Paper Citation Record · LEDGER

DiTalker: A Unified DiT-based Framework for High-Quality and Speaking Styles Controllable Portrait Animation

As of 19 August 2026, this Paper Citation Record lists 71 of 71 outbound references and 2 inbound Pith citation observations for arXiv:2508.06511.

A citation records a reference. It does not transfer a finding from one paper to another.

pith.paper-citation-record.v1
2508.06511 v1

Coverage vector

measured 71 of 71 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-06T12:43:27.553611Z

measured 73 of 73 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-19T06:32:44.657259+00:00

measured 2 of 2 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-02T01:01:54.160626Z

measured 0 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: arxiv_reference, observed 2026-06-29T13:13:27.684326Z

Reference resolution

71 of 71 outbound references displayed

verified exact0
verified fuzzy57
unresolved14
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 23e7f1ae-2355-4938-bc93-9c8cc521c53c · outbound

This paper cites Spatio- temporal energy-guided diffusion model for zero-shot video synthesis and editing,.

DiTalker: A Unified DiT-based Framework for High-Quality and Speaking Styles Controllable Portrait Animation Spatio- temporal energy-guided diffusion model for zero-shot video synthesis and editing,

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T12:43:38.779195Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 61d0c4ad-4374-47cc-be30-e068769bfe9b · outbound

This paper cites Tvg: A training-free transition video generation method with diffusion models,.

DiTalker: A Unified DiT-based Framework for High-Quality and Speaking Styles Controllable Portrait Animation Tvg: A training-free transition video generation method with diffusion models,

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T12:43:38.565940Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 0d1cd090-bf90-4703-a118-f3a4e125a3dc · outbound

This paper cites Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets.

DiTalker: A Unified DiT-based Framework for High-Quality and Speaking Styles Controllable Portrait Animation Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-06T12:43:20.763128Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 76b08039-2173-4305-a945-c8532ab21bea · outbound

This paper cites Corrtalk: Correlation between hierarchical speech and facial activity variances for 3d animation,.

DiTalker: A Unified DiT-based Framework for High-Quality and Speaking Styles Controllable Portrait Animation Corrtalk: Correlation between hierarchical speech and facial activity variances for 3d animation,

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T12:43:38.365671Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 15db9d35-dc96-49b4-b9bb-608b5e91ebef · outbound

This paper cites Wonderjourney: Going from anywhere to everywhere,.

DiTalker: A Unified DiT-based Framework for High-Quality and Speaking Styles Controllable Portrait Animation Wonderjourney: Going from anywhere to everywhere,

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T12:43:38.228910Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation ac4c71df-2336-42b2-87ca-4dfcb924d932 · outbound

This paper cites Omnihuman-1: Rethinking the scaling-up of one-stage conditioned human animation models,.

DiTalker: A Unified DiT-based Framework for High-Quality and Speaking Styles Controllable Portrait Animation Omnihuman-1: Rethinking the scaling-up of one-stage conditioned human animation models,

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T12:43:37.998274Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation a84b4c09-8d90-4c46-b4de-15bb8d934705 · outbound

This paper cites Audio-semantic enhanced pose-driven talking head generation,.

DiTalker: A Unified DiT-based Framework for High-Quality and Speaking Styles Controllable Portrait Animation Audio-semantic enhanced pose-driven talking head generation,

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T12:43:37.769317Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation b29b8937-4508-40fc-9517-030d68a8c97b · outbound

This paper cites Alleviating one- to-many mapping in talking head synthesis with dynamic adaptation context and style adapter,.

DiTalker: A Unified DiT-based Framework for High-Quality and Speaking Styles Controllable Portrait Animation Alleviating one- to-many mapping in talking head synthesis with dynamic adaptation context and style adapter,

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T12:43:37.587619Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 76152d6b-50ad-45db-a1ca-01b56ee10fb1 · outbound

This paper cites Stochastic latent talking face generation toward emotional expressions and head poses,.

