PulseQuant: Propagation-Guided Subspace Correction for 4-Bit Video Diffusion Transformers

Yutong Wang; Xingtong Ge; Enhuai Liu; Yunke Wang; Tianfan Xue; Xinyuan Chen; Chang Xu

cs.CVSep 27, 2026

PulseQuant: Propagation-Guided Subspace Correction for 4-Bit Video Diffusion Transformers

Authors: Yutong Wang, Xingtong Ge, Enhuai Liu, Yunke Wang, Tianfan Xue, Xinyuan Chen, Chang Xu

Organizations: The University of Sydney · The Hong Kong University of Science and Technology · The Chinese University of Hong Kong · Shanghai AI Laboratory

Abstract

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.

Figures & tables

Figure 1: Propagation diagnostics from 80 isolated 4-bit interventions on Wan 2.1-14B (10 blocks $\times$ eight denoising steps), each followed by dense continuation. (a) Local block-output RMSE is weakly associated with final latent error. (b) Four-step propagated error $E_{H}$ predicts final damage after ranking blocks within each timestep. (c) Final damage depends strongly on trajectory position. Colors encode block depth and markers encode injection timestep.

Figure 2: Overview of PulseQuant. Isolated 4-bit pulses reveal how local perturbations propagate through denoising (left). The resulting risk weights guide per-row radius selection through a mean–tail output-error objective (center). With the selected radii fixed, legal neighboring-code edits reduce residual components along high-energy activation directions (right). The calibrated weights are exported as packed 4-bit indices and per-row scales, with no online profiling or correction.

Model	Method	W/A	VBench attributes (%)							Dense-reference fidelity
Model	Method	W/A	IQ $\uparrow$	AQ $\uparrow$	MS $\uparrow$	BC $\uparrow$	SC $\uparrow$	Scene $\uparrow$	OC $\uparrow$	PSNR $\uparrow$	SSIM $\uparrow$	LPIPS $\downarrow$
Wan 2.1-1.3B	Dense BF16	16/16	67.71	66.06	98.29	96.19	93.97	42.44	26.15	ref.	ref.	ref.
	SmoothQuant ( Xiao et al., 2023 )	4/6	59.83	58.12	98.12	94.77	91.14	30.96	24.20	14.78	0.464	0.499
	SVDQuant ( Li et al., 2024 )	4/6	63.68	63.57	97.83	95.20	92.62	35.61	25.42	15.36	0.513	0.433
	ViDiT-Q ( Zhao et al., 2024 )	4/6	63.60	63.68	97.78	95.03	92.70	38.08	25.73	14.86	0.503	0.447
	DVD-Quant ( Li et al., 2026c )	4/6	63.21	64.04	98.62	95.23	94.38	41.86	25.60	14.96	0.529	0.430

Table 1: Quantitative evaluations on VBench (T2V). VBench attributes are percentages; PSNR, SSIM, and LPIPS compare matched quantized and Dense BF16 videos. We bold the best results and underline the second-best results .

Model	Method	W/A	VBench attributes (%)								Dense-reference fidelity
Model	Method	W/A	IQ $\uparrow$	AQ $\uparrow$	MS $\uparrow$	DD $\uparrow$	BC $\uparrow$	SC $\uparrow$	Scene $\uparrow$	OC $\uparrow$	PSNR $\uparrow$	SSIM $\uparrow$	LPIPS $\downarrow$
Wan 2.1-T2V (#Param:14B)	Dense BF16	16/16	67.14	67.12	98.48	66.67	96.69	94.36	39.46	26.46	ref.	ref.	ref.
	ViDiT-Q ( Zhao et al., 2024 )	4/6	67.25	66.23	98.58	56.94	96.30	94.10	41.72	26.31	15.89	0.545	0.378
	OrbitQuant ( Lee et al., 2026 )	4/6	67.18	67.14	98.60	62.50	96.44	95.01	37.86	26.22	16.93	0.585	0.325
	PulseQuant (ours)	4/6	67.22	67.34	98.73	61.11	96.56	95.21	42.81	26.52	16.90	0.579	0.331
	ViDiT-Q ( Zhao et al., 2024 )	4/4	59.41	58.36	98.13	30.56	95.00	91.59	25.29	23.60	13.27	0.415	0.567

Table 2: Quantitative evaluations of scale and architecture transfer on VBench (T2V).

