Tag: causal machine learning
Browse our exclusive articles!
Hybrid Fine-Tuning for LLMs: Efficient Algorithm & Analysis
Discover a novel hybrid fine-tuning method for LLMs combining zeroth and first-order optimization to boost efficiency and performance.
What Logits Reveal About AI Models: Surprising Insights
Discover how logits in AI models can unintentionally leak sensitive info and what it means for privacy, security, and ethical AI development.
Teaching LLMs to Negotiate via Reinforcement Learning
Learn how Reinforcement Learning with verifiable rewards trains LLMs to master negotiation, outperforming larger models in strategic bargaining.
COMPOSITE-STEM: Benchmarking AI for Scientific Discovery
Discover COMPOSITE-STEM, a new AI benchmark with 70 expert tasks across STEM fields, enhancing AI evaluation in scientific discovery workflows.
Controllable Tool-Use Data Synthesis for Reinforcement Learning
Discover COVERT, a method for reliable, verifiable tool-use data synthesis that boosts reinforcement learning agent accuracy and robustness.