Showing 2026Show all
3 papers · 1 filter
cs.AI2026
Tropical Reinforcement Learning
Arip Asadulaev, Aladin Djuhera, Karim Salta +3
Reinforcement learning for large language models typically maximizes expected return, adding up the probabilities of all successful trajectories. However, the classical sum formula…
cs.LG2026
Perturb-and-Solve: Efficient Learned-Operator Conditioning for Latent Diffusion Inverse Problems
Abduragim Shtanchaev, Arip Asadulaev, Luiza Labazanova +3
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 tra…
cs.LG2026
Value-Gradient Hypothesis of RL for LLMs
Arip Asadulaev, Daniil Ognev, Karim Salta +1
Reinforcement learning substantially improves pretrained language models, but it remains understudied why critic-free methods such as PPO and GRPO work as well as they do, and when…