Yue Dong

46 papers · 2017–2026 · 13 conferences · across top CS/AI conferences

Achievements

🏃 Academic Marathon (8) 🐣 Hot Topic Early Bird 🗺️ Taxonomy Completionist (84) 🌈 Renaissance Researcher (10) 🌉 Interdisciplinary Bridge 🧭 Keyword Pioneer 🐝 Cross-Pollinator (7) 🌍 Conference Polyglot (13) 🤝 Dynamic Duo (12) 🧬 Topic Evolution 🏆 Keyword Champion (2) 🚀 Conference Pioneer 📈 Trend Setter 🗃️ Keyword Collector (183) ⚡ Prolific Year (5) ❓ The Questioner (2) 🔥 Unstoppable (9) 💎 Century Club (45)

Conferences

EMNLP (15) ACL (10) CVPR (4) AAAI (3) ICLR (3) IJCNLP (3) NAACL (2) EACL (1) ECCV (1) ICCV (1) ICML (1) INTERSPEECH (1) NSDI (1)

Top co-authors

Jackie Chi Kit CHEUNG (12) Yu Fu (7) Meng Cao (4) Yan Xu (3) Jiachen Li (3) Erfan Shayegani (3) Trishna Chakraborty (3) Nael Abu-Ghazaleh (3) Wen Xiao (3) Shengyu Zhao (3)

Research topics

Learning Paradigms (1) Learning Paradigms (1)

Keywords

large language model (7) abstractive summarization (6) adversarial attack (6) extractive summarization (4) text classification (4) safety alignment (4) text generation (4) transfer learning (3) factual consistency (3) rouge score (3) scientific document (3) text summarization (3) reinforcement learning (3) attack success rate (2) news summarization (2) long document (2) auxiliary loss (2) language model (2) question answering (2) multi-task learning (2)

Papers

Harnessing the Unseen: The Hidden Influence of Intrinsic Knowledge in Long-Context Language Models AAAI 2026

HEAL: An Empirical Study on Hallucinations in Embodied Agents Driven by Large Language Models EMNLP 2025

ExpertGenQA: Open-ended QA generation in Specialized Domains EMNLP 2025

Attention Eclipse: Manipulating Attention to Bypass LLM Safety-Alignment EMNLP 2025

Layer-wise Alignment: Examining Safety Alignment Across Image Encoder Layers in Vision Language Models ICML 2025

Not All Heads Matter: A Head-Level KV Cache Compression Method with Integrated Retrieval and Reasoning ICLR 2025

Biasly: An Expert-Annotated Dataset for Subtle Misogyny Detection and Mitigation ACL 2024

Asymmetric Bias in Text-to-Image Generation with Adversarial Attacks ACL 2024

EcoRank: Budget-Constrained Text Re-ranking Using Large Language Models ACL 2024

PAT-Questions: A Self-Updating Benchmark for Present-Anchored Temporal Question-Answering ACL 2024

Jailbreak in pieces: Compositional Adversarial Attacks on Multi-Modal Language Models ICLR 2024

Adversarial Attacks on Parts of Speech: An Empirical Study in Text-to-Image Generation EMNLP 2024

Can Textual Unlearning Solve Cross-Modality Safety Alignment? EMNLP 2024

Mechanistic Understanding and Mitigation of Language Model Non-Factual Hallucinations EMNLP 2024

Watermarking Conditional Text Generation for AI Detection: Unveiling Challenges and a Semantic-Aware Watermark Remedy AAAI 2024

QuickUpdate: a Real-Time Personalization System for Large-Scale Recommendation Models NSDI 2024

Cross-Task Defense: Instruction-Tuning LLMs for Content Safety NAACL 2024

Safety Alignment in NLP Tasks: Weakly Aligned Summarization as an In-Context Attack ACL 2024

Vulnerabilities of Large Language Models to Adversarial Attacks ACL 2024

Inverse Reinforcement Learning for Text Summarization EMNLP 2023

Hallucinated but Factual! Inspecting the Factuality of Hallucinations in Abstractive Summarization ACL 2022

Learning with Rejection for Abstractive Text Summarization EMNLP 2022

Faithful to the Document or to the World? Mitigating Hallucinations via Entity-Linked Knowledge in Abstractive Summarization EMNLP 2022

Text Generation with Text-Editing Models NAACL 2022

Discourse-Aware Unsupervised Summarization for Long Scientific Documents EACL 2021

On-the-Fly Attention Modulation for Neural Generation ACL 2021

On-the-Fly Attention Modulation for Neural Generation IJCNLP 2021

Large Scale Image Completion via Co-Modulated Generative Adversarial Networks ICLR 2021

Bringing Structure into Summaries: a Faceted Summarization Dataset for Long Scientific Documents IJCNLP 2021

Bringing Structure into Summaries: a Faceted Summarization Dataset for Long Scientific Documents ACL 2021

Multi-Fact Correction in Abstractive Text Summarization EMNLP 2020

Object-based Illumination Estimation with Rendering-aware Neural Networks ECCV 2020

MaskFlownet: Asymmetric Feature Matching With Learnable Occlusion Mask CVPR 2020

TextureFusion: High-Quality Texture Acquisition for Real-Time RGB-D Scanning CVPR 2020

Large-Scale End-to-End Multilingual Speech Recognition and Language Identification with Multi-Task Learning INTERSPEECH 2020

Factual Error Correction for Abstractive Summarization Models EMNLP 2020

Multi-XScience: A Large-scale Dataset for Extreme Multi-document Summarization of Scientific Articles EMNLP 2020

Learning Multi-Task Communication with Message Passing for Sequence Learning AAAI 2019

Countering the Effects of Lead Bias in News Summarization via Multi-Stage Training and Auxiliary Losses IJCNLP 2019

EditNTS: An Neural Programmer-Interpreter Model for Sentence Simplification through Explicit Editing ACL 2019

Recursive Cascaded Networks for Unsupervised Medical Image Registration ICCV 2019

Synthesizing 3D Shapes From Silhouette Image Collections Using Multi-Projection Generative Adversarial Networks CVPR 2019

Countering the Effects of Lead Bias in News Summarization via Multi-Stage Training and Auxiliary Losses EMNLP 2019

A Hierarchical Neural Attention-based Text Classifier EMNLP 2018

BanditSum: Extractive Summarization as a Contextual Bandit EMNLP 2018

Learning Non-Lambertian Object Intrinsics Across ShapeNet Categories CVPR 2017