4 papers
ParBench: A Benchmark for Reliable Evaluation of LLM Parallel Code Translation
Samyak Jhaveri, Erel Kaplan, Tom Yotam +4
Modern compute-intensive software must migrate across a changing ecosystem of accelerators, programming APIs, compiler stacks, and portability layers, including CUDA, OpenMP, OpenC…
Latent Reasoning Guidance for Parallel Code Translation
Tomer Bitan, Erel Kaplan, Roee Bar-Yadin +5
Tackling complex coding tasks often requires autonomous agents and iterative repair pipelines. These increasingly rely on large amounts of test-time computation, often spending man…
Optimizing Long-Form Clinical Text Generation with Claim-Based Rewards
Samyak Jhaveri, Praphul Singh, Jangwon Kim +2
Automating clinical documentation with large language models requires precise alignment with priorities such as completeness and factual grounding. We present an evaluation-integra…
ACCeLLiuM: Supervised Fine-Tuning for Automated OpenACC Pragma Generation
Samyak Jhaveri, Vanessa Klotzmann, Crista Lopes
The increasing ubiquity of GPUs is accompanied by the increasing complexity of their hardware and parallel programming frameworks. Directive-based parallel programming standards li…