Picture for Sheng Zhong

Sheng Zhong

Robotics Institute, University of Michigan

LLM-based Human-like Traffic Simulation for Self-driving Tests

Add code
Aug 23, 2025
Viaarxiv icon

Chordless Structure: A Pathway to Simple and Expressive GNNs

Add code
May 25, 2025
Viaarxiv icon

FlashForge: Ultra-Efficient Prefix-Aware Attention for LLM Decoding

Add code
May 23, 2025
Viaarxiv icon

Divide-and-Conquer: Dual-Hierarchical Optimization for Semantic 4D Gaussian Spatting

Add code
Mar 25, 2025
Viaarxiv icon

DriveEditor: A Unified 3D Information-Guided Framework for Controllable Object Editing in Driving Scenes

Add code
Dec 27, 2024
Figure 1 for DriveEditor: A Unified 3D Information-Guided Framework for Controllable Object Editing in Driving Scenes
Figure 2 for DriveEditor: A Unified 3D Information-Guided Framework for Controllable Object Editing in Driving Scenes
Figure 3 for DriveEditor: A Unified 3D Information-Guided Framework for Controllable Object Editing in Driving Scenes
Figure 4 for DriveEditor: A Unified 3D Information-Guided Framework for Controllable Object Editing in Driving Scenes
Viaarxiv icon

FLiP: Privacy-Preserving Federated Learning based on the Principle of Least Privileg

Add code
Oct 25, 2024
Figure 1 for FLiP: Privacy-Preserving Federated Learning based on the Principle of Least Privileg
Figure 2 for FLiP: Privacy-Preserving Federated Learning based on the Principle of Least Privileg
Figure 3 for FLiP: Privacy-Preserving Federated Learning based on the Principle of Least Privileg
Figure 4 for FLiP: Privacy-Preserving Federated Learning based on the Principle of Least Privileg
Viaarxiv icon

Revisiting SLO and Goodput Metrics in LLM Serving

Add code
Oct 18, 2024
Figure 1 for Revisiting SLO and Goodput Metrics in LLM Serving
Figure 2 for Revisiting SLO and Goodput Metrics in LLM Serving
Figure 3 for Revisiting SLO and Goodput Metrics in LLM Serving
Figure 4 for Revisiting SLO and Goodput Metrics in LLM Serving
Viaarxiv icon

ESVO2: Direct Visual-Inertial Odometry with Stereo Event Cameras

Add code
Oct 12, 2024
Figure 1 for ESVO2: Direct Visual-Inertial Odometry with Stereo Event Cameras
Figure 2 for ESVO2: Direct Visual-Inertial Odometry with Stereo Event Cameras
Figure 3 for ESVO2: Direct Visual-Inertial Odometry with Stereo Event Cameras
Figure 4 for ESVO2: Direct Visual-Inertial Odometry with Stereo Event Cameras
Viaarxiv icon

Detecting Dataset Abuse in Fine-Tuning Stable Diffusion Models for Text-to-Image Synthesis

Add code
Sep 27, 2024
Figure 1 for Detecting Dataset Abuse in Fine-Tuning Stable Diffusion Models for Text-to-Image Synthesis
Figure 2 for Detecting Dataset Abuse in Fine-Tuning Stable Diffusion Models for Text-to-Image Synthesis
Figure 3 for Detecting Dataset Abuse in Fine-Tuning Stable Diffusion Models for Text-to-Image Synthesis
Figure 4 for Detecting Dataset Abuse in Fine-Tuning Stable Diffusion Models for Text-to-Image Synthesis
Viaarxiv icon

Perceptual-Distortion Balanced Image Super-Resolution is a Multi-Objective Optimization Problem

Add code
Sep 05, 2024
Viaarxiv icon