Viacheslav

ummagumm-a's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

authored 3 papers 5 months ago

You Do Not Fully Utilize Transformer's Representation Capacity

Paper • 2502.09245 • Published Feb 13 • 38

XLand-100B: A Large-Scale Multi-Task Dataset for In-Context Reinforcement Learning

Paper • 2406.08973 • Published Jun 13, 2024 • 90

The Differences Between Direct Alignment Algorithms are a Blur

Paper • 2502.01237 • Published Feb 3 • 115

authored 3 papers over 1 year ago

XLand-MiniGrid: Scalable Meta-Reinforcement Learning Environments in JAX

Paper • 2312.12044 • Published Dec 19, 2023 • 4

In-Context Reinforcement Learning for Variable Action Spaces

Paper • 2312.13327 • Published Dec 20, 2023 • 4

Emergence of In-Context Reinforcement Learning from Noise Distillation

Paper • 2312.12275 • Published Dec 19, 2023 • 4