{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/video-generation/papers/13","list_of":"/task/video-generation","task":"Video Generation","archive":{"snapshot":"2025-07-28"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"repositories listed in the archive (most first), then date (newest first), then slug","page":13,"pages_in_order":15,"rows_per_page":100,"rows":[1201,1300],"of":1466,"counts":{"archive_papers_tagged":1466,"with_a_code_link":609,"where_syntology_ran_a_sample":257,"not_listed_spam_title":0,"listed":1466,"listed_where_code_ran":257,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":221,"every_run_a_failure_of_syntologys_instrument":36,"listed_with_a_run_with_no_instrument_failure":221,"listed_every_run_a_failure_of_syntologys_instrument":36,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/task/video-generation","prev":"/task/video-generation/papers/12","next":"/task/video-generation/papers/14","papers":[{"url":null,"slug":"sync4d-video-guided-controllable-dynamics-for","title":"Sync4D: Video Guided Controllable Dynamics for Physics-Based 4D Generation","date":"2024-05-27","arxiv_id":"2405.16849","repositories_listed":0,"syntology":null},{"url":null,"slug":"disentangling-foreground-and-background","title":"Disentangling Foreground and Background Motion for Enhanced Realism in Human Video Generation","date":"2024-05-26","arxiv_id":"2405.16393","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-multi-task-multi-modal-models-a-video","title":"Towards Multi-Task Multi-Modal Models: A Video Generative Perspective","date":"2024-05-26","arxiv_id":"2405.16728","repositories_listed":0,"syntology":null},{"url":null,"slug":"scaling-diffusion-mamba-with-bidirectional","title":"Scaling Diffusion Mamba with Bidirectional SSMs for Efficient Image and Video Generation","date":"2024-05-24","arxiv_id":"2405.15881","repositories_listed":0,"syntology":null},{"url":"/paper/fisher-flow-matching-for-generative-modeling","slug":"fisher-flow-matching-for-generative-modeling","title":"Fisher Flow Matching for Generative Modeling over Discrete Data","date":"2024-05-23","arxiv_id":"2405.14664","repositories_listed":0,"syntology":{"n":11,"n_ran":10,"n_constructed":0,"n_ran_checked":8,"n_instrument":2,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":7,"n_pointer_only":11,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 0 violated, 7 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/fisher-flow-matching-for-generative-modeling#ran","syntology_url":"https://syntology.ai/paper/2405.14664","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.14664"}},"official":null}},{"url":null,"slug":"magicdrive3d-controllable-3d-generation-for","title":"MagicDrive3D: Controllable 3D Generation for Any-View Rendering in Street Scenes","date":"2024-05-23","arxiv_id":"2405.14475","repositories_listed":0,"syntology":null},{"url":null,"slug":"posecrafter-one-shot-personalized-video","title":"PoseCrafter: One-Shot Personalized Video Synthesis Following Flexible Pose Control","date":"2024-05-23","arxiv_id":"2405.14582","repositories_listed":0,"syntology":null},{"url":null,"slug":"revideo-remake-a-video-with-motion-and","title":"ReVideo: Remake a Video with Motion and Content Control","date":"2024-05-22","arxiv_id":"2405.13865","repositories_listed":0,"syntology":null},{"url":null,"slug":"camvig-camera-aware-image-to-video-generation","title":"CamViG: Camera Aware Image-to-Video Generation with Multimodal Transformers","date":"2024-05-21","arxiv_id":"2405.13195","repositories_listed":0,"syntology":null},{"url":null,"slug":"disenstudio-customized-multi-subject-text-to","title":"DisenStudio: Customized Multi-subject Text-to-Video Generation with Disentangled Spatial Control","date":"2024-05-21","arxiv_id":"2405.12796","repositories_listed":0,"syntology":null},{"url":null,"slug":"dance-any-beat-blending-beats-with-visuals-in","title":"Dance Any Beat: Blending Beats with Visuals in Dance Video Generation","date":"2024-05-15","arxiv_id":"2405.09266","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-lost-melody-empirical-observations-on","title":"The