alfredplpl (Yasunori Ozaki)

upvoted a paper 2 days ago

VILA^2: VILA Augmented VILA

Paper • 2407.17453 • Published 3 days ago • 31

upvoted a paper 10 days ago

Scaling Diffusion Transformers to 16 Billion Parameters

Paper • 2407.11633 • Published 11 days ago • 22

upvoted 2 papers 16 days ago

Graph-Based Captioning: Enhancing Visual Descriptions by Interconnecting Region Captions

Paper • 2407.06723 • Published 18 days ago • 9

Inference Performance Optimization for Large Language Models on CPUs

Paper • 2407.07304 • Published 17 days ago • 48

upvoted a collection 22 days ago

CommonCatalog

Collection

Common Catalog, a dataset with Creative Commons licensed images and machine-generated caption pairs • 8 items • Updated May 16 • 13

upvoted a collection 30 days ago

Gemma 2 Release

Collection

10 items • Updated 2 days ago • 132

upvoted an article about 1 month ago

Article

Fine-tuning Florence-2 - Microsoft's Cutting-edge Vision Language Models

Jun 24

• 149

upvoted a paper about 1 month ago

MMWorld: Towards Multi-discipline Multi-faceted World Model Evaluation in Videos

Paper • 2406.08407 • Published Jun 12 • 24

upvoted an article about 1 month ago

Article

🧨 Diffusers welcomes Stable Diffusion 3

Jun 12

• 78

upvoted a paper about 1 month ago

What If We Recaption Billions of Web Images with LLaMA-3?

Paper • 2406.08478 • Published Jun 12 • 38

upvoted 3 papers about 2 months ago

Autoregressive Model Beats Diffusion: Llama for Scalable Image Generation

Paper • 2406.06525 • Published Jun 10 • 62

MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark

Paper • 2406.01574 • Published Jun 3 • 42

Kaleido Diffusion: Improving Conditional Diffusion Models with Autoregressive Latent Modeling

Paper • 2405.21048 • Published May 31 • 11

upvoted a paper 2 months ago

CommonCanvas: An Open Diffusion Model Trained with Creative-Commons Images

Paper • 2310.16825 • Published Oct 25, 2023 • 30

upvoted a collection 2 months ago

Trained on AWS Trainium

Collection

Collection of models on Hugging Face that have been trained on AWS Trainium. Learn more here: https://huggingface.co/docs/optimum-neuron/index • 7 items • Updated May 7 • 6

upvoted 3 papers 3 months ago

Revisiting Text-to-Image Evaluation with Gecko: On Metrics, Prompts, and Human Ratings

Paper • 2404.16820 • Published Apr 25 • 15

Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone

Paper • 2404.14219 • Published Apr 22 • 243

PhysDreamer: Physics-Based Interaction with 3D Objects via Video Generation

Paper • 2404.13026 • Published Apr 19 • 21

upvoted 5 papers 4 months ago

On the Scalability of Diffusion-based Text-to-Image Generation

Paper • 2404.02883 • Published Apr 3 • 17

Bigger is not Always Better: Scaling Properties of Latent Diffusion Models

Paper • 2404.01367 • Published Apr 1 • 19

Aurora-M: The First Open Source Multilingual Language Model Red-teamed according to the U.S. Executive Order

Paper • 2404.00399 • Published Mar 30 • 40

Are We on the Right Way for Evaluating Large Vision-Language Models?

Paper • 2403.20330 • Published Mar 29 • 6

MM1: Methods, Analysis & Insights from Multimodal LLM Pre-training

Paper • 2403.09611 • Published Mar 14 • 123

upvoted 7 papers 5 months ago

Algorithmic progress in language models

Paper • 2403.05812 • Published Mar 9 • 17

Synth^2: Boosting Visual-Language Models with Synthetic Captions and Image Embeddings

Paper • 2403.07750 • Published Mar 12 • 19

GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection

Paper • 2403.03507 • Published Mar 6 • 180

Sora: A Review on Background, Technology, Limitations, and Opportunities of Large Vision Models

