5 papers
Audio Token Attention Is Predictable Before the Language Model Runs
Kyoungjun Park, Yunzhe Li, Lili Qiu
A large audio language model (LALM) turns a minute of speech into 750-1,500 tokens and prefills every one. Image-token pruning often cuts after the language model's first layers, w…
ASD: Accelerating On-Demand Audio Understanding on Mobile Devices
Yunzhe Li, Kyoungjun Park, Hongzi Zhu +1
Speculative decoding accelerates autoregressive generation by using a smaller drafter to propose tokens for batched verification by a larger target. However, conventional speculati…
OmniCache: Multidimensional Hierarchical Feature Caching For Diffusion Models
Zhaoyuan He, Muhammad Muaz, Lili Qiu
High-resolution image and video diffusion models, including SD3, FLUX, and recent video diffusion transformers, have substantially improved generative quality but remain expensive…
Diffusion^2: Turning 3D Environments into Radio Frequency Heatmaps
Kyoungjun Park, Yifan Yang, Changhan Ge +2
Modeling radio frequency (RF) signal propagation is essential for understanding the environment, as RF signals offer valuable insights beyond the capabilities of RGB cameras, which…
VidGuard-R1: AI-Generated Video Detection and Explanation via Reasoning MLLMs and RL
Kyoungjun Park, Yifan Yang, Juheon Yi +6
The rapid proliferation of AI-generated video necessitates robust detection tools that offer both high accuracy and human-interpretable explanations. While existing MLLM-based dete…