Lost Melody: Empirical Observations on Text-to-Video Generation From A Storytelling Perspective","date":"2024-05-13","arxiv_id":"2405.08720","repositories_listed":0,"syntology":null},{"url":null,"slug":"reviewing-intelligent-cinematography-ai","title":"Reviewing Intelligent Cinematography: AI research for camera-based video production","date":"2024-05-08","arxiv_id":"2405.05039","repositories_listed":0,"syntology":null},{"url":null,"slug":"audio-visual-speech-representation-expert-for","title":"Audio-Visual Speech Representation Expert for Enhanced Talking Face Video Generation and Evaluation","date":"2024-05-07","arxiv_id":"2405.04327","repositories_listed":0,"syntology":null},{"url":null,"slug":"exposing-ai-generated-videos-a-benchmark","title":"Exposing AI-generated Videos: A Benchmark Dataset and a Local-and-Global Temporal Defect Based Detection Method","date":"2024-05-07","arxiv_id":"2405.04133","repositories_listed":0,"syntology":null},{"url":null,"slug":"vidu-a-highly-consistent-dynamic-and-skilled","title":"Vidu: a Highly Consistent, Dynamic and Skilled Text-to-Video Generator with Diffusion Models","date":"2024-05-07","arxiv_id":"2405.04233","repositories_listed":0,"syntology":null},{"url":null,"slug":"matten-video-generation-with-mamba-attention","title":"Matten: Video Generation with Mamba-Attention","date":"2024-05-05","arxiv_id":"2405.03025","repositories_listed":0,"syntology":null},{"url":null,"slug":"bridge-to-non-barrier-communication-gloss","title":"Bridge to Non-Barrier Communication: Gloss-Prompted Fine-grained Cued Speech Gesture Generation with Diffusion Model","date":"2024-04-30","arxiv_id":"2404.19277","repositories_listed":0,"syntology":null},{"url":null,"slug":"motionmaster-training-free-camera-motion","title":"MotionMaster: Training-free Camera Motion Transfer For Video Generation","date":"2024-04-24","arxiv_id":"2404.15789","repositories_listed":0,"syntology":null},{"url":null,"slug":"accelerating-image-generation-with-sub-path","title":"Accelerating Image Generation with Sub-path Linear Approximation Model","date":"2024-04-22","arxiv_id":"2404.13903","repositories_listed":0,"syntology":null},{"url":null,"slug":"motion-aware-latent-diffusion-models-for","title":"Motion-aware Latent Diffusion Models for Video Frame Interpolation","date":"2024-04-21","arxiv_id":"2404.13534","repositories_listed":0,"syntology":null},{"url":null,"slug":"music-consistency-models","title":"Music Consistency Models","date":"2024-04-20","arxiv_id":"2404.13358","repositories_listed":0,"syntology":null},{"url":null,"slug":"physdreamer-physics-based-interaction-with-3d","title":"PhysDreamer: Physics-Based Interaction with 3D Objects via Video Generation","date":"2024-04-19","arxiv_id":"2404.13026","repositories_listed":0,"syntology":null},{"url":null,"slug":"aniclipart-clipart-animation-with-text-to","title":"AniClipart: Clipart Animation with Text-to-Video Priors","date":"2024-04-18","arxiv_id":"2404.12347","repositories_listed":0,"syntology":null},{"url":null,"slug":"sparsedm-toward-sparse-efficient-diffusion","title":"SparseDM: Toward Sparse Efficient Diffusion Models","date":"2024-04-16","arxiv_id":"2404.10445","repositories_listed":0,"syntology":null},{"url":null,"slug":"ctrl-adapter-an-efficient-and-versatile","title":"Ctrl-Adapter: An Efficient and Versatile Framework for Adapting Diverse Controls to Any Diffusion Model","date":"2024-04-15","arxiv_id":"2404.09967","repositories_listed":0,"syntology":null},{"url":null,"slug":"loopanimate-loopable-salient-object-animation","title":"LoopAnimate: Loopable Salient Object Animation","date":"2024-04-14","arxiv_id":"2404.09172","repositories_listed":0,"syntology":null},{"url":null,"slug":"action-conditioned-video-data-improves","title":"Action-conditioned video data improves predictability","date":"2024-04-08","arxiv_id":"2404.05439","repositories_listed":0,"syntology":null},{"url":null,"slug":"animatezoo-zero-shot-video-generation-of","title":"AnimateZoo: Zero-shot Video Generation of Cross-Species Animation via Subject