10 citations · 29 across the 8 of their papers we have counts for
5 papers · 1 filter
BOAD: Discovering Hierarchical Software Engineering Agents via Bandit Optimization
Iris Xu, Guangtao Zeng, Zexue He +5
Large language models (LLMs) have shown strong reasoning and coding capabilities, yet they struggle to generalize to real-world software engineering (SWE) problems that are long-ho…
Emergent Representations of Program Semantics in Language Models Trained on Programs
Charles Jin, Martin Rinard
We present evidence that language models (LMs) of code can learn to represent the formal semantics of programs, despite being trained only to perform next-token prediction. Specifi…
Neural Architecture Search using Property Guided Synthesis
Charles Jin, Phitchaya Mangpo Phothilimthana, Sudip Roy
In the past few years, neural architecture search (NAS) has become an increasingly important tool within the deep learning community. Despite the many recent successes of NAS, howe…
Incompatibility Clustering as a Defense Against Backdoor Poisoning Attacks
Charles Jin, Melinda Sun, Martin Rinard
We propose a novel clustering mechanism based on an incompatibility property between subsets of data that emerges during model training. This mechanism partitions the dataset into…
Towards Context-Agnostic Learning Using Synthetic Data
Charles Jin, Martin Rinard
We propose a novel setting for learning, where the input domain is the image of a map defined on the product of two sets, one of which completely determines the labels. We derive a…