Dmitry Ignatov

Architecture-specific learning rate schedulers can boost model accuracy by over 6% compared to basic decay strategies, revealing a critical factor in neural network training success.

Unlocking over 14,000 unique neural architectures, LEMUR 2 sets a new standard for cross-domain evaluation and deployment in AI design.

Source-guided neural network modifications can boost model accuracy by over 56% compared to traditional methods, demonstrating the power of LLM adaptation in model improvement.

LLM-based neural architecture search isn't just trial and error: this paper proves it converges, and derives a surprisingly simple formula to check if your proxy metrics are trustworthy.

LLMs can now generate neural architectures with 75% less code and higher accuracy by learning to write code "diffs" instead of building from scratch.

Forget cloud TPUs: this NAS method coaxes surprisingly good CNN architectures out of commodity GPUs using LLMs and a clever feedback loop.

LLMs can evolve into autonomous neural architecture designers, learning to generate novel and high-performing architectures by internalizing execution feedback, even surpassing their initial training data.