2025 Poster "rotary position embedding" Papers
7 papers found
ComRoPE: Scalable and Robust Rotary Position Embedding Parameterized by Trainable Commuting Angle Matrices
Hao Yu, Tangyu Jiang, Shuning Jia et al.
CVPR 2025posterarXiv:2506.03737
3
citations
DynImg: Key Frames with Visual Prompts are Good Representation for Multi-Modal Video Understanding
Xiaoyi Bao, Chen-Wei Xie, Hao Tang et al.
ICCV 2025posterarXiv:2507.15569
1
citations
Rope to Nope and Back Again: A New Hybrid Attention Strategy
Bowen Yang, Bharat Venkitesh, Dwaraknath Gnaneshwar Talupuru et al.
NEURIPS 2025posterarXiv:2501.18795
20
citations
SALS: Sparse Attention in Latent Space for KV Cache Compression
Junlin Mu, Hantao Huang, Jihang Zhang et al.
NEURIPS 2025posterarXiv:2510.24273
Scaling Instruction-tuned LLMs to Million-token Contexts via Hierarchical Synthetic Data Generation
Linda He, Jue Wang, Maurice Weber et al.
ICLR 2025posterarXiv:2504.12637
2
citations
Wavelet-based Positional Representation for Long Context
Yui Oka, Taku Hasegawa, Kyosuke Nishida et al.
ICLR 2025posterarXiv:2502.02004
2
citations
Why RoPE Struggles to Maintain Long-Term Decay in Long Sequences?
Wei Shen, Chao Yin, Yuliang Liu et al.
ICLR 2025poster