6 papers
CORA-Diff: Confidence-Oriented Residual Acceptance for Efficient Diffusion Language Model Inference
Yifan Wu, Yufeng Zhang, Kenli Li
Diffusion language models (DLMs) update many tokens in parallel, yet practical decoders often use a fixed denoising horizon. Many predictions stabilize early, but blockwise decodin…
A-IO: Adaptive Inference Orchestration for Memory-Bound NPUs
Chen Zhang, Yan Ding, Haotian Wang +3
During the deployment of Large Language Models (LLMs), the autoregressive decoding phase on heterogeneous NPU platforms (e.g., Ascend 910B) faces severe memory-bound challenges. Th…
Relaxed Triangle Inequality for Kullback-Leibler Divergence Between Multivariate Gaussian Distributions
Shiji Xiao, Yufeng Zhang, Chubo Liu +3
The Kullback-Leibler (KL) divergence is not a proper distance metric and does not satisfy the triangle inequality, posing theoretical challenges in certain practical applications.…
All Cities are Equal: A Unified Human Mobility Generation Model Enabled by LLMs
Bo Liu, Tong Li, Zhu Xiao +4
Synthetic human mobility generation is gaining traction as an ethical and practical approach to supporting the data needs of intelligent urban systems. Existing methods perform wel…
fMRI2GES: Co-speech Gesture Reconstruction from fMRI Signal with Dual Brain Decoding Alignment
Chunzheng Zhu, Jialin Shao, Jianxin Lin +4
Understanding how the brain responds to external stimuli and decoding this process has been a significant challenge in neuroscience. While previous studies typically concentrated o…
LiNeXt: Revisiting LiDAR Completion with Efficient Non-Diffusion Architectures
Wenzhe He, Xiaojun Chen, Ruiqi Wang +5
3D LiDAR scene completion from point clouds is a fundamental component of perception systems in autonomous vehicles. Previous methods have predominantly employed diffusion models f…