DiTalker: A Unified DiT-based Framework for High-Quality and Speaking Styles Controllable Portrait Animation Stochastic latent talking face generation toward emotional expressions and head poses,

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T12:43:37.403599Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation d19d0b5e-9631-4218-a31d-96a41128f5e8 · outbound

This paper cites Hallo2: Long-duration and high-resolution audio-driven portrait image animation,.

DiTalker: A Unified DiT-based Framework for High-Quality and Speaking Styles Controllable Portrait Animation Hallo2: Long-duration and high-resolution audio-driven portrait image animation,

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T12:43:37.249313Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 452e0136-51ca-4206-a242-b16880eb494e · outbound

This paper cites Out of time: automated lip sync in the wild,.

DiTalker: A Unified DiT-based Framework for High-Quality and Speaking Styles Controllable Portrait Animation Out of time: automated lip sync in the wild,

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T12:43:37.073999Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation d97cfdfd-9130-4f64-aa87-18fec9500e84 · outbound

This paper cites Styletalk++: A unified framework for controlling the speaking styles of talking heads,.

DiTalker: A Unified DiT-based Framework for High-Quality and Speaking Styles Controllable Portrait Animation Styletalk++: A unified framework for controlling the speaking styles of talking heads,

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T12:43:36.881020Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 1788aa76-1a4c-4014-80e0-d6f57b38682f · outbound

This paper cites Multimodal inputs driven talking face generation with spatial–temporal dependency,.

DiTalker: A Unified DiT-based Framework for High-Quality and Speaking Styles Controllable Portrait Animation Multimodal inputs driven talking face generation with spatial–temporal dependency,

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T12:43:36.666264Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 6d903a5b-71d8-4679-b2f9-6a477f61c1e7 · outbound

This paper cites A lip sync expert is all you need for speech to lip generation in the wild,.

DiTalker: A Unified DiT-based Framework for High-Quality and Speaking Styles Controllable Portrait Animation A lip sync expert is all you need for speech to lip generation in the wild,

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T12:43:36.466007Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 6d23a5b6-e5de-4f06-b5a4-c1ed4db6f079 · outbound

This paper cites Difftalk: Crafting diffusion models for generalized audio-driven portraits anima- tion,.

DiTalker: A Unified DiT-based Framework for High-Quality and Speaking Styles Controllable Portrait Animation Difftalk: Crafting diffusion models for generalized audio-driven portraits anima- tion,

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T12:43:36.226831Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 717e74f8-781b-4d37-8072-472b6c6aad71 · outbound

This paper cites InstructAvatar: Text-Guided Emotion and Motion Control for Avatar Generation.

DiTalker: A Unified DiT-based Framework for High-Quality and Speaking Styles Controllable Portrait Animation InstructAvatar: Text-Guided Emotion and Motion Control for Avatar Generation

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-06T12:43:22.208132Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 88dafea1-90d0-4a4f-91e9-b5bf13a1187e · outbound

This paper cites Moee: Mixture of emotion experts for audio-driven portrait animation,.

DiTalker: A Unified DiT-based Framework for High-Quality and Speaking Styles Controllable Portrait Animation Moee: Mixture of emotion experts for audio-driven portrait animation,

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T12:43:36.088689Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation d38c91a5-5f69-4b5b-a381-49458102688f · outbound

This paper cites Face recognition based on fitting a 3d mor- phable model,.

DiTalker: A Unified DiT-based Framework for High-Quality and Speaking Styles Controllable Portrait Animation Face recognition based on fitting a 3d mor- phable model,

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T12:43:35.845916Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 35c75f7c-e5a3-489b-8dce-e3561e78b74a · outbound

This paper cites Echomimic: Lifelike audio-driven portrait animations through editable landmark conditioning,.

DiTalker: A Unified DiT-based Framework for High-Quality and Speaking Styles Controllable Portrait Animation Echomimic: Lifelike audio-driven portrait animations through editable landmark conditioning,

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T12:43:35.645001Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation b95cff9c-01c3-4fe1-92c9-21f702ab2b5e · outbound

This paper cites Hallo3: Highly dynamic and realistic portrait image animation with diffusion transformer networks,.

