TokDrift: When LLM Speaks in Subwords but Code Speaks in Grammar Paper • 2510.14972 • Published Oct 16 • 34
Interactive Training: Feedback-Driven Neural Network Optimization Paper • 2510.02297 • Published Oct 2 • 42
Why Can't Transformers Learn Multiplication? Reverse-Engineering Reveals Long-Range Dependency Pitfalls Paper • 2510.00184 • Published Sep 30 • 16
NeuralOS: Towards Simulating Operating Systems via Neural Generative Models Paper • 2507.08800 • Published Jul 11 • 80
