3 accepted papers
Modern GPUs evolve rapidly, yet production compilers still rely on hand-crafted register allocation heuristics that require substantial re-tuning for each hardware generation. We introduce VeriLocc, a framework that combines large language models (LLMs) with formal compiler techniques to enable gene
Existing backdoor defense methods are only effective for limited trigger types. To defend different trigger types at once, we start from the class-irrelevant nature of the poisoning process and propose a novel weakly supervised backdoor defense framework WeDef. Recent advances in weak supervision ma…
Neural network language models have gained considerable popularity due to their promising performance. Distributed word embeddings are utilized to represent semantic information. However, each word is associated with a single vector in the embedding layer, disabling the model from capturing the mean…