Records found: 5
ByteDance researchers introduce ProtoReasoning, a new framework leveraging logic-based prototypes to significantly improve reasoning and planning abilities in large language models across various domains.
New research reveals that generalization in flow matching models emerges from the neural network's approximation of velocity fields during early trajectories, challenging the belief that stochasticity drives this process.
Researchers reveal a new method using latent vector fields to understand how neural autoencoders balance memorization and generalization, enhancing interpretability without modifying models.
New research reveals how integrating in-context learning insights into fine-tuning datasets significantly improves language model generalization on complex reasoning tasks.
Researchers reveal that training large language models with just one example using 1-shot reinforcement learning significantly enhances their math reasoning abilities, matching results from large datasets.