Paper Citation Record · LEDGER

FixTalk: Taming Identity Leakage for High-Quality Talking Head Generation in Extreme Cases

As of 7 August 2026, this Paper Citation Record lists 100 of 100 outbound references and 3 inbound Pith citation observations for arXiv:2507.01390.

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

pith.paper-citation-record.v1
2507.01390 v1

Coverage vector

measured 100 of 100 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-06T20:58:32.804437Z

measured 103 of 103 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-06T06:34:29.942622+00:00

measured 3 of 3 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-05T19:07:29.217054Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-06-29T08:03:13.813124Z

Reference resolution

100 of 100 outbound references displayed

verified exact3
verified fuzzy42
unresolved54
parse uncertain1
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 5f833766-b682-420b-aad2-d79e16885251 · outbound

This paper cites MagicPose: Realistic Human Poses and Facial Expressions Retargeting with Identity-aware Diffusion.

FixTalk: Taming Identity Leakage for High-Quality Talking Head Generation in Extreme Cases MagicPose: Realistic Human Poses and Facial Expressions Retargeting with Identity-aware Diffusion

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-06T20:58:21.467931Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9390c551-17ff-4675-80c0-b9b92e7aba57 · outbound

This paper cites AniFaceDiff: Animating Stylized Avatars via Parametric Conditioned Diffusion Models.

FixTalk: Taming Identity Leakage for High-Quality Talking Head Generation in Extreme Cases AniFaceDiff: Animating Stylized Avatars via Parametric Conditioned Diffusion Models

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-06T20:58:21.554078Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d8534d57-228d-4ed3-be0a-1c5f21ee91b5 · outbound

This paper cites Lip movements generation at a glance.

FixTalk: Taming Identity Leakage for High-Quality Talking Head Generation in Extreme Cases Lip movements generation at a glance

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-06T20:58:21.715441Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 09a1aa1f-f02a-48a6-aebd-cc71fddf10a2 · outbound

This paper cites Hierarchical cross-modal talking face generation with dynamic pixel-wise loss.

FixTalk: Taming Identity Leakage for High-Quality Talking Head Generation in Extreme Cases Hierarchical cross-modal talking face generation with dynamic pixel-wise loss

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-06T20:58:21.876831Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a0317fcc-ef60-484e-9aa4-418d68f9e562 · outbound

This paper cites Talking-head generation with rhyth- mic head motion.

FixTalk: Taming Identity Leakage for High-Quality Talking Head Generation in Extreme Cases Talking-head generation with rhyth- mic head motion

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-06T20:58:22.046172Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8c8f1b63-48d9-40f5-b7b2-18fbb7008636 · outbound

This paper cites Vast: Vivify your talk- ing avatar via zero-shot expressive facial style transfer.

FixTalk: Taming Identity Leakage for High-Quality Talking Head Generation in Extreme Cases Vast: Vivify your talk- ing avatar via zero-shot expressive facial style transfer

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-06T20:58:22.197475Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d2afcd9e-6efc-48d3-97ef-7e7d6fc4ee67 · outbound

This paper cites EchoMimic: Lifelike Audio-Driven Portrait Animations through Editable Landmark Conditions.

FixTalk: Taming Identity Leakage for High-Quality Talking Head Generation in Extreme Cases EchoMimic: Lifelike Audio-Driven Portrait Animations through Editable Landmark Conditions

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-06T20:58:22.315210Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3365c6d2-17ee-4693-9e3e-29929e1b7240 · outbound

This paper cites Out of time: auto- mated lip sync in the wild.

FixTalk: Taming Identity Leakage for High-Quality Talking Head Generation in Extreme Cases Out of time: auto- mated lip sync in the wild

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-06T20:58:22.475622Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5c6c34f5-2787-48e5-ad04-0801b8d182cd · outbound

This paper cites Hallo2: Long-Duration and High-Resolution Audio-Driven Portrait Image Animation.

FixTalk: Taming Identity Leakage for High-Quality Talking Head Generation in Extreme Cases Hallo2: Long-Duration and High-Resolution Audio-Driven Portrait Image Animation

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-06T20:58:22.630703Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 02d17b77-7cb3-43cf-9141-75f12639f65e · outbound

This paper cites Hallo3: Highly Dynamic and Realistic Portrait Image Animation with Video Diffusion Transformer.

FixTalk: Taming Identity Leakage for High-Quality Talking Head Generation in Extreme Cases Hallo3: Highly Dynamic and Realistic Portrait Image Animation with Video Diffusion Transformer

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-06T20:58:22.787467Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5f6892af-eed6-4aee-9b20-49d12c35b591 · outbound

This paper cites Speech-driven facial animation using cas- caded gans for learning of motion and texture.

FixTalk: Taming Identity Leakage for High-Quality Talking Head Generation in Extreme Cases Speech-driven facial animation using cas- caded gans for learning of motion and texture

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-06T20:58:22.904616Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 91569752-12db-4caf-b3d0-41df5f9b889a · outbound

This paper cites Megaportraits: One-shot megapixel neural head avatars.

