From the 1 of 5 linked papers with an AI index.
5 papers
InfoFlow KV: Information-Flow-Aware KV Recomputation for Long Context
Xin Teng, Canyu Zhang, Shaoyi Zheng +3
The paper proposes InfoFlow KV, a method that uses an attention‑norm signal to identify which key‑value cache tokens should be recomputed during retrieval‑augmented generation, imp…
Smoothing Dark Areas in Molecular Latent Diffusion
Xi Wang, Jiahan Li, Yuxuan Xia +3
Latent diffusion is a promising framework for scalable 3D molecular generation, but it requires a latent space that remains smooth, valid, and navigable beyond posterior samples. E…
ToMA: Token Merge with Attention for Diffusion Models
Wenbo Lu, Shaoyi Zheng, Yuxuan Xia +1
Diffusion models excel in high-fidelity image generation but face scalability limits due to transformers' quadratic attention complexity. Plug-and-play token reduction methods like…
Submodular Context Partitioning and Compression for In-Context Learning
Shaoyi Zheng, Canyu Zhang, Tianyi Zhou +1
In-context learning (ICL) enables efficient few-shot learning in large language models (LLMs) without training, but suffers from the quadratic input complexity of transformers, lim…
HilbertA: Hilbert Attention for Image Generation with Diffusion Models
Shaoyi Zheng, Wenbo Lu, Yuxuan Xia +2
Designing sparse attention for diffusion transformers requires reconciling two-dimensional spatial locality with GPU efficiency, a trade-off that current methods struggle to achiev…