Ximing Lu

Affiliations

University of Washington

papers

1,826

total citations

papers (17)

ProRL: Prolonged Reinforcement Learning Expands Reasoning Boundaries in Large Language Models

NEURIPS 2025arXiv

104

citations

Value Kaleidoscope: Engaging AI with Pluralistic Human Values, Rights, and Duties

AAAI 2024arXiv

citations

NaturalProver: Grounded Mathematical Proof Generation with Language Models

NEURIPS 2022arXiv

citations

AI as Humanity’s Salieri: Quantifying Linguistic Creativity of Language Models via Systematic Attribution of Machine Text against Web Text

ICLR 2025arXiv

citations

Prismatic Synthesis: Gradient-based Data Diversification Boosts Generalization in LLM Reasoning

NEURIPS 2025arXiv

citations

Leftover Lunch: Advantage-based Offline Reinforcement Learning for Language Models

ICLR 2024arXiv

citations

Localized Symbolic Knowledge Distillation for Visual Commonsense Models

NEURIPS 2023arXiv

citations

Verifying the Verifiers: Unveiling Pitfalls and Potentials in Fact Verifiers

COLM 2025arXiv

citations

Bias in Gender Bias Benchmarks: How Spurious Features Distort Evaluation

ICCV 2025arXiv

citations

Synthetic Visual Genome

CVPR 2025arXiv

citations

The Surprising Effectiveness of Membership Inference with Simple N-Gram Coverage

COLM 2025arXiv

citations

Position: A Roadmap to Pluralistic Alignment

ICML 2024

citations

Fusing Pre-Trained Language Models With Multimodal Prompts Through Reinforcement Learning

CVPR 2023

citations

Ximing Lu

Affiliations

papers (17)

Faith and Fate: Limits of Transformers on Compositionality

MERLOT: Multimodal Neural Script Knowledge Models

QUARK: Controllable Text Generation with Reinforced Unlearning

MERLOT Reserve: Neural Script Knowledge Through Vision and Language and Sound

ProRL: Prolonged Reinforcement Learning Expands Reasoning Boundaries in Large Language Models

Value Kaleidoscope: Engaging AI with Pluralistic Human Values, Rights, and Duties

NaturalProver: Grounded Mathematical Proof Generation with Language Models

AI as Humanity’s Salieri: Quantifying Linguistic Creativity of Language Models via Systematic Attribution of Machine Text against Web Text

Prismatic Synthesis: Gradient-based Data Diversification Boosts Generalization in LLM Reasoning

Leftover Lunch: Advantage-based Offline Reinforcement Learning for Language Models

Localized Symbolic Knowledge Distillation for Visual Commonsense Models

Verifying the Verifiers: Unveiling Pitfalls and Potentials in Fact Verifiers

Bias in Gender Bias Benchmarks: How Spurious Features Distort Evaluation

Synthetic Visual Genome

The Surprising Effectiveness of Membership Inference with Simple N-Gram Coverage

Position: A Roadmap to Pluralistic Alignment

Fusing Pre-Trained Language Models With Multimodal Prompts Through Reinforcement Learning

papers (17)

Faith and Fate: Limits of Transformers on Compositionality

MERLOT: Multimodal Neural Script Knowledge Models

QUARK: Controllable Text Generation with Reinforced Unlearning

MERLOT Reserve: Neural Script Knowledge Through Vision and Language and Sound

ProRL: Prolonged Reinforcement Learning Expands Reasoning Boundaries in Large Language Models

Value Kaleidoscope: Engaging AI with Pluralistic Human Values, Rights, and Duties

NaturalProver: Grounded Mathematical Proof Generation with Language Models

AI as Humanity’s Salieri: Quantifying Linguistic Creativity of Language Models via Systematic Attribution of Machine Text against Web Text

Prismatic Synthesis: Gradient-based Data Diversification Boosts Generalization in LLM Reasoning

Leftover Lunch: Advantage-based Offline Reinforcement Learning for Language Models

Localized Symbolic Knowledge Distillation for Visual Commonsense Models

Verifying the Verifiers: Unveiling Pitfalls and Potentials in Fact Verifiers

Bias in Gender Bias Benchmarks: How Spurious Features Distort Evaluation

Synthetic Visual Genome

The Surprising Effectiveness of Membership Inference with Simple N-Gram Coverage

Position: A Roadmap to Pluralistic Alignment

Fusing Pre-Trained Language Models With Multimodal Prompts Through Reinforcement Learning