FixTalk: Taming Identity Leakage for High-Quality Talking Head Generation in Extreme Cases Megaportraits: One-shot megapixel neural head avatars

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-06T20:58:23.039770Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 36621e5f-53a4-4240-b2f7-c99f68f6bf17 · outbound

This paper cites Emoportraits: Emotion-enhanced multimodal one-shot head avatars.

FixTalk: Taming Identity Leakage for High-Quality Talking Head Generation in Extreme Cases Emoportraits: Emotion-enhanced multimodal one-shot head avatars

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-06T20:58:23.160720Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1bed86f5-5460-43ba-8d8b-9c8e43a036c8 · outbound

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

FixTalk: Taming Identity Leakage for High-Quality Talking Head Generation in Extreme Cases Efficient emotional adaptation for audio-driven talking-head generation

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-06T20:58:23.309161Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1b6ca795-ca90-4898-856c-05c71a67acdb · outbound

This paper cites Generative adversarial networks.

FixTalk: Taming Identity Leakage for High-Quality Talking Head Generation in Extreme Cases Generative adversarial networks

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-06T20:58:23.444115Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8d5f2a63-e22f-40d2-8c4d-1f49d785d6f3 · outbound

This paper cites Stylesync: High-fidelity generalized and personalized lip sync in style-based genera- tor.

FixTalk: Taming Identity Leakage for High-Quality Talking Head Generation in Extreme Cases Stylesync: High-fidelity generalized and personalized lip sync in style-based genera- tor

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-06T20:58:23.599505Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 326d3489-574c-4c39-b447-d864d5888c40 · outbound

This paper cites ReSyncer: Rewiring Style-based Generator for Unified Audio-Visually Synced Facial Performer.

FixTalk: Taming Identity Leakage for High-Quality Talking Head Generation in Extreme Cases ReSyncer: Rewiring Style-based Generator for Unified Audio-Visually Synced Facial Performer

Reference 17

Resolution: verified exact; local_arxiv, observed 2026-08-06T20:58:34.043456Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 53726732-687d-45fc-80d2-701344beac12 · outbound

This paper cites LivePortrait: Efficient Portrait Animation with Stitching and Retargeting Control.

FixTalk: Taming Identity Leakage for High-Quality Talking Head Generation in Extreme Cases LivePortrait: Efficient Portrait Animation with Stitching and Retargeting Control

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-06T20:58:23.941280Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 49a37c06-cd84-4cc2-bf49-df0975b38007 · outbound

This paper cites MIMAFace: Face Animation via Motion-Identity Modulated Appearance Feature Learning.

FixTalk: Taming Identity Leakage for High-Quality Talking Head Generation in Extreme Cases MIMAFace: Face Animation via Motion-Identity Modulated Appearance Feature Learning

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-06T20:58:24.056864Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bff06acf-b371-42f8-9b8f-5f3d863c157d · outbound

This paper cites Depth-aware generative adversarial network for talking head video generation.

FixTalk: Taming Identity Leakage for High-Quality Talking Head Generation in Extreme Cases Depth-aware generative adversarial network for talking head video generation

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-06T20:58:24.222486Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 87f4bb73-c48b-4ebf-8415-3c952b96d92f · outbound

This paper cites Image quality metrics: Psnr vs.

FixTalk: Taming Identity Leakage for High-Quality Talking Head Generation in Extreme Cases Image quality metrics: Psnr vs

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-06T20:58:24.412644Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 54de9502-8151-4291-abb5-d848315272c2 · outbound

This paper cites Animate Anyone: Consistent and Controllable Image-to-Video Synthesis for Character Animation.

FixTalk: Taming Identity Leakage for High-Quality Talking Head Generation in Extreme Cases Animate Anyone: Consistent and Controllable Image-to-Video Synthesis for Character Animation

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-06T20:58:24.581586Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 53f342e7-3c36-4954-9794-7317db3a2a97 · outbound

This paper cites You said that?: Synthesising talking faces from audio.

FixTalk: Taming Identity Leakage for High-Quality Talking Head Generation in Extreme Cases You said that?: Synthesising talking faces from audio

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-06T20:58:24.716893Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b95e8d46-d00e-40ed-b3c9-720002ddcd98 · outbound

This paper cites Stylevr: Stylizing character animations with normal- izing flows.

FixTalk: Taming Identity Leakage for High-Quality Talking Head Generation in Extreme Cases Stylevr: Stylizing character animations with normal- izing flows

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-06T20:58:24.913012Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6329ee8a-5a73-4019-8d8c-8d79c8b3a4cf · outbound

This paper cites Sport: From zero-shot prompts to real-time motion gener- ation.

