Search Results - "Kuciński, Łukasz"

There and Back Again: On the relation between noises, images, and their inversions in diffusion models by Staniszewski, Łukasz, Kuciński, Łukasz, Deja, Kamil

“…Denoising Diffusion Probabilistic Models (DDPMs) achieve state-of-the-art performance in synthesizing new images from random noise, but they lack meaningful…”
Get full text

Complete discounted cash flow valuation by Gajek, Lesław, Kuciński, Łukasz

“…This paper concerns discounted cash flow valuation of a company. When the company is in trouble, the owners have an option to provide it with a new capital;…”
Get full text

RoboMorph: Evolving Robot Morphology using Large Language Models by Qiu, Kevin, Ciebiera, Krzysztof, Fijałkowski, Paweł, Cygan, Marek, Kuciński, Łukasz

“…We introduce RoboMorph, an automated approach for generating and optimizing modular robot designs using large language models (LLMs) and evolutionary…”
Get full text

GUIDE: Guidance-based Incremental Learning with Diffusion Models by Cywiński, Bartosz, Deja, Kamil, Trzciński, Tomasz, Twardowski, Bartłomiej, Kuciński, Łukasz

“…We introduce GUIDE, a novel continual learning approach that directs diffusion models to rehearse samples at risk of being forgotten. Existing generative…”
Get full text

Accelerating Goal-Conditioned RL Algorithms and Research by Bortkiewicz, Michał, Pałucki, Władek, Myers, Vivek, Dziarmaga, Tadeusz, Arczewski, Tomasz, Kuciński, Łukasz, Eysenbach, Benjamin

“…Abstract Self-supervision has the potential to transform reinforcement learning (RL), paralleling the breakthroughs it has enabled in other areas of machine…”
Get full text

Disentangling Transfer in Continual Reinforcement Learning by Wołczyk, Maciej, Zając, Michał, Pascanu, Razvan, Kuciński, Łukasz, Miłoś, Piotr

“…The ability of continual learning systems to transfer knowledge from previously seen tasks in order to maximize performance on new tasks is a significant…”
Get full text

What Matters in Hierarchical Search for Combinatorial Reasoning Problems? by Zawalski, Michał, Góral, Gracjan, Tyrolski, Michał, Wiśnios, Emilia, Budrowski, Franciszek, Kuciński, Łukasz, Miłoś, Piotr

“…Efficiently tackling combinatorial reasoning problems, particularly the notorious NP-hard tasks, remains a significant challenge for AI research. Recent…”
Get full text

Fine-tuning Reinforcement Learning Models is Secretly a Forgetting Mitigation Problem by Wołczyk, Maciej, Cupiał, Bartłomiej, Ostaszewski, Mateusz, Bortkiewicz, Michał, Zając, Michał, Pascanu, Razvan, Kuciński, Łukasz, Miłoś, Piotr

“…Fine-tuning is a widespread technique that allows practitioners to transfer pre-trained capabilities, as recently showcased by the successful applications of…”
Get full text

Structured Packing in LLM Training Improves Long Context Utilization by Staniszewski, Konrad, Tworkowski, Szymon, Jaszczur, Sebastian, Zhao, Yu, Michalewski, Henryk, Kuciński, Łukasz, Miłoś, Piotr

“…Recent advancements in long-context large language models have attracted significant attention, yet their practical applications often suffer from suboptimal…”
Get full text

RapidDock: Unlocking Proteome-scale Molecular Docking by Powalski, Rafał, Klockiewicz, Bazyli, Jaśkowski, Maciej, Topolski, Bartosz, Dąbrowski-Tumański, Paweł, Wiśniewski, Maciej, Kuciński, Łukasz, Miłoś, Piotr, Plewczynski, Dariusz

“…Accelerating molecular docking -- the process of predicting how molecules bind to protein targets -- could boost small-molecule drug discovery and…”
Get full text

Catalytic Role Of Noise And Necessity Of Inductive Biases In The Emergence Of Compositional Communication by Kuciński, Łukasz, Korbak, Tomasz, Kołodziej, Paweł, Miłoś, Piotr

