ZARZA We are Zarza, the prestigious firm behind major projects in information technology.

UQ - Assessing Language Models on Unsolved Questions

Mechanical Dreams

04/09/2025 13 min Temporada 1 Episodio 75

UQ - Assessing Language Models on Unsolved Questions

Listen "UQ - Assessing Language Models on Unsolved Questions"

Descargar episodio

More episodes of the podcast Mechanical Dreams

Challenges and Research Directions for Large Language Model Inference Hardware 17/01/2026

Extending the Context of Pretrained LLMs by Dropping Their Positional Embeddings 16/01/2026

The Quantization Model of Neural Scaling 15/01/2026

EAGLE-3 14/01/2026

Engram Paper 12/01/2026

From Entropy to Epiplexity- Rethinking Information for Computationally Bounded Intelligence 09/01/2026

Completed Hyperparameter Transfer across Modules, Width, Depth, Batch and Duration 08/01/2026

NorMuon- Making Muon more efficient and scalable 07/01/2026

Dion- Distributed Orthonormalized Updates 06/01/2026

How Learning Rate Decay Wastes Your Best Data in Curriculum-Based LLM Pretraining 05/01/2026

Ver todos los episodios