Ming-Ming Cheng

WOW-Seg: A Word-free Open World Segmentation Model

ORION: Decoupling and Alignment for Unified Autoregressive Understanding and Generation

NAIPv2: Debiased Pairwise Learning for Efficient Paper Quality Estimation

Visibility-Uncertainty-guided 3D Gaussian Inpainting via Scene Conceptional Learning

PersonalQ: Select, Quantize, and Serve Personalized Diffusion Models for Efficient Inference

Revisiting Data Challenges of Computational Pathology: A Pack-based Multiple Instance Learning Framework

Value-Alignment via Safe Semantic Manifold-Constrained Latent Diffusion

Few-Shot Idea Auto-Generation: Reasoning Over Idea Representations to Predict New Research Ideas

Representation Entanglement for Generation: Training Diffusion Transformers Is Much Easier Than You Think

Multimodality Helps Few-shot 3D Point Cloud Semantic Segmentation

One-Prompt-One-Story: Free-Lunch Consistent Text-to-Image Generation Using a Single Prompt

OmniSegmentor: A Flexible Multi-Modal Learning Framework for Semantic Segmentation

Knowledge Graph Enhanced Generative Multi-modal Models for Class-Incremental Learning

TempSamp-R1: Effective Temporal Sampling with Reinforcement Fine-Tuning for Video LLMs

DepthVanish: Optimizing Adversarial Interval Structures for Stereo-Depth-Invisible Patches

DIPO: Dual-State Images Controlled Articulated Object Generation Powered by Diverse Data

AngleRoCL: Angle-Robust Concept Learning for Physically View-Invariant Adversarial Patches

Revisiting End-to-End Learning with Slide-level Supervision in Computational Pathology

MaskCLIP++: A Mask-Based CLIP Fine-tuning Framework for Open-Vocabulary Image Segmentation

EmoAttack: Emotion-to-Image Diffusion Models for Emotional Backdoor Generation

Visibility-Uncertainty-guided 3D Gaussian Inpainting via Scene Conceptional Learning

Re-Aligning Language to Visual Objects with an Agentic Workflow

ClearSR: Latent Low-Resolution Image Embeddings Help Diffusion-Based Real-World Super Resolution Models See Clearer

$InterLCM$: Low-Quality Images as Intermediate States of Latent Consistency Models for Effective Blind Face Restoration

AR-1-to-3: Single Image to Consistent 3D Object Generation via Next-View Prediction

KAC: Kolmogorov-Arnold Classifier for Continual Learning

Efficient Multi-Level Learning for Dense Object Detection