Publications (6)
GitChameleon 2.0: Evaluating AI Code Generation Against Python Library Version Incompatibilities
Diganta Misra, Nizar Islah, Victor May +9
The rapid evolution of software libraries poses a considerable hurdle for code generation, necessitating continuous adaptation to frequent version updates while preserving backward…
An algorithm for improving Non-Local Means operators via low-rank approximation
Victor May, Yosi Keller, Nir Sharon +1
We present a method for improving a Non Local Means operator by computing its low-rank approximation. The low-rank operator is constructed by applying a filter to the spectrum of t…
MixtureVitae: Open Web-Scale Pretraining Dataset With High Quality Instruction and Reasoning Data Built from Permissive-First Text Sources
Huu Nguyen, Victor May, Harsh Raj +14
We present MixtureVitae, an open-access pretraining corpus built to minimize legal risk while providing strong downstream performance. MixtureVitae follows a permissive-first, risk…
FreshBrew: A Benchmark for Evaluating AI Agents on Java Code Migration
Victor May, Diganta Misra, Yanqi Luo +3
AI coding assistants are rapidly becoming integral to modern software development. A key challenge in this space is the continual need to migrate and modernize codebases in respons…
Agents Learn Their Runtime: Interpreter Persistence as Training-Time Semantics
Victor May, Aaditya Salgarkar, Yishan Wang +2
Tool-augmented LLMs are increasingly deployed as agents that interleave natural-language reasoning with executable Python actions, as in CodeAct-style frameworks. In deployment, th…
Aurora-M: Open Source Continual Pre-training for Multilingual Language and Code
Taishi Nakamura, Mayank Mishra, Simone Tedeschi +42
Pretrained language models are an integral part of AI applications, but their high computational cost for training limits accessibility. Initiatives such as Bloom and StarCoder aim…