ldwang's picture

ldwang

ldwang

·

ftgreat

AI & ML interests

LLM, MLLM, Infra

Recent Activity

upvoted a paper about 2 hours ago

Uniform Discrete Diffusion with Metric Path for Video Generation

upvoted a collection 1 day ago

Reasoning Efficiency Research

liked a model 1 day ago

nvidia/omnivinci

View all activity

Organizations

upvoted a paper about 2 hours ago

Uniform Discrete Diffusion with Metric Path for Video Generation

Paper • 2510.24717 • Published 1 day ago • 35

upvoted a collection 1 day ago

Reasoning Efficiency Research

Ultra-efficient reasoning model! SOTA Accuracy / CoT Length trade-offs • 3 items • Updated 6 days ago • 7

upvoted an article 1 day ago

Article

设计位置编码

Nov 25, 2024

• 7

upvoted an article 2 days ago

Article

`LeRobotDataset`: Bringing large-scale datasets to lerobot

Sep 16

• 44

upvoted a paper 4 days ago

Glyph: Scaling Context Windows via Visual-Text Compression

Paper • 2510.17800 • Published 9 days ago • 61

upvoted an article 5 days ago

Article

Supercharge your OCR Pipelines with Open Models

9 days ago

• 211

upvoted a paper 10 days ago

CommonForms: A Large, Diverse Dataset for Form Field Detection

Paper • 2509.16506 • Published Sep 20 • 18

upvoted a collection 14 days ago

The Ultimate Collection of Code Classifiers

🔥 15 classifiers, 124M parameters, one per programming language— for assessing the educational value of GitHub code • 15 items • Updated May 5 • 15

upvoted a paper 14 days ago

EditScore: Unlocking Online RL for Image Editing via High-Fidelity Reward Modeling

Paper • 2509.23909 • Published Sep 28 • 30

upvoted 2 collections 14 days ago

DataDecide

A suite of models, data, and evals over 25 corpora, 14 sizes, and 3 seeds to measure how accurately small experiments predict rankings at large scale. • 358 items • Updated Apr 30 • 21

MolmoAct

All models for the MolmoAct (Multimodal Open Language Model for Action) release. • 10 items • Updated Sep 6 • 29

upvoted a paper 22 days ago

MixtureVitae: Open Web-Scale Pretraining Dataset With High Quality Instruction and Reasoning Data Built from Permissive-First Text Sources

Paper • 2509.25531 • Published about 1 month ago • 7

upvoted a paper 26 days ago

LLaVA-OneVision-1.5: Fully Open Framework for Democratized Multimodal Training

Paper • 2509.23661 • Published Sep 28 • 44

upvoted a collection 26 days ago

Qwen3-VL

25 items • Updated 9 days ago • 337

upvoted 2 papers about 1 month ago

FlagEval Findings Report: A Preliminary Evaluation of Large Reasoning Models on Automatically Verifiable Textual and Visual Questions

Paper • 2509.17177 • Published Sep 21 • 13

Aguvis: Unified Pure Vision Agents for Autonomous GUI Interaction

Paper • 2412.04454 • Published Dec 5, 2024 • 70

upvoted a collection about 1 month ago

smol2operator Release

4 items • Updated Sep 23 • 21

upvoted 2 articles about 1 month ago

Article

Smol2Operator: Post-Training GUI Agents for Computer Use

Sep 23

• 123

Article

📢 NVIDIA Releases Nemotron-CC-Math Pre-Training Dataset: A High-Quality, Web-Scale Math Corpus for Pretraining Large Language Models

By

and 1 other •

Aug 18

• 5

upvoted a paper about 1 month ago

Towards A Generalist Code Embedding Model Based On Massive Data Synthesis

Paper • 2505.12697 • Published May 19 • 2