Hoigi Seo

Agorium's activity

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

authored a paper 8 days ago

Upsample What Matters: Region-Adaptive Latent Sampling for Accelerated Diffusion Transformers

Paper • 2507.08422 • Published 20 days ago • 35

upvoted a paper 8 days ago

Upsample What Matters: Region-Adaptive Latent Sampling for Accelerated Diffusion Transformers

Paper • 2507.08422 • Published 20 days ago • 35

commented a paper 8 days ago

Upsample What Matters: Region-Adaptive Latent Sampling for Accelerated Diffusion Transformers

Paper • 2507.08422 • Published 20 days ago • 35 •

5

upvoted 2 papers 9 days ago

EXAONE 4.0: Unified Large Language Models Integrating Non-reasoning and Reasoning Modes

Paper • 2507.11407 • Published 15 days ago • 51

Robust 3D-Masked Part-level Editing in 3D Gaussian Splatting with Regularized Score Distillation Sampling

Paper • 2507.11061 • Published 16 days ago • 37

upvoted a paper about 2 months ago

Revisit What You See: Disclose Language Prior in Vision Tokens for Efficient Guided Decoding of LVLMs

Paper • 2506.09522 • Published Jun 11 • 20

upvoted a paper 4 months ago

DDT: Decoupled Diffusion Transformer

Paper • 2504.05741 • Published Apr 8 • 76

authored a paper 4 months ago

Efficient Personalization of Quantized Diffusion Model without Backpropagation

Paper • 2503.14868 • Published Mar 19 • 20

upvoted a paper 4 months ago

Efficient Personalization of Quantized Diffusion Model without Backpropagation

Paper • 2503.14868 • Published Mar 19 • 20

commented a paper 4 months ago

Efficient Personalization of Quantized Diffusion Model without Backpropagation

Paper • 2503.14868 • Published Mar 19 • 20 •

2

upvoted 3 papers 5 months ago

PLADIS: Pushing the Limits of Attention in Diffusion Models at Inference Time by Leveraging Sparsity

Paper • 2503.07677 • Published Mar 10 • 87

Kanana: Compute-efficient Bilingual Language Models

Paper • 2502.18934 • Published Feb 26 • 66

SLEB: Streamlining LLMs through Redundancy Verification and Elimination of Transformer Blocks

Paper • 2402.09025 • Published Feb 14, 2024 • 9

authored a paper 6 months ago

Skrr: Skip and Re-use Text Encoder Layers for Memory Efficient Text-to-Image Generation

Paper • 2502.08690 • Published Feb 12 • 44

upvoted 2 papers 6 months ago

BeyondScene: Higher-Resolution Human-Centric Scene Generation With Pretrained Diffusion

Paper • 2404.04544 • Published Apr 6, 2024 • 24

Skrr: Skip and Re-use Text Encoder Layers for Memory Efficient Text-to-Image Generation

Paper • 2502.08690 • Published Feb 12 • 44

commented a paper 6 months ago

Skrr: Skip and Re-use Text Encoder Layers for Memory Efficient Text-to-Image Generation

Paper • 2502.08690 • Published Feb 12 • 44 •

2

upvoted 3 papers 6 months ago

Weak-to-Strong Diffusion with Reflection

Paper • 2502.00473 • Published Feb 1 • 23

FastKV: KV Cache Compression for Fast Long-Context Processing with Token-Selective Propagation

Paper • 2502.01068 • Published Feb 3 • 17

Inference-Time Scaling for Diffusion Models beyond Scaling Denoising Steps

Paper • 2501.09732 • Published Jan 16 • 72