💡 Remember Box

Binary and Scalar Embedding Quantization for Significantly Faster & Cheaper Retrieval
https://huggingface.co/blog/embedding-quantization#performance-summarization

huggingface.co

Binary and Scalar Embedding Quantization for Significantly Faster & Cheaper Retrieval

We’re on a journey to advance and democratize artificial intelligence through open source and open science.

19 views21:21

💡 Remember Box

#todo write good blogs

🫡1

10 views21:31

💡 Remember Box

https://arxiv.org/abs/2512.20605

arXiv.org

Emergent temporal abstractions in autoregressive models enable...

Large-scale autoregressive models pretrained on next-token prediction and finetuned with reinforcement learning (RL) have achieved unprecedented success on many problem domains. During RL, these...

7 views04:25

💡 Remember Box

https://github.com/yifanzhang-pro/deep-delta-learning

GitHub

GitHub - yifanzhang-pro/deep-delta-learning: Official Project Page for Deep Delta Learning (https://huggingface.co/papers/2601.00417)

Official Project Page for Deep Delta Learning (https://huggingface.co/papers/2601.00417) - yifanzhang-pro/deep-delta-learning

6 views04:52

💡 Remember Box

https://arxiv.org/abs/2601.00417

arXiv.org

Deep Delta Learning

The effectiveness of deep residual networks hinges on the identity shortcut connection. While this mechanism alleviates the vanishing-gradient problem, it also has a strictly additive inductive...

7 views04:52

💡 Remember Box

reasoning is better described as discrete search over symbolic structures

7 views04:54

💡 Remember Box

neural front-end, symbolic core, verified output

6 views05:00

💡 Remember Box

https://github.com/parcadei/Continuous-Claude-v3

6 views05:04

💡 Remember Box

❤3

7 views14:36

💡 Remember Box

❤1

11 views14:54

💡 Remember Box

Reishi mushroom is really good for stress relief

8 views16:23

💡 Remember Box

Emergent temporal abstractions in autoregressive models enable hierarchical reinforcement learning
https://www.k-a.in/ETA-HRL.html

10 views05:15

💡 Remember Box

[2504.17033] Breaking the Sorting Barrier for Directed Single-Source Shortest Paths
https://arxiv.org/abs/2504.17033

arXiv.org

Breaking the Sorting Barrier for Directed Single-Source Shortest Paths

We give a deterministic $O(m\log^{2/3}n)$-time algorithm for single-source shortest paths (SSSP) on directed graphs with real non-negative edge weights in the comparison-addition model. This is...

16 views11:39

About

Blog

Apps

Platform