# Training-Free Guidance

Compressing visual tokens for video large language models costs feature comparisons in the compression decisions themselves. This method aligns reference-frame dependencies, motion vectors and residuals already present in compressed video to the visual token grid, uses them to propose small candidate sets, then verifies with local visual similarity. Across three video LLMs and four video-understanding benchmarks, performance matches the training-free baseline FlashVID and sometimes exceeds it, while comparisons for token protection and temporal matching drop substantially.

Compressing visual tokens for video large language models costs feature comparisons in the compression decisions themselves. This method aligns reference-frame dependencies, motion vectors and residuals already present in compressed video to the visual token grid, uses them to propose small candidate sets, then verifies with local visual similarity. Across three video LLMs and four video-understanding benchmarks, performance matches the training-free baseline FlashVID and sometimes exceeds it, while comparisons for token protection and temporal matching drop substantially.

The work represents polycrystalline microstructures as anisotropic power diagrams (APDs), learns a flow-matching generative model over their compact geometric parameters with a graph neural network, and introduces a C4-equivariant architecture so that rotations of the input noise produce corresponding rotations of the generated microstructure; a training-free guidance framework then generates morphologies qualitatively inspired by copper welds, cast metal slabs, 3D-printed stainless steel, and heterogeneous lamella titanium without retraining.

The work represents polycrystalline microstructures as anisotropic power diagrams (APDs), learns a flow-matching generative model over their compact geometric parameters with a graph neural network, and introduces a C4-equivariant architecture so that rotations of the input noise produce corresponding rotations of the generated microstructure; a training-free guidance framework then generates morphologies qualitatively inspired by copper welds, cast metal slabs, 3D-printed stainless steel, and heterogeneous lamella titanium without retraining.