Difan Jiao

difanjiao

·

difanj0713

AI & ML interests

Generative Models & Mech Interp

Recent Activity

upvoted a paper about 2 months ago

RankJudge: A Multi-Turn LLM-as-a-Judge Synthetic Benchmark Generator

updated a model 2 months ago

UofTCSSLab/SIREN-Llama-3.1-8B

updated a model 2 months ago

UofTCSSLab/SIREN-Llama-3.2-1B

View all activity

Organizations

submitted a paper to Daily Papers 3 months ago

LLM Safety From Within: Detecting Harmful Content with Internal Representations

Paper • 2604.18519 • Published Apr 20 • 26

authored a paper 3 months ago

LLM Safety From Within: Detecting Harmful Content with Internal Representations

Paper • 2604.18519 • Published Apr 20 • 26

submitted a paper to Daily Papers 3 months ago

ThinkTwice: Jointly Optimizing Large Language Models for Reasoning and Self-Refinement

Paper • 2604.01591 • Published Apr 2 • 42

authored 2 papers 3 months ago

SEAM: Semantically Equivalent Across Modalities Benchmark for Vision-Language Models

Paper • 2508.18179 • Published Aug 25, 2025 • 9

ThinkTwice: Jointly Optimizing Large Language Models for Reasoning and Self-Refinement

Paper • 2604.01591 • Published Apr 2 • 42