Pith. sign in

Paper Citation Record · LEDGER

Avatar-Forever: Decoupled Parallel Training for High-Quality Real-Time Infinite Avatars

As of 18 August 2026, this Paper Citation Record lists 63 of 63 outbound references and 0 inbound Pith citation observations for arXiv:2608.12107.

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

pith.paper-citation-record.v1
2608.12107 v1

Coverage vector

measured 63 of 63 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-16T00:21:12.348163Z

measured 63 of 63 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-17T06:30:58.91139+00:00

measured 0 of 0 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

63 of 63 outbound references displayed

  • verified exact0
  • verified fuzzy22
  • unresolved41
  • parse uncertain0
  • malformed identifier0
  • metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 90cd8ea8-3005-468f-8ca2-699e73b4fdea · outbound

This paper cites Sadtalker: Learningrealistic3dmotioncoefficientsforstylizedaudio-drivensingleimagetalkingfaceanimation.

Avatar-Forever: Decoupled Parallel Training for High-Quality Real-Time Infinite Avatars Sadtalker: Learningrealistic3dmotioncoefficientsforstylizedaudio-drivensingleimagetalkingfaceanimation

Reference 1

Resolution
verified fuzzy
raw_fallback, observed 2026-08-16T00:21:13.799437Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

source=pdf_text observed=2026-08-16T00:21:12.030393Z digest=sha256:52d825e60f5a3140ad129d20420807cc7e81059af23fe0593976e006a79522bd

Observation 618a305f-6689-4f40-b2a8-f058bc22732b · outbound

This paper cites Latentsync: Audio conditioned latent diffusion models for lip sync.arXiv e-prints, pages arXiv–2412, 2024.

Avatar-Forever: Decoupled Parallel Training for High-Quality Real-Time Infinite Avatars Latentsync: Audio conditioned latent diffusion models for lip sync.arXiv e-prints, pages arXiv–2412, 2024

Reference 2

Resolution
verified fuzzy
raw_fallback, observed 2026-08-16T00:21:13.784914Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

source=pdf_text observed=2026-08-16T00:21:12.036059Z digest=sha256:18d8093a856575ea82706a54cfc9361ae82f68373e8523b4af7758cadc3caa3d

Observation 7b6f2e13-f60a-4832-ad28-9fd1b8622004 · outbound

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

Avatar-Forever: Decoupled Parallel Training for High-Quality Real-Time Infinite Avatars EMO: Emote Portrait Alive -- Generating Expressive Portrait Videos with Audio2Video Diffusion Model under Weak Conditions

Reference 3

Resolution
unresolved
no resolver link, observed 2026-08-16T00:21:12.041570Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-16T00:21:12.041570Z digest=sha256:ad026aef30c4a0671f4f2dca7ff8b1c623342abbda883e7b0d8a2d134deaeb0f

Observation fdad2762-73a8-4444-9ded-843be592acdb · outbound

This paper cites Seedance 2.0: Advancing Video Generation for World Complexity.

Avatar-Forever: Decoupled Parallel Training for High-Quality Real-Time Infinite Avatars Seedance 2.0: Advancing Video Generation for World Complexity

Reference 4

Resolution
unresolved
no resolver link, observed 2026-08-16T00:21:12.047702Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-16T00:21:12.047702Z digest=sha256:9a2368739841793f741c31433c83ec8f748de45a9a0ab64c80b129732a6e8196

Observation f26f6fed-c8e4-43e0-8430-9837f46bb40a · outbound

This paper cites Wan: Open and Advanced Large-Scale Video Generative Models.

Avatar-Forever: Decoupled Parallel Training for High-Quality Real-Time Infinite Avatars Wan: Open and Advanced Large-Scale Video Generative Models

Reference 5

Resolution
unresolved
no resolver link, observed 2026-08-16T00:21:12.055000Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-16T00:21:12.055000Z digest=sha256:4ab14e3a450ba196401c259d95c3701223366a1fc879511c0de2955b19274150

Observation ecf31078-0af0-41eb-9bcb-f416835758ec · outbound

This paper cites LTX-2: Efficient Joint Audio-Visual Foundation Model.

Avatar-Forever: Decoupled Parallel Training for High-Quality Real-Time Infinite Avatars LTX-2: Efficient Joint Audio-Visual Foundation Model

Reference 6

Resolution
unresolved
no resolver link, observed 2026-08-16T00:21:12.066046Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-16T00:21:12.066046Z digest=sha256:c016919969d9b986dc0481d4df292441e6e6ed1c809386eaf611e0ba47ab17cc

Observation f9f675ff-4c71-42f0-952e-4d99f4517a21 · outbound

This paper cites Many-for-many: Unify the training of multiple video and image generation and manipulation tasks.arXiv preprint arXiv:2506.01758, 2025.

