r PRO

oceansweep's activity

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

liked a model about 9 hours ago

stepfun-ai/Step-Audio-EditX

Text-to-Speech • 4B • Updated 1 day ago • 120 • 26

upvoted a paper 2 days ago

Diffusion Language Models are Super Data Learners

Paper • 2511.03276 • Published 4 days ago • 94

liked a Space 2 days ago

Running on Zero

17

17

Step-Audio-EditX

🚀

Try out Step-Audio-EditX

liked a model 3 days ago

aquif-ai/aquif-3.5-Max-42B-A3B

Text Generation • 42B • Updated 1 day ago • 1.73k • 54

upvoted a collection 3 days ago

MDGA

Collection

Make Diffusion Great Again. The resource list for Super Data Learners, Quokka, and OpenMoE 2. • 16 items • Updated 5 days ago • 5

liked a model 7 days ago

meituan-longcat/LongCat-Flash-Omni

Text Generation • 561B • Updated 9 days ago • 565 • 87

liked a model 8 days ago

bullerwins/MiniMax-M2-GGUF

Text Generation • 229B • Updated 11 days ago • 6.56k • 6

liked a model 13 days ago

MiniMaxAI/MiniMax-M2

Text Generation • 229B • Updated 2 days ago • 863k • • 1.22k

liked 2 models 20 days ago

IndexTeam/IndexTTS-2

Updated Sep 8 • 25.5k • 455

deepseek-ai/DeepSeek-OCR

Image-Text-to-Text • 3B • Updated 5 days ago • 3M • • 2.56k

upvoted 4 papers 22 days ago

Large Language Models Do NOT Really Know What They Don't Know

Paper • 2510.09033 • Published about 1 month ago • 16

BitNet Distillation

Paper • 2510.13998 • Published 25 days ago • 52

AI for Service: Proactive Assistance with AI Glasses

Paper • 2510.14359 • Published 24 days ago • 71

When Models Lie, We Learn: Multilingual Span-Level Hallucination Detection with PsiloQA

Paper • 2510.04849 • Published Oct 6 • 111

upvoted 6 papers about 1 month ago

UNIDOC-BENCH: A Unified Benchmark for Document-Centric Multimodal RAG

Paper • 2510.03663 • Published Oct 4 • 15

Fine-Grained Detection of Context-Grounded Hallucinations Using LLMs

Paper • 2509.22582 • Published Sep 26 • 10

Learning to Reason for Hallucination Span Detection

Paper • 2510.02173 • Published Oct 2 • 18

F2LLM Technical Report: Matching SOTA Embedding Performance with 6 Million Open-Source Data

Paper • 2510.02294 • Published Oct 2 • 43

Tree-based Dialogue Reinforced Policy Optimization for Red-Teaming Attacks

Paper • 2510.02286 • Published Oct 2 • 28

The Rogue Scalpel: Activation Steering Compromises LLM Safety

Paper • 2509.22067 • Published Sep 26 • 27