Kyu Song PRO

deepkyu's activity

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

upvoted 3 papers 7 days ago

WorldAuditBench: Interactive 3D World Auditing with Multimodal Agents

Paper • 2609.40325 • Published 9 days ago • 104

Mid-Harness: Scaling Actions Between Model and Harness for Terminal Agents

Paper • 2609.39982 • Published 9 days ago • 119

The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation

Paper • 2609.36484 • Published 10 days ago • 582

published 2 datasets 7 days ago

deepkyu/cosmos3-physicsiq-verified-v2v-prompt-upsampling

Viewer • Updated 7 days ago • 24 • 78

deepkyu/cosmos3-physicsiq-verified-i2v-prompt-upsampling

Viewer • Updated 7 days ago • 24 • 89

updated 2 datasets 7 days ago

deepkyu/cosmos3-physicsiq-verified-v2v-prompt-upsampling

Viewer • Updated 7 days ago • 24 • 78

deepkyu/cosmos3-physicsiq-verified-i2v-prompt-upsampling

Viewer • Updated 7 days ago • 24 • 89

upvoted 2 papers 8 days ago

LEGO-Anything: Coding Agents for 3D Scene Reconstruction

Paper • 2609.36380 • Published 11 days ago • 140

PanoVLN: Towards Effective Panoramic Vision-and-Language Navigation

Paper • 2609.34759 • Published 11 days ago • 168

liked a model 8 days ago

nvidia/SOMA-X

Robotics • Updated 10 days ago • 31

upvoted 3 papers about 1 month ago

FlashRender: Few-Step Generative Rendering via Camera-Controlled Video MeanFlow

Paper • 2609.03563 • Published Sep 3 • 18

WorldReward: Reward Modeling for Camera-Conditioned World Models

Paper • 2609.03952 • Published Sep 3 • 28

Why Gated DeltaNet Survives 4-Bit Quantization: NVFP4 W4A4 for the Recurrent Half of a Hybrid 27B LLM

Paper • 2609.04098 • Published Sep 3 • 86

updated a Space about 1 month ago

Build error

Agents

Featured

563

Talking Face Generation with Multilingual TTS

👄

563

Generate multilingual talking-face videos from your text

upvoted a paper about 2 months ago

Beyond Pixels: From Video Priors to 4D Worlds

Paper • 2608.10744 • Published Aug 11 • 192

upvoted 2 collections 2 months ago

Efficient Stable Diffusion

Collection

Block-removed Knowledge-distilled SD models; https://github.com/Nota-NetsPresso/BK-SDM • 9 items • Updated Jul 1, 2024 • 6

Efficient Solar Open Family

Collection

Solar Open models officially optimized by Nota AI for Korea’s government-led Sovereign AI initiative as part of the Upstage consortium. • 7 items • Updated Aug 31 • 26

liked a model 2 months ago

nota-ai/Solar-Open2-250B-Nota-NVFP4

Text Generation • 145B • Updated Aug 7 • 1.39k • 178

liked a model 5 months ago

HiDream-ai/HiDream-O1-Image

Image-Text-to-Image • 9B • Updated Jun 22 • 4.72k • 553

upvoted a paper 6 months ago

Out of Sight but Not Out of Mind: Hybrid Memory for Dynamic Video World Models

Paper • 2603.25716 • Published Mar 26 • 76