FixTalk: Taming Identity Leakage for High-Quality Talking Head Generation in Extreme Cases Sport: From zero-shot prompts to real-time motion gener- ation

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-06T20:58:25.124693Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0e998991-59a5-4f91-b10b-e24aa973e0c1 · outbound

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

FixTalk: Taming Identity Leakage for High-Quality Talking Head Generation in Extreme Cases Eamm: One-shot emotional talking face via audio-based emotion-aware motion model

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-06T20:58:25.339089Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a8f7659b-237e-432f-b8f1-d8c16d291a53 · outbound

This paper cites Loopy: Taming Audio-Driven Portrait Avatar with Long-Term Motion Dependency.

FixTalk: Taming Identity Leakage for High-Quality Talking Head Generation in Extreme Cases Loopy: Taming Audio-Driven Portrait Avatar with Long-Term Motion Dependency

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-06T20:58:25.497728Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9838acb1-9a47-452f-9d4e-646f031f3948 · outbound

This paper cites Percep- tual losses for real-time style transfer and super-resolution.

FixTalk: Taming Identity Leakage for High-Quality Talking Head Generation in Extreme Cases Percep- tual losses for real-time style transfer and super-resolution

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-06T20:58:25.704083Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ab19e5d0-2d8a-4875-9fd6-131475d75aee · outbound

This paper cites Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models.

FixTalk: Taming Identity Leakage for High-Quality Talking Head Generation in Extreme Cases Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-06T20:58:25.793774Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7597572e-a216-4343-be70-88d0ed1b0ef1 · outbound

This paper cites Intergen: Diffusion-based multi-human motion genera- tion under complex interactions.

FixTalk: Taming Identity Leakage for High-Quality Talking Head Generation in Extreme Cases Intergen: Diffusion-based multi-human motion genera- tion under complex interactions

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-06T20:58:25.880766Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 116419c8-75ac-4a35-a5cc-d9c71e95eac8 · outbound

This paper cites CyberHost: Taming Audio-driven Avatar Diffusion Model with Region Codebook Attention.

FixTalk: Taming Identity Leakage for High-Quality Talking Head Generation in Extreme Cases CyberHost: Taming Audio-driven Avatar Diffusion Model with Region Codebook Attention

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-06T20:58:25.954676Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 42b51f07-8418-4ce0-b1a8-65fce0b9a4fc · outbound

This paper cites AniTalker: Animate Vivid and Diverse Talking Faces through Identity-Decoupled Facial Motion Encoding.

FixTalk: Taming Identity Leakage for High-Quality Talking Head Generation in Extreme Cases AniTalker: Animate Vivid and Diverse Talking Faces through Identity-Decoupled Facial Motion Encoding

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-06T20:58:26.077777Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8970cea0-eb16-4c25-beb7-0ad61023ec35 · outbound

This paper cites VQTalker: Towards Multilingual Talking Avatars through Facial Motion Tokenization.

FixTalk: Taming Identity Leakage for High-Quality Talking Head Generation in Extreme Cases VQTalker: Towards Multilingual Talking Avatars through Facial Motion Tokenization

Reference 33

Resolution: verified exact; local_arxiv, observed 2026-08-06T20:58:33.668649Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 1f82563c-333c-4f26-a612-7f79f2b70c6b · outbound

This paper cites Cvthead: One-shot controllable head avatar with vertex-feature transformer.

FixTalk: Taming Identity Leakage for High-Quality Talking Head Generation in Extreme Cases Cvthead: One-shot controllable head avatar with vertex-feature transformer

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:58:43.696425Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation abad82ae-21ab-4e66-b392-e5c7026b074a · outbound

This paper cites Follow-Your-Emoji: Fine-Controllable and Expressive Freestyle Portrait Animation.

FixTalk: Taming Identity Leakage for High-Quality Talking Head Generation in Extreme Cases Follow-Your-Emoji: Fine-Controllable and Expressive Freestyle Portrait Animation

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-06T20:58:26.335483Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b234cd9c-b898-4562-9e7a-7fba56894c4e · outbound

This paper cites Echomimicv2: Towards striking, simplified, and semi-body human animation.

FixTalk: Taming Identity Leakage for High-Quality Talking Head Generation in Extreme Cases Echomimicv2: Towards striking, simplified, and semi-body human animation

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-06T20:58:26.442215Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7a79d737-fc3b-41dd-95e6-1234db06ff9d · outbound

This paper cites completely blind.

FixTalk: Taming Identity Leakage for High-Quality Talking Head Generation in Extreme Cases completely blind

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:58:43.488774Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation ba1c3d46-a838-436d-aeee-c88931d91d78 · outbound

This paper cites Emotional voice puppetry.

FixTalk: Taming Identity Leakage for High-Quality Talking Head Generation in Extreme Cases Emotional voice puppetry

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:58:43.237797Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 1c104941-3f65-4724-a74b-2f4a1d345243 · outbound

This paper cites Expressive talking avatars.

