Guangyao Dou

gydou's activity

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

upvoted a paper 8 days ago

Information Abundance Paradox: Long-Context Training Undermines Parametric Knowledge

Paper • 2608.12218 • Published 11 days ago • 6

upvoted a paper 15 days ago

HarnessOpt-Bench: Evaluating LLMs at Harness Optimization

Paper • 2608.06301 • Published 17 days ago • 35

upvoted 2 papers 2 months ago

DAR: Deontic Reasoning with Agentic Harnesses

Paper • 2606.05009 • Published Jun 3 • 6

Trust Functions: Near-Lossless Weak-to-Strong Generalization by Learning When to Trust the Weak Teacher

Paper • 2606.01000 • Published May 31 • 6

upvoted a paper 4 months ago

Many-Tier Instruction Hierarchy in LLM Agents

Paper • 2604.09443 • Published Apr 10 • 16

upvoted a paper 5 months ago

DeonticBench: A Benchmark for Reasoning over Rules

Paper • 2604.04443 • Published Apr 6 • 9