TAPES: Task-Aligned Joint Predictive Pretraining for Transaction Event Sequences
cs.LG, cs.AI
Submitted: 2026-11-03
Updated: 2026-11-03
Terminology
Sources
- Layer Normalization
- Gaussian Error Linear Units (GELUs)
- When Losses Align: Gradient-Based Composite Loss Weighting for Efficient Pretraining
- MLEM: Generative and Contrastive Learning as Distinct Modalities for Event Sequences
- GLU Variants Improve Transformer
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