Avatar-Forever: Decoupled Parallel Training for High-Quality Real-Time Infinite Avatars Many-for-many: Unify the training of multiple video and image generation and manipulation tasks.arXiv preprint arXiv:2506.01758, 2025

Reference 7

Resolution
unresolved
no resolver link, observed 2026-08-16T00:21:12.073048Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-16T00:21:12.073048Z digest=sha256:f1a2638812ebab8aad844bc2645222af3609c8f1d3976bcdeab074a037b755ef

Observation d62fafee-c74f-4e7f-80f3-9e3c92e771b9 · outbound

This paper cites an unresolved cited work.

Avatar-Forever: Decoupled Parallel Training for High-Quality Real-Time Infinite Avatars Unresolved cited work

Reference 8

Resolution
unresolved
no resolver link, observed 2026-08-16T00:21:12.079436Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-16T00:21:12.079436Z digest=sha256:52c27f827674346099a260387e1fdb15ba38205d379680a3646e49d97a5802de

Observation e62645fd-4876-41a8-a455-9d0ddbc6c3eb · outbound

This paper cites Arig: Autoregressive interactive head generation for real-time conversations.

Avatar-Forever: Decoupled Parallel Training for High-Quality Real-Time Infinite Avatars Arig: Autoregressive interactive head generation for real-time conversations

Reference 9

Resolution
unresolved
no resolver link, observed 2026-08-16T00:21:12.084992Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-16T00:21:12.084992Z digest=sha256:93bace653dc5b18d8c38b2094ac80b8a78d797bb5396f3e675dffc380adcbd27

Observation 39bc82e2-0472-416d-8b3f-9ad5572fa5b4 · outbound

This paper cites Ditto: Motion-space diffusion for controllable realtime talking head synthesis.

Avatar-Forever: Decoupled Parallel Training for High-Quality Real-Time Infinite Avatars Ditto: Motion-space diffusion for controllable realtime talking head synthesis

Reference 10

Resolution
verified fuzzy
raw_fallback, observed 2026-08-16T00:21:13.759589Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

source=pdf_text observed=2026-08-16T00:21:12.090273Z digest=sha256:b175f5239be19404060d7d56e56916a8439659646526fb88bec8080f5dcff5d1

Observation 8eb8e918-304f-4e40-8570-7394b01ae850 · outbound

This paper cites TalkingMachines: Real-Time Audio-Driven FaceTime-Style Video via Autoregressive Diffusion Models.

Avatar-Forever: Decoupled Parallel Training for High-Quality Real-Time Infinite Avatars TalkingMachines: Real-Time Audio-Driven FaceTime-Style Video via Autoregressive Diffusion Models

Reference 11

Resolution
unresolved
no resolver link, observed 2026-08-16T00:21:12.095443Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-16T00:21:12.095443Z digest=sha256:217d58f6514662ad103d3f454edd54c4a4dda3a50a18b0feb69c6d188a709cf6

Observation ad22e35a-f5ce-4676-acb2-d0bfa848c2fe · outbound

This paper cites Avatarforcing: One-step streaming talking avatars via local-future sliding-window denoising.arXiv preprint arXiv:2603.14331, 2026.

Avatar-Forever: Decoupled Parallel Training for High-Quality Real-Time Infinite Avatars Avatarforcing: One-step streaming talking avatars via local-future sliding-window denoising.arXiv preprint arXiv:2603.14331, 2026

Reference 12

Resolution
unresolved
no resolver link, observed 2026-08-16T00:21:12.100874Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-16T00:21:12.100874Z digest=sha256:91150cbc2d5c480208ffddf23a379d170952439dc6ab958b93d9dc0a98630ea8

Observation e30ab339-5b55-4a96-b8c5-5d40fa2a9c79 · outbound

This paper cites From slow bidirectional to fast autoregressive video diffusion models.

Avatar-Forever: Decoupled Parallel Training for High-Quality Real-Time Infinite Avatars From slow bidirectional to fast autoregressive video diffusion models

Reference 13

Resolution
unresolved
no resolver link, observed 2026-08-16T00:21:12.105881Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-16T00:21:12.105881Z digest=sha256:82ceeb06af7eee7490106ff5794e9d8e491631d1a63a37e9def151e52b7ecd2a

Observation 764de3f2-471f-4c22-9da4-40c1d0adeb9d · outbound

This paper cites Self forcing: Bridging the train-test gap in autoregressive video diffusion.Advances in Neural Information Processing Systems, 38:167283–167308, 2026.

Avatar-Forever: Decoupled Parallel Training for High-Quality Real-Time Infinite Avatars Self forcing: Bridging the train-test gap in autoregressive video diffusion.Advances in Neural Information Processing Systems, 38:167283–167308, 2026

Reference 14

Resolution
unresolved
no resolver link, observed 2026-08-16T00:21:12.110194Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-16T00:21:12.110194Z digest=sha256:3e9a58a8a9c98c848ae146bea090c72ec6cbb4df99b5ea7c0ed8185a489eb18d

Observation 6fd224b0-3a27-4159-8068-740421c39671 · outbound

This paper cites Streamavatar: Streaming diffusion models for real-time interactive human avatars.arXiv preprint arXiv:2512.22065, 2026.

