Ying-Cong Chen

LongLive: Real-time Interactive Long Video Generation

DA$^{2}$: Depth Anything in Any Direction

DiMeR: Disentangled Mesh Reconstruction Model with Normal-only Geometry Training

UniCalli: A Unified Diffusion Framework for Column-Level Generation and Recognition of Chinese Calligraphy

PhysToolBench: Benchmarking Physical Tool Understanding for MLLMs

STANCE: Motion Coherent Video Generation Via Sparse-To-dense Anchored Encoding

CamPilot: Improving Camera Control in Video Diffusion Model with Efficient Camera Reward Feedback

Efficient Training-Free High-Resolution Synthesis with Energy Rectification in Diffusion Models

$SDPose$: Exploiting Diffusion Priors for Out-of-Domain and Robust Pose Estimation

Go with Your Gut: Scaling Confidence for Autoregressive Image Generation

Consistent3DGen: Bridging Stochastic Generation and Deterministic Reconstruction for Image-to-3D Diffusion Models

Motion Dreamer: Realizing Physically Coherent Video Generation through Scene-Aware Motion Reasoning

No Place to Hide: Benchmarking Video Hallucination with Background-Controlled Pairs

SyntheOcc: Synthesize Occupancy-Controlled Street View Images through 3D Semantic MPIs

ComfyMind: Toward General-Purpose Generation via Tree-Based Planning and Reactive Feedback

Lotus: Diffusion-based Visual Foundation Model for High-quality Dense Prediction

PRM: Photometric Stereo based Large Reconstruction Model

DisEnvisioner: Disentangled and Enriched Visual Prompt for Customized Image Generation

Motion Inversion for Video Customization

Event-Guided Consistent Video Enhancement with Modality-Adaptive Diffusion Pipeline

DrivingRecon: Large 4D Gaussian Reconstruction Model For Autonomous Driving

OmniBooth: Learning Latent Control for Image Synthesis with Multi-modal Instruction

PARM: Multi-Objective Test-Time Alignment via Preference-Aware Autoregressive Reward Model

SG-Adapter: Enhancing Text-to-Image Generation with Scene Graph Guidance

DrivingRecon: Large 4D Gaussian Reconstruction Model For Autonomous Driving

SyntheOcc: Synthesize Geometric-Controlled Street View Images through 3D Semantic MPIs

FlexGen: Flexible Multi-View Generation from Text and Image Inputs

Explicit-Constrained Single Agent for Enhanced Task-Solving in LLMs

SEED-Story: Multimodal Long Story Generation with Large Language Model

A Super-Aligned Driving Generalist Is Your Cockpit

LucidFusion: Generating 3D Gaussians with Arbitrary Unposed Images