Haoqian Wang

When Models Judge Themselves: Unsupervised Self-Evolution for Multimodal Reasoning

arXiv 2026

MeshCoder: LLM-Powered Structured Mesh Code Generation from Point Clouds

arXiv 2025

MergeVQ: A Unified Framework for Visual Generation and Representation with Disentangled Token Merging and Quantization

CVPR 2025 1

DPoser-X: Diffusion Model as Robust 3D Whole-body Human Pose Prior

arXiv 2025

HumanMM: Global Human Motion Recovery from Multi-shot Videos

CVPR 2025 1

Taming Hallucinations: Boosting MLLMs' Video Understanding via Counterfactual Video Generation

arXiv 2025

LangSplat: 3D Language Gaussian Splatting

CVPR 2024 1

Retinexformer: One-stage Retinex-based Transformer for Low-light Image Enhancement

ICCV 2023 1

Motion-X: A Large-scale 3D Expressive Whole-body Human Motion Dataset

NeurIPS 2023 11

One-Stage 3D Whole-Body Mesh Recovery with Component Aware Transformer

CVPR 2023 1

Jing Lin

Ailing Zeng

Lei Zhang

Haonan Lu

Luyuan Zhang

Minghan Qin

Yuanhao Cai

Yulun Zhang

Aiming Hao

Bingquan Dai