Papers › Ca2-VDM: Efficient Autoregressive Video Diffusion Model with Causal Generation and...

Ca2-VDM: Efficient Autoregressive Video Diffusion Model with Causal Generation and Cache Sharing

25 Nov 2024arXiv:2411.16375archive 2025-07-28

Kaifeng Gao, Jiaxin Shi, Hanwang Zhang, Chunping Wang, Jun Xiao, Long Chen

With the advance of diffusion models, today's video generation has achieved impressive quality. To extend the generation length and facilitate real-world applications, a majority of video diffusion models (VDMs) generate videos in an autoregressive manner, i.e., generating subsequent clips conditioned on the last frame(s) of the previous clip. However, existing autoregressive VDMs are highly inefficient and redundant: The model must re-compute all the conditional frames that are overlapped between adjacent clips. This issue is exacerbated when the conditional frames are extended autoregressively to provide the model with long-term context. In such cases, the computational demands increase significantly (i.e., with a quadratic complexity w.r.t. the autoregression step). In this paper, we propose Ca2-VDM, an efficient autoregressive VDM with Causal generation and Cache sharing. For causal generation, it introduces unidirectional feature computation, which ensures that the cache of conditional frames can be precomputed in previous autoregression steps and reused in every subsequent step, eliminating redundant computations. For cache sharing, it shares the cache across all denoising steps to avoid the huge cache storage cost. Extensive experiments demonstrated that our Ca2-VDM achieves state-of-the-art quantitative and qualitative video generation results and significantly improves the generation speed. Code is available: https://github.com/Dawn-LX/CausalCache-VDM

PaperPDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2411.16375")

Code

Syntology Ran 9 of 21 code samples harvested from 3 repositories linked to this paper; 12 have no recorded run. Of those that ran: 2 ran · fixture could not drive it; 7 ran with no contract checked.

By repository: community (archive-listed): 6 samples from 1 repository, 0 ran; found in paper text by Syntology: 15 samples from 2 repositories, 9 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

dawn-lx/causalcache-vdm officialmentioned in papermentioned on GitHubpytorchApache-2.0 report
dawn-lx/causal-videogen mentioned on GitHubpytorchApache-2.0 report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

21 samples harvested; 9 ran; 0 honoured the contract we drafted; 12 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

2ran · fixture could not drive it
7ran
12unverified

Licence: 5 of the 21 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 3 repositories linked to this paper, official or community; each sample names its own and says which. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

all_to_all dawn-lx/causal-videogen/opensora/acceleration/communications.py community (archive-listed) unverified Apache-2.0 (permissive) · b51f59051d16f7df · report
auto_grad_checkpoint dawn-lx/causal-videogen/opensora/acceleration/checkpoint.py community (archive-listed) unverified Apache-2.0 (permissive) · 20336f4981288332 · report
build_module dawn-lx/causal-videogen/opensora/registry.py community (archive-listed) unverified Apache-2.0 (permissive) · 496f3cd2af0df2e1 · report
gather_forward_split_backward dawn-lx/causal-videogen/opensora/acceleration/communications.py community (archive-listed) unverified Apache-2.0 (permissive) · 97c082db7efd0240 · report
partial_causal_flash_attn dawn-lx/causal-videogen/opensora/models/causal_stdit2/attention.py community (archive-listed) unverified Apache-2.0 (permissive) · 5cbd445824659be5 · report
split_forward_gather_backward dawn-lx/causal-videogen/opensora/acceleration/communications.py community (archive-listed) unverified Apache-2.0 (permissive) · a771d32bab25e50b · report
Block songweige/TATS/tats/tats_transformer.py found in paper text by Syntology ran MIT (permissive) · c36e0664ff375f5b · report
CausalSelfAttention songweige/TATS/tats/tats_transformer.py found in paper text by Syntology ran fingerprinted MIT (permissive) · 0dcc3d2b5989bb48 · report
GPT songweige/TATS/tats/tats_transformer.py found in paper text by Syntology ran MIT (permissive) · 20e50a0db3aadd39 · report
GPTConfig songweige/TATS/tats/tats_transformer.py found in paper text by Syntology ran MIT (permissive) · cd407b6b077bc83e · report
Identity songweige/TATS/tats/tats_transformer.py found in paper text by Syntology ran MIT (permissive) · f020bb1b02990123 · report
Labelator songweige/TATS/tats/tats_transformer.py found in paper text by Syntology ran MIT (permissive) · b9f40f41b93875c6 · report
SOSProvider songweige/TATS/tats/tats_transformer.py found in paper text by Syntology ran MIT (permissive) · 6e1c0c9a43690fdb · report
accuracy songweige/TATS/tats/tats_transformer.py found in paper text by Syntology ran · fixture could not drive it MIT (permissive) · 085a09050f4f41dc · report
shift_dim songweige/TATS/tats/tats_transformer.py found in paper text by Syntology ran · fixture could not drive it fingerprinted MIT (permissive) · 791774067a83bf99 · report
Net2NetTransformer songweige/TATS/tats/tats_transformer.py found in paper text by Syntology unverified MIT (permissive) · af840b748b65873d · report
cfg_to_args_str universome/stylegan-v/src/infra/utils.py found in paper text by Syntology unverified no licence file found · pointer only · 2dc4f95b756cb2b3 · report
compute_fvd universome/stylegan-v/src/metrics/frechet_video_distance.py found in paper text by Syntology unverified no licence file found · pointer only · 0bf504441d3b1c0e · report
construct_experiments_args universome/stylegan-v/src/infra/slurm_batch_launch.py found in paper text by Syntology unverified no licence file found · pointer only · 2c35749b6eaa5bfe · report
num_gpus_to_mem universome/stylegan-v/src/infra/utils.py found in paper text by Syntology unverified no licence file found · pointer only · f29fb27caa548814 · report
to_dict universome/stylegan-v/src/infra/slurm_batch_launch.py found in paper text by Syntology unverified no licence file found · pointer only · 90b1bec775ebe652 · report

Tasks

DenoisingVideo Generation

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Diffusion

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections