ML and Data Projects To Know

Tweeting papers & OSS projects advancing ML & data. Weekly newsletter with summaries: Curator @amplifypartners @sarahcat21.

[ML and Data Projects To Know @PTKDaily]

📙 Agent Laboratory: Using LLM Agents as Research Assistants

Authors: @SRSchmidgall @thu_yushengsu @JoelLiu0501 @ZeWang1995 @xiaodi95 @Xiaodong_Yu_126 @XimengSun1 Zhicheng Liu, @EmadBarsoumPi

Paper: https://t.co/NE8EI1d1SS

[ML and Data Projects To Know @PTKDaily]

📙 Scaling Language-Free Visual Representation Learning

Authors:@DavidJFan @TongPetersb @JiachenAI @koustuvsinha @liuzhuang1234 @endernewton Michael Rabbat, Nicolas Ballas, @ylecun @_amirbar @sainingxie

Paper: https://t.co/ZqlvXmBaHY

[ML and Data Projects To Know @PTKDaily]

📙 Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters

Authors: @sea_snell, @hoonkp, @imkelvinxu, @aviral_kumar2

Featured in PTK #127 https://t.co/mhSkZeoQJ3

Paper: https://t.co/h4l8UFZ6TM

[ML and Data Projects To Know @PTKDaily]

📙 The Unreasonable Effectiveness of Easy Training Data for Hard Tasks

Authors: @peterbhase, @mohitban47, Peter Clark,
@sarahwiegreffe

Paper: https://t.co/GmOVgWTzz2

[ML and Data Projects To Know @PTKDaily]

Why Chatbots Are Not the Future by: Amelia Wattenberger

Featured in PTK #124 https://t.co/DpNJu1QSh1

Post: https://t.co/pvzwk1ixTC

[ML and Data Projects To Know @PTKDaily]

📙 MEGABYTE: Predicting Million-byte Sequences with Multiscale Transformers

Authors: Lili Yu, Dániel Simig, Colin Flaherty, Armen Aghajanyan, Luke Zettlemoyer, Mike Lewis

Featured in PTK #124 https://t.co/DpNJu1Qkrt

Paper: https://t.co/jmVvfN1XS5

[ML and Data Projects To Know @PTKDaily]

🖥️Guidance

Featured in PTK #124 https://t.co/DpNJu1Qkrt

Code: https://t.co/SJcOSBGdRo
Blog: https://t.co/gyFGah1l0k

[ML and Data Projects To Know @PTKDaily]

Large sequence models for software development activities by: Petros Maniatis, Daniel Tarlow

Featured in PTK #124 https://t.co/DpNJu1QSh1

Blog: https://t.co/HoIZgHsife

[ML and Data Projects To Know @PTKDaily]

🖥️ Git-Theta by: @kandpal_nikhil, @blester125, @Muqeeth10, @anisham197, @montymevans, Vishal Baskaran, @TenghaoHuang45, @liu_haokun, @colinraffel

Featured in PTK #124 https://t.co/DpNJu1Qkrt

Code: https://t.co/SRZp6W76PQ
Paper: https://t.co/eDZb9WEw8z

[ML and Data Projects To Know @PTKDaily]

📙 Reflexion: Language Agents with Verbal Reinforcement Learning

Authors: @noahshinn024, @ellev3n11, Beck Labash, @ashwingop, @karthik_r_n, @ShunyuYao12

Featured in PTK #124 https://t.co/DpNJu1QSh1

Paper: https://t.co/03NUnLFZ0s
Code: https://t.co/jnFWC5AayO

[ML and Data Projects To Know @PTKDaily]

Open Vector Data Lakes by: Ziheng Wang

Featured in PTK #124 https://t.co/DpNJu1Qkrt

Post: https://t.co/2RrcpTqeOh

[ML and Data Projects To Know @PTKDaily]

🖥️ QLoRA by: Tim Dettmers, Artidoro Pagnoni, Ari Holtzman, Luke Zettlemoyer

Featured in PTK #124 https://t.co/DpNJu1Qkrt

Code: https://t.co/1S2F619JHr

[ML and Data Projects To Know @PTKDaily]

📙 How Far Can Camels Go? Exploring the State of Instruction Tuning on Open Resources

Featured in PTK #124 https://t.co/DpNJu1Qkrt

Paper: https://t.co/IH0Ahqzs8y

[ML and Data Projects To Know @PTKDaily]

Enterprise Restaurant Compute by: Brian Chambers, Chick-fil-A

Featured in PTK #121 https://t.co/3asL8nl2xA

Post: https://t.co/SxsG6LufXb

[ML and Data Projects To Know @PTKDaily]

🖥️ Zeno

Featured in PTK #121 https://t.co/3asL8nl2xA

Code: https://t.co/ErDpdKR7S1

[ML and Data Projects To Know @PTKDaily]

📙 Parsel : A (De-)compositional Framework for Algorithmic Reasoning with Language Models

Authors: Eric Zelikman, Qian Huang, Gabriel Poesia, Noah D. Goodman, Nick Haber

Featured in PTK #121 https://t.co/3asL8nl2xA

Paper: https://t.co/vKXszwhyDP

[ML and Data Projects To Know @PTKDaily]

🖥️ 𝗗𝗦𝗣: The Demonstrate–Search–Predict Framework by: Omar Khattab, Keshav Santhanam, Xiang Lisa Li, David Hall, Percy Liang, Christopher Potts, Matei Zaharia

Featured in PTK #121 https://t.co/3asL8nl2xA

Code: https://t.co/Am0D19Cmol
Paper: https://t.co/IY0GANXuTj

[ML and Data Projects To Know @PTKDaily]

📙 Toolformer: Language Models Can Teach Themselves to Use Tools

Authors: @timo_schick @JaneDwivedi @robdessi @robertarail @MariaLomeli_, @LukeZettlemoyer Nicola Cancedda, @ThomasScialom

Featured in PTK #121 https://t.co/3asL8nl2xA

Paper: https://t.co/sLewqsRLGX

[ML and Data Projects To Know @PTKDaily]

A Twitter Thread from Neeva

Featured in PTK #121 https://t.co/3asL8nl2xA

Thread: https://t.co/jrZyYnjlzS

[Neeva @Neeva]

1/ NeevaAI serves abstractive summaries of web pages that are generated in real-time.

We achieved this by a ~10x reduction in latency of a fine-tuned t5-large encoder-decoder model.

TY @asimshankar, @rajhans_samdani, @AshwinDevaraj3 + @spacemanidol

See our lessons learned.. 🧵

[ML and Data Projects To Know @PTKDaily]

🖥️ iWF by: Indeed

Featured in PTK #121 https://t.co/3asL8nl2xA

Code: https://t.co/If4mNmpUyC