DiTalker: A Unified DiT-based Framework for High-Quality and Speaking Styles Controllable Portrait Animation Hallo3: Highly dynamic and realistic portrait image animation with diffusion transformer networks,

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T12:43:35.470591Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 791123d2-719c-4b7b-9375-4d5aab3d8325 · outbound

This paper cites Styletalk: One-shot talking head generation with controllable speaking styles,.

DiTalker: A Unified DiT-based Framework for High-Quality and Speaking Styles Controllable Portrait Animation Styletalk: One-shot talking head generation with controllable speaking styles,

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T12:43:35.296235Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation d8ebe8a7-1bc3-4514-86e7-30e255eb9b84 · outbound

This paper cites Style2talker: High-resolution talking head generation with emotion style and art style,.

DiTalker: A Unified DiT-based Framework for High-Quality and Speaking Styles Controllable Portrait Animation Style2talker: High-resolution talking head generation with emotion style and art style,

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T12:43:35.101665Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 0dbb7566-bc70-4c97-a2e8-b83e276edda7 · outbound

This paper cites Edtalk: Efficient disentanglement for emotional talking head synthesis,.

DiTalker: A Unified DiT-based Framework for High-Quality and Speaking Styles Controllable Portrait Animation Edtalk: Efficient disentanglement for emotional talking head synthesis,

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T12:43:34.858085Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation c14acd06-90e2-43af-a9dc-f3c400550026 · outbound

This paper cites Say anything with any style,.

DiTalker: A Unified DiT-based Framework for High-Quality and Speaking Styles Controllable Portrait Animation Say anything with any style,

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T12:43:34.701760Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 0d175107-6644-4bba-96a0-2bc4906775bd · outbound

This paper cites Emo: Emote portrait alive generating expressive portrait videos with audio2video diffusion model under weak conditions,.

DiTalker: A Unified DiT-based Framework for High-Quality and Speaking Styles Controllable Portrait Animation Emo: Emote portrait alive generating expressive portrait videos with audio2video diffusion model under weak conditions,

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T12:43:34.476957Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation b24e3996-28ca-44c3-81fa-d4db7c263a02 · outbound

This paper cites Sadtalker: Learning realistic 3d motion coefficients for stylized audio-driven single image talking face animation,.

DiTalker: A Unified DiT-based Framework for High-Quality and Speaking Styles Controllable Portrait Animation Sadtalker: Learning realistic 3d motion coefficients for stylized audio-driven single image talking face animation,

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T12:43:34.307021Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 46cb5150-1c18-4cd5-a097-6fe6d9085ed0 · outbound

This paper cites Real3d-portrait: One-shot realistic 3d talking portrait synthesis,.

DiTalker: A Unified DiT-based Framework for High-Quality and Speaking Styles Controllable Portrait Animation Real3d-portrait: One-shot realistic 3d talking portrait synthesis,

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T12:43:34.138099Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 7c348509-6106-48d2-b11a-2e557bc8570f · outbound

This paper cites Scalable diffusion models with transformers,.

DiTalker: A Unified DiT-based Framework for High-Quality and Speaking Styles Controllable Portrait Animation Scalable diffusion models with transformers,

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T12:43:33.907031Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 6c8df61a-d7fe-40cd-9420-e1bc79c41d92 · outbound

This paper cites Cogvideox: Text-to-video diffusion models with an expert transformer,.

DiTalker: A Unified DiT-based Framework for High-Quality and Speaking Styles Controllable Portrait Animation Cogvideox: Text-to-video diffusion models with an expert transformer,

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T12:43:33.727718Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation fd53d714-bd38-4778-b867-a7e1fb121158 · outbound

This paper cites Exploring the limits of transfer learning with a unified text-to-text transformer,.

DiTalker: A Unified DiT-based Framework for High-Quality and Speaking Styles Controllable Portrait Animation Exploring the limits of transfer learning with a unified text-to-text transformer,

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-06T12:43:23.332696Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 64874710-1360-4236-96b1-bf5fe39e4031 · outbound

This paper cites Efficient emotional adaptation for audio-driven talking-head generation,.

