collaborators

5 papers

cs.CV2026

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…

cs.RO2026

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…

cs.LG2026

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…

cs.LG2026

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…

cs.LG2026

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…