Alignment","date":"2024-04-07","arxiv_id":"2404.04946","repositories_listed":0,"syntology":null},{"url":"/paper/grid-diffusion-models-for-text-to-video-1","slug":"grid-diffusion-models-for-text-to-video-1","title":"Grid Diffusion Models for Text-to-Video Generation","date":"2024-03-30","arxiv_id":"2404.00234","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-review-of-multi-modal-large-language-and","title":"A Review of Multi-Modal Large Language and Vision Models","date":"2024-03-28","arxiv_id":"2404.01322","repositories_listed":0,"syntology":null},{"url":null,"slug":"frame-by-familiar-frame-understanding","title":"Frame by Familiar Frame: Understanding Replication in Video Diffusion Models","date":"2024-03-28","arxiv_id":"2403.19593","repositories_listed":0,"syntology":null},{"url":null,"slug":"tc4d-trajectory-conditioned-text-to-4d","title":"TC4D: Trajectory-Conditioned Text-to-4D Generation","date":"2024-03-26","arxiv_id":"2403.17920","repositories_listed":0,"syntology":null},{"url":null,"slug":"tutorial-on-diffusion-models-for-imaging-and","title":"Tutorial on Diffusion Models for Imaging and Vision","date":"2024-03-26","arxiv_id":"2403.18103","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-survey-on-long-video-generation-challenges","title":"A Survey on Long Video Generation: Challenges, Methods, and Prospects","date":"2024-03-25","arxiv_id":"2403.16407","repositories_listed":0,"syntology":null},{"url":null,"slug":"trip-temporal-residual-learning-with-image","title":"TRIP: Temporal Residual Learning with Image Noise Prior for Image-to-Video Diffusion Models","date":"2024-03-25","arxiv_id":"2403.17005","repositories_listed":0,"syntology":null},{"url":null,"slug":"opportunities-and-challenges-in-the","title":"Opportunities and challenges in the application of large artificial intelligence models in radiology","date":"2024-03-24","arxiv_id":"2403.16112","repositories_listed":0,"syntology":null},{"url":null,"slug":"spectral-motion-alignment-for-video-motion","title":"Spectral Motion Alignment for Video Motion Transfer using Diffusion Models","date":"2024-03-22","arxiv_id":"2403.15249","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-video-diffusion-models-via-content","title":"Efficient Video Diffusion Models via Content-Frame Motion-Latent Decomposition","date":"2024-03-21","arxiv_id":"2403.14148","repositories_listed":0,"syntology":null},{"url":null,"slug":"enabling-visual-composition-and-animation-in","title":"Enabling Visual Composition and Animation in Unsupervised Video Generation","date":"2024-03-21","arxiv_id":"2403.14368","repositories_listed":0,"syntology":null},{"url":null,"slug":"explorative-inbetweening-of-time-and-space","title":"Explorative Inbetweening of Time and Space","date":"2024-03-21","arxiv_id":"2403.14611","repositories_listed":0,"syntology":null},{"url":null,"slug":"s2dm-sector-shaped-diffusion-models-for-video","title":"S2DM: Sector-Shaped Diffusion Models for Video Generation","date":"2024-03-20","arxiv_id":"2403.13408","repositories_listed":0,"syntology":null},{"url":null,"slug":"animatediff-lightning-cross-model-diffusion","title":"AnimateDiff-Lightning: Cross-Model Diffusion Distillation","date":"2024-03-19","arxiv_id":"2403.12706","repositories_listed":0,"syntology":null},{"url":null,"slug":"endora-video-generation-models-as-endoscopy","title":"Endora: Video Generation Models as Endoscopy Simulators","date":"2024-03-17","arxiv_id":"2403.11050","repositories_listed":0,"syntology":null},{"url":null,"slug":"animate-your-motion-turning-still-images-into","title":"Animate Your Motion: Turning Still Images into Dynamic Videos","date":"2024-03-15","arxiv_id":"2403.10179","repositories_listed":0,"syntology":null},{"url":null,"slug":"intention-driven-ego-to-exo-video-generation","title":"Intention-driven Ego-to-Exo Video Generation","date":"2024-03-14","arxiv_id":"2403.09194","repositories_listed":0,"syntology":null},{"url":null,"slug":"video-editing-via-factorized-diffusion","title":"Video Editing via Factorized Diffusion Distillation","date":"2024-03-14","arxiv_id":"2403.09334","repositories_listed":0,"syntology":null},{"url":null,"slug":"vlogger-multimodal-diffusion-for-embodied","title":"VLOGGER: