10 papers
Multi-Resolution Flow Matching: Training-Free Diffusion Acceleration via Staged Sampling
Xingyu Zheng, Xianglong Liu, Yifu Ding +4
Hardware-agnostic strategies for accelerating text-to-image diffusion, such as timestep distillation and feature caching, can reduce inference time without custom kernels or system…
An Empirical Study of openPangu Quantization on Ascend NPUs
Tong Shi, Jiacheng Wang, Hui Xie +4
openPangu models are attractive targets for private and domestic large-language-model deployment, yet their robustness under aggressive post-training quantization on Ascend NPUs ha…
Frequency-Aware Flow Matching for Continuous and Consistent Robotic Action Generation
Jianing Guo, Fangzheng Chen, Zihao Mao +12
Flow matching has emerged as a standard paradigm for robotic manipulation owing to its strong expressive power for modelling complex, multimodal action distributions, alongside sim…
Attribution-Guided and Coverage-Maximized Pruning for Structural MoE Compression
Yifu Ding, Jiacheng Wang, Ge Yang +4
Mixture-of-Experts (MoE) models scale compute efficiently, yet remain expensive to deploy due to their substantial memory footprint and inference overhead. Prior compression method…
LoopCoder-v2: Only Loop Once for Efficient Test-Time Computation Scaling
Jian Yang, Shawn Guo, Wei Zhang +16
Looped Transformers scale latent computation by repeatedly applying shared blocks, but sequential looping increases latency and KV-cache memory with the loop count. Parallel loop T…
BWTA: Accurate and Efficient Binarized Transformer by Algorithm-Hardware Co-design
Yifu Ding, Xianglong Liu, Shenghao Jin +2
Ultra low-bit quantization brings substantial efficiency for Transformer-based models, but the accuracy degradation and limited GPU support hinder its wide usage. In this paper, we…