Seas0 (Sichen Liu)

upvoted a paper 5 months ago

Seed Diffusion: A Large-Scale Diffusion Language Model with High-Speed Inference

Paper • 2508.02193 • Published Aug 4, 2025 • 133

upvoted a collection 7 months ago

Qwen3

Collection

84 items • Updated 4 days ago • 1.54k

upvoted a paper 8 months ago

Parallel Scaling Law for Language Models

Paper • 2505.10475 • Published May 15, 2025 • 83

upvoted a paper 9 months ago

InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models

Paper • 2504.10479 • Published Apr 14, 2025 • 306

upvoted a collection 9 months ago

💫StarVector Models

Collection

StarVector is a multimodal LLM for Scalable Vector Graphics (SVG) generation, producing structured SVG code directly from images and text. • 2 items • Updated Mar 20, 2025 • 96

upvoted 5 papers 10 months ago

FlowTok: Flowing Seamlessly Across Text and Image Tokens

Paper • 2503.10772 • Published Mar 13, 2025 • 19

Learning Few-Step Diffusion Models by Trajectory Distribution Matching

Paper • 2503.06674 • Published Mar 9, 2025 • 8

Block Diffusion: Interpolating Between Autoregressive and Diffusion Language Models

Paper • 2503.09573 • Published Mar 12, 2025 • 74

Extrapolating and Decoupling Image-to-Video Generation Models: Motion Modeling is Easier Than You Think

Paper • 2503.00948 • Published Mar 2, 2025 • 3

Make LoRA Great Again: Boosting LoRA with Adaptive Singular Values and Mixture-of-Experts Optimization Alignment

Paper • 2502.16894 • Published Feb 24, 2025 • 32

upvoted a paper 11 months ago

Timestep Embedding Tells: It's Time to Cache for Video Diffusion Model

Paper • 2411.19108 • Published Nov 28, 2024 • 20

upvoted a paper 12 months ago

Test-Time Preference Optimization: On-the-Fly Alignment via Iterative Textual Feedback

Paper • 2501.12895 • Published Jan 22, 2025 • 61

upvoted a collection about 1 year ago

InternVL2.5

Collection

Better than InternVL 2.0 • 19 items • Updated Sep 28, 2025 • 92

upvoted 2 collections over 1 year ago

Qwen2.5

Collection

Qwen2.5 language models, including pretrained and instruction-tuned models of 7 sizes, including 0.5B, 1.5B, 3B, 7B, 14B, 32B, and 72B. • 46 items • Updated 4 days ago • 672

Qwen2-VL

Collection

Vision-language model series based on Qwen2 • 16 items • Updated 4 days ago • 227

upvoted an article over 1 year ago

Article

Explaining the SDXL latent space

May 20, 2024

•

52

upvoted a paper over 1 year ago

Transformer Explainer: Interactive Learning of Text-Generative Models

Paper • 2408.04619 • Published Aug 8, 2024 • 174

upvoted 3 papers almost 2 years ago

Sichen Liu

AI & ML interests

Organizations

Seed Diffusion: A Large-Scale Diffusion Language Model with High-Speed Inference

Qwen3

Parallel Scaling Law for Language Models

InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models

💫StarVector Models

FlowTok: Flowing Seamlessly Across Text and Image Tokens

Learning Few-Step Diffusion Models by Trajectory Distribution Matching

Block Diffusion: Interpolating Between Autoregressive and Diffusion Language Models

Extrapolating and Decoupling Image-to-Video Generation Models: Motion Modeling is Easier Than You Think

Make LoRA Great Again: Boosting LoRA with Adaptive Singular Values and Mixture-of-Experts Optimization Alignment

Timestep Embedding Tells: It's Time to Cache for Video Diffusion Model

Test-Time Preference Optimization: On-the-Fly Alignment via Iterative Textual Feedback

InternVL2.5

Qwen2.5

Qwen2-VL

Explaining the SDXL latent space

Transformer Explainer: Interactive Learning of Text-Generative Models

SDXL-Lightning: Progressive Adversarial Diffusion Distillation

LongRoPE: Extending LLM Context Window Beyond 2 Million Tokens

Multi-LoRA Composition for Image Generation

Sichen Liu

AI & ML interests

Organizations

Seas0's activity

Explaining the SDXL latent space