Společný seminář katedry teoretické informatiky a matematické logiky MFF UK a oddělění umělé inteligence ústavu informatiky AV ČR
Organized jointly by the Department of Theoretical Computer Science and Mathematical Logic, Faculty of Mathemeatics and Physics of the Charles University, and by the Department of Artificial Intelligence, Institute of Computer Science of the Czech Academy of Sciences
Kontakt: / Contact:
Martin Holeňa
www.cs.cas.cz/~martin
+420 737 860 939
martin@cs.cas.cz
Isam Vrce. Reinforcement Learning Built for Acceleration: Sparse Topology Control, Stability, and Hardware-Aware Training
Isam will explore how hardware-aware semi-structured sparsity can make deep reinforcement learning more computationally efficient while preserving final performance, using sparse training from scratch, sparse topology adaptation, and replay-aware mask updates
Přehled seminářů v roce 2026 / List of seminars in 2026
26. 11. |
Johannes Bendler |
Configuring Neuro-Symbolic Systems for Guaranteed CARE Properties with Application in Hybrid Intelligence | |
12. 11. |
Davide Cazzarola |
AI for Value-Based Procurement: Interpretable and Uncertainty-Aware Methods to Support Healthcare Purchasing | |
29. 10. |
Michael Rottoli |
Adaptive Output Length for Efficient Inference in Diffusion Language Models | |
15. 10. |
Storm Visser |
Artificial Immune Systems: Multiclass Classification and Hybrid Methods | |
1. 10. |
Isam Vrce |
Reinforcement Learning Built for Acceleration: Sparse Topology Control, Stability, and Hardware-Aware Training | |
14. 5. |
Noe Lallouet |
Multi-objective Neural Architecture Design Using Monte Carlo Search |
|
30. 4. |
Dario Vajda |
Scaling LLM Alignment Beyond Supervised Fine-Tuning: Solving the Data Reliance Bottleneck |
|
16. 4. |
Benjamin Moore |
Automated and Robust Shape Optimisation of Industrial Wastewater Systems Using Multi-Objective Bayesian Methods |
|
2. 4. |
Marcel Salvenmoser |
Evolving Prompt Embeddings of Diffusion Models for Optimization and Exploration of Synthetic Images |
|
19. 3. |
David Moe |
Conformal Predictors meet Active Learning: Adaptive Systems for Efficient Industrial Monitoring in Non-Stationary Environments |
|
19. 2. |
Ondřej Maršálek and Pavol Šimko |
Machine-learned interatomic potentials for molecular dynamics: committees and foundation models |
Přehled seminářů v roce 2025 / List of seminars in 2025
18. 12. |
Valentin Margraf |
Imprecise Acquisitions in Bayesian Optimization |
|
4. 12. |
Matthias Wolf |
CVKAN: Complex-Valued Kolmogorov-Arnold Networks |
|
20. 11. |
Antonio Purificato |
Recommendation Systems: From Traditional Approaches to Sheaf Neural Networks |
|
6. 11. |
Christos Fragkathoulas |
Counterfactual Explanations in ML: Concepts, Methods, and Fairness Audits |
|
23. 10. |
Francesco Caso |
Entropy, Renormalization, and Structure: Toward Physically-Inspired Learning Across Domains |
|
9. 10. |
Arno Geimer |
To the Winner Go the Spoils: Decentralized Machine Learning and the Fair Rewarding of Participation |
|
22. 5. |
Victor Letzelter |
Learning under Ambiguity through Multiple Hypotheses and Quantization |
|
24. 4. |
Jelle Hüntelmann |
Learning to be Uncertain: Of Soft Labels and Soft Losses |
|
10. 4. |
Marcel Kühn |
Anti-Correlated Noise in Epoch-Based Stochastic Gradient Descent and its Implications |
|
27. 3. |
Andreas Opedal |
Systematic Analysis of the Arithmetic Reasoning Capabilities of LLMs |
|
13. 3. |
Antoni Kowalczuk |
Image Autoregressive Models Leak More Training Data Than Diffusion Models |
|
27. 2. |
Thomas Kleine Buening |
Strategic Interactive Decision-Making |
Archiv: / Archive: 2008, 2009, 2010, 2011, 2012, 2013, 2014, 2015, 2016, 2017, 2018, 2019, 2020, 2021, 2022, 2023, 2024