Zhiyuan Ma

15

Papers

53

Total Citations

Papers (15)

ScaleDreamer: Scalable Text-to-3D Synthesis with Asynchronous Score Distillation

AdapEdit: Spatio-Temporal Guided Adaptive Editing Algorithm for Text-Based Continuity-Sensitive Image Editing

Dense Multimodal Alignment for Open-Vocabulary 3D Scene Understanding

Zero-Shot Blind-spot Image Denoising via Implicit Neural Sampling

CADGrasp: Learning Contact and Collision Aware General Dexterous Grasping in Cluttered Scenes

DreamAlign: Dynamic Text-to-3D Optimization with Human Preference Alignment

Retrieval-Augmented Visual Question Answering via Built-in Autoregressive Search Engines

Automated Creation of Reusable and Diverse Toolsets for Enhancing LLM Reasoning

Generative Multi-Modal Knowledge Retrieval with Large Language Models

Dual Memory Networks: A Versatile Adaptation Approach for Vision-Language Models

VideoDirector: Precise Video Editing via Text-to-Video Models

OTAvatar: One-Shot Talking Face Avatar With Controllable Tri-Plane Rendering

Pixel-level and Semantic-level Adjustable Super-resolution: A Dual-LoRA Approach

Progressive Rendering Distillation: Adapting Stable Diffusion for Instant Text-to-Mesh Generation without 3D Data

MVBoost: Boost 3D Reconstruction with Multi-View Refinement