Fengyuan Liu

7 papers · 2023–2026 · 5 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 · Silver 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (14) ❓ The Questioner (2)

Venues

EMNLP (2) ICLR (2) ACL (1) ECCV (1) ICML (1)

Top co-authors

Jindong Gu (3) Philip Torr (3) Haochen Luo (2) Nikhil Kandpal (2) Colin Raffel (1) Li Jian (1) Zhiyuan Fan (1) Qi Liu (1) Rishab Balasubramanian (1) Yiming Li (1)

Research topics

Machine Learning (6) Artificial Intelligence (4) Core AI (4) Application Areas (3) Learning Types (3) Deep Learning (1) Mathematics & Optimization (1) Architectures (1) Optimization (1)

Keywords

large language model (2) adversarial attack (2) prompt learning (1) adversarial perturbation (1) language model (1) vision-language model (1) feature engineering (1) tabular data (1) evolutionary search (1) context attribution (1) genetic programming (1) automated machine learning (1) leave-one-out error (1) adversarial sample (1) multi-agent system (1) feature pruning (1) collective decision (1) alpha mining (1) automated feature generation (1) feature boosting (1)

Papers

Cognitive Alpha Mining via LLM-Driven Code-Based Evolution ACL 2026 AttriBoT: A Bag of Tricks for Efficiently Approximating Leave-One-Out Context Attribution ICLR 2025 Can an Individual Manipulate the Collective Decisions of Multi-Agents? EMNLP 2025 Efficient Model Development through Fine-tuning Transfer EMNLP 2025 An Image Is Worth 1000 Lies: Transferability of Adversarial Images across Prompts on Vision-Language Models ICLR 2024 Which Model Generated This Image? A Model-Agnostic Approach for Origin Attribution ECCV 2024 OpenFE: Automated Feature Generation with Expert-level Performance ICML 2023