training-free acceleration

2 papers across 2 sessions

Poster Session 1

1 paper

Wednesday, December 3, 2025 · 11:00 AM → 2:00 PM

Exhibit Hall C,D,E

MagCache: Fast Video Generation with Magnitude-Aware Cache

#4308 · Zehong Ma, Longhui Wei, Feng Wang, Shiliang Zhang, Qi Tian

Poster Session 2

1 paper

Wednesday, December 3, 2025 · 4:30 PM → 7:30 PM

Exhibit Hall C,D,E

Beyond Attention or Similarity: Maximizing Conditional Diversity for Token Pruning in MLLMs

#4718 · Qizhe Zhang, Mengzhen Liu, Lichen Li, Ming Lu, Yuan Zhang, Junwen Pan, Qi She, Shanghang Zhang

We propose a training-free visual token pruning method CDPruner for MLLM inference acceleration by maximizing the conditional diversity of retained tokens.