Yanzhi Wang

CircuitSense: A Hierarchical MLLM Benchmark Bridging Visual Comprehension and Symbolic Reasoning in Engineering Design Process

Taming Diffusion Transformer for Efficient Mobile Video Generation in Seconds

H3AE: High Compression, High Speed, and High Quality AutoEncoder for Video Diffusion Models

Efficient Reasoning with Hidden Thinking

From Bits to Chips: An LLM-based Hardware-Aware Quantization Agent for Streamlined Deployment of LLMs

Diff-StyGS: 3D Gaussian Splatting Stylization via Tuning-Free Multi-View Sparse Diffusion

LightCache: Memory-Efficient, Training-Free Acceleration for Video Generation

Advancing Physiological Time Series Reconstruction and Imputation via Mixture of Receptive Fields and Experts Fusion

DraftAttention: Fast Video Diffusion via Low-Resolution Attention Guidance

ALTER: All-in-One Layer Pruning and Temporal Expert Routing for Efficient Diffusion Generation

Sparse Learning for State Space Models on Mobile

Harmony in Divergence: Towards Fast, Accurate, and Memory-efficient Zeroth-order LLM Fine-tuning

Routing Mamba: Scaling State Space Models with Mixture-of-Experts Projection

Taming Diffusion for Dataset Distillation with High Representativeness

MoE-Pruner: Pruning Mixture-of-Experts Large Language Model using the Hints from Its Router

Fusion-$\mathcal{X}$: Advancing LLM Ability with Adaptive Heterogeneous Model Integration