MACaQ: Fast, Model Agnostic Calibrated Quantization for Low-Precision Weights and Activations Paper • 2611.10649 • Published 12 days ago • 31
Jeff 1.1 Collection Jeff 1.1 decision models (backbones: Gemma 4 31B, Qwen3.6-27B, Gemma 4 12B, Qwen3.5-4B). Previous version: Jeff 1.0. • 4 items • Updated 19 days ago • 1
Releasing the Inner Jev: A Simple Recipe for Open Decision Models Paper • 2610.17205 • Published Oct 12 • 3
view article Article llama.cpp v1.0.0 : A stronger foundation for the local AI ecosystem ggml-org • 5 days ago • 216
e-means: outperforming k-means (in one-tenth the epochs) Paper • 2611.09501 • Published 13 days ago • 20
Draft in Parallel, Condition Through Depth: Adjacent Causal Injection for Speculative Decoding Paper • 2609.36173 • Published Sep 28 • 5
Benchmarking Large Language Models in Retrieval-Augmented Generation Paper • 2309.01431 • Published Sep 4, 2023 • 2
LLM Evaluators Recognize and Favor Their Own Generations Paper • 2404.13076 • Published Apr 15, 2024 • 3
Proving and Improving the Platonic Representation Hypothesis with JEPAs Paper • 2610.39302 • Published 21 days ago • 79
What If We Recaption Billions of Web Images with LLaMA-3? Paper • 2406.08478 • Published Jun 12, 2024 • 42
Text-Only Training for Image Captioning using Noise-Injected CLIP Paper • 2211.00575 • Published Nov 1, 2022 • 1