HamiFormer: Dual-Expert Diffusion Fields with Affine Symplectic Maps

arXiv:2609.32838 · cs.LG · Submitted 2026-09-26 · Read on arXiv

cs.LG

Submitted: 2026-09-26

Updated: 2026-09-26

Code: https://github.com/starx237/HamiFormer

Project page: https://hamiformer.github.io

Terminology

• Accuracy — 30× in this paper · explained in 1 episode
• Transformer — 19× in this paper · explained in 2 episodes
• Consistency — 16× in this paper · explained in 3 episodes
• Regret — 11× in this paper · explained in 3 episodes
• Ablation — 8× in this paper · explained in 1 episode
• Calibration — 4× in this paper · explained in 7 episodes
• Diffusion Model — 4× in this paper · explained in 8 episodes
• Aggregation — 3× in this paper · explained in 1 episode
• Denoising Hamiltonian Network — 2× in this paper
• Diffusion Models — 2× in this paper · explained in 6 episodes
• Flow Matching — 2× in this paper · explained in 8 episodes
• Parallel Local Affine Scan — 2× in this paper
• Rectified Flow — 2× in this paper · explained in 3 episodes
• Regularization — 2× in this paper · explained in 3 episodes
• Adam — 1× in this paper · explained in 2 episodes
• Alignment — 1× in this paper · explained in 1 episode
• Allocator — 1× in this paper · explained in 1 episode
• Distribution Shift — 1× in this paper · explained in 6 episodes
• Dynamical regimes — 1× in this paper · explained in 2 episodes
• Error Decomposition — 1× in this paper · explained in 3 episodes
• Generative Modeling — 1× in this paper · explained in 3 episodes
• Hamiltonian Learning — 1× in this paper · explained in 2 episodes
• Iterative Refinement — 1× in this paper · explained in 3 episodes
• Provenance — 1× in this paper · explained in 4 episodes
• Self-consistency — 1× in this paper · explained in 2 episodes
• Verification — 1× in this paper · explained in 2 episodes

Sources

• PhysiFormer: Learning to Simulate Mechanics in World Space
• Port--Hamiltonian Diffusion Models: A Control-Theoretic Perspective on Generative Modeling
• Dissipative Hamiltonian Neural Networks: Learning Dissipative and Conservative Dynamics Separately

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