Gaowen Liu

16

Papers

53

Total Citations

Papers (16)

UniMuMo: Unified Text, Music, and Motion Generation

Effective Training Data Synthesis for Improving MLLM Chart Understanding

Self-Adapting Large Visual-Language Models to Edge Devices across Visual Modalities

Efficient Multitask Dense Predictor via Binarization

CaO2: Rectifying Inconsistencies in Diffusion-Based Dataset Distillation

Compositional Caching for Training-free Open-vocabulary Attribute Detection

Enhancing Dance-to-Music Generation via Negative Conditioning Latent Diffusion Model

Efficient Multimodal Dataset Distillation via Generative Models

NeurIPS 2025arXiv

Orientation-anchored Hyper-Gaussian for 4D Reconstruction from Casual Videos

NeurIPS 2025arXiv

Targeted Forgetting of Image Subgroups in CLIP Models

Enhancing Post-training Quantization Calibration through Contrastive Learning

Invisible Watermarks, Visible Gains: Steering Machine Unlearning with Bi-Level Watermarking Design

WaveFormer: Wavelet Transformer for Noise-Robust Video Inpainting

MULTIFLOW: Shifting Towards Task-Agnostic Vision-Language Pruning

Riemannian Multinomial Logistics Regression for SPD Neural Networks

MonoTAKD: Teaching Assistant Knowledge Distillation for Monocular 3D Object Detection