Avatar-Forever: Decoupled Parallel Training for High-Quality Real-Time Infinite Avatars Streamavatar: Streaming diffusion models for real-time interactive human avatars.arXiv preprint arXiv:2512.22065, 2026

Reference 15

Resolution
unresolved
no resolver link, observed 2026-08-16T00:21:12.114842Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-16T00:21:12.114842Z digest=sha256:f89eab0623a7e647a0fc24705ecab201a3982e9545267e0aedc5828e665e6d14

Observation b7c9e462-2470-45e9-a20f-dbe923b636a2 · outbound

This paper cites LongLive: Real-time Interactive Long Video Generation.

Avatar-Forever: Decoupled Parallel Training for High-Quality Real-Time Infinite Avatars LongLive: Real-time Interactive Long Video Generation

Reference 16

Resolution
unresolved
no resolver link, observed 2026-08-16T00:21:12.119524Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-16T00:21:12.119524Z digest=sha256:d38f49ecf73a4a6a77428de65be339adc4e8ca3f6b77697828044393787afd8c

Observation 1aee4f68-01ae-4eca-ad98-b265ed3bc14e · outbound

This paper cites Reward forcing: Efficient streaming video generation with rewarded distribution matching distillation.

Avatar-Forever: Decoupled Parallel Training for High-Quality Real-Time Infinite Avatars Reward forcing: Efficient streaming video generation with rewarded distribution matching distillation

Reference 17

Resolution
verified fuzzy
raw_fallback, observed 2026-08-16T00:21:13.724164Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

source=pdf_text observed=2026-08-16T00:21:12.124098Z digest=sha256:8a3529822e053888e22c41a027cea85d0cfba3eb952d90efcde205ae0a3841ca

Observation dc812a9b-08cc-46af-ad35-c90d6ad53e44 · outbound

This paper cites Stable video infinity: Infinite-length video generation with error recycling.arXiv preprint arXiv:2510.09212, 2025.

Avatar-Forever: Decoupled Parallel Training for High-Quality Real-Time Infinite Avatars Stable video infinity: Infinite-length video generation with error recycling.arXiv preprint arXiv:2510.09212, 2025

Reference 18

Resolution
unresolved
no resolver link, observed 2026-08-16T00:21:12.129120Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-16T00:21:12.129120Z digest=sha256:be34db4c0a9fc9d6b522ef1d2c49c5872bc9bec9219b17a8a701a18e4054f9d0

Observation c5036238-6655-409f-b957-2a8aac9fe464 · outbound

This paper cites Causal Forcing: Autoregressive Diffusion Distillation Done Right for High-Quality Real-Time Interactive Video Generation.

Avatar-Forever: Decoupled Parallel Training for High-Quality Real-Time Infinite Avatars Causal Forcing: Autoregressive Diffusion Distillation Done Right for High-Quality Real-Time Interactive Video Generation

Reference 19

Resolution
unresolved
no resolver link, observed 2026-08-16T00:21:12.133863Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-16T00:21:12.133863Z digest=sha256:6e537557d41d5af75d68adb32db72af98aeb14ebd7f66ae7228c6f1e2f405864

Observation d42b35fc-e772-4623-acb2-cb93084164b8 · outbound

This paper cites Infinity-rope: Action-controllable infinite video generation emerges from autoregressive self-rollout.

Avatar-Forever: Decoupled Parallel Training for High-Quality Real-Time Infinite Avatars Infinity-rope: Action-controllable infinite video generation emerges from autoregressive self-rollout

Reference 20

Resolution
verified fuzzy
raw_fallback, observed 2026-08-16T00:21:13.703045Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

source=pdf_text observed=2026-08-16T00:21:12.139765Z digest=sha256:3d6a617a465632081b364f14614dacf838a9bfa5463c29fe9445128be64d2d10

Observation 20bf3793-c4c4-4892-af18-b210139c2f30 · outbound

This paper cites Helios: Real real-time long video generation model.arXiv preprint arXiv:2603.04379, 2026.

Avatar-Forever: Decoupled Parallel Training for High-Quality Real-Time Infinite Avatars Helios: Real real-time long video generation model.arXiv preprint arXiv:2603.04379, 2026

Reference 21

Resolution
unresolved
no resolver link, observed 2026-08-16T00:21:12.144832Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-16T00:21:12.144832Z digest=sha256:5891becb47b315ba6a1e3f3fc9a2b2ac8c68eaef1f4294c780fa8f15ab4bc4e3

Observation e9eff270-f3c1-47d5-ac4f-304309c95a4a · outbound

This paper cites LongLive-2.0: An NVFP4 Parallel Infrastructure for Long Video Generation.

Avatar-Forever: Decoupled Parallel Training for High-Quality Real-Time Infinite Avatars LongLive-2.0: An NVFP4 Parallel Infrastructure for Long Video Generation

Reference 22

Resolution
unresolved
no resolver link, observed 2026-08-16T00:21:12.149933Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-16T00:21:12.149933Z digest=sha256:0f655df275b9b1d17b9e8150f05586f780b010ca2447e6c1a934585ce643b7b8

Observation f36093aa-6eb9-4129-a7a4-3c65de403f76 · outbound

This paper cites LPM 1.0: Video-based Character Performance Model.

