logo
today local_bar
🏛 AMD

3 papers across 3 sessions

Poster Session 2

1 paper
Wednesday, December 3, 2025 · 4:30 PM → 7:30 PM
Exhibit Hall C,D,E
Zebra-Llama: Towards Extremely Efficient Hybrid Models
#3710 · Mingyu Yang, Mehdi Rezagholizadeh, Guihong Li, Vikram Appia, Emad Barsoum

Poster Session 5

1 paper
Friday, December 5, 2025 · 11:00 AM → 2:00 PM
Exhibit Hall C,D,E
Unleashing Hour-Scale Video Training for Long Video-Language Understanding
#4604 Spotlight · Jingyang Lin, Jialian Wu, Ximeng Sun, Ze Wang, Jiang Liu, Yusheng Su, Xiaodong Yu, Hao Chen, Jiebo Luo, Zicheng Liu, Emad Barsoum

We present VideoMarathon, a large-scale synthetic video instruction-following dataset for hour-long video-language understanding, and propose Hour-LLaVA, a Video-LLMs that enables efficient video-language modeling.

Poster Session 6

1 paper
Friday, December 5, 2025 · 4:30 PM → 7:30 PM
Exhibit Hall C,D,E
Týr-the-Pruner: Structural Pruning LLMs via Global Sparsity Distribution Optimization
#904 · Guanchen Li, Yixing Xu, Zeping Li, Ji Liu, Xuanwu Yin, Dong Li, Emad Barsoum