Sylvestre Bcht's picture

Sylvestre Bcht

Sylvestre

·

Kakulukian

AI & ML interests

None yet

Articles

Deprecation of Git Authentication using password

Introducing DOI: the Digital Object Identifier to Datasets and Models

Organizations

Sylvestre's activity

upvoted a paper 17 days ago

Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusion

Paper • 2407.01392 • Published 21 days ago • 39

upvoted a paper 20 days ago

LiteSearch: Efficacious Tree Search for LLM

Paper • 2407.00320 • Published 23 days ago • 37

upvoted a paper 25 days ago

The FineWeb Datasets: Decanting the Web for the Finest Text Data at Scale

Paper • 2406.17557 • Published 27 days ago • 75

upvoted 6 papers about 1 month ago

Hierarchical Patch Diffusion Models for High-Resolution Video Generation

Paper • 2406.07792 • Published Jun 12 • 13

AV-DiT: Efficient Audio-Visual Diffusion Transformer for Joint Audio and Video Generation

Paper • 2406.07686 • Published Jun 11 • 13

Magpie: Alignment Data Synthesis from Scratch by Prompting Aligned LLMs with Nothing

Paper • 2406.08464 • Published Jun 12 • 49

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

Paper • 2406.08407 • Published Jun 12 • 24

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

Paper • 2406.08478 • Published Jun 12 • 38

Zero-shot Image Editing with Reference Imitation

Paper • 2406.07547 • Published Jun 11 • 30

upvoted a paper about 2 months ago

MOFA-Video: Controllable Image Animation via Generative Motion Field Adaptions in Frozen Image-to-Video Diffusion Model

Paper • 2405.20222 • Published May 30 • 10

upvoted an article about 2 months ago

Article

AI has a problem with objectifying women

By

•

May 24

• 54

upvoted a collection 3 months ago

Common Corpus

The largest public domain dataset for training LLMs. • 27 items • Updated 5 days ago • 107

upvoted a paper 3 months ago

Rho-1: Not All Tokens Are What You Need

Paper • 2404.07965 • Published Apr 11 • 80

upvoted a collection 4 months ago

From screenshots to HTML

WebSight is a dataset of 823,000 HTML/CSS codes representing synthetically generated English websites, each accompanied by a corresponding screenshot. • 4 items • Updated Apr 15 • 17

upvoted a paper 4 months ago

Unlocking the conversion of Web Screenshots into HTML Code with the WebSight Dataset

Paper • 2403.09029 • Published Mar 14 • 54

upvoted a paper 5 months ago

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

Paper • 2403.03507 • Published Mar 6 • 180

upvoted a paper 7 months ago

StarVector: Generating Scalable Vector Graphics Code from Images

Paper • 2312.11556 • Published Dec 17, 2023 • 26

upvoted 5 papers 8 months ago

MeshGPT: Generating Triangle Meshes with Decoder-Only Transformers

Paper • 2311.15475 • Published Nov 27, 2023 • 2

FeedRec: News Feed Recommendation with Various User Feedbacks

Paper • 2102.04903 • Published Feb 9, 2021 • 2

GAIA: a benchmark for General AI Assistants

Paper • 2311.12983 • Published Nov 21, 2023 • 176

The Chosen One: Consistent Characters in Text-to-Image Diffusion Models

Paper • 2311.10093 • Published Nov 16, 2023 • 55

LCM-LoRA: A Universal Stable-Diffusion Acceleration Module

Paper • 2311.05556 • Published Nov 9, 2023 • 78

upvoted a collection 8 months ago

SVG Collection

Collection of SVG files from various sources. • 7 items • Updated Oct 22, 2023 • 5

upvoted 2 collections 9 months ago

CoEdIT

Collection of the publicly available CoEdIT dataset and instruction-tuned models for text editing. • 6 items • Updated Apr 15 • 5

Geospatial Datasets

Geospatial datases on the Hub. If you want to submit more items to this collection, please request to join the geospatial organisation. • 9 items • Updated Nov 7, 2023 • 9

upvoted 5 papers 9 months ago

Distil-Whisper: Robust Knowledge Distillation via Large-Scale Pseudo Labelling

Paper • 2311.00430 • Published Nov 1, 2023 • 54

Hierarchical Neural Coding for Controllable CAD Model Generation

Paper • 2307.00149 • Published Jun 30, 2023 • 2

SkexGen: Autoregressive Generation of CAD Construction Sequences with Disentangled Codebooks

Paper • 2207.04632 • Published Jul 11, 2022 • 2

VectorFusion: Text-to-SVG by Abstracting Pixel-Based Diffusion Models

Paper • 2211.11319 • Published Nov 21, 2022 • 5

IconShop: Text-Guided Vector Icon Synthesis with Autoregressive Transformers

Paper • 2304.14400 • Published Apr 27, 2023 • 4

upvoted a collection 10 months ago

DistilBERT release

Original DistilBERT model, checkpoints obtained from using teacher-student learning from the original BERT checkpoints. • 6 items • Updated Apr 17 • 12

upvoted a paper 12 months ago

TokenFlow: Consistent Diffusion Features for Consistent Video Editing

Paper • 2307.10373 • Published Jul 19, 2023 • 55

upvoted 13 papers about 1 year ago

Retentive Network: A Successor to Transformer for Large Language Models

Paper • 2307.08621 • Published Jul 17, 2023 • 169

LEDITS: Real Image Editing with DDPM Inversion and Semantic Guidance

Paper • 2307.00522 • Published Jul 2, 2023 • 29

OBELICS: An Open Web-Scale Filtered Dataset of Interleaved Image-Text Documents

Paper • 2306.16527 • Published Jun 21, 2023 • 44

Extending Context Window of Large Language Models via Positional Interpolation

Paper • 2306.15595 • Published Jun 27, 2023 • 53

MIMIC: Masked Image Modeling with Image Correspondences

Paper • 2306.15128 • Published Jun 27, 2023 • 7

MagicBrush: A Manually Annotated Dataset for Instruction-Guided Image Editing

Paper • 2306.10012 • Published Jun 16, 2023 • 34

The RefinedWeb Dataset for Falcon LLM: Outperforming Curated Corpora with Web Data, and Web Data Only

Paper • 2306.01116 • Published Jun 1, 2023 • 30

WizardCoder: Empowering Code Large Language Models with Evol-Instruct

Paper • 2306.08568 • Published Jun 14, 2023 • 28

Knowledge Distillation of Large Language Models

Paper • 2306.08543 • Published Jun 14, 2023 • 18

Hidden Biases of End-to-End Driving Models

Paper • 2306.07957 • Published Jun 13, 2023 • 4

SnapFusion: Text-to-Image Diffusion Model on Mobile Devices within Two Seconds

Paper • 2306.00980 • Published Jun 1, 2023 • 14

HuggingFace's Transformers: State-of-the-art Natural Language Processing

Paper • 1910.03771 • Published Oct 9, 2019 • 16

DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter

Paper • 1910.01108 • Published Oct 2, 2019 • 12