Avatar-Forever: Decoupled Parallel Training for High-Quality Real-Time Infinite Avatars LPM 1.0: Video-based Character Performance Model

Reference 23

Resolution
unresolved
no resolver link, observed 2026-08-16T00:21:12.155161Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-16T00:21:12.155161Z digest=sha256:b1fff09f8c9533d543d00b6c6d5e94dc3a4b04b504bd906f8fc7ca0d6898c57c

Observation 9e44b0d0-da37-4eee-b5c2-b1d572d05ea7 · outbound

This paper cites Soulx-flashtalk: Real-time infinite streaming of audio-driven avatars via self-correcting bidirectional distillation.arXiv preprint arXiv:2512.23379, 2026.

Avatar-Forever: Decoupled Parallel Training for High-Quality Real-Time Infinite Avatars Soulx-flashtalk: Real-time infinite streaming of audio-driven avatars via self-correcting bidirectional distillation.arXiv preprint arXiv:2512.23379, 2026

Reference 24

Resolution
unresolved
no resolver link, observed 2026-08-16T00:21:12.160212Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-16T00:21:12.160212Z digest=sha256:d9eff938aa68cd66cbf53cb6206ac5c2a2eb57728c5a0a0d9545c68e740be606

Observation 96efb50d-98b5-4749-b213-c292a111abba · outbound

This paper cites Self-Forcing++: Towards Minute-Scale High-Quality Video Generation.

Avatar-Forever: Decoupled Parallel Training for High-Quality Real-Time Infinite Avatars Self-Forcing++: Towards Minute-Scale High-Quality Video Generation

Reference 25

Resolution
unresolved
no resolver link, observed 2026-08-16T00:21:12.164936Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-16T00:21:12.164936Z digest=sha256:ff20a72dc02cf5843040c067a3e712ab06219a74d19ca4a56b086a030e189425

Observation 7f8f4b10-de11-45d0-8722-507d9acc7dfd · outbound

This paper cites InfiniteTalk: Audio-driven Video Generation for Sparse-Frame Video Dubbing.

Avatar-Forever: Decoupled Parallel Training for High-Quality Real-Time Infinite Avatars InfiniteTalk: Audio-driven Video Generation for Sparse-Frame Video Dubbing

Reference 26

Resolution
unresolved
no resolver link, observed 2026-08-16T00:21:12.170183Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-16T00:21:12.170183Z digest=sha256:b51ac024744639a46c0984b07568eefc8a7558f1aaa446dbac651faa9095cf27

Observation 86f23342-35e0-4206-9ea2-62d1a78b32b6 · outbound

This paper cites Live Avatar: Streaming Real-time Audio-Driven Avatar Generation with Infinite Length.

Avatar-Forever: Decoupled Parallel Training for High-Quality Real-Time Infinite Avatars Live Avatar: Streaming Real-time Audio-Driven Avatar Generation with Infinite Length

Reference 27

Resolution
unresolved
no resolver link, observed 2026-08-16T00:21:12.175287Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-16T00:21:12.175287Z digest=sha256:18403e0d7fdd3a1e27e589d675457c1bd0a4b140c82b0a79109ed8ed3dc39e8c

Observation a7c37c01-35c7-4189-aa1d-9d0e8f35c80a · outbound

This paper cites Style transfer for 2d talking head generation.

Avatar-Forever: Decoupled Parallel Training for High-Quality Real-Time Infinite Avatars Style transfer for 2d talking head generation

Reference 28

Resolution
verified fuzzy
raw_fallback, observed 2026-08-16T00:21:13.687449Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

source=pdf_text observed=2026-08-16T00:21:12.180388Z digest=sha256:82b26b69d8047ff14450c335ef7e1066830ccca3a52db83e62b0d16b53be36a5

Observation 20795f95-83ad-41ad-8dfd-a348fa910f9b · outbound

This paper cites Disentangledandcontrollablefaceimagegeneration via 3d imitative-contrastive learning.

Avatar-Forever: Decoupled Parallel Training for High-Quality Real-Time Infinite Avatars Disentangledandcontrollablefaceimagegeneration via 3d imitative-contrastive learning

Reference 29

Resolution
verified fuzzy
raw_fallback, observed 2026-08-16T00:21:13.671952Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

source=pdf_text observed=2026-08-16T00:21:12.184975Z digest=sha256:2a9b1e3429c24cd90cdd404fb7b8b00d002c11361118a8ca5b5b728674e8b212

Observation 1e4d0bfc-b0b0-4729-a4e7-86fac01d7642 · outbound

This paper cites Capture, learning, and synthesis of 3d speaking styles.

