Xinyin Ma

horseee's activity

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

authored a paper 2 months ago

In-Video Instructions: Visual Signals as Generative Control

Paper • 2511.19401 • Published Nov 24, 2025 • 32

authored a paper 8 months ago

Thinkless: LLM Learns When to Think

Paper • 2505.13379 • Published May 19, 2025 • 50

authored a paper 11 months ago

Introducing Visual Perception Token into Multimodal Large Language Model

Paper • 2502.17425 • Published Feb 24, 2025 • 16

authored a paper 12 months ago

CoT-Valve: Length-Compressible Chain-of-Thought Tuning

Paper • 2502.09601 • Published Feb 13, 2025 • 14

authored 2 papers about 1 year ago

TinyFusion: Diffusion Transformers Learned Shallow

Paper • 2412.01199 • Published Dec 2, 2024 • 14

Collaborative Decoding Makes Visual Auto-Regressive Modeling Efficient

Paper • 2411.17787 • Published Nov 26, 2024 • 12

authored a paper over 1 year ago

AsyncDiff: Parallelizing Diffusion Models by Asynchronous Denoising

Paper • 2406.06911 • Published Jun 11, 2024 • 12

authored a paper about 2 years ago

DeepCache: Accelerating Diffusion Models for Free

Paper • 2312.00858 • Published Dec 1, 2023 • 23