Łukasz Kuciński

Senior Research Scientist@IDEAS NCBR·波兰·OpenReview

研究方向

continual reinforcement learning · language models · reinforcement learning · planning · model-free · model-based · stochastic control · levy processes · stochastic processes · stochastic calculus

Łukasz Kuciński

There and Back Again: On the relation between Noise and Image Inversions in Diffusion Models

Accelerating Goal-Conditioned Reinforcement Learning Algorithms and Research

BALROG: Benchmarking Agentic LLM and VLM Reasoning On Games

There and Back Again: On the relation between noises, images, and their inversions in diffusion models

Since Faithfulness Fails: The Performance Limits of Neural Causal Discovery

What Matters in Hierarchical Search for Combinatorial Reasoning Problems?

GUIDE: Guidance-based Incremental Learning with Diffusion Models

RapidDock: Unlocking Proteome-scale Molecular Docking

Cayley Maze: Universal Open-Ended Reinforcement Learning Environment