UC Berkeley EPIC Lab

88 posts

UC Berkeley EPIC Lab banner
UC Berkeley EPIC Lab

UC Berkeley EPIC Lab

@UCBEPIC

Effective Programming, Interaction, and Computation with Data Lab @UCBerkeley

Berkeley CA Katılım Kasım 2021
22 Takip Edilen472 Takipçiler
UC Berkeley EPIC Lab
UC Berkeley EPIC Lab@UCBEPIC·
Can you explore the space using LLMs - but do it in a way that is efficient? How do we find the high error regions?
UC Berkeley EPIC Lab tweet media
English
0
1
2
312
UC Berkeley EPIC Lab
UC Berkeley EPIC Lab@UCBEPIC·
It’s hard to robustly test edge cases in a model and make user defined concepts explicit
UC Berkeley EPIC Lab tweet media
English
1
0
1
399
UC Berkeley EPIC Lab
UC Berkeley EPIC Lab@UCBEPIC·
Fereshte Khani from Microsoft describes how to collaboratively develop NLP models, ensuring alignment and safety
UC Berkeley EPIC Lab tweet media
English
1
2
3
2.3K
UC Berkeley EPIC Lab
UC Berkeley EPIC Lab@UCBEPIC·
A new system they are working on is Humboldt for data discovery. You shouldn’t have to ask experts about what data you should explore!
UC Berkeley EPIC Lab tweet media
English
0
1
3
406
UC Berkeley EPIC Lab
UC Berkeley EPIC Lab@UCBEPIC·
Alex Bauerle from Sigma Computing tells us about what’s hard when building a spreadsheet for cloud data warehouses
UC Berkeley EPIC Lab tweet media
English
2
3
8
1.5K
UC Berkeley EPIC Lab
UC Berkeley EPIC Lab@UCBEPIC·
Can you fuse structural understanding of API programs with LLM techniques? Naman provides a way! Parametric templates for the win!
UC Berkeley EPIC Lab tweet media
English
0
0
2
198
UC Berkeley EPIC Lab
UC Berkeley EPIC Lab@UCBEPIC·
LLMs by themselves are insufficient for this task - brittle and hard to control
UC Berkeley EPIC Lab tweet media
English
1
0
2
214
UC Berkeley EPIC Lab
UC Berkeley EPIC Lab@UCBEPIC·
Naman Jain explores how to summarize data transformation scripts using a template-based approach, informed by LLMs
UC Berkeley EPIC Lab tweet media
English
1
1
2
847
UC Berkeley EPIC Lab
UC Berkeley EPIC Lab@UCBEPIC·
Flor allows users to travel back in time to help debug ML training. You can also inspect and “jump into” another user’s training history. Time travel and shapeshifting!
English
0
0
3
167
UC Berkeley EPIC Lab
UC Berkeley EPIC Lab@UCBEPIC·
Rolando Garcia @rogarcia_sanz describes the next generation of Flor, a tool for rapid iteration during ML training via a live notebook demo!
UC Berkeley EPIC Lab tweet media
English
1
1
3
761
UC Berkeley EPIC Lab
UC Berkeley EPIC Lab@UCBEPIC·
Haotian leverages large language models to identify visualization intent (variants of BERT) and prior work on automatically translating visualization intent into actual visualizations (eg Lux).
English
0
0
1
168
UC Berkeley EPIC Lab
UC Berkeley EPIC Lab@UCBEPIC·
Haotian Li describes how to support conversation with data via visualization - why write code when you can just talk to your data!
UC Berkeley EPIC Lab tweet media
English
1
1
6
1.1K
UC Berkeley EPIC Lab
UC Berkeley EPIC Lab@UCBEPIC·
Can we check extensional equality (ie two programs have similar outputs) for constrained domains like biology? So that we can automatically rewrite and make code more performant — component by component?
UC Berkeley EPIC Lab tweet media
English
0
0
1
133
UC Berkeley EPIC Lab
UC Berkeley EPIC Lab@UCBEPIC·
There is a trade off between easy to understand code (eg one that loops through arrays) and those that are performant (eg one that manipulates arrays in NumPy)
English
1
0
1
138
UC Berkeley EPIC Lab
UC Berkeley EPIC Lab@UCBEPIC·
Justin Lubin @jplubin embedded himself in a “wet lab” biology group to identify their programming challenges
UC Berkeley EPIC Lab tweet media
English
1
1
3
545
UC Berkeley EPIC Lab
UC Berkeley EPIC Lab@UCBEPIC·
Yet more challenges in Machine Learning - operationalizing, explaining and trusting it.
English
0
0
1
95
UC Berkeley EPIC Lab
UC Berkeley EPIC Lab@UCBEPIC·
More open challenges in helping novice users through the data science workflow - so that one can go from “zero to hero”
UC Berkeley EPIC Lab tweet media
English
1
0
1
119
UC Berkeley EPIC Lab
UC Berkeley EPIC Lab@UCBEPIC·
Barbara Stanley from Google BQ tells us about user challenges in end to end data analytics/science
UC Berkeley EPIC Lab tweet media
English
1
1
1
478