VIAR embeds implicit equilibrium layers in visual autoregressive models to achieve ImageNet FID 2.16 with 38.4% of VAR parameters and controllable inference compute.
Advances in neural information processing systems , volume=
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
years
2026 4representative citing papers
Denoising Recursion Models train multi-step noise reversal in looped transformers and outperform the prior Tiny Recursion Model on ARC-AGI.
Neural Control introduces adjoint-based differentiation through implicit equilibrium constraints to enable memory-efficient gradient computation and robust receding-horizon MPC for multi-stable deformable object manipulation, outperforming gradient-free baselines in simulation and hardware.
citing papers explorer
-
Visual Implicit Autoregressive Modeling
VIAR embeds implicit equilibrium layers in visual autoregressive models to achieve ImageNet FID 2.16 with 38.4% of VAR parameters and controllable inference compute.
-
One Step Forward and K Steps Back: Better Reasoning with Denoising Recursion Models
Denoising Recursion Models train multi-step noise reversal in looped transformers and outperform the prior Tiny Recursion Model on ARC-AGI.
-
Neural Control: Adjoint Learning Through Equilibrium Constraints
Neural Control introduces adjoint-based differentiation through implicit equilibrium constraints to enable memory-efficient gradient computation and robust receding-horizon MPC for multi-stable deformable object manipulation, outperforming gradient-free baselines in simulation and hardware.
- Simply Stabilizing the Loop via Fully Looped Transformer