arxiv:2602.10231
Alexander
djalexj
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
about 2 hours ago
Blockwise Advantage Estimation for Multi-Objective RL with Verifiable Rewards
authored
a paper
about 4 hours ago
Blockwise Advantage Estimation for Multi-Objective RL with Verifiable Rewards
authored
a paper
about 4 hours ago
Guided Search Strategies in Non-Serializable Environments with Applications to Software Engineering Agents
Organizations
models
16
djalexj/gte-large-en-v1.5-rm
Text Classification
•
0.4B
•
Updated
•
1
djalexj/gpt-neo-1.3B-rlhf-se-150steps-latest
Text Generation
•
Updated
•
1
djalexj/gpt-neo-1.3B-rlhf-se-150steps-lora-latest
Updated
djalexj/gpt-neo-1.3B-rlhf-se-250steps-latest
Text Generation
•
Updated
•
1
djalexj/gpt-neo-1.3B-rlhf-se-250steps-lora-latest
Updated
djalexj/gpt-neo-1.3B-rlhf-se-100steps
Text Generation
•
Updated
•
1
djalexj/gpt-neo-1.3B-rlhf-se-100steps-lora
Updated
djalexj/bert-base-cased-rm-se-100000steps
Text Classification
•
Updated
•
3
djalexj/bert-base-cased-rm-se-100000steps-lora
Updated
djalexj/gpt-neo-1.3B-sft-se-4000steps
Text Generation
•
Updated
•
3