Open-MAGVIT2 An Open-Source Project Toward Democratizing Auto-regressive Visual Generation paper page: https://
huggingface.co/papers/2409.04
410
… We present Open-MAGVIT2, a family of auto-regressive image generation models ranging from 300M to 1.5B. The Open-MAGVIT2 project produces an
GENERATIVE AI
-
Open-MAGVIT2: Open-Source Auto-Regressive Visual Generation Models
By
–
-
SEAL: Expert-Created Private AI Evaluations Without Overfitting
By
–
Totally. Also, expert-created private evaluations that are impossible to overfit like SEAL (disclaimer, this is our work at Scale)
-
Qihoo-T2X: Efficient Diffusion Transformer with Proxy Tokens
By
–
Qihoo-T2X An Efficiency-Focused Diffusion Transformer via Proxy Tokens for Text-to-Any-Task discuss: https://
huggingface.co/papers/2409.04
005
… The global self-attention mechanism in diffusion transformers involves redundant computation due to the sparse and redundant nature of visual -
AI Evaluation Ecosystem Needs Better Benchmark Overfitting Detection
By
–
The whole Reflection-70B debacle points the the desperate need for a better AI evaluation ecosystem. It needs to be extremely easy to adjudicate:
(1) is the model overfit to benchmarks
(2) is the model truly unique (i.e. not a wrapper or thin fine-tune) https://
x.com/shinboson/stat
/shinboson/status/1832933747529834747
… -
Compact coding assistant challenges AI industry’s model size obsession
By
–
Try this "a powerful yet surprisingly compact coding assistant that threatens to disrupt the AI industry’s fixation on ever-larger models"
-
Best iOS Whisper App with Pre-Prompt Support
By
–
Is there a good iOS whisper app that lets me put in a pre-prompt to try this out?
-
Prompt Spelling Correction Fails on Subsequent Requests
By
–
Actually I just tried something similar, which is to use the domain specific words in the first request, then go back and edit the prompt to correct their spelling. Interestingly, that didn't work — when using those terms again in the next prompt saw them misspelled.
-
Jeremy Howard uncertain about ChatGPT voice mode technical details
By
–
I don't really understand your question, sorry. I'm just using the ChatGPT mobile app's voice mode — I dunno what it's doing behind the scenes.
-
Separate AI Chats with Domain-Specific Terminology
By
–
You can even have separate stored chats with different domain specific terminology in each, which you come back to later as needed.
-
ChatGPT Mobile App as Custom Voice Recognition Tool
By
–
I figured out how to use the ChatGPT mobile app as a custom voice recognition tool including special domain specific words! Just use the prompt below and then copy the requests from the app. It’s way more accurate than the iOS builtin one.