NVIDIA's GenAIR team on July 3 released Flex-Forcing, proposing a chunk mechanism defined along both the time axis and the denoising step count, unifying bidirectional diffusion and autoregressive video generation in the same model; bidirectional between chunks, autoregressive within chunks, granularity scales with the memory budget, supports arbitrary order rearrangement, simultaneously capturing longer video stability, higher visual quality, and faster inference on multiple video benchmarks. Project page: research.nvidia.com/labs/genair/flex-forcing.