DIET: Deletion-response Expert Trimming for Video Diffusion Transformers
cs.AI
Submitted: 2026-09-29
Updated: 2026-09-29
Project page: https://zjc301.top/Video-DiT-MoE-Pruning-Page
Terminology
Sources
- Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets
- LExI: Layer-Adaptive Active Experts for Efficient MoE Model Inference
- DeepSeek-V3 Technical Report
- Scaling Diffusion Transformers to 16 Billion Parameters
- REAM: Merging Improves Pruning of Experts in LLMs
- Mixtral of Experts
- EvoESAP: Non-Uniform Expert Pruning for Sparse MoE
- How to Score Experts for One-Shot MoE Expert Pruning: A Unified Formulation and Selection Principle
- Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence
- Seedance 2.0: Advancing Video Generation for World Complexity
- Beyond Geometric Complementarity: Coherent Overlap in Sparse Mixture-of-Experts Routing
- Higher-order pruning of experts in mixture-of-experts language models
- MoE-Pruner: Pruning Mixture-of-Experts Large Language Model using the Hints from Its Router
- MoE Pathfinder: Trajectory-driven Expert Pruning
- Generic Expert Coverage for Pruning SparseMixture-of-Experts Language Models
- SHAPE: Coalition-Aware Expert Pruning for Sparse Mixture-of-Experts LLMs
Related papers
- 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
- Agents' Last Exam
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems