Difan Jiao

3 papers · 2024–2026 · 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) NeurIPS (1)

Top co-authors

Zhenwei Tang (3) Ashton Anderson (3) Yilun Liu (2) Daniel Matter (1) Jon Kleinberg (1) Siddhartha Sen (1) Jürgen Pfeffer (1) Linfeng Du (1) Ye Yuan (1) Reid McIlroy-Young (1)

Research topics

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

Keywords

model compression (1) text classification (1) attention mechanism (1) neural network optimization (1) game ai (1) linear probing (1) harmful content detection (1) human-ai interaction (1) internal representation (1) guard model (1) large language model (1) neural network (1) internal neuron (1) skill-aware modeling (1)

Papers

LLM Safety From Within: Detecting Harmful Content with Internal Representations ACL 2026 Maia-2: A Unified Model for Human-AI Alignment in Chess NeurIPS 2024 SPIN: Sparsifying and Integrating Internal Neurons in Large Language Models for Text Classification ACL 2024