List your company

Semantic Recognition on AIDE 5->5 rollout (test)

73.35DBR (F1)Non-causal (bidir)
5.666823.238440.8158.3816May 6, 2026

Evaluation results

MethodLinks
Non-causal (bidir)Rollout Protocol=5→5, VLM Interface=Qwen3-VL, Causality=Non-causal2026.0573.3574.4688.6568.82
Driver-WM (full pretrained)Rollout Protocol=5→5, VLM Interface=Qwen3-VL, Causality=Causal, Pre-training status=Full pretrained2026.0573.2273.9790.5462.09
Driver-WM (main)Rollout Protocol=5→5, VLM Interface=Qwen3-VL, Causality=Causal2026.0568.0772.6190.1568.34
Cross-Attn onlyRollout Protocol=5→5, VLM Interface=Qwen3-VL, Causality=Causal2026.0562.5268.7587.9469.09
MotionBERTRollout Protocol=5→5, VLM Interface=None, Causality=Causal2026.0556.752.71——
Static pooling (no rollout)Rollout Protocol=5→5, VLM Interface=Qwen3-VL, Causality=Causal (no rollout)2026.0554.0460.0726.3914
Offline Enc-DecRollout Protocol=5→5, VLM Interface=None, Causality=Offline2026.0553.8250.68——
Late fusionRollout Protocol=5→5, VLM Interface=Qwen3-VL, Causality=Causal2026.0545.8749.187.8565.97
SiMLPeRollout Protocol=5→5, VLM Interface=None, Causality=Causal2026.0537.2641.69——
Single-streamRollout Protocol=5→5, VLM Interface=Qwen3-VL, Causality=Causal2026.0524.5624.3526.3914
ST-GCNRollout Protocol=5→5, VLM Interface=None, Causality=Causal2026.0518.9622.66——
Zero-VelocityRollout Protocol=5→5, VLM Interface=None, Causality=Causal2026.058.2714.94——