MiroThinker-1.7 & H1: Towards Heavy-Duty Research Agents via Verification
Paper • 2603.15726 • Published • 185
AI & ML interests
The World’s First General Purpose Solver.
Recent Activity
View all activity
binwang
authored a
paper about 1 month ago
binwang
authored a
paper 9 months ago
Vanint
authored 18
papers 10 months ago
Disentangling Writer and Character Styles for Handwriting Generation
Paper • 2303.14736 • Published • 3
HiPA: Enabling One-Step Text-to-Image Diffusion Models via High-Frequency-Promoting Adaptation
Paper • 2311.18158 • Published
Dataset Quantization
Paper • 2308.10524 • Published
Efficient Test-Time Model Adaptation without Forgetting
Paper • 2204.02610 • Published
Fully Test-Time Adaptation for Monocular 3D Object Detection
Paper • 2405.19682 • Published
MEMO: Memory-Guided Diffusion for Expressive Talking Video Generation
Paper • 2412.04448 • Published • 10
One-Shot Diffusion Mimicker for Handwritten Text Generation
Paper • 2409.04004 • Published
Poison-splat: Computation Cost Attack on 3D Gaussian Splatting
Paper • 2410.08190 • Published • 1
DriveGEN: Generalized and Robust 3D Detection in Driving via Controllable Text-to-Image Diffusion Generation
Paper • 2503.11122 • Published
Guiding VLM Agents with Process Rewards at Inference Time for GUI Navigation
Paper • 2504.16073 • Published
Matrix-Game: Interactive World Foundation Model
Paper • 2506.18701 • Published • 72
Deep Long-Tailed Learning: A Survey
Paper • 2110.04596 • Published
No Fear of Heterogeneity: Classifier Calibration for Federated Learning with Non-IID Data
Paper • 2106.05001 • Published
Towards Stable Test-Time Adaptation in Dynamic Wild World
Paper • 2302.12400 • Published
Self-Supervised Aggregation of Diverse Experts for Test-Agnostic Long-Tailed Recognition
Paper • 2107.09249 • Published
Source-free Domain Adaptation via Avatar Prototype Generation and Adaptation
Paper • 2106.15326 • Published
Cost-Sensitive Portfolio Selection via Deep Reinforcement Learning
Paper • 2003.03051 • Published
Unleashing the Power of Contrastive Self-Supervised Visual Models via Contrast-Regularized Fine-Tuning
Paper • 2102.06605 • Published