Dongfu Jiang

DongfuJiang's activity

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

upvoted a paper 1 day ago

Code2LoRA: Hypernetwork-Generated Adapters for Code Language Models under Software Evolution

Paper • 2606.06492 • Published 4 days ago • 72

authored 3 papers 2 days ago

RewardHarness: Self-Evolving Agentic Post-Training

Paper • 2605.08703 • Published 30 days ago • 10

Cosmos 3: Omnimodal World Models for Physical AI

Paper • 2606.02800 • Published 7 days ago • 93

AutoLab: Can Frontier Models Solve Long-Horizon Auto Research and Engineering Tasks?

Paper • 2606.05080 • Published 5 days ago • 27

upvoted 2 papers 3 days ago

Cosmos 3: Omnimodal World Models for Physical AI

Paper • 2606.02800 • Published 7 days ago • 93

AutoLab: Can Frontier Models Solve Long-Horizon Auto Research and Engineering Tasks?

Paper • 2606.05080 • Published 5 days ago • 27

liked a model 3 days ago

nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16

Text Generation • 561B • Updated 1 day ago • 49.8k • 156

liked a Space 6 days ago

Running on Zero

Agents

8

Cosmos3 Nano

🌌

8

Create videos (and images) from text prompts

liked 2 models 7 days ago

nvidia/Cosmos3-Super

65B • Updated 2 days ago • 24k • 151

nvidia/Cosmos3-Nano

16B • Updated 7 days ago • 29.7k • 193

updated a dataset 23 days ago

DongfuJiang/5M_corpus

Preview • Updated 23 days ago • 1.12k

authored 4 papers 25 days ago

Watch Before You Answer: Learning from Visually Grounded Post-Training

Paper • 2604.05117 • Published Apr 6 • 36

ClawBench: Can AI Agents Complete Everyday Online Tasks?

Paper • 2604.08523 • Published Apr 9 • 263

Nemotron 3 Super: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning

Paper • 2604.12374 • Published Apr 14 • 37

Beyond Semantic Similarity: Rethinking Retrieval for Agentic Search via Direct Corpus Interaction

Paper • 2605.05242 • Published May 3 • 122

liked a dataset 26 days ago

google/deepsearchqa

Viewer • Updated Dec 17, 2025 • 900 • 19.2k • 120

upvoted a paper 26 days ago

WorldReasonBench: Human-Aligned Stress Testing of Video Generators as Future World-State Predictors

Paper • 2605.10434 • Published 28 days ago • 29

New activity in DongfuJiang/5M_corpus 27 days ago

Add complete QA eval data hierarchy

#2 opened 27 days ago by

jiangdongfu

Add offline QA eval metadata

#1 opened 27 days ago by

jiangdongfu

published a dataset 27 days ago

DongfuJiang/5M_corpus

Preview • Updated 23 days ago • 1.12k