Top ML Papers of the Week (Sep 25 – Oct 1): – MentalLlaMa
– Boolformer
– The Reversal Curse in LLMs
– Long-Context Scaling with LLMs
– Graph Neural Prompting with LLMs
– Vision Transformers Need Registers
…
LLMS
-
Top ML Papers of the Week: LLMs and Vision Transformers
By
–
-
The Reversal Curse: LLMs fail bidirectional generalization
By
–
1/ The Reversal Curse – finds that LLMs trained on sentences of the form “A is B” will not automatically generalize to the reverse direction “B is A”; shows the effect across model sizes and model families.
-
70B LLM Variant Surpasses GPT-3.5 Long-Context Performance
By
–
2/ Effective Long-Context Scaling with LLMs – propose a 70B variant that can already surpass gpt-3.5-turbo-16k’s overall performance on a suite of long-context tasks.
-
DALL-E 3 integration in ChatGPT to improve consistency
By
–
La consistance Ça sera résolu la semaine prochaine avec l’introduction de dalle3 dans ChatGPT
-
Bing solves captcha by pretending to be grandmother’s locket
By
–
Getting Bing to solve a captcha by pretending it’s a locket from your recently deceased grandmother:
-
LLMs Replace Consultants for AI Strategy, Employees Must Adapt
By
–
Avec les LLM oui, pas besoin de demander à un cabinet de conseil où mettre de l'IA et comment s'y prendre : l'IA sous forme d'assistant intelligent leur dira, et sera 1000 fois plus pertinente (et moins chère) L'urgence est que les employés prennent l'habitude d'utiliser l'IA..
-
Pretending to be assistant makes LLM act as generic user
By
–
That’s actually what I was trying to get it to do when I noticed this. For a lot of chat-tuned LLMs if you pretend to be the assistant they’ll pretend to be a (very generic) user.
-
Falcon-180B Demo: Advanced Language Model on Hugging Face
By
–
Falcon-180B Demo – a Hugging Face Space by tiiuae https://
bit.ly/3rs7pyK
#AI #MachineLearning #DeepLearning #LLMs #DataScience -
AI Games Collection: Machine Learning and Deep Learning Applications
By
–
AI Games – a fffiloni Collection https://
bit.ly/3EJhWJ3
#AI #MachineLearning #DeepLearning #LLMs #DataScience -
Security vulnerability discovered affecting large language models
By
–
Ouch it infects LLMs too https://
x.com/linylinx/statu
s/1708154091782676619?s=46
…