Kyu Song

kyunocap's activity

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

upvoted a paper about 13 hours ago

OmniAlign-V: Towards Enhanced Alignment of MLLMs with Human Preference

Paper • 2502.18411 • Published 1 day ago • 54

liked 2 models 1 day ago

Qwen/Qwen2.5-VL-7B-Instruct

Image-Text-to-Text • Updated 12 days ago • 1.84M • 567

Qwen/Qwen2.5-VL-72B-Instruct

Image-Text-to-Text • Updated 12 days ago • 244k • 332

upvoted a paper 7 days ago

Phantom: Subject-consistent video generation via cross-modal alignment

Paper • 2502.11079 • Published 11 days ago • 51

liked a Space 7 days ago

Running

1.67k

1.67k

The Ultra-Scale Playbook

🌌

The ultimate guide to training LLM on large GPU Clusters

upvoted a paper 9 days ago

On-device Sora: Enabling Diffusion-Based Text-to-Video Generation for Mobile Devices

Paper • 2502.04363 • Published 22 days ago • 11

upvoted a paper 14 days ago

Magic 1-For-1: Generating One Minute Video Clips within One Minute

Paper • 2502.07701 • Published 15 days ago • 32

liked a model 16 days ago

DAMO-NLP-SG/VideoLLaMA3-7B

Visual Question Answering • Updated 10 days ago • 14.3k • 37

upvoted 2 papers 19 days ago

ConceptAttention: Diffusion Transformers Learn Highly Interpretable Features

Paper • 2502.04320 • Published 20 days ago • 33

DynVFX: Augmenting Real Videos with Dynamic Content

Paper • 2502.03621 • Published 21 days ago • 27

upvoted 2 papers 21 days ago

LayerTracer: Cognitive-Aligned Layered SVG Synthesis via Diffusion Transformer

Paper • 2502.01105 • Published 24 days ago • 19

SmolLM2: When Smol Goes Big -- Data-Centric Training of a Small Language Model

Paper • 2502.02737 • Published 22 days ago • 195

upvoted a paper 22 days ago

OmniHuman-1: Rethinking the Scaling-Up of One-Stage Conditioned Human Animation Models

Paper • 2502.01061 • Published 24 days ago • 183

liked a Space 28 days ago

Running on Zero

1.16k

1.16k

FLUX Prompt Generator

😻

Display a user interface for various tasks

upvoted a paper 28 days ago

Qwen2.5-1M Technical Report

Paper • 2501.15383 • Published Jan 26 • 62

upvoted 5 papers about 1 month ago

Test-Time Preference Optimization: On-the-Fly Alignment via Iterative Textual Feedback

Paper • 2501.12895 • Published Jan 22 • 56

DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Paper • 2501.12948 • Published Jan 22 • 333

Inference-Time Scaling for Diffusion Models beyond Scaling Denoising Steps

Paper • 2501.09732 • Published Jan 16 • 70

Diffusion Adversarial Post-Training for One-Step Video Generation

Paper • 2501.08316 • Published Jan 14 • 33

MiniMax-01: Scaling Foundation Models with Lightning Attention

Paper • 2501.08313 • Published Jan 14 • 273