Objective Mismatch in Model-based Reinforcement Learning
Paper
•
2002.04523
•
Published
🤗 H4 Community
community
AI & ML interests
Community efforts from the HuggingFace H4 team.
Recent Activity
View all activity
h4community's activity
natolambert
authored
9
papers
about 14 hours ago
Confidence-Building Measures for Artificial Intelligence: Workshop Proceedings
Paper
•
2308.00862
•
Published
A Survey on Data Selection for Language Models
Paper
•
2402.16827
•
Published
•
4
D2PO: Discriminator-Guided DPO with Response Evaluation Models
Paper
•
2405.01511
•
Published
Unpacking DPO and PPO: Disentangling Best Practices for Learning from Preference Feedback
Paper
•
2406.09279
•
Published
•
2
WildGuard: Open One-Stop Moderation Tools for Safety Risks, Jailbreaks, and Refusals of LLMs
Paper
•
2406.18495
•
Published
•
13
Towards a Framework for Openness in Foundation Models: Proceedings from the Columbia Convening on Openness in Artificial Intelligence
Paper
•
2405.15802
•
Published
Molmo and PixMo: Open Weights and Open Data for State-of-the-Art Multimodal Models
Paper
•
2409.17146
•
Published
•
106
2 OLMo 2 Furious
Paper
•
2501.00656
•
Published
•
13
Post
2079
🇪🇺 Policy Thoughts in the EU AI Act Implementation 🇪🇺
There is a lot to like in the first draft of the EU GPAI Code of Practice, especially as regards transparency requirements. The Systemic Risks part, on the other hand, is concerning for both smaller developers and for external stakeholders.
I wrote more on this topic ahead of the next draft. TLDR: more attention to immediate large-scale risks and to collaborative solutions supported by evidence can help everyone - as long as developers disclose sufficient information about their design choices and deployment contexts.
Full blog here, based on our submitted response with @frimelle and @brunatrevelin :
https://huggingface.co/blog/yjernite/eu-draft-cop-risks#on-the-proposed-taxonomy-of-systemic-risks
There is a lot to like in the first draft of the EU GPAI Code of Practice, especially as regards transparency requirements. The Systemic Risks part, on the other hand, is concerning for both smaller developers and for external stakeholders.
I wrote more on this topic ahead of the next draft. TLDR: more attention to immediate large-scale risks and to collaborative solutions supported by evidence can help everyone - as long as developers disclose sufficient information about their design choices and deployment contexts.
Full blog here, based on our submitted response with @frimelle and @brunatrevelin :
https://huggingface.co/blog/yjernite/eu-draft-cop-risks#on-the-proposed-taxonomy-of-systemic-risks
- 2 replies
natolambert
authored
a
paper
about 1 month ago
rmahesh
authored
a
paper
2 months ago
natolambert
authored
a
paper
2 months ago
natolambert
authored
a
paper
4 months ago
natolambert
authored
a
paper
5 months ago
Shayne
authored
4
papers
6 months ago
The Responsible Foundation Model Development Cheatsheet: A Review of Tools & Resources
Paper
•
2406.16746
•
Published
Entity-Based Knowledge Conflicts in Question Answering
Paper
•
2109.05052
•
Published
The Flan Collection: Designing Data and Methods for Effective Instruction Tuning
Paper
•
2301.13688
•
Published
•
8
MKQA: A Linguistically Diverse Benchmark for Multilingual Open Domain Question Answering
Paper
•
2007.15207
•
Published
rmahesh
authored
a
paper
6 months ago