Running Reproduction: Partial Fusion of Neural Networks: Efficient Tradeoffs Between Ensembles and Weight Aggregation ๐ฏ
Running Repro: Offline Two-Player Zero-Sum Markov Games with KL Regularization ๐ฏ Explore and share experiment logbook with a coding agent
Running Repro: Enhancing LLMs for Graph Tasks via Graph-aware LoRA Generation ๐ฏ Collaborate with an AI agent using a shared logbook