FixTalk: Taming Identity Leakage for High-Quality Talking Head Generation in Extreme Cases Expressive talking avatars

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:58:42.991292Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 30be8b83-68b0-4b8f-97f5-1f1721d796b3 · outbound

This paper cites Vasa-rig: Audio-driven 3d facial animation with ‘live’mood dynamics in virtual reality.

FixTalk: Taming Identity Leakage for High-Quality Talking Head Generation in Extreme Cases Vasa-rig: Audio-driven 3d facial animation with ‘live’mood dynamics in virtual reality

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:58:42.710067Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 2d8a285e-3a8e-4328-86fa-56318be32cfd · outbound

This paper cites Dpe: Dis- entanglement of pose and expression for general video por- trait editing.

FixTalk: Taming Identity Leakage for High-Quality Talking Head Generation in Extreme Cases Dpe: Dis- entanglement of pose and expression for general video por- trait editing

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-06T20:58:26.983504Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1eb63fe8-f14d-43ae-b645-876b9c74348e · outbound

This paper cites ControlNeXt: Powerful and Efficient Control for Image and Video Generation.

FixTalk: Taming Identity Leakage for High-Quality Talking Head Generation in Extreme Cases ControlNeXt: Powerful and Efficient Control for Image and Video Generation

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-06T20:58:27.059131Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f5c24d2f-8b78-498e-be3e-7f1b7b1ef125 · outbound

This paper cites High-resolution image syn- thesis with latent diffusion models.

FixTalk: Taming Identity Leakage for High-Quality Talking Head Generation in Extreme Cases High-resolution image syn- thesis with latent diffusion models

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-06T20:58:27.157855Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ff5085ea-8f6d-46b7-9e9d-8e1ef0ac780a · outbound

This paper cites pytorch-fid: FID Score for PyTorch.

FixTalk: Taming Identity Leakage for High-Quality Talking Head Generation in Extreme Cases pytorch-fid: FID Score for PyTorch

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-06T20:58:27.225742Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fa30d92d-fc59-4934-b54a-4f122da70942 · outbound

This paper cites Learning dynamic facial radiance fields for few-shot talking head synthesis.

FixTalk: Taming Identity Leakage for High-Quality Talking Head Generation in Extreme Cases Learning dynamic facial radiance fields for few-shot talking head synthesis

Reference 45

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:58:42.404195Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 31b7320f-a108-4da5-8791-cbc5278595ff · outbound

This paper cites Difftalk: Crafting diffusion models for generalized audio-driven portraits animation.

FixTalk: Taming Identity Leakage for High-Quality Talking Head Generation in Extreme Cases Difftalk: Crafting diffusion models for generalized audio-driven portraits animation

Reference 46

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:58:42.107540Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation fa16f019-5c28-4429-be99-0d3731a603fc · outbound

This paper cites Motionstone: Decoupled motion in- tensity modulation with diffusion transformer for image-to- video generation.

FixTalk: Taming Identity Leakage for High-Quality Talking Head Generation in Extreme Cases Motionstone: Decoupled motion in- tensity modulation with diffusion transformer for image-to- video generation

Reference 47

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:58:41.912248Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 531ad2a9-b71f-4779-9e82-c793ee3b63dc · outbound

This paper cites Very Deep Convolutional Networks for Large-Scale Image Recognition.

FixTalk: Taming Identity Leakage for High-Quality Talking Head Generation in Extreme Cases Very Deep Convolutional Networks for Large-Scale Image Recognition

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-06T20:58:27.622630Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dcd1f923-e9d2-415d-82a3-217aa1d593fd · outbound

This paper cites Talking face generation by conditional recurrent adversarial network.

FixTalk: Taming Identity Leakage for High-Quality Talking Head Generation in Extreme Cases Talking face generation by conditional recurrent adversarial network

Reference 49

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:58:41.638652Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation b1ec8c6e-db41-485d-8036-33705b0dd78f · outbound

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

FixTalk: Taming Identity Leakage for High-Quality Talking Head Generation in Extreme Cases Emmn: Emotional motion memory network for audio-driven emotional talking face generation

Reference 50

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:58:41.522224Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 2421377a-b90b-4b9c-9c20-e6245e05c527 · outbound

This paper cites Say anything with any style.

FixTalk: Taming Identity Leakage for High-Quality Talking Head Generation in Extreme Cases Say anything with any style

Reference 51

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:58:41.280602Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation fb7f0277-3747-4a2b-b88d-1a002a64eed9 · outbound

This paper cites Flowvqtalker: High-quality emotional talking face generation through normalizing flow and quantization.

FixTalk: Taming Identity Leakage for High-Quality Talking Head Generation in Extreme Cases Flowvqtalker: High-quality emotional talking face generation through normalizing flow and quantization

Reference 52

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:58:41.040401Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 3d9b1bc7-0dde-44ad-81b4-13337c1db04c · outbound

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

FixTalk: Taming Identity Leakage for High-Quality Talking Head Generation in Extreme Cases Style2talker: High-resolution talking head generation with emotion style and art style

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-06T20:58:28.159722Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4a987c1c-7873-44d4-9077-67d2aaf5b470 · outbound

This paper cites Mimir: Improving video diffusion models for precise text understanding.