Paper • 2402.17177 • Published Feb 27 • 88

upvoted 4 papers 6 months ago

Machine Unlearning for Image-to-Image Generative Models

Paper • 2402.00351 • Published Feb 1 • 11

MobileDiffusion: Subsecond Text-to-Image Generation on Mobile Devices

Paper • 2311.16567 • Published Nov 28, 2023 • 22

MoE-LLaVA: Mixture of Experts for Large Vision-Language Models

Paper • 2401.15947 • Published Jan 29 • 48

Lumiere: A Space-Time Diffusion Model for Video Generation

Paper • 2401.12945 • Published Jan 23 • 85

upvoted 4 papers 7 months ago

VideoPoet: A Large Language Model for Zero-Shot Video Generation

Paper • 2312.14125 • Published Dec 21, 2023 • 43

Fairy: Fast Parallelized Instruction-Guided Video-to-Video Synthesis

Paper • 2312.13834 • Published Dec 20, 2023 • 26

StreamDiffusion: A Pipeline-level Solution for Real-time Interactive Generation

Paper • 2312.12491 • Published Dec 19, 2023 • 67

StarVector: Generating Scalable Vector Graphics Code from Images

Paper • 2312.11556 • Published Dec 17, 2023 • 26

upvoted 12 papers 8 months ago

VideoLCM: Video Latent Consistency Model

Paper • 2312.09109 • Published Dec 14, 2023 • 22

DiffMorpher: Unleashing the Capability of Diffusion Models for Image Morphing

Paper • 2312.07409 • Published Dec 12, 2023 • 22

ECLIPSE: A Resource-Efficient Text-to-Image Prior for Image Generations

Paper • 2312.04655 • Published Dec 7, 2023 • 19

Sherpa3D: Boosting High-Fidelity Text-to-3D Generation via Coarse 3D Prior

Paper • 2312.06655 • Published Dec 11, 2023 • 21

Beyond Human Data: Scaling Self-Training for Problem-Solving with Language Models

Paper • 2312.06585 • Published Dec 11, 2023 • 27

Evaluation of Large Language Models for Decision Making in Autonomous Driving

Paper • 2312.06351 • Published Dec 11, 2023 • 5

Photorealistic Video Generation with Diffusion Models

Paper • 2312.06662 • Published Dec 11, 2023 • 23

Efficient Quantization Strategies for Latent Diffusion Models

Paper • 2312.05431 • Published Dec 9, 2023 • 11

DreaMoving: A Human Dance Video Generation Framework based on Diffusion Models

Paper • 2312.05107 • Published Dec 8, 2023 • 36

Analyzing and Improving the Training Dynamics of Diffusion Models

Paper • 2312.02696 • Published Dec 5, 2023 • 31

Using Human Feedback to Fine-tune Diffusion Models without Any Reward Model

Paper • 2311.13231 • Published Nov 22, 2023 • 25

UFOGen: You Forward Once Large Scale Text-to-Image Generation via Diffusion GANs

Paper • 2311.09257 • Published Nov 14, 2023 • 43

upvoted 10 papers 9 months ago

Q-Instruct: Improving Low-level Visual Abilities for Multi-modality Foundation Models

Paper • 2311.06783 • Published Nov 12, 2023 • 26

On the Road with GPT-4V(ision): Early Explorations of Visual-Language Model on Autonomous Driving

Paper • 2311.05332 • Published Nov 9, 2023 • 7

LCM-LoRA: A Universal Stable-Diffusion Acceleration Module

Paper • 2311.05556 • Published Nov 9, 2023 • 78

OtterHD: A High-Resolution Multi-modality Model

Paper • 2311.04219 • Published Nov 7, 2023 • 31

I2VGen-XL: High-Quality Image-to-Video Synthesis via Cascaded Diffusion Models

Paper • 2311.04145 • Published Nov 7, 2023 • 31

LLaVA-Interactive: An All-in-One Demo for Image Chat, Segmentation, Generation and Editing

Paper • 2311.00571 • Published Nov 1, 2023 • 40

Beyond U: Making Diffusion Models Faster & Lighter

Paper • 2310.20092 • Published Oct 31, 2023 • 11

CapsFusion: Rethinking Image-Text Data at Scale

Paper • 2310.20550 • Published Oct 31, 2023 • 25

An Early Evaluation of GPT-4V(ision)

Paper • 2310.16534 • Published Oct 25, 2023 • 21

Matryoshka Diffusion Models

Paper • 2310.15111 • Published Oct 23, 2023 • 39

Yasunori Ozaki PRO

AI & ML interests

Organizations

alfredplpl's activity

Fine-tuning Florence-2 - Microsoft's Cutting-edge Vision Language Models

🧨 Diffusers welcomes Stable Diffusion 3