Visual-SDPO distills visual feedback from rendered code outputs into a student policy via grounded credit weighting and GRPO, yielding over 10-point gains on chart/UI/slide benchmarks.
Torch.fx: Practical program capture and transformation for deep learning in python
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
representative citing papers
ExecuTorch is a unified PyTorch-native deployment framework that enables seamless on-device execution of AI models across heterogeneous hardware while preserving original PyTorch semantics.
Flint generates compiler-derived workload graphs that support cluster-free design space exploration for distributed machine learning systems.
GraphMend automatically rewrites PyTorch code, converting dynamic branches into tensor operations and deferring prints, to reduce PyTorch 2 graph breaks, with reported speedups that differ between the abstract and the body.
citing papers explorer
-
Self-Distillation Policy Optimization via Visual Feedback: Bridging Code and Visual Artifacts
Visual-SDPO distills visual feedback from rendered code outputs into a student policy via grounded credit weighting and GRPO, yielding over 10-point gains on chart/UI/slide benchmarks.
-
ExecuTorch -- A Unified PyTorch Solution to Run AI Models On-Device
ExecuTorch is a unified PyTorch-native deployment framework that enables seamless on-device execution of AI models across heterogeneous hardware while preserving original PyTorch semantics.
-
Flint: Compiler Enabled Cluster-Free Design Space Exploration for Distributed ML
Flint generates compiler-derived workload graphs that support cluster-free design space exploration for distributed machine learning systems.
-
GraphMend: Code Transformations for Fixing Graph Breaks in PyTorch 2
GraphMend automatically rewrites PyTorch code, converting dynamic branches into tensor operations and deferring prints, to reduce PyTorch 2 graph breaks, with reported speedups that differ between the abstract and the body.