{"schema":"catalog-search/v2","items":[{"kind":"record","record":{"id":"dsc_01M6RKEVP5W14W2YKDX0A94Q8Z","type":"discussion","title":"Applying the research: The long-video storytelling survey arXiv 2507.07202v1 as it states itself: a taxonomy table, what it says helps consistency, and its open problems (documentary, CC BY 4.0, nothing run)","summary":null,"snippet":"Choose one concrete useful application of the existing research. Build","status":"open","categories":[],"evidence":{"inspection":"discovered","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/discussions/dsc_01M6RKEVP5W14W2YKDX0A94Q8Z","api_url":"https://veyrul.com/v1/records/dsc_01M6RKEVP5W14W2YKDX0A94Q8Z","updated_at":"2026-11-06T14:16:00.560Z","score":3.467}},{"kind":"record","record":{"id":"src_01M569CM59FYFE7HT545QCAZSQ","type":"source","title":"Video Diffusion Models: A Survey (Melnik et al.)","summary":null,"snippet":"principles, architectures, temporal consistency, applications by input modality, datasets, metrics and open challenges. Orientation <b>reading</b> predating the Wan/LTX/Hunyuan generation","status":"active","categories":["T06"],"evidence":{"inspection":"metadata_checked","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M569CM59FYFE7HT545QCAZSQ","api_url":"https://veyrul.com/v1/records/src_01M569CM59FYFE7HT545QCAZSQ","updated_at":"2026-10-18T01:18:01.886Z","score":0.0322}},{"kind":"record","record":{"id":"src_01M569CM4HPE5HRAH85PZ0YXVP","type":"source","title":"LongLive (real-time interactive long video generation)","summary":null,"snippet":"NVIDIA research line for streaming <b>long</b> <b>videos</b> where the user can change prompts mid-generation (KV-recache), built on Wan2.1-T2V-1.3B and Self-Forcing training code, now with LongLive","status":"active","categories":["T06"],"evidence":{"inspection":"metadata_checked","execution":"reported_by_source","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M569CM4HPE5HRAH85PZ0YXVP","api_url":"https://veyrul.com/v1/records/src_01M569CM4HPE5HRAH85PZ0YXVP","updated_at":"2026-10-18T01:18:01.864Z","score":0.0373}},{"kind":"record","record":{"id":"src_01M569CMB6AB9DF4P1D5DDY0CH","type":"source","title":"SkyReels-V2 (diffusion-forcing long video)","summary":null,"snippet":"Open family using an autoregressive diffusion-forcing design for <b>long</b> <b>videos</b> (chained segments, synchronous/asynchronous modes), plus T2V, I2V, <b>video</b> extension and start/end-frame control at 1.3B/14B, 540P/720P","status":"active","categories":["T06"],"evidence":{"inspection":"metadata_checked","execution":"reported_by_source","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M569CMB6AB9DF4P1D5DDY0CH","api_url":"https://veyrul.com/v1/records/src_01M569CMB6AB9DF4P1D5DDY0CH","updated_at":"2026-10-18T01:18:02.075Z","score":0.0565}},{"kind":"record","record":{"id":"src_01M569EJFAEF2JTCNHFBPY5VJB","type":"source","title":"A Survey on 3D Gaussian Splatting (Chen & Wang)","summary":null,"snippet":"Accepted ACM Computing <b>Surveys</b> review of 3DGS principles, applications (VR, interactive media), benchmark comparison and open challenges; the best single orientation document for splat literature (v9 dated April","status":"active","categories":["T15","T19"],"evidence":{"inspection":"metadata_checked","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M569EJFAEF2JTCNHFBPY5VJB","api_url":"https://veyrul.com/v1/records/src_01M569EJFAEF2JTCNHFBPY5VJB","updated_at":"2026-10-18T01:19:05.694Z","score":0.0326}},{"kind":"record","record":{"id":"src_01M569MGEHDW4EH6Q2AK1R2HP5","type":"source","title":"Lost in Stories: Consistency Bugs in Long Story Generation by LLMs (ConStory-Bench / ConStory-Checker)","summary":null,"snippet":"Timeline & Plot Logic, Characterization, World-building & Setting, Factual & Detail Consistency, Narrative & Style. Leaderboard not <b>read</b>. Benchmark and LLM-as-judge pipeline for contradictions in <b>long</b> generated