DiTalker: A Unified DiT-based Framework for High-Quality and Speaking Styles Controllable Portrait Animation Efficient emotional adaptation for audio-driven talking-head generation,

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T12:43:33.566500Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 86f3dfd8-79ed-4ef6-b804-61215e02fe25 · outbound

This paper cites Talkclip: Talking head generation with text-guided expressive speaking styles,.

DiTalker: A Unified DiT-based Framework for High-Quality and Speaking Styles Controllable Portrait Animation Talkclip: Talking head generation with text-guided expressive speaking styles,

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T12:43:33.404635Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 9faeff50-dbcb-4bb2-8b88-134aec1e951d · outbound

This paper cites Whisperx: Time-accurate speech transcription of long-form audio,.

DiTalker: A Unified DiT-based Framework for High-Quality and Speaking Styles Controllable Portrait Animation Whisperx: Time-accurate speech transcription of long-form audio,

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-06T12:43:23.589831Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 499289a0-6f66-421d-af3e-61575593d220 · outbound

This paper cites AniPortrait: Audio-Driven Synthesis of Photorealistic Portrait Animation.

DiTalker: A Unified DiT-based Framework for High-Quality and Speaking Styles Controllable Portrait Animation AniPortrait: Audio-Driven Synthesis of Photorealistic Portrait Animation

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-06T12:43:23.684599Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9da71d78-ef20-4e73-bb0d-8d84202ec70f · outbound

This paper cites Hallo: Hierarchical Audio-Driven Visual Synthesis for Portrait Image Animation.

DiTalker: A Unified DiT-based Framework for High-Quality and Speaking Styles Controllable Portrait Animation Hallo: Hierarchical Audio-Driven Visual Synthesis for Portrait Image Animation

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-06T12:43:23.782760Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 85e08829-a9c3-4242-8017-f0cb3d426677 · outbound

This paper cites Rep- resentation alignment for generation: Training diffusion transformers is easier than you think,.

DiTalker: A Unified DiT-based Framework for High-Quality and Speaking Styles Controllable Portrait Animation Rep- resentation alignment for generation: Training diffusion transformers is easier than you think,

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T12:43:33.244426Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 73f9ec82-391c-47bf-95dd-a89513ed5f6a · outbound

This paper cites Dinov2: Learning robust visual features without supervision,.

DiTalker: A Unified DiT-based Framework for High-Quality and Speaking Styles Controllable Portrait Animation Dinov2: Learning robust visual features without supervision,

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T12:43:33.038179Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 0c8471b9-20c6-470d-bb11-dddd135e1d93 · outbound

This paper cites Flow-guided one-shot talking face generation with a high-resolution audio-visual dataset,.

DiTalker: A Unified DiT-based Framework for High-Quality and Speaking Styles Controllable Portrait Animation Flow-guided one-shot talking face generation with a high-resolution audio-visual dataset,

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T12:43:32.847464Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 8be51ba6-c19e-4c1e-a37d-b2156889883f · outbound

This paper cites CelebV-HQ: A large-scale video facial attributes dataset,.

DiTalker: A Unified DiT-based Framework for High-Quality and Speaking Styles Controllable Portrait Animation CelebV-HQ: A large-scale video facial attributes dataset,

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T12:43:32.636580Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation fe30ef19-9d24-4883-be37-144cd3bed17a · outbound

This paper cites Hierarchical feature warping and blending for talking head animation,.

DiTalker: A Unified DiT-based Framework for High-Quality and Speaking Styles Controllable Portrait Animation Hierarchical feature warping and blending for talking head animation,

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T12:43:32.433129Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 75d24d69-e53d-4113-a87b-be33cd9f0c26 · outbound

This paper cites Denoising diffusion probabilistic models,.

DiTalker: A Unified DiT-based Framework for High-Quality and Speaking Styles Controllable Portrait Animation Denoising diffusion probabilistic models,

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-06T12:43:24.356376Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7a07d779-5799-4c25-bbcc-a72fdf3677c9 · outbound

This paper cites Diffused heads: Diffusion models beat gans on talking-face generation,.

