Dmitri Babaev
dllllb
		AI & ML interests
PLP, RL, sequential data
		Recent Activity
						upvoted 
								an
								article
							
						24 days ago
						
					
						
						
						From GRPO to DAPO and GSPO: What, Why, and How
						
						authored 
								a paper
							
						about 1 month ago
						
					
						
						
						SWE-MERA: A Dynamic Benchmark for Agenticly Evaluating Large Language
  Models on Software Engineering Tasks
						
						authored 
								a paper
							
						about 1 month ago
						
					
						
						
						MERA Code: A Unified Framework for Evaluating Code Generation Across
  Tasks