Tinkoff.AI Research Papers

2024

• Linear Transformers with Learnable Kernel Functions are Better In-Context Models – ACL 2024, arxiv
• In-Context Reinforcement Learning for Variable Action Spaces – ICML 2024, arxiv
• Emergence of In-Context Reinforcement Learning from Noise Distillation – ICML 2024, arxiv
• Diversifying Deep Ensembles: A Saliency Map Approach for Enhanced OOD Detection, Calibration, and Accuracy – IEEE ICIP 2024, arxiv

2023

• Revisiting the Minimalist Approach to Offline Reinforcement Learning – NeurIPS 2023, code, arxiv
• CORL: Research-oriented Deep Offline Reinforcement Learning Library – NeurIPS 2023, code, arxiv
• Katakomba: Tools and Benchmarks for Data-Driven NetHack – NeurIPS 2023, code, arxiv
• XLand-MiniGrid: Scalable Meta-Reinforcement Learning Environments in JAX - IMOL@NeurIPS 2023, code, arxiv
• **Anti-Exploration by Random Network Distillation – ICML 2023, code**
• Time-dependent next-basket recommendations – ECIR 2023
• Time-Aware Item Weighting for the Next Basket Recommendations – RecSys 2023, arxiv
• Make your next item recommendation model time sensitive – First Workshop on Context Representation in User Modeling (CRUM) at UMAP 2023
• Revisiting Behavior Regularized Actor-Critic – Reincarnating Reinforcement Learning Workshop at ICLR 2023
• Hifi-vc: High quality asr-based voice conversion – Speech Synthesis Workshop 2023
• RecBaselines2023: a new dataset for choosing baselines for recommender models - BIR@ECIR
• Catching Image Retrieval Generalization
• …