FixTalk: Taming Identity Leakage for High-Quality Talking Head Generation in Extreme Cases Mimir: Improving video diffusion models for precise text understanding

Reference 54

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:58:40.896869Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation b58591a4-7f66-41c4-9dc1-707728e03e4c · outbound

This paper cites Animate-x: Universal character image ani- mation with enhanced motion representation.

FixTalk: Taming Identity Leakage for High-Quality Talking Head Generation in Extreme Cases Animate-x: Universal character image ani- mation with enhanced motion representation

Reference 55

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:58:40.753289Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 20fd1b1f-af0c-452d-94b4-116723df07bb · outbound

This paper cites SynMotion: Semantic-Visual Adaptation for Motion Customized Video Generation.

FixTalk: Taming Identity Leakage for High-Quality Talking Head Generation in Extreme Cases SynMotion: Semantic-Visual Adaptation for Motion Customized Video Generation

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-06T20:58:28.474259Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 887adebb-fad8-453c-9328-086947d0e3ea · outbound

This paper cites Edtalk: Effi- cient disentanglement for emotional talking head synthesis.

FixTalk: Taming Identity Leakage for High-Quality Talking Head Generation in Extreme Cases Edtalk: Effi- cient disentanglement for emotional talking head synthesis

Reference 57

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:58:40.538330Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 9cedcbad-b5c4-4e9b-8b1f-7f14712dbb82 · outbound

This paper cites SVP: Style-Enhanced Vivid Portrait Talking Head Diffusion Model.

FixTalk: Taming Identity Leakage for High-Quality Talking Head Generation in Extreme Cases SVP: Style-Enhanced Vivid Portrait Talking Head Diffusion Model

Reference 58

Resolution: verified exact; local_arxiv, observed 2026-08-06T20:58:33.273982Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation dbca7167-10d2-4387-bd09-2df7452ec0cd · outbound

This paper cites Neural voice puppetry: Audio-driven facial reenactment.

FixTalk: Taming Identity Leakage for High-Quality Talking Head Generation in Extreme Cases Neural voice puppetry: Audio-driven facial reenactment

Reference 59

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:58:40.154927Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation befc3a51-deff-4126-a597-9c3651d1d961 · outbound

This paper cites EMO: Emote Portrait Alive -- Generating Expressive Portrait Videos with Audio2Video Diffusion Model under Weak Conditions.

FixTalk: Taming Identity Leakage for High-Quality Talking Head Generation in Extreme Cases EMO: Emote Portrait Alive -- Generating Expressive Portrait Videos with Audio2Video Diffusion Model under Weak Conditions

Reference 60

Resolution: unresolved; no resolver link, observed 2026-08-06T20:58:29.031658Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e66f2708-d428-452b-896a-08f7ebeccf12 · outbound

This paper cites Musepose: a pose-driven image-to-video framework for virtual human generation.

FixTalk: Taming Identity Leakage for High-Quality Talking Head Generation in Extreme Cases Musepose: a pose-driven image-to-video framework for virtual human generation

Reference 61

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:58:39.852794Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 98d04961-ce78-42d9-b84f-7ae201428550 · outbound

This paper cites Nonlinear 3d face morphable model.

FixTalk: Taming Identity Leakage for High-Quality Talking Head Generation in Extreme Cases Nonlinear 3d face morphable model

Reference 62

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:58:39.600375Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation ee190d78-90bf-4f79-ad74-d0c88e692da8 · outbound

This paper cites V-Express: Conditional Dropout for Progressive Training of Portrait Video Generation.

FixTalk: Taming Identity Leakage for High-Quality Talking Head Generation in Extreme Cases V-Express: Conditional Dropout for Progressive Training of Portrait Video Generation

Reference 63

Resolution: unresolved; no resolver link, observed 2026-08-06T20:58:29.324951Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 99ffb67b-0bda-43c0-9d6e-2bf9cf544c0b · outbound

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

FixTalk: Taming Identity Leakage for High-Quality Talking Head Generation in Extreme Cases Progressive disentangled representation learning for fine-grained controllable talking head synthesis

Reference 64

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:58:39.318871Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 1fbeee6a-3035-4a17-8af4-1c4f00409678 · outbound

This paper cites Seeing what you said: Talking face gen- eration guided by a lip reading expert.

FixTalk: Taming Identity Leakage for High-Quality Talking Head Generation in Extreme Cases Seeing what you said: Talking face gen- eration guided by a lip reading expert

Reference 65

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:58:39.034756Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 72634791-17c9-42a2-9019-621edc2e9e4a · outbound

This paper cites Lipformer: High- fidelity and generalizable talking face generation with a pre- learned facial codebook.

