Weiran Lin

3 papers · 2022–2025 · 2 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (11) 🐣 Hot Topic Early Bird 👥 Mega-Team · Squad

Venues

ICML (2) EMNLP (1)

Top co-authors

Lujo Bauer (2) David Campbell (1) Brad Jokubaitis (1) Bhrugu Bharathi (1) Michael K. Reiter (1) Adam Alfred Hunt (1) Ponnurangam Kumaraguru (1) Dan Hendrycks (1) Uday Tupakula (1) Alice Gatti (1)

Research topics

Artificial Intelligence (3) Machine Learning (3) Core AI (3) Deep Learning (2) Natural Language Processing (2) Learning Types · Machine Learning (2) Applications (1) Core Methods (1) Generation (1) Learning Types · Deep Learning (1) Models (1) Optimization & Theory (1)

Keywords

large language model (2) constrained optimization (1) probability estimation (1) gradient descent (1) adversarial attack (1) ensemble method (1) language model (1) evasion attack (1) adversarial example (1) response consistency (1) hallucination detection (1) human evaluation (1) white-box attack (1) logit analysis (1) neural network (1) consistency measurement (1) unlearning (1) hazardous knowledge (1) biosecurity (1) proxy measurement (1)

Papers

Estimating LLM Consistency: A User Baseline vs Surrogate Metrics EMNLP 2025 The WMDP Benchmark: Measuring and Reducing Malicious Use with Unlearning ICML 2024 Constrained Gradient Descent: A Powerful and Principled Evasion Attack Against Neural Networks ICML 2022