EvoPolicyGym: Evaluating Autonomous Policy Evolution in Interactive Environments Paper • 2607.02440 • Published Jul 2 • 51
Speed Always Wins: A Survey on Efficient Architectures for Large Language Models Paper • 2508.09834 • Published Aug 13, 2025 • 53
Beyond LoRA vs. Full Fine-Tuning: Gradient-Guided Optimizer Routing for LLM Adaptation Paper • 2605.07111 • Published May 18