Figure 3: MiniMax-H3 W4A4 comparison at frames 5, 60, and 100 under the same condition.

Configuration	IQ $\uparrow$	AQ $\uparrow$	OC $\uparrow$	PSNR $\uparrow$	LPIPS $\downarrow$
Uniform PTQ	56.90	57.29	23.43	14.00	0.549
$+$ Rotation	63.20	62.39	24.70	14.97	0.443
$+$ Risk	64.38	64.97	25.73	15.59	0.414
$+$ Subspace corr.	64.64	64.24	25.74	15.61	0.412
PulseQuant	65.83	64.93	26.18	16.08	0.385

Table 3: Component ablation on Wan 2.1-T2V-1.3B W4A6 with

\lambda=0.5

and

\rho=0.25

Configuration	IQ $\uparrow$	AQ $\uparrow$	OC $\uparrow$	PSNR $\uparrow$	LPIPS $\downarrow$
Uniform PTQ	56.90	57.29	23.43	14.00	0.549
$+$ Rotation	63.20	62.39	24.70	14.97	0.443
$+$ Risk	64.38	64.97	25.73	15.59	0.414
$+$ Subspace corr.	64.64	64.24	25.74	15.61	0.412
PulseQuant	65.83	64.93	26.18	16.08	0.385

Table 3: Component ablation on Wan 2.1-T2V-1.3B W4A6 with

\lambda=0.5

and

\rho=0.25

Direction	IQ $\uparrow$	AQ $\uparrow$	DD $\uparrow$	Scene $\uparrow$	OC $\uparrow$
None	62.17	62.90	51.39	35.17	25.50
Random	61.62	62.86	48.61	37.72	25.38
Fixed Walsh	61.96	62.24	51.39	34.52	25.08
Calibrated (ours)	62.70	62.46	55.56	37.78	25.64

Table 4: Ablation results of correction-direction ablation on Wan 2.1-T2V-1.3B W4A4 with

\lambda=0.5

and

\rho=0.25

Figure 4: Sensitivity and profiling choices. (a–b) Risk-objective robustness on Wan 2.1-T2V-1.3B W4A4. (c–d) Propagation-horizon stability and anchor-grid agreement on Wan 2.1-T2V-14B.

Figure 5: Response-axis adaptation lowers subspace error with code edits and weight MSE in Wan-14B.

Figure 6: RTX 5080 W4A4 efficiency: (a) DiT memory; (b,c) VC/SageAttention2 per-step latency and speedup relative to BF16.

Appendix figures & tables15 assets

Supplementary material from the paper’s appendix.

Appendix

Stage	Setting	Default
Calibration data	Number of prompts	3
Calibration data	Prompt composition	Complementary coverage
Propagation profile	Horizon $H$	4 steps
Propagation profile	Anchor grid	$10$ blocks $\times$ $8$ timesteps
Risk objective	Tail weight $\lambda$	0.75
Risk objective	Tail fraction $\rho$	0.5

Appendix

Table 5: Default PulseQuant calibration configuration. Model-specific exceptions are reported with the evaluation protocol.

Symbol	Meaning
$\mathbf{W},\mathbf{x},\mathbf{X};m,d,N$	Weight matrix, token, batch; output/input widths, tokens
$\boldsymbol{\Pi}_{d},\mathbf{D}$	Orthogonal RPBH transform; positive channel scaling
$\mathcal{C},C_{k},c_{ij}$	Shared 16-value codebook, entry, and coordinate index
$Q_{A},b_{a}$	Activation quantizer and activation bit width
$r_{i}^{(0)},r_{i},\bar{r}_{i}$	Initial row norm (also denoted $r_{i}$ ) and calibrated radius
$\mathcal{R}_{i},K_{r},\eta$	Radius candidates, grid size, and relative half-span

Appendix

Table 6: Notation used in the method and implementation details.

