collaborators

10 papers

cs.CV2026

Region-Adaptive Sampling for Diffusion Transformers

Ziming Liu, Yifan Yang, Chengruidong Zhang +4

Diffusion models (DMs) have become the leading choice for generative tasks across diverse domains. However, their reliance on multiple sequential forward passes significantly limit…

cs.CL2026

Time-Annealed Perturbation Sampling: Diverse Generation for Diffusion Language Models

Jingxuan Wu, Zhenglin Wan, Xingrui Yu +4

Diffusion language models (Diffusion-LMs) introduce an explicit temporal dimension into text generation, yet how this structure can be leveraged to control generation diversity for…

cs.LG2026

MoNE: Replacing Redundant Experts with Lightweight Novices for Structured Pruning of MoE

Geng Zhang, Yuxuan Han, Yuxuan Lou +3

Mixture-of-Experts (MoE) enables efficient scaling of large language models by activating only a subset of experts per input token. However, deploying MoE-based models incurs signi…

cs.LG2026

HBVLA: Pushing 1-Bit Post-Training Quantization for Vision-Language-Action Models

Xin Yan, Zhenglin Wan, Feiyang Ye +4

Vision-Language-Action (VLA) models enable instruction-following embodied control, but their large compute and memory footprints hinder deployment on resource-constrained robots an…

cs.CV2026

K-Sort Eval: Efficient Preference Evaluation for Visual Generation via Corrected VLM-as-a-Judge

Zhikai Li, Jiatong Li, Xuewen Liu +7

The rapid development of visual generative models raises the need for more scalable and human-aligned evaluation methods. While the crowdsourced Arena platforms offer human prefere…

cs.CL2026

DiffuSpeech: Silent Thought, Spoken Answer via Unified Speech-Text Diffusion

Yuxuan Lou, Ziming Wu, Yaochen Wang +6

Current speech language models generate responses directly without explicit reasoning, leading to errors that cannot be corrected once audio is produced. We introduce \textbf{``Sil…