Ganqu Cui

ganqu's activity

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

upvoted a paper 2 days ago

Liger: Linearizing Large Language Models to Gated Recurrent Structures

Paper • 2503.01496 • Published 3 days ago • 13

liked a dataset 13 days ago

HuggingFaceH4/ultrafeedback_binarized

Viewer • Updated Oct 16, 2024 • 187k • 5.65k • 275

liked 3 datasets 20 days ago

openbmb/UltraFeedback

Viewer • Updated Dec 29, 2023 • 64k • 3.07k • 352

kkk-an/UltraIF-dpo-20k

Preview • Updated 24 days ago • 79 • 4

kkk-an/UltraIF-sft-175k

Viewer • Updated 24 days ago • 181k • 133 • 2

upvoted a paper 21 days ago

LASP-2: Rethinking Sequence Parallelism for Linear Attention and Its Hybrid

Paper • 2502.07563 • Published 23 days ago • 24

authored a paper 27 days ago

UltraIF: Advancing Instruction Following from the Wild

Paper • 2502.04153 • Published 28 days ago • 22

upvoted a paper 27 days ago

UltraIF: Advancing Instruction Following from the Wild

Paper • 2502.04153 • Published 28 days ago • 22

authored a paper about 1 month ago

Process Reinforcement through Implicit Rewards

Paper • 2502.01456 • Published about 1 month ago • 55

upvoted a paper about 1 month ago

Process Reinforcement through Implicit Rewards

Paper • 2502.01456 • Published about 1 month ago • 55

liked a model about 2 months ago

internlm/internlm3-8b-instruct

Text Generation • Updated 23 days ago • 10.4k • 204

updated a Space 2 months ago

Running

README

🏃

liked a dataset 2 months ago

PRIME-RL/Eurus-2-RL-Data

Viewer • Updated 15 days ago • 483k • 2.28k • 28

published an article 2 months ago

view article

Article

Process Reinforcement through Implicit Rewards

By and 1 other •

Jan 3

• 24

liked 2 models 2 months ago

PRIME-RL/Eurus-2-7B-PRIME

Text Generation • Updated 15 days ago • 595 • 60

PRIME-RL/EurusPRM-Stage2

Updated 15 days ago • 6.63k • 6

updated a model 2 months ago

PRIME-RL/Eurus-2-7B-PRIME

Text Generation • Updated 15 days ago • 595 • 60

authored 3 papers 3 months ago

RLAIF-V: Aligning MLLMs through Open-Source AI Feedback for Super GPT-4V Trustworthiness

Paper • 2405.17220 • Published May 27, 2024 • 1

UltraMedical: Building Specialized Generalists in Biomedicine

Paper • 2406.03949 • Published Jun 6, 2024

Free Process Rewards without Process Labels

Paper • 2412.01981 • Published Dec 2, 2024 • 32