Junchi Yao

3 papers · 2025–2026 · 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 (12)

Venues

ACL (2) CVPR (1)

Top co-authors

Di Wang (3) Lijie Hu (3) Shu Yang (2) Mengdi Li (2) Keyu Wang (1) Hongji Li (1) Priyanka Singh (1) Derek F. Wong (1) Xue Li (1) Shenzhe Zhu (1)

Research topics

Artificial Intelligence (3) Deep Learning (3) Core AI (3) Learning Types · Deep Learning (3) Machine Learning (2) Natural Language Processing (1) Application Areas (1) Applications (1) Core Methods (1) Learning Types · Machine Learning (1)

Keywords

large language model (2) feature extraction (1) chain-of-thought reasoning (1) text generation (1) machine unlearning (1) fraud detection (1) multimodal large language model (1) mechanistic interpretability (1) sparse autoencoder (1) activation manipulation (1) unlearning benchmark (1) phishing detection (1) repeat curse (1) repetition feature (1) reasoning leakage (1) adversarial robustness (1) reasoning retention (1)

Papers

Towards Reasoning-Preserving Unlearning in Multimodal Large Language Models CVPR 2026 Fraud-R1 : A Multi-Round Benchmark for Assessing the Robustness of LLM Against Augmented Fraud and Phishing Inducements ACL 2025 Understanding the Repeat Curse in Large Language Models from a Feature Perspective ACL 2025