Qwen3.5-9B-aerialsim-rl-step100 API & Inference Endpoint

Base: Qwen/Qwen3.5-9B (dense multimodal, qwen3_5 arch)
Environment: aerialsim-env v0.1, Cosys-AirSim / UE5.5 Blocks scene, 17 scenario families
Observation mode: both (RGB frame + text scaffold with landing_zone_clear, obstacle_ahead, distance_to_goal, waypoints)
Reward: binary success on terminal action
Algorithm: GRPO, batch_size=4, group_size=4
Optimizer: AdamW with CPU offload, lr=5e-7
Rollout sampler: temperature=0.3, max_completion_tokens=1024
Eval sampler: temperature=0.0
Sequence length: 4096
GPU split: 2 train + 2 infer, tensor_parallel=2 on each side
Steps: 100

Per-family deterministic (T=0, single decode) eval with scaffolded text state is pending; will be reported in the accompanying paper.

Research on visual-grounded aerial safety decisions and RL fine-tuning of multimodal LLMs on simulated aerial mission scenarios.

Nahid Alam (@nahidalam) — Maya Multimodal

Base: Qwen/Qwen3.5-9B (dense multimodal, qwen3_5 arch)
Environment: aerialsim-env v0.1, Cosys-AirSim / UE5.5 Blocks scene, 17 scenario families
Observation mode: both (RGB frame + text scaffold with landing_zone_clear, obstacle_ahead, distance_to_goal, waypoints)
Reward: binary success on terminal action
Algorithm: GRPO, batch_size=4, group_size=4
Optimizer: AdamW with CPU offload, lr=5e-7
Rollout sampler: temperature=0.3, max_completion_tokens=1024
Eval sampler: temperature=0.0
Sequence length: 4096
GPU split: 2 train + 2 infer, tensor_parallel=2 on each side
Steps: 100

Per-family deterministic (T=0, single decode) eval with scaffolded text state is pending; will be reported in the accompanying paper.

Research on visual-grounded aerial safety decisions and RL fine-tuning of multimodal LLMs on simulated aerial mission scenarios.

Nahid Alam (@nahidalam) — Maya Multimodal

Qwen3.5-9B-aerialsim-rl-step100