DiTalker: A Unified DiT-based Framework for High-Quality and Speaking Styles Controllable Portrait Animation Diffused heads: Diffusion models beat gans on talking-face generation,

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T12:43:32.261330Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation e1da9b9c-3384-4687-9fd7-cb1f31ca2b0f · outbound

This paper cites Loopy: Taming audio-driven portrait avatar with long-term motion dependency,.

DiTalker: A Unified DiT-based Framework for High-Quality and Speaking Styles Controllable Portrait Animation Loopy: Taming audio-driven portrait avatar with long-term motion dependency,

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T12:43:32.085060Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 977c85de-1616-4d4b-978d-883bfa9f98d4 · outbound

This paper cites wav2vec 2.0: A framework for self-supervised learning of speech representations,.

DiTalker: A Unified DiT-based Framework for High-Quality and Speaking Styles Controllable Portrait Animation wav2vec 2.0: A framework for self-supervised learning of speech representations,

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-06T12:43:24.682758Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ca2ad9aa-9256-48cc-b7c2-f94119409e40 · outbound

This paper cites Efficient emotional adaptation for audio-driven talking-head generation,.

DiTalker: A Unified DiT-based Framework for High-Quality and Speaking Styles Controllable Portrait Animation Efficient emotional adaptation for audio-driven talking-head generation,

Reference 45

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T12:43:31.863138Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation bbde5224-6056-47f0-aa05-f09de5ef64a0 · outbound

This paper cites Emmn: Emotional motion memory network for audio-driven emotional talking face generation,.

DiTalker: A Unified DiT-based Framework for High-Quality and Speaking Styles Controllable Portrait Animation Emmn: Emotional motion memory network for audio-driven emotional talking face generation,

Reference 46

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T12:43:31.669046Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 001f16cd-4748-4652-a42f-0e9d09616507 · outbound

This paper cites Talking face gener- ation with audio-deduced emotional landmarks,.

DiTalker: A Unified DiT-based Framework for High-Quality and Speaking Styles Controllable Portrait Animation Talking face gener- ation with audio-deduced emotional landmarks,

Reference 47

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T12:43:31.452342Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 82de0386-a1b7-4c06-8e82-c8e3a89ccabe · outbound

This paper cites Eamm: One-shot emotional talking face via audio-based emotion-aware motion model,.

DiTalker: A Unified DiT-based Framework for High-Quality and Speaking Styles Controllable Portrait Animation Eamm: One-shot emotional talking face via audio-based emotion-aware motion model,

Reference 48

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T12:43:31.294588Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation e06e0b86-af4b-4930-8ac4-68a5f866dc0d · outbound

This paper cites Neural discrete representation learning,.

DiTalker: A Unified DiT-based Framework for High-Quality and Speaking Styles Controllable Portrait Animation Neural discrete representation learning,

Reference 49

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T12:43:31.103654Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 1df25f53-5755-424b-b07b-c463d8e2d844 · outbound

This paper cites Progressive disentangled representation learning for fine-grained controllable talking head synthesis,.

DiTalker: A Unified DiT-based Framework for High-Quality and Speaking Styles Controllable Portrait Animation Progressive disentangled representation learning for fine-grained controllable talking head synthesis,

Reference 50

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T12:43:30.839573Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 4841976a-bf37-4262-a744-c86f37d48914 · outbound

This paper cites PLLaVA : Parameter-free LLaVA Extension from Images to Videos for Video Dense Captioning.

DiTalker: A Unified DiT-based Framework for High-Quality and Speaking Styles Controllable Portrait Animation PLLaVA : Parameter-free LLaVA Extension from Images to Videos for Video Dense Captioning

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-06T12:43:25.371332Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 12e53d0b-d73e-49f8-9cd5-eaf8efb3e117 · outbound

This paper cites Animate anyone: Consistent and controllable image-to-video synthesis for character animation,.

DiTalker: A Unified DiT-based Framework for High-Quality and Speaking Styles Controllable Portrait Animation Animate anyone: Consistent and controllable image-to-video synthesis for character animation,

Reference 52

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T12:43:30.685967Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation d8204951-6415-48ad-8c77-e803742d4b90 · outbound

This paper cites Megactor- σ: Unlocking flexible mixed-modal control in portrait animation with diffusion transformer,.

