conftrace_

multi-modal tokenizer

2 papers

Explore in graph

Co-occurring keywords · papers mentioning both

scene affordance (1) human-scene interaction (1) text-to-motion generation (1) conditional variational autoencoder (1) edge device inference (1) discrete tokenization (1) next-token prediction (1) lossless compression (1) motion generation (1) context modeling (1)

Papers

OmniZip: Learning a Unified and Lightweight Lossless Compressor for Multi-Modal Data CVPR 2026 HSI-GPT: A General-Purpose Large Scene-Motion-Language Model for Human Scene Interaction CVPR 2025