FixTalk: Taming Identity Leakage for High-Quality Talking Head Generation in Extreme Cases Lipformer: High- fidelity and generalizable talking face generation with a pre- learned facial codebook

Reference 66

Resolution: unresolved; no resolver link, observed 2026-08-06T20:58:29.636580Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0bc4fbf0-f1fc-477e-840d-fd165aedb2dd · outbound

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

FixTalk: Taming Identity Leakage for High-Quality Talking Head Generation in Extreme Cases Mead: A large-scale audio-visual dataset for emo- tional talking-face generation

Reference 67

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:58:38.816675Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 3ed927c6-e97b-4e08-a417-6a6429683fed · outbound

This paper cites Audio2head: Audio-driven one-shot talking-head generation with natural head motion.

FixTalk: Taming Identity Leakage for High-Quality Talking Head Generation in Extreme Cases Audio2head: Audio-driven one-shot talking-head generation with natural head motion

Reference 68

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:58:38.598452Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation aea350c2-958e-4a8a-a74a-5b4f0822ec4c · outbound

This paper cites Disco: Disentangled control for referring human dance generation in real world.

FixTalk: Taming Identity Leakage for High-Quality Talking Head Generation in Extreme Cases Disco: Disentangled control for referring human dance generation in real world

Reference 69

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:58:38.406625Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation bab25467-5366-4cad-b580-e8b49db5d21d · outbound

This paper cites UniAnimate: Taming Unified Video Diffusion Models for Consistent Human Image Animation.

FixTalk: Taming Identity Leakage for High-Quality Talking Head Generation in Extreme Cases UniAnimate: Taming Unified Video Diffusion Models for Consistent Human Image Animation

Reference 70

Resolution: unresolved; no resolver link, observed 2026-08-06T20:58:29.969998Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f1f2911d-d7fd-45f2-aa6a-753bfd1a4426 · outbound

This paper cites Latent image animator: Learning to animate im- ages via latent space navigation.

FixTalk: Taming Identity Leakage for High-Quality Talking Head Generation in Extreme Cases Latent image animator: Learning to animate im- ages via latent space navigation

Reference 71

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:58:38.138612Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation d2d91d2a-a9aa-4d63-aa86-94125651dfc8 · outbound

This paper cites Image quality assessment: from error visibility to structural similarity.

FixTalk: Taming Identity Leakage for High-Quality Talking Head Generation in Extreme Cases Image quality assessment: from error visibility to structural similarity

Reference 72

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:58:37.928749Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 534c2f23-5cda-436d-a0eb-70529f971d27 · outbound

This paper cites Restoreformer: High-quality blind face restoration from undegraded key-value pairs.

FixTalk: Taming Identity Leakage for High-Quality Talking Head Generation in Extreme Cases Restoreformer: High-quality blind face restoration from undegraded key-value pairs

Reference 73

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:58:37.684026Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation b3eff734-9988-4b39-90e7-632f17a4d897 · outbound

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

FixTalk: Taming Identity Leakage for High-Quality Talking Head Generation in Extreme Cases AniPortrait: Audio-Driven Synthesis of Photorealistic Portrait Animation

Reference 74

Resolution: unresolved; no resolver link, observed 2026-08-06T20:58:30.336835Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5e8cc5b2-7334-4f99-86d0-90d1ae5c7bfd · outbound

This paper cites F 3a-gan: Facial flow for face animation with generative adversarial networks.

FixTalk: Taming Identity Leakage for High-Quality Talking Head Generation in Extreme Cases F 3a-gan: Facial flow for face animation with generative adversarial networks

Reference 75

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:58:37.408365Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 1fe8539c-6dd0-497f-878e-44a5c2e4a2e4 · outbound

This paper cites Vfhq: A high-quality dataset and bench- mark for video face super-resolution.

FixTalk: Taming Identity Leakage for High-Quality Talking Head Generation in Extreme Cases Vfhq: A high-quality dataset and bench- mark for video face super-resolution

Reference 76

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:58:37.235525Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation cb433dee-9d90-4745-9793-0096570269d7 · outbound

This paper cites X-portrait: Expressive portrait anima- tion with hierarchical motion attention.

FixTalk: Taming Identity Leakage for High-Quality Talking Head Generation in Extreme Cases X-portrait: Expressive portrait anima- tion with hierarchical motion attention

Reference 77

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:58:37.023590Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 7ee5b291-450d-4725-a774-594001b100eb · outbound

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

FixTalk: Taming Identity Leakage for High-Quality Talking Head Generation in Extreme Cases Hallo: Hierarchical Audio-Driven Visual Synthesis for Portrait Image Animation

Reference 78

Resolution: unresolved; no resolver link, observed 2026-08-06T20:58:30.681138Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bd6d5c86-2636-4b16-af03-b15bd429c157 · outbound

This paper cites VASA-1: Lifelike Audio-Driven Talking Faces Generated in Real Time.