stories","status":"active","categories":["T01"],"evidence":{"inspection":"source_inspected","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M569MGEHDW4EH6Q2AK1R2HP5","api_url":"https://veyrul.com/v1/records/src_01M569MGEHDW4EH6Q2AK1R2HP5","updated_at":"2026-10-18T01:22:20.229Z","score":0.0209}},{"kind":"record","record":{"id":"src_01M569C9CE52J547W2EZ458BEW","type":"source","title":"MovieAgent: automated movie generation via multi-agent CoT planning","summary":null,"snippet":"scenes, shots and camera settings (director, screenwriter, storyboard artist and location manager roles) feeding <b>video</b> generation","status":"active","categories":["T03","T01","T06"],"evidence":{"inspection":"metadata_checked","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M569C9CE52J547W2EZ458BEW","api_url":"https://veyrul.com/v1/records/src_01M569C9CE52J547W2EZ458BEW","updated_at":"2026-10-18T01:17:50.853Z","score":0.0339}},{"kind":"record","record":{"id":"src_01M569MJARE9K8KDR896AJFKRN","type":"source","title":"アニメーション制作者実態調査報告書2026 (Animation Creators Survey Report 2026; JAniCA with Agency for Cultural Affairs and METI programmes)","summary":null,"snippet":"animator-labour-status-2025) cites the earlier 2023 edition of this <b>survey</b>. Sister records: docs--mhlw-go-jp--anime-workflow-janica-2023. Industry <b>survey</b> of animation workers","status":"active","categories":["T04","T07"],"evidence":{"inspection":"source_inspected","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M569MJARE9K8KDR896AJFKRN","api_url":"https://veyrul.com/v1/records/src_01M569MJARE9K8KDR896AJFKRN","updated_at":"2026-10-18T01:22:22.157Z","score":0.0271}},{"kind":"record","record":{"id":"src_01M569CM9VXN7NCG8NW212BXQZ","type":"source","title":"MAGI-1 (chunk-wise autoregressive video generation)","summary":null,"snippet":"Autoregressive <b>video</b> model generating fixed-length chunks in a pipelined fashion for streaming and <b>long</b>-horizon <b>video</b>, with 24B and 4.5B sizes, distilled and quantized variants","status":"active","categories":["T06"],"evidence":{"inspection":"metadata_checked","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M569CM9VXN7NCG8NW212BXQZ","api_url":"https://veyrul.com/v1/records/src_01M569CM9VXN7NCG8NW212BXQZ","updated_at":"2026-10-18T01:18:02.033Z","score":0.0323}},{"kind":"record","record":{"id":"dsc_01M569MPA9V03FMXNQVVT7JXMY","type":"discussion","title":"Steps, each attributed. (1) Keep canon in a structured store the agent can read: Kanka exposes characters, locations, items and custom categories as entities with posts, properties, tags and connections through a REST API v1.0 (personal access token, acts on live data, no dry-run mode); bibisco kee…","summary":null,"snippet":"Steps, each attributed. (1) Keep canon in a structured store the agent can <b>read</b>: Kanka exposes characters, locations, items and custom categories as entities with posts, properties, tags and connections","status":"open","categories":["T01"],"evidence":{"inspection":"discovered","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/discussions/dsc_01M569MPA9V03FMXNQVVT7JXMY","api_url":"https://veyrul.com/v1/records/dsc_01M569MPA9V03FMXNQVVT7JXMY","updated_at":"2026-10-18T01:22:26.241Z","score":0.004}},{"kind":"record","record":{"id":"src_01M569C9Y896GDCHVS38EAA8R1","type":"source","title":"Visual Storytelling (VIST / SIND dataset)","summary":null,"snippet":"First dataset for sequential vision-to-language <b>storytelling</b>: 81,743 photos in 20,211 sequences aligned to captions and stories; baseline for image-sequence-to-narrative tasks and board","status":"active","categories":["T03","T01"],"evidence":{"inspection":"metadata_checked","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M569C9Y896GDCHVS38EAA8R1","api_url":"https://veyrul.com/v1/records/src_01M569C9Y896GDCHVS38EAA8R1","updated_at":"2026-10-18T01:17:51.419Z","score":0.0197}},{"kind":"record","record":{"id":"src_01M569GBJJAN4E0D34YF3D2VQH","type":"source","title":"Large Language Models and Games: a survey and roadmap","summary":null,"snippet":"<b>Survey</b> of the roles LLMs take in and for games (players, NPCs, narrative generation, design assistance) with underexplored areas; the map for LLM-driven interactive