UofTCSSLab/Maia3-79M
Updated • 11
AI & ML interests
None defined yet.
Recent Activity
View all activity
Papers
LLM Safety From Within: Detecting Harmful Content with Internal Representations
ThinkTwice: Jointly Optimizing Large Language Models for Reasoning and Self-Refinement
UofTCSSLab/Maia3-ablate-3M
Updated • 1
UofTCSSLab/Maia3-23M
Updated • 1
UofTCSSLab/Maia3-5M
Updated • 1
UofTCSSLab/Maia3-ablate-relpos
Updated
UofTCSSLab/Maia3-ablate-abspos
Updated
UofTCSSLab/Maia3-ablate-hist1
Updated
UofTCSSLab/Maia3-ablate-hist32
Updated
UofTCSSLab/SIREN-Llama-3.1-8B
Updated • 12
UofTCSSLab/SIREN-Llama-3.2-1B
Updated • 15
UofTCSSLab/SIREN-Qwen3-4B
Updated • 24
UofTCSSLab/SIREN-Qwen3-0.6B
Updated • 19