pull down to refresh

Achieving 10,000x training data reduction with high-fidelity labelsresearch.google/blog/achieving-10000x-training-data-reduction-with-high-fidelity-labels/
232 sats \ 3 comments \ @carter 8 Aug AI
related
Linear Representation Transferability: Using Small Models to Steer Larger Onesarxiv.org/pdf/2506.00653
110 sats \ 0 comments \ @carter 2 Jul AI
PixNerd: Pixel Neural Field Diffusionarxiv.org/abs/2507.23268
302 sats \ 2 comments \ @optimism 4 Aug AI
FAMO: A Fast Optimization Method for Multitask Learning (MTL)www.marktechpost.com/2024/05/05/famo-a-fast-optimization-method-for-multitask-learning-mtl-that-mitigates-the-conflicting-gradients-using-o1-space-and-time/
111 sats \ 0 comments \ @ch0k1 7 May 2024 science
Scaling up: how increasing inputs has made artificial intelligence more capableourworldindata.org/scaling-up-ai
279 sats \ 0 comments \ @0xbitcoiner 20 Jan charts_and_numbers
Zero-Knowledge Proofs of Training for Deep Neural Networkseprint.iacr.org/2024/162
2026 sats \ 5 comments \ @0xbitcoiner 5 Feb 2024 crypto
DeepScaleR: Surpassing O1-Preview with a 1.5B Model by Scaling RLpretty-radio-b75.notion.site/DeepScaleR-Surpassing-O1-Preview-with-a-1-5B-Model-by-Scaling-RL-19681902c1468005bed8ca303013a4e2
21 sats \ 0 comments \ @hn 11 Feb tech
Has generative AI already peaked?youtu.be/dDUC-LqVrPU
1368 sats \ 19 comments \ @davidw 10 May 2024 AI freebie
The Math Behind Batch Normalizationtowardsdatascience.com/the-math-behind-batch-normalization-90ebbc0b1b0b
100 sats \ 0 comments \ @ch0k1 9 May 2024 science
SPANN: Highly-efficient Billion-scale Approximate Nearest Neighbor Searcharxiv.org/abs/2111.08566
10 sats \ 0 comments \ @Rsync25 3 Nov 2024 tech
Full scan of 1 cubic millimeter of brain tissue took 1.4 petabytes of datawww.tomshardware.com/tech-industry/full-scan-of-1-cubic-millimeter-of-brain-tissue-took-14-petabytes-of-data-equivalent-to-14000-full-length-4k-movies
171 sats \ 2 comments \ @ch0k1 11 May 2024 science
Machine unlearning: ML model minus the information to be unlearnedai.stanford.edu/~kzliu/blog/unlearning
10 sats \ 0 comments \ @hn 5 May 2024 tech
The FFT Strikes Back: An Efficient Alternative to Self-Attentionarxiv.org/abs/2502.18394
69 sats \ 0 comments \ @hn 26 Feb tech
Advancements in machine learning for machine learningblog.research.google/2023/12/advancements-in-machine-learning-for.html
162 sats \ 1 comment \ @hn 16 Dec 2023 tech
Every model learned by gradient descent is approximately a kernel machine (2020)arxiv.org/abs/2012.00152
100 sats \ 1 comment \ @hn 25 Feb 2024 tech
Super-learningnewsletter.tomosman.com/p/super-learning
2320 sats \ 9 comments \ @kr 26 Jan 2024 tech
TinyML: Ultra-low power Machine Learningwww.ikkaro.net/what-tinyml-is/
105 sats \ 1 comment \ @hn 16 Jan 2024 tech
Weaponizing image scaling against production AI systemsblog.trailofbits.com/2025/08/21/weaponizing-image-scaling-against-production-ai-systems/
110 sats \ 0 comments \ @carter 21 Aug AI
Hidet: A Deep Learning Compiler for Efficient Model Servingpytorch.org/blog/introducing-hidet/
110 sats \ 1 comment \ @hn 28 Apr 2023 tech
Google AI Proposes TransformerFAM: A Novel Transformer Architecturewww.marktechpost.com/2024/04/17/google-ai-proposes-transformerfam-a-novel-transformer-architecture-that-leverages-a-feedback-loop-to-enable-the-neural-network-to-attend-to-its-latent-representations/
61 sats \ 2 comments \ @ch0k1 20 Apr 2024 tech
What Every User Should Know About Mixed Precision Training in PyTorchpytorch.org/blog/what-every-user-should-know-about-mixed-precision-training-in-pytorch/
10 sats \ 1 comment \ @hn 15 Mar 2024 tech
OpenAI's GPT-5 is a cost cutting exercisewww.theregister.com/2025/08/13/gpt_5_cost_cutting
217 sats \ 1 comment \ @Coinsreporter 13 Aug AI