Łukasz Kuciński
11 papers · 2021–2025 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+4 more ↓ Show less ↑
🐝 Cross-Pollinator (15) 🌉 Interdisciplinary Bridge 🗺️ Taxonomy Completionist (19) 🧭 Keyword Pioneer 🌍 Conference Polyglot (4)
🌈
Renaissance Researcher
(7)
🏆
Grand Slam
💎
Century Club
(11)
🔥
Unstoppable
(5)
Conferences
NIPS (5)
ICLR (4)
AAAI (1)
ICML (1)
Top co-authors
Keywords
reinforcement learning
(2)
continual learning
(2)
transfer learning
(1)
causal discovery
(1)
puzzle solving
(1)
signaling games
(1)
best-first search
(1)
continual reinforcement learning
(1)
gradient descent
(1)
continuous control
(1)
inductive bia
(1)
soft actor-critic
(1)
context window
(1)
interventional datum
(1)
long context
(1)
search algorithm
(1)
emergent communication
(1)
context utilization
(1)
noisy channel
(1)
large language model
(1)
Papers
Structured Packing in LLM Training Improves Long Context Utilization
AAAI 2025
BALROG: Benchmarking Agentic LLM and VLM Reasoning On Games
ICLR 2025
Accelerating Goal-Conditioned Reinforcement Learning Algorithms and Research
ICLR 2025
Fine-tuning Reinforcement Learning Models is Secretly a Forgetting Mitigation Problem
ICML 2024
Magnushammer: A Transformer-Based Approach to Premise Selection
ICLR 2024
Fast and Precise: Adjusting Planning Horizon with Adaptive Subgoal Search
ICLR 2023
Trust Your $\nabla$: Gradient-based Intervention Targeting for Causal Discovery
NIPS 2023
Disentangling Transfer in Continual Reinforcement Learning
NIPS 2022
Subgoal Search For Complex Reasoning Tasks
NIPS 2021
Continual World: A Robotic Benchmark For Continual Reinforcement Learning
NIPS 2021
Catalytic Role Of Noise And Necessity Of Inductive Biases In The Emergence Of Compositional Communication
NIPS 2021