·
DataBubble
  • Home
  • Models
  • News
  • Compare
  • Boards
  • Pricing
  • About
  • Newsletter
  • Methodology
  • Contact
Latest
Instagram’s Adam Mosseri: If you don’t like AI, ‘then you shouldn’t have it in your feed’3h◆Would you host part of an AI data center in your home?4h◆How Deutsche Telekom is rewiring telecommunications with AI10h◆Svarna: An Open Corpus Workbench for Modern Greek13h◆When LLMs Agree, Are They Right? Auditing Self-Consistency and Cross-Model Agreement as Confidence Signals13h◆PLURAL: A Global Dataset for Value Alignment13h◆BiSCo-LLM: Lookup-Free Binary Spherical Coding for Extreme Low-Bit Large Language Model Compression13h◆Infinity-Parser2 Technical Report13h◆Agentic Neural Architecture Search13h◆Leveraging Color Naming for Image Enhancement13h◆($\theta_l, \theta_u$)-Parametric Multi-Task Optimization: Joint Search in Solution and Infinite Task Spaces13h◆MetaHGNIE: Meta-Path Induced Hypergraph Contrastive Learning in Heterogeneous Knowledge Graphs13h◆Generalization Theory for Through-the-Wall Radar Human Activity Recognition13h◆ProsMAE: Multi-Source MAE Pretraining for ISUP Grade Classification13h◆Improving Engine Sound Analysis in Hot-Test Environments via a RAB-U-Net (Residual Attention Block U-Net) Noise Removal Method13h◆Validating LLMs in social science: Epistemic threats and emerging norms13h◆Partial Causal Structure Learning for Valid Selective Conformal Inference under Interventions13h◆Tessera: Unlocking Heterogeneous GPUs through Kernel-Granularity Disaggregation13h◆Kime-Representation Formulations of Three Open Problems in the Foundations of Classical Mechanics: Uncertainty, Invariant Entropy, and Directional Degrees of Freedom13h◆Idiobionics: The Unification of Privacy and Intelligent Robotic Prostheses13h◆Instagram’s Adam Mosseri: If you don’t like AI, ‘then you shouldn’t have it in your feed’3h◆Would you host part of an AI data center in your home?4h◆How Deutsche Telekom is rewiring telecommunications with AI10h◆Svarna: An Open Corpus Workbench for Modern Greek13h◆When LLMs Agree, Are They Right? Auditing Self-Consistency and Cross-Model Agreement as Confidence Signals13h◆PLURAL: A Global Dataset for Value Alignment13h◆BiSCo-LLM: Lookup-Free Binary Spherical Coding for Extreme Low-Bit Large Language Model Compression13h◆Infinity-Parser2 Technical Report13h◆Agentic Neural Architecture Search13h◆Leveraging Color Naming for Image Enhancement13h◆($\theta_l, \theta_u$)-Parametric Multi-Task Optimization: Joint Search in Solution and Infinite Task Spaces13h◆MetaHGNIE: Meta-Path Induced Hypergraph Contrastive Learning in Heterogeneous Knowledge Graphs13h◆Generalization Theory for Through-the-Wall Radar Human Activity Recognition13h◆ProsMAE: Multi-Source MAE Pretraining for ISUP Grade Classification13h◆Improving Engine Sound Analysis in Hot-Test Environments via a RAB-U-Net (Residual Attention Block U-Net) Noise Removal Method13h◆Validating LLMs in social science: Epistemic threats and emerging norms13h◆Partial Causal Structure Learning for Valid Selective Conformal Inference under Interventions13h◆Tessera: Unlocking Heterogeneous GPUs through Kernel-Granularity Disaggregation13h◆Kime-Representation Formulations of Three Open Problems in the Foundations of Classical Mechanics: Uncertainty, Invariant Entropy, and Directional Degrees of Freedom13h◆Idiobionics: The Unification of Privacy and Intelligent Robotic Prostheses13h◆
News/KSDiff: Keyframe-Augmented Speech-Aware Dual-Path Diffusion for Facial Animation
arxiv
PublishedApril 14, 2026 at 4:00 AM

KSDiff: Keyframe-Augmented Speech-Aware Dual-Path Diffusion for Facial Animation

Source
arxiv.orgfull article ↗
Read on arxiv→
Publisher summary· verbatim

arXiv:2509.20128v2 Announce Type: replace-cross Abstract: Audio-driven facial animation has made significant progress in multimedia applications, with diffusion models showing strong potential for talking-face synthesis. However, most existing works treat speech features as a monolithic representati

Stay posted· Newsletter

A 5-min weekly brief — top movers, price watch, story of the week.

// no spam · unsubscribe one-click · free forever

Discussion
Source
↗
arxiv
Read original ↗All from arxiv →

No replies yet. Be first.

Source
↗
arxiv
Read original ↗All from arxiv →

Related coverage

More from ARXIV
arxivSvarna: An Open Corpus Workbench for Modern Greek13harxivWhen LLMs Agree, Are They Right? Auditing Self-Consistency and Cross-Model Agreement as Confidence Signals13harxivPLURAL: A Global Dataset for Value Alignment13harxivBiSCo-LLM: Lookup-Free Binary Spherical Coding for Extreme Low-Bit Large Language Model Compression13h
The Bubble Brief
WEEKLY

Read AI insights every Tuesday — top movers, new releases, story of the week.

// no spam · unsubscribe one-click · free forever

Originally published on arxiv ↗
HomeModelsNews