Tag
The author shares insights from training a small model with DeepSeek's latent attention, observing layer-dependent latent usage and a test-time trick that reduces KV cache 4x without loss change.
This paper introduces a paradigm where Vision-Language Models (VLMs) act as test-time teachers to guide Video Generation Models (VGMs) via differentiable rewards and LoRA optimization, achieving a 16.7-point average improvement on video reasoning benchmarks.