Qwen/Qwen3.5-9B

Timeline

1. Oct 6, 2026 · Research paper · 2 sources
   CARE: Certifying Acceleration for Vision-Language-Action Inference
   Prior work accelerates VLA inference using techniques like action chunking and visual-token pruning, typically evaluating based on latency and average task success.
2. Sep 30, 2026 · Open-source release · 1 source
   Cloudflare/clef-flash
   Cloudflare published the model clef-flash on Hugging Face.

Often appears with