Avatar-Forever: Decoupled Parallel Training for High-Quality Real-Time Infinite Avatars Capture, learning, and synthesis of 3d speaking styles

Reference 30

Resolution
unresolved
no resolver link, observed 2026-08-16T00:21:12.189441Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-16T00:21:12.189441Z digest=sha256:a818caaa327b2629e6360b19ad3d5230a68e97c2cc9cff61c396c72fb5d88424

Observation d2aaee70-5473-4139-8e8e-682d813f32b4 · outbound

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

Avatar-Forever: Decoupled Parallel Training for High-Quality Real-Time Infinite Avatars A lip sync expert is all you need for speech to lip generation in the wild

Reference 31

Resolution
verified fuzzy
raw_fallback, observed 2026-08-16T00:21:13.645011Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

source=pdf_text observed=2026-08-16T00:21:12.194118Z digest=sha256:7bef02856c210ade4c41f8f2594458270ac50a996c115bc80d8a82e113f4a7b5

Observation eb470aa7-d2f7-468e-8299-0bd0f347a809 · outbound

This paper cites Dreamavatar: Text-and-shape guided 3d human avatar generation via diffusion models.

Avatar-Forever: Decoupled Parallel Training for High-Quality Real-Time Infinite Avatars Dreamavatar: Text-and-shape guided 3d human avatar generation via diffusion models

Reference 32

Resolution
verified fuzzy
raw_fallback, observed 2026-08-16T00:21:13.627224Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

source=pdf_text observed=2026-08-16T00:21:12.198723Z digest=sha256:5fde9d9549997addff0b81d624758822f4ab0e8257077a8d1356a8a8bdfb6871

Observation 1b572d5c-2d21-4821-ba3f-d7cd1d486aca · outbound

This paper cites Latentavatar: Learninglatentexpressioncodeforexpressiveneuralheadavatar.

Avatar-Forever: Decoupled Parallel Training for High-Quality Real-Time Infinite Avatars Latentavatar: Learninglatentexpressioncodeforexpressiveneuralheadavatar

Reference 33

Resolution
verified fuzzy
raw_fallback, observed 2026-08-16T00:21:13.610490Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

source=pdf_text observed=2026-08-16T00:21:12.203513Z digest=sha256:9b1d8f506c0e4e4a773b50116b2eafffd6a26c2ef3eb16d37746c78f817ac46b

Observation 1f82974d-2bf1-4f9f-b5f5-360f2038fcbd · outbound

This paper cites Denoisingdiffusionprobabilisticmodels.Advancesinneuralinformation processing systems, 33:6840–6851, 2020.

Avatar-Forever: Decoupled Parallel Training for High-Quality Real-Time Infinite Avatars Denoisingdiffusionprobabilisticmodels.Advancesinneuralinformation processing systems, 33:6840–6851, 2020

Reference 34

Resolution
verified fuzzy
raw_fallback, observed 2026-08-16T00:21:13.593784Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

source=pdf_text observed=2026-08-16T00:21:12.208581Z digest=sha256:9ac56795430f05d3538de7e31cf6b5eabaf9cb4017bd782181387c5157c71637

Observation 0c0782c3-3df7-413e-8ce3-2a88e6fdced6 · outbound

This paper cites Flow Matching for Generative Modeling.

Avatar-Forever: Decoupled Parallel Training for High-Quality Real-Time Infinite Avatars Flow Matching for Generative Modeling

Reference 35

Resolution
unresolved
no resolver link, observed 2026-08-16T00:21:12.213693Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-16T00:21:12.213693Z digest=sha256:8d6b0c513ba3fde53698393486ed482ad7f3b97605483b6b1d677d978b222030

Observation 5138590f-5e18-45a2-a2dc-a08aebe60401 · outbound

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

Avatar-Forever: Decoupled Parallel Training for High-Quality Real-Time Infinite Avatars High-resolution image synthesis with latent diffusion models

Reference 36

Resolution
unresolved
no resolver link, observed 2026-08-16T00:21:12.218419Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-16T00:21:12.218419Z digest=sha256:49e204c16d3f475e8eb2ccd0d7f4c7082dfa1b5620876b867964fb52b5097ce8

Observation 8fd17803-5805-4049-bec2-d69e2882cad5 · outbound

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

Avatar-Forever: Decoupled Parallel Training for High-Quality Real-Time Infinite Avatars Difftalk: Crafting diffusion models for generalized audio-driven portraits animation

Reference 37

Resolution
verified fuzzy
raw_fallback, observed 2026-08-16T00:21:13.567513Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

source=pdf_text observed=2026-08-16T00:21:12.222740Z digest=sha256:601983012016a36ba974374590040ba86ab93e5780fb67f2f668b936ed0481e2

Observation 17c45409-c629-412d-be9b-6d1f7be09bc5 · outbound

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

Avatar-Forever: Decoupled Parallel Training for High-Quality Real-Time Infinite Avatars Hallo: Hierarchical Audio-Driven Visual Synthesis for Portrait Image Animation

Reference 38

Resolution
unresolved
no resolver link, observed 2026-08-16T00:21:12.227373Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-16T00:21:12.227373Z digest=sha256:916a43e06059fd970b884b00dda11a9a428b662f0bc49b491cd6c0f57a90ec98

