Daniil Tiapkin

Adaptive Destruction Processes for Diffusion Samplers

Beyond Softmax and Entropy: Convergence Rates of Policy Gradients with $\boldsymbol{f}$-SoftArgmax Parameterization $&$ Coupled Regularization

Revisiting Non-Acyclic GFlowNets in Discrete Environments

Optimizing Backward Policies in GFlowNets via Trajectory Likelihood Maximization

On Teacher Hacking in Language Model Distillation

Finite-Sample Convergence Bounds for Trust Region Policy Optimization in Mean Field Games