Picture for Changdi Yang

Changdi Yang

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

Add code
May 27, 2025
Viaarxiv icon

Structured Agent Distillation for Large Language Model

Add code
May 20, 2025
Viaarxiv icon

QuartDepth: Post-Training Quantization for Real-Time Depth Estimation on the Edge

Add code
Mar 20, 2025
Viaarxiv icon

Fully Open Source Moxin-7B Technical Report

Add code
Dec 08, 2024
Figure 1 for Fully Open Source Moxin-7B Technical Report
Figure 2 for Fully Open Source Moxin-7B Technical Report
Figure 3 for Fully Open Source Moxin-7B Technical Report
Figure 4 for Fully Open Source Moxin-7B Technical Report
Viaarxiv icon

Fast and Memory-Efficient Video Diffusion Using Streamlined Inference

Add code
Nov 02, 2024
Figure 1 for Fast and Memory-Efficient Video Diffusion Using Streamlined Inference
Figure 2 for Fast and Memory-Efficient Video Diffusion Using Streamlined Inference
Figure 3 for Fast and Memory-Efficient Video Diffusion Using Streamlined Inference
Figure 4 for Fast and Memory-Efficient Video Diffusion Using Streamlined Inference
Viaarxiv icon

Rethinking Token Reduction for State Space Models

Add code
Oct 16, 2024
Figure 1 for Rethinking Token Reduction for State Space Models
Figure 2 for Rethinking Token Reduction for State Space Models
Figure 3 for Rethinking Token Reduction for State Space Models
Figure 4 for Rethinking Token Reduction for State Space Models
Viaarxiv icon

Efficient Pruning of Large Language Model with Adaptive Estimation Fusion

Add code
Mar 16, 2024
Viaarxiv icon

InstructGIE: Towards Generalizable Image Editing

Add code
Mar 08, 2024
Viaarxiv icon

DiffClass: Diffusion-Based Class Incremental Learning

Add code
Mar 08, 2024
Figure 1 for DiffClass: Diffusion-Based Class Incremental Learning
Figure 2 for DiffClass: Diffusion-Based Class Incremental Learning
Figure 3 for DiffClass: Diffusion-Based Class Incremental Learning
Figure 4 for DiffClass: Diffusion-Based Class Incremental Learning
Viaarxiv icon

EdgeQAT: Entropy and Distribution Guided Quantization-Aware Training for the Acceleration of Lightweight LLMs on the Edge

Add code
Feb 16, 2024
Figure 1 for EdgeQAT: Entropy and Distribution Guided Quantization-Aware Training for the Acceleration of Lightweight LLMs on the Edge
Figure 2 for EdgeQAT: Entropy and Distribution Guided Quantization-Aware Training for the Acceleration of Lightweight LLMs on the Edge
Figure 3 for EdgeQAT: Entropy and Distribution Guided Quantization-Aware Training for the Acceleration of Lightweight LLMs on the Edge
Figure 4 for EdgeQAT: Entropy and Distribution Guided Quantization-Aware Training for the Acceleration of Lightweight LLMs on the Edge
Viaarxiv icon