kk

zhangyikai's activity

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

upvoted a paper about 20 hours ago

CoBA-RL: Capability-Oriented Budget Allocation for Reinforcement Learning in LLMs

Paper • 2602.03048 • Published 2 days ago • 33

updated a Space about 22 hours ago

Running

1

Generalist Value Model V0

😻

1

Predict how well language models will perform on new tasks

liked a Space about 22 hours ago

Running

1

Generalist Value Model V0

😻

1

Predict how well language models will perform on new tasks

upvoted a paper about 22 hours ago

V_0: A Generalist Value Model for Any Policy at State Zero

Paper • 2602.03584 • Published 1 day ago • 20

updated a model 1 day ago

Now-Join-Us/Generalist-Value-Model-V0

Updated about 21 hours ago

published a Space 4 days ago

Running

1

Generalist Value Model V0

😻

1

Predict how well language models will perform on new tasks

published a model 4 days ago

Now-Join-Us/Generalist-Value-Model-V0

Updated about 21 hours ago

liked a model 7 months ago

AIDC-AI/Ovis-U1-3B

Any-to-Any • 4B • Updated Jul 3, 2025 • 1.98k • 212

upvoted 2 papers 8 months ago

Advancing Multimodal Reasoning via Reinforcement Learning with Cold Start

Paper • 2505.22334 • Published May 28, 2025 • 36

Unsupervised Post-Training for Multi-Modal LLM Reasoning via GRPO

Paper • 2505.22453 • Published May 28, 2025 • 46

upvoted a paper 9 months ago

Unified Multimodal Understanding and Generation Models: Advances, Challenges, and Opportunities

Paper • 2505.02567 • Published May 5, 2025 • 80

updated 6 models 11 months ago

AIDC-AI/Ovis2-2B-GPTQ-Int4

Image-Text-to-Text • 2B • Updated Mar 25, 2025 • 125 • 2

AIDC-AI/Ovis2-8B-GPTQ-Int4

Image-Text-to-Text • 9B • Updated Mar 25, 2025 • 35 • 3

AIDC-AI/Ovis2-4B-GPTQ-Int4

Image-Text-to-Text • 4B • Updated Mar 25, 2025 • 1.38k • 3

AIDC-AI/Ovis2-34B-GPTQ-Int8

Image-Text-to-Text • 35B • Updated Mar 28, 2025 • 20 • 2

AIDC-AI/Ovis2-16B-GPTQ-Int4

Image-Text-to-Text • 16B • Updated Mar 25, 2025 • 21 • 5

AIDC-AI/Ovis2-34B-GPTQ-Int4

Image-Text-to-Text • 35B • Updated Mar 28, 2025 • 31 • 8

updated a Space 11 months ago

Runtime error

7

Ovis2 34B GPTQ Int4

📚

7

Stays powerful, with much lighter VRAM usage

liked 2 models 12 months ago

AIDC-AI/Ovis2-34B

Image-Text-to-Text • 35B • Updated Aug 15, 2025 • 1.17k • 152

AIDC-AI/Ovis2-16B

Image-Text-to-Text • 16B • Updated Aug 15, 2025 • 201 • 101