Zhen Dong

25

Papers

192

Total Citations

Papers (25)

PB-LLM: Partially Binarized Large Language Models

Meissonic: Revitalizing Masked Generative Transformers for Efficient High-Resolution Text-to-Image Synthesis

VistaDream: Sampling multiview consistent images for single-view scene reconstruction

Efficient Deweahter Mixture-of-Experts with Uncertainty-Aware Feature-Wise Linear Modulation

K-Sort Arena: Efficient and Reliable Benchmarking for Generative Models via K-wise Human Preferences

CityAnchor: City-scale 3D Visual Grounding with Multi-modality LLMs

Learning to Detect Objects from Multi-Agent LiDAR Scans without Manual Labels

Learnable Motion Coherence for Correspondence Pruning

3D Shape Reconstruction From 2D Images With Disentangled Attribute Flow

NoisyQuant: Noisy Bias-Enhanced Post-Training Activation Quantization for Vision Transformers

Robust Multiview Point Cloud Registration With Reliable Pose Graph Initialization and History Reweighting

HAWQ: Hessian AWare Quantization of Neural Networks With Mixed-Precision

P2-Net: Joint Description and Detection of Local Features for Pixel and Point Matching

AdaFit: Rethinking Learning-Based Normal Estimation on Point Clouds

Q-Diffusion: Quantizing Diffusion Models

QD-BEV : Quantization-aware View-guided Distillation for Multi-view 3D Object Detection

DeepLA-Net: Very Deep Local Aggregation Networks for Point Cloud Analysis

Align3R: Aligned Monocular Depth Estimation for Dynamic Videos

An Item Is Worth a Prompt: Versatile Image Editing with Disentangled Control

PromptCoT: Align Prompt Distribution via Adapted Chain-of-Thought

SqueezeLLM: Dense-and-Sparse Quantization

Split-Ensemble: Efficient OOD-aware Ensemble via Task and Model Splitting

ZeroQ: A Novel Zero Shot Quantization Framework

HAWQ-V2: Hessian Aware trace-Weighted Quantization of Neural Networks

Enhancing Robot Program Synthesis Through Environmental Context