CCTest · Blog
ProVisE Tests Spatial Reasoning by Letting Models Draw the Answer
Evaluation & Benchmarks
cctest.ai

ProVisE Tests Spatial Reasoning by Letting Models Draw the Answer

ProVisE addresses a subtle evaluation mismatch: many spatial tasks are easier to answer by pointing, marking, or drawing than by producing coordinates or text. The framework lets image-generation models respond in pixels and converts those visual answers back into benchmark-compatible predictions.

Read more
CCTest · Blog
SANA-Video 2.0: Hybrid Attention for Faster High-Resolution Video Generation
Vision & Video
cctest.ai
Vision & Video

SANA-Video 2.0: Hybrid Attention for Faster High-Resolution Video Generation

SANA-Video 2.0 proposes a hybrid video diffusion Transformer that keeps most of the efficiency benefits of linear attention while periodically restoring full softmax interactions. The paper reports competitive quality on a single H100, with notable speedups for longer and higher-resolution video generation.

Read more