Piotr Milos

Venues

Frequent coauthors

Papers

1. Contrastive Representations for Temporal Reasoning
   NeurIPS 2025 ·

   Alicja Ziarko

   DBLP profile ↗ORCID search ↗
2. Joint MoE Scaling Laws: Mixture of Experts Can Be Memory Efficient
   ICML 2025 ·

   Jan Ludziejewski

   DBLP profile ↗ORCID search ↗
3. Since Faithfulness Fails: The Performance Limits of Neural Causal Discovery
   ICML 2025 ·

   Mateusz Olko

   DBLP profile ↗ORCID search ↗
4. Structured Packing in LLM Training Improves Long Context Utilization
   AAAI 2025 ·

   Konrad Staniszewski

   DBLP profile ↗ORCID search ↗
5. Analysing The Impact of Sequence Composition on Language Model Pre-Training
   ACL 2024 ·

   Yu Zhao

   DBLP profile ↗ORCID search ↗
6. Bigger, Regularized, Optimistic: scaling for compute and sample efficient continuous control
   NeurIPS 2024 ·

   Michal Nauman

   DBLP profile ↗ORCID search ↗
7. Fine-tuning Reinforcement Learning Models is Secretly a Forgetting Mitigation Problem
   ICML 2024 ·

   Maciej Wolczyk

   DBLP profile ↗ORCID search ↗
8. Magnushammer: A Transformer-Based Approach to Premise Selection
   ICLR 2024 ·

   Maciej Mikula

   DBLP profile ↗ORCID search ↗
9. Overestimation, Overfitting, and Plasticity in Actor-Critic: the Bitter Lesson of Reinforcement Learning
   ICML 2024 ·

   Michal Nauman

   DBLP profile ↗ORCID search ↗
10. Repurposing Language Models into Embedding Models: Finding the Compute-Optimal Recipe
    NeurIPS 2024 ·

    Albert Q. Jiang

    DBLP profile ↗ORCID search ↗