{"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/redefining-temporal-modeling-in-video","title":"Redefining Temporal Modeling in Video Diffusion: The Vectorized Timestep Approach","arxiv_id":"2410.03160","date":"2024-10-04","proceeding":null,"authors":["Yaofang Liu","Yumeng Ren","Xiaodong Cun","Aitor Artola","Yang Liu","Tieyong Zeng","Raymond H. Chan","Jean-Michel Morel"],"abstract":"Diffusion models have revolutionized image generation, and their extension to video generation has shown promise. However, current video diffusion models~(VDMs) rely on a scalar timestep variable applied at the clip level, which limits their ability to model complex temporal dependencies needed for various tasks like image-to-video generation. To address this limitation, we propose a frame-aware video diffusion model~(FVDM), which introduces a novel vectorized timestep variable~(VTV). Unlike conventional VDMs, our approach allows each frame to follow an independent noise schedule, enhancing the model's capacity to capture fine-grained temporal dependencies. FVDM's flexibility is demonstrated across multiple tasks, including standard video generation, image-to-video generation, video interpolation, and long video synthesis. Through a diverse set of VTV configurations, we achieve superior quality in generated videos, overcoming challenges such as catastrophic forgetting during fine-tuning and limited generalizability in zero-shot methods.Our empirical evaluations show that FVDM outperforms state-of-the-art methods in video generation quality, while also excelling in extended tasks. By addressing fundamental shortcomings in existing VDMs, FVDM sets a new paradigm in video synthesis, offering a robust framework with significant implications for generative modeling and multimedia applications.","url_abs":"https://arxiv.org/abs/2410.03160v1","url_pdf":"https://arxiv.org/pdf/2410.03160v1.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":"redefining-temporal-modeling-in-video","repo_url":"https://github.com/yaofang-liu/fvdm","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"image-generation","task_name":"Image Generation"},{"task_slug":"image-to-video","task_name":"Image to Video Generation"},{"task_slug":"video-generation","task_name":"Video Generation"}],"methods":[{"method_slug":"clip","method_name":"CLIP"},{"method_slug":"diffusion","method_name":"Diffusion"},{"method_slug":"set","method_name":"SET"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2410.03160","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.03160"}},"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/yaofang-liu/fvdm","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":4,"ran_honours":1,"ran_draft_wrong":2,"unverified":3},"by_repo_kind":{"official":{"samples":10,"ran":7,"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":"72ee7e991255ed28","entry":"clip_grad_norm_","repo":"yaofang-liu/fvdm","repo_kind":"official","path":"utils.py","file_url":"https://github.com/yaofang-liu/fvdm/blob/HEAD/utils.py","link_basis":"first_harvest_node","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":"72ee7e991255ed28"}},{"code_sha256_prefix":"c92c27c924b517e8","entry":"get_2d_sincos_pos_embed","repo":"yaofang-liu/fvdm","repo_kind":"official","path":"models/latte.py","file_url":"https://github.com/yaofang-liu/fvdm/blob/HEAD/models/latte.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"c92c27c924b517e8"}},{"code_sha256_prefix":"f2b6bc25cb2bbec8","entry":"get_experiment_dir","repo":"yaofang-liu/fvdm","repo_kind":"official","path":"utils.py","file_url":"https://github.com/yaofang-liu/fvdm/blob/HEAD/utils.py","link_basis":"first_harvest_node","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":"f2b6bc25cb2bbec8"}},{"code_sha256_prefix":"64900e821beadb4e","entry":"get_grad_norm","repo":"yaofang-liu/fvdm","repo_kind":"official","path":"utils.py","file_url":"https://github.com/yaofang-liu/fvdm/blob/HEAD/utils.py","link_basis":"first_harvest_node","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":"64900e821beadb4e"}},{"code_sha256_prefix":"03310bba324ae4fb","entry":"modulate","repo":"yaofang-liu/fvdm","repo_kind":"official","path":"models/latte.py","file_url":"https://github.com/yaofang-liu/fvdm/blob/HEAD/models/latte.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"03310bba324ae4fb"}},{"code_sha256_prefix":"8456d8791757b15c","entry":"modulate_temp","repo":"yaofang-liu/fvdm","repo_kind":"official","path":"models/latte_video.py","file_url":"https://github.com/yaofang-liu/fvdm/blob/HEAD/models/latte_video.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"8456d8791757b15c"}},{"code_sha256_prefix":"129b804760b3115f","entry":"zero_module","repo":"yaofang-liu/fvdm","repo_kind":"official","path":"models/utils.py","file_url":"https://github.com/yaofang-liu/fvdm/blob/HEAD/models/utils.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"129b804760b3115f"}},{"code_sha256_prefix":"6fe195fcfd10e259","entry":"checkpoint","repo":"yaofang-liu/fvdm","repo_kind":"official","path":"models/utils.py","file_url":"https://github.com/yaofang-liu/fvdm/blob/HEAD/models/utils.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":"6fe195fcfd10e259"}},{"code_sha256_prefix":"c8dc321d086803c8","entry":"get_1d_sincos_temp_embed","repo":"yaofang-liu/fvdm","repo_kind":"official","path":"models/latte.py","file_url":"https://github.com/yaofang-liu/fvdm/blob/HEAD/models/latte.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":"c8dc321d086803c8"}},{"code_sha256_prefix":"319f00691ca1b97c","entry":"timestep_embedding","repo":"yaofang-liu/fvdm","repo_kind":"official","path":"models/utils.py","file_url":"https://github.com/yaofang-liu/fvdm/blob/HEAD/models/utils.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":"319f00691ca1b97c"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}