Zikai Zhou

Klayand's activity

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

upvoted a paper 7 days ago

FlashVSR: Towards Real-Time Diffusion-Based Streaming Video Super-Resolution

Paper • 2510.12747 • Published Oct 14 • 37

upvoted a paper 10 days ago

UniVA: Universal Video Agent towards Open-Source Next-Generation Video Generalist

Paper • 2511.08521 • Published 12 days ago • 37

upvoted a paper 12 days ago

VideoSSR: Video Self-Supervised Reinforcement Learning

Paper • 2511.06281 • Published 15 days ago • 22

upvoted a paper 15 days ago

Thinking with Video: Video Generation as a Promising Multimodal Reasoning Paradigm

Paper • 2511.04570 • Published 17 days ago • 197

upvoted a paper 26 days ago

Latent Sketchpad: Sketching Visual Thoughts to Elicit Multimodal Reasoning in MLLMs

Paper • 2510.24514 • Published 27 days ago • 20

upvoted a paper 29 days ago

AlphaFlow: Understanding and Improving MeanFlow Models

Paper • 2510.20771 • Published Oct 23 • 7

upvoted 14 papers about 1 month ago

Pico-Banana-400K: A Large-Scale Dataset for Text-Guided Image Editing

Paper • 2510.19808 • Published Oct 22 • 28

MoGA: Mixture-of-Groups Attention for End-to-End Long Video Generation

Paper • 2510.18692 • Published Oct 21 • 39

MUG-V 10B: High-efficiency Training Pipeline for Large Video Generation Models

Paper • 2510.17519 • Published Oct 20 • 9

Scaling Instruction-Based Video Editing with a High-Quality Synthetic Dataset

Paper • 2510.15742 • Published Oct 17 • 50

BLIP3o-NEXT: Next Frontier of Native Image Generation

Paper • 2510.15857 • Published Oct 17 • 22

ContextGen: Contextual Layout Anchoring for Identity-Consistent Multi-Instance Generation

Paper • 2510.11000 • Published Oct 13 • 8

Diffusion Transformers with Representation Autoencoders

Paper • 2510.11690 • Published Oct 13 • 162

PickStyle: Video-to-Video Style Transfer with Context-Style Adapters

Paper • 2510.07546 • Published Oct 8 • 21

InstructX: Towards Unified Visual Editing with MLLM Guidance

Paper • 2510.08485 • Published Oct 9 • 16

DreamOmni2: Multimodal Instruction-based Editing and Generation

Paper • 2510.06679 • Published Oct 8 • 73

VideoCanvas: Unified Video Completion from Arbitrary Spatiotemporal Patches via In-Context Conditioning

Paper • 2510.08555 • Published Oct 9 • 63

Hyperparameters are all you need: Using five-step inference for an original diffusion model to generate images comparable to the latest distillation model

Paper • 2510.02390 • Published Sep 30 • 3

Training-Free Group Relative Policy Optimization

Paper • 2510.08191 • Published Oct 9 • 44

UniVideo: Unified Understanding, Generation, and Editing for Videos

Paper • 2510.08377 • Published Oct 9 • 70