FixTalk: Taming Identity Leakage for High-Quality Talking Head Generation in Extreme Cases VASA-1: Lifelike Audio-Driven Talking Faces Generated in Real Time

Reference 79

Resolution: unresolved; no resolver link, observed 2026-08-06T20:58:30.797463Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f358ffa3-3f07-4dfb-8b15-1b8a457cd832 · outbound

This paper cites MagicAnimate: Temporally Consistent Human Image Animation using Diffusion Model.

FixTalk: Taming Identity Leakage for High-Quality Talking Head Generation in Extreme Cases MagicAnimate: Temporally Consistent Human Image Animation using Diffusion Model

Reference 80

Resolution: unresolved; no resolver link, observed 2026-08-06T20:58:30.864897Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c888266b-5d39-424b-896a-7a7db9673c9f · outbound

This paper cites SMGDiff: Soccer Motion Generation using diffusion probabilistic models.

FixTalk: Taming Identity Leakage for High-Quality Talking Head Generation in Extreme Cases SMGDiff: Soccer Motion Generation using diffusion probabilistic models

Reference 81

Resolution: unresolved; no resolver link, observed 2026-08-06T20:58:30.937663Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 041d4b38-36c0-4eb5-8e61-a2cfbd792a98 · outbound

This paper cites Face2face ρ: Real- time high-resolution one-shot face reenactment.

FixTalk: Taming Identity Leakage for High-Quality Talking Head Generation in Extreme Cases Face2face ρ: Real- time high-resolution one-shot face reenactment

Reference 82

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:58:36.844445Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 734c68aa-587f-4c4e-bccf-543d181d8d9d · outbound

This paper cites MegActor: Harness the Power of Raw Video for Vivid Portrait Animation.

FixTalk: Taming Identity Leakage for High-Quality Talking Head Generation in Extreme Cases MegActor: Harness the Power of Raw Video for Vivid Portrait Animation

Reference 83

Resolution: unresolved; no resolver link, observed 2026-08-06T20:58:31.076359Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f4a97ade-ec12-49e6-9a14-2af222fe9663 · outbound

This paper cites SUPERB: Speech processing Universal PERformance Benchmark.

FixTalk: Taming Identity Leakage for High-Quality Talking Head Generation in Extreme Cases SUPERB: Speech processing Universal PERformance Benchmark

Reference 84

Resolution: unresolved; no resolver link, observed 2026-08-06T20:58:31.169287Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 97a29b95-7c82-4e85-89e8-27cabbab07b9 · outbound

This paper cites Mesh guided one-shot face reenactment using graph convo- lutional networks.

FixTalk: Taming Identity Leakage for High-Quality Talking Head Generation in Extreme Cases Mesh guided one-shot face reenactment using graph convo- lutional networks

Reference 85

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:58:36.622982Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 37c67c33-680e-4964-81aa-b5805b6574a1 · outbound

This paper cites Few-shot adversarial learning of realistic neural talking head models.

FixTalk: Taming Identity Leakage for High-Quality Talking Head Generation in Extreme Cases Few-shot adversarial learning of realistic neural talking head models

Reference 86

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:58:36.392325Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation edf1eeea-1cc9-45bf-ab9c-3cbf164a06af · outbound

This paper cites Metaportrait: Identity-preserving talking head gener- ation with fast personalized adaptation.

FixTalk: Taming Identity Leakage for High-Quality Talking Head Generation in Extreme Cases Metaportrait: Identity-preserving talking head gener- ation with fast personalized adaptation

Reference 87

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:58:36.149735Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation c9d21c2c-a648-4d50-a1e3-2baaddcab1f5 · outbound

This paper cites The unreasonable effectiveness of deep features as a perceptual metric.

FixTalk: Taming Identity Leakage for High-Quality Talking Head Generation in Extreme Cases The unreasonable effectiveness of deep features as a perceptual metric

Reference 88

Resolution: unresolved; no resolver link, observed 2026-08-06T20:58:31.622546Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 23998122-e4a8-459c-9bd5-0cb71faf8c0b · outbound

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

FixTalk: Taming Identity Leakage for High-Quality Talking Head Generation in Extreme Cases Sadtalker: Learning realistic 3d motion coefficients for stylized audio- driven single image talking face animation

Reference 89

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:58:35.941143Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation b74cd972-0564-48eb-9b7e-586f0ba90e56 · outbound

This paper cites MimicMotion: High-Quality Human Motion Video Generation with Confidence-aware Pose Guidance.

FixTalk: Taming Identity Leakage for High-Quality Talking Head Generation in Extreme Cases MimicMotion: High-Quality Human Motion Video Generation with Confidence-aware Pose Guidance

Reference 90

Resolution: unresolved; no resolver link, observed 2026-08-06T20:58:31.799959Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0a96a28b-9d1f-46aa-9e78-fca47e338a99 · outbound

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

FixTalk: Taming Identity Leakage for High-Quality Talking Head Generation in Extreme Cases Flow-guided one-shot talking face generation with a high-resolution audio-visual dataset

Reference 91

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:58:35.781103Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation ae71de02-63db-4621-828b-e57a83df5ead · outbound

This paper cites Thin-plate spline motion model for image animation.

