This seems like cool work! I'm a big fan of problems related to robustness. Have you seen this paper by #ICML2022 paper by @andrew_ilyas @smsampark @logan_engstrom @gpoleclerc @aleks_madry
? Covers a similar problem. https://
arxiv.org/abs/2202.00622
MACHINE LEARNING
-
ICML 2022 Paper on Robustness in Machine Learning Research
By
–
-
DAGGER vs RL: Feedback Methods for LLM Training
By
–
While DAGGER is a great idea to enable Feedback for LLMs (eg chat) it is not a replacement for RL because RL opens up room for different forms of feedback (eg preferences). However, as a teacher I would advise careful measurement of the contribution of each to the final metric.
-
DAGGER Counterfactual Teaching Method for LLM Training
By
–
DAGGER is a form of counterfactual teaching as explained in https://
arxiv.org/abs/2110.10819 – Note that it is the student who always acts. The teacher only provides corrections, which are used to minimise the LLM loss directly. Note however that this imitation IS NOT supervised learning. -
DAGGER: Imitation Learning Alternative to Reinforcement Learning
By
–
People are asking if there are alternatives to RL in RLHF. Yes, imitation with DAGGER (tutorial: https://
ri.cmu.edu/publications/a
n-invitation-to-imitation/
… ). The user provides feedback with corrections, e.g. when the agent says “that” the user tells the agent that instead of saying “that”, it should say “this”. -
Microsoft to allow companies to create custom ChatGPT versions
By
–
CNBC reporting Microsoft will let companies create their own custom versions of ChatGPT
-
AI Resume Checker Scans and Scores Resumes
By
–
3. AI Resume Checker Resume is scanned, read, reviewed, and scored against other resumes. Great use case for a GPT API. Worth checking out. http://
kickresume.com -
Efficient Deep Learning Algorithms Part 4 Series
By
–
Part 4 in the series is out, by Sanjiv Kumar (on behalf of many!), covering a few different aspects of algorithms for efficient deep learning.
-
Deep Learning Models: Improving Robustness and Efficiency Through Algorithms Research
By
–
As #DeepLearning models become more widely used, it is increasingly important that they be both robust and efficient. Today we summarize some of our many efforts to improve #ML efficiency through algorithms research. → https://
goo.gle/3I6asCj -
E3B: New Method for Exploring Complex Variable Environments
By
–
E3B is a method for exploring complex environments which vary across episodes. This work set a new SOTA for MiniHack & reward-free exploration on Habitat in October.
— AI at Meta (@AIatMeta) 7 février 2023
Read the paper ➡️ https://t.co/5oxIf1kDAy
Get the code ➡️ https://t.co/omz9GLkkha pic.twitter.com/elUIs4FIofE3B is a method for exploring complex environments which vary across episodes. This work set a new SOTA for MiniHack & reward-free exploration on Habitat in October. Read the paper https://
bit.ly/3JUCceJ
Get the code https://
bit.ly/3YulsPk -
FDA Approves 500+ AI Algorithms for Medical Imaging Detection
By
–
FDA has now approved the use of more than 500 AI algorithms, mostly for medical imaging. Pictured below is an AI-automated detection of an intracranial hemorrhage on CT. The software can alert the care team before a radiologist even sees the exam.