Observation 1b2d76ed-79bb-4259-85b8-49a434c4dc5c · outbound

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

Avatar-Forever: Decoupled Parallel Training for High-Quality Real-Time Infinite Avatars AniPortrait: Audio-Driven Synthesis of Photorealistic Portrait Animation

Reference 39

Resolution
unresolved
no resolver link, observed 2026-08-16T00:21:12.231872Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-16T00:21:12.231872Z digest=sha256:a21e5352a1c2b1c7d9e1f728c559be8b236812d8a77efdfb35d652a3a9187ba4

Observation 9aca3269-b7df-4d30-9a35-692ee4781302 · outbound

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

Avatar-Forever: Decoupled Parallel Training for High-Quality Real-Time Infinite Avatars EchoMimic: Lifelike Audio-Driven Portrait Animations through Editable Landmark Conditions

Reference 40

Resolution
unresolved
no resolver link, observed 2026-08-16T00:21:12.236636Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-16T00:21:12.236636Z digest=sha256:a5208d01528ed91f79efb8c97122f8c6ad48517c84687ccdfe23de8a772dc26a

Observation 5b7568ba-9217-44e8-88be-f4c2c46d83ce · outbound

This paper cites Kling-Omni Technical Report.

Avatar-Forever: Decoupled Parallel Training for High-Quality Real-Time Infinite Avatars Kling-Omni Technical Report

Reference 41

Resolution
unresolved
no resolver link, observed 2026-08-16T00:21:12.241690Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-16T00:21:12.241690Z digest=sha256:0f9b2095396366c75eb4905765be15aefed2a6289bbe5bee8b27c7d3a7a795f6

Observation c7a1b3da-b90e-4b8b-bc53-12ef7590362d · outbound

This paper cites Video generation models as world simulators.

Avatar-Forever: Decoupled Parallel Training for High-Quality Real-Time Infinite Avatars Video generation models as world simulators

Reference 42

Resolution
verified fuzzy
raw_fallback, observed 2026-08-16T00:21:13.551489Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

source=pdf_text observed=2026-08-16T00:21:12.247704Z digest=sha256:1a787c46f1b09df1752cbec577dcae7c02a7c23a1d510bf248c99db291b54cc2

Observation a5f19dca-31fa-47f0-920b-43afb5f6df00 · outbound

This paper cites Freeman, and Taesung Park.

Avatar-Forever: Decoupled Parallel Training for High-Quality Real-Time Infinite Avatars Freeman, and Taesung Park

Reference 43

Resolution
verified fuzzy
raw_fallback, observed 2026-08-16T00:21:13.535426Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

source=pdf_text observed=2026-08-16T00:21:12.252293Z digest=sha256:1f86cb5fff00f01aeea9804fa646477339e2fe9957f399c705e36137284f2f05

Observation d4754a20-ae4e-4f10-99f0-9dd07f957558 · outbound

This paper cites Improved Distribution Matching Distillation for Fast Image Synthesis.

Avatar-Forever: Decoupled Parallel Training for High-Quality Real-Time Infinite Avatars Improved Distribution Matching Distillation for Fast Image Synthesis

Reference 44

Resolution
unresolved
no resolver link, observed 2026-08-16T00:21:12.257149Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-16T00:21:12.257149Z digest=sha256:6af646a73712048fb78a6a303890c71a4ba647032059174dbed7193cb4262363

Observation ed2c87ef-4e9a-44bb-b312-fd1dd2300fef · outbound

This paper cites Adversarial diffusion distillation.

Avatar-Forever: Decoupled Parallel Training for High-Quality Real-Time Infinite Avatars Adversarial diffusion distillation

Reference 45

Resolution
verified fuzzy
raw_fallback, observed 2026-08-16T00:21:13.519277Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

source=pdf_text observed=2026-08-16T00:21:12.262291Z digest=sha256:c5bd39e8bb28ee85fd6c631e28bb159ad636c1bce3ff516bce0bdb805cb7edb3

Observation 9317226e-16d5-4697-95ce-17057e92034b · outbound

This paper cites Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inference.

Avatar-Forever: Decoupled Parallel Training for High-Quality Real-Time Infinite Avatars Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inference

Reference 46

Resolution
unresolved
no resolver link, observed 2026-08-16T00:21:12.266993Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-16T00:21:12.266993Z digest=sha256:108b86ae6e001ed85d10b6bc4d42039700ed25105f4fbb911c7d512eda4299ab

Observation 27550522-1b35-4bc6-848e-61eaf90c7e27 · outbound

This paper cites Phased consistency models.

Avatar-Forever: Decoupled Parallel Training for High-Quality Real-Time Infinite Avatars Phased consistency models

Reference 47

Resolution
verified fuzzy
raw_fallback, observed 2026-08-16T00:21:13.502786Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

source=pdf_text observed=2026-08-16T00:21:12.272001Z digest=sha256:d49d9079c213b141fa34f78dfd820d447d7ab89e91e5c74657789a0dfc6f0c03

Observation 9a423730-100a-4d15-bef0-c949c03d51b8 · outbound

This paper cites Diversity-Preserved Distribution Matching Distillation for Fast Visual Synthesis.

