making it challenging to train models that can generalize well to unseen deepfakkes.
Approach: They propose a large-scale speech deepfake dataset that includes over 3 million deepfak samples, totaling more than 3,000 hours of audio, generated using 40 different speech synthesis tools.
Outcome: The proposed dataset includes over 3 million deepfake samples, totaling more than 3,000 hours of audio, generated using 40 different speech synthesis tools.
Turning Trash into Treasure: Accelerating Inference of Large Language Models with Token Recycling (2025.acl-long)

Copied to clipboard

Challenge: Large Language Models (LLMs) generate only one token at each decoding step, leading to high latency.
Approach: They propose a speculative decoding paradigm that stores tokens in an adjacency matrix and employs a breadth-first-search algorithm to construct a draft tree.
Outcome: The proposed method outperforms existing train-free methods by 30% and even a training method by 25%.

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