2 papers
cs.LG2025
Taxonomy-Adaptive Moderation Model with Robust Guardrails for Large Language Models
Mahesh Kumar Nandwana, Youngwan Lim, Joseph Liu +3
Large Language Models (LLMs) are typically aligned for safety during the post-training phase; however, they may still generate inappropriate outputs that could potentially pose ris…
cs.CV2025
Cube: A Roblox View of 3D Intelligence
Foundation AI Team, Kiran Bhat, Nishchaie Khanna +44
Foundation models trained on vast amounts of data have demonstrated remarkable reasoning and generation capabilities in the domains of text, images, audio and video. Our goal at Ro…