6 accepted papers
Mechanistic interpretability research seeks to reverse-engineer large language models (LLMs) by uncovering the internal representations of concepts within their activations. Sparse Autoencoders (SAEs) have emerged as a valuable tool for disentangling polysemantic neurons into more monosemantic, inte…
Major search engine providers are rapidly incorporating Large Language Model (LLM)-generated content in response to user queries. These *conversational search engines* operate by loading retrieved website text into the LLM context for summarization and interpretation. Recent research demonstrates th…
Machine learning often aims to produce latent embeddings of inputs which lie in a larger, abstract mathematical space. For example, in the field of 3D modeling, subsets of Euclidean space can be embedded as vectors using implicit neural representations. Such subsets also have a natural algebraic str…
Real-world adversarial attacks on machine learning models often feature an asymmetric structure wherein adversaries only attempt to induce false negatives (e.g., classify a spam email as not spam). We formalize the asymmetric robustness certification problem and correspondingly present the feature-c…
Network data can be conveniently modeled as a graph signal, where data values are assigned to the nodes of a graph describing the underlying network topology. Successful learning from network data requires methods that effectively exploit this graph structure. Graph neural networks (GNNs) provide on…
Common methods for learning robot dynamics assume motion is continuous, causing unrealistic model predictions for systems undergoing discontinuous impact and stiction behavior. In this work, we resolve this conflict with a smooth, implicit encoding of the structure inherent to contact-induced discon