Tianyu Yu

Yirany's activity

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

upvoted a paper about 1 month ago

MiniCPM-V 4.5: Cooking Efficient MLLMs via Architecture, Data, and Training Recipe

Paper • 2509.18154 • Published Sep 16 • 49

upvoted a paper 3 months ago

Euclid: Supercharging Multimodal LLMs with Synthetic High-Fidelity Visual Descriptions

Paper • 2412.08737 • Published Dec 11, 2024 • 54

upvoted a collection 4 months ago

MiniCPM-o & MiniCPM-V

Collection

Multimodal models with leading performance. • 28 items • Updated Sep 1 • 56

upvoted a paper 4 months ago

RLPR: Extrapolating RLVR to General Domains without Verifiers

Paper • 2506.18254 • Published Jun 23 • 31

upvoted a collection 4 months ago

RLPR

Collection

Extrapolating RLVR to General Domains without Verifiers • 6 items • Updated Aug 7 • 4

upvoted a paper 5 months ago

The Entropy Mechanism of Reinforcement Learning for Reasoning Language Models

Paper • 2505.22617 • Published May 28 • 130

upvoted a paper 9 months ago

Process Reinforcement through Implicit Rewards

Paper • 2502.01456 • Published Feb 3 • 61

upvoted 2 papers 11 months ago

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

Paper • 2405.17220 • Published May 27, 2024 • 1

Free Process Rewards without Process Labels

Paper • 2412.01981 • Published Dec 2, 2024 • 34

upvoted a collection about 1 year ago

MiniCPM

Collection

The MiniCPM family of LLMs and VLLMs. • 33 items • Updated Aug 7 • 73

upvoted a paper about 1 year ago

MiniCPM-V: A GPT-4V Level MLLM on Your Phone

Paper • 2408.01800 • Published Aug 3, 2024 • 89

upvoted 2 papers almost 2 years ago

SeqGPT: An Out-of-the-box Large Language Model for Open Domain Sequence Understanding

Paper • 2308.10529 • Published Aug 21, 2023 • 1

RLHF-V: Towards Trustworthy MLLMs via Behavior Alignment from Fine-grained Correctional Human Feedback

Paper • 2312.00849 • Published Dec 1, 2023 • 12