Skip to content
Experiments (Continuously Updated)
Experiments
Oct 12, 2026
Adaptive Swarm
Oct 7, 2026
How Vocabulary Size Shapes Overfitting
Oct 5, 2026
Training a Policy from Scratch against a Frozen Critic
Oct 4, 2026
How to design reward function in Multi-Agent RL
Oct 3, 2026
Quantifying the
Per-layer
Contribution of LLMs
Oct 3, 2026
Sampled Softmax with Over-Tokenized Transformer
Sep 2025
LoopDiT: Loop Transformers for Diffusion Models
Template
Experiment Template