Yiwei Wang

Orcid: 0000-0001-5921-2575

Affiliations:
  • University of California, Merced, CA, USA
  • University of California, Los Angeles, CA, USA (former)
  • National University of Singapore (former)
  • Hong Kong University of Science and Technology, Hong Kong (former)


According to our database1, Yiwei Wang authored at least 103 papers between 2017 and 2025.

Collaborative distances:

Timeline

Legend:

Book 
In proceedings 
Article 
PhD thesis 
Dataset
Other 

Links

Online presence:

On csauthors.net:

Bibliography

2025
Depth-Breadth Synergy in RLVR: Unlocking LLM Reasoning Gains with Adaptive Exploration.
CoRR, August, 2025

MRFD: Multi-Region Fusion Decoding with Self-Consistency for Mitigating Hallucinations in LVLMs.
CoRR, August, 2025

Cure or Poison? Embedding Instructions Visually Alters Hallucination in Vision-Language Models.
CoRR, August, 2025

A<sup>2</sup>R<sup>2</sup>: Advancing Img2LaTeX Conversion via Visual Reasoning with Attention-Guided Refinement.
CoRR, July, 2025

A Survey of Context Engineering for Large Language Models.
CoRR, July, 2025

Unveiling the Potential of Diffusion Large Language Model in Controllable Generation.
CoRR, July, 2025

RefineX: Learning to Refine Pre-training Data at Scale from Expert-Guided Programs.
CoRR, July, 2025

Symbolic or Numerical? Understanding Physics Problem Solving in Reasoning LLMs.
CoRR, July, 2025

DiMo-GUI: Advancing Test-time Scaling in GUI Grounding via Modality-Aware Visual Reasoning.
CoRR, July, 2025

Structured Attention Matters to Multimodal LLMs in Document Understanding.
CoRR, June, 2025

Answer-Centric or Reasoning-Driven? Uncovering the Latent Memory Anchor in LLMs.
CoRR, June, 2025

Understanding GUI Agent Localization Biases through Logit Sharpness.
CoRR, June, 2025

Who is in the Spotlight: The Hidden Bias Undermining Multimodal Retrieval-Augmented Generation.
CoRR, June, 2025

BRIGHT+: Upgrading the BRIGHT Benchmark with MARCUS, a Multi-Agent RAG Clean-Up Suite.
CoRR, June, 2025

TreeRPO: Tree Relative Policy Optimization.
CoRR, June, 2025

SemVink: Advancing VLMs' Semantic Understanding of Optical Illusions via Visual Global Thinking.
CoRR, June, 2025

STDR: Spatio-Temporal Decoupling for Real-Time Dynamic Scene Rendering.
CoRR, May, 2025

FastCar: Cache Attentive Replay for Fast Auto-Regressive Video Generation on the Edge.
CoRR, May, 2025

DraftAttention: Fast Video Diffusion via Low-Resolution Attention Guidance.
CoRR, May, 2025

Mapping the Minds of LLMs: A Graph-Based Analysis of Reasoning LLM.
CoRR, May, 2025

Token-Efficient Prompt Injection Attack: Provoking Cessation in LLM Reasoning via Adaptive Token Compression.
CoRR, April, 2025

a1: Steep Test-time Scaling Law via Environment Augmented Generation.
CoRR, April, 2025

Do "New Snow Tablets" Contain Snow? Large Language Models Over-Rely on Names to Identify Ingredients of Chinese Drugs.
CoRR, April, 2025

Text Speaks Louder than Vision: ASCII Art Reveals Textual Biases in Vision-Language Models.
CoRR, April, 2025

How does Watermarking Affect Visual Language Models in Document Understanding?
CoRR, April, 2025

Texture or Semantics? Vision-Language Models Get Lost in Font Recognition.
CoRR, March, 2025

Innate Reasoning is Not Enough: In-Context Learning Enhances Reasoning Large Language Models with Less Overthinking.
CoRR, March, 2025

Process or Result? Manipulated Ending Tokens Can Mislead Reasoning LLMs to Ignore the Correct Reasoning Steps.
CoRR, March, 2025

MIRAGE: Multimodal Immersive Reasoning and Guided Exploration for Red-Team Jailbreak Attacks.
CoRR, March, 2025

Parameters vs. Context: Fine-Grained Control of Knowledge Reliance in Language Models.
CoRR, March, 2025

Making Every Step Effective: Jailbreaking Large Vision-Language Models Through Hierarchical KV Equalization.
CoRR, March, 2025

