6 papers
Fairness Aware Reward Optimization
Ching Lam Choi, Vighnesh Subramaniam, Phillip Isola +2
Demographic skews in human preference data propagate systematic unfairness through reward models into aligned LLMs. We introduce Fairness Aware Reward Optimization (Faro), an in-pr…
Network of Theseus (like the ship)
Vighnesh Subramaniam, Colin Conwell, Boris Katz +2
A standard assumption in deep learning is that the inductive bias introduced by a neural network architecture must persist from training through inference. The architecture you tra…
Training the Untrainable: Introducing Inductive Bias via Representational Alignment
Vighnesh Subramaniam, David Mayo, Colin Conwell +4
We demonstrate that architectures which traditionally are considered to be ill-suited for a task can be trained using inductive biases from another architecture. We call a network…
Population Transformer: Learning Population-level Representations of Neural Activity
Geeling Chau, Christopher Wang, Sabera Talukder +5
We present a self-supervised framework that learns population-level codes for arbitrary ensembles of neural recordings at scale. We address key challenges in scaling models with ne…
Multiagent Finetuning: Self Improvement with Diverse Reasoning Chains
Vighnesh Subramaniam, Yilun Du, Joshua B. Tenenbaum +3
Large language models (LLMs) have achieved remarkable performance in recent years but are fundamentally limited by the underlying training data. To improve models beyond the traini…
Brain Treebank: Large-scale intracranial recordings from naturalistic language stimuli
Christopher Wang, Adam Uri Yaari, Aaditya K Singh +10
We present the Brain Treebank, a large-scale dataset of electrophysiological neural responses, recorded from intracranial probes while 10 subjects watched one or more Hollywood mov…