adaptive autoencoder 1human motion generation 1motion-language grounding 1retrieval evaluation 1text-to-motion 1
From the 1 of 3 linked papers with an AI index.
3 papers
cs.LG2026
MUGEN: A Unified Framework for Efficient Motion Understanding and Generation
Zhankai Ye, Yukai Jin, Bingyang Wei +5
The paper introduces MUGEN, a unified framework that uses a single adaptive-length autoencoder to compress human motion into continuous latent slots, enabling efficient text-to-mot…
cs.LG2026
ToMoE: Converting Dense Large Language Models to Mixture-of-Experts through Dynamic Structural Pruning
Shangqian Gao, Ting Hua, Reza Shirkavand +10
Large Language Models (LLMs) have demonstrated remarkable abilities in tackling a wide range of complex tasks. However, their huge computational and memory costs raise significant…
cs.CL2024
All-in-One Tuning and Structural Pruning for Domain-Specific LLMs
Lei Lu, Zhepeng Wang, Runxue Bao +7
Existing pruning techniques for large language models (LLMs) targeting domain-specific applications typically follow a two-stage process: pruning the pretrained general-purpose LLM…