Shiva-DiT: Residual-Based Differentiable Top-$k$ Selection for Efficient Diffusion Transformers

arXiv:2602.05605v2 Announce Type: replace-cross Abstract: Diffusion Transformers (DiTs) are costly at high resolution because self-attention scales quadratically with token sequence length.

Existing pruning methods do not jointly provide end-to-end learnability, low training overhead, and deterministic token counts for predictable token-dependent computation.

We propose Shiva-DiT, based on Residual-Based Differentiable Top-k Selection. Its forward pass executes hard top-k selection, while a residual-aware straight-through estimator propagates gradients to both token scores and the budget k without evaluating a second backbone path. A Context-Aware Router and Adaptive Ratio Policy learn layer- and timestep-dependent retention schedules under a target average budget.

Experiments on SD3-Medium, Flux.1-dev, and PixArt-{\Sigma} show consistent reductions in FLOPs and measured latency. On SD3-Medium, Shiva-DiT provides four fidelity-latency operating points and reaches a 1.54x wall-clock speedup with competitive fidelity.