21 36 62

Tony Wu

tonywu71

AI & ML interests

LLM, Multimodal, Agents, Information Retrieval, RAG, Speech

Recent Activity

liked a Space about 1 month ago

HuggingFaceFW/finephrase

upvoted an article about 2 months ago

Mixture of Experts (MoEs) in Transformers

upvoted an article 2 months ago

LateOn-Code & ColGrep: LightOn unveils state-of-the-art code retrieval models and code search tooling

View all activity

Organizations

upvoted an article about 2 months ago

Article

Mixture of Experts (MoEs) in Transformers

Feb 26

•

154

upvoted an article 2 months ago

Article

LateOn-Code & ColGrep: LightOn unveils state-of-the-art code retrieval models and code search tooling

Feb 12

•

upvoted 2 articles 5 months ago

Article

Transformers v5: Simple model definitions powering the AI ecosystem

Dec 1, 2025

•

309

Article

Continuous batching from first principles

Nov 25, 2025

•

359

upvoted a paper 6 months ago

Surfer 2: The Next Generation of Cross-Platform Computer Use Agents

Paper • 2510.19949 • Published Oct 22, 2025 • 38

upvoted a collection 7 months ago

Holo1.5

Collection

Holo1.5 - Open Foundation Models for Computer Use Agents • 5 items • Updated Sep 15, 2025 • 35

upvoted 3 articles 9 months ago

Article

You could have designed state of the art positional encoding

Nov 25, 2024

•

467

Article

Merge Large Language Models with mergekit

Jan 9, 2024

•

154

Article

SmolLM3: smol, multilingual, long-context reasoner

Jul 8, 2025

•

769

upvoted a collection 11 months ago

Holo1

Collection

Vision-Language Action Model for use in Surfer-H web navigation agent • 6 items • Updated Jun 10, 2025 • 49

upvoted 3 articles 11 months ago

Article

nanoVLM: The simplest repository to train your VLM in pure PyTorch

May 21, 2025

•

255

Article

Preference Optimization for Vision Language Models

Jul 10, 2024

•

Article

Vision Language Models (Better, faster, stronger)

May 12, 2025

•

606

upvoted an article 12 months ago

Article

Gotchas in Tokenizer Behavior Every Developer Should Know

Apr 18, 2025

•

upvoted 2 papers about 1 year ago

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

Paper • 2504.10479 • Published Apr 14, 2025 • 308

SmolVLM: Redefining small and efficient multimodal models

Paper • 2504.05299 • Published Apr 7, 2025 • 207

upvoted 2 articles about 1 year ago

Article

ViDoRe Benchmark V2: Raising the Bar for Visual Retrieval

Mar 18, 2025

•

Article

Fine-tune Llama 3.1 Ultra-Efficiently with Unsloth

Jul 29, 2024

•

370

upvoted a paper about 1 year ago

SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features

Paper • 2502.14786 • Published Feb 20, 2025 • 164

upvoted an article about 1 year ago

Article

SigLIP 2: A better multilingual vision language encoder

Feb 21, 2025

•

210

Tony Wu

AI & ML interests

Recent Activity

Organizations

tonywu71's activity

Mixture of Experts (MoEs) in Transformers

LateOn-Code & ColGrep: LightOn unveils state-of-the-art code retrieval models and code search tooling

Transformers v5: Simple model definitions powering the AI ecosystem

Continuous batching from first principles

You could have designed state of the art positional encoding

Merge Large Language Models with mergekit

SmolLM3: smol, multilingual, long-context reasoner

nanoVLM: The simplest repository to train your VLM in pure PyTorch

Preference Optimization for Vision Language Models

Vision Language Models (Better, faster, stronger)

Gotchas in Tokenizer Behavior Every Developer Should Know

ViDoRe Benchmark V2: Raising the Bar for Visual Retrieval

Fine-tune Llama 3.1 Ultra-Efficiently with Unsloth

SigLIP 2: A better multilingual vision language encoder