SeongWan Kim

idgmatrix's activity

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

upvoted a paper about 15 hours ago

TriAttention: Efficient Long Reasoning with Trigonometric KV Compression

Paper • 2604.04921 • Published 2 days ago • 64

upvoted a paper about 23 hours ago

Do LLMs "Feel"? Emotion Circuits Discovery and Control

Paper • 2510.11328 • Published Oct 13, 2025 • 6

upvoted a paper 5 days ago

DynaVid: Learning to Generate Highly Dynamic Videos using Synthetic Motion Data

Paper • 2604.01666 • Published 6 days ago • 8

upvoted a paper 7 days ago

Extend3D: Town-Scale 3D Generation

Paper • 2603.29387 • Published 8 days ago • 24

upvoted 2 papers 9 days ago

Sommelier: Scalable Open Multi-turn Audio Pre-processing for Full-duplex Speech Language Models

Paper • 2603.25750 • Published 19 days ago • 35

Representation Alignment for Just Image Transformers is not Easier than You Think

Paper • 2603.14366 • Published 23 days ago • 13

upvoted a paper 20 days ago

InCoder-32B: Code Foundation Model for Industrial Scenarios

Paper • 2603.16790 • Published 21 days ago • 307

upvoted 3 papers 22 days ago

Attention Residuals

Paper • 2603.15031 • Published 23 days ago • 176

AI Can Learn Scientific Taste

Paper • 2603.14473 • Published 23 days ago • 416

Grounding World Simulation Models in a Real-World Metropolis

Paper • 2603.15583 • Published 22 days ago • 153

upvoted 2 papers about 1 month ago

GLM-5: from Vibe Coding to Agentic Engineering

Paper • 2602.15763 • Published Feb 17 • 126

Unified Latents (UL): How to train your latents

Paper • 2602.17270 • Published Feb 19 • 60

upvoted a paper 2 months ago

Advancing Open-source World Models

Paper • 2601.20540 • Published Jan 28 • 134

upvoted a collection 2 months ago

Qwen3-TTS

Collection

7 items • Updated Jan 22 • 342

upvoted 6 papers 3 months ago

Solar Open Technical Report

Paper • 2601.07022 • Published Jan 11 • 66

Ministral 3

Paper • 2601.08584 • Published Jan 13 • 60

User-Oriented Multi-Turn Dialogue Generation with Tool Use at scale

Paper • 2601.08225 • Published Jan 13 • 53

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

Paper • 2601.05242 • Published Jan 8 • 230

LTX-Video: Realtime Video Latent Diffusion

Paper • 2501.00103 • Published Dec 30, 2024 • 50

LTX-2: Efficient Joint Audio-Visual Foundation Model

Paper • 2601.03233 • Published Jan 6 • 175