arxiv:2602.23881
Sergei
southfreebird
AI & ML interests
None yet
Recent Activity
authored a paper about 1 month ago
LK Losses: Direct Acceptance Rate Optimization for Speculative Decoding authored a paper about 1 month ago
Guided Search Strategies in Non-Serializable Environments with Applications to Software Engineering Agents authored a paper about 1 month ago
Training Long-Context, Multi-Turn Software Engineering Agents with
Reinforcement LearningOrganizations
models 16
southfreebird/vla-0-smol-so101-test100-10k
Updated
southfreebird/act_so101_test_100_500k
Updated
southfreebird/act_so101_test_100_200k
Updated
southfreebird/act_so101_test_2_200k
Updated • 2
southfreebird/act_so101_test_1
Updated
southfreebird/act_so101_test
Updated
southfreebird/evgerher-secret
Updated
southfreebird/Qwen2.5-Coder-1.5B-Instruct-FP8
2B • Updated • 1
southfreebird/Qwen2.5-Coder-1.5B-Instruct
Text Generation • Updated • 1
southfreebird/Qwen2.5-Coder-0.5B-Instruct-FP8
0.6B • Updated • 1