Hallo-Live achieves 20.38 FPS real-time text-to-audio-video avatar generation with 0.94s latency using asynchronous dual-stream diffusion and HP-DMD preference distillation, matching teacher model quality at 16x higher throughput.
Canonical reference
Title resolution pending
Canonical reference. 80% of citing Pith papers cite this work as background.
15
Pith papers citing it
Background
80% of classified citations
citation-role summary
background 4
method 1
citation-polarity summary
years
2026 15representative citing papers
FlowAnchor stabilizes editing signals in flow-based inversion-free video editing via spatial-aware attention refinement and adaptive magnitude modulation for improved faithfulness and temporal coherence.
Multi-head Gaussian kernels inject temporal scale discrepancy as inductive bias to enable full-duplex talking-listening avatar generation, supported by a new decoupled VoxHear dataset and claimed SOTA naturalness.
Task-aware localization via attention cues and feature centroids from source/target streams in IIE models improves non-edit consistency while preserving instruction following.
OFlow unifies temporal foresight and object-aware reasoning inside a shared latent space via flow matching to improve VLA robustness in robotic manipulation under distribution shifts.
Long-CODE isolates long-context video evaluation with a new benchmark dataset and shot-dynamics metric that correlates better with human judgments on narrative richness and global consistency than short-video metrics.
VersaVogue unifies garment generation and virtual dressing via trait-routing attention with mixture-of-experts and an automated multi-perspective preference optimization pipeline that uses DPO without human labels.
InsTraj generates realistic, instruction-faithful GPS trajectories by using an LLM to parse natural-language travel intent and a multimodal diffusion transformer to produce the paths.
SRast is a generalist framework using self-supervised decoupling of gene and spatial representations plus flow matching for physically consistent super-resolution of spatial transcriptomics data with strong zero-shot generalization.
A diffusion model with dynamic modality gating and cross-modal mutual learning restores missing features in VLMs bi-directionally while preserving the original model's generalization.
SubFlow restores full mode coverage in one-step flow matching by conditioning on sub-modes from semantic clustering, yielding higher diversity on ImageNet-256 while preserving FID.
PASA uses curvature-aware dynamic budgeting, grouped approximations, and stochastic attention routing to accelerate video diffusion transformers while eliminating temporal flickering from sparse patterns.
LaDA-Band generates complete vocal-aligned instrumental accompaniments with discrete masked diffusion, claiming simultaneous gains in audio fidelity, long-range coherence, and orchestration quality.
citing papers explorer
-
Hallo-Live: Real-Time Streaming Joint Audio-Video Avatar Generation with Asynchronous Dual-Stream and Human-Centric Preference Distillation
Hallo-Live achieves 20.38 FPS real-time text-to-audio-video avatar generation with 0.94s latency using asynchronous dual-stream diffusion and HP-DMD preference distillation, matching teacher model quality at 16x higher throughput.
-
FlowAnchor: Stabilizing the Editing Signal for Inversion-Free Video Editing
FlowAnchor stabilizes editing signals in flow-based inversion-free video editing via spatial-aware attention refinement and adaptive magnitude modulation for improved faithfulness and temporal coherence.
-
Beyond Monologue: Interactive Talking-Listening Avatar Generation with Conversational Audio Context-Aware Kernels
Multi-head Gaussian kernels inject temporal scale discrepancy as inductive bias to enable full-duplex talking-listening avatar generation, supported by a new decoupled VoxHear dataset and claimed SOTA naturalness.
-
Rethinking Where to Edit: Task-Aware Localization for Instruction-Based Image Editing
Task-aware localization via attention cues and feature centroids from source/target streams in IIE models improves non-edit consistency while preserving instruction following.
-
OFlow: Injecting Object-Aware Temporal Flow Matching for Robust Robotic Manipulation
OFlow unifies temporal foresight and object-aware reasoning inside a shared latent space via flow matching to improve VLA robustness in robotic manipulation under distribution shifts.
-
Long-CODE: Isolating Pure Long-Context as an Orthogonal Dimension in Video Evaluation
Long-CODE isolates long-context video evaluation with a new benchmark dataset and shot-dynamics metric that correlates better with human judgments on narrative richness and global consistency than short-video metrics.
-
VersaVogue: Visual Expert Orchestration and Preference Alignment for Unified Fashion Synthesis
VersaVogue unifies garment generation and virtual dressing via trait-routing attention with mixture-of-experts and an automated multi-perspective preference optimization pipeline that uses DPO without human labels.
-
InsTraj: Instructing Diffusion Models with Travel Intentions to Generate Real-world Trajectories
InsTraj generates realistic, instruction-faithful GPS trajectories by using an LLM to parse natural-language travel intent and a multimodal diffusion transformer to produce the paths.
-
Towards Universal Spatial Transcriptomics Super-Resolution: A Generalist Physically Consistent Flow Matching Framework
SRast is a generalist framework using self-supervised decoupling of gene and spatial representations plus flow matching for physically consistent super-resolution of spatial transcriptomics data with strong zero-shot generalization.
-
Enhancing Foundation VLM Robustness to Missing Modality: Scalable Diffusion for Bi-directional Feature Restoration
A diffusion model with dynamic modality gating and cross-modal mutual learning restores missing features in VLMs bi-directionally while preserving the original model's generalization.
-
SubFlow: Sub-mode Conditioned Flow Matching for Diverse One-Step Generation
SubFlow restores full mode coverage in one-step flow matching by conditioning on sub-modes from semantic clustering, yielding higher diversity on ImageNet-256 while preserving FID.
-
Ride the Wave: Precision-Allocated Sparse Attention for Smooth Video Generation
PASA uses curvature-aware dynamic budgeting, grouped approximations, and stochastic attention routing to accelerate video diffusion transformers while eliminating temporal flickering from sparse patterns.
-
LaDA-Band: Language Diffusion Models for Vocal-to-Accompaniment Generation
LaDA-Band generates complete vocal-aligned instrumental accompaniments with discrete masked diffusion, claiming simultaneous gains in audio fidelity, long-range coherence, and orchestration quality.
- Not All Frames Deserve Full Computation: Accelerating Autoregressive Video Generation via Selective Computation and Predictive Extrapolation
- SHARP: Spectrum-aware Highly-dynamic Adaptation for Resolution Promotion in Remote Sensing Synthesis