Unchun Yang's picture

Unchun Yang

ucyang

·

https://ucyang.com/

AI & ML interests

None yet

Recent Activity

upvoted an article about 9 hours ago

Training and Finetuning Reranker Models with Sentence Transformers v4

liked a model about 20 hours ago

distilbert/distilbert-base-multilingual-cased

liked a model about 20 hours ago

distilbert/distilbert-base-cased-distilled-squad

View all activity

Organizations

ucyang's activity

upvoted an article about 9 hours ago

Article

Training and Finetuning Reranker Models with Sentence Transformers v4

8 days ago

• 86

upvoted a paper 1 day ago

MoCha: Towards Movie-Grade Talking Character Synthesis

Paper • 2503.23307 • Published 3 days ago • 56

upvoted an article 1 day ago

Article

Bamba: Inference-Efficient Hybrid Mamba2 Model

Dec 18, 2024

• 49

upvoted a paper 3 days ago

Qwen2.5-Omni Technical Report

Paper • 2503.20215 • Published 7 days ago • 112

upvoted a collection 5 days ago

CoRNStack

State-of-the-art code retrieval and re-ranking models and datasets • 9 items • Updated 7 days ago • 15

upvoted 3 collections 7 days ago

Qwen2.5-Omni

End-to-End Omni (text, audio, image, video, and natural speech interaction) model based Qwen2.5 • 3 items • Updated 6 days ago • 75

Ling

6 items • Updated 23 days ago • 8

TxGemma Release

Collection of open models to accelerate the development of therapeutics. • 5 items • Updated 6 days ago • 38

upvoted a paper 10 days ago

Why Do Multi-Agent LLM Systems Fail?

Paper • 2503.13657 • Published 16 days ago • 41

upvoted a paper 11 days ago

SynCity: Training-Free Generation of 3D Worlds

Paper • 2503.16420 • Published 13 days ago • 25

upvoted a collection 11 days ago

💫StarVector Models

StarVector is a multimodal LLM for Scalable Vector Graphics (SVG) generation, producing structured SVG code directly from images and text. • 2 items • Updated 13 days ago • 88

upvoted a paper 11 days ago

Survey on Evaluation of LLM-based Agents

Paper • 2503.16416 • Published 13 days ago • 80

upvoted 3 collections 12 days ago

MoshiVis v0.1

MoshiVis is a Vision Speech Model built as a perceptually-augmented version of Moshi v0.1 for conversing about image inputs • 8 items • Updated 12 days ago • 16

DeepHermes

Preview models of hybrid reasoner Hermes series • 6 items • Updated 20 days ago • 27

Llama Nemotron

Open, Production-ready Enterprise Models • 3 items • Updated 7 days ago • 25

upvoted a collection 13 days ago

EXAONE-Deep

EXAONE reasoning model series of 2.4B, 7.8B, and 32B, optimized for reasoning tasks including math and coding • 9 items • Updated 16 days ago • 84

upvoted a collection 14 days ago

Orpheus TTS

TTS Towards Human-Sounding Speech • 2 items • Updated 15 days ago • 52

upvoted a paper 14 days ago

DAPO: An Open-Source LLM Reinforcement Learning System at Scale

Paper • 2503.14476 • Published 15 days ago • 111

upvoted a paper 16 days ago

SmolDocling: An ultra-compact vision-language model for end-to-end multi-modal document conversion

Paper • 2503.11576 • Published 19 days ago • 79