conftrace_

attention kernel

2 papers

Explore in graph

Co-occurring keywords · papers mentioning both

gradient descent dynamics (1) cuda kernel (1) intermediate representation (1) large language model (1) weight initialization (1) convergence guarantee (1) optimization theory (1) gradient descent (1) loss landscape (1) neural network optimization (1)

Papers

CuBridge: An LLM-Based Framework for Understanding and Reconstructing High-Performance Attention Kernels ACL 2026 Unraveling the Gradient Descent Dynamics of Transformers NeurIPS 2024