6 accepted papers
Low-Rank Adaptation (LoRA) has become the de facto paradigm for parameter-efficient fine-tuning, with its effectiveness critically influenced by rank allocation across modules. However, existing approaches face a fundamental dilemma: uniform allocation ignores module heterogeneity, while adaptive me…
Large language models fine-tuned on instruction–code pairs may memorize and subsequently leak sensitive training data. Existing differentially private (DP) code generation methods primarily protect code snippets while assuming prompts are public, which fails in realistic scenarios where prompts may …
Recent works have explored using language models for planning problems. One approach examines translating natural language descriptions of planning tasks into structured planning languages, such as the planning domain definition language (PDDL). Existing evaluation methods struggle to ensure semanti…
Detoxifying multilingual Large Language Models (LLMs) has become crucial due to their increasing global use. In this work, we explore zero-shot cross-lingual generalization of preference tuning in detoxifying LLMs. Unlike previous studies that show limited cross-lingual generalization for other safe…
As software development projects increasingly rely on open-source software, users face the risk of security vulnerabilities from third-party libraries. To address label and character noise in code changes, we present VF-Detector to automatically identifying bug-fix commits in actual noise developmen…
Training long-horizon robotic policies in complex physical environments is essential for many applications, such as robotic manipulation. However, learning a policy that can generalize to unseen tasks is challenging. In this work, we propose to achieve one-shot task generalization by decoupling plan…