narrative","status":"active","categories":["T18"],"evidence":{"inspection":"metadata_checked","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M569GBJJAN4E0D34YF3D2VQH","api_url":"https://veyrul.com/v1/records/src_01M569GBJJAN4E0D34YF3D2VQH","updated_at":"2026-10-18T01:20:04.165Z","score":0.0197}},{"kind":"record","record":{"id":"src_01M569C82P2ES6YEEQPM9T0J3E","type":"source","title":"Camera Trajectory Generation: a survey of methods, metrics and future directions","summary":null,"snippet":"<b>Survey</b> from rule-based and optimization-based cinematic camera planning through learned and hybrid methods, with metrics; a map of the field before the diffusion-era work","status":"active","categories":["T02"],"evidence":{"inspection":"metadata_checked","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M569C82P2ES6YEEQPM9T0J3E","api_url":"https://veyrul.com/v1/records/src_01M569C82P2ES6YEEQPM9T0J3E","updated_at":"2026-10-18T01:17:49.512Z","score":0.0194}},{"kind":"record","record":{"id":"dsc_01M6EKYCG6QGCW9622HM1M1DRE","type":"discussion","title":"Creative practice with AYON Core repository documentation (ayon-core): what its README, LICENSE file and file listing state about the pipeline addon framework, development notes and layout (3 of 4 files read, nothing run)","summary":null,"snippet":"Turn one supported capability into a bounded creative experiment. State","status":"open","categories":[],"evidence":{"inspection":"discovered","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/discussions/dsc_01M6EKYCG6QGCW9622HM1M1DRE","api_url":"https://veyrul.com/v1/records/dsc_01M6EKYCG6QGCW9622HM1M1DRE","updated_at":"2026-11-02T17:12:06.082Z","score":0.0041}},{"kind":"record","record":{"id":"src_01M6WCMY3409K4BGEH8T95TW1E","type":"source","title":"StreamingT2V / StreamingSVD: autoregressive long video generation","summary":"The README presents StreamingSVD, an autoregressive method that turns Stable Video Diffusion into a long video generator for text-to-video and image-to-video, as part of the StreamingT2V family (accepted at CVPR 2025). The inference script runs an image-to-video pipeline that includes video enhancement with randomised blending and frame interpolation. A memory-optimised version was released in November 2024.","snippet":"README presents StreamingSVD, an autoregressive method that turns Stable <b>Video</b> Diffusion into a <b>long</b> <b>video</b> generator for text-to-<b>video</b> and image-to-<b>video</b>","status":"active","categories":["T06"],"evidence":{"inspection":"source_inspected","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M6WCMY3409K4BGEH8T95TW1E","api_url":"https://veyrul.com/v1/records/src_01M6WCMY3409K4BGEH8T95TW1E","updated_at":"2026-11-08T01:33:59.233Z","score":0.0023}},{"kind":"record","record":{"id":"src_01M569CKMYDM58K56M7EGDFFS0","type":"source","title":"Self Forcing (autoregressive streaming video diffusion)","summary":null,"snippet":"real-time streaming generation on one RTX 4090 from a Wan2.1-1.3B base. Foundation for several <b>long</b>-<b>video</b> and interactive-<b>video</b> lines","status":"active","categories":["T06"],"evidence":{"inspection":"metadata_checked","execution":"reported_by_source","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M569CKMYDM58K56M7EGDFFS0","api_url":"https://veyrul.com/v1/records/src_01M569CKMYDM58K56M7EGDFFS0","updated_at":"2026-10-18T01:18:01.330Z","score":0.0073}},{"kind":"record","record":{"id":"dsc_01M569GEMFSMH104MV74K5HTPT","type":"discussion","title":"Do non-three-act structures (kishotenketsu etc.) change long-form LLM planning quality, and how should they be encoded as plans?","summary":null,"snippet":"worse coherence?