University of Toronto CSSLab

university

https://csslab.cs.toronto.edu/

AI & ML interests

None defined yet.

Recent Activity

lilvjosephtang authored a paper 13 days ago

SafeGEO: Understanding Generative Engine Optimization Risks in Recommendation Agents

lilvjosephtang authored a paper 13 days ago

Chessformer: A Unified Architecture for Chess Modeling

lilvjosephtang authored a paper 13 days ago

Humanity's Last Choice: A Common Evaluation Standard for Generative Engine Optimization

View all activity

Papers

Social Priors: Descriptions of AI Users Shape How Language Models Trust and Cooperate

LLM Safety From Within: Detecting Harmful Content with Internal Representations

View all Papers

UofTCSSLab 's papers 3

Social Priors: Descriptions of AI Users Shape How Language Models Trust and Cooperate

UofTCSSLab

University of Toronto CSSLab

Submitted by

Difan Jiao

LLM Safety From Within: Detecting Harmful Content with Internal Representations

UofTCSSLab

University of Toronto CSSLab

Submitted by

Difan Jiao

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

UofTCSSLab

University of Toronto CSSLab