IdealCache: Rethinking Cache Scheduling in Diffusion Transformers via Ideal Trajectories
cs.AI
Submitted: 2026-11-07
Updated: 2026-11-07
Terminology
Sources
- DiCache: Let Diffusion Model Determine Its Own Cache
- $\Delta$-DiT: A Training-Free Acceleration Method Tailored for Diffusion Transformers
- Chain-of-Trajectories: Unlocking the Intrinsic Generative Optimality of Diffusion Models via Graph-Theoretic Planning
- Adaptive Caching for Faster Video Generation with Diffusion Transformers
- HunyuanVideo: A Systematic Framework For Large Video Generative Models
- Timestep Embedding Tells: It's Time to Cache for Video Diffusion Model
- Step1X-Edit: A Practical Framework for General Image Editing
- DPM-Solver++: Fast Solver for Guided Sampling of Diffusion Probabilistic Models
- Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inference
- FORA: Fast-Forward Caching in Diffusion Transformer Acceleration
- Qwen-Image Technical Report
- Real-Time Video Generation with Pyramid Attention Broadcast
- Let Features Decide Their Own Solvers: Hybrid Feature Caching for Diffusion Transformers
- Rethinking Token-wise Feature Caching: Accelerating Diffusion Transformers with Dual Feature Caching
Related papers
- Multi-Objective Structured Pruning of LLMs for Latency and Model Size Optimization
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Embeddings for Preferences, Not Semantics
- Can We Trust Item Response Theory for AI Evaluation?
- Diagnosing Task Insensitivity in Language Agents