Kyu Song

kyunocap's activity

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

upvoted a paper about 3 hours ago

DreamDojo: A Generalist Robot World Model from Large-Scale Human Videos

Paper • 2602.06949 • Published 14 days ago • 34

upvoted 2 papers about 5 hours ago

SpargeAttention2: Trainable Sparse Attention via Hybrid Top-k+Top-p Masking and Distillation Fine-Tuning

Paper • 2602.13515 • Published 7 days ago • 23

Unified Latents (UL): How to train your latents

Paper • 2602.17270 • Published 1 day ago • 21

upvoted a paper about 6 hours ago

DDiT: Dynamic Patch Scheduling for Efficient Diffusion Transformers

Paper • 2602.16968 • Published 2 days ago • 9

upvoted 3 papers 2 days ago

jina-embeddings-v5-text: Task-Targeted Embedding Distillation

Paper • 2602.15547 • Published 3 days ago • 19

UniT: Unified Multimodal Chain-of-Thought Test-time Scaling

Paper • 2602.12279 • Published 8 days ago • 19

SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Tasks

Paper • 2602.12670 • Published 8 days ago • 46

liked a model 8 days ago

yaolily/TimeChat-Captioner-GRPO-7B

Video-Text-to-Text • 9B • Updated 10 days ago • 136 • 1

upvoted a paper 16 days ago

3D-Aware Implicit Motion Control for View-Adaptive Human Video Generation

Paper • 2602.03796 • Published 17 days ago • 57

upvoted an article 23 days ago

view article

Article

We Got Claude to Build CUDA Kernels and teach open models!

• 
• 
• +2

24 days ago

•

138

upvoted a paper 29 days ago

Agentic Reasoning for Large Language Models

Paper • 2601.12538 • Published Jan 18 • 195

upvoted 2 papers about 1 month ago

LTX-2: Efficient Joint Audio-Visual Foundation Model

Paper • 2601.03233 • Published Jan 6 • 154

OpenVoxel: Training-Free Grouping and Captioning Voxels for Open-Vocabulary 3D Scene Understanding

Paper • 2601.09575 • Published Jan 14 • 26

liked a model about 1 month ago

lovis93/next-scene-qwen-image-lora-2509

Image-to-Image • Updated Oct 21, 2025 • 36.4k • • 576

liked a Space about 1 month ago

Running on Zero

Featured

206

LTX-2 Video Fast

🎥

206

Fast high quality video with audio generation

upvoted 3 papers about 1 month ago

GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimization

Paper • 2601.05242 • Published Jan 8 • 226

Thinking with Map: Reinforced Parallel Map-Augmented Agent for Geolocalization

Paper • 2601.05432 • Published Jan 8 • 166

InfiniDepth: Arbitrary-Resolution and Fine-Grained Depth Estimation with Neural Implicit Fields

Paper • 2601.03252 • Published Jan 6 • 101

liked a model 2 months ago

facebook/pe-av-large

Updated 22 days ago • 1k • 51

upvoted a paper 2 months ago

EgoX: Egocentric Video Generation from a Single Exocentric Video

Paper • 2512.08269 • Published Dec 9, 2025 • 119