Avatar-Forever: Decoupled Parallel Training for High-Quality Real-Time Infinite Avatars Diversity-Preserved Distribution Matching Distillation for Fast Visual Synthesis

Reference 48

Resolution
unresolved
no resolver link, observed 2026-08-16T00:21:12.276476Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-16T00:21:12.276476Z digest=sha256:e64982c039a47897ac056c186e22dfb31dcb667456c47debcd1601a631108323

Observation 3ac0be64-ce07-488f-b185-4f423d656b90 · outbound

This paper cites Self Forcing: Bridging the Train-Test Gap in Autoregressive Video Diffusion.

Avatar-Forever: Decoupled Parallel Training for High-Quality Real-Time Infinite Avatars Self Forcing: Bridging the Train-Test Gap in Autoregressive Video Diffusion

Reference 49

Resolution
unresolved
no resolver link, observed 2026-08-16T00:21:12.281657Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-16T00:21:12.281657Z digest=sha256:9377d46cc9ad04d36a2726f4c449c21ef8fc35996fab1250a586f64597f886f4

Observation 38fc14af-b7b2-403b-8769-03738a8c4d4a · outbound

This paper cites Long-Horizon Streaming Video Generation via Hybrid Attention with Decoupled Distillation.

Avatar-Forever: Decoupled Parallel Training for High-Quality Real-Time Infinite Avatars Long-Horizon Streaming Video Generation via Hybrid Attention with Decoupled Distillation

Reference 50

Resolution
unresolved
no resolver link, observed 2026-08-16T00:21:12.287157Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-16T00:21:12.287157Z digest=sha256:fc23f0f4c5b30c3679c4170ae6725634fd3dce1babf01205d4e07b8d7c8abd8c

Observation 125da127-580f-4c48-9cb4-a5602e9cfad1 · outbound

This paper cites Rolling Forcing: Autoregressive Long Video Diffusion in Real Time.

Avatar-Forever: Decoupled Parallel Training for High-Quality Real-Time Infinite Avatars Rolling Forcing: Autoregressive Long Video Diffusion in Real Time

Reference 51

Resolution
unresolved
no resolver link, observed 2026-08-16T00:21:12.292341Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-16T00:21:12.292341Z digest=sha256:720b22f0e906933aa6f1b0d38ff1efe353da96abf497d945db76c45263d8e831

Observation 0343a79b-8544-47a7-97d1-105b4e95489e · outbound

This paper cites OmniAvatar: Efficient Audio-Driven Avatar Video Generation with Adaptive Body Animation.

Avatar-Forever: Decoupled Parallel Training for High-Quality Real-Time Infinite Avatars OmniAvatar: Efficient Audio-Driven Avatar Video Generation with Adaptive Body Animation

Reference 52

Resolution
unresolved
no resolver link, observed 2026-08-16T00:21:12.297641Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-16T00:21:12.297641Z digest=sha256:22b979967b2751fc6540ac0e686960b2db0bc6f95926ab62243422b61a42e68d

Observation 08990fbb-5c71-46f1-bfd7-354b05afb300 · outbound

This paper cites HunyuanVideo-Avatar: High-Fidelity Audio-Driven Human Animation for Multiple Characters.

Avatar-Forever: Decoupled Parallel Training for High-Quality Real-Time Infinite Avatars HunyuanVideo-Avatar: High-Fidelity Audio-Driven Human Animation for Multiple Characters

Reference 53

Resolution
unresolved
no resolver link, observed 2026-08-16T00:21:12.302668Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-16T00:21:12.302668Z digest=sha256:e5f17ab4fb3bfd745a6a080f7671f4f90d52b22d19f4aaec662fa3a067b0d417

Observation 0152f6cf-3747-4f1c-b86b-5c67c7b6f478 · outbound

This paper cites Evaluating prerequisite qualities for learning end-to-end dialog systems, 2016.

Avatar-Forever: Decoupled Parallel Training for High-Quality Real-Time Infinite Avatars Evaluating prerequisite qualities for learning end-to-end dialog systems, 2016

Reference 54

Resolution
verified fuzzy
raw_fallback, observed 2026-08-16T00:21:13.486572Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

source=pdf_text observed=2026-08-16T00:21:12.307628Z digest=sha256:5ba17fe8297f35c21f29b4a02953c48cf0d3e7f38a9d359b906d7c940792dd9e

Observation efa924e2-d089-488b-a4d6-8348cfc93c8e · outbound

This paper cites an unresolved cited work.

Avatar-Forever: Decoupled Parallel Training for High-Quality Real-Time Infinite Avatars Unresolved cited work

Reference 55

Resolution
unresolved
raw_fallback, observed 2026-08-16T00:21:13.470285Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

source=pdf_text observed=2026-08-16T00:21:12.312343Z digest=sha256:e5b44ccf2f616a11e2ec20759d871e1e9921bb8c93f8bcb8f9abac587a4f3a80

Observation b8c68e1a-69f6-481a-8621-f2ff52c058ae · outbound

This paper cites Imagebind: One embedding space to bind them all.