DiTalker: A Unified DiT-based Framework for High-Quality and Speaking Styles Controllable Portrait Animation Megactor- σ: Unlocking flexible mixed-modal control in portrait animation with diffusion transformer,

Reference 53

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T12:43:30.479263Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation fedecec2-efc7-46d6-9efa-406140d0c4be · outbound

This paper cites Vasa-1: Lifelike audio-driven talking faces generated in real time,.

DiTalker: A Unified DiT-based Framework for High-Quality and Speaking Styles Controllable Portrait Animation Vasa-1: Lifelike audio-driven talking faces generated in real time,

Reference 54

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T12:43:30.267860Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation d810176f-352f-4331-9db9-d1a337d234a0 · outbound

This paper cites High- resolution image synthesis with latent diffusion models,.

DiTalker: A Unified DiT-based Framework for High-Quality and Speaking Styles Controllable Portrait Animation High- resolution image synthesis with latent diffusion models,

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-06T12:43:25.877250Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1395334b-d60f-4ab7-82ed-0b771d9c44b9 · outbound

This paper cites Easyanimate: A high-performance long video gen- eration method based on transformer architecture,.

DiTalker: A Unified DiT-based Framework for High-Quality and Speaking Styles Controllable Portrait Animation Easyanimate: A high-performance long video gen- eration method based on transformer architecture,

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-06T12:43:25.953112Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c4f017e6-91b8-4be8-aa3d-ed68e2a76e37 · outbound

This paper cites Sora: A Review on Background, Technology, Limitations, and Opportunities of Large Vision Models.

DiTalker: A Unified DiT-based Framework for High-Quality and Speaking Styles Controllable Portrait Animation Sora: A Review on Background, Technology, Limitations, and Opportunities of Large Vision Models

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-06T12:43:26.010676Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 99c38c09-4ff1-48b9-b933-742b6633e492 · outbound

This paper cites An image is worth 16x16 words: Transformers for image recognition at scale,.

DiTalker: A Unified DiT-based Framework for High-Quality and Speaking Styles Controllable Portrait Animation An image is worth 16x16 words: Transformers for image recognition at scale,

Reference 58

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T12:43:30.081629Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 07ce0a9e-4aa9-42c5-9f5c-51fbb3c3124a · outbound

This paper cites Effective whole-body pose estimation with two-stages distillation,.

DiTalker: A Unified DiT-based Framework for High-Quality and Speaking Styles Controllable Portrait Animation Effective whole-body pose estimation with two-stages distillation,

Reference 59

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T12:43:29.879551Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 97dc7f49-0224-44b6-967f-5e19fca39027 · outbound

This paper cites Stylecrafter: Enhancing stylized text-to-video generation with style adapter,.

DiTalker: A Unified DiT-based Framework for High-Quality and Speaking Styles Controllable Portrait Animation Stylecrafter: Enhancing stylized text-to-video generation with style adapter,

Reference 60

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T12:43:29.655657Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation b0e833b1-9f78-4b4d-97ba-b86315713c97 · outbound

This paper cites Learning transferable visual models from natural language supervision,.

DiTalker: A Unified DiT-based Framework for High-Quality and Speaking Styles Controllable Portrait Animation Learning transferable visual models from natural language supervision,

Reference 61

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T12:43:29.491485Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 0bc9ccad-1c30-45bf-bf48-2b8db2da1e75 · outbound

This paper cites Vision transformer with quad- rangle attention,.

DiTalker: A Unified DiT-based Framework for High-Quality and Speaking Styles Controllable Portrait Animation Vision transformer with quad- rangle attention,

Reference 62

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T12:43:29.346309Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 10ac8c89-d956-4722-8868-8d3baa0e54ed · outbound

This paper cites Celebv-text: A large-scale facial text-video dataset,.

DiTalker: A Unified DiT-based Framework for High-Quality and Speaking Styles Controllable Portrait Animation Celebv-text: A large-scale facial text-video dataset,

Reference 63

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T12:43:29.150137Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation eb870c7b-82ee-490b-9c7b-310cc136010f · outbound

This paper cites DH-FaceVid-1K: A Large-Scale High-Quality Dataset for Face Video Generation.

