Chang Liu

43

Papers

185

Total Citations

Papers (43)

ParCo: Part-Coordinating Text-to-Motion Synthesis

Orthus: Autoregressive Interleaved Image-Text Generation with Modality-Specific Heads

MUSE-VL: Modeling Unified VLM through Semantic Discrete Encoding

Latent Reward: LLM-Empowered Credit Assignment in Episodic Reinforcement Learning

Local Action-Guided Motion Diffusion Model for Text-to-Motion Generation

Learning Spatially Collaged Fourier Bases for Implicit Neural Representation

Enhancing the Scalability and Applicability of Kohn-Sham Hamiltonians for Molecular Systems

Efficient and Scalable Density Functional Theory Hamiltonian Prediction through Adaptive Sparsity

Specifying What You Know or Not for Multi-Label Class-Incremental Learning

iSegMan: Interactive Segment-and-Manipulate 3D Gaussians

PatchVSR: Breaking Video Diffusion Resolution Limits with Patch-wise Video Super-Resolution

HumanSAM: Classifying Human-centric Forgery Videos in Human Spatial, Appearance, and Motion Anomaly

DCA: Dividing and Conquering Amnesia in Incremental Object Detection

Beyond Circuit Connections: A Non-Message Passing Graph Transformer Approach for Quantum Error Mitigation

GCRayDiffusion: Pose-Free Surface Reconstruction via Geometric Consistent Ray Diffusion

When Schrödinger Bridge Meets Real-World Image Dehazing with Unpaired Training

ScenePainter: Semantically Consistent Perpetual 3D Scene Generation with Concept Relation Alignment

Tune-Your-Style: Intensity-tunable 3D Style Transfer with Gaussian Splatting

Wavelet-Driven Masked Image Modeling: A Path to Efficient Visual Representation

ACM-MILP: Adaptive Constraint Modification via Grouping and Selection for Hardness-Preserving MILP Instance Generation

Machine Vision Therapy: Multimodal Large Language Models Can Enhance Visual Robustness via Denoising In-Context Learning

LLM-Empowered State Representation for Reinforcement Learning

VoroNav: Voronoi-based Zero-shot Object Navigation with Large Language Model

Self-Consistency Training for Density-Functional-Theory Hamiltonian Prediction

Kepler codebook

Linguistics-aware Masked Image Modeling for Self-supervised Scene Text Recognition

Advancing Myopia To Holism: Fully Contrastive Language-Image Pre-training

UnZipLoRA: Separating Content and Style from a Single Image

Temporal-aware Query Routing for Real-time Video Instance Segmentation

TAD-E2E: A Large-scale End-to-end Autonomous Driving Dataset

SUV: Suppressing Undesired Video Content via Semantic Modulation Based on Text Embeddings

Robust Heterogeneous Graph Classification for Molecular Property Prediction with Information Bottleneck

Aligning Instance Brownian Bridge with Texts for Open-Vocabulary Video Instance Segmentation

Exploiting Diffusion Prior for Real-World Image Dehazing with Unpaired Training

DigitalLLaVA: Incorporating Digital Cognition Capability for Physical World Comprehension in Multimodal LLMs

Parallel Vertex Diffusion for Unified Visual Grounding

Quantum Interference Model for Semantic Biases of Glosses in Word Sense Disambiguation

MuST: Robust Image Watermarking for Multi-Source Tracing

Bootstrapping Large Language Models for Radiology Report Generation

GraCo: Granularity-Controllable Interactive Segmentation

Referring Image Editing: Object-level Image Editing via Referring Expressions

Intelligent Grimm - Open-ended Visual Storytelling via Latent Diffusion Models

FaceChain-SuDe: Building Derived Class to Inherit Category Attributes for One-shot Subject-Driven Generation