Avatar-Forever: Decoupled Parallel Training for High-Quality Real-Time Infinite Avatars Imagebind: One embedding space to bind them all

Reference 56

Resolution
unresolved
no resolver link, observed 2026-08-16T00:21:12.316501Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-16T00:21:12.316501Z digest=sha256:861afb645178ed807d7916a533cfc874bcfe931df37a960f387c485ea0f82613

Observation 09082a70-3b25-4f36-8902-db0ba61286fb · outbound

This paper cites Large- scale contrastive language-audio pretraining with feature fusion and keyword-to-caption augmentation.

Avatar-Forever: Decoupled Parallel Training for High-Quality Real-Time Infinite Avatars Large- scale contrastive language-audio pretraining with feature fusion and keyword-to-caption augmentation

Reference 57

Resolution
verified fuzzy
raw_fallback, observed 2026-08-16T00:21:13.443117Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

source=pdf_text observed=2026-08-16T00:21:12.320678Z digest=sha256:efdaa4ffcbb854dc92769b61d90f8444661f38bc4243ab1b307567d73ac6e26f

Observation 3eebf83b-8724-4865-8117-9d00d1ef082d · outbound

This paper cites Unified Reward Model for Multimodal Understanding and Generation.

Avatar-Forever: Decoupled Parallel Training for High-Quality Real-Time Infinite Avatars Unified Reward Model for Multimodal Understanding and Generation

Reference 58

Resolution
unresolved
no resolver link, observed 2026-08-16T00:21:12.325127Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-16T00:21:12.325127Z digest=sha256:ccaf2fedc740d48ef0df8869c401b06dc55f5483b0d9851f0599335d0bea15b1

Observation cdb83860-187a-47b5-b690-9d7ac1c4cd0b · outbound

This paper cites Gemini 3.5 flash.

Avatar-Forever: Decoupled Parallel Training for High-Quality Real-Time Infinite Avatars Gemini 3.5 flash

Reference 59

Resolution
verified fuzzy
raw_fallback, observed 2026-08-16T00:21:13.427426Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

source=pdf_text observed=2026-08-16T00:21:12.329523Z digest=sha256:0ad2b5e0d6bf0a24d97b93829bff68db9799841e1351449bcfcd62e4bc278c22

Observation 852ac723-d1cc-4591-9d32-879c5d6c9596 · outbound

This paper cites Lora: Low-rank adaptation of large language models.Iclr, 1(2):3, 2022.

Avatar-Forever: Decoupled Parallel Training for High-Quality Real-Time Infinite Avatars Lora: Low-rank adaptation of large language models.Iclr, 1(2):3, 2022

Reference 60

Resolution
verified fuzzy
raw_fallback, observed 2026-08-16T00:21:13.411140Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

source=pdf_text observed=2026-08-16T00:21:12.333634Z digest=sha256:cfe5f1ea701227ef1b6597e5019102495a09bf7a3d3b3fcd6451680215d201b5

Observation 6ec32269-823b-431c-ab8e-67288dc46b4e · outbound

This paper cites Talkvid: A large-scale diversified dataset for audio-driven talking head synthesis.

Avatar-Forever: Decoupled Parallel Training for High-Quality Real-Time Infinite Avatars Talkvid: A large-scale diversified dataset for audio-driven talking head synthesis

Reference 61

Resolution
verified fuzzy
raw_fallback, observed 2026-08-16T00:21:13.394868Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

source=pdf_text observed=2026-08-16T00:21:12.338605Z digest=sha256:b55cef02012df0595b40d4578df19321e631a4d4081decd30c9c96884c24c7ea

Observation b4d2fa8f-271a-4e50-ae96-76768cf8b6a7 · outbound

This paper cites Echomimicv2: Towards striking, simplified, and semi-body human animation.arXiv preprint arXiv:2411.10061, 2024.

Avatar-Forever: Decoupled Parallel Training for High-Quality Real-Time Infinite Avatars Echomimicv2: Towards striking, simplified, and semi-body human animation.arXiv preprint arXiv:2411.10061, 2024

Reference 62

Resolution
unresolved
no resolver link, observed 2026-08-16T00:21:12.343399Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-16T00:21:12.343399Z digest=sha256:12a406cd1b7474daf8298f6daac3916a8a69b68cdf6ff0ac5f93b0e7f1d20c01

Observation e136beb3-fdc4-49eb-bcd6-a4b75e9685c3 · outbound

This paper cites audio_visual_consistency.

Avatar-Forever: Decoupled Parallel Training for High-Quality Real-Time Infinite Avatars audio_visual_consistency

Reference 63

Resolution
verified fuzzy
raw_fallback, observed 2026-08-16T00:21:13.377783Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

source=pdf_text observed=2026-08-16T00:21:12.348163Z digest=sha256:c51df5b13e53b4061b3a145343dadc1031d401f0bb510a4a21b69e402ed3eebc

Pith citing papers

No inbound Pith citation observations are available.