C2C is a new testbed where LM agents negotiate differently from humans and targeted prompting raises their win rate from 22.2% to 32.7% across 1,100+ games.
On the limited memory bfgs method for large scale optimization
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
representative citing papers
A new rectified and renormalized Fisher-Bingham model is proposed for compositional data containing zeros, achieved via square-root mapping to the sphere and a deterministic transformation on a latent Fisher-Bingham variable.
ActNet is a new KST-based neural network that outperforms KANs and competes with MLPs in PINN benchmarks for PDE simulation tasks.
citing papers explorer
-
Cooperate to Compete: Strategic Coordination in Multi-Agent Conquest
C2C is a new testbed where LM agents negotiate differently from humans and targeted prompting raises their win rate from 22.2% to 32.7% across 1,100+ games.
-
Rectified Fisher-Bingham Model for Compositional Data with Zeros
A new rectified and renormalized Fisher-Bingham model is proposed for compositional data containing zeros, achieved via square-root mapping to the sphere and a deterministic transformation on a latent Fisher-Bingham variable.
-
Deep Learning Alternatives of the Kolmogorov Superposition Theorem
ActNet is a new KST-based neural network that outperforms KANs and competes with MLPs in PINN benchmarks for PDE simulation tasks.