Patrick Jiang

pat-jj's activity

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

upvoted 2 papers 3 days ago

Learning from Teacher Continuations at Student States

Paper • 2609.36246 • Published 6 days ago • 38

Selecting Diverse SFT Traces Improves Post-RL Generalization

Paper • 2609.33780 • Published 7 days ago • 37

updated a model 4 days ago

pat-jj/value-transplant

Updated 4 days ago

upvoted a paper 11 days ago

RRSI: Regularized Recursive Self-Improvement of Agent Harnesses

Paper • 2609.24972 • Published 13 days ago • 221

upvoted a paper 29 days ago

Random Attention: Rethinking KV Cache Eviction for Efficient Reasoning

Paper • 2609.03430 • Published about 1 month ago • 188

published a model about 2 months ago

pat-jj/value-transplant

Updated 4 days ago

updated a dataset 4 months ago

pat-jj/harness-1-train-data

Viewer • Updated Jun 15 • 4.35k • 4.07k

published a dataset 4 months ago

pat-jj/harness-1-train-data

Viewer • Updated Jun 15 • 4.35k • 4.07k

updated a model 4 months ago

pat-jj/harness-1

Text Generation • 21B • Updated Jun 15 • 302 • 106

authored a paper 4 months ago

Harness-1: Reinforcement Learning for Search Agents with State-Externalizing Harnesses

Paper • 2606.02373 • Published Jun 1 • 59

upvoted a paper 4 months ago

Harness-1: Reinforcement Learning for Search Agents with State-Externalizing Harnesses

Paper • 2606.02373 • Published Jun 1 • 59

submitted a paper to Daily Papers 4 months ago

Harness-1: Reinforcement Learning for Search Agents with State-Externalizing Harnesses

Paper • 2606.02373 • Published Jun 1 • 59

upvoted a paper 4 months ago

Masking Stale Observations Helps Search Agents -- Until It Doesn't: A Regime Map and Its Mechanism

Paper • 2606.00408 • Published May 29 • 64

liked a model 5 months ago

pat-jj/harness-1

Text Generation • 21B • Updated Jun 15 • 302 • 106

upvoted 2 papers 5 months ago

Learning to Predict Future-Aligned Research Proposals with Language Models

Paper • 2603.27146 • Published Apr 6 • 6

Retrieval is Cheap, Show Me the Code: Executable Multi-Hop Reasoning for Retrieval-Augmented Generation

Paper • 2605.12975 • Published May 13 • 9

published a model 5 months ago

pat-jj/harness-1

Text Generation • 21B • Updated Jun 15 • 302 • 106

updated 2 models 5 months ago

pat-jj/backdoor_models_tinker

Updated Apr 29

pat-jj/em_models_tinker

Updated Apr 29

published a model 5 months ago

pat-jj/backdoor_models_tinker

Updated Apr 29