65 citations · 69 across the 5 of their papers we have counts for
4 papers · 1 filter
Tracing the Representation Geometry of Language Models from Pretraining to Post-training
Melody Zixuan Li, Kumar Krishna Agrawal, Arna Ghosh +4
Standard training metrics like loss fail to explain the emergence of complex capabilities in large language models. We take a spectral approach to investigate the geometry of learn…
Off-Policy Policy Gradient Algorithms by Constraining the State Distribution Shift
Riashat Islam, Komal K. Teru, Deepak Sharma +1
Off-policy deep reinforcement learning (RL) algorithms are incapable of learning solely from batch offline data without online interactions with the environment, due to the phenome…
Towards Reducing Bias in Gender Classification
Komal K. Teru, Aishik Chakraborty
Societal bias towards certain communities is a big problem that affects a lot of machine learning systems. This work aims at addressing the racial bias present in many modern gende…
Inductive Relation Prediction by Subgraph Reasoning
Komal K. Teru, Etienne Denis, William L. Hamilton
The dominant paradigm for relation prediction in knowledge graphs involves learning and operating on latent representations (i.e., embeddings) of entities and relations. However, t…