RealCompanion: Benchmarking Human Understanding from Reasoning over Longitudinal Real-World Conversations
Paper • 2610.01780 • Published • 285
Alignment Avengers
AlignmentAvengers
·
AI & ML interests
None yet
Recent Activity
View all activity
Organizations
None yet
upvoted a paper 8 days ago
upvoted 4
papers 13 days ago
Act First, Reason Later: Accelerating On-Policy Distillation for Multi-Turn Agents via Reference-Conditioned Inverse Dynamics
Paper • 2609.36608 • Published • 8
Adversarial Training for Pixel Diffusion
Paper • 2609.38170 • Published • 22
EasyPPO: Stabilizing the Critic Is Key
Paper • 2609.36802 • Published • 39
Scaling Properties of Same-Family On-Policy Distillation
Paper • 2609.32722 • Published • 326