stealthcat
- Karma
- 144
- Created
- November 20, 2017 (8y ago)
- Submissions
- 0
- The Judgment on Fiat Currency [pdf] (realmoney.com.my)
-
Multi-modal LLM like PaLM, GPT4, MiniGPTv2 relies on data encoder (image, speech models) to map data to token embedding space. Is there any attempt to directly train on file bytes? Make the only vocab of LLM as base-2,…
- Unary Computer for Matrix Multiplication [pdf] (jsm.ece.wisc.edu)
-
Is it the only way to produce fast cross-platform binaries? LLVM is huge and compile times can be slow. I found several compilers related: 0. GCC 1. Zig started as LLVM frontend, finally with self-hosting, can do…
-
Is LLVM the only way to generate fast cross-platform nowadaysk? Last time Zig managed to be self-hosting and codegen for various platforms is possible without LLVM.
-
Python classes may be clunky but it is said that Python class system is more flexible than other languages' OOP, even Lisp CLOS. How does Python class system actually compare to Lisp CLOS? I've seen arguments for Python…
- Compiling AI with AI (openreview.net)
-
Or else, where is the best way to start writing one? Need to able to handle online real-time multiplayer without much lag.
- Paperlike 3: E-ink Monitor with 13.3”, 2200*1650 Resolution (indiegogo.com)
-
Anyone here participated as student for past Google Summer of Code? For which organization? How was your experience?
- Advice on Reading a Book (youtube.com)
- Neuromorphic vs. Quantum vs. HPC (datasciencecentral.com)
-
Any HNers doing deep learning with TF? I am currently learning Tensorflow, and seems the API is too big, learning curve is too steep compared to Theano, Pytorch and Chainer. I can't get doing declarative programming in…