arXiv subjects

Tomáš Čížek

Publications and source records attributed to Tomáš Čížek.

4 recordsLinked to original sources

arXiv2026

SAM3RL: Memory Control via Reinforcement Learning for Visual Object Tracking

Segment Anything Model 3 (SAM 3) is a foundation model for image and video segmentation that sets the state of the art in visual object tracking. Its tracker, inherited from SAM 2, stores information from past frames in a memory bank, managed by a simple First-In-First-Out rule, allowing temporal consistency in complex videos. Several recent methods improve SAM 2 with hand-crafted memory update rules, each targeting a specific failure mode, such as distractors, occlusions, or object motion. However, their gains transfer only partially to the stronger SAM 3 backbone. We instead present a more general, data-driven approach that frames memory control as a sequential decision-making task. SAM3RL is an extension of the SAM 3 tracker with a lightweight memory controller, trained by reinforcement learning, that decides which frames enter the memory bank in order to maximize tracking performance. SAM3RL sets a new state of the art on 10 of 12 tracking and video object segmentation benchmarks, outperforming all hand-crafted rules without any runtime overhead. The same approach applied to SAM 2 gives SAM2RL, which outperforms hand-crafted rules on 9 of the 12 benchmarks, showing the generality of our method across model generations.

cs.CV↗

arXiv2026

Massively Parallel Proof-Number Search for Impartial Games and Beyond

Proof-Number Search is a best-first search algorithm with many successful applications, especially in game solving. As large-scale computing clusters become increasingly accessible, parallelization is a natural way to accelerate computation. However, existing parallel versions of Proof-Number Search are known to scale poorly on many CPU cores. Using two parallelized levels and shared information among workers, we present the first massively parallel version of Proof-Number Search that scales efficiently even on a large number of CPUs. We apply our solver, enhanced with Grundy numbers for reducing game trees of impartial games, to the Sprouts game, a case study motivated by the long-standing Sprouts Conjecture. Our algorithm achieves 332.9$\times$ speedup on 1024 cores, significantly improving previous parallelizations and outperforming the state-of-the-art Sprouts solver GLOP by four orders of magnitude in runtime while generating proofs 1,000$\times$ more complex. Despite exponential growth in game tree size, our solver verified the Sprouts Conjecture for 42 new positions, nearly doubling the number of known outcomes.

cs.AI↗

arXiv2025

SAM2RL: Towards Reinforcement Learning Memory Control in Segment Anything Model 2

Segment Anything Model 2 (SAM 2) has demonstrated strong performance in object segmentation tasks and has become the state-of-the-art for visual object tracking. The model stores information from previous frames in a memory bank, enabling temporal consistency across video sequences. Recent methods augment SAM 2 with hand-crafted update rules to better handle distractors, occlusions, and object motion. We propose a fundamentally different approach using reinforcement learning for optimizing memory updates in SAM 2 by framing memory control as a sequential decision-making problem. In an overfitting setup with a separate agent per video, our method achieves a relative improvement over SAM 2 that exceeds by more than three times the gains of existing heuristics. These results reveal the untapped potential of the memory bank and highlight reinforcement learning as a powerful alternative to hand-crafted update rules for memory control in visual object tracking.

cs.CV↗

arXiv2021

Implementation of Sprouts: a graph drawing game

Sprouts is a two-player pencil-and-paper game invented by John Conway and Michael Paterson in 1967. In the game, the players take turns in joining dots by curves according to simple rules, until one player cannot make a move. The game of Sprouts is very popular and simple-looking, so it may come as a surprise that there are essentially no AI Sprouts players available. This lack of computer opponents is caused by the fact that the game hides a surprisingly high combinatorial complexity and implementing it involves fascinating programming challenges. We overcome all the implementation barriers and create the first user-friendly Sprouts application with a strong artificial intelligence after more than 50 years of the existence of the game. In particular, we combine results from the theory of nimbers with new methods based on Delaunay triangulations and crossing-preserving force-directed algorithms to develop an AI Sprouts player which plays a perfect game on up to 11 spots.

cs.DM↗