Multimodal Diffusion for Embodied Avatar Synthesis","date":"2024-03-13","arxiv_id":"2403.08764","repositories_listed":0,"syntology":null},{"url":null,"slug":"aesopagent-agent-driven-evolutionary-system","title":"AesopAgent: Agent-driven Evolutionary System on Story-to-Video Production","date":"2024-03-12","arxiv_id":"2403.07952","repositories_listed":0,"syntology":null},{"url":null,"slug":"video-generation-with-consistency-tuning","title":"Video Generation with Consistency Tuning","date":"2024-03-11","arxiv_id":"2403.06356","repositories_listed":0,"syntology":null},{"url":null,"slug":"blazebvd-make-scale-time-equalization-great","title":"BlazeBVD: Make Scale-Time Equalization Great Again for Blind Video Deflickering","date":"2024-03-10","arxiv_id":"2403.06243","repositories_listed":0,"syntology":null},{"url":null,"slug":"fastvideoedit-leveraging-consistency-models","title":"FastVideoEdit: Leveraging Consistency Models for Efficient Text-to-Video Editing","date":"2024-03-10","arxiv_id":"2403.06269","repositories_listed":0,"syntology":null},{"url":null,"slug":"worldgpt-a-sora-inspired-video-ai-agent-as","title":"WorldGPT: A Sora-Inspired Video AI Agent as Rich World Models from Text and Image Inputs","date":"2024-03-10","arxiv_id":"2403.07944","repositories_listed":0,"syntology":null},{"url":null,"slug":"sora-as-an-agi-world-model-a-complete-survey","title":"Sora as an AGI World Model? A Complete Survey on Text-to-Video Generation","date":"2024-03-08","arxiv_id":"2403.05131","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-spatiotemporal-style-transfer-algorithm-for","title":"A spatiotemporal style transfer algorithm for dynamic visual stimulus generation","date":"2024-03-07","arxiv_id":"2403.04940","repositories_listed":0,"syntology":null},{"url":null,"slug":"tuning-free-noise-rectification-for-high","title":"Tuning-Free Noise Rectification for High Fidelity Image-to-Video Generation","date":"2024-03-05","arxiv_id":"2403.02827","repositories_listed":0,"syntology":null},{"url":null,"slug":"atomovideo-high-fidelity-image-to-video","title":"AtomoVideo: High Fidelity Image-to-Video Generation","date":"2024-03-04","arxiv_id":"2403.01800","repositories_listed":0,"syntology":null},{"url":null,"slug":"abductive-ego-view-accident-video","title":"Abductive Ego-View Accident Video Understanding for Safe Driving Perception","date":"2024-03-01","arxiv_id":"2403.00436","repositories_listed":0,"syntology":null},{"url":null,"slug":"context-aware-talking-face-video-generation","title":"Context-aware Talking Face Video Generation","date":"2024-02-28","arxiv_id":"2402.18092","repositories_listed":0,"syntology":null},{"url":null,"slug":"emo-emote-portrait-alive-generating","title":"EMO: Emote Portrait Alive -- Generating Expressive Portrait Videos with Audio2Video Diffusion Model under Weak Conditions","date":"2024-02-27","arxiv_id":"2402.17485","repositories_listed":0,"syntology":null},{"url":null,"slug":"sora-generates-videos-with-stunning","title":"Sora Generates Videos with Stunning Geometrical Consistency","date":"2024-02-27","arxiv_id":"2402.17403","repositories_listed":0,"syntology":null},{"url":null,"slug":"video-as-the-new-language-for-real-world","title":"Video as the New Language for Real-World Decision Making","date":"2024-02-27","arxiv_id":"2402.17139","repositories_listed":0,"syntology":null},{"url":null,"slug":"customize-a-video-one-shot-motion","title":"Customize-A-Video: One-Shot Motion Customization of Text-to-Video Diffusion Models","date":"2024-02-22","arxiv_id":"2402.14780","repositories_listed":0,"syntology":null},{"url":"/paper/snap-video-scaled-spatiotemporal-transformers","slug":"snap-video-scaled-spatiotemporal-transformers","title":"Snap Video: Scaled Spatiotemporal Transformers for Text-to-Video Synthesis","date":"2024-02-22","arxiv_id":"2402.14797","repositories_listed":0,"syntology":null},{"url":null,"slug":"hybrid-video-diffusion-models-with-2d","title":"Hybrid Video Diffusion Models with 2D Triplane and 3D Wavelet Representation","date":"2024-02-21","arxiv_id":"2402.13729","repositories_listed":0,"syntology":null},{"url":null,"slug":"denoising-diffusion-probabilistic-models-in","title":"Denoising