Improved Content Understanding With Effective Use of Multi-task Contrastive Learning

no code implementations • 18 May 2024 • Akanksha Bindal, Sudarshan Ramanujam, Dave Golland, TJ Hazen, Tina Jiang, Fengyu Zhang, Peng Yan

This work provides a robust foundation for vertical teams across LinkedIn to customize and fine-tune the LLM to their specific applications.

Contrastive Learning Multi-Task Learning +1

Joint Policy Search for Multi-agent Collaboration with Imperfect Information

1 code implementation • NeurIPS 2020 • Yuandong Tian, Qucheng Gong, Tina Jiang

Based on this, we propose Joint Policy Search(JPS) that iteratively improves joint policies of collaborative agents in imperfect information games, without re-evaluating the entire game.

Luck Matters: Understanding Training Dynamics of Deep ReLU Networks

1 code implementation • 31 May 2019 • Yuandong Tian, Tina Jiang, Qucheng Gong, Ari Morcos

We analyze the dynamics of training deep ReLU networks and their implications on generalization capability.