Authors

Karim Salta

Publications 2

Preprint Open access

Tropical Reinforcement Learning

Arip Asadulaev, Aladin Djuhera, Karim Salta et al. · 2026

Reinforcement learning for large language models typically maximizes expected return, adding up the probabilities of all successful trajectories. However, the classical sum formulation can only report how often the model policy succeeds, not which solution actually worked, and because probabilities sum to one, reinforc …

Preprint Open access

Perturb-and-Solve: Efficient Learned-Operator Conditioning for Latent Diffusion Inverse Problems

Abduragim Shtanchaev, Arip Asadulaev, Luiza Labazanova et al. · 2026

Latent diffusion models serve as powerful priors for solving inverse problems in image restoration, such as deblurring, inpainting, and super-resolution. Current methods have a trade-off between generality and efficiency. Solvers that are restricted to a fixed set of degradation operators are fast and efficient. Method …

Co-authors