Dokyoon

leeloolee

Eruly

AI & ML interests

Recent Activity

reacted to Parveshiiii's post with 🔥 2 days ago

🚀 Wanna train your own AI Model or Tokenizer from scratch? Building models isn’t just for big labs anymore — with the right data, compute, and workflow, you can create **custom AI models** and **tokenizers** tailored to any domain. Whether it’s NLP, domain‑specific datasets, or experimental architectures, training from scratch gives you full control over vocabulary, embeddings, and performance. ✨ Why train your own? - Full control over vocabulary & tokenization - Domain‑specific optimization (medical, legal, technical, etc.) - Better performance on niche datasets - Freedom to experiment with architectures ⚡ The best part? - Tokenizer training (TikToken / BPE) can be done in **just 3 lines of code**. - Model training runs smoothly on **Google Colab notebooks** — no expensive hardware required. 📂 Try out my work: - 🔗 https://github.com/OE-Void/Tokenizer-from_scratch - 🔗 https://github.com/OE-Void/GPT

upvoted a paper 2 days ago

VISTA-PATH: An interactive foundation model for pathology image segmentation and quantitative analysis in computational pathology

liked a dataset 2 days ago

Reubencf/2023_events

View all activity

Organizations

upvoted a paper 2 days ago

VISTA-PATH: An interactive foundation model for pathology image segmentation and quantitative analysis in computational pathology

Paper • 2601.16451 • Published 6 days ago • 2

upvoted a paper 3 days ago

Jet-RL: Enabling On-Policy FP8 Reinforcement Learning with Unified Training and Rollout Precision Flow

Paper • 2601.14243 • Published 9 days ago • 18

upvoted a paper 9 days ago

Think-Then-Generate: Reasoning-Aware Text-to-Image Diffusion with LLM Encoders

Paper • 2601.10332 • Published 14 days ago • 28

upvoted a paper 11 days ago

STEP3-VL-10B Technical Report

Paper • 2601.09668 • Published 15 days ago • 189

upvoted 2 papers 17 days ago

VAR RL Done Right: Tackling Asynchronous Policy Conflicts in Visual Autoregressive Generation

Paper • 2601.02256 • Published 24 days ago • 33

Enhancing Inflation Nowcasting with LLM: Sentiment Analysis on News

Paper • 2410.20198 • Published Oct 26, 2024 • 1

upvoted an article 23 days ago

Article

Building Deep Research: How we Achieved State of the Art

Nov 24, 2025

•

upvoted a paper 27 days ago

DiffThinker: Towards Generative Multimodal Reasoning with Diffusion Models

Paper • 2512.24165 • Published 30 days ago • 50

upvoted 5 papers about 1 month ago

MMGR: Multi-Modal Generative Reasoning

Paper • 2512.14691 • Published Dec 16, 2025 • 118

Differences That Matter: Auditing Models for Capability Gap Discovery and Rectification

Paper • 2512.16921 • Published Dec 18, 2025 • 8

Next-Embedding Prediction Makes Strong Vision Learners

Paper • 2512.16922 • Published Dec 18, 2025 • 84

Insight Miner: A Time Series Analysis Dataset for Cross-Domain Alignment with Natural Language

Paper • 2512.11251 • Published Dec 12, 2025 • 8

DiffusionVL: Translating Any Autoregressive Models into Diffusion Vision Language Models

Paper • 2512.15713 • Published Dec 17, 2025 • 17

upvoted 2 papers about 2 months ago

OmniPSD: Layered PSD Generation with Diffusion Transformer

Paper • 2512.09247 • Published Dec 10, 2025 • 46

Qwen3-VL Technical Report

Paper • 2511.21631 • Published Nov 26, 2025 • 151

upvoted a paper 2 months ago

Think-at-Hard: Selective Latent Iterations to Improve Reasoning Language Models

Paper • 2511.08577 • Published Nov 11, 2025 • 107

upvoted an article 3 months ago

Article

Optimizing Mixture-of-Experts Training: A Cost-Effective, Two-Sided Approach

Sep 30, 2025

•

upvoted a paper 3 months ago

Follow the Flow: Fine-grained Flowchart Attribution with Neurosymbolic Agents

Paper • 2506.01344 • Published Jun 2, 2025 • 6

upvoted a collection 3 months ago

LLaDA 2.0

Collection

7 items • Updated 1 day ago • 40

upvoted a paper 4 months ago

THOR: Tool-Integrated Hierarchical Optimization via RL for Mathematical Reasoning

Paper • 2509.13761 • Published Sep 17, 2025 • 16