Ximing Lu

47 papers · 2021–2025 · 10 conferences · across top CS/AI conferences

Achievements

🌍 Conference Polyglot (10) 🌈 Renaissance Researcher (7) 🐝 Cross-Pollinator (4) 🌉 Interdisciplinary Bridge 🧭 Keyword Pioneer 🗺️ Taxonomy Completionist (85) 🐣 Hot Topic Early Bird 🤝 Dynamic Duo (46) 👑 Triple Crown 🏆 Grand Slam 🔬 Deep Specialist (11) 🏆 Keyword Champion (2) 📈 Trend Setter 💎 Century Club (47) ⚡ Prolific Year (10) 🔥 Unstoppable (5) 🗃️ Keyword Collector (167)

Conferences

EMNLP (11) ICLR (8) NAACL (7) ACL (6) NIPS (6) CVPR (3) IJCNLP (3) AAAI (1) ICCV (1) ICML (1)

Top co-authors

Yejin Choi (46) Peter West (17) Liwei Jiang (17) Chandra Bhagavatula (16) Jack Hessel (12) Sean Welleck (10) Ronan Le Bras (9) Nouha Dziri (9) Youngjae Yu (9) Jena D. Hwang (9)

Keywords

language model (13) large language model (8) text generation (7) reinforcement learning (6) knowledge distillation (6) commonsense reasoning (6) unsupervised learning (4) multimodal learning (4) vision-language model (4) self-supervised learning (3) knowledge graph (3) zero-shot learning (3) paraphrase generation (3) product of expert (3) constrained decoding (2) beam search (2) style transfer (2) video understanding (2) visual reasoning (2) model compression (2)

Papers

Bias in Gender Bias Benchmarks: How Spurious Features Distort Evaluation ICCV 2025

AI as Humanity’s Salieri: Quantifying Linguistic Creativity of Language Models via Systematic Attribution of Machine Text against Web Text ICLR 2025

Synthetic Visual Genome CVPR 2025

CertainlyUncertain: A Benchmark and Metric for Multimodal Epistemic and Aleatoric Awareness ICLR 2025

Information-Guided Identification of Training Data Imprint in (Proprietary) Large Language Models NAACL 2025

Socratic-MCTS: Test-Time Visual Reasoning by Asking the Right Questions EMNLP 2025

Leftover Lunch: Advantage-based Offline Reinforcement Learning for Language Models ICLR 2024

Impossible Distillation for Paraphrasing and Summarization: How to Make High-quality Lemonade out of Small, Low-quality Model NAACL 2024

The Generative AI Paradox: “What It Can Create, It May Not Understand” ICLR 2024

WildTeaming at Scale: From In-the-Wild Jailbreaks to (Adversarially) Safer Language Models NIPS 2024

The Unlocking Spell on Base LLMs: Rethinking Alignment via In-Context Learning ICLR 2024

Tailoring Self-Rationalizers with Multi-Reward Distillation ICLR 2024

Value Kaleidoscope: Engaging AI with Pluralistic Human Values, Rights, and Duties AAAI 2024

Phenomenal Yet Puzzling: Testing Inductive Reasoning Capabilities of Language Models with Hypothesis Refinement ICLR 2024

JAMDEC: Unsupervised Authorship Obfuscation using Constrained Decoding over Small Language Models NAACL 2024

Position: A Roadmap to Pluralistic Alignment ICML 2024

In Search of the Long-Tail: Systematic Generation of Long-Tail Inferential Knowledge via Logical Rule Guided Search EMNLP 2024

StyleRemix: Interpretable Authorship Obfuscation via Distillation and Perturbation of Style Elements EMNLP 2024

How to Train Your Fact Verifier: Knowledge Transfer with Multimodal Open Models EMNLP 2024

Generating Sequences by Learning to Self-Correct ICLR 2023

Localized Symbolic Knowledge Distillation for Visual Commonsense Models NIPS 2023

Faith and Fate: Limits of Transformers on Compositionality NIPS 2023

I2D2: Inductive Knowledge Distillation with NeuroLogic and Self-Imitation ACL 2023

ClarifyDelphi: Reinforced Clarification Questions with Defeasibility Rewards for Social and Moral Situations ACL 2023

Fusing Pre-Trained Language Models With Multimodal Prompts Through Reinforcement Learning CVPR 2023

Inference-Time Policy Adapters (IPA): Tailoring Extreme-Scale LMs without Fine-tuning EMNLP 2023

SODA: Million-scale Dialogue Distillation with Social Commonsense Contextualization EMNLP 2023

NovaCOMET: Open Commonsense Foundation Models with Symbolic Knowledge Distillation EMNLP 2023

STEER: Unified Style Transfer with Expert Reinforcement EMNLP 2023

Generated Knowledge Prompting for Commonsense Reasoning ACL 2022

Rainier: Reinforced Knowledge Introspector for Commonsense Question Answering EMNLP 2022

NeuroLogic A*esque Decoding: Constrained Text Generation with Lookahead Heuristics NAACL 2022

Connecting the Dots between Audio and Text without Parallel Data through Visual Knowledge Transfer NAACL 2022

Symbolic Knowledge Distillation: from General Language Models to Commonsense Models NAACL 2022

Twist Decoding: Diverse Generators Guide Each Other EMNLP 2022

QUARK: Controllable Text Generation with Reinforced Unlearning NIPS 2022

NaturalProver: Grounded Mathematical Proof Generation with Language Models NIPS 2022

ProsocialDialog: A Prosocial Backbone for Conversational Agents EMNLP 2022

MERLOT Reserve: Neural Script Knowledge Through Vision and Language and Sound CVPR 2022

DExperts: Decoding-Time Controlled Text Generation with Experts and Anti-Experts IJCNLP 2021

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

DExperts: Decoding-Time Controlled Text Generation with Experts and Anti-Experts ACL 2021

Reflective Decoding: Beyond Unidirectional Generation with Off-the-Shelf Language Models IJCNLP 2021

MERLOT: Multimodal Neural Script Knowledge Models NIPS 2021

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

NeuroLogic Decoding: (Un)supervised Neural Text Generation with Predicate Logic Constraints NAACL 2021

Reflective Decoding: Beyond Unidirectional Generation with Off-the-Shelf Language Models ACL 2021