“…Communication is compositional if complex signals can be represented as a combination of simpler subparts. In this paper, we theoretically show that inductive…”
Get full text

tsGT: Stochastic Time Series Modeling With Transformer by Kuciński, Łukasz, Drzewakowski, Witold, Olko, Mateusz, Kozakowski, Piotr, Maziarka, Łukasz, Nowakowska, Marta Emilia, Kaiser, Łukasz, Miłoś, Piotr

“…Time series methods are of fundamental importance in virtually any field of science that deals with temporally structured data. Recently, there has been a…”
Get full text

BALROG: Benchmarking Agentic LLM and VLM Reasoning On Games by Paglieri, Davide, Cupiał, Bartłomiej, Coward, Samuel, Piterbarg, Ulyana, Wolczyk, Maciej, Khan, Akbir, Pignatelli, Eduardo, Kuciński, Łukasz, Pinto, Lerrel, Fergus, Rob, Foerster, Jakob Nicolaus, Parker-Holder, Jack, Rocktäschel, Tim

“…Large Language Models (LLMs) and Vision Language Models (VLMs) possess extensive knowledge and exhibit promising reasoning abilities; however, they still…”
Get full text

Continual World: A Robotic Benchmark For Continual Reinforcement Learning by Wołczyk, Maciej, Zając, Michał, Pascanu, Razvan, Kuciński, Łukasz, Miłoś, Piotr

“…Continual learning (CL) -- the ability to continuously learn, building on previously acquired knowledge -- is a natural requirement for long-lived autonomous…”
Get full text

Trust Your $\nabla$: Gradient-based Intervention Targeting for Causal Discovery by Olko, Mateusz, Zając, Michał, Nowak, Aleksandra, Scherrer, Nino, Annadani, Yashas, Bauer, Stefan, Kuciński, Łukasz, Miłoś, Piotr

“…Inferring causal structure from data is a challenging task of fundamental importance in science. Observational data are often insufficient to identify a…”
Get full text

Continuous Control With Ensemble Deep Deterministic Policy Gradients by Januszewski, Piotr, Olko, Mateusz, Królikowski, Michał, Świątkowski, Jakub, Andrychowicz, Marcin, Kuciński, Łukasz, Miłoś, Piotr

“…The growth of deep reinforcement learning (RL) has brought multiple exciting tools and methods to the field. This rapid expansion makes it important to…”
Get full text

Uncertainty-sensitive Learning and Planning with Ensembles by Miłoś, Piotr, Kuciński, Łukasz, Czechowski, Konrad, Kozakowski, Piotr, Klimek, Maciek

“…We propose a reinforcement learning framework for discrete environments in which an agent makes both strategic and tactical decisions. The former manifests…”
Get full text

Subgoal Search For Complex Reasoning Tasks by Czechowski, Konrad, Odrzygóźdź, Tomasz, Zbysiński, Marek, Zawalski, Michał, Olejnik, Krzysztof, Wu, Yuhuai, Kuciński, Łukasz, Miłoś, Piotr

“…Humans excel in solving complex reasoning tasks through a mental process of moving from one idea to a related one. Inspired by this, we propose Subgoal Search…”
Get full text

Fast and Precise: Adjusting Planning Horizon with Adaptive Subgoal Search by Zawalski, Michał, Tyrolski, Michał, Czechowski, Konrad, Odrzygóźdź, Tomasz, Stachura, Damian, Piękos, Piotr, Wu, Yuhuai, Kuciński, Łukasz, Miłoś, Piotr

“…Complex reasoning problems contain states that vary in the computational cost required to determine a good action plan. Taking advantage of this property, we…”
Get full text

Magnushammer: A Transformer-Based Approach to Premise Selection by Mikuła, Maciej, Tworkowski, Szymon, Antoniak, Szymon, Piotrowski, Bartosz, Jiang, Albert Qiaochu, Zhou, Jin Peng, Szegedy, Christian, Kuciński, Łukasz, Miłoś, Piotr, Wu, Yuhuai

“…This paper presents a novel approach to premise selection, a crucial reasoning task in automated theorem proving. Traditionally, symbolic methods that rely on…”
Get full text