Papers › PISA Experiments: Exploring Physics Post-Training for Video Diffusion Models by...

PISA Experiments: Exploring Physics Post-Training for Video Diffusion Models by Watching Stuff Drop

12 Mar 2025arXiv:2503.09595archive 2025-07-28

Chenyu Li, Oscar Michel, Xichen Pan, Sainan Liu, Mike Roberts, Saining Xie

Large-scale pre-trained video generation models excel in content creation but are not reliable as physically accurate world simulators out of the box. This work studies the process of post-training these models for accurate world modeling through the lens of the simple, yet fundamental, physics task of modeling object freefall. We show state-of-the-art video generation models struggle with this basic task, despite their visually impressive outputs. To remedy this problem, we find that fine-tuning on a relatively small amount of simulated videos is effective in inducing the dropping behavior in the model, and we can further improve results through a novel reward modeling procedure we introduce. Our study also reveals key limitations of post-training in generalization and distribution modeling. Additionally, we release a benchmark for this task that may serve as a useful diagnostic tool for tracking physical accuracy in large-scale video generative model development.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

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

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 8 code samples harvested from 1 repository linked to this paper: 8 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 8 samples from 1 repository, 8 ran (7 with no instrument failure; 1 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written between 2026-09-24 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

vision-x-nyu/pisa-experiments officialmentioned in papermentioned on GitHubpytorchApache-2.0Syntology: 8 samples, 8 ran (1 instrument-failed) · 0 unverified 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

8 samples harvested: 8 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · our draft was wrong
7ran

Licence: 3 of the 8 samples are pointer only, meaning Syntology does not serve that copy's text. For 3 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from vision-x-nyu/pisa-experiments. “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. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (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 are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. 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 six 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; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. 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.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

vision-x-nyu/pisa-experiments official repository 8 samples, 8 ran (1 instrument-failed) · 0 unverified
binary_mask_IOU utils/metrics.py ran Apache-2.0 (permissive) · 0008d9cdcc5af39e · report fixture: signature mask1:ndarray/4/int, mask2:ndarray/4/int · returned float64 · level recorded 2026-09-24
build_module in 5 papers opensora/registry.py ran · our draft was wrong Apache-2.0 (permissive) · af810cd485700e94 · report fixture: signature module:dict/0/?, builder:SimpleRegistry/0/? · returned SimpleModule · level recorded 2026-09-24
dice_loss in 193 papers
census: 10 implementations from 16 papers, 7 distinct outputs across 4 buckets, one shared input per bucket
sam2/training/loss_fns.py ran Apache-2.0 (permissive) here; the stored copy is pointer only · e473e66fedc883c7 · report fixture: signature inputs:Tensor/2/float, targets:Tensor/2/float, num_objects:int/0/int, loss_on_multimask:bool/0/bool · returned Tensor · level recorded 2026-09-25
iou_loss in 17 papers sam2/training/loss_fns.py ran Apache-2.0 (permissive) here; the stored copy is pointer only · b8f501ca29e77f1a · report fixture: signature inputs:Tensor/4/float, targets:Tensor/4/float, pred_ious:Tensor/2/float, num_objects:int/0/int, loss_on_multimask:bool/0/bool, use_l1_loss:bool/0/bool · returned Tensor · level recorded 2026-09-25
mask_to_points utils/metrics.py ran Apache-2.0 (permissive) · 67ba74e6741bc072 · report fixture: signature mask:ndarray/2/bool · returned ndarray · level recorded 2026-09-24
save_video_from_frames data_processing/process_results.py ran fingerprinted Apache-2.0 (permissive) · 17da8dff24475bcc · report fixture: signature frame_dir:str/0/str, fps:int/0/int · returned str · level recorded 2026-09-24
scaled_l2_distance utils/metrics.py ran Apache-2.0 (permissive) · 7556f7e8aa8c3bc4 · report fixture: signature centroid1:ndarray/1/float, centroid2:ndarray/1/float, resolution:float/0/float, scale_factor:float/0/float · returned float64 · level recorded 2026-09-24
sigmoid_focal_loss in 122 papers
census: 3 implementations from 9 papers, 2 distinct outputs across 2 buckets, one shared input per bucket
sam2/training/loss_fns.py ran Apache-2.0 (permissive) here; the stored copy is pointer only · 42fec6fdc1faf6f1 · report fixture: signature inputs:Tensor/2/float, targets:Tensor/2/float, num_objects:int/0/int, alpha:float/0/float, gamma:float/0/float, loss_on_multimask:bool/0/bool · returned Tensor · level recorded 2026-09-25

Tasks

DiagnosticVideo Generation

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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