CAFIN: CUDA-accelerated Adaptive Fisher Information Matrix Network Optimization via GPU-Native Kernel Fusion
cs.LG, cs.AI
Submitted: 2026-11-10
Updated: 2026-11-10
Code: https://github.com/NVIDIA/apex
Terminology
Sources
- Rewarded Region Replay (R3) for Policy Learning with Discrete Action Space
- Sophia: A Scalable Stochastic Second-order Optimizer for Language Model Pre-training
- FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis