On the Resilience of Text-to-Video Diffusion Models to Hardware Faults
cs.LG
Submitted: 2026-08-30
Updated: 2026-08-30
Comments: Accepted to ICML 2026 Workshop on From Frames to Stories (F2S)
Code: https://github.com/ztcoalson/T2V-Resilience
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Animate-A-Story: Storytelling with Retrieval-Augmented Video Generation
- PrisonBreak: Jailbreaking Large Language Models with at Most Twenty-Five Targeted Bit-flips
- A Study of BFLOAT16 for Deep Learning Training
- Global Clipper: Enhancing Safety and Reliability of Transformer-based Object Detection Models
- Open-Sora: Democratizing Efficient Video Production for All
- Understanding the Landscape of Ampere GPU Memory Errors
- Wan: Open and Advanced Large-Scale Video Generative Models
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks