4 papers
Training-Free Task Vectors for LLM Behavioral Control
Gabriel J. Perin, Lucas Boscaini, André Araujo +1
Task vectors enable post-training model editing by identifying semantically meaningful directions in weight space, typically computed as the difference between a fine-tuned model a…
Equivariant Interatomic Potentials without Tensor Products
Thiago Reschützegger, Sarp Aykent, Gabriel Jacob Perin +5
Foundational machine-learned interatomic potentials have emerged as powerful tools for atomistic simulations, promising near first-principles accuracy across diverse chemical space…
LAD-VF: LLM-Automatic Differentiation Enables Fine-Tuning-Free Robot Planning from Formal Methods Feedback
Yunhao Yang, Junyuan Hong, Gabriel Jacob Perin +4
Large language models (LLMs) can translate natural language instructions into executable action plans for robotics, autonomous driving, and other domains. Yet, deploying LLM-driven…
Extracting and Understanding the Superficial Knowledge in Alignment
Runjin Chen, Gabriel Jacob Perin, Xuxi Chen +5
Alignment of large language models (LLMs) with human values and preferences, often achieved through fine-tuning based on human feedback, is essential for ensuring safe and responsi…