15 citations · 16 across the 15 of their papers we have counts for
7 papers · 1 filter
Few-Shot Demonstrations Elicit the Use of In-Context World Representations in LLMs
Kohsei Matsutani, Gouki Minegishi, Core Francisco Park +3
Large language models (LLMs), when acting as agents, are expected to take observed data in context, infer the latent state space underlying the world, and leverage it for downstrea…
Shared Circuits for Shared Grammar: Tracing Subject-Verb Agreement Across Languages
Isabella Gidi, Antonio Almudévar, Core Francisco Park +2
Multilingual large language models often generalize across languages, and prior work suggests that their internal mechanisms can overlap cross-lingually. It remains unclear, howeve…
CreativityNeuro: Steering Language Model Weights to Improve Divergent Thinking and Reduce Mode Collapse
Samuel Schapiro, Core Francisco Park, Felix Sosa +1
Divergent thinking is a crucial aspect of creativity, yet large language models (LLMs) tend to consistently generate similar responses to open-ended questions, in what has been ter…
Viral Proteins Reveal Geometry of Protein Language Models
Arthur Bigot, Harmon Bhasin, Core Francisco Park +2
Protein language models are trained on highly imbalanced datasets, raising the question of how they represent underrepresented biological sequences. Using viral proteins as a case…
A Systematic Study of Behavioral Cloning for Scientific Data Annotation
Ishaan Singh Chandok, Core Francisco Park
Scientific data annotation, such as tracking animals in video or proofreading neural reconstructions, remains bottlenecked by the "last mile" problem: even with strong automation,…
Mechanisms of Misgeneralization in Physical Sequence Modeling
Kento Nishi, Raphael Tang, Karun Kumar +2
Generative sequence models are often trained to plan motion in physical domains, from robotics to mechanical simulations. When constructing a dataset to train such a model, enginee…
Convergent World Representations and Divergent Tasks
Core Francisco Park
While neural representations are central to modern deep learning, the conditions governing their geometry and their roles in downstream adaptability remain poorly understood. We de…