hongyu

learn12138's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted 20 papers 25 days ago

DreamRelation: Relation-Centric Video Customization

Paper • 2503.07602 • Published 25 days ago • 14

EasyControl: Adding Efficient and Flexible Control for Diffusion Transformer

Paper • 2503.07027 • Published 26 days ago • 27

Feature-Level Insights into Artificial Text Detection with Sparse Autoencoders

Paper • 2503.03601 • Published about 1 month ago • 223

LoRACode: LoRA Adapters for Code Embeddings

Paper • 2503.05315 • Published 29 days ago • 10

TrajectoryCrafter: Redirecting Camera Trajectory for Monocular Videos via Diffusion Models

Paper • 2503.05638 • Published 28 days ago • 18

VideoPainter: Any-length Video Inpainting and Editing with Plug-and-Play Context Control

Paper • 2503.05639 • Published 28 days ago • 22

Forgetting Transformer: Softmax Attention with a Forget Gate

Paper • 2503.02130 • Published Mar 3 • 29

Union of Experts: Adapting Hierarchical Routing to Equivalently Decomposed Transformer

Paper • 2503.02495 • Published Mar 4 • 8

Diverse Controllable Diffusion Policy with Signal Temporal Logic

Paper • 2503.02924 • Published Mar 4 • 3

Remasking Discrete Diffusion Models with Inference-Time Scaling

Paper • 2503.00307 • Published Mar 1 • 9

RectifiedHR: Enable Efficient High-Resolution Image Generation via Energy Rectification

Paper • 2503.02537 • Published Mar 4 • 11

Unified Video Action Model

Paper • 2503.00200 • Published Feb 28 • 12

Direct Discriminative Optimization: Your Likelihood-Based Visual Generative Model is Secretly a GAN Discriminator

Paper • 2503.01103 • Published Mar 3 • 3

Training Consistency Models with Variational Noise Coupling

Paper • 2502.18197 • Published Feb 25 • 6

Building Interactable Replicas of Complex Articulated Objects via Gaussian Splatting

Paper • 2502.19459 • Published Feb 26 • 10

Mobius: Text to Seamless Looping Video Generation via Latent Shift

Paper • 2502.20307 • Published Feb 27 • 17

FlexiDiT: Your Diffusion Transformer Can Easily Generate High-Quality Samples with Less Compute

Paper • 2502.20126 • Published Feb 27 • 20

Beyond Next-Token: Next-X Prediction for Autoregressive Visual Generation

Paper • 2502.20388 • Published Feb 27 • 15

UniTok: A Unified Tokenizer for Visual Generation and Understanding

Paper • 2502.20321 • Published Feb 27 • 29

KV-Edit: Training-Free Image Editing for Precise Background Preservation

Paper • 2502.17363 • Published Feb 24 • 35