Yanzhe Zhang PRO

zyanzhe's activity

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

upvoted a paper about 21 hours ago

Sherpa: Teaching LLMs to Teach Adaptively

Paper • 2610.08778 • Published 3 days ago • 9

authored 2 papers about 21 hours ago

Sherpa: Teaching LLMs to Teach Adaptively

Paper • 2610.08778 • Published 3 days ago • 9

Matryoshka attribution: Learning to attribute language model outputs to representations and weights

Paper • 2609.25518 • Published 17 days ago • 1

submitted a paper to Daily Papers about 21 hours ago

Sherpa: Teaching LLMs to Teach Adaptively

Paper • 2610.08778 • Published 3 days ago • 9

updated a dataset 14 days ago

SALT-NLP/agent-collusion

Viewer • Updated 14 days ago • 143k • 1.16k • 1

authored 2 papers 15 days ago

Emergent Collusion in Long-Horizon LLM Agent Interaction

Paper • 2609.24967 • Published 18 days ago • 19

Contextualized Privacy Defense for LLM Agents

Paper • 2603.02983 • Published Mar 3

upvoted a paper 15 days ago

Emergent Collusion in Long-Horizon LLM Agent Interaction

Paper • 2609.24967 • Published 18 days ago • 19

submitted a paper to Daily Papers 15 days ago

Emergent Collusion in Long-Horizon LLM Agent Interaction

Paper • 2609.24967 • Published 18 days ago • 19

updated 2 collections 3 months ago

Context-induced Instability

Collection

14 items • Updated Jul 15

Context Length Ablation

Collection

Part of the Context-induced Instability dataset release. • 24 items • Updated Jul 15