Daniel Fried
@daniel-fried.bsky.social
Assistant prof at LTI CMU; Research scientist at Meta AI. Working on NLP: language interfaces, applied pragmatics, language-to-code, grounding. https://dpfried.github.io/
Paper: arxiv.org/abs/2503.07358
Code: github.com/yiqingxyq/Re...
Work led by Yiqing Xie, with Alex Xie, Divyanshu Sheth, Pengfei Liu, @daniel-fried.bsky.social and @carolynrose.bsky.social
Code: github.com/yiqingxyq/Re...
Work led by Yiqing Xie, with Alex Xie, Divyanshu Sheth, Pengfei Liu, @daniel-fried.bsky.social and @carolynrose.bsky.social
RepoST: Scalable Repository-Level Coding Environment Construction with Sandbox Testing
We present RepoST, a scalable method to construct environments that provide execution feedback for repository-level code generation for both training and evaluation. Unlike existing works that aim to ...
arxiv.org
July 16, 2025 at 6:33 PM
Paper: arxiv.org/abs/2503.07358
Code: github.com/yiqingxyq/Re...
Work led by Yiqing Xie, with Alex Xie, Divyanshu Sheth, Pengfei Liu, @daniel-fried.bsky.social and @carolynrose.bsky.social
Code: github.com/yiqingxyq/Re...
Work led by Yiqing Xie, with Alex Xie, Divyanshu Sheth, Pengfei Liu, @daniel-fried.bsky.social and @carolynrose.bsky.social
2) RepoST.
We automatically create executable environments from real GitHub repos, allowing us to train and evaluate models for function generation in real-world contexts.
Presenting at the CODEML workshop on Fri Jul 18th.
Also accepted to COLM, upcoming!
We automatically create executable environments from real GitHub repos, allowing us to train and evaluate models for function generation in real-world contexts.
Presenting at the CODEML workshop on Fri Jul 18th.
Also accepted to COLM, upcoming!
July 16, 2025 at 6:33 PM
2) RepoST.
We automatically create executable environments from real GitHub repos, allowing us to train and evaluate models for function generation in real-world contexts.
Presenting at the CODEML workshop on Fri Jul 18th.
Also accepted to COLM, upcoming!
We automatically create executable environments from real GitHub repos, allowing us to train and evaluate models for function generation in real-world contexts.
Presenting at the CODEML workshop on Fri Jul 18th.
Also accepted to COLM, upcoming!
Paper: arxiv.org/abs/2409.07429
Code: github.com/zorazrw/agen...
Work led by @zorazrw.bsky.social, with Jiayuan Mao and @gneubig.bsky.social
Code: github.com/zorazrw/agen...
Work led by @zorazrw.bsky.social, with Jiayuan Mao and @gneubig.bsky.social
Agent Workflow Memory
Despite the potential of language model-based agents to solve real-world tasks such as web navigation, current methods still struggle with long-horizon tasks with complex action trajectories. In contr...
arxiv.org
July 16, 2025 at 6:33 PM
Paper: arxiv.org/abs/2409.07429
Code: github.com/zorazrw/agen...
Work led by @zorazrw.bsky.social, with Jiayuan Mao and @gneubig.bsky.social
Code: github.com/zorazrw/agen...
Work led by @zorazrw.bsky.social, with Jiayuan Mao and @gneubig.bsky.social
1) Agent Workflow Memory.
Allow agents to adapt online to carry out new tasks more accurately by inducing workflows for common sub-tasks.
Today (Wed 7/17): 4:30-7pm. West Exhibition Hall B2-B3 W-202):
Also at the CUA workshop, morning of Sat 7/19.
Allow agents to adapt online to carry out new tasks more accurately by inducing workflows for common sub-tasks.
Today (Wed 7/17): 4:30-7pm. West Exhibition Hall B2-B3 W-202):
Also at the CUA workshop, morning of Sat 7/19.
July 16, 2025 at 6:33 PM
1) Agent Workflow Memory.
Allow agents to adapt online to carry out new tasks more accurately by inducing workflows for common sub-tasks.
Today (Wed 7/17): 4:30-7pm. West Exhibition Hall B2-B3 W-202):
Also at the CUA workshop, morning of Sat 7/19.
Allow agents to adapt online to carry out new tasks more accurately by inducing workflows for common sub-tasks.
Today (Wed 7/17): 4:30-7pm. West Exhibition Hall B2-B3 W-202):
Also at the CUA workshop, morning of Sat 7/19.
Congrats Mohit!!
January 15, 2025 at 5:07 PM
Congrats Mohit!!
You can execute each generated function on a set of possible inputs to the function, group the functions according to the outputs, then choose the largest group: arxiv.org/abs/2204.11454 and Sec 4.6 of arxiv.org/abs/2203.07814, although I'm not sure what was done in these plots
Natural Language to Code Translation with Execution
Generative models of code, pretrained on large corpora of programs, have shown great success in translating natural language to code (Chen et al., 2021; Austin et al., 2021; Li et al., 2022, inter ali...
arxiv.org
January 6, 2025 at 4:07 AM
You can execute each generated function on a set of possible inputs to the function, group the functions according to the outputs, then choose the largest group: arxiv.org/abs/2204.11454 and Sec 4.6 of arxiv.org/abs/2203.07814, although I'm not sure what was done in these plots
So sorry to hear this, what a loss - such a kind and fun guy and his work is so creative.
January 2, 2025 at 11:53 PM
So sorry to hear this, what a loss - such a kind and fun guy and his work is so creative.