AmericasNLP 2026 entry with Aya Vision 32B, using SFT for MT and SFT for Indigenous-language image captioning.
Luis Lara
ludolara
AI & ML interests
None yet
Recent Activity
liked a model 6 days ago
CohereLabs/North-Small-Translate-1.0 liked a model 7 days ago
deepseek-ai/DeepSeek-V4.1-Flash liked a Space about 1 month ago
ICML-2026-agent-repro/challengeOrganizations
LoRA-based SFT adapters and RLVR-trained checkpoints for RPLAN floor-plan generation with Llama-3.3-70B-Instruct.
-
Generative Floor Plan Design with LLMs via Reinforcement Learning with Verifiable Rewards
Paper • 2605.14117 • Published • 1 -
ludolara/fp5-rlvr-Llama3.3-70B
Text Generation • 71B • Updated • 17 -
ludolara/fp5-sft-Llama3.3-70B
Updated • 10 -
ludolara/fp6-rlvr-Llama3.3-70B
Text Generation • 71B • Updated • 13
AmericasNLP 2026 entry with Aya Vision 32B, using SFT for MT and SFT for Indigenous-language image captioning.
LoRA-based SFT adapters and RLVR-trained checkpoints for RPLAN floor-plan generation with Llama-3.3-70B-Instruct.
-
Generative Floor Plan Design with LLMs via Reinforcement Learning with Verifiable Rewards
Paper • 2605.14117 • Published • 1 -
ludolara/fp5-rlvr-Llama3.3-70B
Text Generation • 71B • Updated • 17 -
ludolara/fp5-sft-Llama3.3-70B
Updated • 10 -
ludolara/fp6-rlvr-Llama3.3-70B
Text Generation • 71B • Updated • 13