Viacheslav Sinii

16 papers A* 4Journal 11Unranked 1

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	F-GRPO: Don't Let Your Policy Learn the Obvious and Forget the Rare. CoRR Daniil Plyusov, Alexey Gorbatovski, Boris Shaposhnikov, Viacheslav Sinii, Alexey Malakhov, Daniil Gavrilov
2025	J	`jnl`	ESSA: Evolutionary Strategies for Scalable Alignment. CoRR Daria Korotyshova, Boris Shaposhnikov, Alexey Malakhov, Nikita Surnachev, George Bredis, Alexey Gorbatovski, Viacheslav Sinii, Daniil Gavrilov
2025	J	`jnl`	Enhancing Vision-Language Model Training with Reinforcement Learning in Synthetic Worlds for Real-World Success. CoRR George Bredis, Stanislav Dereka, Viacheslav Sinii, Ruslan Rakhimov, Daniil Gavrilov
2025	J	`jnl`	Small Vectors, Big Effects: A Mechanistic Study of RL-Induced Reasoning via Steering Vectors. CoRR Viacheslav Sinii, Nikita Balagansky, Gleb Gerasimov, Daniil Laptev, Yaroslav Aksenov, Vadim Kurochkin, Alexey Gorbatovski, Boris Shaposhnikov, Daniil Gavrilov
2025	A*	`conf`	Steering LLM Reasoning Through Bias-Only Adaptation. EMNLP Viacheslav Sinii, Alexey Gorbatovski, Artem Cherepanov, Boris Shaposhnikov, Nikita Balagansky, Daniil Gavrilov
2025	J	`jnl`	Steering LLM Reasoning Through Bias-Only Adaptation. CoRR Viacheslav Sinii, Alexey Gorbatovski, Artem Cherepanov, Boris Shaposhnikov, Nikita Balagansky, Daniil Gavrilov
2025	J	`jnl`	The Differences Between Direct Alignment Algorithms are a Blur. CoRR Alexey Gorbatovski, Boris Shaposhnikov, Viacheslav Sinii, Alexey Malakhov, Daniil Gavrilov
2025	J	`jnl`	You Do Not Fully Utilize Transformer's Representation Capacity. CoRR Gleb Gerasimov, Yaroslav Aksenov, Nikita Balagansky, Viacheslav Sinii, Daniil Gavrilov
2024	A*	`conf`	Emergence of In-Context Reinforcement Learning from Noise Distillation. ICML Ilya Zisman, Vladislav Kurenkov, Alexander Nikulin, Viacheslav Sinii, Sergey Kolesnikov
2024	A*	`conf`	In-Context Reinforcement Learning for Variable Action Spaces. ICML Viacheslav Sinii, Alexander Nikulin, Vladislav Kurenkov, Ilya Zisman, Sergey Kolesnikov
2024	J	`jnl`	XLand-100B: A Large-Scale Multi-Task Dataset for In-Context Reinforcement Learning. CoRR Alexander Nikulin, Ilya Zisman, Alexey Zemtsov, Viacheslav Sinii, Vladislav Kurenkov, Sergey Kolesnikov
2024	A*	`conf`	XLand-MiniGrid: Scalable Meta-Reinforcement Learning Environments in JAX. NeurIPS Alexander Nikulin, Vladislav Kurenkov, Ilya Zisman, Artem Agarkov, Viacheslav Sinii, Sergey Kolesnikov
2023	J	`jnl`	Emergence of In-Context Reinforcement Learning from Noise Distillation. CoRR Ilya Zisman, Vladislav Kurenkov, Alexander Nikulin, Viacheslav Sinii, Sergey Kolesnikov
2023	J	`jnl`	In-Context Reinforcement Learning for Variable Action Spaces. CoRR Viacheslav Sinii, Alexander Nikulin, Vladislav Kurenkov, Ilya Zisman, Sergey Kolesnikov
2023	—	`conf`	Understanding the Effectiveness of Cross-Domain Contrastive Unsupervised Domain Adaptation. Tiny Papers @ ICLR Viacheslav Sinii, Adín Ramírez Rivera, Adil Khan
2023	J	`jnl`	XLand-MiniGrid: Scalable Meta-Reinforcement Learning Environments in JAX. CoRR Alexander Nikulin, Vladislav Kurenkov, Ilya Zisman, Artem Agarkov, Viacheslav Sinii, Sergey Kolesnikov