HanSaem Kim

kensaem's activity

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

upvoted a paper 1 day ago

Enhancing Train-Free Infinite-Frame Generation for Consistent Long Videos

Paper • 2605.18233 • Published 5 days ago • 87

upvoted 6 papers 4 days ago

RAVEN: Real-time Autoregressive Video Extrapolation with Consistency-model GRPO

Paper • 2605.15190 • Published 9 days ago • 13

SANA-WM: Efficient Minute-Scale World Modeling with Hybrid Linear Diffusion Transformer

Paper • 2605.15178 • Published 9 days ago • 80

Causal Forcing++: Scalable Few-Step Autoregressive Diffusion Distillation for Real-Time Interactive Video Generation

Paper • 2605.15141 • Published 9 days ago • 91

LiteFrame: Efficient Vision Encoders Unlock Frame Scaling in Video LLMs

Paper • 2605.17260 • Published 6 days ago • 24

LongLive-2.0: An NVFP4 Parallel Infrastructure for Long Video Generation

Paper • 2605.18739 • Published 5 days ago • 108

AI for Auto-Research: Roadmap & User Guide

Paper • 2605.18661 • Published 5 days ago • 63

upvoted a paper 9 days ago

Qwen-Image-VAE-2.0 Technical Report

Paper • 2605.13565 • Published 10 days ago • 58

upvoted 3 papers 11 days ago

Mean Mode Screaming: Mean--Variance Split Residuals for 1000-Layer Diffusion Transformers

Paper • 2605.06169 • Published 16 days ago • 195

Model Merging Scaling Laws in Large Language Models

Paper • 2509.24244 • Published 12 days ago • 44

Soohak: A Mathematician-Curated Benchmark for Evaluating Research-level Math Capabilities of LLMs

Paper • 2605.09063 • Published 14 days ago • 78

upvoted a collection 23 days ago

SenseNova-U1

Collection

SenseNova-U1: Unifying Multimodal Understanding and Generation with NEO-Unify Architecture • 8 items • Updated 8 days ago • 67

upvoted a paper 23 days ago

Sapiens2

Paper • 2604.21681 • Published about 1 month ago • 19

upvoted a paper 24 days ago

HP-Edit: A Human-Preference Post-Training Framework for Image Editing

Paper • 2604.19406 • Published Apr 21 • 7

upvoted 5 papers 25 days ago

LLaDA2.0-Uni: Unifying Multimodal Understanding and Generation with Diffusion Large Language Model

Paper • 2604.20796 • Published Apr 22 • 240

Reward Hacking in the Era of Large Models: Mechanisms, Emergent Misalignment, Challenges

Paper • 2604.13602 • Published Apr 15 • 32

Seeing Fast and Slow: Learning the Flow of Time in Videos

Paper • 2604.21931 • Published about 1 month ago • 19

Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generation

Paper • 2604.24763 • Published 26 days ago • 71

FlowAnchor: Stabilizing the Editing Signal for Inversion-Free Video Editing

Paper • 2604.22586 • Published 29 days ago • 16

upvoted a collection 26 days ago

Qwen-Image

Collection

14 items • Updated Dec 31, 2025 • 106