Sichen Liu's picture

23 47

Sichen Liu

Seas0

·

https://seashkey.com

Seas0

AI & ML interests

Diffusion, Flow, Any Generative model

Recent Activity

liked a model 5 days ago

Lightricks/LTX-Video

View all activity

Organizations

None yet

Seas0's activity

upvoted a paper 21 days ago

Parallel Scaling Law for Language Models

Paper • 2505.10475 • Published 23 days ago • 78

upvoted a paper about 2 months ago

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

Paper • 2504.10479 • Published Apr 14 • 268

upvoted a collection about 2 months ago

💫StarVector Models

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 • 96

upvoted 5 papers 3 months ago

FlowTok: Flowing Seamlessly Across Text and Image Tokens

Paper • 2503.10772 • Published Mar 13 • 19

Learning Few-Step Diffusion Models by Trajectory Distribution Matching

Paper • 2503.06674 • Published Mar 9 • 7

Block Diffusion: Interpolating Between Autoregressive and Diffusion Language Models

Paper • 2503.09573 • Published Mar 12 • 72

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

Paper • 2503.00948 • Published Mar 2 • 3

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

Paper • 2502.16894 • Published Feb 24 • 31

upvoted 2 papers 4 months ago

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

Paper • 2411.19108 • Published Nov 28, 2024 • 19

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

Paper • 2501.12895 • Published Jan 22 • 63

upvoted a collection 6 months ago

InternVL2.5

Better than InternVL 2.0 • 19 items • Updated Apr 20 • 90

upvoted a collection 8 months ago

Qwen2.5

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 Apr 28 • 616

upvoted a collection 9 months ago

Qwen2-VL

Vision-language model series based on Qwen2 • 16 items • Updated Apr 28 • 217

upvoted an article 9 months ago

Article

Explaining the SDXL latent space

By

•

May 20, 2024

• 45

upvoted a paper 10 months ago

Transformer Explainer: Interactive Learning of Text-Generative Models

Paper • 2408.04619 • Published Aug 8, 2024 • 162

upvoted 5 papers about 1 year ago

SDXL-Lightning: Progressive Adversarial Diffusion Distillation

Paper • 2402.13929 • Published Feb 21, 2024 • 28

LongRoPE: Extending LLM Context Window Beyond 2 Million Tokens

Paper • 2402.13753 • Published Feb 21, 2024 • 117

Multi-LoRA Composition for Image Generation

Paper • 2402.16843 • Published Feb 26, 2024 • 33

The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits

Paper • 2402.17764 • Published Feb 27, 2024 • 618

InstantID: Zero-shot Identity-Preserving Generation in Seconds

Paper • 2401.07519 • Published Jan 15, 2024 • 58