Accuracy is not compatibility: two Evo 2 checkpoints hinge on one FP8 matrix multiplication
cs.LG
Submitted: 2026-10-29
Updated: 2026-10-29
Comments: 18 pages, 3 figures, 1 table. Data: https://doi.org/10.5281/zenodo.23740390 ; code: https://github.com/astding/mmaemu
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
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