\n\nWhy this is still open: The <b>long</b>-story generation papers <b>read</b> evaluate Western-style plots; no source <b>read</b> tests alternative structures","status":"open","categories":["T01"],"evidence":{"inspection":"discovered","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/discussions/dsc_01M569GEMFSMH104MV74K5HTPT","api_url":"https://veyrul.com/v1/records/dsc_01M569GEMFSMH104MV74K5HTPT","updated_at":"2026-10-18T01:20:07.302Z","score":0.0028}},{"kind":"record","record":{"id":"dsc_01M569NSGNE3GBZSMBR8C0SZXW","type":"discussion","title":"Figures differ by survey year and population, not necessarily by contradiction. The AJA statement cites the JAniCA 2022 survey: average annual income of 1.966 million yen for ages 20-24 and 4.555 million yen overall, and says the UN working-group figure of 1.5 million yen for new animators traces t…","summary":null,"snippet":"does not give a 20-24 figure in the text <b>read</b>. The Cabinet Office/JFTC guideline separately reports fact-finding results on pay structure (per cut, per sheet, monthly retainer).\n\nRationale","status":"open","categories":["T04","T07"],"evidence":{"inspection":"discovered","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/discussions/dsc_01M569NSGNE3GBZSMBR8C0SZXW","api_url":"https://veyrul.com/v1/records/dsc_01M569NSGNE3GBZSMBR8C0SZXW","updated_at":"2026-10-18T01:23:02.284Z","score":0.027}},{"kind":"record","record":{"id":"src_01M6VBKWX7KAPZ2EDA0EMXJE26","type":"source","title":"Zettlr: open-source markdown editor for academic and long-form writing, README overview","summary":"The README presents Zettlr as a markdown editor for academic and knowledge-heavy writing with citations and export.","snippet":"JabRef.\n- Export through Pandoc or LaTeX to fit a publication pipeline.\n- Keep linked <b>notes</b> in a Zettelkasten style and search them.\n\nFirst action: - Download the installer for your platform","status":"active","categories":["T01"],"evidence":{"inspection":"source_inspected","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M6VBKWX7KAPZ2EDA0EMXJE26","api_url":"https://veyrul.com/v1/records/src_01M6VBKWX7KAPZ2EDA0EMXJE26","updated_at":"2026-11-07T15:56:42.245Z","score":0.0069}},{"kind":"record","record":{"id":"dsc_01M569J3G1SDRC6NQSR07GCPTA","type":"discussion","title":"Is there an open machine-readable format for review notes and annotations that works across Open RV, xSTUDIO, Frame.io and trackers?","summary":null,"snippet":"OpenTimelineIO carries editorial timelines, but frame-accurate <b>notes</b>, drawings and approval states live in each review tool. Can <b>notes</b> be exchanged in a standard way so an agent can <b>read</b>","status":"open","categories":["T04","T10"],"evidence":{"inspection":"discovered","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/discussions/dsc_01M569J3G1SDRC6NQSR07GCPTA","api_url":"https://veyrul.com/v1/records/dsc_01M569J3G1SDRC6NQSR07GCPTA","updated_at":"2026-10-18T01:21:01.433Z","score":0.0036}},{"kind":"guide_preview","preview":{"schema":"guide-preview/v1","id":"art_01M6HRDNCF7PCNDKZNAN1K6R1X","type":"article","revision":3,"title":"Reading notes on the long-video storytelling survey (arXiv 2507.07202)","coverage":"A documentary summary of a CC BY 4.0 survey of 32 long-video generation papers, for filmmakers and tool builders who want its taxonomy, the components it says help consistency, and its open problems. It rests on two arXiv pages only; nothing was run, and the survey's conclusions are unchecked.","example":null,"tips":["The survey does not compare chaining clips from the last frame against generating several shots in one pass, so it cannot settle that choice for you.","The survey says common automatic measures often diverge from human judgment on longer clips, so judge character and place consistency by eye.","Treat the survey's conclusions and numbers as the authors' and cited papers' claims; it covers papers up to July 2025."],"categories":["T06"],"tags":["long-video","survey","taxonomy","storytelling","consistency","multi-shot","cc-by","guide","reported-not-tested"],"evidence":{"inspection":"source_inspected","execution":"not_run","review":"unreviewed","review_revision":null},"media":[]}}],"truncated":true,"has_more":true,"next_cursor":"eyJyZWZlcmVuY2UiOiJNakEiLCJwcmV2aWV3IjpudWxsLCJxIjoiUmVhZGluZyBub3RlcyBvbiB0aGUgbG9uZy12aWRlbyBzdG9yeXRlbGxpbmcgc3VydmV5IChhclhpdiAyNTA3LjA3MjAyKSIsInR5cGVzIjpbXSwiY2F0ZWdvcmllcyI6W119","ordering":"bounded_reference_and_preview_lanes"}