	Components			VBench attributes (%)					Dense-reference fidelity
Configuration	Rotation	Risk	Subsp. corr.	IQ $\uparrow$	AQ $\uparrow$	MS $\uparrow$	BC $\uparrow$	OC $\uparrow$	PSNR $\uparrow$	SSIM $\uparrow$	LPIPS $\downarrow$	T-HP $\downarrow$
Uniform PTQ				56.90	57.29	97.38	95.01	23.43	14.00	0.421	0.549	0.161
Rotation only	$\checkmark$			63.20	62.39	98.09	95.01	24.70	14.97	0.512	0.443	0.155
Risk only	$\checkmark$	$\checkmark$		64.38	64.97	98.18	95.58	25.73	15.59	0.529	0.414	0.150
Subspace corr. only	$\checkmark$		$\checkmark$	64.64	64.24	98.26	95.69	25.74	15.61	0.536	0.412	0.142
PulseQuant	$\checkmark$	$\checkmark$	$\checkmark$	65.83	64.93	98.47	95.30	26.18	16.08	0.546	0.385	0.144

Appendix

Table 7: Complete component ablation on Wan 2.1-T2V-1.3B W4A6 under matched 300-layer coverage.

Figure 7: Layer-level activation and error diagnostics on Wan 2.1-14B W4A4 over one matched 50-step calibration trajectory. (a,b) Per-channel peak activation magnitudes before and after scaling and RPBH for the most outlier-heavy 128-channel group; planes and stars mark the 99th percentile and maximum, respectively. (c) Four-step propagation gains measured on $10$ blocks $\times$ $8$ timestep anchors; intermediate timesteps are interpolated only for visualization. (d,e) RMS output-response residuals relative to BF16 for naive W4A4 and PulseQuant, evaluated on 128 sampled output channels with a shared scale; bars report relative RMSE. (f) Pointwise residual reduction, where positive values favor PulseQuant. At this audited layer, relative RMSE decreases from 9.0% to 5.3%, and 96% of channel–timestep locations improve.

$\lambda$	$\rho$	VBench attributes (%)									Dense-reference fidelity			N-Jerk $\downarrow$
$\lambda$	$\rho$	IQ $\uparrow$	AQ $\uparrow$	MS $\uparrow$	DD $\uparrow$	BC $\uparrow$	SC $\uparrow$	Scene $\uparrow$	OC $\uparrow$	TF $\uparrow$	PSNR $\uparrow$	SSIM $\uparrow$	LPIPS $\downarrow$	N-Jerk $\downarrow$
$\rho$ sweep with $\lambda=0.75$
0.75	0.125	61.97	62.03	97.78	51.39	94.62	92.02	38.15	25.23	98.60	15.45	0.506	0.442	1.429
0.75	0.250	62.50	62.40	97.80	52.78	94.73	91.89	35.61	25.41	98.59	15.43	0.503	0.443	1.429
0.75	0.375	62.78	62.37	97.79	56.94	94.91	91.76	35.03	25.24	98.57	15.38	0.503	0.444	1.429
0.75	0.500	62.70	62.46	97.83	55.56	94.84	91.97	36.70	25.44	98.57	15.42	0.503	0.443	1.427

Appendix

Table 8: Propagation-risk sensitivity on Wan 2.1-T2V-1.3B W4A4. Gray rows mark the default

(\lambda,\rho)=(0.75,0.5)

Calibration set	ID	Calibration prompt
Complementary coverage	P1	A ceramic teapot rotating slowly on a wooden table in soft studio light
	P2	A glass marble rolling across a linen cloth while the camera tracks beside it
	P3	A small sailboat crossing a calm lake at dawn with gentle camera movement
Similar static	P1	A ceramic teapot resting on a wooden table under soft studio light, locked-off camera
	P2	A polished red apple resting on a linen-covered table under soft studio light, locked-off camera
	P3	A porcelain vase resting on a wooden shelf under soft studio light, locked-off camera

Appendix

Table 9: Exact three-prompt calibration sets for the MiniMax-H3 composition study; prompts are reproduced verbatim.

Prompt count: shared ordered prefix
Calibration set	# Prompts	VBench attributes (%)								Dense-reference fidelity
Calibration set	# Prompts	IQ $\uparrow$	AQ $\uparrow$	MS $\uparrow$	DD $\uparrow$	BC $\uparrow$	SC $\uparrow$	Scene $\uparrow$	OC $\uparrow$	PSNR $\uparrow$	SSIM $\uparrow$	LPIPS $\downarrow$
Dense BF16	–	68.57	65.38	99.01	75.00	96.08	92.55	47.60	26.64	ref.	ref.	ref.
Prefix-1	1	66.39	65.55	98.73	68.06	95.33	92.42	46.51	25.97	14.26	0.424	0.509
Prefix-3	3	66.83	65.43	98.73	70.83	94.97	92.23	46.88	26.24	14.17	0.424	0.514
Prefix-6	6	66.74	65.75	98.74	68.06	95.29	92.65	40.84	26.15	14.22	0.426	0.512

Appendix

Table 10: MiniMax-H3 W4A4 calibration-set sensitivity on the VBench.

