pull down to refresh

FlashAttention: Fast Transformer training with long sequenceswww.adept.ai/blog/flashier-attention
10 sats \ 1 comment \ @hn 1 Oct 2023 tech
related
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
Mass Editing Memory in a Transformermemit.baulab.info/
60 sats \ 1 comment \ @hn 21 Apr 2023 tech
But what is a GPT? Visual intro to Transformers | Deep learning, chapter 5m.youtube.com/watch?v=wjZofJX0v4M
1000 sats \ 0 comments \ @south_korea_ln 2 Apr 2024 science
Understanding Transformers Using A Minimal Examplerti.github.io/gptvis/
228 sats \ 0 comments \ @carter 4 Sep 2025 AI
Chain of Thought Empowers Transformers to Solve Inherently Serial Problemsarxiv.org/abs/2402.12875
10 sats \ 0 comments \ @Rsync25 17 Sep 2024 tech
RustGPT: A pure-Rust transformer LLM built from scratchgithub.com/tekaratzas/RustGPT
100 sats \ 0 comments \ @hn 15 Sep 2025 tech
VGGT: Visual Geometry Grounded Transformergithub.com/facebookresearch/vggt
10 sats \ 0 comments \ @hn 25 Mar 2025 tech
Visualizing Attention, a Transformer's Heart [video]www.3blue1brown.com/lessons/attention
31 sats \ 0 comments \ @hn 15 Apr 2024 tech
Generative AI exists because of the transformerig.ft.com/generative-ai/
232 sats \ 2 comments \ @elvismercury 14 Oct 2023 tech
Transformer – Spreadsheetwww.byhand.ai/p/transformer-spreadsheet
9 sats \ 0 comments \ @hn 7 Feb 2025 tech
The Missing Link between the Transformer and Models of the Brainarxiv.org/abs/2509.26507
136 sats \ 0 comments \ @carter 22 Oct 2025 AI
The FFT Strikes Back: An Efficient Alternative to Self-Attentionarxiv.org/abs/2502.18394
69 sats \ 0 comments \ @hn 26 Feb 2025 tech
Launch HN: Deepsilicon (YC S24) – Software and hardware for ternary transformenews.ycombinator.com/item?id=41490196
21 sats \ 0 comments \ @hn 9 Sep 2024 tech
Real-time human-to-humanoid robot full-body teleoperation unlockedinterestingengineering.com/innovation/human-to-humanoid-teleoperation
41 sats \ 0 comments \ @ch0k1 17 Mar 2024 tech
Alibaba's Wan 2.5 video generation neural network has been releasedwan.video/
187 sats \ 2 comments \ @lunin 25 Sep 2025 AI
Transformers are Graph Neural Networksarxiv.org/pdf/2506.22084
110 sats \ 0 comments \ @carter 1 Jul 2025 AI
Transforming animation with machine learningmedium.com/embarkstudios/transforming-animation-with-machine-learning-27ac694590c
1381 sats \ 10k boost \ 10 comments \ @ek 9 Nov 2025 gaming
Transformer based AI will not lead us to AGI/ASI and is just a hype machine
3109 sats \ 18 comments \ @cy 2 Jul 2025 AI
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 2025 tech
What are transformer models and how do they work?txt.cohere.ai/what-are-transformer-models/
23 sats \ 0 comments \ @hn 15 Apr 2023 tech
Lightning Decoderlightningdecoder.com/
15 sats \ 10 boost \ 0 comments \ @yetanother 29 Jul 2021 bitcoin freebie