James Song

shxjames's activity

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

upvoted a paper 30 days ago

SecOPD: Mitigating Adaptive Prompt Injections by On-Policy Distillation

Paper • 2608.21500 • Published Aug 21 • 41

updated a model 7 months ago

shxjames/checkpoints

Updated Feb 23

published a model 8 months ago

shxjames/checkpoints

Updated Feb 23

authored a paper 11 months ago

When "Correct" Is Not Safe: Can We Trust Functionally Correct Patches Generated by Code Agents?

Paper • 2510.17862 • Published Oct 15, 2025 • 8

upvoted a paper 11 months ago

When "Correct" Is Not Safe: Can We Trust Functionally Correct Patches Generated by Code Agents?

Paper • 2510.17862 • Published Oct 15, 2025 • 8

upvoted a paper 12 months ago

Prosperity before Collapse: How Far Can Off-Policy RL Reach with Stale Data on LLMs?

Paper • 2510.01161 • Published Oct 1, 2025 • 14

liked a model about 1 year ago

openai/gpt-oss-20b

Text Generation • 21B • Updated Aug 26, 2025 • 6.69M • • 5.09k