Controllable Process Data Synthesis for Reward Models
Discover a novel framework for controllable, verifiable process data synthesis enhancing process reward models with improved error control and reasoning.
AI Agent for Fast Conversational Grant Discovery
Discover research grants faster with a compound AI agent offering conversational search across 12,000+ funding sources in real time.
ANO: Robust Policy Optimization for Deep Reinforcement Learning
Discover ANO, a novel robust policy optimization method enhancing stability and performance in deep reinforcement learning beyond PPO and SPO.
Using Causal Discovery Algorithms to Generate Legal Arguments
Explore how causal discovery algorithms can uncover legal concept relationships and aid automated generation of legal arguments for better justice outcomes...
Anon Optimizer: Bridging Adaptive and SGD Methods
Discover Anon, a novel optimizer that tunes adaptivity across the real spectrum, enhancing AI model training with robust convergence and superior performan...