Josef Chen PRO

josefchen

5 4 14

https://josef.cn

josefchen

AI & ML interests

Food

Recent Activity

authored a paper 1 day ago

Ready Cohorts: Bounding GPU Opportunity and Avoiding Host Round Trips in LLM-Agent Control

liked a dataset 1 day ago

josefchen/ready-cohorts

updated a Space 1 day ago

josefchen/ready-cohorts

View all activity

Organizations

authored a paper 1 day ago

Ready Cohorts: Bounding GPU Opportunity and Avoiding Host Round Trips in LLM-Agent Control

Paper • 2608.12123 • Published 3 days ago • 2

liked a dataset 1 day ago

josefchen/ready-cohorts

Preview • Updated 1 day ago • 73 • 2

updated a Space 1 day ago

Ready Cohorts Explorer

🚀

Explore GPU-ready cohorts for deterministic agent control.

updated a dataset 1 day ago

josefchen/ready-cohorts

Preview • Updated 1 day ago • 73 • 2

submitted a paper to Daily Papers 1 day ago

Ready Cohorts: Bounding GPU Opportunity and Avoiding Host Round Trips in LLM-Agent Control

Paper • 2608.12123 • Published 3 days ago • 2

published a Space 2 days ago

Ready Cohorts Explorer

🚀

Explore GPU-ready cohorts for deterministic agent control.

published a dataset 2 days ago

josefchen/ready-cohorts

Preview • Updated 1 day ago • 73 • 2

updated a Space 3 days ago

Epicure Explorer

🌶

Operators behind the FlavourBench culinary benchmark

authored a paper about 2 months ago

When Does Combining Language Models Help? A Co-Failure Ceiling on Routing, Voting, and Mixture-of-Agents Across 67 Frontier Models

Paper • 2606.27288 • Published Jun 25 • 4

liked a Space about 2 months ago

Combining LLMs Rarely Beats the Single Best Model

🎲

beta=P(all wrong): the co-failure ceiling on LLM ensembles

New activity in josefchen/co-failure-67-models about 2 months ago

Add task category to metadata

#1 opened about 2 months ago by

nielsr

liked a dataset about 2 months ago

josefchen/co-failure-67-models

Updated Jun 27 • 158 • 1

submitted a paper to Daily Papers about 2 months ago

When Does Combining Language Models Help? A Co-Failure Ceiling on Routing, Voting, and Mixture-of-Agents Across 67 Frontier Models

Paper • 2606.27288 • Published Jun 25 • 4

upvoted a paper about 2 months ago

When Does Combining Language Models Help? A Co-Failure Ceiling on Routing, Voting, and Mixture-of-Agents Across 67 Frontier Models

Paper • 2606.27288 • Published Jun 25 • 4

updated a dataset about 2 months ago

josefchen/co-failure-67-models

Updated Jun 27 • 158 • 1

published a dataset about 2 months ago

josefchen/co-failure-67-models

Updated Jun 27 • 158 • 1

updated a Space about 2 months ago

Combining LLMs Rarely Beats the Single Best Model

🎲

beta=P(all wrong): the co-failure ceiling on LLM ensembles

published a Space about 2 months ago

Combining LLMs Rarely Beats the Single Best Model

🎲

beta=P(all wrong): the co-failure ceiling on LLM ensembles

authored a paper about 2 months ago

Memory as a Wasting Asset: Pricing Flash Endurance for Embodied Agents, and the Limits of Doing So

Paper • 2606.18144 • Published Jun 16

liked a Space about 2 months ago

Memory as a Wasting Asset

💾

Interactive companion to the wasting-asset memory paper.

Josef Chen PRO

AI & ML interests

Recent Activity

Organizations

josefchen's activity

Ready Cohorts Explorer

Ready Cohorts Explorer

Epicure Explorer

Combining LLMs Rarely Beats the Single Best Model

Add task category to metadata

Combining LLMs Rarely Beats the Single Best Model

Combining LLMs Rarely Beats the Single Best Model

Memory as a Wasting Asset