SeongWan Kim's picture

22

SeongWan Kim

idgmatrix

AI & ML interests

None yet

Organizations

None yet

idgmatrix's activity

upvoted a paper about 20 hours ago

Scaling Laws with Vocabulary: Larger Models Deserve Larger Vocabularies

Paper • 2407.13623 • Published 4 days ago • 39

upvoted a paper 6 days ago

GRUtopia: Dream General Robots in a City at Scale

Paper • 2407.10943 • Published 7 days ago • 20

upvoted a paper 8 days ago

Transformer Layers as Painters

Paper • 2407.09298 • Published 10 days ago • 12

upvoted a paper 9 days ago

Vision language models are blind

Paper • 2407.06581 • Published 14 days ago • 73

upvoted 4 papers 15 days ago

Agentless: Demystifying LLM-based Software Engineering Agents

Paper • 2407.01489 • Published 21 days ago • 41

Magic Insert: Style-Aware Drag-and-Drop

Paper • 2407.02489 • Published 20 days ago • 17

PicoAudio: Enabling Precise Timestamp and Frequency Controllability of Audio Events in Text-to-audio Generation

Paper • 2407.02869 • Published 20 days ago • 15

No Training, No Problem: Rethinking Classifier-Free Guidance for Diffusion Models

Paper • 2407.02687 • Published 20 days ago • 20

upvoted a paper 20 days ago

RealTalk: Real-time and Realistic Audio-driven Face Generation with 3D Facial Prior-guided Identity Alignment Network

Paper • 2406.18284 • Published 26 days ago • 17

upvoted 2 papers 21 days ago

Scaling Synthetic Data Creation with 1,000,000,000 Personas

Paper • 2406.20094 • Published 24 days ago • 84

E2 TTS: Embarrassingly Easy Fully Non-Autoregressive Zero-Shot TTS

Paper • 2406.18009 • Published 27 days ago • 18

upvoted 3 papers about 1 month ago

Autoregressive Model Beats Diffusion: Llama for Scalable Image Generation

Paper • 2406.06525 • Published Jun 10 • 62

Depth Anything V2

Paper • 2406.09414 • Published Jun 13 • 88

Make It Count: Text-to-Image Generation with an Accurate Number of Objects

Paper • 2406.10210 • Published Jun 14 • 75

upvoted an article about 1 month ago

Article

Fish Speech V1 - New Multilingual Open Source TTS Model

By

•

May 3

• 10

upvoted 3 papers about 2 months ago

Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality

Paper • 2405.21060 • Published May 31 • 61

Transformers Can Do Arithmetic with the Right Embeddings

Paper • 2405.17399 • Published May 27 • 50

Phased Consistency Model

Paper • 2405.18407 • Published May 28 • 44

upvoted a paper 10 months ago

Emu: Enhancing Image Generation Models Using Photogenic Needles in a Haystack

Paper • 2309.15807 • Published Sep 27, 2023 • 30

upvoted 3 papers about 1 year ago

Unleashing Cognitive Synergy in Large Language Models: A Task-Solving Agent through Multi-Persona Self-Collaboration

Paper • 2307.05300 • Published Jul 11, 2023 • 18

Collaborative Score Distillation for Consistent Visual Synthesis

Paper • 2307.04787 • Published Jul 4, 2023 • 27

SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis

Paper • 2307.01952 • Published Jul 4, 2023 • 78