Thomas Liang's picture

Thomas Liang PRO

thliang01

·

https://ating.dev/

thliang01

AI & ML interests

Efficient ML, diffusion model, LLM, post-training

Recent Activity

liked a dataset 4 days ago

VisTai/vistw-mcq

liked a model 9 days ago

moonshotai/Kimi-K2-Thinking

liked a dataset 10 days ago

ntuai/multi-tw

View all activity

Organizations

upvoted an article 10 days ago

Article

Fast LoRA inference for Flux with Diffusers and PEFT

Jul 23

•

50

upvoted a paper 12 days ago

INT v.s. FP: A Comprehensive Study of Fine-Grained Low-bit Quantization Formats

Paper • 2510.25602 • Published 17 days ago • 68

upvoted a collection 12 days ago

🦙 Llama-3.2-Taiwan

Based on the meta-llama/Llama-3.2-*B model, we continue pre-training on a large corpus of Traditional Chinese and non-Chinese language data. • 9 items • Updated Apr 26 • 1

upvoted a paper 17 days ago

UltraHR-100K: Enhancing UHR Image Synthesis with A Large-Scale High-Quality Dataset

Paper • 2510.20661 • Published 23 days ago • 13

upvoted an article about 1 month ago

Article

Vision Language Model Alignment in TRL ⚡️

Aug 7

•

99

upvoted a changelog about 2 months ago

Changelog

Repositories total file size is now displayed

Sep 18

• 171

upvoted an article about 2 months ago

Article

Generate Images with Claude and Hugging Face

Aug 19

•

36

upvoted a collection about 2 months ago

🏎️ Formosa-1 Series

A collection of Formosa-1 (F1) reasoning models and datasets focused on Traditional Chinese instruction-following and logic. • 4 items • Updated Oct 13 • 4

upvoted a changelog about 2 months ago

Changelog

Custom Domains for Spaces

Sep 17

• 80

upvoted an article 2 months ago

Article

Tricks from OpenAI gpt-oss YOU 🫵 can use with transformers

Sep 11

•

162

upvoted a collection 3 months ago

📋 Eval Logs

Benchmark log generated with Twinkle Eval, recording the model's outputs for each prompt. • 2 items • Updated Oct 13 • 4

upvoted a paper 3 months ago

InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency

Paper • 2508.18265 • Published Aug 25 • 205

upvoted 3 collections 3 months ago

InternVL3.5

This collection includes all released checkpoints of InternVL3.5, covering different training stages (e.g., Pretraining, SFT, MPO, Cascade RL). • 54 items • Updated Sep 28 • 102

GPT OSS

2 items • Updated Aug 20 • 12

gpt-oss

Open-weight models designed for powerful reasoning, agentic tasks, and versatile developer use cases. • 2 items • Updated Aug 7 • 379

upvoted a changelog 4 months ago

Changelog

Trending Papers

Jul 28

• 104

upvoted a paper 4 months ago

FineWeb2: One Pipeline to Scale Them All -- Adapting Pre-Training Data Processing to Every Language

Paper • 2506.20920 • Published Jun 26 • 75

upvoted an article 4 months ago

Article

Reachy Mini - The Open-Source Robot for Today's and Tomorrow's AI Builders

Jul 9

•

711

upvoted a collection 4 months ago

FLUX.1

A collection of our FLUX.1 models and LoRAs. • 10 items • Updated Oct 14 • 243

upvoted an article 4 months ago

Article

Topic 23: What is LLM Inference, it's challenges and solutions for it

Jan 17

•

17