DiTalker: A Unified DiT-based Framework for High-Quality and Speaking Styles Controllable Portrait Animation DH-FaceVid-1K: A Large-Scale High-Quality Dataset for Face Video Generation

Reference 64

Resolution: unresolved; no resolver link, observed 2026-08-06T12:43:26.732825Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cfad3b58-5566-457a-8896-b88f521e39f0 · outbound

This paper cites Mead: A large-scale audio-visual dataset for emotional talking-face generation,.

DiTalker: A Unified DiT-based Framework for High-Quality and Speaking Styles Controllable Portrait Animation Mead: A large-scale audio-visual dataset for emotional talking-face generation,

Reference 65

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T12:43:28.940438Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 74c75899-b98c-4529-acdf-2cdec7496d4e · outbound

This paper cites LatentSync: Taming Audio-Conditioned Latent Diffusion Models for Lip Sync with SyncNet Supervision.

DiTalker: A Unified DiT-based Framework for High-Quality and Speaking Styles Controllable Portrait Animation LatentSync: Taming Audio-Conditioned Latent Diffusion Models for Lip Sync with SyncNet Supervision

Reference 66

Resolution: unresolved; no resolver link, observed 2026-08-06T12:43:27.004117Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6d984e16-3249-45e2-a821-dcc5d65678b2 · outbound

This paper cites Gans trained by a two time-scale update rule converge to a local nash equilibrium,.

DiTalker: A Unified DiT-based Framework for High-Quality and Speaking Styles Controllable Portrait Animation Gans trained by a two time-scale update rule converge to a local nash equilibrium,

Reference 67

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T12:43:28.758591Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation d756d998-225c-4e56-8b4b-280b72fec00a · outbound

This paper cites Video-to-video synthesis,.

DiTalker: A Unified DiT-based Framework for High-Quality and Speaking Styles Controllable Portrait Animation Video-to-video synthesis,

Reference 68

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T12:43:28.559570Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 7db45693-961c-4dc3-afe1-336b58182499 · outbound

This paper cites Ani- mating arbitrary objects via deep motion transfer,.

DiTalker: A Unified DiT-based Framework for High-Quality and Speaking Styles Controllable Portrait Animation Ani- mating arbitrary objects via deep motion transfer,

Reference 69

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T12:43:28.352098Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation fb8e6625-bf93-43b8-9a23-5b65c68f696c · outbound

This paper cites Seeing what you said: Talking face generation guided by a lip reading expert,.

DiTalker: A Unified DiT-based Framework for High-Quality and Speaking Styles Controllable Portrait Animation Seeing what you said: Talking face generation guided by a lip reading expert,

Reference 70

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T12:43:28.145129Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 64953955-4a54-4cc1-a894-2bdbaeebdd65 · outbound

This paper cites Towards robust blind face restoration with codebook lookup transformer,.

DiTalker: A Unified DiT-based Framework for High-Quality and Speaking Styles Controllable Portrait Animation Towards robust blind face restoration with codebook lookup transformer,

Reference 71

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T12:43:27.914596Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Pith citing papers

Observation d773345f-2744-4f8c-a9d3-c70dc31562d1 · inbound

CogPortrait: Fine-Grained Eye-Region Control in Portrait Animation via Hierarchical Agent Planning cites this paper.

CogPortrait: Fine-Grained Eye-Region Control in Portrait Animation via Hierarchical Agent Planning DiTalker: A Unified DiT-based Framework for High-Quality and Speaking Styles Controllable Portrait Animation

Reference 15

Resolution: verified exact; arxiv_id, observed 2026-06-29T13:13:27.685726Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation be47e19f-0ab2-41bd-8864-6cb4b794748e · inbound

LaCache: Exact Caching and Precision-Adaptive Inference for Diffusion Large Language Models cites this paper.

LaCache: Exact Caching and Precision-Adaptive Inference for Diffusion Large Language Models DiTalker: A Unified DiT-based Framework for High-Quality and Speaking Styles Controllable Portrait Animation

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-02T01:01:54.160626Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.