FixTalk: Taming Identity Leakage for High-Quality Talking Head Generation in Extreme Cases Thin-plate spline motion model for image animation

Reference 92

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:58:35.564029Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 248fe8b6-4486-4b99-b8a6-eebe0ce884ef · outbound

This paper cites Media2face: Co-speech facial animation gen- eration with multi-modality guidance.

FixTalk: Taming Identity Leakage for High-Quality Talking Head Generation in Extreme Cases Media2face: Co-speech facial animation gen- eration with multi-modality guidance

Reference 93

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:58:35.326278Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation e2e0994e-c849-4a23-8191-a65b98914173 · outbound

This paper cites Sparse to dense motion transfer for face image animation.

FixTalk: Taming Identity Leakage for High-Quality Talking Head Generation in Extreme Cases Sparse to dense motion transfer for face image animation

Reference 94

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:58:35.136674Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 24b38b98-b672-4f55-8dc5-ff3dc8e3f219 · outbound

This paper cites Identity- preserving talking face generation with landmark and ap- pearance priors.

FixTalk: Taming Identity Leakage for High-Quality Talking Head Generation in Extreme Cases Identity- preserving talking face generation with landmark and ap- pearance priors

Reference 95

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:58:34.913685Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 86d62245-8607-43dd-98f6-9a6d06df0322 · outbound

This paper cites Talking face generation by adversarially disentangled audio-visual representation.

FixTalk: Taming Identity Leakage for High-Quality Talking Head Generation in Extreme Cases Talking face generation by adversarially disentangled audio-visual representation

Reference 96

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:58:34.662889Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 65decd62-8445-40e4-8255-57cb9076e37d · outbound

This paper cites Makelttalk: speaker-aware talking-head animation.

FixTalk: Taming Identity Leakage for High-Quality Talking Head Generation in Extreme Cases Makelttalk: speaker-aware talking-head animation

Reference 97

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:58:34.488488Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation da599dc7-6007-4580-9dc4-642d3dbee57a · outbound

This paper cites Champ: Controllable and consistent human image animation with 3d parametric guidance.

FixTalk: Taming Identity Leakage for High-Quality Talking Head Generation in Extreme Cases Champ: Controllable and consistent human image animation with 3d parametric guidance

Reference 98

Resolution: unresolved; no resolver link, observed 2026-08-06T20:58:32.668949Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 492f786e-81f3-44a5-afbd-1a0c0165079b · outbound

This paper cites Face alignment in full pose range: A 3d total solution.IEEE trans- actions on pattern analysis and machine intelligence, 41(1): 78–92, 2017.

FixTalk: Taming Identity Leakage for High-Quality Talking Head Generation in Extreme Cases Face alignment in full pose range: A 3d total solution.IEEE trans- actions on pattern analysis and machine intelligence, 41(1): 78–92, 2017

Reference 99

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:58:34.307232Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 5b9376e4-dd8a-4112-9744-5df75b1e02ee · outbound

This paper cites an unresolved cited work.

FixTalk: Taming Identity Leakage for High-Quality Talking Head Generation in Extreme Cases Unresolved cited work

Reference 416

Resolution: parse uncertain; raw_fallback, observed 2026-08-06T20:58:40.322472Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Pith citing papers

Observation c52eddb4-771e-42d3-8b71-97be5006d837 · inbound

EDTalk++: Full Disentanglement for Controllable Talking Head Synthesis cites this paper.

EDTalk++: Full Disentanglement for Controllable Talking Head Synthesis FixTalk: Taming Identity Leakage for High-Quality Talking Head Generation in Extreme Cases

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-05T19:07:29.217054Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d74195c8-79f0-493a-aa5d-bfeaa318aa64 · inbound

PortraitDirector: A Hierarchical Disentanglement Framework for Controllable and Real-time Facial Reenactment cites this paper.

PortraitDirector: A Hierarchical Disentanglement Framework for Controllable and Real-time Facial Reenactment FixTalk: Taming Identity Leakage for High-Quality Talking Head Generation in Extreme Cases

Reference 44

Resolution: verified exact; arxiv_id, observed 2026-05-11T12:31:04.324918Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation c47e529a-4b32-4ba9-bb48-a179bbb9cebd · inbound

Archon: A Unified Multimodal Model for Holistic Digital Human Generation cites this paper.

Archon: A Unified Multimodal Model for Holistic Digital Human Generation FixTalk: Taming Identity Leakage for High-Quality Talking Head Generation in Extreme Cases

Reference 43

Resolution: verified exact; arxiv_id, observed 2026-06-29T08:03:13.814718Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.