5 papers
ELAS: Efficient Pre-Training of Low-Rank Large Language Models via 2:4 Activation Sparsity
Jiaxi Li, Lu Yin, Li Shen +5
Large Language Models (LLMs) have achieved remarkable capabilities, but their immense computational demands during training remain a critical bottleneck for widespread adoption. Lo…
GCDance: Genre-Controlled Music-Driven 3D Full Body Dance Generation
Xinran Liu, Xu Dong, Shenbin Qian +3
Music-driven dance generation is a challenging task as it requires strict adherence to genre-specific choreography while ensuring physically realistic and precisely synchronized da…
LOST: Low-rank and Sparse Pre-training for Large Language Models
Jiaxi Li, Lu Yin, Li Shen +6
While large language models (LLMs) have achieved remarkable performance across a wide range of tasks, their massive scale incurs prohibitive computational and memory costs for pre-…
DGFM: Full Body Dance Generation Driven by Music Foundation Models
Xinran Liu, Zhenhua Feng, Diptesh Kanojia +1
In music-driven dance motion generation, most existing methods use hand-crafted features and neglect that music foundation models have profoundly impacted cross-modal content gener…
The ICME 2025 Audio Encoder Capability Challenge
Junbo Zhang, Heinrich Dinkel, Qiong Song +8
This challenge aims to evaluate the capabilities of audio encoders, especially in the context of multi-task learning and real-world applications. Participants are invited to submit…