Diffusion Probabilistic Models in Six Simple Steps","date":"2024-02-06","arxiv_id":"2402.04384","repositories_listed":0,"syntology":null},{"url":null,"slug":"direct-a-video-customized-video-generation","title":"Direct-a-Video: Customized Video Generation with User-Directed Camera Movement and Object Motion","date":"2024-02-05","arxiv_id":"2402.03162","repositories_listed":0,"syntology":null},{"url":null,"slug":"neurocine-decoding-vivid-video-sequences-from","title":"NeuroCine: Decoding Vivid Video Sequences from Human Brain Activties","date":"2024-02-02","arxiv_id":"2402.01590","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-survey-on-generative-ai-and-llm-for-video","title":"A Survey on Generative AI and LLM for Video Generation, Understanding, and Streaming","date":"2024-01-30","arxiv_id":"2404.16038","repositories_listed":0,"syntology":null},{"url":null,"slug":"motion-i2v-consistent-and-controllable-image","title":"Motion-I2V: Consistent and Controllable Image-to-Video Generation with Explicit Motion Modeling","date":"2024-01-29","arxiv_id":"2401.15977","repositories_listed":0,"syntology":null},{"url":"/paper/customvideo-customizing-text-to-video","slug":"customvideo-customizing-text-to-video","title":"CustomVideo: Customizing Text-to-Video Generation with Multiple Subjects","date":"2024-01-18","arxiv_id":"2401.09962","repositories_listed":0,"syntology":null},{"url":null,"slug":"inflation-with-diffusion-efficient-temporal","title":"Inflation with Diffusion: Efficient Temporal Adaptation for Text-to-Video Super-Resolution","date":"2024-01-18","arxiv_id":"2401.10404","repositories_listed":0,"syntology":null},{"url":null,"slug":"motion-zero-zero-shot-moving-object-control","title":"Motion-Zero: Zero-Shot Moving Object Control Framework for Diffusion-Based Video Generation","date":"2024-01-18","arxiv_id":"2401.10150","repositories_listed":0,"syntology":null},{"url":null,"slug":"worlddreamer-towards-general-world-models-for","title":"WorldDreamer: Towards General World Models for Video Generation via Predicting Masked Tokens","date":"2024-01-18","arxiv_id":"2401.09985","repositories_listed":0,"syntology":null},{"url":null,"slug":"univg-towards-unified-modal-video-generation","title":"UniVG: Towards UNIfied-modal Video Generation","date":"2024-01-17","arxiv_id":"2401.09084","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-a-better-metric-for-text-to-video","title":"Towards A Better Metric for Text-to-Video Generation","date":"2024-01-15","arxiv_id":"2401.07781","repositories_listed":0,"syntology":null},{"url":null,"slug":"360dvd-controllable-panorama-video-generation","title":"360DVD: Controllable Panorama Video Generation with 360-Degree Video Diffusion Model","date":"2024-01-12","arxiv_id":"2401.06578","repositories_listed":0,"syntology":null},{"url":null,"slug":"raven-rethinking-adversarial-video-generation","title":"RAVEN: Rethinking Adversarial Video Generation with Efficient Tri-plane Networks","date":"2024-01-11","arxiv_id":"2401.06035","repositories_listed":0,"syntology":null},{"url":null,"slug":"magicvideo-v2-multi-stage-high-aesthetic","title":"MagicVideo-V2: Multi-Stage High-Aesthetic Video Generation","date":"2024-01-09","arxiv_id":"2401.04468","repositories_listed":0,"syntology":null},{"url":null,"slug":"neural-rendering-and-its-hardware","title":"Neural Rendering and Its Hardware Acceleration: A Review","date":"2024-01-06","arxiv_id":"2402.00028","repositories_listed":0,"syntology":null},{"url":null,"slug":"diffperformer-iterative-learning-of","title":"DiffPerformer: Iterative Learning of Consistent Latent Guidance for Diffusion-based Human Video Generation","date":"2024-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"lamp-learn-a-motion-pattern-for-few-shot-1","title":"LAMP: Learn A Motion Pattern for Few-Shot Video Generation","date":"2024-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"on-the-content-bias-in-frechet-video-distance-1","title":"On the Content Bias in Frechet Video