Jack Zhang

jackzhang's activity

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

commented a paper about 1 month ago

The Alignment Waltz: Jointly Training Agents to Collaborate for Safety

Paper • 2510.08240 • Published about 1 month ago • 40 •

2

New activity in microsoft/CoSAlign-Train 3 months ago

Remove extra columns

#4 opened 3 months ago by

jackzhang

New activity in microsoft/CoSApien 3 months ago

Update README.md

#6 opened 3 months ago by

jackzhang

simplify dataset

#5 opened 3 months ago by

jackzhang

New activity in allenai/wildjailbreak 5 months ago

load_dataset error for train split

👍 2

2

#4 opened 5 months ago by

jackzhang

New activity in microsoft/CoSAlign-Test 6 months ago

Update README.md

#2 opened 6 months ago by

jackzhang

New activity in microsoft/CoSAlign-Train 6 months ago

Upload README.md

#3 opened 6 months ago by

jackzhang

Upload 8 files

#2 opened 6 months ago by

jackzhang

jack-train

#1 opened 6 months ago by

jackzhang

New activity in microsoft/CoSAlign-Test 6 months ago

jack

#1 opened 6 months ago by

jackzhang

New activity in microsoft/CoSApien 6 months ago

Change paper link to arxiv so that it can show up in the dataset metadata

#4 opened 6 months ago by

jackzhang

commented a paper 6 months ago

Certified Mitigation of Worst-Case LLM Copyright Infringement

Paper • 2504.16046 • Published Apr 22 • 13 •

2

New activity in microsoft/CoSApien 7 months ago

Upload 5 files

#2 opened 7 months ago by

jackzhang

Upload 6 files

#1 opened 7 months ago by

jackzhang

commented a paper about 1 year ago

Controllable Safety Alignment: Inference-Time Adaptation to Diverse Safety Requirements

Paper • 2410.08968 • Published Oct 11, 2024 • 13 •

2

New activity in RLHFlow/LLaMA3-SFT about 1 year ago

LLaMA3.1-SFT

3

#3 opened about 1 year ago by

jackzhang

New activity in mistralai/Mistral-Nemo-Instruct-2407 over 1 year ago

chat_template seems like it was converted incorrectly.

5

#10 opened over 1 year ago by

xzuyn