Tit-for-Tat: Safeguarding Large Vision-Language Models Against Jailbreak Attacks via Adversarial Defense.
CoRR, March, 2025

Structured Outputs Enable General-Purpose LLMs to be Medical Experts.
CoRR, March, 2025

Fact or Guesswork? Evaluating Large Language Model's Medical Knowledge with Structured One-Hop Judgment.
CoRR, February, 2025

Enhancing LLM Character-Level Manipulation via Divide and Conquer.
CoRR, February, 2025

Lost in Edits? A λ-Compass for AIGC Provenance.
CoRR, February, 2025

Disentangling CLIP Features for Enhanced Localized Understanding.
CoRR, February, 2025

UniTST: Effectively Modeling Inter-Series and Intra-Series Dependencies for Multivariate Time Series Forecasting.
Trans. Mach. Learn. Res., 2025

Tricking Retrievers with Influential Tokens: An Efficient Black-Box Corpus Poisoning Attack.
Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies, 2025

Vulnerability of Large Language Models to Output Prefix Jailbreaks: Impact of Positions on Safety.
Proceedings of the Findings of the Association for Computational Linguistics: NAACL 2025, Albuquerque, New Mexico, USA, April 29, 2025

OptiBench Meets ReSocratic: Measure and Improve LLMs for Optimization Modeling.
Proceedings of the Thirteenth International Conference on Learning Representations, 2025

Is Factuality Enhancement a Free Lunch For LLMs? Better Factuality Can Lead to Worse Context-Faithfulness.
Proceedings of the Thirteenth International Conference on Learning Representations, 2025

Con-ReCall: Detecting Pre-training Data in LLMs via Contrastive Decoding.
Proceedings of the 31st International Conference on Computational Linguistics, 2025

"Not Aligned" is Not "Malicious": Being Careful about Hallucinations of Large Language Models' Jailbreak.
Proceedings of the 31st International Conference on Computational Linguistics, 2025

Vulnerability of LLMs to Vertically Aligned Text Manipulations.
Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2025

DRS: Deep Question Reformulation With Structured Output.
Proceedings of the Findings of the Association for Computational Linguistics, 2025

METAL: A Multi-Agent Framework for Chart Generation with Test-Time Scaling.
Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2025

Can Graph Descriptive Order Affect Solving Graph Problems with LLMs?
Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2025

Decoding by Contrasting Knowledge: Enhancing Large Language Model Confidence on Edited Facts.
Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2025

Context-DPO: Aligning Language Models for Context-Faithfulness.
Proceedings of the Findings of the Association for Computational Linguistics, 2025

2024
Are LLMs Really Not Knowledgable? Mining the Submerged Knowledge in LLMs' Memory.
CoRR, 2024

Think Carefully and Check Again! Meta-Generation Unlocking LLMs for Low-Resource Cross-Lingual Summarization.
CoRR, 2024

HiddenGuard: Fine-Grained Safe Generation with Specialized Representation Router.
CoRR, 2024

StruEdit: Structured Outputs Enable the Fast and Accurate Knowledge Editing for Large Language Models.
CoRR, 2024

Benchmarking LLMs for Optimization Modeling and Enhancing Reasoning via Reverse Socratic Synthesis.
CoRR, 2024

Decoding by Contrasting Knowledge: Enhancing LLMs' Confidence on Edited Facts.
CoRR, 2024

Is Factuality Decoding a Free Lunch for LLMs? Evaluation on Knowledge Editing Benchmark.
CoRR, 2024

Scalable Link Prediction on Large-Scale Heterogeneous Graphs with Large Language Models.
CoRR, 2024

SLANG: New Concept Comprehension of Large Language Models.
CoRR, 2024

DeepEdit: Knowledge Editing as Decoding with Constraints.
CoRR, 2024

Fast Graph Sharpness-Aware Minimization for Enhancing and Accelerating Few-Shot Node Classification.
Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, 2024

Scalable and Effective Implicit Graph Neural Networks on Large Graphs.
Proceedings of the Twelfth International Conference on Learning Representations, 2024

AlignedCoT: Prompting Large Language Models via Native-Speaking Demonstrations.
Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2024, 2024

LLM-A*: Large Language Model Enhanced Incremental Heuristic Search on Path Planning.
Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2024, 2024

SLANG: New Concept Comprehension of Large Language Models.
Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, 2024

Control Large Language Models via Divide and Conquer.
Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, 2024

Adaptive Token Biaser: Knowledge Editing via Biasing Key Entities.
Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2024, 2024

LPNL: Scalable Link Prediction with Large Language Models.
Proceedings of the Findings of the Association for Computational Linguistics, 2024

