Unified Factored Representations Resist Catastrophic Forgetting
cs.LG, cs.AI
Submitted: 2026-11-07
Updated: 2026-11-07
Terminology
Sources
- Compositionality Emerges in a Narrow Depth-Connectivity Regime: Architecture Constraints and Solution Manifolds
- The Llama 3 Herd of Models
- Gaussian Error Linear Units (GELUs)
- Questioning Representational Optimism in Deep Learning: The Fractured Entangled Representation Hypothesis
- 2 OLMo 2 Furious
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