HanSaem Kim

kensaem's activity

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

upvoted 2 papers 1 day ago

Unified Personalized Reward Model for Vision Generation

Paper • 2602.02380 • Published 3 days ago • 17

Diversity-Preserved Distribution Matching Distillation for Fast Visual Synthesis

Paper • 2602.03139 • Published 2 days ago • 36

upvoted 17 papers 2 days ago

PromptRL: Prompt Matters in RL for Flow-Based Image Generation

Paper • 2602.01382 • Published 4 days ago • 8

FSVideo: Fast Speed Video Diffusion Model in a Highly-Compressed Latent Space

Paper • 2602.02092 • Published 3 days ago • 17

PixelGen: Pixel Diffusion Beats Latent Diffusion with Perceptual Loss

Paper • 2602.02493 • Published 3 days ago • 36

Causal Forcing: Autoregressive Diffusion Distillation Done Right for High-Quality Real-Time Interactive Video Generation

Paper • 2602.02214 • Published 3 days ago • 22

PISCES: Annotation-free Text-to-Video Post-Training via Optimal Transport-Aligned Rewards

Paper • 2602.01624 • Published 3 days ago • 23

Kimi K2.5: Visual Agentic Intelligence

Paper • 2602.02276 • Published 3 days ago • 190

PaddleOCR-VL-1.5: Towards a Multi-Task 0.9B VLM for Robust In-the-Wild Document Parsing

Paper • 2601.21957 • Published 7 days ago • 13

NativeTok: Native Visual Tokenization for Improved Image Generation

Paper • 2601.22837 • Published 6 days ago • 9

DINO-SAE: DINO Spherical Autoencoder for High-Fidelity Image Reconstruction and Generation

Paper • 2601.22904 • Published 6 days ago • 13

DenseGRPO: From Sparse to Dense Reward for Flow Matching Model Alignment

Paper • 2601.20218 • Published 8 days ago • 15

PaperBanana: Automating Academic Illustration for AI Scientists

Paper • 2601.23265 • Published 6 days ago • 110

One-step Latent-free Image Generation with Pixel Mean Flows

Paper • 2601.22158 • Published 7 days ago • 15

LoL: Longer than Longer, Scaling Video Generation to Hour

Paper • 2601.16914 • Published 13 days ago • 19

ConceptMoE: Adaptive Token-to-Concept Compression for Implicit Compute Allocation

Paper • 2601.21420 • Published 7 days ago • 41

OCRVerse: Towards Holistic OCR in End-to-End Vision-Language Models

Paper • 2601.21639 • Published 7 days ago • 47

DeepSeek-OCR 2: Visual Causal Flow

Paper • 2601.20552 • Published 8 days ago • 52

Advancing Open-source World Models

Paper • 2601.20540 • Published 8 days ago • 113

upvoted a paper 7 days ago

HyperAlign: Hypernetwork for Efficient Test-Time Alignment of Diffusion Models

Paper • 2601.15968 • Published 14 days ago • 6