Multimodal Models · Kuaishou Technology
Kwai Keye-VL-2.0: Open Long-Video Multimodal Agent Model
Kwai Keye-VL-2.0 is a 30B-A3B open MoE multimodal model with 256K context, strong long-video scores, and 62.0 on SWE-bench Verified.
Institution
Kuaishou Technology
Chinese short-video and live-streaming company whose Kling Team builds the Kling video generation models; the Kling team authored this work.
Video Generation · Kuaishou Technology
VLM Teachers Score Video-Model Reasoning at Test Time
Instead of asking a video model to reason directly, a VLM grades its in-progress frames and fine-tunes a per-instance LoRA. The trick lifts RULER-Bench from 46.4 to 68.2.