Distance","date":"2024-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"promptcot-align-prompt-distribution-via","title":"PromptCoT: Align Prompt Distribution via Adapted Chain-of-Thought","date":"2024-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"sned-superposition-network-architecture","title":"SNED: Superposition Network Architecture Search for Efficient Video Diffusion Model","date":"2024-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"flashvideo-a-framework-for-swift-inference-in","title":"FlashVideo: A Framework for Swift Inference in Text-to-Video Generation","date":"2023-12-30","arxiv_id":"2401.00869","repositories_listed":0,"syntology":null},{"url":null,"slug":"align-your-gaussians-text-to-4d-with-dynamic","title":"Align Your Gaussians: Text-to-4D with Dynamic 3D Gaussians and Composed Diffusion Models","date":"2023-12-21","arxiv_id":"2312.13763","repositories_listed":0,"syntology":null},{"url":"/paper/videopoet-a-large-language-model-for-zero","slug":"videopoet-a-large-language-model-for-zero","title":"VideoPoet: A Large Language Model for Zero-Shot Video Generation","date":"2023-12-21","arxiv_id":"2312.14125","repositories_listed":0,"syntology":null},{"url":"/paper/photorealistic-video-generation-with","slug":"photorealistic-video-generation-with","title":"Photorealistic Video Generation with Diffusion Models","date":"2023-12-11","arxiv_id":"2312.06662","repositories_listed":0,"syntology":null},{"url":null,"slug":"dreamoving-a-human-dance-video-generation","title":"DreaMoving: A Human Video Generation Framework based on Diffusion Models","date":"2023-12-08","arxiv_id":"2312.05107","repositories_listed":0,"syntology":null},{"url":null,"slug":"customizing-motion-in-text-to-video-diffusion","title":"NewMove: Customizing text-to-video models with novel motions","date":"2023-12-07","arxiv_id":"2312.04966","repositories_listed":0,"syntology":null},{"url":null,"slug":"gendef-learning-generative-deformation-field","title":"GenDeF: Learning Generative Deformation Field for Video Generation","date":"2023-12-07","arxiv_id":"2312.04561","repositories_listed":0,"syntology":null},{"url":null,"slug":"gentron-delving-deep-into-diffusion","title":"GenTron: Diffusion Transformers for Image and Video Generation","date":"2023-12-07","arxiv_id":"2312.04557","repositories_listed":0,"syntology":null},{"url":null,"slug":"mtvg-multi-text-video-generation-with-text-to","title":"MEVG: Multi-event Video Generation with Text-to-Video Models","date":"2023-12-07","arxiv_id":"2312.04086","repositories_listed":0,"syntology":null},{"url":null,"slug":"faac-facial-animation-generation-with-anchor","title":"FAAC: Facial Animation Generation with Anchor Frame and Conditional Control for Superior Fidelity and Editability","date":"2023-12-06","arxiv_id":"2312.03775","repositories_listed":0,"syntology":null},{"url":null,"slug":"dreamvideo-high-fidelity-image-to-video","title":"DreamVideo: High-Fidelity Image-to-Video Generation with Image Retention and Text Guidance","date":"2023-12-05","arxiv_id":"2312.03018","repositories_listed":0,"syntology":null},{"url":null,"slug":"fine-grained-controllable-video-generation","title":"Fine-grained Controllable Video Generation via Object Appearance and Context","date":"2023-12-05","arxiv_id":"2312.02919","repositories_listed":0,"syntology":null},{"url":null,"slug":"livephoto-real-image-animation-with-text","title":"LivePhoto: Real Image Animation with Text-guided Motion Control","date":"2023-12-05","arxiv_id":"2312.02928","repositories_listed":0,"syntology":null},{"url":null,"slug":"generative-rendering-controllable-4d-guided","title":"Generative Rendering: Controllable 4D-Guided Video Generation with 2D Diffusion Models","date":"2023-12-03","arxiv_id":"2312.01409","repositories_listed":0,"syntology":null},{"url":null,"slug":"videobooth-diffusion-based-video-generation","title":"VideoBooth: Diffusion-based Video Generation with Image Prompts","date":"2023-12-01","arxiv_id":"2312.00777","repositories_listed":0,"syntology":null}],"record_sha256":"dc8fa343a55e30d9c1b75ed8ae2495c04851cd4266a3341171b68f95dab1fe30","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}