PulseQuant：面向4比特视频扩散Transformer的传播引导子空间校正

中文摘要 AI 辅助

视频扩散Transformer中的量化误差会被后续的去噪更新放大或衰减，这使得局部重建误差成为最终影响的非完整预测指标。我们提出PulseQuant，一种4比特训练后量化方法，将轨迹敏感性与激活几何相结合以指导离线校准。孤立的块-步干预用于估计传播风险，该风险在行半径选择过程中优先考虑敏感轨迹状态。在固定这些半径后，响应子空间校正利用相邻码编辑来减少沿主导激活方向的残差分量。两个阶段均保留原始的4比特权重表示。受控干预表明，短时程传播误差比即时块输出误差更可靠地预测最终潜在误差，支持超越局部重建目标的校准。在Wan模型、Self Forcing和MiniMax-H3上的评估表明，关键一致性和密集参考指标得到改善，同时在不同模型规模和生成范式下保持其他属性的竞争力。

英文摘要

Quantization errors in video diffusion transformers can be amplified or attenuated by subsequent denoising updates, making local reconstruction error an incomplete predictor of final impact. We introduce PulseQuant, a 4-bit post-training quantization method that combines trajectory sensitivity with activation geometry to guide offline calibration. Isolated block--step interventions estimate propagation risk, which prioritizes sensitive trajectory states during row-radius selection. With these radii fixed, response-subspace correction uses neighboring-code edits to reduce residual components along dominant activation directions. Both stages preserve the original 4-bit weight representation. Controlled interventions show that short-horizon propagated error predicts final latent error more reliably than immediate block-output error, supporting calibration beyond local reconstruction objectives. Evaluations on Wan models, Self Forcing, and MiniMax-H3 demonstrate improvements in key consistency and dense-reference metrics while remaining competitive on other attributes across model scales and generation paradigms.

发表机构

• The University of Sydney（悉尼大学）
• The Hong Kong University of Science and Technology（香港科技大学）
• Shanghai AI Laboratory（上海人工智能实验室）
• The Chinese University of Hong Kong（香港中文大学）

机构由 AI 辅助整理，请以论文原文为准。