4 papers
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…
REINA: Regularized Entropy Information-Based Loss for Efficient Simultaneous Speech Translation
Nameer Hirschkind, Joseph Liu, Xiao Yu +1
Simultaneous Speech Translation (SimulST) systems stream in audio while simultaneously emitting translated text or speech. Such systems face the significant challenge of balancing…
StyleMotif: Multi-Modal Motion Stylization using Style-Content Cross Fusion
Ziyu Guo, Young Yoon Lee, Joseph Liu +3
We present StyleMotif, a novel Stylized Motion Latent Diffusion model, generating motion conditioned on both content and style from multiple modalities. Unlike existing approaches…
SmoothCache: A Universal Inference Acceleration Technique for Diffusion Transformers
Joseph Liu, Joshua Geddes, Ziyu Guo +2
Diffusion Transformers (DiT) have emerged as powerful generative models for various tasks, including image, video, and speech synthesis. However, their inference process remains co…