Unchun Yang

ucyang's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted a paper about 5 hours ago

Embarrassingly Simple Self-Distillation Improves Code Generation

Paper • 2604.01193 • Published 16 days ago • 40

upvoted a collection about 16 hours ago

Qwen3.6

Collection

2 items • Updated about 18 hours ago • 69

liked 2 models about 17 hours ago

unsloth/Qwen3.6-35B-A3B-GGUF

Image-Text-to-Text • 35B • Updated about 15 hours ago • 259

Qwen/Qwen3.6-35B-A3B

Image-Text-to-Text • 36B • Updated 2 days ago • 570

liked a model about 21 hours ago

tencent/HY-World-2.0

Image-to-3D • Updated about 22 hours ago • 188

upvoted an article 1 day ago

view article

Article

Navigating the RLHF Landscape: From Policy Gradients to PPO, GAE, and DPO for LLM Alignment

• 

Feb 11, 2025

•

119

liked 2 datasets 3 days ago

allenai/IFBench_test

Viewer • Updated Oct 17, 2025 • 300 • 3.88k • 11

wckwan/MT-Eval

Viewer • Updated Feb 20, 2024 • 1.06k • 418 • 2

upvoted a paper 3 days ago

MT-Eval: A Multi-Turn Capabilities Evaluation Benchmark for Large Language Models

Paper • 2401.16745 • Published Jan 30, 2024 • 1

liked 2 datasets 3 days ago

ScaleAI/MultiChallenge

Viewer • Updated 16 days ago • 266 • 120 • 1

google/IFEval

Viewer • Updated Aug 14, 2024 • 541 • 94k • 146

upvoted a collection 3 days ago

IFBench

Collection

Datasets for IFBench benchmark and paper! • 3 items • Updated Dec 23, 2025 • 12

liked 3 models 3 days ago

dealignai/Gemma-4-31B-JANG_4M-CRACK

Image-Text-to-Text • 6B • Updated about 7 hours ago • 143k • 1.25k

HauhauCS/Qwen3.5-35B-A3B-Uncensored-HauhauCS-Aggressive

Image-Text-to-Text • 35B • Updated 12 days ago • 1.22M • 1.32k

BidirLM/BidirLM-Omni-2.5B-Embedding

Sentence Similarity • 2B • Updated 1 day ago • 3.08k • 9

upvoted a paper 3 days ago

BidirLM: From Text to Omnimodal Bidirectional Encoders by Adapting and Composing Causal LLMs

Paper • 2604.02045 • Published 15 days ago • 33

upvoted a collection 3 days ago

BidirLM-Embedding

Collection

BidirLM is a family of 5 frontier bidirectional encoders, including an omnimodal variant at 2.5B. • 6 items • Updated 10 days ago • 5

upvoted a paper 4 days ago

EXAONE 4.5 Technical Report

Paper • 2604.08644 • Published 8 days ago • 61

upvoted an article 5 days ago

view article

Article

Fine-Tuning Your First Large Language Model (LLM) with PyTorch and Hugging Face

• 

Feb 11, 2025

•

117

liked a model 5 days ago

google/timesfm-2.5-200m-pytorch

Time Series Forecasting • Updated Oct 2, 2025 • 221