Where and When to Force: Routed Forcing for Streaming Avatars

arXiv:2609.30963 · cs.CV · Submitted 2026-09-25 · Read on arXiv

cs.CV

Submitted: 2026-09-25

Updated: 2026-09-25

Terminology

• Distillation — 34× in this paper · explained in 2 episodes
• Accuracy — 10× in this paper · explained in 1 episode
• Diffusion Model — 10× in this paper · explained in 8 episodes
• Ablation — 7× in this paper · explained in 1 episode
• Diffusion Models — 7× in this paper · explained in 6 episodes
• Distribution Matching — 7× in this paper · explained in 2 episodes
• Distribution Matching Distillation — 7× in this paper
• Consistency — 5× in this paper · explained in 3 episodes
• Data-Forcing Distillation — 5× in this paper
• Transformer — 4× in this paper · explained in 2 episodes
• ACM Transactions on Graphics — 3× in this paper
• Ablation study — 2× in this paper · explained in 1 episode
• Adam — 2× in this paper · explained in 2 episodes
• Alignment — 2× in this paper · explained in 1 episode
• Fidelity — 2× in this paper · explained in 2 episodes
• Generative Model — 2× in this paper · explained in 2 episodes
• Generative Models — 2× in this paper · explained in 3 episodes
• Mode Collapse — 2× in this paper · explained in 2 episodes
• Ablation Studies — 1× in this paper · explained in 1 episode
• Consistency Distillation — 1× in this paper · explained in 2 episodes
• Fine-Tuning — 1× in this paper · explained in 5 episodes
• Gradient Flow — 1× in this paper · explained in 2 episodes
• Hallucination — 1× in this paper · explained in 4 episodes
• Nash Equilibrium — 1× in this paper · explained in 2 episodes
• On-Policy Distillation — 1× in this paper · explained in 3 episodes
• Optical Flow — 1× in this paper · explained in 2 episodes
• Reconstruction Error — 1× in this paper · explained in 2 episodes
• Score Function — 1× in this paper · explained in 4 episodes
• Steering — 1× in this paper · explained in 2 episodes

Sources

• Rethinking Atrous Convolution for Semantic Image Segmentation
• Data-Forcing Distillation: Restoring Diversity and Fidelity in Few-Step Video Generation
• LiveTalk: Real-Time Multimodal Interactive Video Diffusion via Improved On-Policy Distillation
• Lip Forcing: Few-Step Autoregressive Diffusion for Real-time Lip Synchronization
• OmniAvatar: Efficient Audio-Driven Avatar Video Generation with Adaptive Body Animation
• Reward Forcing: Efficient Streaming Video Generation with Rewarded Distribution Matching Distillation
• Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inference
• Generation Enhances Understanding in Unified Multimodal Models via Multi-Representation Generation
• ConsistentRFT: Reducing Visual Hallucinations in Flow-based Reinforcement Fine-Tuning
• When Policy Entropy Constraint Fails: Preserving Diversity in Flow-based RLHF via Perceptual Entropy
• Wan: Open and Advanced Large-Scale Video Generative Models
• Towards Accurate Generative Models of Video: A New Metric & Challenges
• FantasyTalking: Realistic Talking Portrait Generation via Coherent Motion Synthesis
• AniPortrait: Audio-Driven Synthesis of Photorealistic Portrait Animation
• Diversity-Preserved Distribution Matching Distillation for Fast Visual Synthesis
• Knot Forcing: Taming Autoregressive Video Diffusion Models for Real-time Infinite Interactive Portrait Animation
• CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer
• Improved Distribution Matching Distillation for Fast Image Synthesis
• SpeakerVid-5M: A Large-Scale High-Quality Dataset for Audio-Visual Dyadic Interactive Human Generation

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models