Figure 8: Wan 2.1-1.3B W4A4 comparison for the Eiffel Tower under lightning.

Figure 9: Wan 2.1-1.3B W4A4 comparison for an animated kitten at a garden fountain.

Figure 10: Wan 2.1-1.3B W4A4 comparison for a woman walking along a beach at sunset.

Figure 11: Wan 2.1-1.3B W4A6 comparison for a brown bear in a forest clearing.

Figure 12: MiniMax-H3 W4A6 comparison for a porcelain cup on a carved wooden coaster.

Figure 13: MiniMax-H3 W4A6 comparison for a woman relaxing by the beach at sunset.

Figure 14: MiniMax-H3 W4A4 comparison for a zebra walking across a sunlit savanna.

Figure 15: MiniMax-H3 W4A4 comparison for yellow flowers swaying beside a wooden fence.

Explore similar work

OrbitQuant: Data-Agnostic Quantization for Image and Video Diffusion Transformers
Jul 2, 2026Donghyun Lee, Jitesh Chavan, Duy Nguyen +5Diffusion Transformers Quantizer
Cantina Labs · University of Southern California · *Work done during an internship at Cantina Labs. +1
KroQuant: Kronecker-Structured Block Transforms for Efficient Post-Training Quantization of Diffusion Transformers
Jul 23, 2026Yann Bouquet, Alireza Khodamoradi, Kristof Denolf +1Post-Training Quantization Diffusion Transformers
EPFL, Lausanne, Switzerland. · Advanced Micro Devices, Inc., Longmont, CO, USA.
Boundary-Protection W8A8 HiFloat8 Quantization for Large-Scale Text-to-Video Diffusion Transformers
May 31, 2026Yiming ZhaoText-To-Video Diffusion Models Video Diffusion Models
University of Chinese Academy of Sciences Beijing, China

Jul 2, 2026, cs.CVJ/K move · Enter open · S save

OrbitQuant: Data-Agnostic Quantization for Image and Video Diffusion Transformers

Donghyun Lee, Jitesh Chavan, Duy Nguyen, Sam Huang+4

Cantina Labs · University of Southern California · *Work done during an internship at Cantina Labs.+1

Diffusion Transformers Quantizer Video Generation

Open paper AskPDF arXiv

Diffusion transformers (DiTs) achieve state-of-the-art image and video generation, but their multi-step sampling and growing parameter count make inference expensive. Post-training quantization (PTQ) is the natural remedy, yet DiT activations shift across timesteps, prompts, and guidance branches, forcing prior methods to re-fit calibration data for every new checkpoint or modality. We present OrbitQuant, a data-agnostic weight-activation quantizer that bypasses range estimation by quantizing in a normalized, rotated basis. In this basis, a randomized permuted block-Hadamard (RPBH) rotation concentrates each coordinate around one fixed, known marginal regardless of the input, so a single Lloyd-Max codebook serves all timesteps, prompts, and layers of a given input dimension. We extend the same quantizer to weight rows offline, absorbing the rotation into the weights so that it cancels inside each linear layer and only a forward rotation on the activations remains at runtime. The same recipe transfers from image to video with no per-modality tuning. Across FLUX.1, Z-Image-Turbo, Wan 2.1, and CogVideoX, it sets the state of the art for PTQ at several low-bit settings. It also pushes PTQ of image diffusion transformers to W2A4 with usable generation quality.

Abstract

Explore similar work

OrbitQuant: Data-Agnostic Quantization for Image and Video Diffusion Transformers

KroQuant: Kronecker-Structured Block Transforms for Efficient Post-Training Quantization of Diffusion Transformers

Boundary-Protection W8A8 HiFloat8 Quantization for Large-Scale Text-to-Video Diffusion Transformers