Loading...
AI Dashboard
A simpler, high-signal dashboard focused on recent releases, important product updates, major industry moves, and a limited set of research that matters in practice.
2,249
Total tracked
458
Last 24h
1,319
Last 3 days
Feed Controls
Filtered Feed
A simplified feed view based on the current lens and filters.
Abstract: Detecting when a language model is wrong without ground truth labels is a fundamental challenge for safe deployment. Existing approaches rely on a model...
Abstract: Quantization techniques such as BitsAndBytes, AWQ, and GPTQ are widely used as a standard method in deploying large language models but often degrades...
Abstract: Large Language Models (LLMs) perform internal computations in continuous vector spaces yet produce discrete tokens -- a fundamental mismatch whose geo...
Abstract: Independently trained domain specialists can be fused post-hoc into a single model that outperforms any individual specialist, and the gain is predict...
Abstract: Deploying large language models (LLMs) on edge devices requires extremely low-bit quantization. Ultra-low precision formats such as NVFP4 offer a prom...
Abstract: To embed domain-specific or specialized knowledge into pre-trained foundation models, fine-tuning using techniques such as parameter efficient fine-tuni...