Hugging Face published a paper by Meta titled Research Preference Models (RPMs) that tackles how to instill research taste in agents as they conduct experiments.
Public source
Publisher name
Public post
I quite enjoyed reading Meta's new paper on research preference models (RPMs) this week: https://lnkd.in/eqcKWxWy It tackles a problem that many people are pondering for…
Company
Hugging Face
The AI community building the future.
- Industry
- Software Development
- Location
- US
- Company size
- 1,001–5,000 employees
About Hugging Face
The AI community building the future.
See moreLatest activity
Latest activity from Hugging Face
47 signals
Products & Services
Hugging Face released a new skill allowing agents to automatically publish Blender worlds and agent traces to the Hugging Face Hub using the Hugging Face CLI.
Research & Knowledge
Hugging Face published research on the C. elegans worm with 302 neurons, 3,709 directed chemical connections, and 1,105 electrical pairs from Cook et al. (2019) using OpenWorm’s ConnectomeToolbox
Technology & Infrastructure
Hugging Face upgraded its infrastructure to host Le Chaton Fat
Discover more
Similar signals
Similar public activity from other companies.
Research & Knowledge
Meta
Meta published a new paper focusing on optimizing how Agents choose the right candidates to solve ML research tasks.
Research & Knowledge
Marktechpost AI Media Inc
Marktechpost AI Media Inc reported that Meta FAIR released AI Research Preference Models (RPMs) that rank language models for absolute metrics and execution outcomes, lifting AIRS-Bench from 0.684 to 0.729.
Research & Knowledge
distil labs
distil labs published a blog post titled the three ways a small model actually enters a production system, and how to tell which one you are looking at.
Research & Knowledge
Declarative AI: Build Custom AI Agents from a Single Prompt
Declarative AI: Build Custom AI Agents from a Single Prompt published a report detailing 6 weeks of training and hacking of 1,000+ agents on Hugging Face.
Research & Knowledge
PyMC Labs