.
Ask HN: Which recent research paper blew your mind?
1–10 of 174 posts
Re: Ask HN: Which recent research paper blew your mind?
#2LoRA: Low-Rank Adaptation of Large Language Models [1]
Re: Ask HN: Which recent research paper blew your mind?
#3"Blue Is the New Black (Market): Privacy Leaks and Re-Victimization from Police-Auctioned Cellphones"
https://krebsonsecurity.com/2023/05/re-victimization-from-po...
Researchers bought up a bunch of seized phones from police auction sites and found about 25% of them were trivially unlockable and still held sensitive data about suspects and victims.
Re: Ask HN: Which recent research paper blew your mind?
#4Can Language Models Teach Weaker Agents? Teacher Explanations Improve Students via Theory of Mind
https://arxiv.org/abs/2306.09299
TokenFlow: Consistent Diffusion Features for Consistent Video Editing
https://huggingface.co/papers/2307.10373
Need to see code for second one.
Re: Ask HN: Which recent research paper blew your mind?
#5“A classification of endangered high-THC cannabis (Cannabis sativa subsp. indica) domesticates and their wild relatives”
By McPartland and Small.
Moving on from cannabis sativa indica and cannabis sativa sativa to cannabis sativa indica Himalayansis and cannabis sativa indica asperrima depending on distribution from the original location of the extinct ancient cannabis wildtype.
Following this new classification, I believe there’s a third undocumented variety in North East Asia.
If anyone else has noticed the samesameification of cannabis strains and is wondering what the path forward is, this may be illuminating.
Re: Ask HN: Which recent research paper blew your mind?
#6Toolformer: Language Models Can Teach Themselves to Use Tools
https://arxiv.org/abs/2302.04761
Older one, but still very nice work.
Re: Ask HN: Which recent research paper blew your mind?
#7I was impressed by the Voyager paper on a GPT-powered Minecraft bot.
Re: Ask HN: Which recent research paper blew your mind?
#8https://cseweb.ucsd.edu/~tullsen/halfandhalf.pdf
Half&Half: Demystifying Intel’s Directional Branch Predictors for Fast, Secure Partitioned Execution
Re: Ask HN: Which recent research paper blew your mind?
#9Toolformer: Language Models Can Teach Themselves to Use Tools https://arxiv.org/abs/2302.04761 Older one, but still very nice work.
I just posted the Voyager paper at exactly the same moment you posted this - a lot of the same ideas. https://voyager.minedojo.org/
Re: Ask HN: Which recent research paper blew your mind?
#10Someone managed to GPU-accelerate program synthesis, a form of symbolic ML. First time for ML that is not deep learning:
https://dl.acm.org/doi/10.1145/3591274
Deep learning took off precisely when the ImageNet paper dropped around 2010. Before nobody believed that backprop can be GPU-accelerated.