rs

HA-SA-ki's activity

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

upvoted 3 papers about 2 months ago

TiDAR: Think in Diffusion, Talk in Autoregression

Paper • 2511.08923 • Published Nov 12, 2025 • 117

Group Relative Attention Guidance for Image Editing

Paper • 2510.24657 • Published Oct 28, 2025 • 25

Step-Audio-EditX Technical Report

Paper • 2511.03601 • Published Nov 5, 2025 • 28

upvoted 8 papers 2 months ago

Hyperspherical Latents Improve Continuous-Token Autoregressive Generation

Paper • 2509.24335 • Published Sep 29, 2025 • 8

Map the Flow: Revealing Hidden Pathways of Information in VideoLLMs

Paper • 2510.13251 • Published Oct 15, 2025 • 12

Reasoning with Sampling: Your Base Model is Smarter Than You Think

Paper • 2510.14901 • Published Oct 16, 2025 • 47

Sample By Step, Optimize By Chunk: Chunk-Level GRPO For Text-to-Image Generation

Paper • 2510.21583 • Published Oct 24, 2025 • 30

DeepSeek-OCR: Contexts Optical Compression

Paper • 2510.18234 • Published Oct 21, 2025 • 84

RL makes MLLMs see better than SFT

Paper • 2510.16333 • Published Oct 18, 2025 • 48

Visual Autoregressive Models Beat Diffusion Models on Inference Time Scaling

Paper • 2510.16751 • Published Oct 19, 2025 • 20

PICABench: How Far Are We from Physically Realistic Image Editing?

Paper • 2510.17681 • Published Oct 20, 2025 • 62