Deflating the Hessian: Rank-4 W4A4 Quantization for Multimodal Diffusion Transformers

arXiv:2610.11315 · cs.LG, cs.CV, math.OC · Submitted 2026-10-08 · Read on arXiv

cs.LG, cs.CV, math.OC

Submitted: 2026-10-08

Updated: 2026-10-08

Terminology

• Quantization — 67× in this paper · explained in 12 episodes
• Calibration — 41× in this paper · explained in 7 episodes
• Transformer — 23× in this paper · explained in 2 episodes
• Fidelity — 17× in this paper · explained in 2 episodes
• Diffusion Model — 9× in this paper · explained in 8 episodes
• Diffusion Models — 9× in this paper · explained in 6 episodes
• Perplexity — 9× in this paper · explained in 3 episodes
• Accuracy — 8× in this paper · explained in 1 episode
• Ablation — 6× in this paper · explained in 1 episode
• In International Conference on Learning Representations — 5× in this paper
• Adaptation — 4× in this paper · explained in 1 episode
• Benchmark — 3× in this paper · explained in 2 episodes
• Regularization — 3× in this paper · explained in 3 episodes
• Unified Framework — 3× in this paper · explained in 5 episodes
• Ablation Studies — 2× in this paper · explained in 1 episode
• Alignment — 2× in this paper · explained in 1 episode
• Error Decomposition — 2× in this paper · explained in 3 episodes
• International Conference on Computer Vision — 2× in this paper
• Allocator — 1× in this paper · explained in 1 episode
• Core — 1× in this paper · explained in 2 episodes
• Downstream Tasks — 1× in this paper · explained in 2 episodes
• Elias — 1× in this paper · explained in 2 episodes
• Non-stationarity — 1× in this paper · explained in 2 episodes
• Reconstruction Error — 1× in this paper · explained in 2 episodes
• Semantic Alignment — 1× in this paper · explained in 3 episodes
• Trace — 1× in this paper · explained in 2 episodes

Sources

• Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge
• OrbitQuant: Data-Agnostic Quantization for Image and Video Diffusion Transformers
• Playground v2.5: Three Insights towards Enhancing Aesthetic Quality in Text-to-Image Generation
• Low-Rank Correction for Quantized LLMs
• DiRotQ: Rotation-Aware Quantization for 4-bit Diffusion Transformers
• Qwen3 Technical Report

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