2023
Mixed-Order Relation-Aware Recurrent Neural Networks for Spatio-Temporal Forecasting.
IEEE Trans. Knowl. Data Eng., September, 2023

Speak Like a Native: Prompting Large Language Models in a Native Style.
CoRR, 2023

Graph Explicit Neural Networks: Explicitly Encoding Graphs for Efficient and Accurate Inference.
Proceedings of the Sixteenth ACM International Conference on Web Search and Data Mining, 2023

LargeST: A Benchmark Dataset for Large-Scale Traffic Forecasting.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

A Causal View of Entity Bias in (Large) Language Models.
Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2023, 2023

Primacy Effect of ChatGPT.
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, 2023

How Fragile is Relation Extraction under Entity Replacements?
Proceedings of the 27th Conference on Computational Natural Language Learning, 2023

AirFormer: Predicting Nationwide Air Quality in China with Transformers.
Proceedings of the Thirty-Seventh AAAI Conference on Artificial Intelligence, 2023

2022
LSCALE: Latent Space Clustering-Based Active Learning for Node Classification.
Proceedings of the Machine Learning and Knowledge Discovery in Databases, 2022

Should We Rely on Entity Mentions for Relation Extraction? Debiasing Relation Extraction with Counterfactual Analysis.
Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, 2022

GraphCache: Message Passing as Caching for Sentence-Level Relation Extraction.
Proceedings of the Findings of the Association for Computational Linguistics: NAACL 2022, 2022

Dangling-Aware Entity Alignment with Mixed High-Order Proximities.
Proceedings of the Findings of the Association for Computational Linguistics: NAACL 2022, 2022

Flashlight: Scalable Link Prediction With Effective Decoders.
Proceedings of the Learning on Graphs Conference, 2022

Time-Aware Neighbor Sampling on Temporal Graphs.
Proceedings of the International Joint Conference on Neural Networks, 2022

TrajFormer: Efficient Trajectory Classification with Transformers.
Proceedings of the 31st ACM International Conference on Information & Knowledge Management, 2022

2021
Time-Aware Neighbor Sampling for Temporal Graph Networks.
CoRR, 2021

Structure-Aware Label Smoothing for Graph Neural Networks.
CoRR, 2021

Mixup for Node and Graph Classification.
Proceedings of the WWW '21: The Web Conference 2021, 2021

CurGraph: Curriculum Learning for Graph Classification.
Proceedings of the WWW '21: The Web Conference 2021, 2021

Fine-Grained Urban Flow Prediction.
Proceedings of the WWW '21: The Web Conference 2021, 2021

GraphAnoGAN: Detecting Anomalous Snapshots from Attributed Graphs.
Proceedings of the Machine Learning and Knowledge Discovery in Databases. Research Track, 2021

Adaptive Data Augmentation on Temporal Graphs.
Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

EIGNN: Efficient Infinite-Depth Graph Neural Networks.
Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Modeling Trajectories with Neural Ordinary Differential Equations.
Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence, 2021

A Unified 3D Human Motion Synthesis Model via Conditional Variational Auto-Encoder<sup>∗</sup>.
Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision, 2021

2020
Active Learning for Node Classification: The Additional Learning Ability from Unlabelled Nodes.
CoRR, 2020

GraphCrop: Subgraph Cropping for Graph Classification.
CoRR, 2020

Progressive Supervision for Node Classification.
Proceedings of the Machine Learning and Knowledge Discovery in Databases, 2020

Revisiting Convolutional Neural Networks for Citywide Crowd Flow Analytics.
Proceedings of the Machine Learning and Knowledge Discovery in Databases, 2020

NodeAug: Semi-Supervised Node Classification with Data Augmentation.
Proceedings of the KDD '20: The 26th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, 2020

Detecting Implementation Bugs in Graph Convolutional Network based Node Classifiers.
Proceedings of the 31st IEEE International Symposium on Software Reliability Engineering, 2020

Provably Robust Node Classification via Low-Pass Message Passing.
Proceedings of the 20th IEEE International Conference on Data Mining, 2020

Learning Progressive Joint Propagation for Human Motion Prediction.
Proceedings of the Computer Vision - ECCV 2020, 2020

2019
Optimization Algorithms for Graph Laplacian Estimation via ADMM and MM.
IEEE Trans. Signal Process., 2019

2017
Using Knowledge Graphs to Explain Entity Co-occurrence in Twitter.
Proceedings of the 2017 ACM on Conference on Information and Knowledge Management, 2017


  Loading...