{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/pisa-experiments-exploring-physics-post","title":"PISA Experiments: Exploring Physics Post-Training for Video Diffusion Models by Watching Stuff Drop","arxiv_id":"2503.09595","date":"2025-03-12","proceeding":null,"authors":["Chenyu Li","Oscar Michel","Xichen Pan","Sainan Liu","Mike Roberts","Saining Xie"],"abstract":"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.","url_abs":"https://arxiv.org/abs/2503.09595v1","url_pdf":"https://arxiv.org/pdf/2503.09595v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"pisa-experiments-exploring-physics-post","repo_url":"https://github.com/vision-x-nyu/pisa-experiments","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"diagnostic","task_name":"Diagnostic"},{"task_slug":"video-generation","task_name":"Video Generation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2503.09595","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.09595"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/vision-x-nyu/pisa-experiments","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":1,"unverified":7},"by_repo_kind":{"official":{"samples":8,"ran":1,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"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"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"af810cd485700e94","entry":"build_module","repo":"vision-x-nyu/pisa-experiments","repo_kind":"official","path":"opensora/registry.py","file_url":"https://github.com/vision-x-nyu/pisa-experiments/blob/HEAD/opensora/registry.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"af810cd485700e94"}},{"code_sha256_prefix":"0008d9cdcc5af39e","entry":"binary_mask_IOU","repo":"vision-x-nyu/pisa-experiments","repo_kind":"official","path":"utils/metrics.py","file_url":"https://github.com/vision-x-nyu/pisa-experiments/blob/HEAD/utils/metrics.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"0008d9cdcc5af39e"}},{"code_sha256_prefix":"e473e66fedc883c7","entry":"dice_loss","repo":"vision-x-nyu/pisa-experiments","repo_kind":"official","path":"sam2/training/loss_fns.py","file_url":"https://github.com/vision-x-nyu/pisa-experiments/blob/HEAD/sam2/training/loss_fns.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"e473e66fedc883c7"}},{"code_sha256_prefix":"b8f501ca29e77f1a","entry":"iou_loss","repo":"vision-x-nyu/pisa-experiments","repo_kind":"official","path":"sam2/training/loss_fns.py","file_url":"https://github.com/vision-x-nyu/pisa-experiments/blob/HEAD/sam2/training/loss_fns.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"b8f501ca29e77f1a"}},{"code_sha256_prefix":"67ba74e6741bc072","entry":"mask_to_points","repo":"vision-x-nyu/pisa-experiments","repo_kind":"official","path":"utils/metrics.py","file_url":"https://github.com/vision-x-nyu/pisa-experiments/blob/HEAD/utils/metrics.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"67ba74e6741bc072"}},{"code_sha256_prefix":"17da8dff24475bcc","entry":"save_video_from_frames","repo":"vision-x-nyu/pisa-experiments","repo_kind":"official","path":"data_processing/process_results.py","file_url":"https://github.com/vision-x-nyu/pisa-experiments/blob/HEAD/data_processing/process_results.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"17da8dff24475bcc"}},{"code_sha256_prefix":"7556f7e8aa8c3bc4","entry":"scaled_l2_distance","repo":"vision-x-nyu/pisa-experiments","repo_kind":"official","path":"utils/metrics.py","file_url":"https://github.com/vision-x-nyu/pisa-experiments/blob/HEAD/utils/metrics.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"7556f7e8aa8c3bc4"}},{"code_sha256_prefix":"42fec6fdc1faf6f1","entry":"sigmoid_focal_loss","repo":"vision-x-nyu/pisa-experiments","repo_kind":"official","path":"sam2/training/loss_fns.py","file_url":"https://github.com/vision-x-nyu/pisa-experiments/blob/HEAD/sam2/training/loss_fns.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"42fec6fdc1faf6f1"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}